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

Pull initial set_fs() removal from Al Viro:
 "Christoph's set_fs base series + fixups"

* 'work.set_fs' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs:
  fs: Allow a NULL pos pointer to __kernel_read
  fs: Allow a NULL pos pointer to __kernel_write
  powerpc: remove address space overrides using set_fs()
  powerpc: use non-set_fs based maccess routines
  x86: remove address space overrides using set_fs()
  x86: make TASK_SIZE_MAX usable from assembly code
  x86: move PAGE_OFFSET, TASK_SIZE & friends to page_{32,64}_types.h
  lkdtm: remove set_fs-based tests
  test_bitmap: remove user bitmap tests
  uaccess: add infrastructure for kernel builds with set_fs()
  fs: don't allow splice read/write without explicit ops
  fs: don't allow kernel reads and writes without iter ops
  sysctl: Convert to iter interfaces
  proc: add a read_iter method to proc proc_ops
  proc: cleanup the compat vs no compat file ops
  proc: remove a level of indentation in proc_get_inode

4 files changed, 166 insertions, 202 deletions

diff --git a/fs/proc/inode.c b/fs/proc/inode.c
index 28d6105e908e..58c075e2a452 100644
--- a/fs/proc/inode.c
+++ b/fs/proc/inode.c
@@ -297,6 +297,21 @@ static loff_t proc_reg_llseek(struct file *file, loff_t offset, int whence)
 	return rv;
 }
 
+static ssize_t proc_reg_read_iter(struct kiocb *iocb, struct iov_iter *iter)
+{
+	struct proc_dir_entry *pde = PDE(file_inode(iocb->ki_filp));
+	ssize_t ret;
+
+	if (pde_is_permanent(pde))
+		return pde->proc_ops->proc_read_iter(iocb, iter);
+
+	if (!use_pde(pde))
+		return -EIO;
+	ret = pde->proc_ops->proc_read_iter(iocb, iter);
+	unuse_pde(pde);
+	return ret;
+}
+
 static ssize_t pde_read(struct proc_dir_entry *pde, struct file *file, char __user *buf, size_t count, loff_t *ppos)
 {
 	typeof_member(struct proc_ops, proc_read) read;
@@ -572,9 +587,18 @@ static const struct file_operations proc_reg_file_ops = {
 	.write		= proc_reg_write,
 	.poll		= proc_reg_poll,
 	.unlocked_ioctl	= proc_reg_unlocked_ioctl,
-#ifdef CONFIG_COMPAT
-	.compat_ioctl	= proc_reg_compat_ioctl,
-#endif
+	.mmap		= proc_reg_mmap,
+	.get_unmapped_area = proc_reg_get_unmapped_area,
+	.open		= proc_reg_open,
+	.release	= proc_reg_release,
+};
+
+static const struct file_operations proc_iter_file_ops = {
+	.llseek		= proc_reg_llseek,
+	.read_iter	= proc_reg_read_iter,
+	.write		= proc_reg_write,
+	.poll		= proc_reg_poll,
+	.unlocked_ioctl	= proc_reg_unlocked_ioctl,
 	.mmap		= proc_reg_mmap,
 	.get_unmapped_area = proc_reg_get_unmapped_area,
 	.open		= proc_reg_open,
@@ -582,12 +606,26 @@ static const struct file_operations proc_reg_file_ops = {
 };
 
 #ifdef CONFIG_COMPAT
-static const struct file_operations proc_reg_file_ops_no_compat = {
+static const struct file_operations proc_reg_file_ops_compat = {
 	.llseek		= proc_reg_llseek,
 	.read		= proc_reg_read,
 	.write		= proc_reg_write,
 	.poll		= proc_reg_poll,
 	.unlocked_ioctl	= proc_reg_unlocked_ioctl,
+	.compat_ioctl	= proc_reg_compat_ioctl,
+	.mmap		= proc_reg_mmap,
+	.get_unmapped_area = proc_reg_get_unmapped_area,
+	.open		= proc_reg_open,
+	.release	= proc_reg_release,
+};
+
+static const struct file_operations proc_iter_file_ops_compat = {
+	.llseek		= proc_reg_llseek,
+	.read_iter	= proc_reg_read_iter,
+	.write		= proc_reg_write,
+	.poll		= proc_reg_poll,
+	.unlocked_ioctl	= proc_reg_unlocked_ioctl,
+	.compat_ioctl	= proc_reg_compat_ioctl,
 	.mmap		= proc_reg_mmap,
 	.get_unmapped_area = proc_reg_get_unmapped_area,
 	.open		= proc_reg_open,
@@ -619,42 +657,51 @@ struct inode *proc_get_inode(struct super_block *sb, struct proc_dir_entry *de)
 {
 	struct inode *inode = new_inode(sb);
 
