From 74278da9f70d84d715601fe794567a6d2bfdf078 Mon Sep 17 00:00:00 2001
From: Dave Chinner <dchinner@redhat.com>
Date: Wed, 4 Mar 2015 12:37:22 -0500
Subject: inode: convert inode_sb_list_lock to per-sb
The process of reducing contention on per-superblock inode lists
starts with moving the locking to match the per-superblock inode
list. This takes the global lock out of the picture and reduces the
contention problems to within a single filesystem. This doesn't get
rid of contention as the locks still have global CPU scope, but it
does isolate operations on different superblocks form each other.
Signed-off-by: Dave Chinner <dchinner@redhat.com>
Signed-off-by: Josef Bacik <jbacik@fb.com>
Reviewed-by: Jan Kara <jack@suse.cz>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Tested-by: Dave Chinner <dchinner@redhat.com>
---
fs/block_dev.c | 12 ++++++------
1 file changed, 6 insertions(+), 6 deletions(-)
(limited to 'fs/block_dev.c')
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 198243717da5..33b813e04f79 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -1769,7 +1769,7 @@ void iterate_bdevs(void (*func)(struct block_device *, void *), void *arg)
{
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;
@@ -1781,13 +1781,13 @@ void iterate_bdevs(void (*func)(struct block_device *, void *), void *arg)
}
__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);
@@ -1795,8 +1795,8 @@ void iterate_bdevs(void (*func)(struct block_device *, void *), void *arg)
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);
}
--
cgit v1.2.3-70-g09d2
From e2e05394e4a3420dab96f728df4531893494e15d Mon Sep 17 00:00:00 2001
From: Ross Zwisler <ross.zwisler@linux.intel.com>
Date: Tue, 18 Aug 2015 13:55:41 -0600
Subject: pmem, dax: have direct_access use __pmem annotation
Update the annotation for the kaddr pointer returned by direct_access()
so that it is a __pmem pointer. This is consistent with the PMEM driver
and with how this direct_access() pointer is used in the DAX code.
Signed-off-by: Ross Zwisler <ross.zwisler@linux.intel.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
Documentation/filesystems/Locking | 3 ++-
arch/powerpc/sysdev/axonram.c | 7 ++++---
drivers/block/brd.c | 4 ++--
drivers/nvdimm/pmem.c | 4 ++--
drivers/s390/block/dcssblk.c | 10 ++++++----
fs/block_dev.c | 2 +-
fs/dax.c | 37 ++++++++++++++++++++-----------------
include/linux/blkdev.h | 8 ++++----
8 files changed, 41 insertions(+), 34 deletions(-)
(limited to 'fs/block_dev.c')
diff --git a/Documentation/filesystems/Locking b/Documentation/filesystems/Locking
index 6a34a0f4d37c..06d443450f21 100644
--- a/Documentation/filesystems/Locking
+++ b/Documentation/filesystems/Locking
@@ -397,7 +397,8 @@ prototypes:
int (*release) (struct gendisk *, fmode_t);
int (*ioctl) (struct block_device *, fmode_t, unsigned, unsigned long);
int (*compat_ioctl) (struct block_device *, fmode_t, unsigned, unsigned long);
- int (*direct_access) (struct block_device *, sector_t, void **, unsigned long *);
+ int (*direct_access) (struct block_device *, sector_t, void __pmem **,
+ unsigned long *);
int (*media_changed) (struct gendisk *);
