iOS and Apple Silicon host support
Subsystems (4)
cover iOS and Apple Silicon host support
These set of changes brings QEMU TCG to iOS devices and future Apple Silicon devices. They were originally developed last year and have been working in the UTM app. Recently, we ported the changes to master, re-wrote a lot of the build script changes for meson, and broke up the patches into more distinct units.
A summary of the changes:
* CONFIG_IOS and CONFIG_IOS_JIT defined when building for iOS and iOS specific changes (as well as unsupported code) are gated behind it.
* slirp updated to support DNS resolving using libresolv; a separate patch will be submitted to the project. To allow for builds to succeed, the .gitmodule is temporarily changed. We're not entirely sure how cross-project patches should be handled here.
* A new dependency, libucontext is added since iOS does not have native ucontext and broken support for sigaltstack. libucontext is available as a new option for coroutine backend.
* On stock iOS devices, there is a workaround for running JIT code without any special entitlement. It requires the JIT region to be mirror mapped with one region RW and another one RX. To support this style of JIT, TCG is changed to support writing to a different code_ptr. These changes are gated by the CONFIG_IOS_JIT.
* For (recent) jailbroken iOS devices as well as upcoming Apple Silicon devices, there are new rules for applications supporting JIT (with the proper entitlement). These rules are implemented as well.
* An option to build QEMU as a shared library is added because iOS does not support fork().
These patches are also on Github:
https://github.com/utmapp/qemu/tree/ios-support-master
-j
osy (10):
configure: option to disable host block devices
configure: cross-compiling without cross_prefix
qemu: add support for iOS host
meson: option to build as shared library
slirp: update for iOS resolv fix
coroutine: add libucontext as external library
tcg: implement bulletproof JIT
tcg: mirror mapping RWX pages for iOS optional
tcg: support JIT on Apple Silicon
block: check availablity for preadv/pwritev on mac
.gitmodules | 5 +- accel/tcg/cpu-exec-common.c | 2 + accel/tcg/cpu-exec.c | 9 +- accel/tcg/tcg-all.c | 27 +++++- accel/tcg/translate-all.c | 169 ++++++++++++++++++++++++++++++++--- block.c | 2 +- block/file-posix.c | 50 ++++++++--- bsd-user/main.c | 2 +- configure | 118 ++++++++++++++++++++++-- docs/devel/ios.rst | 40 +++++++++ include/exec/exec-all.h | 10 +++ include/sysemu/tcg.h | 2 +- include/tcg/tcg-apple-jit.h | 85 ++++++++++++++++++ include/tcg/tcg.h | 21 ++++- libucontext | 1 + linux-user/main.c | 2 +- meson.build | 74 +++++++++++++-- meson_options.txt | 4 + net/slirp.c | 16 ++-- qemu-options.hx | 11 +++ qga/commands-posix.c | 6 ++ slirp | 2 +- target/arm/arm-semi.c | 2 + target/m68k/m68k-semi.c | 2 + target/nios2/nios2-semi.c | 2 + tcg/aarch64/tcg-target.c.inc | 48 ++++++---- tcg/aarch64/tcg-target.h | 23 ++++- tcg/arm/tcg-target.c.inc | 33 ++++--- tcg/arm/tcg-target.h | 9 +- tcg/i386/tcg-target.c.inc | 28 +++--- tcg/i386/tcg-target.h | 24 ++++- tcg/mips/tcg-target.c.inc | 64 +++++++------ tcg/mips/tcg-target.h | 8 +- tcg/ppc/tcg-target.c.inc | 55 +++++++----- tcg/ppc/tcg-target.h | 8 +- tcg/riscv/tcg-target.c.inc | 51 ++++++----- tcg/riscv/tcg-target.h | 9 +- tcg/s390/tcg-target.c.inc | 25 +++--- tcg/s390/tcg-target.h | 13 ++- tcg/sparc/tcg-target.c.inc | 33 ++++--- tcg/sparc/tcg-target.h | 8 +- tcg/tcg-ldst.c.inc | 2 +- tcg/tcg-pool.c.inc | 9 +- tcg/tcg.c | 64 ++++++++----- tcg/tci/tcg-target.c.inc | 8 +- tcg/tci/tcg-target.h | 9 +- tests/qtest/meson.build | 7 +- util/coroutine-ucontext.c | 9 ++ 48 files changed, 965 insertions(+), 246 deletions(-) create mode 100644 docs/devel/ios.rst create mode 100644 include/tcg/tcg-apple-jit.h create mode 160000 libucontext
Signature · 1 line
2.24.3 (Apple Git-128)
PATCH 1/10 configure: option to disable host block devices
From: osy <[email protected]>
Some hosts (iOS) have a sandboxed filesystem and do not provide low-level APIs for interfacing with host block devices.
--- block/file-posix.c | 8 +++++++- configure | 4 ++++ meson.build | 1 + 3 files changed, 12 insertions(+), 1 deletion(-)
block/file-posix.c +7 -1
@@ -41,7 +41,7 @@#include "scsi/pr-manager.h" #include "scsi/constants.h" -#if defined(__APPLE__) && (__MACH__) +#if defined(CONFIG_HOST_BLOCK_DEVICE ) && defined(__APPLE__) && (__MACH__)#include <paths.h> #include <sys/param.h> #include <IOKit/IOKitLib.h>
@@ -3247,6 +3247,8 @@ BlockDriver bdrv_file = {/***********************************************/ /* host device */ +#if defined(CONFIG_HOST_BLOCK_DEVICE ) +#if defined(__APPLE__) && defined(__MACH__)static kern_return_t GetBSDPath (io_iterator_t mediaIterator,char *bsdPath,CFIndex maxPathSize,int flags);
@@ -3872,6 +3874,8 @@ static BlockDriver bdrv_host_cdrom = { };#endif /* __FreeBSD__ */ +#endif /* CONFIG_HOST_BLOCK_DEVICE */ +static void bdrv_file_init (void ) {/*
@@ -3879,6 +3883,7 @@ static void bdrv_file_init(void)* registered last will get probed first. */ bdrv_register (&bdrv_file); +#if defined(CONFIG_HOST_BLOCK_DEVICE )bdrv_register (&bdrv_host_device);#ifdef __linux__bdrv_register (&bdrv_host_cdrom);
@@ -3886,6 +3891,7 @@ static void bdrv_file_init(void)#if defined(__FreeBSD__) || defined(__FreeBSD_kernel__)bdrv_register (&bdrv_host_cdrom);#endif +#endif /* CONFIG_HOST_BLOCK_DEVICE */ }block_init (bdrv_file_init);
configure +4 -0
@@ -446,6 +446,7 @@ meson="" ninja="" skip_meson=no gettext="" +host_block_device_support="yes" bogus_os="no" malloc_trim="auto"
@@ -6098,6 +6099,9 @@ if test "$default_devices" = "yes" ; then else echo "CONFIG_MINIKCONF_MODE=--allnoconfig" >> $config_host_mak fi +if test "$host_block_device_support" = "yes" ; then + echo "CONFIG_HOST_BLOCK_DEVICE=y" >> $config_host_mak +fi if test "$debug_tcg" = "yes" ; then echo "CONFIG_DEBUG_TCG=y" >> $config_host_mak fi
meson.build +1 -0
@@ -1947,6 +1947,7 @@ summary_info += {'vvfat support': config_host.has_key('CONFIG_VVFAT')} summary_info += {'qed support': config_host.has_key('CONFIG_QED')} summary_info += {'parallels support': config_host.has_key('CONFIG_PARALLELS')} summary_info += {'sheepdog support': config_host.has_key('CONFIG_SHEEPDOG')} +summary_info += {'host block dev support': config_host.has_key('CONFIG_HOST_BLOCK_DEVICE')} summary_info += {'capstone': capstone_opt == 'disabled' ? false : capstone_opt} summary_info += {'libpmem support': config_host.has_key('CONFIG_LIBPMEM')} summary_info += {'libdaxctl support': config_host.has_key('CONFIG_LIBDAXCTL')}
Signature · 1 line
2.24.3 (Apple Git-128)
PATCH 2/10 configure: cross-compiling without cross_prefix
In reply to Joelle van DyneFrom: osy <[email protected]>
The iOS toolchain does not use the host prefix naming convention. We add a new option --enable-cross-compile that forces cross-compile even without a cross_prefix.
--- configure | 13 ++++++++++++- 1 file changed, 12 insertions(+), 1 deletion(-)
configure +12 -1
@@ -234,6 +234,7 @@ cpu="" iasl="iasl" interp_prefix="/usr/gnemul/qemu-%M" static="no" +cross_compile="no" cross_prefix="" audio_drv_list="" block_drv_rw_whitelist=""
@@ -456,6 +457,11 @@ for opt do optarg=$(expr "x$opt" : 'x[^=]*=\(.*\)') case "$opt" in --cross-prefix=*) cross_prefix="$optarg" + cross_compile="yes" + ;; + --enable-cross-compile) cross_compile="yes" + ;; + --disable-cross-compile) cross_compile="no" ;; --cc=*) CC="$optarg" ;;
@@ -878,6 +884,10 @@ for opt do ;; --cross-prefix=*) ;; + --enable-cross-compile) + ;; + --disable-cross-compile) + ;; --cc=*) ;; --host-cc=*) host_cc="$optarg"
@@ -1687,6 +1697,7 @@ Advanced options (experts only): --efi-aarch64=PATH PATH of efi file to use for aarch64 VMs. --with-suffix=SUFFIX suffix for QEMU data inside datadir/libdir/sysconfdir/docdir [$qemu_suffix] --with-pkgversion=VERS use specified string as sub-version of the package + --enable-cross-compile enable cross compiling (set automatically if $cross_prefix is set) --enable-debug enable common debug build options --enable-sanitizers enable default sanitizers --enable-tsan enable thread sanitizer
@@ -7164,7 +7175,7 @@ if has $sdl2_config; then fi echo "strip = [$(meson_quote $strip)]" >> $cross echo "windres = [$(meson_quote $windres)]" >> $cross -if test -n "$cross_prefix"; then +if test "$cross_compile" = "yes"; then cross_arg="--cross-file config-meson.cross" echo "[host_machine]" >> $cross if test "$mingw32" = "yes" ; then
Signature · 1 line
2.24.3 (Apple Git-128)
PATCH 3/10 qemu: add support for iOS host
In reply to Joelle van DyneFrom: osy <[email protected]>
This introduces support for building for iOS hosts. When the correct Xcode toolchain is used, iOS host will be detected automatically.
block: disable features not supported by iOS sandbox
slirp: disable SMB features for iOS
target: disable system() calls for iOS
tcg: use sys_icache_invalidate() instead of GCC builtin for iOS
tests: disable tests on iOS which uses system()
--- block.c | 2 +- block/file-posix.c | 30 ++++++++++++++++----------- configure | 43 ++++++++++++++++++++++++++++++++++++++- meson.build | 2 +- net/slirp.c | 16 +++++++-------- qga/commands-posix.c | 6 ++++++ target/arm/arm-semi.c | 2 ++ target/m68k/m68k-semi.c | 2 ++ target/nios2/nios2-semi.c | 2 ++ tcg/aarch64/tcg-target.h | 10 +++++++++ tests/qtest/meson.build | 7 +++---- 11 files changed, 95 insertions(+), 27 deletions(-)
block.c +1 -1
@@ -53,7 +53,7 @@#ifdef CONFIG_BSD #include <sys/ioctl.h> #include <sys/queue.h> -#ifndef __DragonFly__ +#if !defined(__DragonFly__) && !defined(CONFIG_IOS )#include <sys/disk.h> #endif #endif
block/file-posix.c +18 -12
@@ -181,7 +181,16 @@ typedef struct BDRVRawReopenState {bool check_cache_dropped; } BDRVRawReopenState; -static int fd_open (BlockDriverState *bs); +static int fd_open (BlockDriverState *bs) +{ +BDRVRawState *s = bs->opaque; + +/* this is just to ensure s->fd is sane (its called by io ops) */ +if (s->fd >=0 ) +return 0 ; +return -EIO ; +} +static int64_t raw_getlength (BlockDriverState *bs); typedef struct RawPosixAIOData {
@@ -252,6 +261,12 @@ static int raw_normalize_devicepath(const char **filename, Error **errp) }#endif +#if defined(CONFIG_IOS ) +static int probe_logical_blocksize (int fd,unsigned int *sector_size_p) +{ +return -ENOTSUP ;/* not supported on iOS */ +} +#else /* CONFIG_IOS */ /* * Get logical block size via ioctl. On success store it in @sector_size_p. */
@@ -284,6 +299,7 @@ static int probe_logical_blocksize(int fd, unsigned int *sector_size_p) return success ? 0 : -errno; } +#endif /* !CONFIG_IOS */ /** * Get physical block size of @fd.
