The appended fixes it for me. Can you please test?
[ apply with `git am --scissors' ]
Thanks,
Emilio
---- 8< ----
Commit e75449a3 ("target/aarch64: optimize indirect branches") causes
a regression by which aarch64 guests freeze under TCG with -smp > 1,
even with `-accel accel=tcg,thread=single' (i.e. MTTCG disabled).
I isolated the problem to the MSR handler. This patch forces an exit
after the handler is executed, which fixes the regression.
Signed-off-by: Emilio G. Cota <cota@braap.org>
---
target/arm/translate-a64.c | 6 +++++-
1 file changed, 5 insertions(+), 1 deletion(-)
diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c
index 860e279..5a609a0 100644
--- a/target/arm/translate-a64.c
+++ b/target/arm/translate-a64.c
@@ -1422,7 +1422,7 @@ static void handle_msr_i(DisasContext *s, uint32_t insn,
gen_helper_msr_i_pstate(cpu_env, tcg_op, tcg_imm);
tcg_temp_free_i32(tcg_imm);
tcg_temp_free_i32(tcg_op);
- s->is_jmp = DISAS_UPDATE;
+ s->is_jmp = DISAS_EXIT;
break;
}
default:
@@ -11362,6 +11362,10 @@ void gen_intermediate_code_a64(ARMCPU *cpu, TranslationBlock *tb)
case DISAS_NEXT:
gen_goto_tb(dc, 1, dc->pc);
break;
+ case DISAS_EXIT:
+ gen_a64_set_pc_im(dc->pc);
+ tcg_gen_exit_tb(0);
+ break;
default:
case DISAS_UPDATE:
gen_a64_set_pc_im(dc->pc);
--
2.7.4
Hi,
This series failed automatic build test. Please find the testing commands and
their output below. If you have docker installed, you can probably reproduce it
locally.
Subject: [Qemu-devel] [PATCH] target/aarch64: exit to main loop after handling MSR
Type: series
Message-id: 20170613225352.GA26288@flamenco
=== TEST SCRIPT BEGIN ===
#!/bin/bash
set -e
git submodule update --init dtc
# Let docker tests dump environment info
export SHOW_ENV=1
export J=8
time make docker-test-quick@centos6
time make docker-test-mingw@fedora
time make docker-test-build@min-glib
=== TEST SCRIPT END ===
Updating 3c8cf5a9c21ff8782164d1def7f44bd888713384
From https://github.com/patchew-project/qemu
* [new tag] patchew/20170613225352.GA26288@flamenco -> patchew/20170613225352.GA26288@flamenco
Switched to a new branch 'test'
308f131 target/aarch64: exit to main loop after handling MSR
=== OUTPUT BEGIN ===
Submodule 'dtc' (git://git.qemu-project.org/dtc.git) registered for path 'dtc'
Cloning into '/var/tmp/patchew-tester-tmp-7o9lu4by/src/dtc'...
Submodule path 'dtc': checked out '558cd81bdd432769b59bff01240c44f82cfb1a9d'
BUILD centos6
make[1]: Entering directory '/var/tmp/patchew-tester-tmp-7o9lu4by/src'
ARCHIVE qemu.tgz
ARCHIVE dtc.tgz
COPY RUNNER
RUN test-quick in qemu:centos6
Packages installed:
SDL-devel-1.2.14-7.el6_7.1.x86_64
ccache-3.1.6-2.el6.x86_64
epel-release-6-8.noarch
gcc-4.4.7-17.el6.x86_64
git-1.7.1-4.el6_7.1.x86_64
glib2-devel-2.28.8-5.el6.x86_64
libfdt-devel-1.4.0-1.el6.x86_64
make-3.81-23.el6.x86_64
package g++ is not installed
pixman-devel-0.32.8-1.el6.x86_64
tar-1.23-15.el6_8.x86_64
zlib-devel-1.2.3-29.el6.x86_64
Environment variables:
PACKAGES=libfdt-devel ccache tar git make gcc g++ zlib-devel glib2-devel SDL-devel pixman-devel epel-release
HOSTNAME=546e27c66238
TERM=xterm
MAKEFLAGS= -j8
HISTSIZE=1000
J=8
USER=root
CCACHE_DIR=/var/tmp/ccache
EXTRA_CONFIGURE_OPTS=
V=
SHOW_ENV=1
MAIL=/var/spool/mail/root
PATH=/usr/lib/ccache:/usr/lib64/ccache:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin
PWD=/
LANG=en_US.UTF-8
TARGET_LIST=
HISTCONTROL=ignoredups
SHLVL=1
HOME=/root
TEST_DIR=/tmp/qemu-test
LOGNAME=root
LESSOPEN=||/usr/bin/lesspipe.sh %s
FEATURES= dtc
DEBUG=
G_BROKEN_FILENAMES=1
CCACHE_HASHDIR=
_=/usr/bin/env
Configure options:
--enable-werror --target-list=x86_64-softmmu,aarch64-softmmu --prefix=/var/tmp/qemu-build/install
/tmp/qemu-test/src/configure: line 4683: c++: command not found
No C++ compiler available; disabling C++ specific optional code
Install prefix /var/tmp/qemu-build/install
BIOS directory /var/tmp/qemu-build/install/share/qemu
binary directory /var/tmp/qemu-build/install/bin
library directory /var/tmp/qemu-build/install/lib
module directory /var/tmp/qemu-build/install/lib/qemu
libexec directory /var/tmp/qemu-build/install/libexec
include directory /var/tmp/qemu-build/install/include
config directory /var/tmp/qemu-build/install/etc
local state directory /var/tmp/qemu-build/install/var
Manual directory /var/tmp/qemu-build/install/share/man
ELF interp prefix /usr/gnemul/qemu-%M
Source path /tmp/qemu-test/src
C compiler cc
Host C compiler cc
C++ compiler
Objective-C compiler cc
ARFLAGS rv
CFLAGS -O2 -U_FORTIFY_SOURCE -D_FORTIFY_SOURCE=2 -g
