Skip to content
Snippets Groups Projects

Compare revisions

Changes are shown as if the source revision was being merged into the target revision. Learn more about comparing revisions.

Source

Select target project
No results found

Target

Select target project
  • alistair23/pmaports
  • exkc/pmaports
  • fossdd/pmaports
  • JustSoup321/pmaports
  • Eisenbahnfan/pmaports
  • raihan2000/pmaports
  • sleirsgoevy/pmaports
  • Adrian/pmaports
  • adamthiede/pmaports
  • jianhua/pmaports
  • knuxify/pmaports
  • Arnavion/pmaports
  • barni2000/pmaports
  • longnoserob/pmaports
  • smankusors/pmaports
  • Aren/pmaports
  • langfingaz/pmaports
  • sicelo/pmaports
  • kouta-kun/pmaports
  • craftyguy/pmaports
  • rdacayan/pmaports
  • rmader/pmaports
  • Haui111/pmaports
  • jakko/pmaports
  • dujem/pmaports
  • methanal/pmaports
  • WeirdTreeThing/pmaports
  • MightyM17/pmaports
  • sertonix/pmaports
  • amessier/pmaports
  • akemnade/pmaports
  • setotau/pmaports
  • kevinwidjaja21/pmaports
  • NekoCWD/pmaports
  • ollieparanoid/pmaports
  • manoedinata/pmaports
  • Drakulix/pmaports
  • grimler/pmaports
  • benpicco/pmaports
  • Frieder.Hannenheim/pmaports
  • andrisas/pmaports
  • EspiDev/pmaports
  • maze42/pmaports
  • anjandev/pmaports
  • danct12/pmaports
  • ijiki16/pmaports
  • jja2000/pmaports
  • fancsali/pmaports
  • bolilingmeng89006/pmaports
  • Minecrell/pmaports
  • chipiguay/pmaports
  • cherrypicker/pmaports
  • fortuna-mainline/pmaports
  • pevik/pmaports
  • Patriot-06/pmaports
  • JoseskVolpe/pmaports
  • verdre/pmaports
  • proycon/pmaports
  • AutumnSpark1226/pmaports
  • PsychoGame/pmaports
  • fraolt/pmaports
  • VaporGame/pmaports
  • pugzarecute/pmaports
  • CalcProgrammer1/pmaports
  • hexaheximal/pmaports
  • dabao1955/pmaports
  • HenriDellal/pmaports
  • semfault/pmaports
  • strobo5/pmaports
  • andrewgigena/pmaports
  • Athozus/pmaports
  • 1peter10/pmaports
  • vixalien/pmaports
  • Tooniis/pmaports
  • adomerle/pmaports
  • bjorn3/pmaports
  • StacyHarper/pmaports
  • Jack_Kekzoz/pmaports
  • Ceddicedced/pmaports
  • Justin_Zobel/pmaports
  • airtower-luna/pmaports
  • f-izzo/pmaports
  • cosmo/pmaports
  • 9lore/pmaports
  • postmarketOS/pmaports
  • Johnnynator/pmaports
  • iAboothahir/pmaports
  • N1kroks/pmaports
  • neuschaefer/pmaports
  • DylanVanAssche/pmaports
  • yehiashamaa987/pmaports
  • Operachi/pmaports
  • faveoled/pmaports
  • ilpianista/pmaports
  • johkra/pmaports
  • HDDTHR/pmaports
  • zsoltiv/pmaports
  • Justin/pmaports
  • Kaloyan501/pmaports_huawei_p8_lite_2015_fix
  • joelselvaraj/pmaports
  • rontti/pmaports
  • dsankouski/pmaports
  • StandaSK/pmaports
  • paricbat/pmaports
  • asdfugil/pmaports
  • komaru-yml/pmaports
  • MasterPlexus/pmaports
  • Felix/pmaports
  • ayakael/pmaports
  • feisuzhu/pmaports
  • AJ-RR/pmaports
  • SzczurekYT/pmaports
  • mediaberry/pmaports
  • justsomeguy/pmaports
  • Augis154/pmaports
  • hrdl/pmaports
  • sib0ndt/pmaports
  • 19atlas/pmaports
  • vipaoL/pmaports
  • wannjanjic/pmaports
  • dh/pmaports
  • LogicalErzor/pmaports
  • halamix2/pmaports
  • Shamilkv34/pmaports
  • Cogitri/pmaports
  • fallenritemonk/pmaports
  • user0-07161/pmaports
  • rock3tsprocket/pmaports
  • ellyq/pmaports
  • rodent/pmaports
  • mkorpershoek/pmaports
  • candrew/pmaports
  • fallaciousreasoning/pmaports
  • chalkin/pmaports
  • ungeskriptet/pmaports
  • r00t/pmaports
  • panpanpanpan/pmaports
  • celiffe/pmaports
  • davidfurey/pmaports
  • kidd/pmaports
  • tpikonen/pmaports
  • camelCaseNick/pmaports
  • ermine/pmaports
  • lgh/pmaports
  • sajattack/pmaports
  • StephanieBread/pmaports
  • M0Rf30/pmaports
  • notfound405/pmaports
  • samueldr/pmaports
  • r10nw7fd3/pmaports
  • treid998/pmaports-merge
  • denysvitali/pmaports
  • rodriguezst/pmaports
  • puppiestdoggo1/pmaports
  • donihalim/pmaports
  • EDKPiepaint/pmaports-apple-tonga-test
  • SanyaPilot/pmaports
157 results
Show changes
Commits on Source (276)
Showing
with 849 additions and 283 deletions
......@@ -23,6 +23,7 @@ sh_files="
./main/postmarketos-initramfs/init.sh
./main/postmarketos-initramfs/init_functions.sh
./main/postmarketos-mkinitfs-hook-debug-shell/20-debug-shell.sh
./main/postmarketos-mkinitfs-hook-debug-shell/setup_usb_storage.sh
./main/postmarketos-mkinitfs-hook-netboot/netboot.sh
./main/postmarketos-update-kernel/update-kernel.sh
./main/ttyescape/*.post-install
......
......@@ -7,7 +7,7 @@ import sys
import os
import importlib
import importlib.util
from distutils.sysconfig import get_python_lib
from site import getsitepackages
def path_pmbootstrap():
......@@ -24,13 +24,14 @@ def path_pmbootstrap():
sys.exit(1)
# Resolve the symlink and verify the folder
dir = os.path.dirname(os.path.realpath(bin))
if os.path.exists(dir + "/pmb/__init__.py"):
return dir
dir = get_python_lib()
if os.path.exists(dir + "/pmb/__init__.py"):
return dir
directory = os.path.dirname(os.path.realpath(bin))
if os.path.exists(directory + "/pmb/__init__.py"):
return directory
directories = getsitepackages()
for directory in directories:
if os.path.exists(directory + "/pmb/__init__.py"):
return directory
# Symlink not set up properly
print("ERROR: 'pmbootstrap' is not a symlink to pmbootstrap.py")
......
......@@ -21,8 +21,8 @@
Replace space inside `[ ]` with `x` to fill the checkbox
-->
* [ ] edge (`master` branch)
* [ ] `v23.12`
* [ ] `v23.06`
* [ ] `v22.12` (Supported until 2023-07-06)
* [ ] I confirm that the issue still is present after running `sudo apk upgrade -a`
......
......@@ -8,6 +8,12 @@ branch_pmaports=master
branch_aports=master
mirrordir_alpine=edge
[v23.12]
description=Upcoming stable release (DO NOT USE)
branch_pmaports=v23.12
branch_aports=3.19-stable
mirrordir_alpine=v3.19
[v23.06]
description=Latest release / Recommended for best stability
branch_pmaports=v23.06
......
......@@ -8,7 +8,7 @@ fi
pkgname=busybox-static-aarch64
pkgver=1.36.1
pkgrel=8
pkgrel=16
_arch="aarch64"
_mirror="http://dl-4.alpinelinux.org/alpine/"
......@@ -32,5 +32,5 @@ package() {
}
sha512sums="
89b28ab6e676d9c789375a85840c1f1062670992e4e44199c01d2356c439ab4d07c24ea5251d96388e150eb1343d0043a97316128b9603ad3ecb40dfa80e9072 busybox-static-1.36.1-r8-aarch64-edge.apk
6287ccf7af6347f7b6fb5e49395a9a8bdfef584b4a2611d17d6132076902b057d787c098f563ab3640f770fca20864aff2a4762248ca405e58e032bad276fca5 busybox-static-1.36.1-r16-aarch64-edge.apk
"
......@@ -8,7 +8,7 @@ fi
pkgname=busybox-static-armhf
pkgver=1.36.1
pkgrel=8
pkgrel=16
_arch="armhf"
_mirror="http://dl-4.alpinelinux.org/alpine/"
......@@ -32,5 +32,5 @@ package() {
}
sha512sums="
b9909d463d65476b6ef5766ccf0b5c432f5d6a0209aaef9cb1b838633e8128fd1ddecc821cc63743f9db1f2136b8884ed19986430549660bb89008dd98f986f6 busybox-static-1.36.1-r8-armhf-edge.apk
d216e65b0d08783eb1f6c8bb6eda441037a77530ac1069ff28b1a66846d219eed425b4390c56a3e2a7b9e080873533c3392782bb06b9e190ec004a3ae3ab7857 busybox-static-1.36.1-r16-armhf-edge.apk
"
......@@ -8,7 +8,7 @@ fi
pkgname=busybox-static-armv7
pkgver=1.36.1
pkgrel=8
pkgrel=16
_arch="armv7"
_mirror="http://dl-4.alpinelinux.org/alpine/"
......@@ -32,5 +32,5 @@ package() {
}
sha512sums="
40094ff8b8d45fce75ff872f94cc24da5129c1b2a28da2a7336dd6995ca973cb595d0a46f6346d55c862fb72c6c517fe00f6d6d7b20c604f644d1f8c4fc1afb0 busybox-static-1.36.1-r8-armv7-edge.apk
f9280cf852098400859968249f51bfe16db47655c15f0e384891ba9574ad42d2cef753760e895dfa9d625f2e051e6982a16e459d792e573bde161b1bd563c020 busybox-static-1.36.1-r16-armv7-edge.apk
"
From ef740fff300fd9eb8285fb5611f6205705ee54ec Mon Sep 17 00:00:00 2001
From: Prathamesh Kulkarni <prathamesh.kulkarni@linaro.org>
Date: Fri, 23 Jun 2023 15:27:17 +0530
Subject: [PATCH 35/35] Fix ICE observed in PR110280.
