3 files changed, 31 insertions, 20 deletions

diff --git a/fs/iomap/apply.c b/fs/iomap/apply.c
index 76925b40b5fd..26ab6563181f 100644
--- a/fs/iomap/apply.c
+++ b/fs/iomap/apply.c
@@ -46,10 +46,14 @@ iomap_apply(struct inode *inode, loff_t pos, loff_t length, unsigned flags,
 	ret = ops->iomap_begin(inode, pos, length, flags, &iomap, &srcmap);
 	if (ret)
 		return ret;
-	if (WARN_ON(iomap.offset > pos))
-		return -EIO;
-	if (WARN_ON(iomap.length == 0))
-		return -EIO;
+	if (WARN_ON(iomap.offset > pos)) {
+		written = -EIO;
+		goto out;
+	}
+	if (WARN_ON(iomap.length == 0)) {
+		written = -EIO;
+		goto out;
+	}
 
 	trace_iomap_apply_dstmap(inode, &iomap);
 	if (srcmap.type != IOMAP_HOLE)
@@ -80,6 +84,7 @@ iomap_apply(struct inode *inode, loff_t pos, loff_t length, unsigned flags,
 	written = actor(inode, pos, length, data, &iomap,
 			srcmap.type != IOMAP_HOLE ? &srcmap : &iomap);
 
+out:
 	/*
 	 * Now the data has been copied, commit the range we've copied.  This
 	 * should not fail unless the filesystem has had a fatal error.
diff --git a/fs/iomap/direct-io.c b/fs/iomap/direct-io.c
index ec7b78e6feca..c1aafb2ab990 100644
--- a/fs/iomap/direct-io.c
+++ b/fs/iomap/direct-io.c
@@ -10,6 +10,7 @@
 #include <linux/backing-dev.h>
 #include <linux/uio.h>
 #include <linux/task_io_accounting_ops.h>
+#include "trace.h"
 
 #include "../internal.h"
 
@@ -401,6 +402,9 @@ iomap_dio_actor(struct inode *inode, loff_t pos, loff_t length,
  * can be mapped into multiple disjoint IOs and only a subset of the IOs issued
  * may be pure data writes. In that case, we still need to do a full data sync
  * completion.
+ *
+ * Returns -ENOTBLK In case of a page invalidation invalidation failure for
+ * writes.  The callers needs to fall back to buffered I/O in this case.
  */
 ssize_t
 iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
@@ -475,23 +479,24 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 	if (ret)
 		goto out_free_dio;
 
-	/*
-	 * Try to invalidate cache pages for the range we're direct
-	 * writing.  If this invalidation fails, tough, the write will
-	 * still work, but racing two incompatible write paths is a
-	 * pretty crazy thing to do, so we don't support it 100%.
-	 */
-	ret = invalidate_inode_pages2_range(mapping,
-			pos >> PAGE_SHIFT, end >> PAGE_SHIFT);
-	if (ret)
-		dio_warn_stale_pagecache(iocb->ki_filp);
-	ret = 0;
-
-	if (iov_iter_rw(iter) == WRITE && !wait_for_completion &&
-	    !inode->i_sb->s_dio_done_wq) {
-		ret = sb_init_dio_done_wq(inode->i_sb);
-		if (ret < 0)
+	if (iov_iter_rw(iter) == WRITE) {
+		/*
+		 * Try to invalidate cache pages for the range we are writing.
+		 * If this invalidation fails, let the caller fall back to
+		 * buffered I/O.
+		 */
+		if (invalidate_inode_pages2_range(mapping, pos >> PAGE_SHIFT,
+				end >> PAGE_SHIFT)) {
+			trace_iomap_dio_invalidate_fail(inode, pos, count);
+			ret = -ENOTBLK;
 			goto out_free_dio;
+		}
+
+		if (!wait_for_completion && !inode->i_sb->s_dio_done_wq) {
+			ret = sb_init_dio_done_wq(inode->i_sb);
+			if (ret < 0)
+				goto out_free_dio;
+		}
 	}
 
 	inode_dio_begin(inode);
diff --git a/fs/iomap/trace.h b/fs/iomap/trace.h
index 5693a39d52fb..fdc7ae388476 100644
--- a/fs/iomap/trace.h
+++ b/fs/iomap/trace.h
@@ -74,6 +74,7 @@ DEFINE_EVENT(iomap_range_class, name,	\
 DEFINE_RANGE_EVENT(iomap_writepage);
 DEFINE_RANGE_EVENT(iomap_releasepage);
 DEFINE_RANGE_EVENT(iomap_invalidatepage);
+DEFINE_RANGE_EVENT(iomap_dio_invalidate_fail);
 
 #define IOMAP_TYPE_STRINGS \
 	{ IOMAP_HOLE,		"HOLE" }, \