[PATCH v3 4/5] Revert "block: enable dax for raw block devices"

From: Dan Williams
Date: Wed May 18 2016 - 16:57:49 EST


This reverts commit 5a023cdba50c5f5f2bc351783b3131699deb3937.

The functionality is superseded by the new "Device DAX" facility.

Cc: Jeff Moyer <jmoyer@xxxxxxxxxx>
Cc: Christoph Hellwig <hch@xxxxxx>
Cc: Dave Chinner <david@xxxxxxxxxxxxx>
Cc: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
Cc: Ross Zwisler <ross.zwisler@xxxxxxxxxxxxxxx>
Cc: Jan Kara <jack@xxxxxxxx>
Signed-off-by: Dan Williams <dan.j.williams@xxxxxxxxx>
---
block/ioctl.c | 32 ----------------
fs/block_dev.c | 96 ++++++++++++++---------------------------------
include/linux/fs.h | 8 ----
include/uapi/linux/fs.h | 1
4 files changed, 29 insertions(+), 108 deletions(-)

diff --git a/block/ioctl.c b/block/ioctl.c
index 4ff1f92f89ca..698c7933d582 100644
--- a/block/ioctl.c
+++ b/block/ioctl.c
@@ -407,35 +407,6 @@ static inline int is_unrecognized_ioctl(int ret)
ret == -ENOIOCTLCMD;
}

-#ifdef CONFIG_FS_DAX
-bool blkdev_dax_capable(struct block_device *bdev)
-{
- struct gendisk *disk = bdev->bd_disk;
-
- if (!disk->fops->direct_access)
- return false;
-
- /*
- * 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)))
- return false;
-
- /*
- * If the device has known bad blocks, force all I/O through the
- * driver / page cache.
- *
- * TODO: support finer grained dax error handling
- */
- if (disk->bb && disk->bb->count)
- return false;
-
- return true;
-}
-#endif
-
static int blkdev_flushbuf(struct block_device *bdev, fmode_t mode,
unsigned cmd, unsigned long arg)
{
@@ -598,9 +569,6 @@ int blkdev_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd,
case BLKTRACESETUP:
case BLKTRACETEARDOWN:
return blk_trace_ioctl(bdev, cmd, argp);
- case BLKDAXGET:
- return put_int(arg, !!(bdev->bd_inode->i_flags & S_DAX));
- break;
case IOC_PR_REGISTER:
return blkdev_pr_register(bdev, argp);
case IOC_PR_RESERVE:
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 20a2c02b77c4..36ee10ca503e 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -29,6 +29,7 @@
#include <linux/log2.h>
#include <linux/cleancache.h>
#include <linux/dax.h>
+#include <linux/badblocks.h>
#include <asm/uaccess.h>
#include "internal.h"

@@ -1159,6 +1160,33 @@ void bd_set_size(struct block_device *bdev, loff_t size)
}
EXPORT_SYMBOL(bd_set_size);

+static bool blkdev_dax_capable(struct block_device *bdev)
+{
+ struct gendisk *disk = bdev->bd_disk;
+
+ if (!disk->fops->direct_access || !IS_ENABLED(CONFIG_FS_DAX))
+ return false;
+
+ /*
+ * 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)))
+ return false;
+
+ /*
+ * If the device has known bad blocks, force all I/O through the
+ * driver / page cache.
+ *
+ * TODO: support finer grained dax error handling
+ */
+ if (disk->bb && disk->bb->count)
+ return false;
+
+ return true;
+}
+
static void __blkdev_put(struct block_device *bdev, fmode_t mode, int for_part);

/*
@@ -1724,79 +1752,13 @@ static const struct address_space_operations def_blk_aops = {
.is_dirty_writeback = buffer_check_dirty_writeback,
};

-#ifdef CONFIG_FS_DAX
-/*
- * In the raw block case we do not need to contend with truncation nor
- * unwritten file extents. Without those concerns there is no need for
- * additional locking beyond the mmap_sem context that these routines
- * are already executing under.
- *
- * Note, there is no protection if the block device is dynamically
- * resized (partition grow/shrink) during a fault. A stable block device
- * size is already not enforced in the blkdev_direct_IO path.
- *
- * For DAX, it is the responsibility of the block device driver to
- * ensure the whole-disk device size is stable while requests are in
- * flight.
- *
- * Finally, unlike the filemap_page_mkwrite() case there is no
- * filesystem superblock to sync against freezing. We still include a
- * pfn_mkwrite callback for dax drivers to receive write fault
- * notifications.
- */
-static int blkdev_dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
-{
- return __dax_fault(vma, vmf, blkdev_get_block, NULL);
-}
-
-static int blkdev_dax_pfn_mkwrite(struct vm_area_struct *vma,
- struct vm_fault *vmf)
-{
- return dax_pfn_mkwrite(vma, vmf);
-}
-
-static int blkdev_dax_pmd_fault(struct vm_area_struct *vma, unsigned long addr,
- pmd_t *pmd, unsigned int flags)
-{
- return __dax_pmd_fault(vma, addr, pmd, flags, blkdev_get_block, NULL);
-}
-
-static const struct vm_operations_struct blkdev_dax_vm_ops = {
- .fault = blkdev_dax_fault,
- .pmd_fault = blkdev_dax_pmd_fault,
- .pfn_mkwrite = blkdev_dax_pfn_mkwrite,
-};
-
-static const struct vm_operations_struct blkdev_default_vm_ops = {
- .fault = filemap_fault,
- .map_pages = filemap_map_pages,
-};
-
-static int blkdev_mmap(struct file *file, struct vm_area_struct *vma)
-{
- struct inode *bd_inode = bdev_file_inode(file);
-
- file_accessed(file);
- if (IS_DAX(bd_inode)) {
- vma->vm_ops = &blkdev_dax_vm_ops;
- vma->vm_flags |= VM_MIXEDMAP | VM_HUGEPAGE;
- } else {
- vma->vm_ops = &blkdev_default_vm_ops;
- }
-
- return 0;
-}
-#else
-#define blkdev_mmap generic_file_mmap
-#endif
-
const struct file_operations def_blk_fops = {
.open = blkdev_open,
.release = blkdev_close,
.llseek = block_llseek,
.read_iter = blkdev_read_iter,
.write_iter = blkdev_write_iter,
- .mmap = blkdev_mmap,
+ .mmap = generic_file_mmap,
.fsync = blkdev_fsync,
.unlocked_ioctl = block_ioctl,
#ifdef CONFIG_COMPAT
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 70e61b58baaf..8363a10660f6 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -2320,14 +2320,6 @@ extern struct super_block *freeze_bdev(struct block_device *);
extern void emergency_thaw_all(void);
extern int thaw_bdev(struct block_device *bdev, struct super_block *sb);
extern int fsync_bdev(struct block_device *);
-#ifdef CONFIG_FS_DAX
-extern bool blkdev_dax_capable(struct block_device *bdev);
-#else
-static inline bool blkdev_dax_capable(struct block_device *bdev)
-{
- return false;
-}
-#endif

extern struct super_block *blockdev_superblock;

diff --git a/include/uapi/linux/fs.h b/include/uapi/linux/fs.h
index a079d50376e1..fbff8b28aa35 100644
--- a/include/uapi/linux/fs.h
+++ b/include/uapi/linux/fs.h
@@ -222,7 +222,6 @@ struct fsxattr {
#define BLKSECDISCARD _IO(0x12,125)
#define BLKROTATIONAL _IO(0x12,126)
#define BLKZEROOUT _IO(0x12,127)
-#define BLKDAXGET _IO(0x12,129)

#define BMAP_IOCTL 1 /* obsolete - kept for compatibility */
#define FIBMAP _IO(0x00,1) /* bmap access */