gcc/ChangeLog:
PR tree-optimization/110280
* match.pd (vec_perm_expr(v, v, mask) -> v): Explicitly build vector
using build_vector_from_val with the element of input operand, and
mask's type if operand and mask's types don't match.
gcc/testsuite/ChangeLog:
PR tree-optimization/110280
* gcc.target/aarch64/sve/pr110280.c: New test.
---
gcc/match.pd | 9 ++++++++-
gcc/testsuite/gcc.target/aarch64/sve/pr110280.c | 12 ++++++++++++
2 files changed, 20 insertions(+), 1 deletion(-)
create mode 100644 gcc/testsuite/gcc.target/aarch64/sve/pr110280.c
diff --git a/gcc/match.pd b/gcc/match.pd
index 91182448250..c3bb4fbc0a7 100644
--- a/gcc/match.pd
+++ b/gcc/match.pd
@@ -8292,7 +8292,14 @@ and,
(simplify
(vec_perm vec_same_elem_p@0 @0 @1)
- @0)
+ (if (types_match (type, TREE_TYPE (@0)))
+ @0
+ (with
+ {
+ tree elem = uniform_vector_p (@0);
+ }
+ (if (elem)
+ { build_vector_from_val (type, elem); }))))
/* Push VEC_PERM earlier if that may help FMA perception (PR101895). */
(simplify
diff --git a/gcc/testsuite/gcc.target/aarch64/sve/pr110280.c b/gcc/testsuite/gcc.target/aarch64/sve/pr110280.c
new file mode 100644
index 00000000000..d3279f38362
--- /dev/null
+++ b/gcc/testsuite/gcc.target/aarch64/sve/pr110280.c
@@ -0,0 +1,12 @@
+/* { dg-do compile } */
+/* { dg-options "-O3 -fdump-tree-optimized" } */
+
+#include "arm_sve.h"
+
+svuint32_t l()
+{
+ _Alignas(16) const unsigned int lanes[4] = {0, 0, 0, 0};
+ return svld1rq_u32(svptrue_b8(), lanes);
+}
+
+/* { dg-final { scan-tree-dump-not "VEC_PERM_EXPR" "optimized" } } */
--
2.41.0
https://gcc.gnu.org/PR110792
https://gcc.gnu.org/git/gitweb.cgi?p=gcc.git;h=790c1f60a5662b16eb19eb4b81922995863c7571
https://github.com/randombit/botan/issues/3637
From 85628c5653ff40963158a24c60eeec6a3b5a8e56 Mon Sep 17 00:00:00 2001
From: Roger Sayle <roger@nextmovesoftware.com>
Date: Thu, 3 Aug 2023 07:12:04 +0100
Subject: [PATCH] PR target/110792: Early clobber issues with
rot32di2_doubleword on i386.
This patch is a conservative fix for PR target/110792, a wrong-code
regression affecting doubleword rotations by BITS_PER_WORD, which
effectively swaps the highpart and lowpart words, when the source to be
rotated resides in memory. The issue is that if the register used to
hold the lowpart of the destination is mentioned in the address of
the memory operand, the current define_insn_and_split unintentionally
clobbers it before reading the highpart.
Hence, for the testcase, the incorrectly generated code looks like:
salq $4, %rdi // calculate address
movq WHIRL_S+8(%rdi), %rdi // accidentally clobber addr
movq WHIRL_S(%rdi), %rbp // load (wrong) lowpart
Traditionally, the textbook way to fix this would be to add an
explicit early clobber to the instruction's constraints.
(define_insn_and_split "<insn>32di2_doubleword"
- [(set (match_operand:DI 0 "register_operand" "=r,r,r")
+ [(set (match_operand:DI 0 "register_operand" "=r,r,&r")
(any_rotate:DI (match_operand:DI 1 "nonimmediate_operand" "0,r,o")
(const_int 32)))]
but unfortunately this currently generates significantly worse code,
due to a strange choice of reloads (effectively memcpy), which ends up
looking like:
salq $4, %rdi // calculate address
movdqa WHIRL_S(%rdi), %xmm0 // load the double word in SSE reg.
movaps %xmm0, -16(%rsp) // store the SSE reg back to the stack
movq -8(%rsp), %rdi // load highpart
movq -16(%rsp), %rbp // load lowpart
Note that reload's "&" doesn't distinguish between the memory being
early clobbered, vs the registers used in an addressing mode being
early clobbered.
The fix proposed in this patch is to remove the third alternative, that
allowed offsetable memory as an operand, forcing reload to place the
operand into a register before the rotation. This results in:
salq $4, %rdi
movq WHIRL_S(%rdi), %rax
movq WHIRL_S+8(%rdi), %rdi
movq %rax, %rbp
I believe there's a more advanced solution, by swapping the order of
the loads (if first destination register is mentioned in the address),
or inserting a lea insn (if both destination registers are mentioned
in the address), but this fix is a minimal "safe" solution, that
should hopefully be suitable for backporting.
2023-08-03 Roger Sayle <roger@nextmovesoftware.com>
gcc/ChangeLog
PR target/110792
* config/i386/i386.md (<any_rotate>ti3): For rotations by 64 bits
place operand in a register before gen_<insn>64ti2_doubleword.
(<any_rotate>di3): Likewise, for rotations by 32 bits, place
operand in a register before gen_<insn>32di2_doubleword.
(<any_rotate>32di2_doubleword): Constrain operand to be in register.
(<any_rotate>64ti2_doubleword): Likewise.
gcc/testsuite/ChangeLog
PR target/110792
* g++.target/i386/pr110792.C: New 32-bit C++ test case.
* gcc.target/i386/pr110792.c: New 64-bit C test case.
