dax,ext2: replace XIP read and write with DAX I/O

Use the generic AIO infrastructure instead of custom read and write
methods.  In addition to giving us support for AIO, this adds the missing
locking between read() and truncate().

Signed-off-by: Matthew Wilcox <matthew.r.wilcox@intel.com>
Reviewed-by: Ross Zwisler <ross.zwisler@linux.intel.com>
Reviewed-by: Jan Kara <jack@suse.cz>
Cc: Andreas Dilger <andreas.dilger@intel.com>
Cc: Boaz Harrosh <boaz@plexistor.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Dave Chinner <david@fromorbit.com>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Randy Dunlap <rdunlap@infradead.org>
Cc: Theodore Ts'o <tytso@mit.edu>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

2 files changed, 2 insertions, 238 deletions

diff --git a/mm/filemap.c b/mm/filemap.c
index 1578c224285e..ad7242043bdb 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -1695,8 +1695,7 @@ generic_file_read_iter(struct kiocb *iocb, struct iov_iter *iter)
 	loff_t *ppos = &iocb->ki_pos;
 	loff_t pos = *ppos;
 
-	/* coalesce the iovecs and go direct-to-BIO for O_DIRECT */
-	if (file->f_flags & O_DIRECT) {
+	if (io_is_direct(file)) {
 		struct address_space *mapping = file->f_mapping;
 		struct inode *inode = mapping->host;
 		size_t count = iov_iter_count(iter);
@@ -2584,8 +2583,7 @@ ssize_t __generic_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
 	if (err)
 		goto out;
 
-	/* coalesce the iovecs and go direct-to-BIO for O_DIRECT */
-	if (unlikely(file->f_flags & O_DIRECT)) {
+	if (io_is_direct(file)) {
 		loff_t endbyte;
 
 		written = generic_file_direct_write(iocb, from, pos);
diff --git a/mm/filemap_xip.c b/mm/filemap_xip.c
index 59e1c5585748..9c869f402c07 100644
--- a/mm/filemap_xip.c
+++ b/mm/filemap_xip.c
@@ -43,119 +43,6 @@ static struct page *xip_sparse_page(void)
 }
 
 /*
- * This is a file read routine for execute in place files, and uses
- * the mapping->a_ops->get_xip_mem() function for the actual low-level
- * stuff.
- *
- * Note the struct file* is not used at all.  It may be NULL.
- */
-static ssize_t
-do_xip_mapping_read(struct address_space *mapping,
-		    struct file_ra_state *_ra,
-		    struct file *filp,
-		    char __user *buf,
-		    size_t len,
-		    loff_t *ppos)
-{
-	struct inode *inode = mapping->host;
-	pgoff_t index, end_index;
-	unsigned long offset;
-	loff_t isize, pos;
-	size_t copied = 0, error = 0;
-
-	BUG_ON(!mapping->a_ops->get_xip_mem);
-
-	pos = *ppos;
-	index = pos >> PAGE_CACHE_SHIFT;
-	offset = pos & ~PAGE_CACHE_MASK;
-
-	isize = i_size_read(inode);
-	if (!isize)
-		goto out;
-
-	end_index = (isize - 1) >> PAGE_CACHE_SHIFT;
-	do {
-		unsigned long nr, left;
-		void *xip_mem;
-		unsigned long xip_pfn;
-		int zero = 0;
-
-		/* nr is the maximum number of bytes to copy from this page */
-		nr = PAGE_CACHE_SIZE;
-		if (index >= end_index) {
-			if (index > end_index)
-				goto out;
-			nr = ((isize - 1) & ~PAGE_CACHE_MASK) + 1;
-			if (nr <= offset) {
-				goto out;
-			}
-		}
-		nr = nr - offset;
-		if (nr > len - copied)
-			nr = len - copied;
-
-		error = mapping->a_ops->get_xip_mem(mapping, index, 0,
-							&xip_mem, &xip_pfn);
-		if (unlikely(error)) {
-			if (error == -ENODATA) {
-				/* sparse */
-				zero = 1;
-			} else
-				goto out;
-		}
-
-		/* If users can be writing to this page using arbitrary
-		 * virtual addresses, take care about potential aliasing
-		 * before reading the page on the kernel side.
-		 */
-		if (mapping_writably_mapped(mapping))
-			/* address based flush */ ;
-
-		/*
-		 * Ok, we have the mem, so now we can copy it to user space...
-		 *
-		 * The actor routine returns how many bytes were actually used..
-		 * NOTE! This may not be the same as how much of a user buffer
-		 * we filled up (we may be padding etc), so we can only update
-		 * "pos" here (the actor routine has to update the user buffer
-		 * pointers and the remaining count).
-		 */
-		if (!zero)
-			left = __copy_to_user(buf+copied, xip_mem+offset, nr);
-		else
-			left = __clear_user(buf + copied, nr);
-
-		if (left) {
-			error = -EFAULT;
-			goto out;
-		}
-
-		copied += (nr - left);
-		offset += (nr - left);
-		index += offset >> PAGE_CACHE_SHIFT;
-		offset &= ~PAGE_CACHE_MASK;
-	} while (copied < len);
-
-out:
-	*ppos = pos + copied;
-	if (filp)
-		file_accessed(filp);
-
-	return (copied ? copied : error);
-}
-
-ssize_t
-xip_file_read(struct file *filp, char __user *buf, size_t len, loff_t *ppos)
-{
-	if (!access_ok(VERIFY_WRITE, buf, len))
-		return -EFAULT;
-
-	return do_xip_mapping_read(filp->f_mapping, &filp->f_ra, filp,
-			    buf, len, ppos);
-}
-EXPORT_SYMBOL_GPL(xip_file_read);
-
-/*
  * __xip_unmap is invoked from xip_unmap and xip_write
  *
  * This function walks all vmas of the address_space and unmaps the
@@ -341,127 +228,6 @@ int xip_file_mmap(struct file * file, struct vm_area_struct * vma)
 }
 EXPORT_SYMBOL_GPL(xip_file_mmap);
 
