patches/old/xz-optimize-for-loop-conditions-in-the-bcj-decoders.patch

From: Lasse Collin <lasse.collin@tukaani.org>
Subject: xz: optimize for-loop conditions in the BCJ decoders
Date: Sun, 21 Jul 2024 16:36:25 +0300

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

Link: https://lkml.kernel.org/r/20240721133633.47721-11-lasse.collin@tukaani.org
Signed-off-by: Lasse Collin <lasse.collin@tukaani.org>
Reviewed-by: Sam James <sam@gentoo.org>
Cc: Albert Ou <aou@eecs.berkeley.edu>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Emil Renner Berthing <emil.renner.berthing@canonical.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Herbert Xu <herbert@gondor.apana.org.au>
Cc: Joel Stanley <joel@jms.id.au>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Jubin Zhong <zhongjubin@huawei.com>
Cc: Jules Maselbas <jmaselbas@zdiv.net>
Cc: Krzysztof Kozlowski <krzk@kernel.org>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Palmer Dabbelt <palmer@dabbelt.com>
Cc: Paul Walmsley <paul.walmsley@sifive.com>
Cc: Randy Dunlap <rdunlap@infradead.org>
Cc: Rui Li <me@lirui.org>
Cc: Simon Glass <sjg@chromium.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Will Deacon <will@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---

 lib/xz/xz_dec_bcj.c |   23 ++++++++++++++++++-----
 1 file changed, 18 insertions(+), 5 deletions(-)

--- a/lib/xz/xz_dec_bcj.c~xz-optimize-for-loop-conditions-in-the-bcj-decoders
+++ a/lib/xz/xz_dec_bcj.c
@@ -161,7 +161,9 @@ static size_t bcj_powerpc(struct xz_dec_
 	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
 	/* 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
 	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
 	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_bc
 	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;
_