linux-kernel - Re: [PATCH v22 1/4] mm: add MAP_DROPPABLE for designating always lazily freeable mappings

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <ZpAqbh3TnB9hIRRh@zx2c4.com>
Date: Thu, 11 Jul 2024 20:54:38 +0200
From: "Jason A. Donenfeld" <Jason@...c4.com>
To: David Hildenbrand <david@...hat.com>
Cc: Linus Torvalds <torvalds@...ux-foundation.org>,
	linux-kernel@...r.kernel.org, patches@...ts.linux.dev,
	tglx@...utronix.de, linux-crypto@...r.kernel.org,
	linux-api@...r.kernel.org, x86@...nel.org,
	Greg Kroah-Hartman <gregkh@...uxfoundation.org>,
	Adhemerval Zanella Netto <adhemerval.zanella@...aro.org>,
	Carlos O'Donell <carlos@...hat.com>,
	Florian Weimer <fweimer@...hat.com>, Arnd Bergmann <arnd@...db.de>,
	Jann Horn <jannh@...gle.com>,
	Christian Brauner <brauner@...nel.org>,
	David Hildenbrand <dhildenb@...hat.com>, linux-mm@...ck.org
Subject: Re: [PATCH v22 1/4] mm: add MAP_DROPPABLE for designating always
 lazily freeable mappings

On Thu, Jul 11, 2024 at 08:24:07PM +0200, David Hildenbrand wrote:
> > And PG_large_rmappable seems to only be used for hugetlb branches.
> 
> It should be set for THP/large folios.

And it's tested too, apparently.

Okay, well, how disappointing is this below? Because I'm running out of
tricks for flag reuse.

diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
index b9e914e1face..c1ea49a7f198 100644
--- a/include/linux/page-flags.h
+++ b/include/linux/page-flags.h
@@ -110,6 +110,7 @@ enum pageflags {
 	PG_workingset,
 	PG_error,
 	PG_owner_priv_1,	/* Owner use. If pagecache, fs may use*/
+	PG_owner_priv_2,
 	PG_arch_1,
 	PG_reserved,
 	PG_private,		/* If pagecache, has fs-private data */
@@ -190,6 +191,9 @@ enum pageflags {
 	/* At least one page in this folio has the hwpoison flag set */
 	PG_has_hwpoisoned = PG_error,
 	PG_large_rmappable = PG_workingset, /* anon or file-backed */
+
+	/* Zero page under memory pressure. */
+	PG_droppable = PG_owner_priv_2,
 };
 
 #define PAGEFLAGS_MASK		((1UL << NR_PAGEFLAGS) - 1)
@@ -549,6 +553,8 @@ PAGEFLAG(Private, private, PF_ANY)
 PAGEFLAG(Private2, private_2, PF_ANY) TESTSCFLAG(Private2, private_2, PF_ANY)
 PAGEFLAG(OwnerPriv1, owner_priv_1, PF_ANY)
 	TESTCLEARFLAG(OwnerPriv1, owner_priv_1, PF_ANY)
+PAGEFLAG(OwnerPriv2, owner_priv_2, PF_ANY)
+	TESTCLEARFLAG(OwnerPriv2, owner_priv_2, PF_ANY)
 
 /*
  * Only test-and-set exist for PG_writeback.  The unconditional operators are
@@ -640,6 +646,8 @@ FOLIO_TEST_CLEAR_FLAG_FALSE(young)
 FOLIO_FLAG_FALSE(idle)
 #endif
 
+FOLIO_FLAG(droppable, FOLIO_SECOND_PAGE)
+
 /*
  * PageReported() is used to track reported free pages within the Buddy
  * allocator. We can use the non-atomic version of the test and set
diff --git a/include/trace/events/mmflags.h b/include/trace/events/mmflags.h
index b63d211bd141..986551588805 100644
--- a/include/trace/events/mmflags.h
+++ b/include/trace/events/mmflags.h
@@ -108,6 +108,7 @@
 	DEF_PAGEFLAG_NAME(active),					\
 	DEF_PAGEFLAG_NAME(workingset),					\
 	DEF_PAGEFLAG_NAME(owner_priv_1),				\
+	DEF_PAGEFLAG_NAME(owner_priv_2),				\
 	DEF_PAGEFLAG_NAME(arch_1),					\
 	DEF_PAGEFLAG_NAME(reserved),					\
 	DEF_PAGEFLAG_NAME(private),					\
diff --git a/mm/rmap.c b/mm/rmap.c
index 1f9b5a9cb121..73b4052b2f82 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -1403,6 +1403,8 @@ void folio_add_new_anon_rmap(struct folio *folio, struct vm_area_struct *vma,
 	 */
 	if (!(vma->vm_flags & VM_DROPPABLE))
 		__folio_set_swapbacked(folio);
+	else
+		folio_set_droppable(folio);
 	__folio_set_anon(folio, vma, address, true);
 
 	if (likely(!folio_test_large(folio))) {
@@ -1852,7 +1854,7 @@ static bool try_to_unmap_one(struct folio *folio, struct vm_area_struct *vma,
 				      * ones can be dropped even if they've
 				      * been dirtied.
 				      */
-				     (vma->vm_flags & VM_DROPPABLE))) {
+				      folio_test_droppable(folio))) {
 					dec_mm_counter(mm, MM_ANONPAGES);
 					goto discard;
 				}
@@ -1866,7 +1868,7 @@ static bool try_to_unmap_one(struct folio *folio, struct vm_area_struct *vma,
 				 * Unlike MADV_FREE mappings, VM_DROPPABLE ones
 				 * never get swap backed on failure to drop.
 				 */
-				if (!(vma->vm_flags & VM_DROPPABLE))
+				if (!folio_test_droppable(folio))
 					folio_set_swapbacked(folio);
 				ret = false;
 				page_vma_mapped_walk_done(&pvmw);
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 2e34de9cd0d4..41340f2a12c7 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -4266,7 +4266,8 @@ static bool sort_folio(struct lruvec *lruvec, struct folio *folio, struct scan_c
 	}
 
 	/* dirty lazyfree */
-	if (type == LRU_GEN_FILE && folio_test_anon(folio) && folio_test_dirty(folio)) {
+	if (type == LRU_GEN_FILE && folio_test_anon(folio) &&
+	    folio_test_dirty(folio) && !folio_test_droppable(folio)) {
 		success = lru_gen_del_folio(lruvec, folio, true);
 		VM_WARN_ON_ONCE_FOLIO(!success, folio);
 		folio_set_swapbacked(folio);