@@ -2306,7 +2322,7 @@ again: } if (size == 0)#endif -#if defined(__APPLE__) && defined(__MACH__) +#if !defined(CONFIG_IOS ) && defined(__APPLE__) && defined(__MACH__) {uint64_t sectors =0 ;uint32_t sector_size =0 ;
@@ -3541,16 +3557,6 @@ hdev_co_ioctl(BlockDriverState *bs, unsigned long int req, void *buf) }#endif /* linux */ -static int fd_open (BlockDriverState *bs) -{ -BDRVRawState *s = bs->opaque; - -/* this is just to ensure s->fd is sane (its called by io ops) */ -if (s->fd >=0 ) -return 0 ; -return -EIO ; -} - static coroutine_fn inthdev_co_pdiscard (BlockDriverState *bs,int64_t offset,int bytes) {
configure +42 -1
79 lines not on this page · raw message
meson.build +1 -1
@@ -140,7 +140,7 @@ if targetos == 'windows' include_directories: include_directories('.')) elif targetos == 'darwin' coref = dependency('appleframeworks', modules: 'CoreFoundation') - iokit = dependency('appleframeworks', modules: 'IOKit') + iokit = dependency('appleframeworks', modules: 'IOKit', required: 'CONFIG_IOS' not in config_host) cocoa = dependency('appleframeworks', modules: 'Cocoa', required: get_option('cocoa')) elif targetos == 'sunos' socket = [cc.find_library('socket'),
net/slirp.c +8 -8
@@ -27,7 +27,7 @@#include "net/slirp.h" -#ifndef _WIN32 +#if !defined(_WIN32) && !defined(CONFIG_IOS )#include <pwd.h> #include <sys/wait.h> #endif
@@ -90,7 +90,7 @@ typedef struct SlirpState {Slirp *slirp;Notifier poll_notifier;Notifier exit_notifier; -#ifndef _WIN32 +#if !defined(_WIN32) && !defined(CONFIG_IOS )gchar *smb_dir;#endif GSList *fwd;
@@ -103,7 +103,7 @@ static QTAILQ_HEAD(, SlirpState) slirp_stacks =static int slirp_hostfwd (SlirpState *s,const char *redir_str,Error **errp);static int slirp_guestfwd (SlirpState *s,const char *config_str,Error **errp); -#ifndef _WIN32 +#if !defined(_WIN32) && !defined(CONFIG_IOS )static int slirp_smb (SlirpState *s,const char *exported_dir,struct in_addr vserver_addr,Error **errp);static void slirp_smb_cleanup (SlirpState *s);
@@ -368,7 +368,7 @@ static int net_slirp_init(NetClientState *peer, const char *model,struct in6_addr ip6_prefix;struct in6_addr ip6_host;struct in6_addr ip6_dns; -#ifndef _WIN32 +#if !defined(_WIN32) && !defined(CONFIG_IOS )struct in_addr smbsrv = { .s_addr =0 };#endif NetClientState *nc;
@@ -478,7 +478,7 @@ static int net_slirp_init(NetClientState *peer, const char *model,return -1 ; } -#ifndef _WIN32 +#if !defined(_WIN32) && !defined(CONFIG_IOS )if (vsmbserver && !inet_aton (vsmbserver, &smbsrv)) {error_setg (errp,"Failed to parse SMB address" );return -1 ;
@@ -593,7 +593,7 @@ static int net_slirp_init(NetClientState *peer, const char *model, } } } -#ifndef _WIN32 +#if !defined(_WIN32) && !defined(CONFIG_IOS )if (smb_export) {if (slirp_smb (s, smb_export, smbsrv, errp) <0 ) { goto error;
@@ -785,7 +785,7 @@ void hmp_hostfwd_add(Monitor *mon, const QDict *qdict) } -#ifndef _WIN32 +#if !defined(_WIN32) && !defined(CONFIG_IOS )/* automatic user mode samba server configuration */ static void slirp_smb_cleanup (SlirpState *s)
