From: Mike Rapoport <rppt@kernel.org> To: Andrew Morton <akpm@linux-foundation.org> Cc: Alexander Viro <viro@zeniv.linux.org.uk>, Andy Lutomirski <luto@kernel.org>, Arnd Bergmann <arnd@arndb.de>, Borislav Petkov <bp@alien8.de>, Catalin Marinas <catalin.marinas@arm.com>, Christopher Lameter <cl@linux.com>, Dan Williams <dan.j.williams@intel.com>, Dave Hansen <dave.hansen@linux.intel.com>, David Hildenbrand <david@redhat.com>, Elena Reshetova <elena.reshetova@intel.com>, "H. Peter Anvin" <hpa@zytor.com>, Ingo Molnar <mingo@redhat.com>, James Bottomley <jejb@linux.ibm.com>, "Kirill A. Shutemov" <kirill@shutemov.name>, Matthew Wilcox <willy@infradead.org>, Mark Rutland <mark.rutland@arm.com>, Mike Rapoport <rppt@linux.ibm.com>, Mike Rapoport <rppt@kernel.org>, Michael Kerrisk <mtk.manpages@gmail.com>, Palmer Dabbelt <palmer@dabbelt.com>, Paul Walmsley <paul.walmsley@sifive.com>, Peter Zijlstra <peterz@infradead.org>, Rick Edgecombe <rick.p.edgecombe@intel.com>, Shuah Khan <shuah@kernel.org>, Thomas Gleixner <tglx@linutronix.de>, Tycho Andersen <tycho@tycho.ws>, Will Deacon <will@kernel.org>, linux-api@vger.kernel.org, linux-arch@vger.kernel.org, linux-arm-kernel@lists.infradead.org, linux-fsdevel@vger.kernel.org, linux-mm@kvack.org, linux-kernel@vger.kernel.org, linux-kselftest@vger.kernel.org, linux-nvdimm@lists.01.org, linux-riscv@lists.infradead.org, x86@kernel.org Subject: [PATCH v7 7/7] secretmem: test: add basic selftest for memfd_secret(2) Date: Mon, 26 Oct 2020 10:37:52 +0200 Message-ID: <20201026083752.13267-8-rppt@kernel.org> (raw) In-Reply-To: <20201026083752.13267-1-rppt@kernel.org> From: Mike Rapoport <rppt@linux.ibm.com> The test verifies that file descriptor created with memfd_secret does not allow read/write operations, that secret memory mappings respect RLIMIT_MEMLOCK and that remote accesses with process_vm_read() and ptrace() to the secret memory fail. Signed-off-by: Mike Rapoport <rppt@linux.ibm.com> --- tools/testing/selftests/vm/.gitignore | 1 + tools/testing/selftests/vm/Makefile | 3 +- tools/testing/selftests/vm/memfd_secret.c | 296 ++++++++++++++++++++++ tools/testing/selftests/vm/run_vmtests | 17 ++ 4 files changed, 316 insertions(+), 1 deletion(-) create mode 100644 tools/testing/selftests/vm/memfd_secret.c diff --git a/tools/testing/selftests/vm/.gitignore b/tools/testing/selftests/vm/.gitignore index 849e8226395a..8a951fed3c3f 100644 --- a/tools/testing/selftests/vm/.gitignore +++ b/tools/testing/selftests/vm/.gitignore @@ -20,3 +20,4 @@ va_128TBswitch map_fixed_noreplace write_to_hugetlbfs hmm-tests +memfd_secret diff --git a/tools/testing/selftests/vm/Makefile b/tools/testing/selftests/vm/Makefile index 30873b19d04b..0fc87d0b140a 100644 --- a/tools/testing/selftests/vm/Makefile +++ b/tools/testing/selftests/vm/Makefile @@ -38,6 +38,7 @@ TEST_GEN_FILES += thuge-gen TEST_GEN_FILES += transhuge-stress TEST_GEN_FILES += userfaultfd TEST_GEN_FILES += khugepaged +TEST_GEN_FILES += memfd_secret ifeq ($(ARCH),x86_64) CAN_BUILD_I386 := $(shell ./../x86/check_cc.sh $(CC) ../x86/trivial_32bit_program.c -m32) @@ -129,4 +130,4 @@ endif $(OUTPUT)/userfaultfd: LDLIBS += -lpthread -$(OUTPUT)/mlock-random-test: LDLIBS += -lcap +$(OUTPUT)/mlock-random-test $(OUTPUT)/memfd_secret: LDLIBS += -lcap diff --git a/tools/testing/selftests/vm/memfd_secret.c b/tools/testing/selftests/vm/memfd_secret.c new file mode 100644 index 000000000000..31be20732e85 --- /dev/null +++ b/tools/testing/selftests/vm/memfd_secret.c @@ -0,0 +1,296 @@ +#define _GNU_SOURCE +#include <sys/uio.h> +#include <sys/mman.h> +#include <sys/wait.h> +#include <sys/types.h> +#include <sys/ptrace.h> +#include <sys/syscall.h> +#include <sys/resource.h> +#include <sys/capability.h> + +#include <stdlib.h> +#include <string.h> +#include <unistd.h> +#include <errno.h> +#include <stdio.h> + +#include "../kselftest.h" + +#define fail(fmt, ...) ksft_test_result_fail(fmt, ##__VA_ARGS__) +#define pass(fmt, ...) ksft_test_result_pass(fmt, ##__VA_ARGS__) +#define skip(fmt, ...) ksft_test_result_skip(fmt, ##__VA_ARGS__) + +#ifdef __NR_memfd_secret + +#include <linux/secretmem.h> + +#define PATTERN 0x55 + +static const int prot = PROT_READ | PROT_WRITE; +static const int mode = MAP_SHARED; + +static unsigned long page_size; +static unsigned long mlock_limit_cur; +static unsigned long mlock_limit_max; + +static int memfd_secret(unsigned long flags) +{ + return syscall(__NR_memfd_secret, flags); +} + +static void test_file_apis(int fd) +{ + char buf[64]; + + if ((read(fd, buf, sizeof(buf)) >= 0) || + (write(fd, buf, sizeof(buf)) >= 0) || + (pread(fd, buf, sizeof(buf), 0) >= 0) || + (pwrite(fd, buf, sizeof(buf), 0) >= 0)) + fail("unexpected file IO\n"); + else + pass("file IO is blocked as expected\n"); +} + +static void test_mlock_limit(int fd) +{ + size_t len; + char *mem; + + len = mlock_limit_cur; + mem = mmap(NULL, len, prot, mode, fd, 0); + if (mem == MAP_FAILED) { + fail("unable to mmap secret memory\n"); + return; + } + munmap(mem, len); + + len = mlock_limit_max * 2; + mem = mmap(NULL, len, prot, mode, fd, 0); + if (mem != MAP_FAILED) { + fail("unexpected mlock limit violation\n"); + munmap(mem, len); + return; + } + + pass("mlock limit is respected\n"); +} + +static void try_process_vm_read(int fd, int pipefd[2]) +{ + struct iovec liov, riov; + char buf[64]; + char *mem; + + if (read(pipefd[0], &mem, sizeof(mem)) < 0) { + fail("pipe write: %s\n", strerror(errno)); + exit(KSFT_FAIL); + } + + liov.iov_len = riov.iov_len = sizeof(buf); + liov.iov_base = buf; + riov.iov_base = mem; + + if (process_vm_readv(getppid(), &liov, 1, &riov, 1, 0) < 0) { + if (errno == ENOSYS) + exit(KSFT_SKIP); + exit(KSFT_PASS); + } + + exit(KSFT_FAIL); +} + +static void try_ptrace(int fd, int pipefd[2]) +{ + pid_t ppid = getppid(); + int status; + char *mem; + long ret; + + if (read(pipefd[0], &mem, sizeof(mem)) < 0) { + perror("pipe write"); + exit(KSFT_FAIL); + } + + ret = ptrace(PTRACE_ATTACH, ppid, 0, 0); + if (ret) { + perror("ptrace_attach"); + exit(KSFT_FAIL); + } + + ret = waitpid(ppid, &status, WUNTRACED); + if ((ret != ppid) || !(WIFSTOPPED(status))) { + fprintf(stderr, "weird waitppid result %ld stat %x\n", + ret, status); + exit(KSFT_FAIL); + } + + /* this access should fail and the task should be killed */ + ret = ptrace(PTRACE_PEEKDATA, ppid, mem, 0); + if (ret < 0) { + perror("ptrace_peek"); + exit(KSFT_FAIL); + } + + /* we shouldn't survive PTRACE_PEEKDATA */ + exit(KSFT_FAIL); +} + +static void check_child_status(pid_t pid, const char *name) +{ + int status; + + waitpid(pid, &status, 0); + + if (WIFEXITED(status) && WEXITSTATUS(status) == KSFT_SKIP) { + skip("%s is not supported\n", name); + return; + } + + if ((WIFEXITED(status) && WEXITSTATUS(status) == KSFT_PASS) || + WIFSIGNALED(status)) { + pass("%s failed as