QEMU_CFLAGS -I/usr/include/pixman-1 -I$(SRC_PATH)/dtc/libfdt -pthread -I/usr/include/glib-2.0 -I/usr/lib64/glib-2.0/include -fPIE -DPIE -m64 -mcx16 -D_GNU_SOURCE -D_FILE_OFFSET_BITS=64 -D_LARGEFILE_SOURCE -Wstrict-prototypes -Wredundant-decls -Wall -Wundef -Wwrite-strings -Wmissing-prototypes -fno-strict-aliasing -fno-common -fwrapv -Wendif-labels -Wno-missing-include-dirs -Wempty-body -Wnested-externs -Wformat-security -Wformat-y2k -Winit-self -Wignored-qualifiers -Wold-style-declaration -Wold-style-definition -Wtype-limits -fstack-protector-all
LDFLAGS -Wl,--warn-common -Wl,-z,relro -Wl,-z,now -pie -m64 -g
make make
install install
python python -B
smbd /usr/sbin/smbd
module support no
host CPU x86_64
host big endian no
target list x86_64-softmmu aarch64-softmmu
tcg debug enabled no
gprof enabled no
sparse enabled no
strip binaries yes
profiler no
static build no
pixman system
SDL support yes (1.2.14)
GTK support no
GTK GL support no
VTE support no
TLS priority NORMAL
GNUTLS support no
GNUTLS rnd no
libgcrypt no
libgcrypt kdf no
nettle no
nettle kdf no
libtasn1 no
curses support no
virgl support no
curl support no
mingw32 support no
Audio drivers oss
Block whitelist (rw)
Block whitelist (ro)
VirtFS support no
VNC support yes
VNC SASL support no
VNC JPEG support no
VNC PNG support no
xen support no
brlapi support no
bluez support no
Documentation no
PIE yes
vde support no
netmap support no
Linux AIO support no
ATTR/XATTR support yes
Install blobs yes
KVM support yes
HAX support no
RDMA support no
TCG interpreter no
fdt support yes
preadv support yes
fdatasync yes
madvise yes
posix_madvise yes
libcap-ng support no
vhost-net support yes
vhost-scsi support yes
vhost-vsock support yes
Trace backends log
spice support no
rbd support no
xfsctl support no
smartcard support no
libusb no
usb net redir no
OpenGL support no
OpenGL dmabufs no
libiscsi support no
libnfs support no
build guest agent yes
QGA VSS support no
QGA w32 disk info no
QGA MSI support no
seccomp support no
coroutine backend ucontext
coroutine pool yes
debug stack usage no
GlusterFS support no
gcov gcov
gcov enabled no
TPM support yes
libssh2 support no
TPM passthrough yes
QOM debugging yes
Live block migration yes
lzo support no
snappy support no
bzip2 support no
NUMA host support no
tcmalloc support no
jemalloc support no
avx2 optimization no
replication support yes
VxHS block device no
GEN x86_64-softmmu/config-devices.mak.tmp
mkdir -p dtc/libfdt
mkdir -p dtc/tests
GEN aarch64-softmmu/config-devices.mak.tmp
GEN config-host.h
GEN qemu-options.def
GEN qmp-commands.h
GEN qapi-types.h
GEN qapi-visit.h
GEN qapi-event.h
GEN x86_64-softmmu/config-devices.mak
GEN qmp-marshal.c
GEN aarch64-softmmu/config-devices.mak
GEN qapi-types.c
GEN qapi-visit.c
GEN qapi-event.c
GEN qmp-introspect.h
GEN qmp-introspect.c
GEN trace/generated-tcg-tracers.h
GEN trace/generated-helpers-wrappers.h
GEN trace/generated-helpers.h
GEN trace/generated-helpers.c
GEN module_block.h
GEN tests/test-qapi-types.h
GEN tests/test-qapi-visit.h
GEN tests/test-qmp-commands.h
GEN tests/test-qapi-event.h
GEN tests/test-qmp-introspect.h
GEN trace-root.h
GEN util/trace.h
GEN crypto/trace.h
GEN io/trace.h
GEN migration/trace.h
GEN block/trace.h
GEN backends/trace.h
GEN chardev/trace.h
GEN hw/block/trace.h
GEN hw/block/dataplane/trace.h
GEN hw/char/trace.h
GEN hw/intc/trace.h
GEN hw/net/trace.h
GEN hw/virtio/trace.h
GEN hw/audio/trace.h
GEN hw/misc/trace.h
GEN hw/usb/trace.h
GEN hw/scsi/trace.h
GEN hw/nvram/trace.h
GEN hw/display/trace.h
GEN hw/input/trace.h
GEN hw/timer/trace.h
GEN hw/dma/trace.h
GEN hw/sparc/trace.h
GEN hw/sd/trace.h
GEN hw/isa/trace.h
GEN hw/mem/trace.h
GEN hw/i386/trace.h
GEN hw/i386/xen/trace.h
GEN hw/9pfs/trace.h
GEN hw/ppc/trace.h
GEN hw/pci/trace.h
GEN hw/s390x/trace.h
GEN hw/vfio/trace.h
GEN hw/acpi/trace.h
GEN hw/arm/trace.h
GEN hw/alpha/trace.h
GEN hw/xen/trace.h
GEN ui/trace.h
GEN audio/trace.h
GEN net/trace.h
GEN target/arm/trace.h
GEN target/i386/trace.h
GEN target/mips/trace.h
GEN target/sparc/trace.h
GEN target/s390x/trace.h
GEN target/ppc/trace.h
GEN qom/trace.h
GEN linux-user/trace.h
GEN trace-root.c
GEN qapi/trace.h
GEN util/trace.c
GEN crypto/trace.c
GEN io/trace.c
GEN migration/trace.c
GEN block/trace.c
GEN backends/trace.c
GEN chardev/trace.c
GEN hw/block/trace.c
GEN hw/block/dataplane/trace.c
GEN hw/char/trace.c
GEN hw/intc/trace.c
GEN hw/net/trace.c
GEN hw/virtio/trace.c
GEN hw/audio/trace.c
GEN hw/misc/trace.c
GEN hw/usb/trace.c
GEN hw/scsi/trace.c
GEN hw/nvram/trace.c
GEN hw/display/trace.c
GEN hw/input/trace.c
GEN hw/timer/trace.c
GEN hw/dma/trace.c
GEN hw/sparc/trace.c
GEN hw/sd/trace.c
