The quilt patch titled
Subject: xz: optimize for-loop conditions in the BCJ decoders
has been removed from the -mm tree. Its filename was
xz-optimize-for-loop-conditions-in-the-bcj-decoders.patch
This patch was dropped because it was merged into the mm-nonmm-stable branch
of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
------------------------------------------------------
From: Lasse Collin <lasse.collin@xxxxxxxxxxx>
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@xxxxxxxxxxx
Signed-off-by: Lasse Collin <lasse.collin@xxxxxxxxxxx>
Reviewed-by: Sam James <sam@xxxxxxxxxx>
Cc: Albert Ou <aou@xxxxxxxxxxxxxxxxx>
Cc: Catalin Marinas <catalin.marinas@xxxxxxx>
Cc: Emil Renner Berthing <emil.renner.berthing@xxxxxxxxxxxxx>
Cc: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx>
Cc: Herbert Xu <herbert@xxxxxxxxxxxxxxxxxxx>
Cc: Joel Stanley <joel@xxxxxxxxx>
Cc: Jonathan Corbet <corbet@xxxxxxx>
Cc: Jubin Zhong <zhongjubin@xxxxxxxxxx>
Cc: Jules Maselbas <jmaselbas@xxxxxxxx>
Cc: Krzysztof Kozlowski <krzk@xxxxxxxxxx>
Cc: Michael Ellerman <mpe@xxxxxxxxxxxxxx>
Cc: Palmer Dabbelt <palmer@xxxxxxxxxxx>
Cc: Paul Walmsley <paul.walmsley@xxxxxxxxxx>
Cc: Randy Dunlap <rdunlap@xxxxxxxxxxxxx>
Cc: Rui Li <me@xxxxxxxxx>
Cc: Simon Glass <sjg@xxxxxxxxxxxx>
Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Cc: Will Deacon <will@xxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
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;
_
Patches currently in -mm which might be from lasse.collin@xxxxxxxxxxx are
