mm: fix madvise WILLNEED performance problem

The calculation of the end page index was incorrect, leading to a
regression of 70% when running stress-ng.

With this fix, we instead see a performance improvement of 3%.

Fixes: e6e8871 ("mm: optimise madvise WILLNEED")
Reported-by: kernel test robot <[email protected]>
Signed-off-by: Matthew Wilcox (Oracle) <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Tested-by: Xing Zhengjun <[email protected]>
Acked-by: Johannes Weiner <[email protected]>
Cc: William Kucharski <[email protected]>
Cc: Feng Tang <[email protected]>
Cc: "Chen, Rong A" <[email protected]>
Link: https://lkml.kernel.org/r/[email protected]
Signed-off-by: Linus Torvalds <[email protected]>

mm/madvise.c

@@ -226,7 +226,7 @@ static void force_shm_swapin_readahead(struct vm_area_struct *vma,
 		struct address_space *mapping)
 {
 	XA_STATE(xas, &mapping->i_pages, linear_page_index(vma, start));
-	pgoff_t end_index = end / PAGE_SIZE;
+	pgoff_t end_index = linear_page_index(vma, end + PAGE_SIZE - 1);
 	struct page *page;
 
 	rcu_read_lock();