1 files changed, 82 insertions, 44 deletions

diff --git a/mm/filemap.c b/mm/filemap.c
index 72940fb38666..1bb007624b53 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -331,23 +331,14 @@ int filemap_flush(struct address_space *mapping)
 }
 EXPORT_SYMBOL(filemap_flush);
 
-/**
- * filemap_fdatawait_range - wait for writeback to complete
- * @mapping:		address space structure to wait for
- * @start_byte:		offset in bytes where the range starts
- * @end_byte:		offset in bytes where the range ends (inclusive)
- *
- * Walk the list of under-writeback pages of the given address space
- * in the given range and wait for all of them.
- */
-int filemap_fdatawait_range(struct address_space *mapping, loff_t start_byte,
-			    loff_t end_byte)
+static int __filemap_fdatawait_range(struct address_space *mapping,
+				     loff_t start_byte, loff_t end_byte)
 {
 	pgoff_t index = start_byte >> PAGE_CACHE_SHIFT;
 	pgoff_t end = end_byte >> PAGE_CACHE_SHIFT;
 	struct pagevec pvec;
 	int nr_pages;
-	int ret2, ret = 0;
+	int ret = 0;
 
 	if (end_byte < start_byte)
 		goto out;
@@ -374,6 +365,29 @@ int filemap_fdatawait_range(struct address_space *mapping, loff_t start_byte,
 		cond_resched();
 	}
 out:
+	return ret;
+}
+
+/**
+ * filemap_fdatawait_range - wait for writeback to complete
+ * @mapping:		address space structure to wait for
+ * @start_byte:		offset in bytes where the range starts
+ * @end_byte:		offset in bytes where the range ends (inclusive)
+ *
+ * Walk the list of under-writeback pages of the given address space
+ * in the given range and wait for all of them.  Check error status of
+ * the address space and return it.
+ *
+ * Since the error status of the address space is cleared by this function,
+ * callers are responsible for checking the return value and handling and/or
+ * reporting the error.
+ */
+int filemap_fdatawait_range(struct address_space *mapping, loff_t start_byte,
+			    loff_t end_byte)
+{
+	int ret, ret2;
+
+	ret = __filemap_fdatawait_range(mapping, start_byte, end_byte);
 	ret2 = filemap_check_errors(mapping);
 	if (!ret)
 		ret = ret2;
@@ -383,11 +397,38 @@ out:
 EXPORT_SYMBOL(filemap_fdatawait_range);
 
 /**
+ * filemap_fdatawait_keep_errors - wait for writeback without clearing errors
+ * @mapping: address space structure to wait for
+ *
+ * Walk the list of under-writeback pages of the given address space
+ * and wait for all of them.  Unlike filemap_fdatawait(), this function
+ * does not clear error status of the address space.
+ *
+ * Use this function if callers don't handle errors themselves.  Expected
+ * call sites are system-wide / filesystem-wide data flushers: e.g. sync(2),
+ * fsfreeze(8)
+ */
+void filemap_fdatawait_keep_errors(struct address_space *mapping)
+{
+	loff_t i_size = i_size_read(mapping->host);
+
+	if (i_size == 0)
+		return;
+
+	__filemap_fdatawait_range(mapping, 0, i_size - 1);
+}
+
+/**
  * filemap_fdatawait - wait for all under-writeback pages to complete
  * @mapping: address space structure to wait for
  *
  * Walk the list of under-writeback pages of the given address space
- * and wait for all of them.
+ * and wait for all of them.  Check error status of the address space
+ * and return it.
+ *
+ * Since the error status of the address space is cleared by this function,
+ * callers are responsible for checking the return value and handling and/or
+ * reporting the error.
  */
 int filemap_fdatawait(struct address_space *mapping)
 {
@@ -510,7 +551,7 @@ int replace_page_cache_page(struct page *old, struct page *new, gfp_t gfp_mask)
 			__inc_zone_page_state(new, NR_SHMEM);
 		spin_unlock_irqrestore(&mapping->tree_lock, flags);
 		mem_cgroup_end_page_stat(memcg);
-		mem_cgroup_migrate(old, new, true);
+		mem_cgroup_replace_page(old, new);
 		radix_tree_preload_end();
 		if (freepage)
 			freepage(old);
@@ -1681,7 +1722,7 @@ no_cached_page:
 			goto out;
 		}
 		error = add_to_page_cache_lru(page, mapping, index,
-					GFP_KERNEL & mapping_gfp_mask(mapping));
+				mapping_gfp_constraint(mapping, GFP_KERNEL));
 		if (error) {
 			page_cache_release(page);
 			if (error == -EEXIST) {
@@ -1783,7 +1824,7 @@ static int page_cache_read(struct file *file, pgoff_t offset)
 			return -ENOMEM;
 
