1 files changed, 71 insertions, 362 deletions

diff --git a/fs/read_write.c b/fs/read_write.c
index 016444255d3e..75f764b43418 100644
--- a/fs/read_write.c
+++ b/fs/read_write.c
@@ -419,27 +419,42 @@ static ssize_t new_sync_read(struct file *filp, char __user *buf, size_t len, lo
 	return ret;
 }
 
+static int warn_unsupported(struct file *file, const char *op)
+{
+	pr_warn_ratelimited(
+		"kernel %s not supported for file %pD4 (pid: %d comm: %.20s)\n",
+		op, file, current->pid, current->comm);
+	return -EINVAL;
+}
+
 ssize_t __kernel_read(struct file *file, void *buf, size_t count, loff_t *pos)
 {
-	mm_segment_t old_fs = get_fs();
+	struct kvec iov = {
+		.iov_base	= buf,
+		.iov_len	= min_t(size_t, count, MAX_RW_COUNT),
+	};
+	struct kiocb kiocb;
+	struct iov_iter iter;
 	ssize_t ret;
 
 	if (WARN_ON_ONCE(!(file->f_mode & FMODE_READ)))
 		return -EINVAL;
 	if (!(file->f_mode & FMODE_CAN_READ))
 		return -EINVAL;
+	/*
+	 * Also fail if ->read_iter and ->read are both wired up as that
+	 * implies very convoluted semantics.
+	 */
+	if (unlikely(!file->f_op->read_iter || file->f_op->read))
+		return warn_unsupported(file, "read");
 
-	if (count > MAX_RW_COUNT)
-		count =  MAX_RW_COUNT;
-	set_fs(KERNEL_DS);
-	if (file->f_op->read)
-		ret = file->f_op->read(file, (void __user *)buf, count, pos);
-	else if (file->f_op->read_iter)
-		ret = new_sync_read(file, (void __user *)buf, count, pos);
-	else
-		ret = -EINVAL;
-	set_fs(old_fs);
+	init_sync_kiocb(&kiocb, file);
+	kiocb.ki_pos = pos ? *pos : 0;
+	iov_iter_kvec(&iter, READ, &iov, 1, iov.iov_len);
+	ret = file->f_op->read_iter(&kiocb, &iter);
 	if (ret > 0) {
+		if (pos)
+			*pos = kiocb.ki_pos;
 		fsnotify_access(file);
 		add_rchar(current, ret);
 	}
@@ -510,28 +525,32 @@ static ssize_t new_sync_write(struct file *filp, const char __user *buf, size_t
 /* caller is responsible for file_start_write/file_end_write */
 ssize_t __kernel_write(struct file *file, const void *buf, size_t count, loff_t *pos)
 {
-	mm_segment_t old_fs;
-	const char __user *p;
+	struct kvec iov = {
+		.iov_base	= (void *)buf,
+		.iov_len	= min_t(size_t, count, MAX_RW_COUNT),
+	};
+	struct kiocb kiocb;
+	struct iov_iter iter;
 	ssize_t ret;
 
 	if (WARN_ON_ONCE(!(file->f_mode & FMODE_WRITE)))
 		return -EBADF;
 	if (!(file->f_mode & FMODE_CAN_WRITE))
 		return -EINVAL;
+	/*
+	 * Also fail if ->write_iter and ->write are both wired up as that
+	 * implies very convoluted semantics.
+	 */
+	if (unlikely(!file->f_op->write_iter || file->f_op->write))
+		return warn_unsupported(file, "write");
 
-	old_fs = get_fs();
-	set_fs(KERNEL_DS);
-	p = (__force const char __user *)buf;
-	if (count > MAX_RW_COUNT)
-		count =  MAX_RW_COUNT;
-	if (file->f_op->write)
-		ret = file->f_op->write(file, p, count, pos);
-	else if (file->f_op->write_iter)
-		ret = new_sync_write(file, p, count, pos);
-	else
-		ret = -EINVAL;
-	set_fs(old_fs);
+	init_sync_kiocb(&kiocb, file);
+	kiocb.ki_pos = pos ? *pos : 0;
+	iov_iter_kvec(&iter, WRITE, &iov, 1, iov.iov_len);
+	ret = file->f_op->write_iter(&kiocb, &iter);
 	if (ret > 0) {
+		if (pos)
+			*pos = kiocb.ki_pos;
 		fsnotify_modify(file);
 		add_wchar(current, ret);
 	}
@@ -760,185 +779,6 @@ static ssize_t do_loop_readv_writev(struct file *filp, struct iov_iter *iter,
 	return ret;
 }
 