(cherry picked from commit 790c1f60a5662b16eb19eb4b81922995863c7571)
---
gcc/config/i386/i386.md | 18 ++++++++++++------
gcc/testsuite/g++.target/i386/pr110792.C | 16 ++++++++++++++++
gcc/testsuite/gcc.target/i386/pr110792.c | 18 ++++++++++++++++++
3 files changed, 46 insertions(+), 6 deletions(-)
create mode 100644 gcc/testsuite/g++.target/i386/pr110792.C
create mode 100644 gcc/testsuite/gcc.target/i386/pr110792.c
diff --git a/gcc/config/i386/i386.md b/gcc/config/i386/i386.md
index f3a3305..a71e837 100644
--- a/gcc/config/i386/i386.md
+++ b/gcc/config/i386/i386.md
@@ -14359,7 +14359,10 @@
emit_insn (gen_ix86_<insn>ti3_doubleword
(operands[0], operands[1], operands[2]));
else if (CONST_INT_P (operands[2]) && INTVAL (operands[2]) == 64)
- emit_insn (gen_<insn>64ti2_doubleword (operands[0], operands[1]));
+ {
+ operands[1] = force_reg (TImode, operands[1]);
+ emit_insn (gen_<insn>64ti2_doubleword (operands[0], operands[1]));
+ }
else
{
rtx amount = force_reg (QImode, operands[2]);
@@ -14394,7 +14397,10 @@
emit_insn (gen_ix86_<insn>di3_doubleword
(operands[0], operands[1], operands[2]));
else if (CONST_INT_P (operands[2]) && INTVAL (operands[2]) == 32)
- emit_insn (gen_<insn>32di2_doubleword (operands[0], operands[1]));
+ {
+ operands[1] = force_reg (DImode, operands[1]);
+ emit_insn (gen_<insn>32di2_doubleword (operands[0], operands[1]));
+ }
else
FAIL;
@@ -14562,8 +14568,8 @@
})
(define_insn_and_split "<insn>32di2_doubleword"
- [(set (match_operand:DI 0 "register_operand" "=r,r,r")
- (any_rotate:DI (match_operand:DI 1 "nonimmediate_operand" "0,r,o")
+ [(set (match_operand:DI 0 "register_operand" "=r,r")
+ (any_rotate:DI (match_operand:DI 1 "register_operand" "0,r")
(const_int 32)))]
"!TARGET_64BIT"
"#"
@@ -14580,8 +14586,8 @@
})
(define_insn_and_split "<insn>64ti2_doubleword"
- [(set (match_operand:TI 0 "register_operand" "=r,r,r")
- (any_rotate:TI (match_operand:TI 1 "nonimmediate_operand" "0,r,o")
+ [(set (match_operand:TI 0 "register_operand" "=r,r")
+ (any_rotate:TI (match_operand:TI 1 "register_operand" "0,r")
(const_int 64)))]
"TARGET_64BIT"
"#"
diff --git a/gcc/testsuite/g++.target/i386/pr110792.C b/gcc/testsuite/g++.target/i386/pr110792.C
new file mode 100644
index 0000000..ce21a7a
--- /dev/null
+++ b/gcc/testsuite/g++.target/i386/pr110792.C
@@ -0,0 +1,16 @@
+/* { dg-do compile { target ia32 } } */
+/* { dg-options "-O2" } */
+
+template <int ROT, typename T>
+inline T rotr(T input)
+{
+ return static_cast<T>((input >> ROT) | (input << (8 * sizeof(T) - ROT)));
+}
+
+unsigned long long WHIRL_S[256] = {0x18186018C07830D8};
+unsigned long long whirl(unsigned char x0)
+{
+ const unsigned long long s4 = WHIRL_S[x0&0xFF];
+ return rotr<32>(s4);
+}
+/* { dg-final { scan-assembler-not "movl\tWHIRL_S\\+4\\(,%eax,8\\), %eax" } } */
diff --git a/gcc/testsuite/gcc.target/i386/pr110792.c b/gcc/testsuite/gcc.target/i386/pr110792.c
new file mode 100644
index 0000000..b65125c
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/pr110792.c
@@ -0,0 +1,18 @@
+/* { dg-do compile { target int128 } } */
+/* { dg-options "-O2" } */
+
+static inline unsigned __int128 rotr(unsigned __int128 input)
+{
+ return ((input >> 64) | (input << (64)));
+}
+
+unsigned __int128 WHIRL_S[256] = {((__int128)0x18186018C07830D8) << 64 |0x18186018C07830D8};
+unsigned __int128 whirl(unsigned char x0)
+{
+ register int t __asm("rdi") = x0&0xFF;
+ const unsigned __int128 s4 = WHIRL_S[t];
+ register unsigned __int128 tt __asm("rdi") = rotr(s4);
+ asm("":::"memory");
+ return tt;
+}
+/* { dg-final { scan-assembler-not "movq\tWHIRL_S\\+8\\(%rdi\\), %rdi" } } */
--
2.41.0
......@@ -24,8 +24,8 @@ CBUILDROOT="/"
_cross_configure="--disable-bootstrap --with-sysroot=/usr/$CTARGET"
pkgname=gcc-aarch64
pkgver=13.1.1_git20230722
# i.e. 13.1.1, must match gcc/BASE-VER
pkgver=13.2.1_git20231014
# i.e. 13.2.1, must match gcc/BASE-VER
_pkgbase="${pkgver%%_git*}"
# date component from snapshots
_pkgsnap="${pkgver##*_git}"
......@@ -34,7 +34,7 @@ _pkgsnap="${pkgver##*_git}"
[ "$CHOST" != "$CTARGET" ] && _target="-$CTARGET_ARCH" || _target=""
pkgname=gcc-aarch64
pkgrel=2
pkgrel=0
pkgdesc="Stage2 cross-compiler for aarch64"
url="https://gcc.gnu.org"
arch="x86_64"
......@@ -268,9 +268,13 @@ source="https://dev.alpinelinux.org/archive/gcc/${_pkgbase%%.*}-$_pkgsnap/gcc-${
0032-libgnat-time_t-is-always-64-bit-on-musl-libc.patch
0033-libphobos-do-not-use-LFS64-symbols.patch
0034-libgo-fix-lfs64-use.patch
0035-Fix-ICE-observed-in-PR110280.patch
0036-PR110792-Early-clobber-issues-with-rot32di2-on-i386.patch
"
# secfixes:
# 13.2.1_git20231014-r0:
# - CVE-2023-4039
# we build out-of-tree
_gccdir="$srcdir"/gcc-${_pkgbase%%.*}-$_pkgsnap
_gcclibdir="/usr/lib/gcc/$CTARGET/${_pkgbase:-$pkgver}"
......@@ -783,7 +787,7 @@ gdb() {
}
sha512sums="
284719308cad4546ebd85934fb9f12112e8f1a4c3e5beea0760da1f73509907c194e7c133e6e755b6148bd1c51a72c071ac0d16b05641d901af7105461686655 gcc-13-20230722.tar.xz
406673a62deba759fc0532a801b3f57cabf894ea328587b23e62a707ba5767b0e3ae9b3f86bf3c6fcf13e8a3c30bc470e6598b625c8231efb629034211c162c2 gcc-13-20231014.tar.xz
1ecffba1b07d60e1b4422302b032bbea918b674c8e12b30aa6965b544d700ce86b61e9f7b8d402c6caf59257f491a394dd0912f0948565d6eae9335ee54f3b35 0001-posix_memalign.patch
163f282455b6a4df33f011bcd8b0440566ba0ffaeeab30d8ac52d39948980a56881ca0eff60687129d59556389a58b9d64e7768750bd70b1fe0fedbc9fc30dc2 0002-gcc-poison-system-directories.patch
3f24bb6a50d3c45b71ea05590e32fe3e69b91377ab185352891d5035c76ed193117c6d0b314a4c364bcf136b9a9dd5c926d6c7c30ab436976c121ebfea8d3ddd 0003-specs-turn-on-Wl-z-now-by-default.patch
......@@ -818,5 +822,5 @@ d47b559075f40d526235f47b91da1d0cf6bfe6c5b7311bbfe08af9dd6e8f27e6c7cd82e3b2d529aa
b325035cb7122d79c6b42ca6d3fc9e02319ed2f7cddb0639dff25d2798d2ce63812cd623462cdf95e21c9ffbf2412193f8b9fc89a4c36fa5a6a041661ac7399d 0032-libgnat-time_t-is-always-64-bit-on-musl-libc.patch
c474f34e6f9a4239d486a65141a133dbe8ce91427d502a57a9fd6eb403478a2b5715ba74f24c1cc0761e16eec77ba2c1ca921fb7d7bc1e040fc3703fc9559e75 0033-libphobos-do-not-use-LFS64-symbols.patch
c4482ffc36e7894b2140800159f4cbc9a3e9011e43a69b69f4fa92d5a11e2ee645c7e21df4423dd1e0636e8890849a5719647bfbdf84f951d638f8f488cb718c 0034-libgo-fix-lfs64-use.patch
048d767f4477c92ee6835850d13063ede21c0be751d0945c94445d04054e134cdc617eeb0b1ac8c892a604d8644580fcfebeccaf537d6b7380558ac6378e445a 0035-Fix-ICE-observed-in-PR110280.patch
cc1e10ac6e72db816f09325e301103109cc212a6f3de3ce0b9b038d149233c467319d203941695dbf3d7b9e2dcbbcd17609cdb056e831fcc323cd592423882d8 0036-PR110792-Early-clobber-issues-with-rot32di2-on-i386.patch
"
From ef740fff300fd9eb8285fb5611f6205705ee54ec Mon Sep 17 00:00:00 2001
From: Prathamesh Kulkarni <prathamesh.kulkarni@linaro.org>
Date: Fri, 23 Jun 2023 15:27:17 +0530
Subject: [PATCH 35/35] Fix ICE observed in PR110280.
gcc/ChangeLog:
PR tree-optimization/110280
* match.pd (vec_perm_expr(v, v, mask) -> v): Explicitly build vector
using build_vector_from_val with the element of input operand, and
mask's type if operand and mask's types don't match.
gcc/testsuite/ChangeLog:
PR tree-optimization/110280
* gcc.target/aarch64/sve/pr110280.c: New test.
---
gcc/match.pd | 9 ++++++++-
gcc/testsuite/gcc.target/aarch64/sve/pr110280.c | 12 ++++++++++++
2 files changed, 20 insertions(+), 1 deletion(-)
create mode 100644 gcc/testsuite/gcc.target/aarch64/sve/pr110280.c
diff --git a/gcc/match.pd b/gcc/match.pd
index 91182448250..c3bb4fbc0a7 100644
--- a/gcc/match.pd
+++ b/gcc/match.pd
@@ -8292,7 +8292,14 @@ and,
(simplify
(vec_perm vec_same_elem_p@0 @0 @1)
- @0)
+ (if (types_match (type, TREE_TYPE (@0)))
+ @0
+ (with
+ {
+ tree elem = uniform_vector_p (@0);
+ }
+ (if (elem)
+ { build_vector_from_val (type, elem); }))))
/* Push VEC_PERM earlier if that may help FMA perception (PR101895). */
(simplify
diff --git a/gcc/testsuite/gcc.target/aarch64/sve/pr110280.c b/gcc/testsuite/gcc.target/aarch64/sve/pr110280.c
new file mode 100644
index 00000000000..d3279f38362
--- /dev/null
+++ b/gcc/testsuite/gcc.target/aarch64/sve/pr110280.c
@@ -0,0 +1,12 @@
+/* { dg-do compile } */
+/* { dg-options "-O3 -fdump-tree-optimized" } */
+
+#include "arm_sve.h"
+
+svuint32_t l()
+{
+ _Alignas(16) const unsigned int lanes[4] = {0, 0, 0, 0};
+ return svld1rq_u32(svptrue_b8(), lanes);
+}
+
+/* { dg-final { scan-tree-dump-not "VEC_PERM_EXPR" "optimized" } } */
--
2.41.0
https://gcc.gnu.org/PR110792
https://gcc.gnu.org/git/gitweb.cgi?p=gcc.git;h=790c1f60a5662b16eb19eb4b81922995863c7571
https://github.com/randombit/botan/issues/3637
From 85628c5653ff40963158a24c60eeec6a3b5a8e56 Mon Sep 17 00:00:00 2001
From: Roger Sayle <roger@nextmovesoftware.com>
Date: Thu, 3 Aug 2023 07:12:04 +0100
Subject: [PATCH] PR target/110792: Early clobber issues with
rot32di2_doubleword on i386.