-	if (inode) {
-		inode->i_ino = de->low_ino;
-		inode->i_mtime = inode->i_atime = inode->i_ctime = current_time(inode);
-		PROC_I(inode)->pde = de;
+	if (!inode) {
+		pde_put(de);
+		return NULL;
+	}
 
-		if (is_empty_pde(de)) {
-			make_empty_dir_inode(inode);
-			return inode;
-		}
-		if (de->mode) {
-			inode->i_mode = de->mode;
-			inode->i_uid = de->uid;
-			inode->i_gid = de->gid;
-		}
-		if (de->size)
-			inode->i_size = de->size;
-		if (de->nlink)
-			set_nlink(inode, de->nlink);
+	inode->i_ino = de->low_ino;
+	inode->i_mtime = inode->i_atime = inode->i_ctime = current_time(inode);
+	PROC_I(inode)->pde = de;
+	if (is_empty_pde(de)) {
+		make_empty_dir_inode(inode);
+		return inode;
+	}
 
-		if (S_ISREG(inode->i_mode)) {
-			inode->i_op = de->proc_iops;
+	if (de->mode) {
+		inode->i_mode = de->mode;
+		inode->i_uid = de->uid;
+		inode->i_gid = de->gid;
+	}
+	if (de->size)
+		inode->i_size = de->size;
+	if (de->nlink)
+		set_nlink(inode, de->nlink);
+
+	if (S_ISREG(inode->i_mode)) {
+		inode->i_op = de->proc_iops;
+		if (de->proc_ops->proc_read_iter)
+			inode->i_fop = &proc_iter_file_ops;
+		else
 			inode->i_fop = &proc_reg_file_ops;
 #ifdef CONFIG_COMPAT
-			if (!de->proc_ops->proc_compat_ioctl) {
-				inode->i_fop = &proc_reg_file_ops_no_compat;
-			}
+		if (de->proc_ops->proc_compat_ioctl) {
+			if (de->proc_ops->proc_read_iter)
+				inode->i_fop = &proc_iter_file_ops_compat;
+			else
+				inode->i_fop = &proc_reg_file_ops_compat;
+		}
 #endif
-		} else if (S_ISDIR(inode->i_mode)) {
-			inode->i_op = de->proc_iops;
-			inode->i_fop = de->proc_dir_ops;
-		} else if (S_ISLNK(inode->i_mode)) {
-			inode->i_op = de->proc_iops;
-			inode->i_fop = NULL;
-		} else
-			BUG();
-	} else
-	       pde_put(de);
+	} else if (S_ISDIR(inode->i_mode)) {
+		inode->i_op = de->proc_iops;
+		inode->i_fop = de->proc_dir_ops;
+	} else if (S_ISLNK(inode->i_mode)) {
+		inode->i_op = de->proc_iops;
+		inode->i_fop = NULL;
+	} else {
+		BUG();
+	}
 	return inode;
 }
diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c
index 6c1166ccdaea..317899222d7f 100644
--- a/fs/proc/proc_sysctl.c
+++ b/fs/proc/proc_sysctl.c
@@ -12,6 +12,7 @@
 #include <linux/cred.h>
 #include <linux/namei.h>
 #include <linux/mm.h>
+#include <linux/uio.h>
 #include <linux/module.h>
 #include <linux/bpf-cgroup.h>
 #include <linux/mount.h>
@@ -540,13 +541,14 @@ out:
 	return err;
 }
 
-static ssize_t proc_sys_call_handler(struct file *filp, void __user *ubuf,
-		size_t count, loff_t *ppos, int write)
+static ssize_t proc_sys_call_handler(struct kiocb *iocb, struct iov_iter *iter,
+		int write)
 {
-	struct inode *inode = file_inode(filp);
+	struct inode *inode = file_inode(iocb->ki_filp);
 	struct ctl_table_header *head = grab_header(inode);
 	struct ctl_table *table = PROC_I(inode)->sysctl_entry;
-	void *kbuf;
+	size_t count = iov_iter_count(iter);
+	char *kbuf;
 	ssize_t error;
 
 	if (IS_ERR(head))
@@ -569,32 +571,30 @@ static ssize_t proc_sys_call_handler(struct file *filp, void __user *ubuf,
 	error = -ENOMEM;
 	if (count >= KMALLOC_MAX_SIZE)
 		goto out;
+	kbuf = kzalloc(count + 1, GFP_KERNEL);
+	if (!kbuf)
+		goto out;
 
