#include <linux/device_cgroup.h>
#include <linux/highmem.h>
#include <linux/blkdev.h>
+#include <linux/backing-dev.h>
#include <linux/module.h>
#include <linux/blkpg.h>
#include <linux/magic.h>
#include <linux/namei.h>
#include <linux/log2.h>
#include <linux/cleancache.h>
+#include <linux/dax.h>
#include <asm/uaccess.h>
#include "internal.h"
return container_of(inode, struct bdev_inode, vfs_inode);
}
-inline struct block_device *I_BDEV(struct inode *inode)
+struct block_device *I_BDEV(struct inode *inode)
{
return &BDEV_I(inode)->bdev;
}
EXPORT_SYMBOL(I_BDEV);
-static void bdev_write_inode(struct inode *inode)
+static void bdev_write_inode(struct block_device *bdev)
{
+ struct inode *inode = bdev->bd_inode;
+ int ret;
+
spin_lock(&inode->i_lock);
while (inode->i_state & I_DIRTY) {
spin_unlock(&inode->i_lock);
- WARN_ON_ONCE(write_inode_now(inode, true));
+ ret = write_inode_now(inode, true);
+ if (ret) {
+ char name[BDEVNAME_SIZE];
+ pr_warn_ratelimited("VFS: Dirty inode writeback failed "
+ "for block device %s (err=%d).\n",
+ bdevname(bdev, name), ret);
+ }
spin_lock(&inode->i_lock);
}
spin_unlock(&inode->i_lock);
struct file *file = iocb->ki_filp;
struct inode *inode = file->f_mapping->host;
+ if (IS_DAX(inode))
+ return dax_do_io(iocb, inode, iter, offset, blkdev_get_block,
+ NULL, DIO_SKIP_DIO_COUNT);
return __blockdev_direct_IO(iocb, inode, I_BDEV(inode), iter, offset,
blkdev_get_block, NULL, NULL,
DIO_SKIP_DIO_COUNT);
struct page *page)
{
const struct block_device_operations *ops = bdev->bd_disk->fops;
- if (!ops->rw_page)
- return -EOPNOTSUPP;
- return ops->rw_page(bdev, sector + get_start_sect(bdev), page, READ);
+ int result = -EOPNOTSUPP;
+
+ if (!ops->rw_page || bdev_get_integrity(bdev))
+ return result;
+
+ result = blk_queue_enter(bdev->bd_queue, GFP_KERNEL);
+ if (result)
+ return result;
+ result = ops->rw_page(bdev, sector + get_start_sect(bdev), page, READ);
+ blk_queue_exit(bdev->bd_queue);
+ return result;
}
EXPORT_SYMBOL_GPL(bdev_read_page);
int result;
int rw = (wbc->sync_mode == WB_SYNC_ALL) ? WRITE_SYNC : WRITE;
const struct block_device_operations *ops = bdev->bd_disk->fops;
- if (!ops->rw_page)
+
+ if (!ops->rw_page || bdev_get_integrity(bdev))
return -EOPNOTSUPP;
+ result = blk_queue_enter(bdev->bd_queue, GFP_KERNEL);
+ if (result)
+ return result;
+
set_page_writeback(page);
result = ops->rw_page(bdev, sector + get_start_sect(bdev), page, rw);
if (result)
end_page_writeback(page);
else
unlock_page(page);
+ blk_queue_exit(bdev->bd_queue);
return result;
}
EXPORT_SYMBOL_GPL(bdev_write_page);
* accessible at this address.
*/
long bdev_direct_access(struct block_device *bdev, sector_t sector,
- void **addr, unsigned long *pfn, long size)
+ void __pmem **addr, unsigned long *pfn, long size)
{
long avail;
const struct block_device_operations *ops = bdev->bd_disk->fops;
+ /*
+ * The device driver is allowed to sleep, in order to make the
+ * memory directly accessible.