-static ssize_t
-__xip_file_write(struct file *filp, const char __user *buf,
-		  size_t count, loff_t pos, loff_t *ppos)
-{
-	struct address_space * mapping = filp->f_mapping;
-	const struct address_space_operations *a_ops = mapping->a_ops;
-	struct inode 	*inode = mapping->host;
-	long		status = 0;
-	size_t		bytes;
-	ssize_t		written = 0;
-
-	BUG_ON(!mapping->a_ops->get_xip_mem);
-
-	do {
-		unsigned long index;
-		unsigned long offset;
-		size_t copied;
-		void *xip_mem;
-		unsigned long xip_pfn;
-
-		offset = (pos & (PAGE_CACHE_SIZE -1)); /* Within page */
-		index = pos >> PAGE_CACHE_SHIFT;
-		bytes = PAGE_CACHE_SIZE - offset;
-		if (bytes > count)
-			bytes = count;
-
-		status = a_ops->get_xip_mem(mapping, index, 0,
-						&xip_mem, &xip_pfn);
-		if (status == -ENODATA) {
-			/* we allocate a new page unmap it */
-			mutex_lock(&xip_sparse_mutex);
-			status = a_ops->get_xip_mem(mapping, index, 1,
-							&xip_mem, &xip_pfn);
-			mutex_unlock(&xip_sparse_mutex);
-			if (!status)
-				/* unmap page at pgoff from all other vmas */
-				__xip_unmap(mapping, index);
-		}
-
-		if (status)
-			break;
-
-		copied = bytes -
-			__copy_from_user_nocache(xip_mem + offset, buf, bytes);
-
-		if (likely(copied > 0)) {
-			status = copied;
-
-			if (status >= 0) {
-				written += status;
-				count -= status;
-				pos += status;
-				buf += status;
-			}
-		}
-		if (unlikely(copied != bytes))
-			if (status >= 0)
-				status = -EFAULT;
-		if (status < 0)
-			break;
-	} while (count);
-	*ppos = pos;
-	/*
-	 * No need to use i_size_read() here, the i_size
-	 * cannot change under us because we hold i_mutex.
-	 */
-	if (pos > inode->i_size) {
-		i_size_write(inode, pos);
-		mark_inode_dirty(inode);
-	}
-
-	return written ? written : status;
-}
-
-ssize_t
-xip_file_write(struct file *filp, const char __user *buf, size_t len,
-	       loff_t *ppos)
-{
-	struct address_space *mapping = filp->f_mapping;
-	struct inode *inode = mapping->host;
-	size_t count;
-	loff_t pos;
-	ssize_t ret;
-
-	mutex_lock(&inode->i_mutex);
-
-	if (!access_ok(VERIFY_READ, buf, len)) {
-		ret=-EFAULT;
-		goto out_up;
-	}
-
-	pos = *ppos;
-	count = len;
-
-	/* We can write back this queue in page reclaim */
-	current->backing_dev_info = inode_to_bdi(inode);
-
-	ret = generic_write_checks(filp, &pos, &count, S_ISBLK(inode->i_mode));
-	if (ret)
-		goto out_backing;
-	if (count == 0)
-		goto out_backing;
-
-	ret = file_remove_suid(filp);
-	if (ret)
-		goto out_backing;
-
-	ret = file_update_time(filp);
-	if (ret)
-		goto out_backing;
-
-	ret = __xip_file_write (filp, buf, count, pos, ppos);
-
- out_backing:
-	current->backing_dev_info = NULL;
- out_up:
-	mutex_unlock(&inode->i_mutex);
-	return ret;
-}
-EXPORT_SYMBOL_GPL(xip_file_write);
-
 /*
  * truncate a page used for execute in place
  * functionality is analog to block_truncate_page but does use get_xip_mem