GEN hw/isa/trace.c
GEN hw/mem/trace.c
GEN hw/i386/trace.c
GEN hw/i386/xen/trace.c
GEN hw/9pfs/trace.c
GEN hw/ppc/trace.c
GEN hw/pci/trace.c
GEN hw/s390x/trace.c
GEN hw/vfio/trace.c
GEN hw/acpi/trace.c
GEN hw/arm/trace.c
GEN hw/alpha/trace.c
GEN hw/xen/trace.c
GEN ui/trace.c
GEN audio/trace.c
GEN net/trace.c
GEN target/arm/trace.c
GEN target/i386/trace.c
GEN target/mips/trace.c
GEN target/sparc/trace.c
GEN target/s390x/trace.c
GEN target/ppc/trace.c
GEN qom/trace.c
GEN linux-user/trace.c
GEN qapi/trace.c
GEN config-all-devices.mak
DEP /tmp/qemu-test/src/dtc/tests/dumptrees.c
DEP /tmp/qemu-test/src/dtc/tests/trees.S
DEP /tmp/qemu-test/src/dtc/tests/testutils.c
DEP /tmp/qemu-test/src/dtc/tests/value-labels.c
DEP /tmp/qemu-test/src/dtc/tests/asm_tree_dump.c
DEP /tmp/qemu-test/src/dtc/tests/truncated_property.c
DEP /tmp/qemu-test/src/dtc/tests/check_path.c
DEP /tmp/qemu-test/src/dtc/tests/overlay_bad_fixup.c
DEP /tmp/qemu-test/src/dtc/tests/overlay.c
DEP /tmp/qemu-test/src/dtc/tests/subnode_iterate.c
DEP /tmp/qemu-test/src/dtc/tests/property_iterate.c
DEP /tmp/qemu-test/src/dtc/tests/integer-expressions.c
DEP /tmp/qemu-test/src/dtc/tests/utilfdt_test.c
DEP /tmp/qemu-test/src/dtc/tests/path_offset_aliases.c
DEP /tmp/qemu-test/src/dtc/tests/add_subnode_with_nops.c
DEP /tmp/qemu-test/src/dtc/tests/dtbs_equal_unordered.c
DEP /tmp/qemu-test/src/dtc/tests/dtb_reverse.c
DEP /tmp/qemu-test/src/dtc/tests/dtbs_equal_ordered.c
DEP /tmp/qemu-test/src/dtc/tests/extra-terminating-null.c
DEP /tmp/qemu-test/src/dtc/tests/incbin.c
DEP /tmp/qemu-test/src/dtc/tests/boot-cpuid.c
DEP /tmp/qemu-test/src/dtc/tests/phandle_format.c
DEP /tmp/qemu-test/src/dtc/tests/path-references.c
DEP /tmp/qemu-test/src/dtc/tests/references.c
DEP /tmp/qemu-test/src/dtc/tests/string_escapes.c
DEP /tmp/qemu-test/src/dtc/tests/propname_escapes.c
DEP /tmp/qemu-test/src/dtc/tests/appendprop2.c
DEP /tmp/qemu-test/src/dtc/tests/appendprop1.c
DEP /tmp/qemu-test/src/dtc/tests/del_node.c
DEP /tmp/qemu-test/src/dtc/tests/del_property.c
DEP /tmp/qemu-test/src/dtc/tests/setprop.c
DEP /tmp/qemu-test/src/dtc/tests/set_name.c
DEP /tmp/qemu-test/src/dtc/tests/rw_tree1.c
DEP /tmp/qemu-test/src/dtc/tests/open_pack.c
DEP /tmp/qemu-test/src/dtc/tests/nopulate.c
DEP /tmp/qemu-test/src/dtc/tests/mangle-layout.c
DEP /tmp/qemu-test/src/dtc/tests/move_and_save.c
DEP /tmp/qemu-test/src/dtc/tests/sw_tree1.c
DEP /tmp/qemu-test/src/dtc/tests/nop_node.c
DEP /tmp/qemu-test/src/dtc/tests/nop_property.c
DEP /tmp/qemu-test/src/dtc/tests/setprop_inplace.c
DEP /tmp/qemu-test/src/dtc/tests/stringlist.c
DEP /tmp/qemu-test/src/dtc/tests/sized_cells.c
DEP /tmp/qemu-test/src/dtc/tests/addr_size_cells.c
DEP /tmp/qemu-test/src/dtc/tests/notfound.c
DEP /tmp/qemu-test/src/dtc/tests/char_literal.c
DEP /tmp/qemu-test/src/dtc/tests/get_alias.c
DEP /tmp/qemu-test/src/dtc/tests/node_offset_by_compatible.c
DEP /tmp/qemu-test/src/dtc/tests/node_check_compatible.c
DEP /tmp/qemu-test/src/dtc/tests/node_offset_by_phandle.c
DEP /tmp/qemu-test/src/dtc/tests/parent_offset.c
DEP /tmp/qemu-test/src/dtc/tests/node_offset_by_prop_value.c
DEP /tmp/qemu-test/src/dtc/tests/supernode_atdepth_offset.c
DEP /tmp/qemu-test/src/dtc/tests/get_path.c
DEP /tmp/qemu-test/src/dtc/tests/get_phandle.c
DEP /tmp/qemu-test/src/dtc/tests/getprop.c
DEP /tmp/qemu-test/src/dtc/tests/get_name.c
DEP /tmp/qemu-test/src/dtc/tests/path_offset.c
DEP /tmp/qemu-test/src/dtc/tests/subnode_offset.c
DEP /tmp/qemu-test/src/dtc/tests/find_property.c
DEP /tmp/qemu-test/src/dtc/tests/root_node.c
DEP /tmp/qemu-test/src/dtc/libfdt/fdt_overlay.c
DEP /tmp/qemu-test/src/dtc/tests/get_mem_rsv.c
DEP /tmp/qemu-test/src/dtc/libfdt/fdt_addresses.c
DEP /tmp/qemu-test/src/dtc/libfdt/fdt_empty_tree.c
DEP /tmp/qemu-test/src/dtc/libfdt/fdt_rw.c
DEP /tmp/qemu-test/src/dtc/libfdt/fdt_sw.c
DEP /tmp/qemu-test/src/dtc/libfdt/fdt_strerror.c
DEP /tmp/qemu-test/src/dtc/libfdt/fdt_wip.c
DEP /tmp/qemu-test/src/dtc/libfdt/fdt.c
DEP /tmp/qemu-test/src/dtc/libfdt/fdt_ro.c
DEP /tmp/qemu-test/src/dtc/util.c
DEP /tmp/qemu-test/src/dtc/fdtput.c
DEP /tmp/qemu-test/src/dtc/fdtget.c
DEP /tmp/qemu-test/src/dtc/fdtdump.c
LEX convert-dtsv0-lexer.lex.c
make[1]: flex: Command not found
DEP /tmp/qemu-test/src/dtc/srcpos.c
BISON dtc-parser.tab.c
make[1]: bison: Command not found
LEX dtc-lexer.lex.c
make[1]: flex: Command not found
DEP /tmp/qemu-test/src/dtc/livetree.c
DEP /tmp/qemu-test/src/dtc/treesource.c
DEP /tmp/qemu-test/src/dtc/fstree.c
DEP /tmp/qemu-test/src/dtc/flattree.c
DEP /tmp/qemu-test/src/dtc/dtc.c
DEP /tmp/qemu-test/src/dtc/data.c
