diff mbox series

[10/11] ceph: Fix race between hole punch and page fault

Message ID 20210512134631.4053-10-jack@suse.cz (mailing list archive)
State New
Headers show
Series fs: Hole punch vs page cache filling races | expand

Commit Message

Jan Kara May 12, 2021, 1:46 p.m. UTC
Ceph has a following race between hole punching and page fault:

CPU1                                  CPU2
ceph_fallocate()
  ...
  ceph_zero_pagecache_range()
                                      ceph_filemap_fault()
                                        faults in page in the range being
                                        punched
  ceph_zero_objects()

And now we have a page in punched range with invalid data. Fix the
problem by using mapping->invalidate_lock similarly to other
filesystems. Note that using invalidate_lock also fixes a similar race
wrt ->readpage().

CC: Jeff Layton <jlayton@kernel.org>
CC: ceph-devel@vger.kernel.org
Signed-off-by: Jan Kara <jack@suse.cz>
---
 fs/ceph/addr.c | 9 ++++++---
 fs/ceph/file.c | 2 ++
 2 files changed, 8 insertions(+), 3 deletions(-)

Comments

Jeff Layton May 12, 2021, 3:19 p.m. UTC | #1
On Wed, 2021-05-12 at 15:46 +0200, Jan Kara wrote:
> Ceph has a following race between hole punching and page fault:
> 
> CPU1                                  CPU2
> ceph_fallocate()
>   ...
>   ceph_zero_pagecache_range()
>                                       ceph_filemap_fault()
>                                         faults in page in the range being
>                                         punched
>   ceph_zero_objects()
> 
> And now we have a page in punched range with invalid data. Fix the
> problem by using mapping->invalidate_lock similarly to other
> filesystems. Note that using invalidate_lock also fixes a similar race
> wrt ->readpage().
> 
> CC: Jeff Layton <jlayton@kernel.org>
> CC: ceph-devel@vger.kernel.org
> Signed-off-by: Jan Kara <jack@suse.cz>
> ---
>  fs/ceph/addr.c | 9 ++++++---
>  fs/ceph/file.c | 2 ++
>  2 files changed, 8 insertions(+), 3 deletions(-)
> 
> diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
> index c1570fada3d8..6d868faf97b5 100644
> --- a/fs/ceph/addr.c
> +++ b/fs/ceph/addr.c
> @@ -1401,9 +1401,11 @@ static vm_fault_t ceph_filemap_fault(struct vm_fault *vmf)
>  		ret = VM_FAULT_SIGBUS;
>  	} else {
>  		struct address_space *mapping = inode->i_mapping;
> -		struct page *page = find_or_create_page(mapping, 0,
> -						mapping_gfp_constraint(mapping,
> -						~__GFP_FS));
> +		struct page *page;
> +
> +		down_read(&mapping->invalidate_lock);
> +		page = find_or_create_page(mapping, 0,
> +				mapping_gfp_constraint(mapping, ~__GFP_FS));
>  		if (!page) {
>  			ret = VM_FAULT_OOM;
>  			goto out_inline;
> @@ -1424,6 +1426,7 @@ static vm_fault_t ceph_filemap_fault(struct vm_fault *vmf)
>  		vmf->page = page;
>  		ret = VM_FAULT_MAJOR | VM_FAULT_LOCKED;
>  out_inline:
> +		up_read(&mapping->invalidate_lock);
>  		dout("filemap_fault %p %llu read inline data ret %x\n",
>  		     inode, off, ret);
>  	}
> diff --git a/fs/ceph/file.c b/fs/ceph/file.c
> index 77fc037d5beb..91693d8b458e 100644
> --- a/fs/ceph/file.c
> +++ b/fs/ceph/file.c
> @@ -2083,6 +2083,7 @@ static long ceph_fallocate(struct file *file, int mode,
>  	if (ret < 0)
>  		goto unlock;
>  
> +	down_write(&inode->i_mapping->invalidate_lock);
>  	ceph_zero_pagecache_range(inode, offset, length);
>  	ret = ceph_zero_objects(inode, offset, length);
>  
> @@ -2095,6 +2096,7 @@ static long ceph_fallocate(struct file *file, int mode,
>  		if (dirty)
>  			__mark_inode_dirty(inode, dirty);
>  	}
> +	up_write(&inode->i_mapping->invalidate_lock);
>  
>  	ceph_put_cap_refs(ci, got);
>  unlock:

Assuming the basic concept is sound, then this looks reasonable. 

Reviewed-by: Jeff Layton <jlayton@kernel.org>
diff mbox series

Patch

diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
index c1570fada3d8..6d868faf97b5 100644
--- a/fs/ceph/addr.c
+++ b/fs/ceph/addr.c
@@ -1401,9 +1401,11 @@  static vm_fault_t ceph_filemap_fault(struct vm_fault *vmf)
 		ret = VM_FAULT_SIGBUS;
 	} else {
 		struct address_space *mapping = inode->i_mapping;
-		struct page *page = find_or_create_page(mapping, 0,
-						mapping_gfp_constraint(mapping,
-						~__GFP_FS));
+		struct page *page;
+
+		down_read(&mapping->invalidate_lock);
+		page = find_or_create_page(mapping, 0,
+				mapping_gfp_constraint(mapping, ~__GFP_FS));
 		if (!page) {
 			ret = VM_FAULT_OOM;
 			goto out_inline;
@@ -1424,6 +1426,7 @@  static vm_fault_t ceph_filemap_fault(struct vm_fault *vmf)
 		vmf->page = page;
 		ret = VM_FAULT_MAJOR | VM_FAULT_LOCKED;
 out_inline:
+		up_read(&mapping->invalidate_lock);
 		dout("filemap_fault %p %llu read inline data ret %x\n",
 		     inode, off, ret);
 	}
diff --git a/fs/ceph/file.c b/fs/ceph/file.c
index 77fc037d5beb..91693d8b458e 100644
--- a/fs/ceph/file.c
+++ b/fs/ceph/file.c
@@ -2083,6 +2083,7 @@  static long ceph_fallocate(struct file *file, int mode,
 	if (ret < 0)
 		goto unlock;
 
+	down_write(&inode->i_mapping->invalidate_lock);
 	ceph_zero_pagecache_range(inode, offset, length);
 	ret = ceph_zero_objects(inode, offset, length);
 
@@ -2095,6 +2096,7 @@  static long ceph_fallocate(struct file *file, int mode,
 		if (dirty)
 			__mark_inode_dirty(inode, dirty);
 	}
+	up_write(&inode->i_mapping->invalidate_lock);
 
 	ceph_put_cap_refs(ci, got);
 unlock: