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-next>] [day] [month] [year] [list]
Message-ID: <20251009155403.1379150-1-snovitoll@gmail.com>
Date: Thu,  9 Oct 2025 20:54:01 +0500
From: Sabyrzhan Tasbolatov <snovitoll@...il.com>
To: andreyknvl@...il.com,
	ryabinin.a.a@...il.com,
	glider@...gle.com,
	dvyukov@...gle.com,
	vincenzo.frascino@....com,
	akpm@...ux-foundation.org,
	bhe@...hat.com
Cc: christophe.leroy@...roup.eu,
	ritesh.list@...il.com,
	snovitoll@...il.com,
	kasan-dev@...glegroups.com,
	linux-kernel@...r.kernel.org,
	linux-mm@...ck.org
Subject: [PATCH 0/2] kasan: cleanups for kasan_enabled() checks

This patch series is the continuation of [1] the previous discussion
related to the KASAN internal refactoring.

Here we remove kasan_enabled() checks which are duplicated by higher callers.
These checks deduplication are also related to the separate patch series [2].

[1] https://lore.kernel.org/all/CA+fCnZce3AR+pUesbDkKMtMJ+iR8eDrcjFTbVpAcwjBoZ=gJnQ@mail.gmail.com/
[2] https://lore.kernel.org/all/aNTfPjS2buXMI46D@MiWiFi-R3L-srv/

* Altered functions:

check_page_allocation
	Delete the check because callers have it already in __wrappers in
	include/linux/kasan.h:
		__kasan_kfree_large
		__kasan_mempool_poison_pages
		__kasan_mempool_poison_object

kasan_populate_vmalloc, kasan_release_vmalloc
	Add __wrappers in include/linux/kasan.h.
	They are called externally in mm/vmalloc.c.

__kasan_unpoison_vmalloc, __kasan_poison_vmalloc
	Delete checks because there're already kasan_enabled() checks
	in respective __wrappers in include/linux/kasan.h.

release_free_meta -- Delete the check because the higher caller path
	has it already. See the stack trace:

	__kasan_slab_free -- has the check already
	__kasan_mempool_poison_object -- has the check already
		poison_slab_object
			kasan_save_free_info
				release_free_meta
					kasan_enabled() -- Delete here

* Other mm/kasan/* functions with kasan_enabled()
	where callers are defined in internal mm/kasan/kasan.h:

mm/kasan/generic.c:
	kasan_check_range
		check_region_inline
	kasan_byte_accessible

mm/kasan/shadow.c:
	kasan_poison
	kasan_poison_last_granule

mm/kasan/kasan_test_c.c:
	kasan_suite_init

== Tests:

* ARCH=um defconfig (-e KASAN, selects ARCH_DEFER_KASAN)
	Compiled and run ./linux with no issue

* ARCH=powerpc ppc64le_defconfig (-e KASAN, selects ARCH_DEFER_KASAN)
	Compiled and run qemu-system-ppc64 with no issue

* ARCH=arm64 defconfig (-e KASAN_GENERIC) and KUnit tests:

[    4.065375] # kasan: pass:61 fail:1 skip:14 total:76
[    4.065529] # Totals: pass:61 fail:1 skip:14 total:76
[    4.065682] not ok 1 kasan

1 test is failing:

[    3.772739]     # kasan_strings: EXPECTATION FAILED at mm/kasan/kasan_test_c.c:1700
[    3.772739]     KASAN failure expected in "strscpy(ptr, src + KASAN_GRANULE_SIZE, KASAN_GRANULE_SIZE)", but none occurred

which is also reproducable in the main tree.

Sabyrzhan Tasbolatov (2):
  kasan: remove __kasan_save_free_info wrapper
  kasan: cleanup of kasan_enabled() checks

 include/linux/kasan.h | 20 ++++++++++++++++++--
 mm/kasan/common.c     |  3 ---
 mm/kasan/generic.c    |  5 +----
 mm/kasan/kasan.h      |  7 +------
 mm/kasan/shadow.c     | 20 ++++----------------
 mm/kasan/tags.c       |  2 +-
 6 files changed, 25 insertions(+), 32 deletions(-)

-- 
2.34.1


Powered by blists - more mailing lists

Powered by Openwall GNU/*/Linux Powered by OpenVZ