From f5a1a536fa14895ccff4e94e6a5af90901ce86aa Mon Sep 17 00:00:00 2001 From: Aleksa Sarai Date: Tue, 1 Oct 2019 11:10:52 +1000 Subject: lib: introduce copy_struct_from_user() helper A common pattern for syscall extensions is increasing the size of a struct passed from userspace, such that the zero-value of the new fields result in the old kernel behaviour (allowing for a mix of userspace and kernel vintages to operate on one another in most cases). While this interface exists for communication in both directions, only one interface is straightforward to have reasonable semantics for (userspace passing a struct to the kernel). For kernel returns to userspace, what the correct semantics are (whether there should be an error if userspace is unaware of a new extension) is very syscall-dependent and thus probably cannot be unified between syscalls (a good example of this problem is [1]). Previously there was no common lib/ function that implemented the necessary extension-checking semantics (and different syscalls implemented them slightly differently or incompletely[2]). Future patches replace common uses of this pattern to make use of copy_struct_from_user(). Some in-kernel selftests that insure that the handling of alignment and various byte patterns are all handled identically to memchr_inv() usage. [1]: commit 1251201c0d34 ("sched/core: Fix uclamp ABI bug, clean up and robustify sched_read_attr() ABI logic and code") [2]: For instance {sched_setattr,perf_event_open,clone3}(2) all do do similar checks to copy_struct_from_user() while rt_sigprocmask(2) always rejects differently-sized struct arguments. Suggested-by: Rasmus Villemoes Signed-off-by: Aleksa Sarai Reviewed-by: Kees Cook Reviewed-by: Christian Brauner Link: https://lore.kernel.org/r/20191001011055.19283-2-cyphar@cyphar.com Signed-off-by: Christian Brauner --- include/linux/uaccess.h | 70 +++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 70 insertions(+) (limited to 'include/linux/uaccess.h') diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h index 70bbdc38dc37..e47d0522a1f4 100644 --- a/include/linux/uaccess.h +++ b/include/linux/uaccess.h @@ -231,6 +231,76 @@ __copy_from_user_inatomic_nocache(void *to, const void __user *from, #endif /* ARCH_HAS_NOCACHE_UACCESS */ +extern __must_check int check_zeroed_user(const void __user *from, size_t size); + +/** + * copy_struct_from_user: copy a struct from userspace + * @dst: Destination address, in kernel space. This buffer must be @ksize + * bytes long. + * @ksize: Size of @dst struct. + * @src: Source address, in userspace. + * @usize: (Alleged) size of @src struct. + * + * Copies a struct from userspace to kernel space, in a way that guarantees + * backwards-compatibility for struct syscall arguments (as long as future + * struct extensions are made such that all new fields are *appended* to the + * old struct, and zeroed-out new fields have the same meaning as the old + * struct). + * + * @ksize is just sizeof(*dst), and @usize should've been passed by userspace. + * The recommended usage is something like the following: + * + * SYSCALL_DEFINE2(foobar, const struct foo __user *, uarg, size_t, usize) + * { + * int err; + * struct foo karg = {}; + * + * if (usize > PAGE_SIZE) + * return -E2BIG; + * if (usize < FOO_SIZE_VER0) + * return -EINVAL; + * + * err = copy_struct_from_user(&karg, sizeof(karg), uarg, usize); + * if (err) + * return err; + * + * // ... + * } + * + * There are three cases to consider: + * * If @usize == @ksize, then it's copied verbatim. + * * If @usize < @ksize, then the userspace has passed an old struct to a + * newer kernel. The rest of the trailing bytes in @dst (@ksize - @usize) + * are to be zero-filled. + * * If @usize > @ksize, then the userspace has passed a new struct to an + * older kernel. The trailing bytes unknown to the kernel (@usize - @ksize) + * are checked to ensure they are zeroed, otherwise -E2BIG is returned. + * + * Returns (in all cases, some data may have been copied): + * * -E2BIG: (@usize > @ksize) and there are non-zero trailing bytes in @src. + * * -EFAULT: access to userspace failed. + */ +static __always_inline __must_check int +copy_struct_from_user(void *dst, size_t ksize, const void __user *src, + size_t usize) +{ + size_t size = min(ksize, usize); + size_t rest = max(ksize, usize) - size; + + /* Deal with trailing bytes. */ + if (usize < ksize) { + memset(dst + size, 0, rest); + } else if (usize > ksize) { + int ret = check_zeroed_user(src + size, rest); + if (ret <= 0) + return ret ?: -E2BIG; + } + /* Copy the interoperable parts of the struct. */ + if (copy_from_user(dst, src, size)) + return -EFAULT; + return 0; +} + /* * probe_kernel_read(): safely attempt to read from a location * @dst: pointer to the buffer that shall take the data -- cgit v1.2.3 From c512c69187197fe08026cb5bbe7b9709f4f89b73 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Mon, 7 Oct 2019 12:56:48 -0700 Subject: uaccess: implement a proper unsafe_copy_to_user() and switch filldir over to it In commit 9f79b78ef744 ("Convert filldir[64]() from __put_user() to unsafe_put_user()") I made filldir() use unsafe_put_user(), which improves code generation on x86 enormously. But because we didn't have a "unsafe_copy_to_user()", the dirent name copy was also done by hand with unsafe_put_user() in a loop, and it turns out that a lot of other architectures didn't like that, because unlike x86, they have various alignment issues. Most non-x86 architectures trap and fix it up, and some (like xtensa) will just fail unaligned put_user() accesses unconditionally. Which makes that "copy using put_user() in a loop" not work for them at all. I could make that code do explicit alignment etc, but the architectures that don't like unaligned accesses also don't really use the fancy "user_access_begin/end()" model, so they might just use the regular old __copy_to_user() interface. So this commit takes that looping implementation, turns it into the x86 version of "unsafe_copy_to_user()", and makes other architectures implement the unsafe copy version as __copy_to_user() (the same way they do for the other unsafe_xyz() accessor functions). Note that it only does this for the copying _to_ user space, and we still don't have a unsafe version of copy_from_user(). That's partly because we have no current users of it, but also partly because the copy_from_user() case is slightly different and cannot efficiently be implemented in terms of a unsafe_get_user() loop (because gcc can't do asm goto with outputs). It would be trivial to do this using "rep movsb", which would work really nicely on newer x86 cores, but really badly on some older ones. Al Viro is looking at cleaning up all our user copy routines to make this all a non-issue, but for now we have this simple-but-stupid version for x86 that works fine for the dirent name copy case because those names are short strings and we simply don't need anything fancier. Fixes: 9f79b78ef744 ("Convert filldir[64]() from __put_user() to unsafe_put_user()") Reported-by: Guenter Roeck Reported-and-tested-by: Tony Luck Cc: Al Viro Cc: Max Filippov Signed-off-by: Linus Torvalds --- include/linux/uaccess.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include/linux/uaccess.h') diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h index e47d0522a1f4..d4ee6e942562 100644 --- a/include/linux/uaccess.h +++ b/include/linux/uaccess.h @@ -355,8 +355,10 @@ extern long strnlen_unsafe_user(const void __user *unsafe_addr, long count); #ifndef user_access_begin #define user_access_begin(ptr,len) access_ok(ptr, len) #define user_access_end() do { } while (0) -#define unsafe_get_user(x, ptr, err) do { if (unlikely(__get_user(x, ptr))) goto err; } while (0) -#define unsafe_put_user(x, ptr, err) do { if (unlikely(__put_user(x, ptr))) goto err; } while (0) +#define unsafe_op_wrap(op, err) do { if (unlikely(op)) goto err; } while (0) +#define unsafe_get_user(x,p,e) unsafe_op_wrap(__get_user(x,p),e) +#define unsafe_put_user(x,p,e) unsafe_op_wrap(__put_user(x,p),e) +#define unsafe_copy_to_user(d,s,l,e) unsafe_op_wrap(__copy_to_user(d,s,l),e) static inline unsigned long user_access_save(void) { return 0UL; } static inline void user_access_restore(unsigned long flags) { } #endif -- cgit v1.2.3