This patch is a conservative fix for PR target/110792, a wrong-code
regression affecting doubleword rotations by BITS_PER_WORD, which
effectively swaps the highpart and lowpart words, when the source to be
rotated resides in memory. The issue is that if the register used to
hold the lowpart of the destination is mentioned in the address of
the memory operand, the current define_insn_and_split unintentionally
clobbers it before reading the highpart.
Hence, for the testcase, the incorrectly generated code looks like:
salq $4, %rdi // calculate address
movq WHIRL_S+8(%rdi), %rdi // accidentally clobber addr
movq WHIRL_S(%rdi), %rbp // load (wrong) lowpart
Traditionally, the textbook way to fix this would be to add an
explicit early clobber to the instruction's constraints.
(define_insn_and_split "<insn>32di2_doubleword"
- [(set (match_operand:DI 0 "register_operand" "=r,r,r")
+ [(set (match_operand:DI 0 "register_operand" "=r,r,&r")
(any_rotate:DI (match_operand:DI 1 "nonimmediate_operand" "0,r,o")
(const_int 32)))]
but unfortunately this currently generates significantly worse code,
due to a strange choice of reloads (effectively memcpy), which ends up
looking like:
salq $4, %rdi // calculate address
movdqa WHIRL_S(%rdi), %xmm0 // load the double word in SSE reg.
movaps %xmm0, -16(%rsp) // store the SSE reg back to the stack
movq -8(%rsp), %rdi // load highpart
movq -16(%rsp), %rbp // load lowpart
Note that reload's "&" doesn't distinguish between the memory being
early clobbered, vs the registers used in an addressing mode being
early clobbered.
The fix proposed in this patch is to remove the third alternative, that
allowed offsetable memory as an operand, forcing reload to place the
operand into a register before the rotation. This results in:
salq $4, %rdi
movq WHIRL_S(%rdi), %rax
movq WHIRL_S+8(%rdi), %rdi
movq %rax, %rbp
I believe there's a more advanced solution, by swapping the order of
the loads (if first destination register is mentioned in the address),
or inserting a lea insn (if both destination registers are mentioned
in the address), but this fix is a minimal "safe" solution, that
should hopefully be suitable for backporting.
2023-08-03 Roger Sayle <roger@nextmovesoftware.com>
gcc/ChangeLog
PR target/110792
* config/i386/i386.md (<any_rotate>ti3): For rotations by 64 bits
place operand in a register before gen_<insn>64ti2_doubleword.
(<any_rotate>di3): Likewise, for rotations by 32 bits, place
operand in a register before gen_<insn>32di2_doubleword.
(<any_rotate>32di2_doubleword): Constrain operand to be in register.
(<any_rotate>64ti2_doubleword): Likewise.
gcc/testsuite/ChangeLog
PR target/110792
* g++.target/i386/pr110792.C: New 32-bit C++ test case.
* gcc.target/i386/pr110792.c: New 64-bit C test case.
(cherry picked from commit 790c1f60a5662b16eb19eb4b81922995863c7571)
---
gcc/config/i386/i386.md | 18 ++++++++++++------
gcc/testsuite/g++.target/i386/pr110792.C | 16 ++++++++++++++++
gcc/testsuite/gcc.target/i386/pr110792.c | 18 ++++++++++++++++++
3 files changed, 46 insertions(+), 6 deletions(-)
create mode 100644 gcc/testsuite/g++.target/i386/pr110792.C
create mode 100644 gcc/testsuite/gcc.target/i386/pr110792.c
diff --git a/gcc/config/i386/i386.md b/gcc/config/i386/i386.md
index f3a3305..a71e837 100644
--- a/gcc/config/i386/i386.md
+++ b/gcc/config/i386/i386.md
@@ -14359,7 +14359,10 @@
emit_insn (gen_ix86_<insn>ti3_doubleword
(operands[0], operands[1], operands[2]));
else if (CONST_INT_P (operands[2]) && INTVAL (operands[2]) == 64)
- emit_insn (gen_<insn>64ti2_doubleword (operands[0], operands[1]));
+ {
+ operands[1] = force_reg (TImode, operands[1]);
+ emit_insn (gen_<insn>64ti2_doubleword (operands[0], operands[1]));
+ }
else
{
rtx amount = force_reg (QImode, operands[2]);
@@ -14394,7 +14397,10 @@
emit_insn (gen_ix86_<insn>di3_doubleword
(operands[0], operands[1], operands[2]));
else if (CONST_INT_P (operands[2]) && INTVAL (operands[2]) == 32)
- emit_insn (gen_<insn>32di2_doubleword (operands[0], operands[1]));
+ {
+ operands[1] = force_reg (DImode, operands[1]);
+ emit_insn (gen_<insn>32di2_doubleword (operands[0], operands[1]));
+ }
else
FAIL;
@@ -14562,8 +14568,8 @@
})
(define_insn_and_split "<insn>32di2_doubleword"
- [(set (match_operand:DI 0 "register_operand" "=r,r,r")
- (any_rotate:DI (match_operand:DI 1 "nonimmediate_operand" "0,r,o")
+ [(set (match_operand:DI 0 "register_operand" "=r,r")
+ (any_rotate:DI (match_operand:DI 1 "register_operand" "0,r")
(const_int 32)))]
"!TARGET_64BIT"
"#"
@@ -14580,8 +14586,8 @@
})
(define_insn_and_split "<insn>64ti2_doubleword"
- [(set (match_operand:TI 0 "register_operand" "=r,r,r")
- (any_rotate:TI (match_operand:TI 1 "nonimmediate_operand" "0,r,o")
+ [(set (match_operand:TI 0 "register_operand" "=r,r")
+ (any_rotate:TI (match_operand:TI 1 "register_operand" "0,r")
(const_int 64)))]
"TARGET_64BIT"
"#"
diff --git a/gcc/testsuite/g++.target/i386/pr110792.C b/gcc/testsuite/g++.target/i386/pr110792.C
new file mode 100644
index 0000000..ce21a7a
--- /dev/null
+++ b/gcc/testsuite/g++.target/i386/pr110792.C
@@ -0,0 +1,16 @@
+/* { dg-do compile { target ia32 } } */
+/* { dg-options "-O2" } */
+
+template <int ROT, typename T>
+inline T rotr(T input)
+{
+ return static_cast<T>((input >> ROT) | (input << (8 * sizeof(T) - ROT)));
+}
+
+unsigned long long WHIRL_S[256] = {0x18186018C07830D8};
+unsigned long long whirl(unsigned char x0)
+{
+ const unsigned long long s4 = WHIRL_S[x0&0xFF];
+ return rotr<32>(s4);
+}
+/* { dg-final { scan-assembler-not "movl\tWHIRL_S\\+4\\(,%eax,8\\), %eax" } } */
diff --git a/gcc/testsuite/gcc.target/i386/pr110792.c b/gcc/testsuite/gcc.target/i386/pr110792.c
new file mode 100644
index 0000000..b65125c
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/pr110792.c
@@ -0,0 +1,18 @@
+/* { dg-do compile { target int128 } } */
+/* { dg-options "-O2" } */
+
+static inline unsigned __int128 rotr(unsigned __int128 input)
+{
+ return ((input >> 64) | (input << (64)));
+}
+
+unsigned __int128 WHIRL_S[256] = {((__int128)0x18186018C07830D8) << 64 |0x18186018C07830D8};
+unsigned __int128 whirl(unsigned char x0)
+{
+ register int t __asm("rdi") = x0&0xFF;
+ const unsigned __int128 s4 = WHIRL_S[t];
+ register unsigned __int128 tt __asm("rdi") = rotr(s4);
+ asm("":::"memory");
+ return tt;
+}
+/* { dg-final { scan-assembler-not "movq\tWHIRL_S\\+8\\(%rdi\\), %rdi" } } */
--
2.41.0
......@@ -24,8 +24,8 @@ CBUILDROOT="/"
_cross_configure="--disable-bootstrap --with-sysroot=/usr/$CTARGET"
pkgname=gcc-armhf
pkgver=13.1.1_git20230722
# i.e. 13.1.1, must match gcc/BASE-VER
pkgver=13.2.1_git20231014
# i.e. 13.2.1, must match gcc/BASE-VER
_pkgbase="${pkgver%%_git*}"
# date component from snapshots
_pkgsnap="${pkgver##*_git}"
......@@ -34,7 +34,7 @@ _pkgsnap="${pkgver##*_git}"
[ "$CHOST" != "$CTARGET" ] && _target="-$CTARGET_ARCH" || _target=""
pkgname=gcc-armhf
pkgrel=2
pkgrel=0
pkgdesc="Stage2 cross-compiler for armhf"
url="https://gcc.gnu.org"
arch="x86_64"
......@@ -268,9 +268,13 @@ source="https://dev.alpinelinux.org/archive/gcc/${_pkgbase%%.*}-$_pkgsnap/gcc-${
0032-libgnat-time_t-is-always-64-bit-on-musl-libc.patch
0033-libphobos-do-not-use-LFS64-symbols.patch
0034-libgo-fix-lfs64-use.patch
0035-Fix-ICE-observed-in-PR110280.patch
0036-PR110792-Early-clobber-issues-with-rot32di2-on-i386.patch
"
# secfixes:
# 13.2.1_git20231014-r0:
# - CVE-2023-4039
# we build out-of-tree
_gccdir="$srcdir"/gcc-${_pkgbase%%.*}-$_pkgsnap
_gcclibdir="/usr/lib/gcc/$CTARGET/${_pkgbase:-$pkgver}"
......@@ -783,7 +787,7 @@ gdb() {
}
sha512sums="
284719308cad4546ebd85934fb9f12112e8f1a4c3e5beea0760da1f73509907c194e7c133e6e755b6148bd1c51a72c071ac0d16b05641d901af7105461686655 gcc-13-20230722.tar.xz
406673a62deba759fc0532a801b3f57cabf894ea328587b23e62a707ba5767b0e3ae9b3f86bf3c6fcf13e8a3c30bc470e6598b625c8231efb629034211c162c2 gcc-13-20231014.tar.xz
1ecffba1b07d60e1b4422302b032bbea918b674c8e12b30aa6965b544d700ce86b61e9f7b8d402c6caf59257f491a394dd0912f0948565d6eae9335ee54f3b35 0001-posix_memalign.patch
163f282455b6a4df33f011bcd8b0440566ba0ffaeeab30d8ac52d39948980a56881ca0eff60687129d59556389a58b9d64e7768750bd70b1fe0fedbc9fc30dc2 0002-gcc-poison-system-directories.patch
3f24bb6a50d3c45b71ea05590e32fe3e69b91377ab185352891d5035c76ed193117c6d0b314a4c364bcf136b9a9dd5c926d6c7c30ab436976c121ebfea8d3ddd 0003-specs-turn-on-Wl-z-now-by-default.patch
......@@ -818,5 +822,5 @@ d47b559075f40d526235f47b91da1d0cf6bfe6c5b7311bbfe08af9dd6e8f27e6c7cd82e3b2d529aa
b325035cb7122d79c6b42ca6d3fc9e02319ed2f7cddb0639dff25d2798d2ce63812cd623462cdf95e21c9ffbf2412193f8b9fc89a4c36fa5a6a041661ac7399d 0032-libgnat-time_t-is-always-64-bit-on-musl-libc.patch
c474f34e6f9a4239d486a65141a133dbe8ce91427d502a57a9fd6eb403478a2b5715ba74f24c1cc0761e16eec77ba2c1ca921fb7d7bc1e040fc3703fc9559e75 0033-libphobos-do-not-use-LFS64-symbols.patch
c4482ffc36e7894b2140800159f4cbc9a3e9011e43a69b69f4fa92d5a11e2ee645c7e21df4423dd1e0636e8890849a5719647bfbdf84f951d638f8f488cb718c 0034-libgo-fix-lfs64-use.patch
048d767f4477c92ee6835850d13063ede21c0be751d0945c94445d04054e134cdc617eeb0b1ac8c892a604d8644580fcfebeccaf537d6b7380558ac6378e445a 0035-Fix-ICE-observed-in-PR110280.patch
cc1e10ac6e72db816f09325e301103109cc212a6f3de3ce0b9b038d149233c467319d203941695dbf3d7b9e2dcbbcd17609cdb056e831fcc323cd592423882d8 0036-PR110792-Early-clobber-issues-with-rot32di2-on-i386.patch
"
From ef740fff300fd9eb8285fb5611f6205705ee54ec Mon Sep 17 00:00:00 2001
From: Prathamesh Kulkarni <prathamesh.kulkarni@linaro.org>
Date: Fri, 23 Jun 2023 15:27:17 +0530
Subject: [PATCH 35/35] Fix ICE observed in PR110280.
gcc/ChangeLog:
PR tree-optimization/110280
* match.pd (vec_perm_expr(v, v, mask) -> v): Explicitly build vector
using build_vector_from_val with the element of input operand, and
mask's type if operand and mask's types don't match.
gcc/testsuite/ChangeLog:
PR tree-optimization/110280
* gcc.target/aarch64/sve/pr110280.c: New test.
---
gcc/match.pd | 9 ++++++++-
gcc/testsuite/gcc.target/aarch64/sve/pr110280.c | 12 ++++++++++++
2 files changed, 20 insertions(+), 1 deletion(-)
create mode 100644 gcc/testsuite/gcc.target/aarch64/sve/pr110280.c
diff --git a/gcc/match.pd b/gcc/match.pd
index 91182448250..c3bb4fbc0a7 100644
--- a/gcc/match.pd
+++ b/gcc/match.pd
@@ -8292,7 +8292,14 @@ and,
(simplify
(vec_perm vec_same_elem_p@0 @0 @1)
- @0)
+ (if (types_match (type, TREE_TYPE (@0)))
+ @0
+ (with
+ {
+ tree elem = uniform_vector_p (@0);
+ }
+ (if (elem)
+ { build_vector_from_val (type, elem); }))))
/* Push VEC_PERM earlier if that may help FMA perception (PR101895). */
(simplify
diff --git a/gcc/testsuite/gcc.target/aarch64/sve/pr110280.c b/gcc/testsuite/gcc.target/aarch64/sve/pr110280.c
new file mode 100644
index 00000000000..d3279f38362
--- /dev/null
+++ b/gcc/testsuite/gcc.target/aarch64/sve/pr110280.c
@@ -0,0 +1,12 @@
+/* { dg-do compile } */
+/* { dg-options "-O3 -fdump-tree-optimized" } */
+
+#include "arm_sve.h"
+
+svuint32_t l()
+{
+ _Alignas(16) const unsigned int lanes[4] = {0, 0, 0, 0};
+ return svld1rq_u32(svptrue_b8(), lanes);
+}
+
+/* { dg-final { scan-tree-dump-not "VEC_PERM_EXPR" "optimized" } } */
--
2.41.0
https://gcc.gnu.org/PR110792
https://gcc.gnu.org/git/gitweb.cgi?p=gcc.git;h=790c1f60a5662b16eb19eb4b81922995863c7571
https://github.com/randombit/botan/issues/3637
From 85628c5653ff40963158a24c60eeec6a3b5a8e56 Mon Sep 17 00:00:00 2001
From: Roger Sayle <roger@nextmovesoftware.com>
Date: Thu, 3 Aug 2023 07:12:04 +0100
Subject: [PATCH] PR target/110792: Early clobber issues with
rot32di2_doubleword on i386.
This patch is a conservative fix for PR target/110792, a wrong-code
regression affecting doubleword rotations by BITS_PER_WORD, which
effectively swaps the highpart and lowpart words, when the source to be
rotated resides in memory. The issue is that if the register used to
hold the lowpart of the destination is mentioned in the address of
the memory operand, the current define_insn_and_split unintentionally
clobbers it before reading the highpart.
Hence, for the testcase, the incorrectly generated code looks like:
salq $4, %rdi // calculate address
movq WHIRL_S+8(%rdi), %rdi // accidentally clobber addr
movq WHIRL_S(%rdi), %rbp // load (wrong) lowpart
Traditionally, the textbook way to fix this would be to add an
explicit early clobber to the instruction's constraints.
(define_insn_and_split "<insn>32di2_doubleword"
- [(set (match_operand:DI 0 "register_operand" "=r,r,r")
+ [(set (match_operand:DI 0 "register_operand" "=r,r,&r")
(any_rotate:DI (match_operand:DI 1 "nonimmediate_operand" "0,r,o")
(const_int 32)))]
but unfortunately this currently generates significantly worse code,
due to a strange choice of reloads (effectively memcpy), which ends up
looking like:
salq $4, %rdi // calculate address
movdqa WHIRL_S(%rdi), %xmm0 // load the double word in SSE reg.
movaps %xmm0, -16(%rsp) // store the SSE reg back to the stack
movq -8(%rsp), %rdi // load highpart
movq -16(%rsp), %rbp // load lowpart
Note that reload's "&" doesn't distinguish between the memory being
early clobbered, vs the registers used in an addressing mode being
early clobbered.
The fix proposed in this patch is to remove the third alternative, that
allowed offsetable memory as an operand, forcing reload to place the
operand into a register before the rotation. This results in:
salq $4, %rdi
movq WHIRL_S(%rdi), %rax
movq WHIRL_S+8(%rdi), %rdi
movq %rax, %rbp
I believe there's a more advanced solution, by swapping the order of
the loads (if first destination register is mentioned in the address),
or inserting a lea insn (if both destination registers are mentioned
in the address), but this fix is a minimal "safe" solution, that
should hopefully be suitable for backporting.