DEP /tmp/qemu-test/src/dtc/checks.c
CHK version_gen.h
LEX convert-dtsv0-lexer.lex.c
make[1]: flex: Command not found
BISON dtc-parser.tab.c
LEX dtc-lexer.lex.c
make[1]: flex: Command not found
make[1]: bison: Command not found
UPD version_gen.h
DEP /tmp/qemu-test/src/dtc/util.c
LEX convert-dtsv0-lexer.lex.c
BISON dtc-parser.tab.c
make[1]: flex: Command not found
make[1]: bison: Command not found
LEX dtc-lexer.lex.c
make[1]: flex: Command not found
CC libfdt/fdt.o
CC libfdt/fdt_ro.o
CC libfdt/fdt_rw.o
CC libfdt/fdt_strerror.o
CC libfdt/fdt_wip.o
CC libfdt/fdt_sw.o
CC libfdt/fdt_empty_tree.o
CC libfdt/fdt_addresses.o
CC libfdt/fdt_overlay.o
AR libfdt/libfdt.a
ar: creating libfdt/libfdt.a
a - libfdt/fdt.o
a - libfdt/fdt_ro.o
a - libfdt/fdt_wip.o
a - libfdt/fdt_sw.o
a - libfdt/fdt_rw.o
a - libfdt/fdt_strerror.o
a - libfdt/fdt_empty_tree.o
a - libfdt/fdt_addresses.o
a - libfdt/fdt_overlay.o
BISON dtc-parser.tab.c
LEX dtc-lexer.lex.c
make[1]: bison: Command not found
make[1]: flex: Command not found
LEX convert-dtsv0-lexer.lex.c
make[1]: flex: Command not found
CC tests/qemu-iotests/socket_scm_helper.o
GEN qga/qapi-generated/qga-qapi-visit.h
GEN qga/qapi-generated/qga-qapi-types.h
GEN qga/qapi-generated/qga-qmp-commands.h
GEN qga/qapi-generated/qga-qapi-types.c
GEN qga/qapi-generated/qga-qapi-visit.c
CC qmp-introspect.o
GEN qga/qapi-generated/qga-qmp-marshal.c
CC qapi-visit.o
CC qapi-types.o
CC qapi-event.o
CC qapi/qapi-visit-core.o
CC qapi/qapi-dealloc-visitor.o
CC qapi/qobject-input-visitor.o
CC qapi/qobject-output-visitor.o
CC qapi/qmp-dispatch.o
CC qapi/qmp-registry.o
CC qapi/string-input-visitor.o
CC qapi/string-output-visitor.o
CC qapi/qapi-clone-visitor.o
CC qapi/opts-visitor.o
CC qapi/qmp-event.o
CC qapi/qapi-util.o
CC qobject/qnull.o
CC qobject/qint.o
CC qobject/qdict.o
CC qobject/qstring.o
CC qobject/qlist.o
CC qobject/qfloat.o
CC qobject/qbool.o
CC qobject/qjson.o
CC qobject/qobject.o
CC qobject/json-lexer.o
CC qobject/json-streamer.o
CC qobject/json-parser.o
CC trace/control.o
CC trace/qmp.o
CC util/osdep.o
CC util/cutils.o
CC util/unicode.o
CC util/bufferiszero.o
CC util/qemu-timer-common.o
CC util/lockcnt.o
CC util/aiocb.o
CC util/async.o
CC util/thread-pool.o
CC util/main-loop.o
CC util/qemu-timer.o
CC util/iohandler.o
CC util/aio-posix.o
CC util/compatfd.o
CC util/mmap-alloc.o
CC util/event_notifier-posix.o
CC util/oslib-posix.o
CC util/qemu-openpty.o
CC util/qemu-thread-posix.o
CC util/memfd.o
CC util/envlist.o
CC util/path.o
CC util/module.o
CC util/host-utils.o
CC util/bitmap.o
CC util/fifo8.o
CC util/bitops.o
CC util/hbitmap.o
CC util/acl.o
CC util/error.o
CC util/qemu-error.o
CC util/iov.o
CC util/qemu-config.o
CC util/id.o
CC util/qemu-sockets.o
CC util/uri.o
CC util/qemu-option.o
CC util/notify.o
CC util/keyval.o
CC util/qemu-progress.o
CC util/hexdump.o
CC util/crc32c.o
CC util/uuid.o
CC util/throttle.o
CC util/getauxval.o
CC util/readline.o
CC util/qemu-coroutine.o
CC util/rcu.o
CC util/qemu-coroutine-lock.o
CC util/qemu-coroutine-io.o
CC util/coroutine-ucontext.o
CC util/buffer.o
CC util/qemu-coroutine-sleep.o
CC util/timed-average.o
CC util/qdist.o
CC util/log.o
CC util/base64.o
CC util/qht.o
CC util/range.o
CC util/systemd.o
CC util/trace.o
CC trace-root.o
CC crypto/trace.o
CC io/trace.o
CC migration/trace.o
CC block/trace.o
CC backends/trace.o
CC chardev/trace.o
CC hw/block/trace.o
CC hw/block/dataplane/trace.o
CC hw/char/trace.o
CC hw/intc/trace.o
CC hw/net/trace.o
CC hw/virtio/trace.o
CC hw/audio/trace.o
CC hw/misc/trace.o
CC hw/usb/trace.o
CC hw/scsi/trace.o
CC hw/nvram/trace.o
CC hw/display/trace.o
CC hw/input/trace.o
CC hw/timer/trace.o
CC hw/dma/trace.o
CC hw/sparc/trace.o
CC hw/sd/trace.o
CC hw/isa/trace.o
CC hw/mem/trace.o
CC hw/i386/xen/trace.o
CC hw/i386/trace.o
CC hw/9pfs/trace.o
CC hw/ppc/trace.o
CC hw/pci/trace.o
CC hw/s390x/trace.o
CC hw/vfio/trace.o
CC hw/acpi/trace.o
CC hw/arm/trace.o
CC hw/alpha/trace.o
CC hw/xen/trace.o
CC audio/trace.o
CC net/trace.o
CC ui/trace.o
CC target/arm/trace.o
CC target/i386/trace.o
CC target/mips/trace.o
CC target/sparc/trace.o
CC target/s390x/trace.o
CC target/ppc/trace.o
CC linux-user/trace.o
CC qom/trace.o
CC qapi/trace.o
CC crypto/pbkdf-stub.o
CC stubs/arch-query-cpu-model-expansion.o
CC stubs/arch-query-cpu-def.o
CC stubs/arch-query-cpu-model-comparison.o
CC stubs/arch-query-cpu-model-baseline.o
CC stubs/bdrv-next-monitor-owned.o
CC stubs/blk-commit-all.o
CC stubs/blockdev-close-all-bdrv-states.o
CC stubs/cpu-get-clock.o
CC stubs/clock-warp.o
CC stubs/cpu-get-icount.o
CC stubs/dump.o
CC stubs/error-printf.o