 	if (write) {
-		kbuf = memdup_user_nul(ubuf, count);
-		if (IS_ERR(kbuf)) {
-			error = PTR_ERR(kbuf);
-			goto out;
-		}
-	} else {
-		kbuf = kzalloc(count, GFP_KERNEL);
-		if (!kbuf)
-			goto out;
+		error = -EFAULT;
+		if (!copy_from_iter_full(kbuf, count, iter))
+			goto out_free_buf;
+		kbuf[count] = '\0';
 	}
 
 	error = BPF_CGROUP_RUN_PROG_SYSCTL(head, table, write, &kbuf, &count,
-					   ppos);
+					   &iocb->ki_pos);
 	if (error)
 		goto out_free_buf;
 
 	/* careful: calling conventions are nasty here */
-	error = table->proc_handler(table, write, kbuf, &count, ppos);
+	error = table->proc_handler(table, write, kbuf, &count, &iocb->ki_pos);
 	if (error)
 		goto out_free_buf;
 
 	if (!write) {
 		error = -EFAULT;
-		if (copy_to_user(ubuf, kbuf, count))
+		if (copy_to_iter(kbuf, count, iter) < count)
 			goto out_free_buf;
 	}
 
@@ -607,16 +607,14 @@ out:
 	return error;
 }
 
-static ssize_t proc_sys_read(struct file *filp, char __user *buf,
-				size_t count, loff_t *ppos)
+static ssize_t proc_sys_read(struct kiocb *iocb, struct iov_iter *iter)
 {
-	return proc_sys_call_handler(filp, (void __user *)buf, count, ppos, 0);
+	return proc_sys_call_handler(iocb, iter, 0);
 }
 
-static ssize_t proc_sys_write(struct file *filp, const char __user *buf,
-				size_t count, loff_t *ppos)
+static ssize_t proc_sys_write(struct kiocb *iocb, struct iov_iter *iter)
 {
-	return proc_sys_call_handler(filp, (void __user *)buf, count, ppos, 1);
+	return proc_sys_call_handler(iocb, iter, 1);
 }
 
 static int proc_sys_open(struct inode *inode, struct file *filp)
@@ -853,8 +851,10 @@ static int proc_sys_getattr(const struct path *path, struct kstat *stat,
 static const struct file_operations proc_sys_file_operations = {
 	.open		= proc_sys_open,
 	.poll		= proc_sys_poll,
-	.read		= proc_sys_read,
-	.write		= proc_sys_write,
+	.read_iter	= proc_sys_read,
+	.write_iter	= proc_sys_write,
+	.splice_read	= generic_file_splice_read,
+	.splice_write	= iter_file_splice_write,
 	.llseek		= default_llseek,
 };
 
diff --git a/fs/read_write.c b/fs/read_write.c
index 19f5c4bf75aa..a669fb049b84 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);
 	}
@@ -889,7 +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];
diff --git a/fs/splice.c b/fs/splice.c
index 70cc52af780b..599b740f1098 100644
--- a/fs/splice.c
+++ b/fs/splice.c
@@ -341,89 +341,6 @@ const struct pipe_buf_operations nosteal_pipe_buf_ops = {
 };
 EXPORT_SYMBOL(nosteal_pipe_buf_ops);
 
