On Mon, Mar 21, 2022 at 04:48:44PM -0700, Ben Gardon wrote:
> Ensure that the userspace actor attempting to disable NX hugepages has
> permission to reboot the system. Since disabling NX hugepages would
> allow a guest to crash the system, it is similar to reboot permissions.
>
> This approach is the simplest permission gating, but passing a file
> descriptor opened for write for the module parameter would also work
> well and be more precise.
> The latter approach was suggested by Sean Christopherson.
>
> Suggested-by: Jim Mattson <jmattson@xxxxxxxxxx>
> Signed-off-by: Ben Gardon <bgardon@xxxxxxxxxx>
> ---
> arch/x86/kvm/x86.c | 18 ++++++-
> .../selftests/kvm/include/kvm_util_base.h | 2 +
> tools/testing/selftests/kvm/lib/kvm_util.c | 7 +++
> .../selftests/kvm/x86_64/nx_huge_pages_test.c | 49 ++++++++++++++-----
> .../kvm/x86_64/nx_huge_pages_test.sh | 2 +-
> 5 files changed, 65 insertions(+), 13 deletions(-)
>
> diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
> index 74351cbb9b5b..995f30667619 100644
> --- a/arch/x86/kvm/x86.c
> +++ b/arch/x86/kvm/x86.c
> @@ -4256,7 +4256,6 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
> case KVM_CAP_SYS_ATTRIBUTES:
> case KVM_CAP_VAPIC:
> case KVM_CAP_ENABLE_CAP:
> - case KVM_CAP_VM_DISABLE_NX_HUGE_PAGES:
> r = 1;
> break;
> case KVM_CAP_EXIT_HYPERCALL:
> @@ -4359,6 +4358,14 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
> case KVM_CAP_DISABLE_QUIRKS2:
> r = KVM_X86_VALID_QUIRKS;
> break;
> + case KVM_CAP_VM_DISABLE_NX_HUGE_PAGES:
> + /*
> + * Since the risk of disabling NX hugepages is a guest crashing
> + * the system, ensure the userspace process has permission to
> + * reboot the system.
> + */
> + r = capable(CAP_SYS_BOOT);
Duplicating this check and comment isn't ideal. I think it would be fine
to unconditionally return true here (KVM, after all, does support the
capability) and only check for CAP_SYS_BOOT when userspace attempts to
enable the capability.
> + break;
> default:
> break;
> }
> @@ -6050,6 +6057,15 @@ int kvm_vm_ioctl_enable_cap(struct kvm *kvm,
> mutex_unlock(&kvm->lock);
> break;
> case KVM_CAP_VM_DISABLE_NX_HUGE_PAGES:
> + /*
> + * Since the risk of disabling NX hugepages is a guest crashing
> + * the system, ensure the userspace process has permission to
> + * reboot the system.
> + */
> + if (!capable(CAP_SYS_BOOT)) {
> + r = -EPERM;
> + break;
> + }
> kvm->arch.disable_nx_huge_pages = true;
> kvm_update_nx_huge_pages(kvm);
> r = 0;
> diff --git a/tools/testing/selftests/kvm/include/kvm_util_base.h b/tools/testing/selftests/kvm/include/kvm_util_base.h
> index 72163ba2f878..4db8251c3ce5 100644
> --- a/tools/testing/selftests/kvm/include/kvm_util_base.h
> +++ b/tools/testing/selftests/kvm/include/kvm_util_base.h
Can you split out the selftests changes to a separate commit? I have a
feeling you meant to :).
> @@ -411,4 +411,6 @@ uint64_t vm_get_single_stat(struct kvm_vm *vm, const char *stat_name);
>
> uint32_t guest_get_vcpuid(void);
>
> +void vm_disable_nx_huge_pages(struct kvm_vm *vm);
> +
> #endif /* SELFTEST_KVM_UTIL_BASE_H */
> diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c
> index 9d72d1bb34fa..46a7fa08d3e0 100644
> --- a/tools/testing/selftests/kvm/lib/kvm_util.c
> +++ b/tools/testing/selftests/kvm/lib/kvm_util.c
> @@ -2765,3 +2765,10 @@ uint64_t vm_get_single_stat(struct kvm_vm *vm, const char *stat_name)
> return value;
> }
>
> +void vm_disable_nx_huge_pages(struct kvm_vm *vm)
> +{
> + struct kvm_enable_cap cap = { 0 };
> +
> + cap.cap = KVM_CAP_VM_DISABLE_NX_HUGE_PAGES;
> + vm_enable_cap(vm, &cap);
> +}
> diff --git a/tools/testing/selftests/kvm/x86_64/nx_huge_pages_test.c b/tools/testing/selftests/kvm/x86_64/nx_huge_pages_test.c
> index 2bcbe4efdc6a..5ce98f759bc8 100644
> --- a/tools/testing/selftests/kvm/x86_64/nx_huge_pages_test.c
> +++ b/tools/testing/selftests/kvm/x86_64/nx_huge_pages_test.c
Will you add a test to exercise the CAP_SYS_BOOT check? At minimum the
selftest should check if it has CAP_SYS_BOOT and act accordingly (e.g.
exiting with KSFT_SKIP).
