diff options
| author | Jan Kara <jack@suse.cz> | 2016-12-14 15:07:50 -0800 |
|---|---|---|
| committer | Linus Torvalds <torvalds@linux-foundation.org> | 2016-12-14 16:04:09 -0800 |
| commit | 2f89dc12a25ddf995b9acd7b6543fe892e3473d6 (patch) | |
| tree | d162312aa8bdcb6602a9c30dd5810c0f2f8e0a16 | |
| parent | a6abc2c0e77b16480f4d2c1eb7925e5287ae1526 (diff) | |
| download | linux-2f89dc12a25ddf995b9acd7b6543fe892e3473d6.tar.gz | |
dax: protect PTE modification on WP fault by radix tree entry lock
Currently PTE gets updated in wp_pfn_shared() after dax_pfn_mkwrite()
has released corresponding radix tree entry lock. When we want to
writeprotect PTE on cache flush, we need PTE modification to happen
under radix tree entry lock to ensure consistent updates of PTE and
radix tree (standard faults use page lock to ensure this consistency).
So move update of PTE bit into dax_pfn_mkwrite().
Link: http://lkml.kernel.org/r/1479460644-25076-20-git-send-email-jack@suse.cz
Signed-off-by: Jan Kara <jack@suse.cz>
Reviewed-by: Ross Zwisler <ross.zwisler@linux.intel.com>
Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
| -rw-r--r-- | fs/dax.c | 22 | ||||
| -rw-r--r-- | mm/memory.c | 2 |
2 files changed, 17 insertions, 7 deletions
diff --git a/fs/dax.c b/fs/dax.c index df5c0daba69813..cf7a20a5858b6f 100644 --- a/fs/dax.c +++ b/fs/dax.c @@ -783,17 +783,27 @@ int dax_pfn_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf) { struct file *file = vma->vm_file; struct address_space *mapping = file->f_mapping; - void *entry; + void *entry, **slot; pgoff_t index = vmf->pgoff; spin_lock_irq(&mapping->tree_lock); - entry = get_unlocked_mapping_entry(mapping, index, NULL); - if (!entry || !radix_tree_exceptional_entry(entry)) - goto out; + entry = get_unlocked_mapping_entry(mapping, index, &slot); + if (!entry || !radix_tree_exceptional_entry(entry)) { + if (entry) + put_unlocked_mapping_entry(mapping, index, entry); + spin_unlock_irq(&mapping->tree_lock); + return VM_FAULT_NOPAGE; + } radix_tree_tag_set(&mapping->page_tree, index, PAGECACHE_TAG_DIRTY); - put_unlocked_mapping_entry(mapping, index, entry); -out: + entry = lock_slot(mapping, slot); spin_unlock_irq(&mapping->tree_lock); + /* + * If we race with somebody updating the PTE and finish_mkwrite_fault() + * fails, we don't care. We need to return VM_FAULT_NOPAGE and retry + * the fault in either case. + */ + finish_mkwrite_fault(vmf); + put_locked_mapping_entry(mapping, index, entry); return VM_FAULT_NOPAGE; } EXPORT_SYMBOL_GPL(dax_pfn_mkwrite); diff --git a/mm/memory.c b/mm/memory.c index edd899d0decb45..57d0bd1bd2c4c4 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -2315,7 +2315,7 @@ static int wp_pfn_shared(struct vm_fault *vmf) pte_unmap_unlock(vmf->pte, vmf->ptl); vmf->flags |= FAULT_FLAG_MKWRITE; ret = vma->vm_ops->pfn_mkwrite(vma, vmf); - if (ret & VM_FAULT_ERROR) + if (ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE)) return ret; return finish_mkwrite_fault(vmf); } |