void (*unlock_native_capacity) (struct gendisk *);
int (*revalidate_disk) (struct gendisk *);
diff --git a/arch/powerpc/sysdev/axonram.c b/arch/powerpc/sysdev/axonram.c
index ee90db17b097..a2be2a66dab6 100644
--- a/arch/powerpc/sysdev/axonram.c
+++ b/arch/powerpc/sysdev/axonram.c
@@ -141,13 +141,14 @@ axon_ram_make_request(struct request_queue *queue, struct bio *bio)
*/
static long
axon_ram_direct_access(struct block_device *device, sector_t sector,
- void **kaddr, unsigned long *pfn, long size)
+ void __pmem **kaddr, unsigned long *pfn, long size)
{
struct axon_ram_bank *bank = device->bd_disk->private_data;
loff_t offset = (loff_t)sector << AXON_RAM_SECTOR_SHIFT;
+ void *addr = (void *)(bank->ph_addr + offset);
- *kaddr = (void *)(bank->ph_addr + offset);
- *pfn = virt_to_phys(*kaddr) >> PAGE_SHIFT;
+ *kaddr = (void __pmem *)addr;
+ *pfn = virt_to_phys(addr) >> PAGE_SHIFT;
return bank->size - offset;
}
diff --git a/drivers/block/brd.c b/drivers/block/brd.c
index 64ab4951e9d6..c96402fd1560 100644
--- a/drivers/block/brd.c
+++ b/drivers/block/brd.c
@@ -371,7 +371,7 @@ static int brd_rw_page(struct block_device *bdev, sector_t sector,
#ifdef CONFIG_BLK_DEV_RAM_DAX
static long brd_direct_access(struct block_device *bdev, sector_t sector,
- void **kaddr, unsigned long *pfn, long size)
+ void __pmem **kaddr, unsigned long *pfn, long size)
{
struct brd_device *brd = bdev->bd_disk->private_data;
struct page *page;
@@ -381,7 +381,7 @@ static long brd_direct_access(struct block_device *bdev, sector_t sector,
page = brd_insert_page(brd, sector);
if (!page)
return -ENOSPC;
- *kaddr = page_address(page);
+ *kaddr = (void __pmem *)page_address(page);
*pfn = page_to_pfn(page);
/*
diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c
index eb7552d939e1..f3b629779266 100644
--- a/drivers/nvdimm/pmem.c
+++ b/drivers/nvdimm/pmem.c
@@ -92,7 +92,7 @@ static int pmem_rw_page(struct block_device *bdev, sector_t sector,
}
static long pmem_direct_access(struct block_device *bdev, sector_t sector,
- void **kaddr, unsigned long *pfn, long size)
+ void __pmem **kaddr, unsigned long *pfn, long size)
{
struct pmem_device *pmem = bdev->bd_disk->private_data;
size_t offset = sector << 9;
@@ -101,7 +101,7 @@ static long pmem_direct_access(struct block_device *bdev, sector_t sector,
return -ENODEV;
/* FIXME convert DAX to comprehend that this mapping has a lifetime */
- *kaddr = (void __force *) pmem->virt_addr + offset;
+ *kaddr = pmem->virt_addr + offset;
*pfn = (pmem->phys_addr + offset) >> PAGE_SHIFT;
return pmem->size - offset;
diff --git a/drivers/s390/block/dcssblk.c b/drivers/s390/block/dcssblk.c
index da212813f2d5..2c5a397b9f3e 100644
--- a/drivers/s390/block/dcssblk.c
+++ b/drivers/s390/block/dcssblk.c
@@ -29,7 +29,7 @@ static int dcssblk_open(struct block_device *bdev, fmode_t mode);
static void dcssblk_release(struct gendisk *disk, fmode_t mode);
static void dcssblk_make_request(struct request_queue *q, struct bio *bio);
static long dcssblk_direct_access(struct block_device *bdev, sector_t secnum,
- void **kaddr, unsigned long *pfn, long size);
+ void __pmem **kaddr, unsigned long *pfn, long size);