expected\n", name); + return; + } + + fail("%s: unexpected memory access\n", name); +} + +static void test_remote_access(int fd, const char *name, + void (*func)(int fd, int pipefd[2])) +{ + int pipefd[2]; + pid_t pid; + char *mem; + + if (pipe(pipefd)) { + fail("pipe failed: %s\n", strerror(errno)); + return; + } + + pid = fork(); + if (pid < 0) { + fail("fork failed: %s\n", strerror(errno)); + return; + } + + if (pid == 0) { + func(fd, pipefd); + return; + } + + mem = mmap(NULL, page_size, prot, mode, fd, 0); + if (mem == MAP_FAILED) { + fail("Unable to mmap secret memory\n"); + return; + } + + ftruncate(fd, page_size); + memset(mem, PATTERN, page_size); + + if (write(pipefd[1], &mem, sizeof(mem)) < 0) { + fail("pipe write: %s\n", strerror(errno)); + return; + } + + check_child_status(pid, name); +} + +static void test_process_vm_read(int fd) +{ + test_remote_access(fd, "process_vm_read", try_process_vm_read); +} + +static void test_ptrace(int fd) +{ + test_remote_access(fd, "ptrace", try_ptrace); +} + +static int set_cap_limits(rlim_t max) +{ + struct rlimit new; + cap_t cap = cap_init(); + + new.rlim_cur = max; + new.rlim_max = max; + if (setrlimit(RLIMIT_MEMLOCK, &new)) { + perror("setrlimit() returns error"); + return -1; + } + + /* drop capabilities including CAP_IPC_LOCK */ + if (cap_set_proc(cap)) { + perror("cap_set_proc() returns error"); + return -2; + } + + return 0; +} + +static void prepare(void) +{ + struct rlimit rlim; + + page_size = sysconf(_SC_PAGE_SIZE); + if (!page_size) + ksft_exit_fail_msg("Failed to get page size %s\n", + strerror(errno)); + + if (getrlimit(RLIMIT_MEMLOCK, &rlim)) + ksft_exit_fail_msg("Unable to detect mlock limit: %s\n", + strerror(errno)); + + mlock_limit_cur = rlim.rlim_cur; + mlock_limit_max = rlim.rlim_max; + + printf("page_size: %ld, mlock.soft: %ld, mlock.hard: %ld\n", + page_size, mlock_limit_cur, mlock_limit_max); + + if (page_size > mlock_limit_cur) + mlock_limit_cur = page_size; + if (page_size > mlock_limit_max) + mlock_limit_max = page_size; + + if (set_cap_limits(mlock_limit_max)) + ksft_exit_fail_msg("Unable to set mlock limit: %s\n", + strerror(errno)); +} + +#define NUM_TESTS 4 + +int main(int argc, char *argv[]) +{ + int fd; + + prepare(); + + ksft_print_header(); + ksft_set_plan(NUM_TESTS); + + fd = memfd_secret(0); + if (fd < 0) { + if (errno == ENOSYS) + ksft_exit_skip("memfd_secret is not supported\n"); + else + ksft_exit_fail_msg("memfd_secret failed: %s\n", + strerror(errno)); + } + + test_mlock_limit(fd); + test_file_apis(fd); + test_process_vm_read(fd); + test_ptrace(fd); + + close(fd); + + ksft_exit(!ksft_get_fail_cnt()); +} + +#else /* __NR_memfd_secret */ + +int main(int argc, char *argv[]) +{ + printf("skip: skipping memfd_secret test (missing __NR_memfd_secret)\n"); + return KSFT_SKIP; +} + +#endif /* __NR_memfd_secret */ diff --git a/tools/testing/selftests/vm/run_vmtests b/tools/testing/selftests/vm/run_vmtests index a3f4f30f0a2e..bee7365f3cc2 100755 --- a/tools/testing/selftests/vm/run_vmtests +++ b/tools/testing/selftests/vm/run_vmtests @@ -323,4 +323,21 @@ else exitcode=1 fi +echo "running memfd_secret test" +echo "------------------------------------" +./memfd_secret +ret_val=$? + +if [ $ret_val -eq 0 ]; then + echo "[PASS]" +elif [ $ret_val -eq $ksft_skip ]; then + echo "[SKIP]" + exitcode=$ksft_skip +else + echo "[FAIL]" + exitcode=1 +fi + +exit $exitcode + exit $exitcode -- 2.28.0
