1 files changed, 57 insertions, 12 deletions

diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index 7b17ccfa039d..316c4cebd3f3 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -283,6 +283,41 @@ hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
 #endif
 
 /*
+ * Someone wants to read @bytes from a HWPOISON hugetlb @page from @offset.
+ * Returns the maximum number of bytes one can read without touching the 1st raw
+ * HWPOISON subpage.
+ *
+ * The implementation borrows the iteration logic from copy_page_to_iter*.
+ */
+static size_t adjust_range_hwpoison(struct page *page, size_t offset, size_t bytes)
+{
+	size_t n = 0;
+	size_t res = 0;
+
+	/* First subpage to start the loop. */
+	page += offset / PAGE_SIZE;
+	offset %= PAGE_SIZE;
+	while (1) {
+		if (is_raw_hwpoison_page_in_hugepage(page))
+			break;
+
+		/* Safe to read n bytes without touching HWPOISON subpage. */
+		n = min(bytes, (size_t)PAGE_SIZE - offset);
+		res += n;
+		bytes -= n;
+		if (!bytes || !n)
+			break;
+		offset += n;
+		if (offset == PAGE_SIZE) {
+			page++;
+			offset = 0;
+		}
+	}
+
+	return res;
+}
+
+/*
  * Support for read() - Find the page attached to f_mapping and copy out the
  * data. This provides functionality similar to filemap_read().
  */
@@ -300,7 +335,7 @@ static ssize_t hugetlbfs_read_iter(struct kiocb *iocb, struct iov_iter *to)
 
 	while (iov_iter_count(to)) {
 		struct page *page;
-		size_t nr, copied;
+		size_t nr, copied, want;
 
 		/* nr is the maximum number of bytes to copy from this page */
 		nr = huge_page_size(h);
@@ -328,16 +363,26 @@ static ssize_t hugetlbfs_read_iter(struct kiocb *iocb, struct iov_iter *to)
 		} else {
 			unlock_page(page);
 
-			if (PageHWPoison(page)) {
-				put_page(page);
-				retval = -EIO;
-				break;
+			if (!PageHWPoison(page))
+				want = nr;
+			else {
+				/*
+				 * Adjust how many bytes safe to read without
+				 * touching the 1st raw HWPOISON subpage after
+				 * offset.
+				 */
+				want = adjust_range_hwpoison(page, offset, nr);
+				if (want == 0) {
+					put_page(page);
+					retval = -EIO;
+					break;
+				}
 			}
 
 			/*
 			 * We have the page, copy it to user space buffer.
 			 */
-			copied = copy_page_to_iter(page, offset, nr, to);
+			copied = copy_page_to_iter(page, offset, want, to);
 			put_page(page);
 		}
 		offset += copied;
@@ -887,7 +932,7 @@ 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(inode);
+	inode_set_ctime_current(inode);
 out:
 	inode_unlock(inode);
 	return error;
@@ -935,7 +980,7 @@ static struct inode *hugetlbfs_get_root(struct super_block *sb,
 		inode->i_mode = S_IFDIR | ctx->mode;
 		inode->i_uid = ctx->uid;
 		inode->i_gid = ctx->gid;
-		inode->i_atime = inode->i_mtime = inode->i_ctime = current_time(inode);
+		inode->i_atime = inode->i_mtime = inode_set_ctime_current(inode);
 		inode->i_op = &hugetlbfs_dir_inode_operations;
 		inode->i_fop = &simple_dir_operations;
 		/* directory inodes start off with i_nlink == 2 (for "." entry) */
@@ -979,7 +1024,7 @@ static struct inode *hugetlbfs_get_inode(struct super_block *sb,
 		lockdep_set_class(&inode->i_mapping->i_mmap_rwsem,
 				&hugetlbfs_i_mmap_rwsem_key);
 		inode->i_mapping->a_ops = &hugetlbfs_aops;
-		inode->i_atime = inode->i_mtime = inode->i_ctime = current_time(inode);
+		inode->i_atime = inode->i_mtime = inode_set_ctime_current(inode);
 		inode->i_mapping->private_data = resv_map;
 		info->seals = F_SEAL_SEAL;
 		switch (mode & S_IFMT) {
@@ -1022,7 +1067,7 @@ static int hugetlbfs_mknod(struct mnt_idmap *idmap, struct inode *dir,
 	inode = hugetlbfs_get_inode(dir->i_sb, dir, mode, dev);
 	if (!inode)
 		return -ENOSPC;
-	dir->i_ctime = dir->i_mtime = current_time(dir);
+	dir->i_mtime = inode_set_ctime_current(dir);
 	d_instantiate(dentry, inode);
 	dget(dentry);/* Extra count - pin the dentry in core */
 	return 0;
@@ -1054,7 +1099,7 @@ static int hugetlbfs_tmpfile(struct mnt_idmap *idmap,
 	inode = hugetlbfs_get_inode(dir->i_sb, dir, mode | S_IFREG, 0);
 	if (!inode)
 		return -ENOSPC;
-	dir->i_ctime = dir->i_mtime = current_time(dir);
+	dir->i_mtime = inode_set_ctime_current(dir);
 	d_tmpfile(file, inode);
 	return finish_open_simple(file, 0);
 }
@@ -1076,7 +1121,7 @@ static int hugetlbfs_symlink(struct mnt_idmap *idmap,
 		} else
 			iput(inode);
 	}
-	dir->i_ctime = dir->i_mtime = current_time(dir);
+	dir->i_mtime = inode_set_ctime_current(dir);
 
 	return error;
 }