static char dcssblk_segments[DCSSBLK_PARM_LEN] = "\0";
@@ -879,18 +879,20 @@ fail:
static long
dcssblk_direct_access (struct block_device *bdev, sector_t secnum,
- void **kaddr, unsigned long *pfn, long size)
+ void __pmem **kaddr, unsigned long *pfn, long size)
{
struct dcssblk_dev_info *dev_info;
unsigned long offset, dev_sz;
+ void *addr;
dev_info = bdev->bd_disk->private_data;
if (!dev_info)
return -ENODEV;
dev_sz = dev_info->end - dev_info->start;
offset = secnum * 512;
- *kaddr = (void *) (dev_info->start + offset);
- *pfn = virt_to_phys(*kaddr) >> PAGE_SHIFT;
+ addr = (void *) (dev_info->start + offset);
+ *pfn = virt_to_phys(addr) >> PAGE_SHIFT;
+ *kaddr = (void __pmem *) addr;
return dev_sz - offset;
}
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 198243717da5..2345a9870e2c 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -441,7 +441,7 @@ 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;
diff --git a/fs/dax.c b/fs/dax.c
index e07fecc93f80..7c634ac797b1 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -35,7 +35,7 @@ int dax_clear_blocks(struct inode *inode, sector_t block, long size)
might_sleep();
do {
- void *addr;
+ void __pmem *addr;
unsigned long pfn;
long count;
@@ -47,7 +47,7 @@ int dax_clear_blocks(struct inode *inode, sector_t block, long size)
unsigned pgsz = PAGE_SIZE - offset_in_page(addr);
if (pgsz > count)
pgsz = count;
- clear_pmem((void __pmem *)addr, pgsz);
+ clear_pmem(addr, pgsz);
addr += pgsz;
size -= pgsz;
count -= pgsz;
@@ -62,7 +62,8 @@ int dax_clear_blocks(struct inode *inode, sector_t block, long size)
}
EXPORT_SYMBOL_GPL(dax_clear_blocks);
-static long dax_get_addr(struct buffer_head *bh, void **addr, unsigned blkbits)
+static long dax_get_addr(struct buffer_head *bh, void __pmem **addr,
+ unsigned blkbits)
{
unsigned long pfn;
sector_t sector = bh->b_blocknr << (blkbits - 9);
@@ -70,15 +71,15 @@ static long dax_get_addr(struct buffer_head *bh, void **addr, unsigned blkbits)
}
/* the clear_pmem() calls are ordered by a wmb_pmem() in the caller */
-static void dax_new_buf(void *addr, unsigned size, unsigned first, loff_t pos,
- loff_t end)
+static void dax_new_buf(void __pmem *addr, unsigned size, unsigned first,
+ loff_t pos, loff_t end)
{
loff_t final = end - pos + first; /* The final byte of the buffer */
if (first > 0)
- clear_pmem((void __pmem *)addr, first);
+ clear_pmem(addr, first);
if (final < size)
- clear_pmem((void __pmem *)addr + final, size - final);
+ clear_pmem(addr + final, size - final);
}
static bool buffer_written(struct buffer_head *bh)
@@ -106,7 +107,7 @@ static ssize_t dax_io(struct inode *inode, struct iov_iter *iter,
loff_t pos = start;
loff_t max = start;
loff_t bh_max = start;
- void *addr;
+ void __pmem *addr;
bool hole = false;
bool need_wmb = false;
@@ -158,11 +159,11 @@ static ssize_t dax_io(struct inode *inode, struct iov_iter *iter,
}
if (iov_iter_rw(iter) == WRITE) {
- len = copy_from_iter_pmem((void __pmem *)addr,
- max - pos, iter);
+ len = copy_from_iter_pmem(addr, max - pos, iter);
need_wmb = true;
} else if (!hole)
- len = copy_to_iter(addr, max - pos, iter);
+ len = copy_to_iter((void __force *)addr, max - pos,
+ iter);
else