 		ret = add_to_page_cache_lru(page, mapping, offset,
-				GFP_KERNEL & mapping_gfp_mask(mapping));
+				mapping_gfp_constraint(mapping, GFP_KERNEL));
 		if (ret == 0)
 			ret = mapping->a_ops->readpage(file, page);
 		else if (ret == -EEXIST)
@@ -1807,7 +1848,6 @@ static void do_sync_mmap_readahead(struct vm_area_struct *vma,
 				   struct file *file,
 				   pgoff_t offset)
 {
-	unsigned long ra_pages;
 	struct address_space *mapping = file->f_mapping;
 
 	/* If we don't want any read-ahead, don't bother */
@@ -1836,10 +1876,9 @@ static void do_sync_mmap_readahead(struct vm_area_struct *vma,
 	/*
 	 * mmap read-around
 	 */
-	ra_pages = max_sane_readahead(ra->ra_pages);
-	ra->start = max_t(long, 0, offset - ra_pages / 2);
-	ra->size = ra_pages;
-	ra->async_size = ra_pages / 4;
+	ra->start = max_t(long, 0, offset - ra->ra_pages / 2);
+	ra->size = ra->ra_pages;
+	ra->async_size = ra->ra_pages / 4;
 	ra_submit(ra, mapping, file);
 }
 
@@ -2473,6 +2512,26 @@ ssize_t generic_perform_write(struct file *file,
 						iov_iter_count(i));
 
 again:
+		/*
+		 * Bring in the user page that we will copy from _first_.
+		 * Otherwise there's a nasty deadlock on copying from the
+		 * same page as we're writing to, without it being marked
+		 * up-to-date.
+		 *
+		 * Not only is this an optimisation, but it is also required
+		 * to check that the address is actually valid, when atomic
+		 * usercopies are used, below.
+		 */
+		if (unlikely(iov_iter_fault_in_readable(i, bytes))) {
+			status = -EFAULT;
+			break;
+		}
+
+		if (fatal_signal_pending(current)) {
+			status = -EINTR;
+			break;
+		}
+
 		status = a_ops->write_begin(file, mapping, pos, bytes, flags,
 						&page, &fsdata);
 		if (unlikely(status < 0))
@@ -2480,17 +2539,8 @@ again:
 
 		if (mapping_writably_mapped(mapping))
 			flush_dcache_page(page);
-		/*
-		 * 'page' is now locked.  If we are trying to copy from a
-		 * mapping of 'page' in userspace, the copy might fault and
-		 * would need PageUptodate() to complete.  But, page can not be
-		 * made Uptodate without acquiring the page lock, which we hold.
-		 * Deadlock.  Avoid with pagefault_disable().  Fix up below with
-		 * iov_iter_fault_in_readable().
-		 */
-		pagefault_disable();
+
 		copied = iov_iter_copy_from_user_atomic(page, i, offset, bytes);
-		pagefault_enable();
 		flush_dcache_page(page);
 
 		status = a_ops->write_end(file, mapping, pos, bytes, copied,
@@ -2513,24 +2563,12 @@ again:
 			 */
 			bytes = min_t(unsigned long, PAGE_CACHE_SIZE - offset,
 						iov_iter_single_seg_count(i));
-			/*
-			 * This is the fallback to recover if the copy from
-			 * userspace above faults.
-			 */
-			if (unlikely(iov_iter_fault_in_readable(i, bytes))) {
-				status = -EFAULT;
-				break;
-			}
 			goto again;
 		}
 		pos += copied;
 		written += copied;
 
 		balance_dirty_pages_ratelimited(mapping);
-		if (fatal_signal_pending(current)) {
-			status = -EINTR;
-			break;
-		}
 	} while (iov_iter_count(i));
 
 	return written ? written : status;
@@ -2675,7 +2713,7 @@ EXPORT_SYMBOL(generic_file_write_iter);
  * page is known to the local caching routines.
  *
  * The @gfp_mask argument specifies whether I/O may be performed to release
- * this page (__GFP_IO), and whether the call may block (__GFP_WAIT & __GFP_FS).
+ * this page (__GFP_IO), and whether the call may block (__GFP_RECLAIM & __GFP_FS).
  *
  */
 int try_to_release_page(struct page *page, gfp_t gfp_mask)