Commit 476d87d6 authored by Luiz Capitulino's avatar Luiz Capitulino Committed by Andrew Morton
Browse files

fs: stable_page_flags(): use snapshot_page() 

A race condition is possible in stable_page_flags() where user-space is
reading /proc/kpageflags concurrently to a folio split.  This may lead to
oopses or BUG_ON()s being triggered.

To fix this, this commit uses snapshot_page() in stable_page_flags() so
that stable_page_flags() works with a stable page and folio snapshots
instead.

Note that stable_page_flags() makes use of some functions that require the
original page or folio pointer to work properly (eg.  is_free_budy_page()
and folio_test_idle()).  Since those functions can't be used on the page
snapshot, we replace their usage with flags that were set by
snapshot_page() for this purpose.

Link: https://lkml.kernel.org/r/52c16c0f00995a812a55980c2f26848a999a34ab.1752499009.git.luizcap@redhat.com


Signed-off-by: default avatarLuiz Capitulino <luizcap@redhat.com>
Reviewed-by: default avatarShivank Garg <shivankg@amd.com>
Tested-by: default avatarHarry Yoo <harry.yoo@oracle.com>
Acked-by: default avatarDavid Hildenbrand <david@redhat.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Oscar Salvador <osalvador@suse.de>
Cc: SeongJae Park <sj@kernel.org>
Signed-off-by: default avatarAndrew Morton <akpm@linux-foundation.org>
parent 71f2a2c4

fs/proc/page.c

+13 −16
Original line number Diff line number Diff line
@@ -147,6 +147,7 @@ static inline u64 kpf_copy_bit(u64 kflags, int ubit, int kbit) 
u64 stable_page_flags(const struct page *page)

{

	const struct folio *folio;

	struct page_snapshot ps;

	unsigned long k;

	unsigned long mapping;

	bool is_anon;
@@ -158,7 +159,9 @@ u64 stable_page_flags(const struct page *page) 
	 */

	if (!page)

		return 1 << KPF_NOPAGE;

	folio = page_folio(page);



	snapshot_page(&ps, page);

	folio = &ps.folio_snapshot;



	k = folio->flags;

	mapping = (unsigned long)folio->mapping;
@@ -167,7 +170,7 @@ u64 stable_page_flags(const struct page *page) 
	/*

	 * pseudo flags for the well known (anonymous) memory mapped pages

	 */

	if (page_mapped(page))

	if (folio_mapped(folio))

		u |= 1 << KPF_MMAP;

	if (is_anon) {

		u |= 1 << KPF_ANON;
@@ -179,7 +182,7 @@ u64 stable_page_flags(const struct page *page) 
	 * compound pages: export both head/tail info

	 * they together define a compound page's start/end pos and order

	 */

	if (page == &folio->page)

	if (ps.idx == 0)

		u |= kpf_copy_bit(k, KPF_COMPOUND_HEAD, PG_head);

	else

		u |= 1 << KPF_COMPOUND_TAIL;
@@ -189,25 +192,19 @@ u64 stable_page_flags(const struct page *page) 
	         folio_test_large_rmappable(folio)) {

		/* Note: we indicate any THPs here, not just PMD-sized ones */

		u |= 1 << KPF_THP;

	} else if (is_huge_zero_folio(folio)) {

	} else if (is_huge_zero_pfn(ps.pfn)) {

		u |= 1 << KPF_ZERO_PAGE;

		u |= 1 << KPF_THP;

	} else if (is_zero_folio(folio)) {

	} else if (is_zero_pfn(ps.pfn)) {

		u |= 1 << KPF_ZERO_PAGE;

	}



	/*

	 * Caveats on high order pages: PG_buddy and PG_slab will only be set

	 * on the head page.

	 */

	if (PageBuddy(page))

		u |= 1 << KPF_BUDDY;

	else if (page_count(page) == 0 && is_free_buddy_page(page))

	if (ps.flags & PAGE_SNAPSHOT_PG_BUDDY)

		u |= 1 << KPF_BUDDY;



	if (PageOffline(page))

	if (folio_test_offline(folio))

		u |= 1 << KPF_OFFLINE;

	if (PageTable(page))

	if (folio_test_pgtable(folio))

		u |= 1 << KPF_PGTABLE;

	if (folio_test_slab(folio))

		u |= 1 << KPF_SLAB;
@@ -215,7 +212,7 @@ u64 stable_page_flags(const struct page *page) 
#if defined(CONFIG_PAGE_IDLE_FLAG) && defined(CONFIG_64BIT)

	u |= kpf_copy_bit(k, KPF_IDLE,          PG_idle);

#else

	if (folio_test_idle(folio))

	if (ps.flags & PAGE_SNAPSHOT_PG_IDLE)

		u |= 1 << KPF_IDLE;

#endif
@@ -241,7 +238,7 @@ u64 stable_page_flags(const struct page *page) 
	if (u & (1 << KPF_HUGE))

		u |= kpf_copy_bit(k, KPF_HWPOISON,	PG_hwpoison);

	else

		u |= kpf_copy_bit(page->flags, KPF_HWPOISON,	PG_hwpoison);

		u |= kpf_copy_bit(ps.page_snapshot.flags, KPF_HWPOISON, PG_hwpoison);

#endif



	u |= kpf_copy_bit(k, KPF_RESERVED,	PG_reserved);