The patch titled
Subject: xz: optimize for-loop conditions in the BCJ decoders
has been added to the -mm mm-nonmm-unstable branch. Its filename is
xz-optimize-for-loop-conditions-in-the-bcj-decoders.patch
This patch will shortly appear at
https://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new.git/tree/patches/xz-optimize-for-loop-conditions-in-the-bcj-decoders.patch
This patch will later appear in the mm-nonmm-unstable branch at
git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
Before you just go and hit "reply", please:
a) Consider who else should be cc'ed
b) Prefer to cc a suitable mailing list as well
c) Ideally: find the original patch on the mailing list and do a
reply-to-all to that, adding suitable additional cc's
*** Remember to use Documentation/process/submit-checklist.rst when testing your code ***
The -mm tree is included into linux-next via the mm-everything
branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
and is updated there every 2-3 working days
------------------------------------------------------
From: Lasse Collin <lasse.collin@xxxxxxxxxxx>
Subject: xz: optimize for-loop conditions in the BCJ decoders
Date: Wed, 20 Mar 2024 20:38:40 +0200
Compilers cannot optimize the addition "i + 4" away since theoretically
it could overflow.
Link: https://lkml.kernel.org/r/20240320183846.19475-8-lasse.collin@xxxxxxxxxxx
Signed-off-by: Lasse Collin <lasse.collin@xxxxxxxxxxx>
Reviewed-by: Jia Tan <jiat0218@xxxxxxxxx>
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
maintainers-add-xz-embedded-maintainers.patch
licenses-add-0bsd-license-text.patch
xz-switch-from-public-domain-to-bsd-zero-clause-license-0bsd.patch
xz-documentation-staging-xzrst-revise-thoroughly.patch
xz-fix-comments-and-coding-style.patch
xz-cleanup-crc32-edits-from-2018.patch
xz-optimize-for-loop-conditions-in-the-bcj-decoders.patch
xz-add-arm64-bcj-filter.patch
xz-add-risc-v-bcj-filter.patch
xz-use-128-mib-dictionary-and-force-single-threaded-mode.patch
xz-adjust-arch-specific-options-for-better-kernel-compression.patch