2023-08-03 Roger Sayle <roger@nextmovesoftware.com>
gcc/ChangeLog
PR target/110792
* config/i386/i386.md (<any_rotate>ti3): For rotations by 64 bits
place operand in a register before gen_<insn>64ti2_doubleword.
(<any_rotate>di3): Likewise, for rotations by 32 bits, place
operand in a register before gen_<insn>32di2_doubleword.
(<any_rotate>32di2_doubleword): Constrain operand to be in register.
(<any_rotate>64ti2_doubleword): Likewise.
gcc/testsuite/ChangeLog
PR target/110792
* g++.target/i386/pr110792.C: New 32-bit C++ test case.
* gcc.target/i386/pr110792.c: New 64-bit C test case.
(cherry picked from commit 790c1f60a5662b16eb19eb4b81922995863c7571)
---
gcc/config/i386/i386.md | 18 ++++++++++++------
gcc/testsuite/g++.target/i386/pr110792.C | 16 ++++++++++++++++
gcc/testsuite/gcc.target/i386/pr110792.c | 18 ++++++++++++++++++
3 files changed, 46 insertions(+), 6 deletions(-)
create mode 100644 gcc/testsuite/g++.target/i386/pr110792.C
create mode 100644 gcc/testsuite/gcc.target/i386/pr110792.c
diff --git a/gcc/config/i386/i386.md b/gcc/config/i386/i386.md
index f3a3305..a71e837 100644
--- a/gcc/config/i386/i386.md
+++ b/gcc/config/i386/i386.md
@@ -14359,7 +14359,10 @@
emit_insn (gen_ix86_<insn>ti3_doubleword
(operands[0], operands[1], operands[2]));
else if (CONST_INT_P (operands[2]) && INTVAL (operands[2]) == 64)
- emit_insn (gen_<insn>64ti2_doubleword (operands[0], operands[1]));
+ {
+ operands[1] = force_reg (TImode, operands[1]);
+ emit_insn (gen_<insn>64ti2_doubleword (operands[0], operands[1]));
+ }
else
{
rtx amount = force_reg (QImode, operands[2]);
@@ -14394,7 +14397,10 @@
emit_insn (gen_ix86_<insn>di3_doubleword
(operands[0], operands[1], operands[2]));
else if (CONST_INT_P (operands[2]) && INTVAL (operands[2]) == 32)
- emit_insn (gen_<insn>32di2_doubleword (operands[0], operands[1]));
+ {
+ operands[1] = force_reg (DImode, operands[1]);
+ emit_insn (gen_<insn>32di2_doubleword (operands[0], operands[1]));
+ }
else
FAIL;
@@ -14562,8 +14568,8 @@
})
(define_insn_and_split "<insn>32di2_doubleword"
- [(set (match_operand:DI 0 "register_operand" "=r,r,r")
- (any_rotate:DI (match_operand:DI 1 "nonimmediate_operand" "0,r,o")
+ [(set (match_operand:DI 0 "register_operand" "=r,r")
+ (any_rotate:DI (match_operand:DI 1 "register_operand" "0,r")
(const_int 32)))]
"!TARGET_64BIT"
"#"
@@ -14580,8 +14586,8 @@
})
(define_insn_and_split "<insn>64ti2_doubleword"
- [(set (match_operand:TI 0 "register_operand" "=r,r,r")
- (any_rotate:TI (match_operand:TI 1 "nonimmediate_operand" "0,r,o")
+ [(set (match_operand:TI 0 "register_operand" "=r,r")
+ (any_rotate:TI (match_operand:TI 1 "register_operand" "0,r")
(const_int 64)))]
"TARGET_64BIT"
"#"
diff --git a/gcc/testsuite/g++.target/i386/pr110792.C b/gcc/testsuite/g++.target/i386/pr110792.C
new file mode 100644
index 0000000..ce21a7a
--- /dev/null
+++ b/gcc/testsuite/g++.target/i386/pr110792.C
@@ -0,0 +1,16 @@
+/* { dg-do compile { target ia32 } } */
+/* { dg-options "-O2" } */
+
+template <int ROT, typename T>
+inline T rotr(T input)
+{
+ return static_cast<T>((input >> ROT) | (input << (8 * sizeof(T) - ROT)));
+}
+
+unsigned long long WHIRL_S[256] = {0x18186018C07830D8};
+unsigned long long whirl(unsigned char x0)
+{
+ const unsigned long long s4 = WHIRL_S[x0&0xFF];
+ return rotr<32>(s4);
+}
+/* { dg-final { scan-assembler-not "movl\tWHIRL_S\\+4\\(,%eax,8\\), %eax" } } */
diff --git a/gcc/testsuite/gcc.target/i386/pr110792.c b/gcc/testsuite/gcc.target/i386/pr110792.c
new file mode 100644
index 0000000..b65125c
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/pr110792.c
@@ -0,0 +1,18 @@
+/* { dg-do compile { target int128 } } */
+/* { dg-options "-O2" } */
+
+static inline unsigned __int128 rotr(unsigned __int128 input)
+{
+ return ((input >> 64) | (input << (64)));
+}
+
+unsigned __int128 WHIRL_S[256] = {((__int128)0x18186018C07830D8) << 64 |0x18186018C07830D8};
+unsigned __int128 whirl(unsigned char x0)
+{
+ register int t __asm("rdi") = x0&0xFF;
+ const unsigned __int128 s4 = WHIRL_S[t];
+ register unsigned __int128 tt __asm("rdi") = rotr(s4);
+ asm("":::"memory");
+ return tt;
+}
+/* { dg-final { scan-assembler-not "movq\tWHIRL_S\\+8\\(%rdi\\), %rdi" } } */
--
2.41.0
......@@ -24,8 +24,8 @@ CBUILDROOT="/"
_cross_configure="--disable-bootstrap --with-sysroot=/usr/$CTARGET"
pkgname=gcc-armv7
pkgver=13.1.1_git20230722
# i.e. 13.1.1, must match gcc/BASE-VER
pkgver=13.2.1_git20231014
# i.e. 13.2.1, must match gcc/BASE-VER
_pkgbase="${pkgver%%_git*}"
# date component from snapshots
_pkgsnap="${pkgver##*_git}"
......@@ -34,7 +34,7 @@ _pkgsnap="${pkgver##*_git}"
[ "$CHOST" != "$CTARGET" ] && _target="-$CTARGET_ARCH" || _target=""
pkgname=gcc-armv7
pkgrel=2
pkgrel=0
pkgdesc="Stage2 cross-compiler for armv7"
url="https://gcc.gnu.org"
arch="x86_64"
......@@ -268,9 +268,13 @@ source="https://dev.alpinelinux.org/archive/gcc/${_pkgbase%%.*}-$_pkgsnap/gcc-${
0032-libgnat-time_t-is-always-64-bit-on-musl-libc.patch
0033-libphobos-do-not-use-LFS64-symbols.patch
0034-libgo-fix-lfs64-use.patch
0035-Fix-ICE-observed-in-PR110280.patch
0036-PR110792-Early-clobber-issues-with-rot32di2-on-i386.patch
"
# secfixes:
# 13.2.1_git20231014-r0:
# - CVE-2023-4039
# we build out-of-tree
_gccdir="$srcdir"/gcc-${_pkgbase%%.*}-$_pkgsnap
_gcclibdir="/usr/lib/gcc/$CTARGET/${_pkgbase:-$pkgver}"
......@@ -783,7 +787,7 @@ gdb() {
}
sha512sums="
284719308cad4546ebd85934fb9f12112e8f1a4c3e5beea0760da1f73509907c194e7c133e6e755b6148bd1c51a72c071ac0d16b05641d901af7105461686655 gcc-13-20230722.tar.xz
406673a62deba759fc0532a801b3f57cabf894ea328587b23e62a707ba5767b0e3ae9b3f86bf3c6fcf13e8a3c30bc470e6598b625c8231efb629034211c162c2 gcc-13-20231014.tar.xz
1ecffba1b07d60e1b4422302b032bbea918b674c8e12b30aa6965b544d700ce86b61e9f7b8d402c6caf59257f491a394dd0912f0948565d6eae9335ee54f3b35 0001-posix_memalign.patch
163f282455b6a4df33f011bcd8b0440566ba0ffaeeab30d8ac52d39948980a56881ca0eff60687129d59556389a58b9d64e7768750bd70b1fe0fedbc9fc30dc2 0002-gcc-poison-system-directories.patch
3f24bb6a50d3c45b71ea05590e32fe3e69b91377ab185352891d5035c76ed193117c6d0b314a4c364bcf136b9a9dd5c926d6c7c30ab436976c121ebfea8d3ddd 0003-specs-turn-on-Wl-z-now-by-default.patch
......@@ -818,5 +822,5 @@ d47b559075f40d526235f47b91da1d0cf6bfe6c5b7311bbfe08af9dd6e8f27e6c7cd82e3b2d529aa
b325035cb7122d79c6b42ca6d3fc9e02319ed2f7cddb0639dff25d2798d2ce63812cd623462cdf95e21c9ffbf2412193f8b9fc89a4c36fa5a6a041661ac7399d 0032-libgnat-time_t-is-always-64-bit-on-musl-libc.patch
c474f34e6f9a4239d486a65141a133dbe8ce91427d502a57a9fd6eb403478a2b5715ba74f24c1cc0761e16eec77ba2c1ca921fb7d7bc1e040fc3703fc9559e75 0033-libphobos-do-not-use-LFS64-symbols.patch
c4482ffc36e7894b2140800159f4cbc9a3e9011e43a69b69f4fa92d5a11e2ee645c7e21df4423dd1e0636e8890849a5719647bfbdf84f951d638f8f488cb718c 0034-libgo-fix-lfs64-use.patch
048d767f4477c92ee6835850d13063ede21c0be751d0945c94445d04054e134cdc617eeb0b1ac8c892a604d8644580fcfebeccaf537d6b7380558ac6378e445a 0035-Fix-ICE-observed-in-PR110280.patch
cc1e10ac6e72db816f09325e301103109cc212a6f3de3ce0b9b038d149233c467319d203941695dbf3d7b9e2dcbbcd17609cdb056e831fcc323cd592423882d8 0036-PR110792-Early-clobber-issues-with-rot32di2-on-i386.patch
"
From ef740fff300fd9eb8285fb5611f6205705ee54ec Mon Sep 17 00:00:00 2001
From: Prathamesh Kulkarni <prathamesh.kulkarni@linaro.org>
Date: Fri, 23 Jun 2023 15:27:17 +0530
Subject: [PATCH 35/35] Fix ICE observed in PR110280.