len = iov_iter_zero(max - pos, iter);
@@ -268,11 +269,13 @@ static int dax_load_hole(struct address_space *mapping, struct page *page,
static int copy_user_bh(struct page *to, struct buffer_head *bh,
unsigned blkbits, unsigned long vaddr)
{
- void *vfrom, *vto;
+ void __pmem *vfrom;
+ void *vto;
+
if (dax_get_addr(bh, &vfrom, blkbits) < 0)
return -EIO;
vto = kmap_atomic(to);
- copy_user_page(vto, vfrom, vaddr, to);
+ copy_user_page(vto, (void __force *)vfrom, vaddr, to);
kunmap_atomic(vto);
return 0;
}
@@ -283,7 +286,7 @@ static int dax_insert_mapping(struct inode *inode, struct buffer_head *bh,
struct address_space *mapping = inode->i_mapping;
sector_t sector = bh->b_blocknr << (inode->i_blkbits - 9);
unsigned long vaddr = (unsigned long)vmf->virtual_address;
- void *addr;
+ void __pmem *addr;
unsigned long pfn;
pgoff_t size;
int error;
@@ -312,7 +315,7 @@ static int dax_insert_mapping(struct inode *inode, struct buffer_head *bh,
}
if (buffer_unwritten(bh) || buffer_new(bh)) {
- clear_pmem((void __pmem *)addr, PAGE_SIZE);
+ clear_pmem(addr, PAGE_SIZE);
wmb_pmem();
}
@@ -548,11 +551,11 @@ int dax_zero_page_range(struct inode *inode, loff_t from, unsigned length,
if (err < 0)
return err;
if (buffer_written(&bh)) {
- void *addr;
+ void __pmem *addr;
err = dax_get_addr(&bh, &addr, inode->i_blkbits);
if (err < 0)
return err;
- clear_pmem((void __pmem *)addr + offset, length);
+ clear_pmem(addr + offset, length);
wmb_pmem();
}
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index d4068c17d0df..c401ecdff9cb 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -1555,8 +1555,8 @@ struct block_device_operations {
int (*rw_page)(struct block_device *, sector_t, struct page *, int rw);
int (*ioctl) (struct block_device *, fmode_t, unsigned, unsigned long);
int (*compat_ioctl) (struct block_device *, fmode_t, unsigned, unsigned long);
- long (*direct_access)(struct block_device *, sector_t,
- void **, unsigned long *pfn, long size);
+ long (*direct_access)(struct block_device *, sector_t, void __pmem **,
+ unsigned long *pfn, long size);
unsigned int (*check_events) (struct gendisk *disk,
unsigned int clearing);
/* ->media_changed() is DEPRECATED, use ->check_events() instead */
@@ -1574,8 +1574,8 @@ extern int __blkdev_driver_ioctl(struct block_device *, fmode_t, unsigned int,
extern int bdev_read_page(struct block_device *, sector_t, struct page *);
extern int bdev_write_page(struct block_device *, sector_t, struct page *,
struct writeback_control *);
-extern long bdev_direct_access(struct block_device *, sector_t, void **addr,
- unsigned long *pfn, long size);
+extern long bdev_direct_access(struct block_device *, sector_t,
+ void __pmem **addr, unsigned long *pfn, long size);
#else /* CONFIG_BLOCK */
struct block_device;
--
cgit v1.2.3-70-g09d2
From cb389b9c0e00c30c9daf20287f7d91e2466edbb1 Mon Sep 17 00:00:00 2001
From: Dan Williams <dan.j.williams@intel.com>
Date: Fri, 7 Aug 2015 17:41:00 -0400
Subject: dax: drop size parameter to ->direct_access()
None of the implementations currently use it. The common
bdev_direct_access() entry point handles all the size checks before
calling ->direct_access().