> @@ -57,13 +57,40 @@ static void check_split_count(struct kvm_vm *vm, int expected_splits)
> expected_splits, actual_splits);
> }
>
> +static void help(void)
> +{
> + puts("");
> + printf("usage: nx_huge_pages_test.sh [-x]\n");
> + puts("");
> + printf(" -x: Allow executable huge pages on the VM.\n");
> + puts("");
> + exit(0);
> +}
> +
> int main(int argc, char **argv)
> {
> struct kvm_vm *vm;
> struct timespec ts;
> + bool disable_nx = false;
> + int opt;
> +
> + while ((opt = getopt(argc, argv, "x")) != -1) {
> + switch (opt) {
> + case 'x':
> + disable_nx = true;
> + break;
> + case 'h':
> + default:
> + help();
> + break;
> + }
> + }
>
> vm = vm_create(VM_MODE_DEFAULT, DEFAULT_GUEST_PHY_PAGES, O_RDWR);
>
> + if (disable_nx)
> + vm_disable_nx_huge_pages(vm);
> +
> vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS_HUGETLB,
> HPAGE_PADDR_START, HPAGE_SLOT,
> HPAGE_SLOT_NPAGES, 0);
> @@ -83,21 +110,21 @@ int main(int argc, char **argv)
> * at 2M.
> */
> run_guest_code(vm, guest_code0);
> - check_2m_page_count(vm, 2);
> - check_split_count(vm, 2);
> + check_2m_page_count(vm, disable_nx ? 4 : 2);
> + check_split_count(vm, disable_nx ? 0 : 2);
>
> /*
> * guest_code1 is in the same huge page as data1, so it will cause
> * that huge page to be remapped at 4k.
> */
> run_guest_code(vm, guest_code1);
> - check_2m_page_count(vm, 1);
> - check_split_count(vm, 3);
> + check_2m_page_count(vm, disable_nx ? 4 : 1);
> + check_split_count(vm, disable_nx ? 0 : 3);
>
> /* Run guest_code0 again to check that is has no effect. */
> run_guest_code(vm, guest_code0);
> - check_2m_page_count(vm, 1);
> - check_split_count(vm, 3);
> + check_2m_page_count(vm, disable_nx ? 4 : 1);
> + check_split_count(vm, disable_nx ? 0 : 3);
>
> /*
> * Give recovery thread time to run. The wrapper script sets
> @@ -110,7 +137,7 @@ int main(int argc, char **argv)
> /*
> * Now that the reclaimer has run, all the split pages should be gone.
> */
> - check_2m_page_count(vm, 1);
> + check_2m_page_count(vm, disable_nx ? 4 : 1);
> check_split_count(vm, 0);
>
> /*
> @@ -118,13 +145,13 @@ int main(int argc, char **argv)
> * again to check that pages are mapped at 2M again.
> */
> run_guest_code(vm, guest_code0);
> - check_2m_page_count(vm, 2);
> - check_split_count(vm, 2);
> + check_2m_page_count(vm, disable_nx ? 4 : 2);
> + check_split_count(vm, disable_nx ? 0 : 2);
>
> /* Pages are once again split from running guest_code1. */
> run_guest_code(vm, guest_code1);
> - check_2m_page_count(vm, 1);
> - check_split_count(vm, 3);
> + check_2m_page_count(vm, disable_nx ? 4 : 1);
> + check_split_count(vm, disable_nx ? 0 : 3);
>
> kvm_vm_free(vm);
>
> diff --git a/tools/testing/selftests/kvm/x86_64/nx_huge_pages_test.sh b/tools/testing/selftests/kvm/x86_64/nx_huge_pages_test.sh
> index 19fc95723fcb..29f999f48848 100755
> --- a/tools/testing/selftests/kvm/x86_64/nx_huge_pages_test.sh
> +++ b/tools/testing/selftests/kvm/x86_64/nx_huge_pages_test.sh
> @@ -14,7 +14,7 @@ echo 1 > /sys/module/kvm/parameters/nx_huge_pages_recovery_ratio
> echo 100 > /sys/module/kvm/parameters/nx_huge_pages_recovery_period_ms
> echo 200 > /sys/kernel/mm/hugepages/hugepages-2048kB/nr_hugepages
>
> -./nx_huge_pages_test
> +./nx_huge_pages_test "${@}"
> RET=$?
>
> echo $NX_HUGE_PAGES > /sys/module/kvm/parameters/nx_huge_pages
> --
> 2.35.1.894.gb6a874cedc-goog
>