-/**
- * rw_copy_check_uvector() - Copy an array of &struct iovec from userspace
- *     into the kernel and check that it is valid.
- *
- * @type: One of %CHECK_IOVEC_ONLY, %READ, or %WRITE.
- * @uvector: Pointer to the userspace array.
- * @nr_segs: Number of elements in userspace array.
- * @fast_segs: Number of elements in @fast_pointer.
- * @fast_pointer: Pointer to (usually small on-stack) kernel array.
- * @ret_pointer: (output parameter) Pointer to a variable that will point to
- *     either @fast_pointer, a newly allocated kernel array, or NULL,
- *     depending on which array was used.
- *
- * This function copies an array of &struct iovec of @nr_segs from
- * userspace into the kernel and checks that each element is valid (e.g.
- * it does not point to a kernel address or cause overflow by being too
- * large, etc.).
- *
- * As an optimization, the caller may provide a pointer to a small
- * on-stack array in @fast_pointer, typically %UIO_FASTIOV elements long
- * (the size of this array, or 0 if unused, should be given in @fast_segs).
- *
- * @ret_pointer will always point to the array that was used, so the
- * caller must take care not to call kfree() on it e.g. in case the
- * @fast_pointer array was used and it was allocated on the stack.
- *
- * Return: The total number of bytes covered by the iovec array on success
- *   or a negative error code on error.
- */
-ssize_t rw_copy_check_uvector(int type, const struct iovec __user * uvector,
-			      unsigned long nr_segs, unsigned long fast_segs,
-			      struct iovec *fast_pointer,
-			      struct iovec **ret_pointer)
-{
-	unsigned long seg;
-	ssize_t ret;
-	struct iovec *iov = fast_pointer;
-
-	/*
-	 * SuS says "The readv() function *may* fail if the iovcnt argument
-	 * was less than or equal to 0, or greater than {IOV_MAX}.  Linux has
-	 * traditionally returned zero for zero segments, so...
-	 */
-	if (nr_segs == 0) {
-		ret = 0;
-		goto out;
-	}
-
-	/*
-	 * First get the "struct iovec" from user memory and
-	 * verify all the pointers
-	 */
-	if (nr_segs > UIO_MAXIOV) {
-		ret = -EINVAL;
-		goto out;
-	}
-	if (nr_segs > fast_segs) {
-		iov = kmalloc_array(nr_segs, sizeof(struct iovec), GFP_KERNEL);
-		if (iov == NULL) {
-			ret = -ENOMEM;
-			goto out;
-		}
-	}
-	if (copy_from_user(iov, uvector, nr_segs*sizeof(*uvector))) {
-		ret = -EFAULT;
-		goto out;
-	}
-
-	/*
-	 * According to the Single Unix Specification we should return EINVAL
-	 * if an element length is < 0 when cast to ssize_t or if the
-	 * total length would overflow the ssize_t return value of the
-	 * system call.
-	 *
-	 * Linux caps all read/write calls to MAX_RW_COUNT, and avoids the