gcc/ChangeLog:
PR tree-optimization/110280
* match.pd (vec_perm_expr(v, v, mask) -> v): Explicitly build vector
using build_vector_from_val with the element of input operand, and
mask's type if operand and mask's types don't match.
gcc/testsuite/ChangeLog:
PR tree-optimization/110280
* gcc.target/aarch64/sve/pr110280.c: New test.
---
gcc/match.pd | 9 ++++++++-
gcc/testsuite/gcc.target/aarch64/sve/pr110280.c | 12 ++++++++++++
2 files changed, 20 insertions(+), 1 deletion(-)
create mode 100644 gcc/testsuite/gcc.target/aarch64/sve/pr110280.c
diff --git a/gcc/match.pd b/gcc/match.pd
index 91182448250..c3bb4fbc0a7 100644
--- a/gcc/match.pd
+++ b/gcc/match.pd
@@ -8292,7 +8292,14 @@ and,
(simplify
(vec_perm vec_same_elem_p@0 @0 @1)
- @0)
+ (if (types_match (type, TREE_TYPE (@0)))
+ @0
+ (with
+ {
+ tree elem = uniform_vector_p (@0);
+ }
+ (if (elem)
+ { build_vector_from_val (type, elem); }))))
/* Push VEC_PERM earlier if that may help FMA perception (PR101895). */
(simplify
diff --git a/gcc/testsuite/gcc.target/aarch64/sve/pr110280.c b/gcc/testsuite/gcc.target/aarch64/sve/pr110280.c
new file mode 100644
index 00000000000..d3279f38362
--- /dev/null
+++ b/gcc/testsuite/gcc.target/aarch64/sve/pr110280.c
@@ -0,0 +1,12 @@
+/* { dg-do compile } */
+/* { dg-options "-O3 -fdump-tree-optimized" } */
+
+#include "arm_sve.h"
+
+svuint32_t l()
+{
+ _Alignas(16) const unsigned int lanes[4] = {0, 0, 0, 0};
+ return svld1rq_u32(svptrue_b8(), lanes);
+}
+
+/* { dg-final { scan-tree-dump-not "VEC_PERM_EXPR" "optimized" } } */
--
2.41.0
https://gcc.gnu.org/PR110792
https://gcc.gnu.org/git/gitweb.cgi?p=gcc.git;h=790c1f60a5662b16eb19eb4b81922995863c7571
https://github.com/randombit/botan/issues/3637
From 85628c5653ff40963158a24c60eeec6a3b5a8e56 Mon Sep 17 00:00:00 2001
From: Roger Sayle <roger@nextmovesoftware.com>
Date: Thu, 3 Aug 2023 07:12:04 +0100
Subject: [PATCH] PR target/110792: Early clobber issues with
rot32di2_doubleword on i386.
This patch is a conservative fix for PR target/110792, a wrong-code
regression affecting doubleword rotations by BITS_PER_WORD, which
effectively swaps the highpart and lowpart words, when the source to be
rotated resides in memory. The issue is that if the register used to
hold the lowpart of the destination is mentioned in the address of
the memory operand, the current define_insn_and_split unintentionally
clobbers it before reading the highpart.
Hence, for the testcase, the incorrectly generated code looks like:
salq $4, %rdi // calculate address
movq WHIRL_S+8(%rdi), %rdi // accidentally clobber addr
movq WHIRL_S(%rdi), %rbp // load (wrong) lowpart
Traditionally, the textbook way to fix this would be to add an
explicit early clobber to the instruction's constraints.
(define_insn_and_split "<insn>32di2_doubleword"
- [(set (match_operand:DI 0 "register_operand" "=r,r,r")
+ [(set (match_operand:DI 0 "register_operand" "=r,r,&r")
(any_rotate:DI (match_operand:DI 1 "nonimmediate_operand" "0,r,o")
(const_int 32)))]
but unfortunately this currently generates significantly worse code,
due to a strange choice of reloads (effectively memcpy), which ends up
looking like:
salq $4, %rdi // calculate address
movdqa WHIRL_S(%rdi), %xmm0 // load the double word in SSE reg.
movaps %xmm0, -16(%rsp) // store the SSE reg back to the stack
movq -8(%rsp), %rdi // load highpart
movq -16(%rsp), %rbp // load lowpart
Note that reload's "&" doesn't distinguish between the memory being
early clobbered, vs the registers used in an addressing mode being
early clobbered.
The fix proposed in this patch is to remove the third alternative, that
allowed offsetable memory as an operand, forcing reload to place the
operand into a register before the rotation. This results in:
salq $4, %rdi
movq WHIRL_S(%rdi), %rax
movq WHIRL_S+8(%rdi), %rdi
movq %rax, %rbp
I believe there's a more advanced solution, by swapping the order of
the loads (if first destination register is mentioned in the address),
or inserting a lea insn (if both destination registers are mentioned
in the address), but this fix is a minimal "safe" solution, that
should hopefully be suitable for backporting.
2023-08-03 Roger Sayle <roger@nextmovesoftware.com>
gcc/ChangeLog
PR target/110792
* config/i386/i386.md (<any_rotate>ti3): For rotations by 64 bits
place operand in a register before gen_<insn>64ti2_doubleword.
(<any_rotate>di3): Likewise, for rotations by 32 bits, place
operand in a register before gen_<insn>32di2_doubleword.
(<any_rotate>32di2_doubleword): Constrain operand to be in register.
(<any_rotate>64ti2_doubleword): Likewise.
gcc/testsuite/ChangeLog
PR target/110792
* g++.target/i386/pr110792.C: New 32-bit C++ test case.
* gcc.target/i386/pr110792.c: New 64-bit C test case.
