Commit 13e451fd authored by Jan Kara's avatar Jan Kara Committed by Linus Torvalds

dax: fix data corruption when fault races with write

Currently DAX read fault can race with write(2) in the following way:

CPU1 - write(2)			CPU2 - read fault
				  ->iomap_begin() - sees hole
    ->iomap_begin - allocates blocks
        - there's nothing to invalidate
				  - we add zero page in the radix tree
				    and map it to page tables

The result is that hole page is mapped into page tables (and thus zeros
are seen in mmap) while file has data written in that place.

Fix the problem by locking exception entry before mapping blocks for the
fault.  That way we are sure invalidate_inode_pages2_range() call for
racing write will either block on entry lock waiting for the fault to
finish (and unmap stale page tables after that) or read fault will see
already allocated blocks by write(2).

Fixes: 9f141d6e
Link: default avatarJan Kara <>
Reviewed-by: default avatarRoss Zwisler <>
Cc: Dan Williams <>
Cc: <>
Signed-off-by: default avatarAndrew Morton <>
Signed-off-by: default avatarLinus Torvalds <>
parent fb26a1cb
......@@ -1148,6 +1148,12 @@ static int dax_iomap_pte_fault(struct vm_fault *vmf,
if ((vmf->flags & FAULT_FLAG_WRITE) && !vmf->cow_page)
flags |= IOMAP_WRITE;
entry = grab_mapping_entry(mapping, vmf->pgoff, 0);
if (IS_ERR(entry)) {
vmf_ret = dax_fault_return(PTR_ERR(entry));
goto out;
* Note that we don't bother to use iomap_apply here: DAX required
* the file system block size to be equal the page size, which means
......@@ -1156,17 +1162,11 @@ static int dax_iomap_pte_fault(struct vm_fault *vmf,
error = ops->iomap_begin(inode, pos, PAGE_SIZE, flags, &iomap);
if (error) {
vmf_ret = dax_fault_return(error);
goto out;
goto unlock_entry;
if (WARN_ON_ONCE(iomap.offset + iomap.length < pos + PAGE_SIZE)) {
vmf_ret = dax_fault_return(-EIO); /* fs corruption? */
goto finish_iomap;
entry = grab_mapping_entry(mapping, vmf->pgoff, 0);
if (IS_ERR(entry)) {
vmf_ret = dax_fault_return(PTR_ERR(entry));
goto finish_iomap;
error = -EIO; /* fs corruption? */
goto error_finish_iomap;
sector = dax_iomap_sector(&iomap, pos);
......@@ -1188,13 +1188,13 @@ static int dax_iomap_pte_fault(struct vm_fault *vmf,
if (error)
goto error_unlock_entry;
goto error_finish_iomap;
vmf_ret = finish_fault(vmf);
if (!vmf_ret)
vmf_ret = VM_FAULT_DONE_COW;
goto unlock_entry;
goto finish_iomap;
switch (iomap.type) {
......@@ -1214,7 +1214,7 @@ static int dax_iomap_pte_fault(struct vm_fault *vmf,
if (!(vmf->flags & FAULT_FLAG_WRITE)) {
vmf_ret = dax_load_hole(mapping, &entry, vmf);
goto unlock_entry;
goto finish_iomap;
......@@ -1223,10 +1223,8 @@ static int dax_iomap_pte_fault(struct vm_fault *vmf,
vmf_ret = dax_fault_return(error) | major;
put_locked_mapping_entry(mapping, vmf->pgoff, entry);
if (ops->iomap_end) {
int copied = PAGE_SIZE;
......@@ -1241,7 +1239,9 @@ static int dax_iomap_pte_fault(struct vm_fault *vmf,
ops->iomap_end(inode, pos, PAGE_SIZE, copied, flags, &iomap);
put_locked_mapping_entry(mapping, vmf->pgoff, entry);
trace_dax_pte_fault_done(inode, vmf, vmf_ret);
return vmf_ret;
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment