folio_set_order(folio, 0) is used in kernel at two places
__destroy_compound_gigantic_folio and __prep_compound_gigantic_folio.
Currently, It is called to clear out the folio->_folio_nr_pages and
folio->_folio_order.
For __destroy_compound_gigantic_folio:
In past, folio_set_order(folio, 0) was needed because page->mapping used
to overlap with _folio_nr_pages and _folio_order. So if these fields were
left uncleared during freeing gigantic hugepages, they were causing
"BUG: bad page state" due to non-zero page->mapping. Now, After
Commit a01f43901cfb ("hugetlb: be sure to free demoted CMA pages to
CMA") page->mapping has explicitly been cleared out for tail pages. Also,
_folio_order and _folio_nr_pages no longer overlaps with page->mapping.
struct page {
...
struct address_space * mapping; /* 24 8 */
...
}
struct folio {
...
union {
struct {
long unsigned int _flags_1; /* 64 8 */
long unsigned int _head_1; /* 72 8 */
unsigned char _folio_dtor; /* 80 1 */
unsigned char _folio_order; /* 81 1 */
/* XXX 2 bytes hole, try to pack */
atomic_t _entire_mapcount; /* 84 4 */
atomic_t _nr_pages_mapped; /* 88 4 */
atomic_t _pincount; /* 92 4 */
unsigned int _folio_nr_pages; /* 96 4 */
}; /* 64 40 */
struct page __page_1 __attribute__((__aligned__(8))); /* 64 64 */
}
...
}
So, folio_set_order(folio, 0) can be removed from freeing gigantic
folio path (__destroy_compound_gigantic_folio).
Another place, folio_set_order(folio, 0) is called inside
__prep_compound_gigantic_folio during error path. Here,
folio_set_order(folio, 0) can also be removed if we move
folio_set_order(folio, order) after for loop.
The patch also moves _folio_set_head call in __prep_compound_gigantic_folio()
such that we avoid clearing them in the error path.
Also, as Mike pointed out:
"It would actually be better to move the calls _folio_set_head and
folio_set_order in __prep_compound_gigantic_folio() as suggested here. Why?
In the current code, the ref count on the 'head page' is still 1 (or more)
while those calls are made. So, someone could take a speculative ref on the
page BEFORE the tail pages are set up."
This way, folio_set_order(folio, 0) is no more needed. And it will also
helps removing the confusion of folio order being set to 0 (as _folio_order
field is part of first tail page).
Testing: I have run LTP tests, which all passes. and also I have written
the test in LTP which tests the bug caused by compound_nr and page->mapping
overlapping.
https://github.com/linux-test-project/ltp/blob/master/testcases/kernel/mem/hugetlb/hugemmap/hugemmap32.c
Running on older kernel ( < 5.10-rc7) with the above bug this fails while
on newer kernel and, also with this patch it passes.
Signed-off-by: Tarun Sahu <tsahu@xxxxxxxxxxxxx>
---
mm/hugetlb.c | 9 +++------
mm/internal.h | 8 ++------
2 files changed, 5 insertions(+), 12 deletions(-)
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index f154019e6b84..607553445855 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -1489,7 +1489,6 @@ static void __destroy_compound_gigantic_folio(struct folio *folio,
set_page_refcounted(p);
}
- folio_set_order(folio, 0);
__folio_clear_head(folio);
}
@@ -1951,9 +1950,6 @@ static bool __prep_compound_gigantic_folio(struct folio *folio,
struct page *p;
__folio_clear_reserved(folio);
- __folio_set_head(folio);
- /* we rely on prep_new_hugetlb_folio to set the destructor */
- folio_set_order(folio, order);
for (i = 0; i < nr_pages; i++) {
p = folio_page(folio, i);
@@ -1999,6 +1995,9 @@ static bool __prep_compound_gigantic_folio(struct folio *folio,
if (i != 0)
set_compound_head(p, &folio->page);
}
+ __folio_set_head(folio);
+ /* we rely on prep_new_hugetlb_folio to set the destructor */
+ folio_set_order(folio, order);
atomic_set(&folio->_entire_mapcount, -1);
atomic_set(&folio->_nr_pages_mapped, 0);
atomic_set(&folio->_pincount, 0);
@@ -2017,8 +2016,6 @@ static bool __prep_compound_gigantic_folio(struct folio *folio,
p = folio_page(folio, j);
__ClearPageReserved(p);
}
- folio_set_order(folio, 0);
- __folio_clear_head(folio);
return false;
}
diff --git a/mm/internal.h b/mm/internal.h
index 68410c6d97ac..c59fe08c5b39 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -425,16 +425,12 @@ int split_free_page(struct page *free_page,
*/
static inline void folio_set_order(struct folio *folio, unsigned int order)
{
- if (WARN_ON_ONCE(!folio_test_large(folio)))
+ if (WARN_ON_ONCE(!order || !folio_test_large(folio)))
return;
folio->_folio_order = order;
#ifdef CONFIG_64BIT
- /*
- * When hugetlb dissolves a folio, we need to clear the tail
- * page, rather than setting nr_pages to 1.
- */
- folio->_folio_nr_pages = order ? 1U << order : 0;
+ folio->_folio_nr_pages = 1U << order;
#endif
}
--
2.31.1