CC stubs/gdbstub.o
CC stubs/fdset.o
CC stubs/get-vm-name.o
CC stubs/iothread.o
CC stubs/iothread-lock.o
CC stubs/is-daemonized.o
CC stubs/machine-init-done.o
CC stubs/migr-blocker.o
CC stubs/monitor.o
CC stubs/notify-event.o
CC stubs/qtest.o
CC stubs/replay.o
CC stubs/runstate-check.o
CC stubs/set-fd-handler.o
CC stubs/slirp.o
CC stubs/sysbus.o
CC stubs/trace-control.o
CC stubs/uuid.o
CC stubs/vm-stop.o
CC stubs/vmstate.o
CC stubs/qmp_pc_dimm_device_list.o
CC stubs/target-monitor-defs.o
CC stubs/target-get-monitor-def.o
CC stubs/pc_madt_cpu_entry.o
CC stubs/vmgenid.o
CC stubs/xen-common.o
CC stubs/xen-hvm.o
CC contrib/ivshmem-client/main.o
CC contrib/ivshmem-client/ivshmem-client.o
CC contrib/ivshmem-server/ivshmem-server.o
CC contrib/ivshmem-server/main.o
CC qemu-nbd.o
CC block.o
CC blockjob.o
CC replication.o
CC qemu-io-cmds.o
CC block/qcow.o
CC block/raw-format.o
CC block/vdi.o
CC block/cloop.o
CC block/vmdk.o
CC block/bochs.o
CC block/vpc.o
CC block/vvfat.o
CC block/dmg.o
CC block/qcow2.o
CC block/qcow2-refcount.o
CC block/qcow2-cluster.o
CC block/qcow2-snapshot.o
CC block/qcow2-cache.o
CC block/qed.o
CC block/qed-l2-cache.o
CC block/qed-gencb.o
CC block/qed-table.o
CC block/qed-cluster.o
CC block/qed-check.o
CC block/vhdx-endian.o
CC block/vhdx.o
CC block/vhdx-log.o
CC block/quorum.o
CC block/blkdebug.o
CC block/parallels.o
CC block/blkverify.o
CC block/blkreplay.o
CC block/block-backend.o
CC block/snapshot.o
CC block/qapi.o
CC block/file-posix.o
CC block/null.o
CC block/mirror.o
CC block/commit.o
CC block/io.o
CC block/throttle-groups.o
CC block/nbd.o
CC block/nbd-client.o
CC block/sheepdog.o
CC block/accounting.o
CC block/dirty-bitmap.o
CC block/write-threshold.o
CC block/backup.o
CC block/replication.o
CC block/crypto.o
CC nbd/server.o
CC nbd/client.o
CC nbd/common.o
CC crypto/init.o
CC crypto/hash.o
CC crypto/hash-glib.o
CC crypto/hmac-glib.o
CC crypto/hmac.o
CC crypto/aes.o
CC crypto/desrfb.o
CC crypto/cipher.o
CC crypto/tlscreds.o
CC crypto/tlscredsx509.o
CC crypto/tlscredsanon.o
CC crypto/tlssession.o
CC crypto/secret.o
CC crypto/random-platform.o
CC crypto/pbkdf.o
CC crypto/ivgen.o
CC crypto/ivgen-essiv.o
CC crypto/ivgen-plain.o
CC crypto/ivgen-plain64.o
CC crypto/afsplit.o
CC crypto/xts.o
CC crypto/block.o
CC crypto/block-qcow.o
CC crypto/block-luks.o
CC io/channel.o
CC io/channel-buffer.o
CC io/channel-command.o
CC io/channel-file.o
CC io/channel-socket.o
CC io/channel-tls.o
CC io/channel-watch.o
CC io/channel-websock.o
CC io/channel-util.o
CC io/dns-resolver.o
CC io/task.o
CC qom/object.o
CC qom/qom-qobject.o
CC qom/container.o
CC qom/object_interfaces.o
GEN qemu-img-cmds.h
CC qemu-io.o
CC blockdev.o
CC qemu-bridge-helper.o
CC blockdev-nbd.o
CC iothread.o
CC qdev-monitor.o
CC device-hotplug.o
CC os-posix.o
CC accel.o
CC bt-host.o
CC bt-vhci.o
CC dma-helpers.o
CC vl.o
CC tpm.o
CC device_tree.o
CC qmp-marshal.o
CC qmp.o
CC hmp.o
CC cpus-common.o
CC audio/audio.o
CC audio/noaudio.o
CC audio/wavaudio.o
CC audio/mixeng.o
CC audio/sdlaudio.o
CC audio/ossaudio.o
CC audio/wavcapture.o
CC backends/rng.o
CC backends/rng-egd.o
CC backends/rng-random.o
CC backends/tpm.o
CC backends/hostmem.o
CC backends/hostmem-ram.o
CC backends/hostmem-file.o
CC backends/cryptodev.o
CC backends/cryptodev-builtin.o
CC block/stream.o
CC chardev/msmouse.o
CC chardev/wctablet.o
CC chardev/testdev.o
CC disas/i386.o
CC fsdev/qemu-fsdev-dummy.o
CC fsdev/qemu-fsdev-opts.o
CC disas/arm.o
CC fsdev/qemu-fsdev-throttle.o
CC hw/acpi/core.o
CC hw/acpi/piix4.o
CC hw/acpi/pcihp.o
CC hw/acpi/tco.o
CC hw/acpi/cpu_hotplug.o
CC hw/acpi/memory_hotplug.o
CC hw/acpi/ich9.o
CC hw/acpi/cpu.o
CC hw/acpi/nvdimm.o
CC hw/acpi/vmgenid.o
CC hw/acpi/acpi_interface.o
CC hw/acpi/bios-linker-loader.o
CC hw/acpi/ipmi.o
CC hw/acpi/acpi-stub.o
CC hw/acpi/ipmi-stub.o
CC hw/audio/sb16.o
CC hw/acpi/aml-build.o
CC hw/audio/es1370.o
CC hw/audio/ac97.o
CC hw/audio/adlib.o
CC hw/audio/gus.o
CC hw/audio/fmopl.o
CC hw/audio/gusemu_hal.o
CC hw/audio/gusemu_mixer.o
CC hw/audio/cs4231a.o
CC hw/audio/intel-hda.o
CC hw/audio/hda-codec.o
CC hw/audio/pcspk.o
CC hw/audio/wm8750.o
CC hw/audio/pl041.o
CC hw/audio/lm4549.o
CC hw/audio/marvell_88w8618.o
CC hw/audio/soundhw.o
CC hw/block/block.o
CC hw/block/hd-geometry.o
CC hw/block/cdrom.o
CC hw/block/fdc.o
CC hw/block/m25p80.o
CC hw/block/nand.o
CC hw/block/pflash_cfi01.o
CC hw/block/pflash_cfi02.o
CC hw/block/ecc.o
CC hw/block/onenand.o
CC hw/block/nvme.o
CC hw/bt/core.o
CC hw/bt/l2cap.o
CC hw/bt/sdp.o
CC hw/bt/hci.o
CC hw/bt/hid.o
CC hw/char/ipoctal232.o
CC hw/bt/hci-csr.o
CC hw/char/parallel.o