@@ -900,7 +900,7 @@ static int slirp_smb(SlirpState* s, const char *exported_dir, return 0; } -#endif /* !defined(_WIN32) */ +#endif /* !defined(_WIN32) && !defined(CONFIG_IOS) */ static int guestfwd_can_read (void *opaque) {
qga/commands-posix.c +6 -0
@@ -34,6 +34,12 @@#ifndef CONFIG_HAS_ENVIRON #ifdef __APPLE__ +#include "TargetConditionals.h" +#if !TARGET_OS_IPHONE && !TARGET_IPHONE_SIMULATOR +#define APPLE_USE_CRT_EXTERNS +#endif +#endif +#ifdef APPLE_USE_CRT_EXTERNS #include <crt_externs.h> #define environ (*_NSGetEnviron())#else
target/arm/arm-semi.c +2 -0
@@ -891,6 +891,7 @@ target_ulong do_arm_semihosting(CPUARMState *env)return clock () / (CLOCKS_PER_SEC /100 );case TARGET_SYS_TIME :return set_swi_errno (env,time (NULL )); +#if !defined(CONFIG_IOS )/* iOS does not have system() */ case TARGET_SYS_SYSTEM :GET_ARG (0 );GET_ARG (1 );
@@ -907,6 +908,7 @@ target_ulong do_arm_semihosting(CPUARMState *env)unlock_user (s, arg0,0 ); return ret; } +#endif /* CONFIG_IOS */ case TARGET_SYS_ERRNO :return get_swi_errno (env);case TARGET_SYS_GET_CMDLINE :
target/m68k/m68k-semi.c +2 -0
@@ -402,6 +402,7 @@ void do_m68k_semihosting(CPUM68KState *env, int nr) result =isatty (arg0); }break ; +#if !defined(CONFIG_IOS )/* iOS does not have system() */ case HOSTED_SYSTEM :GET_ARG (0 );GET_ARG (1 );
@@ -420,6 +421,7 @@ void do_m68k_semihosting(CPUM68KState *env, int nr) } }break ; +#endif /* CONFIG_IOS */ case HOSTED_INIT_SIM :#if defined(CONFIG_USER_ONLY ) {
target/nios2/nios2-semi.c +2 -0
@@ -426,6 +426,7 @@ void do_nios2_semihosting(CPUNios2State *env) result =isatty (arg0); }break ; +#if !defined(CONFIG_IOS )/* iOS does not have system() */ case HOSTED_SYSTEM :GET_ARG (0 );GET_ARG (1 );
@@ -444,6 +445,7 @@ void do_nios2_semihosting(CPUNios2State *env) } }break ; +#endif default :qemu_log_mask (LOG_GUEST_ERROR ,"nios2-semihosting: unsupported " "semihosting syscall %d\n" , nr);
tcg/aarch64/tcg-target.h +10 -0
@@ -148,9 +148,19 @@ typedef enum {#define TCG_TARGET_DEFAULT_MO (0)#define TCG_TARGET_HAS_MEMORY_BSWAP 1 +#if defined(__APPLE__) +void sys_icache_invalidate (void *start,size_t len); +#endif +static inline void flush_icache_range (uintptr_t start,uintptr_t stop) { +#if defined(__APPLE__) +sys_icache_invalidate ((char *)start, stop - start); +#elif defined(__GNUC__)__builtin___clear_cache ((char *)start, (char *)stop); +#else +#error "Missing builtin to flush instruction cache" +#endif }void tb_target_set_jmp_target (uintptr_t ,uintptr_t ,uintptr_t );
tests/qtest/meson.build +3 -4
@@ -46,12 +46,11 @@ qtests_i386 = \ (config_all_devices.has_key('CONFIG_TPM_TIS_ISA') ? ['tpm-tis-test'] : []) + \ (config_all_devices.has_key('CONFIG_TPM_TIS_ISA') ? ['tpm-tis-swtpm-test'] : []) + \ (config_all_devices.has_key('CONFIG_RTL8139_PCI') ? ['rtl8139-test'] : []) + \ + (not config_host.has_key('CONFIG_IOS') ? ['bios-tables-test', 'hd-geo-test'] : []) + \ qtests_pci + \ ['fdc-test', 'ide-test', - 'hd-geo-test', 'boot-order-test', - 'bios-tables-test', 'rtc-test', 'i440fx-test', 'fw_cfg-test',