-	 * overflow case.
-	 */
-	ret = 0;
-	for (seg = 0; seg < nr_segs; seg++) {
-		void __user *buf = iov[seg].iov_base;
-		ssize_t len = (ssize_t)iov[seg].iov_len;
-
-		/* see if we we're about to use an invalid len or if
-		 * it's about to overflow ssize_t */
-		if (len < 0) {
-			ret = -EINVAL;
-			goto out;
-		}
-		if (type >= 0
-		    && unlikely(!access_ok(buf, len))) {
-			ret = -EFAULT;
-			goto out;
-		}
-		if (len > MAX_RW_COUNT - ret) {
-			len = MAX_RW_COUNT - ret;
-			iov[seg].iov_len = len;
-		}
-		ret += len;
-	}
-out:
-	*ret_pointer = iov;
-	return ret;
-}
-
-#ifdef CONFIG_COMPAT
-ssize_t compat_rw_copy_check_uvector(int type,
-		const struct compat_iovec __user *uvector, unsigned long nr_segs,
-		unsigned long fast_segs, struct iovec *fast_pointer,
-		struct iovec **ret_pointer)
-{
-	compat_ssize_t tot_len;
-	struct iovec *iov = *ret_pointer = fast_pointer;
-	ssize_t ret = 0;
-	int seg;
-
-	/*
-	 * SuS says "The readv() function *may* fail if the iovcnt argument
-	 * was less than or equal to 0, or greater than {IOV_MAX}.  Linux has
-	 * traditionally returned zero for zero segments, so...
-	 */
-	if (nr_segs == 0)
-		goto out;
-
-	ret = -EINVAL;
-	if (nr_segs > UIO_MAXIOV)
-		goto out;
-	if (nr_segs > fast_segs) {
-		ret = -ENOMEM;
-		iov = kmalloc_array(nr_segs, sizeof(struct iovec), GFP_KERNEL);
-		if (iov == NULL)
-			goto out;
-	}
-	*ret_pointer = iov;
-
-	ret = -EFAULT;
-	if (!access_ok(uvector, nr_segs*sizeof(*uvector)))
-		goto out;
-
-	/*
-	 * Single unix specification:
-	 * We should -EINVAL if an element length is not >= 0 and fitting an
-	 * ssize_t.
-	 *
-	 * In Linux, the total length is limited to MAX_RW_COUNT, there is
-	 * no overflow possibility.
-	 */
-	tot_len = 0;
-	ret = -EINVAL;
-	for (seg = 0; seg < nr_segs; seg++) {
-		compat_uptr_t buf;
-		compat_ssize_t len;
-
-		if (__get_user(len, &uvector->iov_len) ||
-		   __get_user(buf, &uvector->iov_base)) {
-			ret = -EFAULT;
-			goto out;
-		}
-		if (len < 0)	/* size_t not fitting in compat_ssize_t .. */
-			goto out;
-		if (type >= 0 &&
-		    !access_ok(compat_ptr(buf), len)) {
-			ret = -EFAULT;
-			goto out;
-		}
-		if (len > MAX_RW_COUNT - tot_len)
-			len = MAX_RW_COUNT - tot_len;
-		tot_len += len;
-		iov->iov_base = compat_ptr(buf);
-		iov->iov_len = (compat_size_t) len;
-		uvector++;
-		iov++;
-	}
-	ret = tot_len;
-
-out:
-	return ret;
-}
-#endif
-
 static ssize_t do_iter_read(struct file *file, struct iov_iter *iter,
 		loff_t *pos, rwf_t flags)
 {
@@ -1068,7 +908,7 @@ ssize_t vfs_iter_write(struct file *file, struct iov_iter *iter, loff_t *ppos,
 }
 EXPORT_SYMBOL(vfs_iter_write);
 
