diff options
| -rw-r--r-- | tools/testing/selftests/memfd/.gitignore | 2 | ||||
| -rw-r--r-- | tools/testing/selftests/memfd/Makefile | 14 | ||||
| -rw-r--r-- | tools/testing/selftests/memfd/fuse_mnt.c | 110 | ||||
| -rw-r--r-- | tools/testing/selftests/memfd/fuse_test.c | 311 | ||||
| -rw-r--r-- | tools/testing/selftests/memfd/run_fuse_test.sh | 14 |
5 files changed, 450 insertions, 1 deletions
diff --git a/tools/testing/selftests/memfd/.gitignore b/tools/testing/selftests/memfd/.gitignore index bcc8ee20c710..afe87c40ac80 100644 --- a/tools/testing/selftests/memfd/.gitignore +++ b/tools/testing/selftests/memfd/.gitignore @@ -1,2 +1,4 @@ +fuse_mnt +fuse_test memfd_test memfd-test-file diff --git a/tools/testing/selftests/memfd/Makefile b/tools/testing/selftests/memfd/Makefile index 36653b903140..6816c491c5ff 100644 --- a/tools/testing/selftests/memfd/Makefile +++ b/tools/testing/selftests/memfd/Makefile @@ -7,6 +7,7 @@ ifeq ($(ARCH),x86_64) ARCH := X86 endif +CFLAGS += -D_FILE_OFFSET_BITS=64 CFLAGS += -I../../../../arch/x86/include/generated/uapi/ CFLAGS += -I../../../../arch/x86/include/uapi/ CFLAGS += -I../../../../include/uapi/ @@ -25,5 +26,16 @@ ifeq ($(ARCH),X86) endif @./memfd_test || echo "memfd_test: [FAIL]" +build_fuse: +ifeq ($(ARCH),X86) + gcc $(CFLAGS) fuse_mnt.c `pkg-config fuse --cflags --libs` -o fuse_mnt + gcc $(CFLAGS) fuse_test.c -o fuse_test +else + echo "Not an x86 target, can't build memfd selftest" +endif + +run_fuse: build_fuse + @./run_fuse_test.sh || echo "fuse_test: [FAIL]" + clean: - $(RM) memfd_test + $(RM) memfd_test fuse_test diff --git a/tools/testing/selftests/memfd/fuse_mnt.c b/tools/testing/selftests/memfd/fuse_mnt.c new file mode 100644 index 000000000000..feacf1280fcd --- /dev/null +++ b/tools/testing/selftests/memfd/fuse_mnt.c @@ -0,0 +1,110 @@ +/* + * memfd test file-system + * This file uses FUSE to create a dummy file-system with only one file /memfd. + * This file is read-only and takes 1s per read. + * + * This file-system is used by the memfd test-cases to force the kernel to pin + * pages during reads(). Due to the 1s delay of this file-system, this is a + * nice way to test race-conditions against get_user_pages() in the kernel. + * + * We use direct_io==1 to force the kernel to use direct-IO for this + * file-system. + */ + +#define FUSE_USE_VERSION 26 + +#include <fuse.h> +#include <stdio.h> +#include <string.h> +#include <errno.h> +#include <fcntl.h> +#include <unistd.h> + +static const char memfd_content[] = "memfd-example-content"; +static const char memfd_path[] = "/memfd"; + +static int memfd_getattr(const char *path, struct stat *st) +{ + memset(st, 0, sizeof(*st)); + + if (!strcmp(path, "/")) { + st->st_mode = S_IFDIR | 0755; + st->st_nlink = 2; + } else if (!strcmp(path, memfd_path)) { + st->st_mode = S_IFREG | 0444; + st->st_nlink = 1; + st->st_size = strlen(memfd_content); + } else { + return -ENOENT; + } + + return 0; +} + +static int memfd_readdir(const char *path, + void *buf, + fuse_fill_dir_t filler, + off_t offset, + struct fuse_file_info *fi) +{ + if (strcmp(path, "/")) + return -ENOENT; + + filler(buf, ".", NULL, 0); + filler(buf, "..", NULL, 0); + filler(buf, memfd_path + 1, NULL, 0); + + return 0; +} + +static int memfd_open(const char *path, struct fuse_file_info *fi) +{ + if (strcmp(path, memfd_path)) + return -ENOENT; + + if ((fi->flags & 3) != O_RDONLY) + return -EACCES; + + /* force direct-IO */ + fi->direct_io = 1; + + return 0; +} + +static int memfd_read(const char *path, + char *buf, + size_t size, + off_t offset, + struct fuse_file_info *fi) +{ + size_t len; + + if (strcmp(path, memfd_path) != 0) + return -ENOENT; + + sleep(1); + + len = strlen(memfd_content); + if (offset < len) { + if (offset + size > len) + size = len - offset; + + memcpy(buf, memfd_content + offset, size); + } else { + size = 0; + } + + return size; +} + +static struct fuse_operations memfd_ops = { + .getattr = memfd_getattr, + .readdir = memfd_readdir, + .open = memfd_open, + .read = memfd_read, +}; + +int main(int argc, char *argv[]) +{ + return fuse_main(argc, argv, &memfd_ops, NULL); +} diff --git a/tools/testing/selftests/memfd/fuse_test.c b/tools/testing/selftests/memfd/fuse_test.c new file mode 100644 index 000000000000..67908b18f035 --- /dev/null +++ b/tools/testing/selftests/memfd/fuse_test.c @@ -0,0 +1,311 @@ +/* + * memfd GUP test-case + * This tests memfd interactions with get_user_pages(). We require the + * fuse_mnt.c program to provide a fake direct-IO FUSE mount-point for us. This + * file-system delays _all_ reads by 1s and forces direct-IO. This means, any + * read() on files in that file-system will pin the receive-buffer pages for at + * least 1s via get_user_pages(). + * + * We use this trick to race ADD_SEALS against a write on a memfd object. The + * ADD_SEALS must fail if the memfd pages are still pinned. Note that we use + * the read() syscall with our memory-mapped memfd object as receive buffer to + * force the kernel to write into our memfd object. + */ + +#define _GNU_SOURCE +#define __EXPORTED_HEADERS__ + +#include <errno.h> +#include <inttypes.h> +#include <limits.h> +#include <linux/falloc.h> +#include <linux/fcntl.h> +#include <linux/memfd.h> +#include <sched.h> +#include <stdio.h> +#include <stdlib.h> +#include <signal.h> +#include <string.h> +#include <sys/mman.h> +#include <sys/stat.h> +#include <sys/syscall.h> +#include <sys/wait.h> +#include <unistd.h> + +#define MFD_DEF_SIZE 8192 +#define STACK_SIZE 65535 + +static int sys_memfd_create(const char *name, + unsigned int flags) +{ + return syscall(__NR_memfd_create, name, flags); +} + +static int mfd_assert_new(const char *name, loff_t sz, unsigned int flags) +{ + int r, fd; + + fd = sys_memfd_create(name, flags); + if (fd < 0) { + printf("memfd_create(\"%s\", %u) failed: %m\n", + name, flags); + abort(); + } + + r = ftruncate(fd, sz); + if (r < 0) { + printf("ftruncate(%llu) failed: %m\n", (unsigned long long)sz); + abort(); + } + + return fd; +} + +static __u64 mfd_assert_get_seals(int fd) +{ + long r; + + r = fcntl(fd, F_GET_SEALS); + if (r < 0) { + printf("GET_SEALS(%d) failed: %m\n", fd); + abort(); + } + + return r; +} + +static void mfd_assert_has_seals(int fd, __u64 seals) +{ + __u64 s; + + s = mfd_assert_get_seals(fd); + if (s != seals) { + printf("%llu != %llu = GET_SEALS(%d)\n", + (unsigned long long)seals, (unsigned long long)s, fd); + abort(); + } +} + +static void mfd_assert_add_seals(int fd, __u64 seals) +{ + long r; + __u64 s; + + s = mfd_assert_get_seals(fd); + r = fcntl(fd, F_ADD_SEALS, seals); + if (r < 0) { + printf("ADD_SEALS(%d, %llu -> %llu) failed: %m\n", + fd, (unsigned long long)s, (unsigned long long)seals); + abort(); + } +} + +static int mfd_busy_add_seals(int fd, __u64 seals) +{ + long r; + __u64 s; + + r = fcntl(fd, F_GET_SEALS); + if (r < 0) + s = 0; + else + s = r; + + r = fcntl(fd, F_ADD_SEALS, seals); + if (r < 0 && errno != EBUSY) { + printf("ADD_SEALS(%d, %llu -> %llu) didn't fail as expected with EBUSY: %m\n", + fd, (unsigned long long)s, (unsigned long long)seals); + abort(); + } + + return r; +} + +static void *mfd_assert_mmap_shared(int fd) +{ + void *p; + + p = mmap(NULL, + MFD_DEF_SIZE, + PROT_READ | PROT_WRITE, + MAP_SHARED, + fd, + 0); + if (p == MAP_FAILED) { + printf("mmap() failed: %m\n"); + abort(); + } + + return p; +} + +static void *mfd_assert_mmap_private(int fd) +{ + void *p; + + p = mmap(NULL, + MFD_DEF_SIZE, + PROT_READ | PROT_WRITE, + MAP_PRIVATE, + fd, + 0); + if (p == MAP_FAILED) { + printf("mmap() failed: %m\n"); + abort(); + } + + return p; +} + +static int global_mfd = -1; +static void *global_p = NULL; + +static int sealing_thread_fn(void *arg) +{ + int sig, r; + + /* + * This thread first waits 200ms so any pending operation in the parent + * is correctly started. After that, it tries to seal @global_mfd as + * SEAL_WRITE. This _must_ fail as the parent thread has a read() into + * that memory mapped object still ongoing. + * We then wait one more second and try sealing again. This time it + * must succeed as there shouldn't be anyone else pinning the pages. + */ + + /* wait 200ms for FUSE-request to be active */ + usleep(200000); + + /* unmount mapping before sealing to avoid i_mmap_writable failures */ + munmap(global_p, MFD_DEF_SIZE); + + /* Try sealing the global file; expect EBUSY or success. Current + * kernels will never succeed, but in the future, kernels might + * implement page-replacements or other fancy ways to avoid racing + * writes. */ + r = mfd_busy_add_seals(global_mfd, F_SEAL_WRITE); + if (r >= 0) { + printf("HURRAY! This kernel fixed GUP races!