On Wed, 28 Nov 2012, Jens Axboe wrote:
> On 2012-11-28 04:57, Mikulas Patocka wrote:
> >
> > This patch is wrong because you must check if the device is mapped while
> > holding bdev->bd_block_size_semaphore (because
> > bdev->bd_block_size_semaphore prevents new mappings from being created)
>
> No it doesn't. If you read the patch, that was moved to i_mmap_mutex.
Hmm, it was wrong before the patch and it is wrong after the patch too.
The problem is that ->mmap method doesn't do the actual mapping, the
caller of ->mmap (mmap_region) does it. So we must actually catch
mmap_region and protect it with the lock, not ->mmap.
Mikulas
---
Introduce a method to catch mmap_region
For block devices, we must prevent the device from being mapped while
block size is being changed.
This was implemented by catching the mmap method and taking
bd_block_size_semaphore in it.
The problem is that the generic_file_mmap method does almost nothing, it
only sets vma->vm_ops = &generic_file_vm_ops, all the hard work is done
by the caller, mmap_region. Consequently, locking the mmap method is
insufficient, to prevent the race condition. The race condition can
happen for example this way:
process 1:
Starts mapping a block device, it goes to mmap_region, calls
file->f_op->mmap (blkdev_mmap - that acquires and releases
bd_block_size_semaphore), and reschedule happens just after blkdev_mmap
returns.
process 2:
Changes block device size, goes into set_blocksize, acquires
percpu_down_write, calls mapping_mapped to test if the device is mapped
(it still isn't). Then, it reschedules.
process 1:
Continues in mmap_region, successfully finishes the mapping.
process 2:
Continues in set_blocksize, changes the block size while the block
device is mapped. (which is incorrect and may result in a crash or
misbehavior).
To fix this possible race condition, we need to catch the function that
does real mapping - mmap_region. This patch adds a new method,
file_operations->mmap_region. mmap_region calls the method
file_operations->mmap_region if it is non-NULL, otherwise, it calls
generic_mmap_region.
Signed-off-by: Mikulas Patocka <mpatocka@xxxxxxxxxx>
---
fs/block_dev.c | 12 ++++++++----
include/linux/fs.h | 4 ++++
include/linux/mm.h | 3 +++
mm/mmap.c | 10 ++++++++++
4 files changed, 25 insertions(+), 4 deletions(-)
Index: linux-3.7-rc7/include/linux/fs.h
===================================================================
--- linux-3.7-rc7.orig/include/linux/fs.h 2012-11-28 17:45:55.000000000 +0100
+++ linux-3.7-rc7/include/linux/fs.h 2012-11-28 18:02:45.000000000 +0100
@@ -27,6 +27,7 @@
#include <linux/lockdep.h>
#include <linux/percpu-rwsem.h>
#include <linux/blk_types.h>
+#include <linux/mm_types.h>
#include <asm/byteorder.h>
#include <uapi/linux/fs.h>
@@ -1528,6 +1529,9 @@ struct file_operations {
unsigned int (*poll) (struct file *, struct poll_table_struct *);
long (*unlocked_ioctl) (struct file *, unsigned int, unsigned long);
long (*compat_ioctl) (struct file *, unsigned int, unsigned long);
+ unsigned long (*mmap_region)(struct file *, unsigned long,
+ unsigned long, unsigned long, vm_flags_t,
+ unsigned long);
int (*mmap) (struct file *, struct vm_area_struct *);
int (*open) (struct inode *, struct file *);
int (*flush) (struct file *, fl_owner_t id);
Index: linux-3.7-rc7/include/linux/mm.h
===================================================================
--- linux-3.7-rc7.orig/include/linux/mm.h 2012-11-28 17:45:55.000000000 +0100
+++ linux-3.7-rc7/include/linux/mm.h 2012-11-28 17:47:12.000000000 +0100
@@ -1444,6 +1444,9 @@ extern unsigned long get_unmapped_area(s
extern unsigned long mmap_region(struct file *file, unsigned long addr,
unsigned long len, unsigned long flags,
vm_flags_t vm_flags, unsigned long pgoff);
+extern unsigned long generic_mmap_region(struct file *file, unsigned long addr,
+ unsigned long len, unsigned long flags,
+ vm_flags_t vm_flags, unsigned long pgoff);
extern unsigned long do_mmap_pgoff(struct file *, unsigned long,
unsigned long, unsigned long,
unsigned long, unsigned long);
Index: linux-3.7-rc7/mm/mmap.c
===================================================================
--- linux-3.7-rc7.orig/mm/mmap.c 2012-11-28 17:45:55.000000000 +0100
+++ linux-3.7-rc7/mm/mmap.c 2012-11-28 17:57:40.000000000 +0100
@@ -1244,6 +1244,16 @@ unsigned long mmap_region(struct file *f
unsigned long len, unsigned long flags,
vm_flags_t vm_flags, unsigned long pgoff)
{
+ if (file && file->f_op->mmap_region)
+ return file->f_op->mmap_region(file, addr, len, flags, vm_flags,
+ pgoff);
+ return generic_mmap_region(file, addr, len, flags, vm_flags, pgoff);
+}
+
+unsigned long generic_mmap_region(struct file *file, unsigned long addr,
+ unsigned long len, unsigned long flags,
+ vm_flags_t vm_flags, unsigned long pgoff)
+{
struct mm_struct *mm = current->mm;
struct vm_area_struct *vma, *prev;
int correct_wcount = 0;
Index: linux-3.7-rc7/fs/block_dev.c
===================================================================
--- linux-3.7-rc7.orig/fs/block_dev.c 2012-11-28 17:45:56.000000000 +0100
+++ linux-3.7-rc7/fs/block_dev.c 2012-11-28 17:47:12.000000000 +0100
@@ -1658,14 +1658,17 @@ ssize_t blkdev_aio_write(struct kiocb *i
}
EXPORT_SYMBOL_GPL(blkdev_aio_write);
-static int blkdev_mmap(struct file *file, struct vm_area_struct *vma)
+static unsigned long blkdev_mmap_region(struct file *file, unsigned long addr,
+ unsigned long len, unsigned long flags,
+ vm_flags_t vm_flags,
+ unsigned long pgoff)
{
- int ret;
+ unsigned long ret;
struct block_device *bdev = I_BDEV(file->f_mapping->host);
percpu_down_read(&bdev->bd_block_size_semaphore);
- ret = generic_file_mmap(file, vma);
+ ret = generic_mmap_region(file, addr, len, flags, vm_flags, pgoff);
percpu_up_read(&bdev->bd_block_size_semaphore);
@@ -1737,7 +1740,8 @@ const struct file_operations def_blk_fop
.write = do_sync_write,
.aio_read = blkdev_aio_read,
.aio_write = blkdev_aio_write,
- .mmap = blkdev_mmap,
+ .mmap_region = blkdev_mmap_region,
+ .mmap = generic_file_mmap,
.fsync = blkdev_fsync,
.unlocked_ioctl = block_ioctl,
#ifdef CONFIG_COMPAT
--
To unsubscribe from this list: send the line "unsubscribe linux-fsdevel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