-ssize_t vfs_readv(struct file *file, const struct iovec __user *vec,
+static ssize_t vfs_readv(struct file *file, const struct iovec __user *vec,
 		  unsigned long vlen, loff_t *pos, rwf_t flags)
 {
 	struct iovec iovstack[UIO_FASTIOV];
@@ -1255,224 +1095,93 @@ SYSCALL_DEFINE6(pwritev2, unsigned long, fd, const struct iovec __user *, vec,
 	return do_pwritev(fd, vec, vlen, pos, flags);
 }
 
+/*
+ * Various compat syscalls.  Note that they all pretend to take a native
+ * iovec - import_iovec will properly treat those as compat_iovecs based on
+ * in_compat_syscall().
+ */
 #ifdef CONFIG_COMPAT
-static size_t compat_readv(struct file *file,
-			   const struct compat_iovec __user *vec,
-			   unsigned long vlen, loff_t *pos, rwf_t flags)
-{
-	struct iovec iovstack[UIO_FASTIOV];
-	struct iovec *iov = iovstack;
-	struct iov_iter iter;
-	ssize_t ret;
-
-	ret = compat_import_iovec(READ, vec, vlen, UIO_FASTIOV, &iov, &iter);
-	if (ret >= 0) {
-		ret = do_iter_read(file, &iter, pos, flags);
-		kfree(iov);
-	}
-	if (ret > 0)
-		add_rchar(current, ret);
-	inc_syscr(current);
-	return ret;
-}
-
-static size_t do_compat_readv(compat_ulong_t fd,
-				 const struct compat_iovec __user *vec,
-				 compat_ulong_t vlen, rwf_t flags)
-{
-	struct fd f = fdget_pos(fd);
-	ssize_t ret;
-	loff_t pos;
-
-	if (!f.file)
-		return -EBADF;
-	pos = f.file->f_pos;
-	ret = compat_readv(f.file, vec, vlen, &pos, flags);
-	if (ret >= 0)
-		f.file->f_pos = pos;
-	fdput_pos(f);
-	return ret;
-
-}
-
-COMPAT_SYSCALL_DEFINE3(readv, compat_ulong_t, fd,
-		const struct compat_iovec __user *,vec,
-		compat_ulong_t, vlen)
-{
-	return do_compat_readv(fd, vec, vlen, 0);
-}
-
-static long do_compat_preadv64(unsigned long fd,
-				  const struct compat_iovec __user *vec,
-				  unsigned long vlen, loff_t pos, rwf_t flags)
-{
-	struct fd f;
-	ssize_t ret;
-
-	if (pos < 0)
-		return -EINVAL;
-	f = fdget(fd);
-	if (!f.file)
-		return -EBADF;
-	ret = -ESPIPE;
-	if (f.file->f_mode & FMODE_PREAD)
-		ret = compat_readv(f.file, vec, vlen, &pos, flags);
-	fdput(f);
-	return ret;
-}
-
 #ifdef __ARCH_WANT_COMPAT_SYS_PREADV64
 COMPAT_SYSCALL_DEFINE4(preadv64, unsigned long, fd,
-		const struct compat_iovec __user *,vec,
+		const struct iovec __user *, vec,
 		unsigned long, vlen, loff_t, pos)
 {
-	return do_compat_preadv64(fd, vec, vlen, pos, 0);
+	return do_preadv(fd, vec, vlen, pos, 0);
 }
 #endif
 
 COMPAT_SYSCALL_DEFINE5(preadv, compat_ulong_t, fd,
-		const struct compat_iovec __user *,vec,
+		const struct iovec __user *, vec,
 		compat_ulong_t, vlen, u32, pos_low, u32, pos_high)
 {
 	loff_t pos = ((loff_t)pos_high << 32) | pos_low;
 
-	return do_compat_preadv64(fd, vec, vlen, pos, 0);
+	return do_preadv(fd, vec, vlen, pos, 0);
 }
 
 #ifdef __ARCH_WANT_COMPAT_SYS_PREADV64V2
 COMPAT_SYSCALL_DEFINE5(preadv64v2, unsigned long, fd,
-		const struct compat_iovec __user *,vec,
+		const struct iovec __user *, vec,
 		unsigned long, vlen, loff_t, pos, rwf_t, flags)
 {
 	if (pos == -1)
-		return do_compat_readv(fd, vec, vlen, flags);
-
-	return do_compat_preadv64(fd, vec, vlen, pos, flags);
+		return do_readv(fd, vec, vlen, flags);
+	return do_preadv(fd, vec, vlen, pos, flags);
 }
 #endif
 
 COMPAT_SYSCALL_DEFINE6(preadv2, compat_ulong_t, fd,
-		const struct compat_iovec __user *,vec,
+		const struct iovec __user *, vec,
 		compat_ulong_t, vlen, u32, pos_low, u32, pos_high,
 		rwf_t, flags)
 {
 	loff_t pos = ((loff_t)pos_high << 32) | pos_low;
 