CC hw/char/pl011.o
CC hw/char/serial.o
CC hw/char/serial-isa.o
CC hw/char/serial-pci.o
CC hw/char/virtio-console.o
CC hw/char/cadence_uart.o
CC hw/char/debugcon.o
CC hw/core/qdev.o
CC hw/core/qdev-properties.o
CC hw/char/imx_serial.o
CC hw/core/bus.o
CC hw/core/reset.o
CC hw/core/fw-path-provider.o
CC hw/core/irq.o
CC hw/core/hotplug.o
CC hw/core/ptimer.o
CC hw/core/sysbus.o
CC hw/core/nmi.o
CC hw/core/loader.o
CC hw/core/machine.o
CC hw/core/register.o
CC hw/core/qdev-properties-system.o
CC hw/core/platform-bus.o
CC hw/cpu/core.o
CC hw/core/or-irq.o
CC hw/display/ads7846.o
CC hw/display/cirrus_vga.o
CC hw/display/pl110.o
CC hw/display/ssd0323.o
CC hw/display/ssd0303.o
CC hw/display/vga-pci.o
CC hw/display/vmware_vga.o
CC hw/display/blizzard.o
CC hw/display/vga-isa.o
CC hw/display/exynos4210_fimd.o
CC hw/display/framebuffer.o
CC hw/display/tc6393xb.o
CC hw/dma/pl080.o
CC hw/dma/pl330.o
CC hw/dma/i8257.o
CC hw/dma/xlnx-zynq-devcfg.o
CC hw/gpio/max7310.o
CC hw/gpio/pl061.o
CC hw/gpio/zaurus.o
CC hw/gpio/gpio_key.o
CC hw/i2c/core.o
CC hw/i2c/smbus.o
CC hw/i2c/smbus_eeprom.o
CC hw/i2c/i2c-ddc.o
CC hw/i2c/versatile_i2c.o
CC hw/i2c/smbus_ich9.o
CC hw/i2c/pm_smbus.o
CC hw/i2c/bitbang_i2c.o
CC hw/i2c/exynos4210_i2c.o
CC hw/i2c/aspeed_i2c.o
CC hw/i2c/imx_i2c.o
CC hw/ide/core.o
CC hw/ide/qdev.o
CC hw/ide/atapi.o
CC hw/ide/pci.o
CC hw/ide/isa.o
CC hw/ide/piix.o
CC hw/ide/microdrive.o
CC hw/ide/ahci.o
CC hw/input/hid.o
CC hw/ide/ich.o
CC hw/input/lm832x.o
CC hw/input/pckbd.o
CC hw/input/pl050.o
CC hw/input/ps2.o
CC hw/input/stellaris_input.o
CC hw/input/tsc2005.o
CC hw/input/virtio-input.o
CC hw/input/vmmouse.o
CC hw/input/virtio-input-hid.o
CC hw/input/virtio-input-host.o
CC hw/intc/i8259_common.o
CC hw/intc/pl190.o
CC hw/intc/i8259.o
CC hw/intc/realview_gic.o
CC hw/intc/imx_avic.o
CC hw/intc/ioapic_common.o
CC hw/intc/arm_gic_common.o
CC hw/intc/arm_gic.o
CC hw/intc/arm_gicv2m.o
CC hw/intc/arm_gicv3_common.o
CC hw/intc/arm_gicv3.o
CC hw/intc/arm_gicv3_dist.o
CC hw/intc/arm_gicv3_redist.o
CC hw/intc/arm_gicv3_its_common.o
CC hw/intc/intc.o
CC hw/ipack/ipack.o
CC hw/ipmi/ipmi.o
CC hw/ipack/tpci200.o
CC hw/ipmi/ipmi_bmc_sim.o
CC hw/ipmi/ipmi_bmc_extern.o
CC hw/ipmi/isa_ipmi_kcs.o
CC hw/ipmi/isa_ipmi_bt.o
CC hw/isa/isa-bus.o
CC hw/isa/apm.o
CC hw/mem/pc-dimm.o
CC hw/misc/applesmc.o
CC hw/misc/max111x.o
CC hw/mem/nvdimm.o
CC hw/misc/tmp105.o
CC hw/misc/tmp421.o
CC hw/misc/debugexit.o
CC hw/misc/sga.o
CC hw/misc/pc-testdev.o
CC hw/misc/pci-testdev.o
CC hw/misc/unimp.o
CC hw/misc/arm_integrator_debug.o
CC hw/misc/arm_l2x0.o
CC hw/misc/a9scu.o
CC hw/misc/arm11scu.o
CC hw/net/ne2000.o
CC hw/net/eepro100.o
CC hw/net/pcnet-pci.o
CC hw/net/pcnet.o
CC hw/net/e1000.o
CC hw/net/e1000x_common.o
CC hw/net/net_tx_pkt.o
CC hw/net/net_rx_pkt.o
CC hw/net/e1000e_core.o
CC hw/net/e1000e.o
CC hw/net/rtl8139.o
CC hw/net/vmxnet3.o
CC hw/net/smc91c111.o
CC hw/net/ne2000-isa.o
CC hw/net/lan9118.o
CC hw/net/xgmac.o
CC hw/net/allwinner_emac.o
CC hw/net/imx_fec.o
CC hw/net/cadence_gem.o
CC hw/net/stellaris_enet.o
CC hw/net/ftgmac100.o
CC hw/net/rocker/rocker.o
CC hw/net/rocker/rocker_fp.o
CC hw/net/rocker/rocker_desc.o
CC hw/net/rocker/rocker_world.o
CC hw/net/rocker/rocker_of_dpa.o
CC hw/nvram/eeprom93xx.o
CC hw/nvram/fw_cfg.o
CC hw/nvram/chrp_nvram.o
CC hw/pci-bridge/pci_bridge_dev.o
CC hw/pci-bridge/pcie_root_port.o
CC hw/pci-bridge/gen_pcie_root_port.o
CC hw/pci-bridge/pci_expander_bridge.o
CC hw/pci-bridge/xio3130_upstream.o
CC hw/pci-bridge/xio3130_downstream.o
CC hw/pci-bridge/ioh3420.o
CC hw/pci-bridge/i82801b11.o
CC hw/pci-host/pam.o
CC hw/pci-host/versatile.o
CC hw/pci-host/piix.o
CC hw/pci-host/q35.o
CC hw/pci-host/gpex.o
CC hw/pci/pci.o
CC hw/pci/pci_bridge.o
CC hw/pci/msix.o
CC hw/pci/msi.o
CC hw/pci/shpc.o
CC hw/pci/slotid_cap.o
CC hw/pci/pci_host.o
CC hw/pci/pcie_host.o
CC hw/pci/pcie.o
CC hw/pci/pcie_aer.o
CC hw/pci/pcie_port.o
CC hw/pci/pci-stub.o
CC hw/scsi/scsi-disk.o
CC hw/pcmcia/pcmcia.o
CC hw/scsi/scsi-generic.o
CC hw/scsi/scsi-bus.o
CC hw/scsi/lsi53c895a.o
CC hw/scsi/mptconfig.o
CC hw/scsi/mptsas.o
CC hw/scsi/mptendian.o
CC hw/scsi/megasas.o
CC hw/scsi/vmw_pvscsi.o
CC hw/scsi/esp.o
CC hw/scsi/esp-pci.o
CC hw/sd/pl181.o
CC hw/sd/ssi-sd.o
In file included from /tmp/qemu-test/src/hw/net/vmxnet3.c:30:
/tmp/qemu-test/src/include/migration/register.h:18: error: redefinition of typedef ‘LoadStateHandler’
/tmp/qemu-test/src/include/migration/vmstate.h:32: note: previous declaration of ‘LoadStateHandler’ was here
make: *** [hw/net/vmxnet3.o] Error 1
make: *** Waiting for unfinished jobs....
