Merge branch 'hwpoison' of git://git.kernel.org/pub/scm/linux/kernel/git/ak/linux-mce-2.6

* 'hwpoison' of git://git.kernel.org/pub/scm/linux/kernel/git/ak/linux-mce-2.6: (21 commits)
  HWPOISON: Enable error_remove_page on btrfs
  HWPOISON: Add simple debugfs interface to inject hwpoison on arbitary PFNs
  HWPOISON: Add madvise() based injector for hardware poisoned pages v4
  HWPOISON: Enable error_remove_page for NFS
  HWPOISON: Enable .remove_error_page for migration aware file systems
  HWPOISON: The high level memory error handler in the VM v7
  HWPOISON: Add PR_MCE_KILL prctl to control early kill behaviour per process
  HWPOISON: shmem: call set_page_dirty() with locked page
  HWPOISON: Define a new error_remove_page address space op for async truncation
  HWPOISON: Add invalidate_inode_page
  HWPOISON: Refactor truncate to allow direct truncating of page v2
  HWPOISON: check and isolate corrupted free pages v2
  HWPOISON: Handle hardware poisoned pages in try_to_unmap
  HWPOISON: Use bitmask/action code for try_to_unmap behaviour
  HWPOISON: x86: Add VM_FAULT_HWPOISON handling to x86 page fault handler v2
  HWPOISON: Add poison check to page fault handling
  HWPOISON: Add basic support for poisoned pages in fault handler v3
  HWPOISON: Add new SIGBUS error codes for hardware poison signals
  HWPOISON: Add support for poison swap entries v2
  HWPOISON: Export some rmap vma locking to outside world
  ...

1 files changed, 52 insertions, 20 deletions

diff --git a/mm/truncate.c b/mm/truncate.c
index ccc3ecf7cb98..a17b3977cfdf 100644
--- a/mm/truncate.c
+++ b/mm/truncate.c
@@ -93,11 +93,11 @@ EXPORT_SYMBOL(cancel_dirty_page);
  * its lock, b) when a concurrent invalidate_mapping_pages got there first and
  * c) when tmpfs swizzles a page between a tmpfs inode and swapper_space.
  */
-static void
+static int
 truncate_complete_page(struct address_space *mapping, struct page *page)
 {
         if (page->mapping != mapping)
-                return;
+                return -EIO;
 
         if (page_has_private(page))
                 do_invalidatepage(page, 0);
@@ -108,6 +108,7 @@ truncate_complete_page(struct address_space *mapping, struct page *page)
         remove_from_page_cache(page);
         ClearPageMappedToDisk(page);
         page_cache_release(page);       /* pagecache ref */
+        return 0;
 }
 
 /*
@@ -135,6 +136,51 @@ invalidate_complete_page(struct address_space *mapping, struct page *page)
         return ret;
 }
 
+int truncate_inode_page(struct address_space *mapping, struct page *page)
+{
+        if (page_mapped(page)) {
+                unmap_mapping_range(mapping,
+                                   (loff_t)page->index << PAGE_CACHE_SHIFT,
+                                   PAGE_CACHE_SIZE, 0);
+        }
+        return truncate_complete_page(mapping, 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.
+ *
+ * Returns 1 if the page is successfully invalidated, otherwise 0.
+ */
+int invalidate_inode_page(struct page *page)
+{
+        struct address_space *mapping = page_mapping(page);
+        if (!mapping)
+                return 0;
+        if (PageDirty(page) || PageWriteback(page))
+                return 0;
+        if (page_mapped(page))
+                return 0;
+        return invalidate_complete_page(mapping, page);
+}
+
 /**
  * truncate_inode_pages - truncate range of pages specified by start & end byte offsets
  * @mapping: mapping to truncate
@@ -196,12 +242,7 @@ void truncate_inode_pages_range(struct address_space *mapping,
                                 unlock_page(page);
                                 continue;
                         }
-                        if (page_mapped(page)) {
-                                unmap_mapping_range(mapping,
-                                  (loff_t)page_index<<PAGE_CACHE_SHIFT,
-                                  PAGE_CACHE_SIZE, 0);
-                        }
-                        truncate_complete_page(mapping, page);
+                        truncate_inode_page(mapping, page);
                         unlock_page(page);
                 }
                 pagevec_release(&pvec);
@@ -238,15 +279,10 @@ void truncate_inode_pages_range(struct address_space *mapping,
                                 break;
                         lock_page(page);
                         wait_on_page_writeback(page);
-                        if (page_mapped(page)) {
-                                unmap_mapping_range(mapping,
-                                  (loff_t)page->index<<PAGE_CACHE_SHIFT,
-                                  PAGE_CACHE_SIZE, 0);
-                        }
+                        truncate_inode_page(mapping, page);
                         if (page->index > next)
                                 next = page->index;
                         next++;
-                        truncate_complete_page(mapping, page);
                         unlock_page(page);
                 }
                 pagevec_release(&pvec);
@@ -311,12 +347,8 @@ unsigned long invalidate_mapping_pages(struct address_space *mapping,
                         if (lock_failed)
                                 continue;
 
-                        if (PageDirty(page) || PageWriteback(page))
-                                goto unlock;
-                        if (page_mapped(page))
-                                goto unlock;
-                        ret += invalidate_complete_page(mapping, page);
-unlock:
+                        ret += invalidate_inode_page(page);
+
                         unlock_page(page);
                         if (next > end)
                                 break;