From 01408c4939479ec46c15aa7ef6e2406be50eeeca Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Sun, 25 Jun 2006 05:47:58 -0700 Subject: [PATCH] [PATCH] Prepare for __copy_from_user_inatomic to not zero missed bytes The problem is that when we write to a file, the copy from userspace to pagecache is first done with preemption disabled, so if the source address is not immediately available the copy fails *and* *zeros* *the* *destination*. This is a problem because a concurrent read (which admittedly is an odd thing to do) might see zeros rather that was there before the write, or what was there after, or some mixture of the two (any of these being a reasonable thing to see). If the copy did fail, it will immediately be retried with preemption re-enabled so any transient problem with accessing the source won't cause an error. The first copying does not need to zero any uncopied bytes, and doing so causes the problem. It uses copy_from_user_atomic rather than copy_from_user so the simple expedient is to change copy_from_user_atomic to *not* zero out bytes on failure. The first of these two patches prepares for the change by fixing two places which assume copy_from_user_atomic does zero the tail. The two usages are very similar pieces of code which copy from a userspace iovec into one or more page-cache pages. These are changed to remove the assumption. The second patch changes __copy_from_user_inatomic* to not zero the tail. Once these are accepted, I will look at similar patches of other architectures where this is important (ppc, mips and sparc being the ones I can find). This patch: There is a problem with __copy_from_user_inatomic zeroing the tail of the buffer in the case of an error. As it is called in atomic context, the error may be transient, so it results in zeros being written where maybe they shouldn't be. In the usage in filemap, this opens a window for a well timed read to see data (zeros) which is not consistent with any ordering of reads and writes. Most cases where __copy_from_user_inatomic is called, a failure results in __copy_from_user being called immediately. As long as the latter zeros the tail, the former doesn't need to. However in *copy_from_user_iovec implementations (in both filemap and ntfs/file), it is assumed that copy_from_user_inatomic will zero the tail. This patch removes that assumption, so that after this patch it will be safe for copy_from_user_inatomic to not zero the tail. This patch also adds some commentary to filemap.h and asm-i386/uaccess.h. After this patch, all architectures that might disable preempt when kmap_atomic is called need to have their __copy_from_user_inatomic* "fixed". This includes - powerpc - i386 - mips - sparc Signed-off-by: Neil Brown Cc: David Howells Cc: Anton Altaparmakov Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Cc: Ralf Baechle Cc: William Lee Irwin III Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/ntfs/file.c | 26 ++++++++++++++------------ include/asm-i386/uaccess.h | 6 ++++++ mm/filemap.c | 8 ++------ mm/filemap.h | 26 ++++++++++++++++++-------- 4 files changed, 40 insertions(+), 26 deletions(-) diff --git a/fs/ntfs/file.c b/fs/ntfs/file.c index 88292f9e4b..2e42c2dcae 100644 --- a/fs/ntfs/file.c +++ b/fs/ntfs/file.c @@ -1358,7 +1358,7 @@ err_out: goto out; } -static size_t __ntfs_copy_from_user_iovec(char *vaddr, +static size_t __ntfs_copy_from_user_iovec_inatomic(char *vaddr, const struct iovec *iov, size_t iov_ofs, size_t bytes) { size_t total = 0; @@ -1376,10 +1376,6 @@ static size_t __ntfs_copy_from_user_iovec(char *vaddr, bytes -= len; vaddr += len; if (unlikely(left)) { - /* - * Zero the rest of the target like __copy_from_user(). - */ - memset(vaddr, 0, bytes); total -= left; break; } @@ -1420,11 +1416,13 @@ static inline void ntfs_set_next_iovec(const struct iovec **iovp, * pages (out to offset + bytes), to emulate ntfs_copy_from_user()'s * single-segment behaviour. * - * We call the same helper (__ntfs_copy_from_user_iovec()) both when atomic and - * when not atomic. This is ok because __ntfs_copy_from_user_iovec() calls - * __copy_from_user_inatomic() and it is ok to call this when non-atomic. In - * fact, the only difference between __copy_from_user_inatomic() and - * __copy_from_user() is that the latter calls might_sleep(). And on many + * We call the same helper (__ntfs_copy_from_user_iovec_inatomic()) both + * when atomic and when not atomic. This is ok because + * __ntfs_copy_from_user_iovec_inatomic() calls __copy_from_user_inatomic() + * and it is ok to call this when non-atomic. + * Infact, the only difference between __copy_from_user_inatomic() and + * __copy_from_user() is that the latter calls might_sleep() and the former + * should not zero the tail of the buffer on error. And on many * architectures __copy_from_user_inatomic() is just defined to * __copy_from_user() so it makes no difference at all on those architectures. */ @@ -1441,14 +1439,18 @@ static inline size_t ntfs_copy_from_user_iovec(struct page **pages, if (len > bytes) len = bytes; kaddr = kmap_atomic(*pages, KM_USER0); - copied = __ntfs_copy_from_user_iovec(kaddr + ofs, + copied = __ntfs_copy_from_user_iovec_inatomic(kaddr + ofs, *iov, *iov_ofs, len); kunmap_atomic(kaddr, KM_USER0); if (unlikely(copied != len)) { /* Do it the slow way. */ kaddr = kmap(*pages); - copied = __ntfs_copy_from_user_iovec(kaddr + ofs, + copied = __ntfs_copy_from_user_iovec_inatomic(kaddr + ofs, *iov, *iov_ofs, len); + /* + * Zero the rest of the target like __copy_from_user(). + */ + memset(kaddr + ofs + copied, 0, len - copied); kunmap(*pages); if (unlikely(copied != len)) goto err_out; diff --git a/include/asm-i386/uaccess.h b/include/asm-i386/uaccess.h index 8462f8e0e6..d0d253277b 100644 --- a/include/asm-i386/uaccess.h +++ b/include/asm-i386/uaccess.h @@ -458,6 +458,12 @@ __copy_to_user(void __user *to, const void *from, unsigned long n) * * If some data could not be copied, this function will pad the copied * data to the requested size using zero bytes. + * + * An alternate version - __copy_from_user_inatomic() - may be called from + * atomic context and will fail rather than sleep. In this case the + * uncopied bytes will *NOT* be padded with zeros. See fs/filemap.h + * for explanation of why this is needed. + * FIXME this isn't implimented yet EMXIF */ static __always_inline unsigned long __copy_from_user_inatomic(void *to, const void __user *from, unsigned long n) diff --git a/mm/filemap.c b/mm/filemap.c index 807a463fd5..1ed4be2a76 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -1892,7 +1892,7 @@ int remove_suid(struct dentry *dentry) EXPORT_SYMBOL(remove_suid); size_t -__filemap_copy_from_user_iovec(char *vaddr, +__filemap_copy_from_user_iovec_inatomic(char *vaddr, const struct iovec *iov, size_t base, size_t bytes) { size_t copied = 0, left = 0; @@ -1908,12 +1908,8 @@ __filemap_copy_from_user_iovec(char *vaddr, vaddr += copy; iov++; - if (unlikely(left)) { - /* zero the rest of the target like __copy_from_user */ - if (bytes) - memset(vaddr, 0, bytes); + if (unlikely(left)) break; - } } return copied - left; } diff --git a/mm/filemap.h b/mm/filemap.h index 5683cde220..536979fb4b 100644 --- a/mm/filemap.h +++ b/mm/filemap.h @@ -16,15 +16,23 @@ #include size_t -__filemap_copy_from_user_iovec(char *vaddr, - const struct iovec *iov, - size_t base, - size_t bytes); +__filemap_copy_from_user_iovec_inatomic(char *vaddr, + const struct iovec *iov, + size_t base, + size_t bytes); /* * Copy as much as we can into the page and return the number of bytes which * were sucessfully copied. If a fault is encountered then clear the page * out to (offset+bytes) and return the number of bytes which were copied. + * + * NOTE: For this to work reliably we really want copy_from_user_inatomic_nocache + * to *NOT* zero any tail of the buffer that it failed to copy. If it does, + * and if the following non-atomic copy succeeds, then there is a small window + * where the target page contains neither the data before the write, nor the + * data after the write (it contains zero). A read at this time will see + * data that is inconsistent with any ordering of the read and the write. + * (This has been detected in practice). */ static inline size_t filemap_copy_from_user(struct page *page, unsigned long offset, @@ -60,13 +68,15 @@ filemap_copy_from_user_iovec(struct page *page, unsigned long offset, size_t copied; kaddr = kmap_atomic(page, KM_USER0); - copied = __filemap_copy_from_user_iovec(kaddr + offset, iov, - base, bytes); + copied = __filemap_copy_from_user_iovec_inatomic(kaddr + offset, iov, + base, bytes); kunmap_atomic(kaddr, KM_USER0); if (copied != bytes) { kaddr = kmap(page); - copied = __filemap_copy_from_user_iovec(kaddr + offset, iov, - base, bytes); + copied = __filemap_copy_from_user_iovec_inatomic(kaddr + offset, iov, + base, bytes); + if (bytes - copied) + memset(kaddr + offset + copied, 0, bytes - copied); kunmap(page); } return copied; -- 2.39.5