(cherry picked from commit 790c1f60a5662b16eb19eb4b81922995863c7571)
---
gcc/config/i386/i386.md | 18 ++++++++++++------
gcc/testsuite/g++.target/i386/pr110792.C | 16 ++++++++++++++++
gcc/testsuite/gcc.target/i386/pr110792.c | 18 ++++++++++++++++++
3 files changed, 46 insertions(+), 6 deletions(-)
create mode 100644 gcc/testsuite/g++.target/i386/pr110792.C
create mode 100644 gcc/testsuite/gcc.target/i386/pr110792.c
diff --git a/gcc/config/i386/i386.md b/gcc/config/i386/i386.md
index f3a3305..a71e837 100644
--- a/gcc/config/i386/i386.md
+++ b/gcc/config/i386/i386.md
@@ -14359,7 +14359,10 @@
emit_insn (gen_ix86_<insn>ti3_doubleword
(operands[0], operands[1], operands[2]));
else if (CONST_INT_P (operands[2]) && INTVAL (operands[2]) == 64)
- emit_insn (gen_<insn>64ti2_doubleword (operands[0], operands[1]));
+ {
+ operands[1] = force_reg (TImode, operands[1]);
+ emit_insn (gen_<insn>64ti2_doubleword (operands[0], operands[1]));
+ }
else
{
rtx amount = force_reg (QImode, operands[2]);
@@ -14394,7 +14397,10 @@
emit_insn (gen_ix86_<insn>di3_doubleword
(operands[0], operands[1], operands[2]));
else if (CONST_INT_P (operands[2]) && INTVAL (operands[2]) == 32)
- emit_insn (gen_<insn>32di2_doubleword (operands[0], operands[1]));
+ {
+ operands[1] = force_reg (DImode, operands[1]);
+ emit_insn (gen_<insn>32di2_doubleword (operands[0], operands[1]));
+ }
else
FAIL;
@@ -14562,8 +14568,8 @@
})
(define_insn_and_split "<insn>32di2_doubleword"
- [(set (match_operand:DI 0 "register_operand" "=r,r,r")
- (any_rotate:DI (match_operand:DI 1 "nonimmediate_operand" "0,r,o")
+ [(set (match_operand:DI 0 "register_operand" "=r,r")
+ (any_rotate:DI (match_operand:DI 1 "register_operand" "0,r")
(const_int 32)))]
"!TARGET_64BIT"
"#"
@@ -14580,8 +14586,8 @@
})
(define_insn_and_split "<insn>64ti2_doubleword"
- [(set (match_operand:TI 0 "register_operand" "=r,r,r")
- (any_rotate:TI (match_operand:TI 1 "nonimmediate_operand" "0,r,o")
+ [(set (match_operand:TI 0 "register_operand" "=r,r")
+ (any_rotate:TI (match_operand:TI 1 "register_operand" "0,r")
(const_int 64)))]
"TARGET_64BIT"
"#"
diff --git a/gcc/testsuite/g++.target/i386/pr110792.C b/gcc/testsuite/g++.target/i386/pr110792.C
new file mode 100644
index 0000000..ce21a7a
--- /dev/null
+++ b/gcc/testsuite/g++.target/i386/pr110792.C
@@ -0,0 +1,16 @@
+/* { dg-do compile { target ia32 } } */
+/* { dg-options "-O2" } */
+
+template <int ROT, typename T>
+inline T rotr(T input)
+{
+ return static_cast<T>((input >> ROT) | (input << (8 * sizeof(T) - ROT)));
+}
+
+unsigned long long WHIRL_S[256] = {0x18186018C07830D8};
+unsigned long long whirl(unsigned char x0)
+{
+ const unsigned long long s4 = WHIRL_S[x0&0xFF];
+ return rotr<32>(s4);
+}
+/* { dg-final { scan-assembler-not "movl\tWHIRL_S\\+4\\(,%eax,8\\), %eax" } } */
diff --git a/gcc/testsuite/gcc.target/i386/pr110792.c b/gcc/testsuite/gcc.target/i386/pr110792.c
new file mode 100644
index 0000000..b65125c
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/pr110792.c
@@ -0,0 +1,18 @@
+/* { dg-do compile { target int128 } } */
+/* { dg-options "-O2" } */
+
+static inline unsigned __int128 rotr(unsigned __int128 input)
+{
+ return ((input >> 64) | (input << (64)));
+}
+
+unsigned __int128 WHIRL_S[256] = {((__int128)0x18186018C07830D8) << 64 |0x18186018C07830D8};
+unsigned __int128 whirl(unsigned char x0)
+{
+ register int t __asm("rdi") = x0&0xFF;
+ const unsigned __int128 s4 = WHIRL_S[t];
+ register unsigned __int128 tt __asm("rdi") = rotr(s4);
+ asm("":::"memory");
+ return tt;
+}
+/* { dg-final { scan-assembler-not "movq\tWHIRL_S\\+8\\(%rdi\\), %rdi" } } */
--
2.41.0
......@@ -24,8 +24,8 @@ CBUILDROOT="/"
_cross_configure="--disable-bootstrap --with-sysroot=/usr/$CTARGET"
pkgname=gcc-riscv64
pkgver=13.1.1_git20230722
# i.e. 13.1.1, must match gcc/BASE-VER
pkgver=13.2.1_git20231014
# i.e. 13.2.1, must match gcc/BASE-VER
_pkgbase="${pkgver%%_git*}"
# date component from snapshots
_pkgsnap="${pkgver##*_git}"
......@@ -34,7 +34,7 @@ _pkgsnap="${pkgver##*_git}"
[ "$CHOST" != "$CTARGET" ] && _target="-$CTARGET_ARCH" || _target=""
pkgname=gcc-riscv64
pkgrel=2
pkgrel=0
pkgdesc="Stage2 cross-compiler for riscv64"
url="https://gcc.gnu.org"
arch="x86_64"
......@@ -268,9 +268,13 @@ source="https://dev.alpinelinux.org/archive/gcc/${_pkgbase%%.*}-$_pkgsnap/gcc-${
0032-libgnat-time_t-is-always-64-bit-on-musl-libc.patch
0033-libphobos-do-not-use-LFS64-symbols.patch
0034-libgo-fix-lfs64-use.patch
0035-Fix-ICE-observed-in-PR110280.patch
0036-PR110792-Early-clobber-issues-with-rot32di2-on-i386.patch
"
# secfixes:
# 13.2.1_git20231014-r0:
# - CVE-2023-4039
# we build out-of-tree
_gccdir="$srcdir"/gcc-${_pkgbase%%.*}-$_pkgsnap
_gcclibdir="/usr/lib/gcc/$CTARGET/${_pkgbase:-$pkgver}"
......@@ -783,7 +787,7 @@ gdb() {
}
sha512sums="
284719308cad4546ebd85934fb9f12112e8f1a4c3e5beea0760da1f73509907c194e7c133e6e755b6148bd1c51a72c071ac0d16b05641d901af7105461686655 gcc-13-20230722.tar.xz
406673a62deba759fc0532a801b3f57cabf894ea328587b23e62a707ba5767b0e3ae9b3f86bf3c6fcf13e8a3c30bc470e6598b625c8231efb629034211c162c2 gcc-13-20231014.tar.xz
1ecffba1b07d60e1b4422302b032bbea918b674c8e12b30aa6965b544d700ce86b61e9f7b8d402c6caf59257f491a394dd0912f0948565d6eae9335ee54f3b35 0001-posix_memalign.patch
163f282455b6a4df33f011bcd8b0440566ba0ffaeeab30d8ac52d39948980a56881ca0eff60687129d59556389a58b9d64e7768750bd70b1fe0fedbc9fc30dc2 0002-gcc-poison-system-directories.patch
3f24bb6a50d3c45b71ea05590e32fe3e69b91377ab185352891d5035c76ed193117c6d0b314a4c364bcf136b9a9dd5c926d6c7c30ab436976c121ebfea8d3ddd 0003-specs-turn-on-Wl-z-now-by-default.patch
......@@ -818,5 +822,5 @@ d47b559075f40d526235f47b91da1d0cf6bfe6c5b7311bbfe08af9dd6e8f27e6c7cd82e3b2d529aa
b325035cb7122d79c6b42ca6d3fc9e02319ed2f7cddb0639dff25d2798d2ce63812cd623462cdf95e21c9ffbf2412193f8b9fc89a4c36fa5a6a041661ac7399d 0032-libgnat-time_t-is-always-64-bit-on-musl-libc.patch
c474f34e6f9a4239d486a65141a133dbe8ce91427d502a57a9fd6eb403478a2b5715ba74f24c1cc0761e16eec77ba2c1ca921fb7d7bc1e040fc3703fc9559e75 0033-libphobos-do-not-use-LFS64-symbols.patch
c4482ffc36e7894b2140800159f4cbc9a3e9011e43a69b69f4fa92d5a11e2ee645c7e21df4423dd1e0636e8890849a5719647bfbdf84f951d638f8f488cb718c 0034-libgo-fix-lfs64-use.patch
048d767f4477c92ee6835850d13063ede21c0be751d0945c94445d04054e134cdc617eeb0b1ac8c892a604d8644580fcfebeccaf537d6b7380558ac6378e445a 0035-Fix-ICE-observed-in-PR110280.patch
cc1e10ac6e72db816f09325e301103109cc212a6f3de3ce0b9b038d149233c467319d203941695dbf3d7b9e2dcbbcd17609cdb056e831fcc323cd592423882d8 0036-PR110792-Early-clobber-issues-with-rot32di2-on-i386.patch
"
From 47b4bd4deb2c356bb07d2a96f22127aefafec3a4 Mon Sep 17 00:00:00 2001
From: Szabolcs Nagy <nsz@port70.net>
Date: Fri, 26 Jan 2018 20:32:50 +0000
Subject: [PATCH 01/35] posix_memalign
---
gcc/config/i386/pmm_malloc.h | 9 +++++----
1 file changed, 5 insertions(+), 4 deletions(-)
diff --git a/gcc/config/i386/pmm_malloc.h b/gcc/config/i386/pmm_malloc.h
index 3527283693b..c4071b64b53 100644
--- a/gcc/config/i386/pmm_malloc.h
+++ b/gcc/config/i386/pmm_malloc.h
@@ -27,12 +27,13 @@
#include <stdlib.h>
/* We can't depend on <stdlib.h> since the prototype of posix_memalign
- may not be visible. */
+ may not be visible and we can't pollute the namespace either. */
#ifndef __cplusplus
-extern int posix_memalign (void **, size_t, size_t);
+extern int _mm_posix_memalign (void **, size_t, size_t)
#else
-extern "C" int posix_memalign (void **, size_t, size_t) throw ();
+extern "C" int _mm_posix_memalign (void **, size_t, size_t) throw ()
#endif
+__asm__("posix_memalign");
static __inline void *
_mm_malloc (size_t __size, size_t __alignment)
@@ -42,7 +43,7 @@ _mm_malloc (size_t __size, size_t __alignment)
return malloc (__size);
if (__alignment == 2 || (sizeof (void *) == 8 && __alignment == 4))
__alignment = sizeof (void *);
- if (posix_memalign (&__ptr, __alignment, __size) == 0)
+ if (_mm_posix_memalign (&__ptr, __alignment, __size) == 0)
return __ptr;
else
return NULL;
--
2.41.0