Merge branch 'work.iov_iter' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs

Pull compat iovec cleanups from Al Viro:
 "Christoph's series around import_iovec() and compat variant thereof"

* 'work.iov_iter' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs:
  security/keys: remove compat_keyctl_instantiate_key_iov
  mm: remove compat_process_vm_{readv,writev}
  fs: remove compat_sys_vmsplice
  fs: remove the compat readv/writev syscalls
  fs: remove various compat readv/writev helpers
  iov_iter: transparently handle compat iovecs in import_iovec
  iov_iter: refactor rw_copy_check_uvector and import_iovec
  iov_iter: move rw_copy_check_uvector() into lib/iov_iter.c
  compat.h: fix a spelling error in <linux/compat.h>

4 files changed, 49 insertions, 398 deletions

diff --git a/fs/aio.c b/fs/aio.c
index d5ec30385566..c45c20d87538 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -1489,12 +1489,8 @@ static ssize_t aio_setup_rw(int rw, const struct iocb *iocb,
 		*iovec = NULL;
 		return ret;
 	}
-#ifdef CONFIG_COMPAT
-	if (compat)
-		return compat_import_iovec(rw, buf, len, UIO_FASTIOV, iovec,
-				iter);
-#endif
-	return import_iovec(rw, buf, len, UIO_FASTIOV, iovec, iter);
+
+	return __import_iovec(rw, buf, len, UIO_FASTIOV, iovec, iter, compat);
 }
 
 static inline void aio_rw_done(struct kiocb *req, ssize_t ret)
diff --git a/fs/io_uring.c b/fs/io_uring.c
index aae0ef2ec34d..f58b3d6bba8a 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -2852,13 +2852,8 @@ static ssize_t __io_import_iovec(int rw, struct io_kiocb *req,
 		return ret;
 	}
 
-#ifdef CONFIG_COMPAT
-	if (req->ctx->compat)
-		return compat_import_iovec(rw, buf, sqe_len, UIO_FASTIOV,
-						iovec, iter);
-#endif
-
-	return import_iovec(rw, buf, sqe_len, UIO_FASTIOV, iovec, iter);
+	return __import_iovec(rw, buf, sqe_len, UIO_FASTIOV, iovec, iter,
+			      req->ctx->compat);
 }
 
 static ssize_t io_import_iovec(int rw, struct io_kiocb *req,
@@ -4200,8 +4195,9 @@ static int __io_recvmsg_copy_hdr(struct io_kiocb *req,
 				sr->len);
 		iomsg->iov = NULL;
 	} else {
-		ret = import_iovec(READ, uiov, iov_len, UIO_FASTIOV,
-					&iomsg->iov, &iomsg->msg.msg_iter);
+		ret = __import_iovec(READ, uiov, iov_len, UIO_FASTIOV,
+				     &iomsg->iov, &iomsg->msg.msg_iter,
+				     false);
 		if (ret > 0)
 			ret = 0;
 	}
@@ -4241,9 +4237,9 @@ static int __io_compat_recvmsg_copy_hdr(struct io_kiocb *req,
 		sr->len = iomsg->iov[0].iov_len;
 		iomsg->iov = NULL;
 	} else {
-		ret = compat_import_iovec(READ, uiov, len, UIO_FASTIOV,
-						&iomsg->iov,
-						&iomsg->msg.msg_iter);
+		ret = __import_iovec(READ, (struct iovec __user *)uiov, len,
+				   UIO_FASTIOV, &iomsg->iov,
+				   &iomsg->msg.msg_iter, true);
 		if (ret < 0)
 			return ret;
 	}
diff --git a/fs/read_write.c b/fs/read_write.c
index d3428189f36b..19f5c4bf75aa 100644
--- a/fs/read_write.c
+++ b/fs/read_write.c
@@ -760,185 +760,6 @@ 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)
 {
@@ -1255,224 +1076,93 @@ 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)
diff --git a/fs/splice.c b/fs/splice.c
index ce75aec52274..70cc52af780b 100644
--- a/fs/splice.c
+++ b/fs/splice.c
@@ -33,7 +33,6 @@
 #include <linux/security.h>
 #include <linux/gfp.h>
 #include <linux/socket.h>
-#include <linux/compat.h>
 #include <linux/sched/signal.h>
 
 #include "internal.h"
@@ -1352,20 +1351,6 @@ static int vmsplice_type(struct fd f, int *type)
  * Currently we punt and implement it as a normal copy, see pipe_to_user().
  *
  */
-static long do_vmsplice(struct file *f, struct iov_iter *iter, unsigned int flags)
-{
-	if (unlikely(flags & ~SPLICE_F_ALL))
-		return -EINVAL;
-
-	if (!iov_iter_count(iter))
-		return 0;
-
-	if (iov_iter_rw(iter) == WRITE)
-		return vmsplice_to_pipe(f, iter, flags);
-	else
-		return vmsplice_to_user(f, iter, flags);
-}
-
 SYSCALL_DEFINE4(vmsplice, int, fd, const struct iovec __user *, uiov,
 		unsigned long, nr_segs, unsigned int, flags)
 {
@@ -1376,6 +1361,9 @@ SYSCALL_DEFINE4(vmsplice, int, fd, const struct iovec __user *, uiov,
 	struct fd f;
 	int type;
 
+	if (unlikely(flags & ~SPLICE_F_ALL))
+		return -EINVAL;
+
 	f = fdget(fd);
 	error = vmsplice_type(f, &type);
 	if (error)
@@ -1383,40 +1371,21 @@ SYSCALL_DEFINE4(vmsplice, int, fd, const struct iovec __user *, uiov,
 
 	error = import_iovec(type, uiov, nr_segs,
 			     ARRAY_SIZE(iovstack), &iov, &iter);
-	if (error >= 0) {
-		error = do_vmsplice(f.file, &iter, flags);
-		kfree(iov);
-	}
-	fdput(f);
-	return error;
-}
+	if (error < 0)
+		goto out_fdput;
 
-#ifdef CONFIG_COMPAT
-COMPAT_SYSCALL_DEFINE4(vmsplice, int, fd, const struct compat_iovec __user *, iov32,
-		    unsigned int, nr_segs, unsigned int, flags)
-{
-	struct iovec iovstack[UIO_FASTIOV];
-	struct iovec *iov = iovstack;
-	struct iov_iter iter;
-	ssize_t error;
-	struct fd f;
-	int type;
-
-	f = fdget(fd);
-	error = vmsplice_type(f, &type);
-	if (error)
-		return error;
+	if (!iov_iter_count(&iter))
+		error = 0;
+	else if (iov_iter_rw(&iter) == WRITE)
+		error = vmsplice_to_pipe(f.file, &iter, flags);
+	else
+		error = vmsplice_to_user(f.file, &iter, flags);
 
-	error = compat_import_iovec(type, iov32, nr_segs,
-			     ARRAY_SIZE(iovstack), &iov, &iter);
-	if (error >= 0) {
-		error = do_vmsplice(f.file, &iter, flags);
-		kfree(iov);
-	}
+	kfree(iov);
+out_fdput:
 	fdput(f);
 	return error;
 }
-#endif
 
 SYSCALL_DEFINE6(splice, int, fd_in, loff_t __user *, off_in,
 		int, fd_out, loff_t __user *, off_out,