tests/docker/Makefile.include:118: recipe for target 'docker-run' failed
make[1]: *** [docker-run] Error 2
make[1]: Leaving directory '/var/tmp/patchew-tester-tmp-7o9lu4by/src'
tests/docker/Makefile.include:149: recipe for target 'docker-run-test-quick@centos6' failed
make: *** [docker-run-test-quick@centos6] Error 2
=== OUTPUT END ===
Test command exited with code: 2
---
Email generated automatically by Patchew [http://patchew.org/].
Please send your feedback to patchew-devel@freelists.org
On 06/13/2017 03:53 PM, Emilio G. Cota wrote:
> The appended fixes it for me. Can you please test?
> [ apply with `git am --scissors' ]
>
> Thanks,
>
> Emilio
>
> ---- 8< ----
>
> Commit e75449a3 ("target/aarch64: optimize indirect branches") causes
> a regression by which aarch64 guests freeze under TCG with -smp > 1,
> even with `-accel accel=tcg,thread=single' (i.e. MTTCG disabled).
>
> I isolated the problem to the MSR handler. This patch forces an exit
> after the handler is executed, which fixes the regression.
Why would that be? The cpu_get_tb_cpu_state within helper_lookup_tb_ptr is
supposed to read the new state that the msr handler would have installed.
r~
On 14/06/2017 06:48, Richard Henderson wrote:
>>
>> Commit e75449a3 ("target/aarch64: optimize indirect branches") causes
>> a regression by which aarch64 guests freeze under TCG with -smp > 1,
>> even with `-accel accel=tcg,thread=single' (i.e. MTTCG disabled).
>>
>> I isolated the problem to the MSR handler. This patch forces an exit
>> after the handler is executed, which fixes the regression.
>
> Why would that be? The cpu_get_tb_cpu_state within helper_lookup_tb_ptr
> is supposed to read the new state that the msr handler would have
> installed.
Could some of these cause an interrupt, or some other change in the
cpu_exec flow?
Thanks,
Paolo
Paolo Bonzini <pbonzini@redhat.com> writes:
> On 14/06/2017 06:48, Richard Henderson wrote:
>>>
>>> Commit e75449a3 ("target/aarch64: optimize indirect branches") causes
>>> a regression by which aarch64 guests freeze under TCG with -smp > 1,
>>> even with `-accel accel=tcg,thread=single' (i.e. MTTCG disabled).
>>>
>>> I isolated the problem to the MSR handler. This patch forces an exit
>>> after the handler is executed, which fixes the regression.
>>
>> Why would that be? The cpu_get_tb_cpu_state within helper_lookup_tb_ptr
>> is supposed to read the new state that the msr handler would have
>> installed.
>
> Could some of these cause an interrupt, or some other change in the
> cpu_exec flow?
Well what I was observing was the secondary_start_kernel stalling and
leaving the main cpu spinning. The msr is actually:
local_irq_enable();
local_fiq_enable();
Which I assume would re-enable IRQs if they are ready to go. However I
guess if we sink into our cpu_idle without exiting the main loop we
never set any pending IRQs?
>
> Thanks,
>
> Paolo
--
Alex Bennée
On 14/06/2017 13:45, Alex Bennée wrote:
>
> Paolo Bonzini <pbonzini@redhat.com> writes:
>
>> On 14/06/2017 06:48, Richard Henderson wrote:
>>>>
>>>> Commit e75449a3 ("target/aarch64: optimize indirect branches") causes
>>>> a regression by which aarch64 guests freeze under TCG with -smp > 1,
>>>> even with `-accel accel=tcg,thread=single' (i.e. MTTCG disabled).
>>>>
>>>> I isolated the problem to the MSR handler. This patch forces an exit
>>>> after the handler is executed, which fixes the regression.
>>>
>>> Why would that be? The cpu_get_tb_cpu_state within helper_lookup_tb_ptr
>>> is supposed to read the new state that the msr handler would have
>>> installed.
>>
>> Could some of these cause an interrupt, or some other change in the
>> cpu_exec flow?
>
> Well what I was observing was the secondary_start_kernel stalling and
> leaving the main cpu spinning. The msr is actually:
>
> local_irq_enable();
> local_fiq_enable();
>
> Which I assume would re-enable IRQs if they are ready to go. However I
> guess if we sink into our cpu_idle without exiting the main loop we
> never set any pending IRQs?
Then Emilio's patch, if a bit of a heavy hammer, is correct. After
aa64_daif_write needs you need an exit_tb so that arm_cpu_exec_interrupt
is executed again.
Compare with this from the x86 front-end:
/* if irq were inhibited with HF_INHIBIT_IRQ_MASK, we clear
the flag and abort the translation to give the irqs a
change to be happen */
if (dc->tf || dc->singlestep_enabled ||
(flags & HF_INHIBIT_IRQ_MASK)) {
gen_jmp_im(pc_ptr - dc->cs_base);
gen_eob(dc);
break;
}
(This triggers one instruction after a STI instruction, due to how x86's
"interrupt shadow" work, so it doesn't happen immediately after
helper_sti; but the idea is the same).
Paolo
Paolo Bonzini <pbonzini@redhat.com> writes:
> On 14/06/2017 13:45, Alex Bennée wrote:
>>
>> Paolo Bonzini <pbonzini@redhat.com> writes:
>>
>>> On 14/06/2017 06:48, Richard Henderson wrote:
>>>>>
>>>>> Commit e75449a3 ("target/aarch64: optimize indirect branches") causes
>>>>> a regression by which aarch64 guests freeze under TCG with -smp > 1,
>>>>> even with `-accel accel=tcg,thread=single' (i.e. MTTCG disabled).