-static ssize_t kernel_readv(struct file *file, const struct kvec *vec,
-			    unsigned long vlen, loff_t offset)
-{
-	mm_segment_t old_fs;
-	loff_t pos = offset;
-	ssize_t res;
-
-	old_fs = get_fs();
-	set_fs(KERNEL_DS);
-	/* The cast to a user pointer is valid due to the set_fs() */
-	res = vfs_readv(file, (const struct iovec __user *)vec, vlen, &pos, 0);
-	set_fs(old_fs);
-
-	return res;
-}
-
-static ssize_t default_file_splice_read(struct file *in, loff_t *ppos,
-				 struct pipe_inode_info *pipe, size_t len,
-				 unsigned int flags)
-{
-	struct kvec *vec, __vec[PIPE_DEF_BUFFERS];
-	struct iov_iter to;
-	struct page **pages;
-	unsigned int nr_pages;
-	unsigned int mask;
-	size_t offset, base, copied = 0;
-	ssize_t res;
-	int i;
-
-	if (pipe_full(pipe->head, pipe->tail, pipe->max_usage))
-		return -EAGAIN;
-
-	/*
-	 * Try to keep page boundaries matching to source pagecache ones -
-	 * it probably won't be much help, but...
-	 */
-	offset = *ppos & ~PAGE_MASK;
-
-	iov_iter_pipe(&to, READ, pipe, len + offset);
-
-	res = iov_iter_get_pages_alloc(&to, &pages, len + offset, &base);
-	if (res <= 0)
-		return -ENOMEM;
-
-	nr_pages = DIV_ROUND_UP(res + base, PAGE_SIZE);
-
-	vec = __vec;
-	if (nr_pages > PIPE_DEF_BUFFERS) {
-		vec = kmalloc_array(nr_pages, sizeof(struct kvec), GFP_KERNEL);
-		if (unlikely(!vec)) {
-			res = -ENOMEM;
-			goto out;
-		}
-	}
-
-	mask = pipe->ring_size - 1;
-	pipe->bufs[to.head & mask].offset = offset;
-	pipe->bufs[to.head & mask].len -= offset;
-
-	for (i = 0; i < nr_pages; i++) {
-		size_t this_len = min_t(size_t, len, PAGE_SIZE - offset);
-		vec[i].iov_base = page_address(pages[i]) + offset;
-		vec[i].iov_len = this_len;
-		len -= this_len;
-		offset = 0;
-	}
-
-	res = kernel_readv(in, vec, nr_pages, *ppos);
-	if (res > 0) {
-		copied = res;
-		*ppos += res;
-	}
-
-	if (vec != __vec)
-		kfree(vec);
-out:
-	for (i = 0; i < nr_pages; i++)
-		put_page(pages[i]);
-	kvfree(pages);
-	iov_iter_advance(&to, copied);	/* truncates and discards */
-	return res;
-}
-
 /*
  * Send 'sd->len' bytes to socket from 'sd->file' at position 'sd->pos'
  * using sendpage(). Return the number of bytes sent.
@@ -807,33 +724,6 @@ done:
 
 EXPORT_SYMBOL(iter_file_splice_write);
 
-static int write_pipe_buf(struct pipe_inode_info *pipe, struct pipe_buffer *buf,
-			  struct splice_desc *sd)
-{
-	int ret;
-	void *data;
-	loff_t tmp = sd->pos;
-
-	data = kmap(buf->page);
-	ret = __kernel_write(sd->u.file, data + buf->offset, sd->len, &tmp);
-	kunmap(buf->page);
-
-	return ret;
-}
-
-static ssize_t default_file_splice_write(struct pipe_inode_info *pipe,
-					 struct file *out, loff_t *ppos,
-					 size_t len, unsigned int flags)
-{
-	ssize_t ret;
-
-	ret = splice_from_pipe(pipe, out, ppos, len, flags, write_pipe_buf);
-	if (ret > 0)
-		*ppos += ret;
-
-	return ret;
-}
-
 /**
  * generic_splice_sendpage - splice data from a pipe to a socket
  * @pipe:	pipe to splice from
@@ -855,15 +745,23 @@ ssize_t generic_splice_sendpage(struct pipe_inode_info *pipe, struct file *out,
 
 EXPORT_SYMBOL(generic_splice_sendpage);
 
+static int warn_unsupported(struct file *file, const char *op)
+{
+	pr_debug_ratelimited(
+		"splice %s not supported for file %pD4 (pid: %d comm: %.20s)\n",
+		op, file, current->pid, current->comm);
+	return -EINVAL;
+}
+
 /*
  * Attempt to initiate a splice from pipe to file.
  */
 static long do_splice_from(struct pipe_inode_info *pipe, struct file *out,
 			   loff_t *ppos, size_t len, unsigned int flags)
 {
-	if (out->f_op->splice_write)
-		return out->f_op->splice_write(pipe, out, ppos, len, flags);
-	return default_file_splice_write(pipe, out, ppos, len, flags);
+	if (unlikely(!out->f_op->splice_write))
+		return warn_unsupported(out, "write");
+	return out->f_op->splice_write(pipe, out, ppos, len, flags);
 }
 
 /*
@@ -885,9 +783,9 @@ static long do_splice_to(struct file *in, loff_t *ppos,
 	if (unlikely(len > MAX_RW_COUNT))
 		len = MAX_RW_COUNT;
 
-	if (in->f_op->splice_read)
-		return in->f_op->splice_read(in, ppos, pipe, len, flags);
-	return default_file_splice_read(in, ppos, pipe, len, flags);
+	if (unlikely(!in->f_op->splice_read))
+		return warn_unsupported(in, "read");
+	return in->f_op->splice_read(in, ppos, pipe, len, flags);
 }
 
 /**