\n"); + } else { + /* wait 1s more so the FUSE-request is done */ + sleep(1); + + /* try sealing the global file again */ + mfd_assert_add_seals(global_mfd, F_SEAL_WRITE); + } + + return 0; +} + +static pid_t spawn_sealing_thread(void) +{ + uint8_t *stack; + pid_t pid; + + stack = malloc(STACK_SIZE); + if (!stack) { + printf("malloc(STACK_SIZE) failed: %m\n"); + abort(); + } + + pid = clone(sealing_thread_fn, + stack + STACK_SIZE, + SIGCHLD | CLONE_FILES | CLONE_FS | CLONE_VM, + NULL); + if (pid < 0) { + printf("clone() failed: %m\n"); + abort(); + } + + return pid; +} + +static void join_sealing_thread(pid_t pid) +{ + waitpid(pid, NULL, 0); +} + +int main(int argc, char **argv) +{ + static const char zero[MFD_DEF_SIZE]; + int fd, mfd, r; + void *p; + int was_sealed; + pid_t pid; + + if (argc < 2) { + printf("error: please pass path to file in fuse_mnt mount-point\n"); + abort(); + } + + /* open FUSE memfd file for GUP testing */ + printf("opening: %s\n", argv[1]); + fd = open(argv[1], O_RDONLY | O_CLOEXEC); + if (fd < 0) { + printf("cannot open(\"%s\"): %m\n", argv[1]); + abort(); + } + + /* create new memfd-object */ + mfd = mfd_assert_new("kern_memfd_fuse", + MFD_DEF_SIZE, + MFD_CLOEXEC | MFD_ALLOW_SEALING); + + /* mmap memfd-object for writing */ + p = mfd_assert_mmap_shared(mfd); + + /* pass mfd+mapping to a separate sealing-thread which tries to seal + * the memfd objects with SEAL_WRITE while we write into it */ + global_mfd = mfd; + global_p = p; + pid = spawn_sealing_thread(); + + /* Use read() on the FUSE file to read into our memory-mapped memfd + * object. This races the other thread which tries to seal the + * memfd-object. + * If @fd is on the memfd-fake-FUSE-FS, the read() is delayed by 1s. + * This guarantees that the receive-buffer is pinned for 1s until the + * data is written into it. The racing ADD_SEALS should thus fail as + * the pages are still pinned. */ + r = read(fd, p, MFD_DEF_SIZE); + if (r < 0) { + printf("read() failed: %m\n"); + abort(); + } else if (!r) { + printf("unexpected EOF on read()\n"); + abort(); + } + + was_sealed = mfd_assert_get_seals(mfd) & F_SEAL_WRITE; + + /* Wait for sealing-thread to finish and verify that it + * successfully sealed the file after the second try. */ + join_sealing_thread(pid); + mfd_assert_has_seals(mfd, F_SEAL_WRITE); + + /* *IF* the memfd-object was sealed at the time our read() returned, + * then the kernel did a page-replacement or canceled the read() (or + * whatever magic it did..). In that case, the memfd object is still + * all zero. + * In case the memfd-object was *not* sealed, the read() was successfull + * and the memfd object must *not* be all zero. + * Note that in real scenarios, there might be a mixture of both, but + * in this test-cases, we have explicit 200ms delays which should be + * enough to avoid any in-flight writes. */ + + p = mfd_assert_mmap_private(mfd); + if (was_sealed && memcmp(p, zero, MFD_DEF_SIZE)) { + printf("memfd sealed during read() but data not discarded\n"); + abort(); + } else if (!was_sealed && !memcmp(p, zero, MFD_DEF_SIZE)) { + printf("memfd sealed after read() but data discarded\n"); + abort(); + } + + close(mfd); + close(fd); + + printf("fuse: DONE\n"); + + return 0; +} diff --git a/tools/testing/selftests/memfd/run_fuse_test.sh b/tools/testing/selftests/memfd/run_fuse_test.sh new file mode 100644 index 000000000000..69b930e1e041 --- /dev/null +++ b/tools/testing/selftests/memfd/run_fuse_test.sh @@ -0,0 +1,14 @@ +#!/bin/sh + +if test -d "./mnt" ; then + fusermount -u ./mnt + rmdir ./mnt +fi + +set -e + +mkdir mnt +./fuse_mnt ./mnt +./fuse_test ./mnt/memfd +fusermount -u ./mnt +rmdir ./mnt |