>>>>>
>>>>> I isolated the problem to the MSR handler. This patch forces an exit
>>>>> after the handler is executed, which fixes the regression.
>>>>
>>>> Why would that be? The cpu_get_tb_cpu_state within helper_lookup_tb_ptr
>>>> is supposed to read the new state that the msr handler would have
>>>> installed.
>>>
>>> Could some of these cause an interrupt, or some other change in the
>>> cpu_exec flow?
>>
>> Well what I was observing was the secondary_start_kernel stalling and
>> leaving the main cpu spinning. The msr is actually:
>>
>> local_irq_enable();
>> local_fiq_enable();
>>
>> Which I assume would re-enable IRQs if they are ready to go. However I
>> guess if we sink into our cpu_idle without exiting the main loop we
>> never set any pending IRQs?
>
> Then Emilio's patch, if a bit of a heavy hammer, is correct. After
> aa64_daif_write needs you need an exit_tb so that arm_cpu_exec_interrupt
> is executed again.
This is a case of cpu->interrupt_request being pending but not having
set cpu->icount_decr yet to signal the exit. Wouldn't another approach
(that didn't involve futzing with each front-end) to be to check
cpu->interrupt_request and force the exit in lookup_tb_ptr?
>
> Compare with this from the x86 front-end:
>
> /* if irq were inhibited with HF_INHIBIT_IRQ_MASK, we clear
> the flag and abort the translation to give the irqs a
> change to be happen */
> if (dc->tf || dc->singlestep_enabled ||
> (flags & HF_INHIBIT_IRQ_MASK)) {
> gen_jmp_im(pc_ptr - dc->cs_base);
> gen_eob(dc);
> break;
> }
>
> (This triggers one instruction after a STI instruction, due to how x86's
> "interrupt shadow" work, so it doesn't happen immediately after
> helper_sti; but the idea is the same).
>
> Paolo
--
Alex Bennée
On 14/06/2017 14:14, Alex Bennée wrote: >> Then Emilio's patch, if a bit of a heavy hammer, is correct. After >> aa64_daif_write needs you need an exit_tb so that arm_cpu_exec_interrupt >> is executed again. > > This is a case of cpu->interrupt_request being pending but not having > set cpu->icount_decr yet to signal the exit. Rather than "yet", "anymore". So far it has always been an invariant that anything that re-enabled an interrupt had to do exit_tb. > Wouldn't another approach > (that didn't involve futzing with each front-end) to be to check > cpu->interrupt_request and force the exit in lookup_tb_ptr? That would cause an unnecessary slowdown in code that runs with interrupts disabled but does a lot of indirect jumps... ppc's SLOF firmware probably qualifies. Paolo
Paolo Bonzini <pbonzini@redhat.com> writes: > On 14/06/2017 14:14, Alex Bennée wrote: >>> Then Emilio's patch, if a bit of a heavy hammer, is correct. After >>> aa64_daif_write needs you need an exit_tb so that arm_cpu_exec_interrupt >>> is executed again. >> >> This is a case of cpu->interrupt_request being pending but not having >> set cpu->icount_decr yet to signal the exit. > > Rather than "yet", "anymore". So far it has always been an invariant > that anything that re-enabled an interrupt had to do exit_tb. > >> Wouldn't another approach >> (that didn't involve futzing with each front-end) to be to check >> cpu->interrupt_request and force the exit in lookup_tb_ptr? > > That would cause an unnecessary slowdown in code that runs with > interrupts disabled but does a lot of indirect jumps... ppc's SLOF > firmware probably qualifies. Really? I'd have to measure the change it makes. Is there a benchmark stanza for measuring the PPC slof firmware time? I have 3 patches now which all fix the same thing so we can pick and choose which we should apply. Patches incoming... -- Alex Bennée
On 14/06/2017 14:35, Alex Bennée wrote: >> That would cause an unnecessary slowdown in code that runs with >> interrupts disabled but does a lot of indirect jumps... ppc's SLOF >> firmware probably qualifies. > > Really? Yes. :) SLOF basically runs a Forth interpreter. If you run "qemu-system-ppc64 -d in_asm", you'll see a lot of "bctr" and "bctrl" instruction (respectively ARM's "br" and "blr" IIRC). > I'd have to measure the change it makes. Is there a benchmark > stanza for measuring the PPC slof firmware time? Just booting. PPC doesn't have tcg_gen_lookup_and_goto_ptr support yet, so it would be a theoretical slowdown at this time. Paolo > I have 3 patches now which all fix the same thing so we can pick and > choose which we should apply. Patches incoming...
Emilio G. Cota <cota@braap.org> writes:
> The appended fixes it for me. Can you please test?
> [ apply with `git am --scissors' ]
>
> Thanks,
>
> Emilio
>
> ---- 8< ----
>
> Commit e75449a3 ("target/aarch64: optimize indirect branches") causes
> a regression by which aarch64 guests freeze under TCG with -smp > 1,
> even with `-accel accel=tcg,thread=single' (i.e. MTTCG disabled).
>
> I isolated the problem to the MSR handler. This patch forces an exit
> after the handler is executed, which fixes the regression.
>
> Signed-off-by: Emilio G. Cota <cota@braap.org>
Tested-by: Alex Bennée <alex.bennee@linaro.org>
But what exactly is the mechanism here? DISAS_UPDATE should have ensured
that the PC was updated before we get to the helper. Is this a case of
msr_i_pstate somehow getting missed or not causing a flag update which
confuses the next TB calculation?
> ---
> target/arm/translate-a64.c | 6 +++++-
> 1 file changed, 5 insertions(+), 1 deletion(-)
>
> diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c
> index 860e279..5a609a0 100644
> --- a/target/arm/translate-a64.c
> +++ b/target/arm/translate-a64.c
> @@ -1422,7 +1422,7 @@ static void handle_msr_i(DisasContext *s, uint32_t insn,
> gen_helper_msr_i_pstate(cpu_env, tcg_op, tcg_imm);
> tcg_temp_free_i32(tcg_imm);
> tcg_temp_free_i32(tcg_op);
> - s->is_jmp = DISAS_UPDATE;
> + s->is_jmp = DISAS_EXIT;
> break;
> }
> default:
> @@ -11362,6 +11362,10 @@ void gen_intermediate_code_a64(ARMCPU *cpu, TranslationBlock *tb)
> case DISAS_NEXT:
> gen_goto_tb(dc, 1, dc->pc);
> break;
> + case DISAS_EXIT:
> + gen_a64_set_pc_im(dc->pc);
> + tcg_gen_exit_tb(0);
> + break;
> default:
> case DISAS_UPDATE:
> gen_a64_set_pc_im(dc->pc);
--
Alex Bennée
© 2016 - 2025 Red Hat, Inc.