linux-kernel - [PATCH v2 10/16] xz: Optimize for-loop conditions in the BCJ decoders

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: <20240721133633.47721-11-lasse.collin@tukaani.org>
Date: Sun, 21 Jul 2024 16:36:25 +0300
From: Lasse Collin <lasse.collin@...aani.org>
To: Andrew Morton <akpm@...ux-foundation.org>
Cc: Lasse Collin <lasse.collin@...aani.org>,
	Sam James <sam@...too.org>,
	linux-kernel@...r.kernel.org
Subject: [PATCH v2 10/16] xz: Optimize for-loop conditions in the BCJ decoders

Compilers cannot optimize the addition "i + 4" away since theoretically
it could overflow.

Reviewed-by: Sam James <sam@...too.org>
Signed-off-by: Lasse Collin <lasse.collin@...aani.org>
---
 lib/xz/xz_dec_bcj.c | 23 ++++++++++++++++++-----
 1 file changed, 18 insertions(+), 5 deletions(-)

diff --git a/lib/xz/xz_dec_bcj.c b/lib/xz/xz_dec_bcj.c
index ab9237ed6db8..e0b4bf4999c0 100644
--- a/lib/xz/xz_dec_bcj.c
+++ b/lib/xz/xz_dec_bcj.c
@@ -161,7 +161,9 @@ static size_t bcj_powerpc(struct xz_dec_bcj *s, uint8_t *buf, size_t size)
 	size_t i;
 	uint32_t instr;
 
-	for (i = 0; i + 4 <= size; i += 4) {
+	size &= ~(size_t)3;
+
+	for (i = 0; i < size; i += 4) {
 		instr = get_unaligned_be32(buf + i);
 		if ((instr & 0xFC000003) == 0x48000001) {
 			instr &= 0x03FFFFFC;
@@ -218,7 +220,9 @@ static size_t bcj_ia64(struct xz_dec_bcj *s, uint8_t *buf, size_t size)
 	/* Instruction normalized with bit_res for easier manipulation */
 	uint64_t norm;
 
-	for (i = 0; i + 16 <= size; i += 16) {
+	size &= ~(size_t)15;
+
+	for (i = 0; i < size; i += 16) {
 		mask = branch_table[buf[i] & 0x1F];
 		for (slot = 0, bit_pos = 5; slot < 3; ++slot, bit_pos += 41) {
 			if (((mask >> slot) & 1) == 0)
@@ -266,7 +270,9 @@ static size_t bcj_arm(struct xz_dec_bcj *s, uint8_t *buf, size_t size)
 	size_t i;
 	uint32_t addr;
 
-	for (i = 0; i + 4 <= size; i += 4) {
+	size &= ~(size_t)3;
+
+	for (i = 0; i < size; i += 4) {
 		if (buf[i + 3] == 0xEB) {
 			addr = (uint32_t)buf[i] | ((uint32_t)buf[i + 1] << 8)
 					| ((uint32_t)buf[i + 2] << 16);
@@ -289,7 +295,12 @@ static size_t bcj_armthumb(struct xz_dec_bcj *s, uint8_t *buf, size_t size)
 	size_t i;
 	uint32_t addr;
 
-	for (i = 0; i + 4 <= size; i += 2) {
+	if (size < 4)
+		return 0;
+
+	size -= 4;
+
+	for (i = 0; i <= size; i += 2) {
 		if ((buf[i + 1] & 0xF8) == 0xF0
 				&& (buf[i + 3] & 0xF8) == 0xF8) {
 			addr = (((uint32_t)buf[i + 1] & 0x07) << 19)
@@ -317,7 +328,9 @@ static size_t bcj_sparc(struct xz_dec_bcj *s, uint8_t *buf, size_t size)
 	size_t i;
 	uint32_t instr;
 
-	for (i = 0; i + 4 <= size; i += 4) {
+	size &= ~(size_t)3;
+
+	for (i = 0; i < size; i += 4) {
 		instr = get_unaligned_be32(buf + i);
 		if ((instr >> 22) == 0x100 || (instr >> 22) == 0x1FF) {
 			instr <<= 2;
-- 
2.45.2