[PATCH 2/3] mm/hugetlb: Setup hugetlb_falloc during fallocate hole punch

[Mike Kravetz <mike.kravetz@xxxxxxxxxx>]

When performing a fallocate hole punch, set up a hugetlb_falloc struct
and make i_private point to it.  i_private will point to this struct for
the duration of the operation.  At the end of the operation, wake up
anyone who faulted on the hole and is on the waitq.

Signed-off-by: Mike Kravetz <mike.kravetz@xxxxxxxxxx>
---
 fs/hugetlbfs/inode.c | 26 +++++++++++++++++++++++---
 1 file changed, 23 insertions(+), 3 deletions(-)

diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index 316adb9..b847e72 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -507,7 +507,9 @@ static long hugetlbfs_punch_hole(struct inode *inode, loff_t offset, loff_t len)
 {
 	struct hstate *h = hstate_inode(inode);
 	loff_t hpage_size = huge_page_size(h);
+	unsigned long hpage_shift = huge_page_shift(h);
 	loff_t hole_start, hole_end;
+	struct hugetlb_falloc hugetlb_falloc;
 
 	/*
 	 * For hole punch round up the beginning offset of the hole and
@@ -518,8 +520,23 @@ static long hugetlbfs_punch_hole(struct inode *inode, loff_t offset, loff_t len)
 
 	if (hole_end > hole_start) {
 		struct address_space *mapping = inode->i_mapping;
+		DECLARE_WAIT_QUEUE_HEAD_ONSTACK(hugetlb_falloc_waitq);
+
+		/*
+		 * Page faults on the area to be hole punched must be
+		 * stopped during the operation.  Initialize struct and
+		 * have inode->i_private point to it.
+		 */
+		hugetlb_falloc.waitq = &hugetlb_falloc_waitq;
+		hugetlb_falloc.start = hole_start >> hpage_shift;
+		hugetlb_falloc.end = hole_end >> hpage_shift;
 
 		mutex_lock(&inode->i_mutex);
+
+		spin_lock(&inode->i_lock);
+		inode->i_private = &hugetlb_falloc;
+		spin_unlock(&inode->i_lock);
+
 		i_mmap_lock_write(mapping);
 		if (!RB_EMPTY_ROOT(&mapping->i_mmap))
 			hugetlb_vmdelete_list(&mapping->i_mmap,
@@ -527,6 +544,12 @@ static long hugetlbfs_punch_hole(struct inode *inode, loff_t offset, loff_t len)
 						hole_end  >> PAGE_SHIFT);
 		i_mmap_unlock_write(mapping);
 		remove_inode_hugepages(inode, hole_start, hole_end);
+
+		spin_lock(&inode->i_lock);
+		inode->i_private = NULL;
+		wake_up_all(&hugetlb_falloc_waitq);
+		spin_unlock(&inode->i_lock);
+
 		mutex_unlock(&inode->i_mutex);
 	}
 
@@ -647,9 +670,6 @@ static long hugetlbfs_fallocate(struct file *file, int mode, loff_t offset,
 	if (!(mode & FALLOC_FL_KEEP_SIZE) && offset + len > inode->i_size)
 		i_size_write(inode, offset + len);
 	inode->i_ctime = CURRENT_TIME;
-	spin_lock(&inode->i_lock);
-	inode->i_private = NULL;
-	spin_unlock(&inode->i_lock);
 out:
 	mutex_unlock(&inode->i_mutex);
 	return error;
-- 
2.4.3

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@xxxxxxxxx.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@xxxxxxxxx";> email@xxxxxxxxx </a>