prev parent reply index Thread overview: 12+ messages / expand[flat|nested] mbox.gz Atom feed top 2020-10-26 8:37 [PATCH v7 0/7] mm: introduce memfd_secret system call to create "secret" memory areas Mike Rapoport 2020-10-26 8:37 ` [PATCH v7 1/7] mm: add definition of PMD_PAGE_ORDER Mike Rapoport 2020-10-27 8:26 ` David Hildenbrand 2020-10-26 8:37 ` [PATCH v7 2/7] mmap: make mlock_future_check() global Mike Rapoport 2020-10-26 8:37 ` [PATCH v7 3/7] set_memory: allow set_direct_map_*_noflush() for multiple pages Mike Rapoport 2020-10-26 19:01 ` Edgecombe, Rick P 2020-10-27 8:12 ` David Hildenbrand 2020-10-27 9:48 ` Mike Rapoport 2020-10-26 8:37 ` [PATCH v7 4/7] mm: introduce memfd_secret system call to create "secret" memory areas Mike Rapoport 2020-10-26 8:37 ` [PATCH v7 5/7] arch, mm: wire up memfd_secret system call were relevant Mike Rapoport 2020-10-26 8:37 ` [PATCH v7 6/7] mm: secretmem: use PMD-size pages to amortize direct map fragmentation Mike Rapoport 2020-10-26 8:37 ` Mike Rapoport [this message]
Reply instructions: You may reply publicly to this message via plain-text email using any one of the following methods: * Save the following mbox file, import it into your mail client, and reply-to-all from there: mbox Avoid top-posting and favor interleaved quoting: https://en.wikipedia.org/wiki/Posting_style#Interleaved_style * Reply using the --to, --cc, and --in-reply-to switches of git-send-email(1): git send-email \ --in-reply-to=20201026083752.13267-8-rppt@kernel.org \ --to=rppt@kernel.org \ --cc=akpm@linux-foundation.org \ --cc=arnd@arndb.de \ --cc=bp@alien8.de \ --cc=catalin.marinas@arm.com \ --cc=cl@linux.com \ --cc=dan.j.williams@intel.com \ --cc=dave.hansen@linux.intel.com \ --cc=david@redhat.com \ --cc=elena.reshetova@intel.com \ --cc=hpa@zytor.com \ --cc=jejb@linux.ibm.com \ --cc=kirill@shutemov.name \ --cc=linux-api@vger.kernel.org \ --cc=linux-arch@vger.kernel.org \ --cc=linux-arm-kernel@lists.infradead.org \ --cc=linux-fsdevel@vger.kernel.org \ --cc=linux-kernel@vger.kernel.org \ --cc=linux-kselftest@vger.kernel.org \ --cc=linux-mm@kvack.org \ --cc=linux-nvdimm@lists.01.org \ --cc=linux-riscv@lists.infradead.org \ --cc=luto@kernel.org \ --cc=mark.rutland@arm.com \ --cc=mingo@redhat.com \ --cc=mtk.manpages@gmail.com \ --cc=palmer@dabbelt.com \ --cc=paul.walmsley@sifive.com \ --cc=peterz@infradead.org \ --cc=rick.p.edgecombe@intel.com \ --cc=rppt@linux.ibm.com \ --cc=shuah@kernel.org \ --cc=tglx@linutronix.de \ --cc=tycho@tycho.ws \ --cc=viro@zeniv.linux.org.uk \ --cc=will@kernel.org \ --cc=willy@infradead.org \ --cc=x86@kernel.org \ /path/to/YOUR_REPLY https://kernel.org/pub/software/scm/git/docs/git-send-email.html * If your mail client supports setting the In-Reply-To header via mailto: links, try the mailto: link
Linux-Fsdevel Archive on lore.kernel.org Archives are clonable: git clone --mirror https://lore.kernel.org/linux-fsdevel/0 linux-fsdevel/git/0.git # If you have public-inbox 1.1+ installed, you may # initialize and index your mirror using the following commands: public-inbox-init -V2 linux-fsdevel linux-fsdevel/ https://lore.kernel.org/linux-fsdevel \ linux-fsdevel@vger.kernel.org public-inbox-index linux-fsdevel Example config snippet for mirrors Newsgroup available over NNTP: nntp://nntp.lore.kernel.org/org.kernel.vger.linux-fsdevel AGPL code for this site: git clone https://public-inbox.org/public-inbox.git