HWPOISON: Define a new error_remove_page address space op for async truncation

Truncating metadata pages is not safe right now before
we haven't audited all file systems.

To enable truncation only for data address space define
a new address_space callback error_remove_page.

This is used for memory_failure.c memory error handling.

This can be then set to truncate_inode_page()

This patch just defines the new operation and adds documentation.

Callers and users come in followon patches.

Signed-off-by: Andi Kleen <ak@linux.intel.com>

4 files changed, 26 insertions, 0 deletions

diff --git a/Documentation/filesystems/vfs.txt b/Documentation/filesystems/vfs.txt
index f49eecf2e573..623f094c9d8d 100644
--- a/Documentation/filesystems/vfs.txt
+++ b/Documentation/filesystems/vfs.txt
@@ -536,6 +536,7 @@ struct address_space_operations {
 	/* migrate the contents of a page to the specified target */
 	int (*migratepage) (struct page *, struct page *);
 	int (*launder_page) (struct page *);
+	int (*error_remove_page) (struct mapping *mapping, struct page *page);
 };
 
   writepage: called by the VM to write a dirty page to backing store.
@@ -694,6 +695,12 @@ struct address_space_operations {
   	prevent redirtying the page, it is kept locked during the whole
 	operation.
 
+  error_remove_page: normally set to generic_error_remove_page if truncation
+	is ok for this address space. Used for memory failure handling.
+	Setting this implies you deal with pages going away under you,
+	unless you have them locked or reference counts increased.
+
+
 The File Object
 ===============
 
diff --git a/include/linux/fs.h b/include/linux/fs.h
index b21cf6b9c80b..4f47afd37647 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -595,6 +595,7 @@ struct address_space_operations {
 	int (*launder_page) (struct page *);
 	int (*is_partially_uptodate) (struct page *, read_descriptor_t *,
 					unsigned long);
+	int (*error_remove_page)(struct address_space *, struct page *);
 };
 
 /*
diff --git a/include/linux/mm.h b/include/linux/mm.h
index b05bbde0296d..a16018f7d61c 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -795,6 +795,7 @@ extern int vmtruncate(struct inode * inode, loff_t offset);
 extern int vmtruncate_range(struct inode * inode, loff_t offset, loff_t end);
 
 int truncate_inode_page(struct address_space *mapping, struct page *page);
+int generic_error_remove_page(struct address_space *mapping, struct page *page);
 
 int invalidate_inode_page(struct page *page);
 
diff --git a/mm/truncate.c b/mm/truncate.c
index ea132f7ea2d2..a17b3977cfdf 100644
--- a/mm/truncate.c
+++ b/mm/truncate.c
@@ -147,6 +147,23 @@ int truncate_inode_page(struct address_space *mapping, struct page *page)
 }
 
 /*
+ * Used to get rid of pages on hardware memory corruption.
+ */
+int generic_error_remove_page(struct address_space *mapping, struct page *page)
+{
+	if (!mapping)
+		return -EINVAL;
+	/*
+	 * Only punch for normal data pages for now.
+	 * Handling other types like directories would need more auditing.
+	 */
+	if (!S_ISREG(mapping->host->i_mode))
+		return -EIO;
+	return truncate_inode_page(mapping, page);
+}
+EXPORT_SYMBOL(generic_error_remove_page);
+
+/*
  * Safely invalidate one page from its pagecache mapping.
  * It only drops clean, unused pages. The page must be locked.
  *