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
arch/powerpc/sysdev/axonram.c | 2 +-
drivers/block/brd.c | 6 +-----
drivers/nvdimm/pmem.c | 2 +-
drivers/s390/block/dcssblk.c | 4 ++--
fs/block_dev.c | 2 +-
include/linux/blkdev.h | 2 +-
6 files changed, 7 insertions(+), 11 deletions(-)
(limited to 'fs/block_dev.c')
diff --git a/arch/powerpc/sysdev/axonram.c b/arch/powerpc/sysdev/axonram.c
index a2be2a66dab6..4419c84ac15a 100644
--- a/arch/powerpc/sysdev/axonram.c
+++ b/arch/powerpc/sysdev/axonram.c
@@ -141,7 +141,7 @@ axon_ram_make_request(struct request_queue *queue, struct bio *bio)
*/
static long
axon_ram_direct_access(struct block_device *device, sector_t sector,
- void __pmem **kaddr, unsigned long *pfn, long size)
+ void __pmem **kaddr, unsigned long *pfn)
{
struct axon_ram_bank *bank = device->bd_disk->private_data;
loff_t offset = (loff_t)sector << AXON_RAM_SECTOR_SHIFT;
diff --git a/drivers/block/brd.c b/drivers/block/brd.c
index c96402fd1560..03c45c41bdfa 100644
--- a/drivers/block/brd.c
+++ b/drivers/block/brd.c
@@ -371,7 +371,7 @@ static int brd_rw_page(struct block_device *bdev, sector_t sector,
#ifdef CONFIG_BLK_DEV_RAM_DAX
static long brd_direct_access(struct block_device *bdev, sector_t sector,
- void __pmem **kaddr, unsigned long *pfn, long size)
+ void __pmem **kaddr, unsigned long *pfn)
{
struct brd_device *brd = bdev->bd_disk->private_data;
struct page *page;
@@ -384,10 +384,6 @@ static long brd_direct_access(struct block_device *bdev, sector_t sector,
*kaddr = (void __pmem *)page_address(page);
*pfn = page_to_pfn(page);
- /*
- * TODO: If size > PAGE_SIZE, we could look to see if the next page in
- * the file happens to be mapped to the next page of physical RAM.
- */
return PAGE_SIZE;
}
#else
diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c
index f3b629779266..3b5b9cb758b6 100644
--- a/drivers/nvdimm/pmem.c
+++ b/drivers/nvdimm/pmem.c
@@ -92,7 +92,7 @@ static int pmem_rw_page(struct block_device *bdev, sector_t sector,
}
static long pmem_direct_access(struct block_device *bdev, sector_t sector,
- void __pmem **kaddr, unsigned long *pfn, long size)
+ void __pmem **kaddr, unsigned long *pfn)
{
struct pmem_device *pmem = bdev->bd_disk->private_data;
size_t offset = sector << 9;
diff --git a/drivers/s390/block/dcssblk.c b/drivers/s390/block/dcssblk.c
index 2c5a397b9f3e..8c027a9e4e8a 100644
--- a/drivers/s390/block/dcssblk.c
+++ b/drivers/s390/block/dcssblk.c
@@ -29,7 +29,7 @@ static int dcssblk_open(struct block_device *bdev, fmode_t mode);
static void dcssblk_release(struct gendisk *disk, fmode_t mode);
static void dcssblk_make_request(struct request_queue *q, struct bio *bio);
static long dcssblk_direct_access(struct block_device *bdev, sector_t secnum,
- void __pmem **kaddr, unsigned long *pfn, long size);
+ void __pmem **kaddr, unsigned long *pfn);
static char dcssblk_segments[DCSSBLK_PARM_LEN] = "\0";
@@ -879,7 +879,7 @@ fail:
static long
dcssblk_direct_access (struct block_device *bdev, sector_t secnum,
- void __pmem **kaddr, unsigned long *pfn, long size)
+ void __pmem **kaddr, unsigned long *pfn)
{
struct dcssblk_dev_info *dev_info;
unsigned long offset, dev_sz;
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 2345a9870e2c..3831e5691b32 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -462,7 +462,7 @@ long bdev_direct_access(struct block_device *bdev, sector_t sector,
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);
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index c401ecdff9cb..c22064f326b2 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -1556,7 +1556,7 @@ struct block_device_operations {
int (*ioctl) (struct block_device *, fmode_t, unsigned, unsigned long);
int (*compat_ioctl) (struct block_device *, fmode_t, unsigned, unsigned long);
long (*direct_access)(struct block_device *, sector_t, void __pmem **,
- unsigned long *pfn, long size);
+ unsigned long *pfn);
unsigned int (*check_events) (struct gendisk *disk,
unsigned int clearing);
/* ->media_changed() is DEPRECATED, use ->check_events() instead */
--
cgit v1.2.3-70-g09d2
From c94c2acf84dc16cf4b989bb0bc849785b7ff52f5 Mon Sep 17 00:00:00 2001
From: Matthew Wilcox <willy@linux.intel.com>
Date: Tue, 8 Sep 2015 14:58:40 -0700
Subject: dax: move DAX-related functions to a new header
In order to handle the !CONFIG_TRANSPARENT_HUGEPAGES case, we need to
return VM_FAULT_FALLBACK from the inlined dax_pmd_fault(), which is
defined in linux/mm.h. Given that we don't want to include <linux/mm.h>
in <linux/fs.h>, the easiest solution is to move the DAX-related
functions to a new header, <linux/dax.h>. We could also have moved
VM_FAULT_* definitions to a new header, or a different header that isn't
quite such a boil-the-ocean header as <linux/mm.h>, but this felt like
the best option.
Signed-off-by: Matthew Wilcox <willy@linux.intel.com>
Cc: Hillf Danton <dhillf@gmail.com>
Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Cc: Theodore Ts'o <tytso@mit.edu>
Cc: Jan Kara <jack@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
fs/block_dev.c | 1 +
fs/ext2/file.c | 1 +
fs/ext2/inode.c | 1 +
fs/ext4/file.c | 1 +
fs/ext4/indirect.c | 1 +
fs/ext4/inode.c | 1 +
fs/xfs/xfs_buf.h | 1 +
include/linux/dax.h | 21 +++++++++++++++++++++
include/linux/fs.h | 14 --------------
9 files changed, 28 insertions(+), 14 deletions(-)
create mode 100644 include/linux/dax.h
(limited to 'fs/block_dev.c')
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 33b813e04f79..28cc525b8d59 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -28,6 +28,7 @@
#include <linux/namei.h>
#include <linux/log2.h>
#include <linux/cleancache.h>
+#include <linux/dax.h>
#include <asm/uaccess.h>
#include "internal.h"
diff --git a/fs/ext2/file.c b/fs/ext2/file.c
index 3b57c9f83c9b..db4c299b7cf6 100644
--- a/fs/ext2/file.c
+++ b/fs/ext2/file.c
@@ -20,6 +20,7 @@
#include <linux/time.h>
#include <linux/pagemap.h>
+#include <linux/dax.h>
#include <linux/quotaops.h>
#include "ext2.h"
#include "xattr.h"
diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c
index a3a404c5df2e..c60a248c640c 100644
--- a/fs/ext2/inode.c
+++ b/fs/ext2/inode.c
@@ -25,6 +25,7 @@
#include <linux/time.h>
#include <linux/highuid.h>
#include <linux/pagemap.h>
+#include <linux/dax.h>
#include <linux/quotaops.h>
#include <linux/writeback.h>
#include <linux/buffer_head.h>
diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index bc313ac5d3fa..f8a631047379 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -22,6 +22,7 @@
#include <linux/fs.h>
#include <linux/mount.h>
#include <linux/path.h>
+#include <linux/dax.h>
#include <linux/quotaops.h>
#include <linux/pagevec.h>
#include <linux/uio.h>
diff --git a/fs/ext4/indirect.c b/fs/ext4/indirect.c
index 4f6ac499f09e..2468261748b2 100644
--- a/fs/ext4/indirect.c
+++ b/fs/ext4/indirect.c
@@ -22,6 +22,7 @@
#include "ext4_jbd2.h"
#include "truncate.h"
+#include <linux/dax.h>
#include <linux/uio.h>
#include <trace/events/ext4.h>
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 29f1af7c2cab..5ebcc7683a5c 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -22,6 +22,7 @@
#include <linux/time.h>
#include <linux/highuid.h>
#include <linux/pagemap.h>
+#include <linux/dax.h>
#include <linux/quotaops.h>
#include <linux/string.h>
#include <linux/buffer_head.h>
diff --git a/fs/xfs/xfs_buf.h b/fs/xfs/xfs_buf.h
index 331c1ccf8264..c79b717d9b88 100644
--- a/fs/xfs/xfs_buf.h
+++ b/fs/xfs/xfs_buf.h
@@ -23,6 +23,7 @@
#include <linux/spinlock.h>
#include <linux/mm.h>
#include <linux/fs.h>
+#include <linux/dax.h>
#include <linux/buffer_head.h>
#include <linux/uio.h>
#include <linux/list_lru.h>
diff --git a/include/linux/dax.h b/include/linux/dax.h
new file mode 100644
index 000000000000..4f27d3dbf6e8
--- /dev/null
+++ b/include/linux/dax.h
@@ -0,0 +1,21 @@
+#ifndef _LINUX_DAX_H
+#define _LINUX_DAX_H
+
+#include <linux/fs.h>
+#include <linux/mm.h>
+#include <asm/pgtable.h>
+
+ssize_t dax_do_io(struct kiocb *, struct inode *, struct iov_iter *, loff_t,
+ get_block_t, dio_iodone_t, int flags);
+int dax_clear_blocks(struct inode *, sector_t block, long size);
+int dax_zero_page_range(struct inode *, loff_t from, unsigned len, get_block_t);
+int dax_truncate_page(struct inode *, loff_t from, get_block_t);
+int dax_fault(struct vm_area_struct *, struct vm_fault *, get_block_t,
+ dax_iodone_t);
+int __dax_fault(struct vm_area_struct *, struct vm_fault *, get_block_t,
+ dax_iodone_t);
+int dax_pfn_mkwrite(struct vm_area_struct *, struct vm_fault *);
+#define dax_mkwrite(vma, vmf, gb, iod) dax_fault(vma, vmf, gb, iod)
+#define __dax_mkwrite(vma, vmf, gb, iod) __dax_fault(vma, vmf, gb, iod)
+
+#endif
diff --git a/include/linux/fs.h b/include/linux/fs.h
index b2f9b9c25e41..72d8a844c692 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -52,7 +52,6 @@ struct swap_info_struct;
struct seq_file;
struct workqueue_struct;
struct iov_iter;
-struct vm_fault;
extern void __init inode_init(void);
extern void __init inode_init_early(void);
@@ -2678,19 +2677,6 @@ extern loff_t fixed_size_llseek(struct file *file, loff_t offset,
extern int generic_file_open(struct inode * inode, struct file * filp);
extern int nonseekable_open(struct inode * inode, struct file * filp);
-ssize_t dax_do_io(struct kiocb *, struct inode *, struct iov_iter *, loff_t,
- get_block_t, dio_iodone_t, int flags);
-int dax_clear_blocks(struct inode *, sector_t block, long size);
-int dax_zero_page_range(struct inode *, loff_t from, unsigned len, get_block_t);
-int dax_truncate_page(struct inode *, loff_t from, get_block_t);
-int dax_fault(struct vm_area_struct *, struct vm_fault *, get_block_t,
- dax_iodone_t);
-int __dax_fault(struct vm_area_struct *, struct vm_fault *, get_block_t,
- dax_iodone_t);
-int dax_pfn_mkwrite(struct vm_area_struct *, struct vm_fault *);
-#define dax_mkwrite(vma, vmf, gb, iod) dax_fault(vma, vmf, gb, iod)
-#define __dax_mkwrite(vma, vmf, gb, iod) __dax_fault(vma, vmf, gb, iod)
-
#ifdef CONFIG_BLOCK
typedef void (dio_submit_t)(int rw, struct bio *bio, struct inode *inode,
loff_t file_offset);
--
cgit v1.2.3-70-g09d2