 	if (pos == -1)
-		return do_compat_readv(fd, vec, vlen, flags);
-
-	return do_compat_preadv64(fd, vec, vlen, pos, flags);
-}
-
-static size_t compat_writev(struct file *file,
-			    const struct compat_iovec __user *vec,
-			    unsigned long vlen, loff_t *pos, rwf_t flags)
-{
-	struct iovec iovstack[UIO_FASTIOV];
-	struct iovec *iov = iovstack;
-	struct iov_iter iter;
-	ssize_t ret;
-
-	ret = compat_import_iovec(WRITE, vec, vlen, UIO_FASTIOV, &iov, &iter);
-	if (ret >= 0) {
-		file_start_write(file);
-		ret = do_iter_write(file, &iter, pos, flags);
-		file_end_write(file);
-		kfree(iov);
-	}
-	if (ret > 0)
-		add_wchar(current, ret);
-	inc_syscw(current);
-	return ret;
-}
-
-static size_t do_compat_writev(compat_ulong_t fd,
-				  const struct compat_iovec __user* vec,
-				  compat_ulong_t vlen, rwf_t flags)
-{
-	struct fd f = fdget_pos(fd);
-	ssize_t ret;
-	loff_t pos;
-
-	if (!f.file)
-		return -EBADF;
-	pos = f.file->f_pos;
-	ret = compat_writev(f.file, vec, vlen, &pos, flags);
-	if (ret >= 0)
-		f.file->f_pos = pos;
-	fdput_pos(f);
-	return ret;
-}
-
-COMPAT_SYSCALL_DEFINE3(writev, compat_ulong_t, fd,
-		const struct compat_iovec __user *, vec,
-		compat_ulong_t, vlen)
-{
-	return do_compat_writev(fd, vec, vlen, 0);
-}
-
-static long do_compat_pwritev64(unsigned long fd,
-				   const struct compat_iovec __user *vec,
-				   unsigned long vlen, loff_t pos, rwf_t flags)
-{
-	struct fd f;
-	ssize_t ret;
-
-	if (pos < 0)
-		return -EINVAL;
-	f = fdget(fd);
-	if (!f.file)
-		return -EBADF;
-	ret = -ESPIPE;
-	if (f.file->f_mode & FMODE_PWRITE)
-		ret = compat_writev(f.file, vec, vlen, &pos, flags);
-	fdput(f);
-	return ret;
+		return do_readv(fd, vec, vlen, flags);
+	return do_preadv(fd, vec, vlen, pos, flags);
 }
 
 #ifdef __ARCH_WANT_COMPAT_SYS_PWRITEV64
 COMPAT_SYSCALL_DEFINE4(pwritev64, unsigned long, fd,
-		const struct compat_iovec __user *,vec,
+		const struct iovec __user *, vec,
 		unsigned long, vlen, loff_t, pos)
 {
-	return do_compat_pwritev64(fd, vec, vlen, pos, 0);
+	return do_pwritev(fd, vec, vlen, pos, 0);
 }
 #endif
 
 COMPAT_SYSCALL_DEFINE5(pwritev, compat_ulong_t, fd,
-		const struct compat_iovec __user *,vec,
+		const struct iovec __user *,vec,
 		compat_ulong_t, vlen, u32, pos_low, u32, pos_high)
 {
 	loff_t pos = ((loff_t)pos_high << 32) | pos_low;
 
-	return do_compat_pwritev64(fd, vec, vlen, pos, 0);
+	return do_pwritev(fd, vec, vlen, pos, 0);
 }
 
 #ifdef __ARCH_WANT_COMPAT_SYS_PWRITEV64V2
 COMPAT_SYSCALL_DEFINE5(pwritev64v2, unsigned long, fd,
-		const struct compat_iovec __user *,vec,
+		const struct iovec __user *, vec,
 		unsigned long, vlen, loff_t, pos, rwf_t, flags)
 {
 	if (pos == -1)
-		return do_compat_writev(fd, vec, vlen, flags);
-
-	return do_compat_pwritev64(fd, vec, vlen, pos, flags);
+		return do_writev(fd, vec, vlen, flags);
+	return do_pwritev(fd, vec, vlen, pos, flags);
 }
 #endif
 
 COMPAT_SYSCALL_DEFINE6(pwritev2, compat_ulong_t, fd,
-		const struct compat_iovec __user *,vec,
+		const struct iovec __user *,vec,
 		compat_ulong_t, vlen, u32, pos_low, u32, pos_high, rwf_t, flags)
 {
 	loff_t pos = ((loff_t)pos_high << 32) | pos_low;
 
 	if (pos == -1)
-		return do_compat_writev(fd, vec, vlen, flags);
-
-	return do_compat_pwritev64(fd, vec, vlen, pos, flags);
+		return do_writev(fd, vec, vlen, flags);
+	return do_pwritev(fd, vec, vlen, pos, flags);
 }
-
-#endif
+#endif /* CONFIG_COMPAT */
 
 static ssize_t do_sendfile(int out_fd, int in_fd, loff_t *ppos,
 		  	   size_t count, loff_t max)