+ */
+ might_sleep();
+
if (size < 0)
return size;
if (!ops->direct_access)
sector += get_start_sect(bdev);
if (sector % (PAGE_SIZE / 512))
return -EINVAL;
- avail = ops->direct_access(bdev, sector, addr, pfn, size);
+ avail = ops->direct_access(bdev, sector, addr, pfn);
if (!avail)
return -ERANGE;
return min(avail, size);
.kill_sb = kill_anon_super,
};
-static struct super_block *blockdev_superblock __read_mostly;
+struct super_block *blockdev_superblock __read_mostly;
+EXPORT_SYMBOL_GPL(blockdev_superblock);
void __init bdev_cache_init(void)
{
return bdev;
}
-int sb_is_blkdev_sb(struct super_block *sb)
-{
- return sb == blockdev_superblock;
-}
-
/* Call when you free inode */
void bd_forget(struct inode *inode)
if (disk->fops->revalidate_disk)
ret = disk->fops->revalidate_disk(disk);
-
+ blk_integrity_revalidate(disk);
bdev = bdget_disk(disk, 0);
if (!bdev)
return ret;
bdev->bd_disk = disk;
bdev->bd_queue = disk->queue;
bdev->bd_contains = bdev;
+ bdev->bd_inode->i_flags = disk->fops->direct_access ? S_DAX : 0;
if (!partno) {
ret = -ENXIO;
bdev->bd_part = disk_get_part(disk, partno);
goto out_clear;
}
bd_set_size(bdev, (loff_t)bdev->bd_part->nr_sects << 9);
+ /*
+ * If the partition is not aligned on a page
+ * boundary, we can't do dax I/O to it.
+ */
+ if ((bdev->bd_part->start_sect % (PAGE_SIZE / 512)) ||
+ (bdev->bd_part->nr_sects % (PAGE_SIZE / 512)))
+ bdev->bd_inode->i_flags &= ~S_DAX;
}
} else {
if (bdev->bd_contains == bdev) {
WARN_ON_ONCE(bdev->bd_holders);
sync_blockdev(bdev);
kill_bdev(bdev);
+
+ bdev_write_inode(bdev);
/*
- * ->release can cause the queue to disappear, so flush all
- * dirty data before.
+ * Detaching bdev inode from its wb in __destroy_inode()
+ * is too late: the queue which embeds its bdi (along with
+ * root wb) can be gone as soon as we put_disk() below.
*/
- bdev_write_inode(bdev->bd_inode);
+ inode_detach_wb(bdev->bd_inode);
}
if (bdev->bd_contains == bdev) {
if (disk->fops->release)
{
struct inode *inode, *old_inode = NULL;
- spin_lock(&inode_sb_list_lock);
+ spin_lock(&blockdev_superblock->s_inode_list_lock);
list_for_each_entry(inode, &blockdev_superblock->s_inodes, i_sb_list) {
struct address_space *mapping = inode->i_mapping;
}
__iget(inode);
spin_unlock(&inode->i_lock);
- spin_unlock(&inode_sb_list_lock);
+ spin_unlock(&blockdev_superblock->s_inode_list_lock);
/*
* We hold a reference to 'inode' so it couldn't have been
* removed from s_inodes list while we dropped the
- * inode_sb_list_lock. We cannot iput the inode now as we can
+ * s_inode_list_lock We cannot iput the inode now as we can
* be holding the last reference and we cannot iput it under
- * inode_sb_list_lock. So we keep the reference and iput it
+ * s_inode_list_lock. So we keep the reference and iput it
* later.
*/
iput(old_inode);
func(I_BDEV(inode), arg);
- spin_lock(&inode_sb_list_lock);
+ spin_lock(&blockdev_superblock->s_inode_list_lock);
}
- spin_unlock(&inode_sb_list_lock);
+ spin_unlock(&blockdev_superblock->s_inode_list_lock);
iput(old_inode);
}