@@ -141,9 +140,9 @@ qtests_arm = \ 'boot-serial-test', 'hexloader-test'] -# TODO: once aarch64 TCG is fixed on ARM 32 bit host, make bios-tables-test unconditional +# TODO: once aarch64 TCG is fixed on ARM 32 bit host, make bios-tables-test unconditional (except on iOS) qtests_aarch64 = \ - (cpu != 'arm' ? ['bios-tables-test'] : []) + \ + (cpu != 'arm' and not config_host.has_key('CONFIG_IOS') ? ['bios-tables-test'] : []) + \ (config_all_devices.has_key('CONFIG_TPM_TIS_SYSBUS') ? ['tpm-tis-device-test'] : []) + \ (config_all_devices.has_key('CONFIG_TPM_TIS_SYSBUS') ? ['tpm-tis-device-swtpm-test'] : []) + \ ['arm-cpu-features',
Signature · 1 line
2.24.3 (Apple Git-128)
PATCH 4/10 meson: option to build as shared library
In reply to Joelle van DyneFrom: osy <[email protected]>
On iOS, we cannot fork() new processes, so the best way to load QEMU into an app is through a shared library. We add a new configure option --enable-shared-lib that will build the bulk of QEMU into a shared lib. The usual executables will then link to the library.
--- configure | 14 ++++++++++++-- meson.build | 40 ++++++++++++++++++++++++++++++++++------ meson_options.txt | 2 ++ 3 files changed, 48 insertions(+), 8 deletions(-)
configure +12 -2
@@ -448,6 +448,7 @@ ninja="" skip_meson=no gettext="" host_block_device_support="yes" +shared_lib="false" bogus_os="no" malloc_trim="auto"
@@ -1563,6 +1564,10 @@ for opt do ;; --disable-libdaxctl) libdaxctl=no ;; + --enable-shared-lib) shared_lib=true + ;; + --disable-shared-lib) shared_lib=false + ;; *) echo "ERROR: unknown option $opt" echo "Try '$0 --help' for more information"
@@ -1770,6 +1775,7 @@ Advanced options (experts only): enable plugins via shared library loading --disable-containers don't use containers for cross-building --gdb=GDB-path gdb to use for gdbstub tests [$gdb_bin] + --enable-shared-lib build QEMU as a shared library Optional features, enabled with --enable-FEATURE and disabled with --disable-FEATURE, default is enabled if available:
@@ -7211,7 +7217,11 @@ echo "ranlib = [$(meson_quote $ranlib)]" >> $cross if has $sdl2_config; then echo "sdl2-config = [$(meson_quote $sdl2_config)]" >> $cross fi -echo "strip = [$(meson_quote $strip)]" >> $cross +if test "$shared_lib" = "true"; then + echo "strip = [$(meson_quote $strip), '-x']" >> $cross +else + echo "strip = [$(meson_quote $strip)]" >> $cross +fi echo "windres = [$(meson_quote $windres)]" >> $cross if test "$cross_compile" = "yes"; then cross_arg="--cross-file config-meson.cross"
@@ -7273,7 +7283,7 @@ NINJA=${ninja:-$PWD/ninjatool} $meson setup \ -Dcocoa=$cocoa -Dmpath=$mpath -Dsdl=$sdl -Dsdl_image=$sdl_image \ -Dvnc=$vnc -Dvnc_sasl=$vnc_sasl -Dvnc_jpeg=$vnc_jpeg -Dvnc_png=$vnc_png \ -Dgettext=$gettext -Dxkbcommon=$xkbcommon -Du2f=$u2f \ - -Dcapstone=$capstone -Dslirp=$slirp -Dfdt=$fdt \ + -Dcapstone=$capstone -Dslirp=$slirp -Dfdt=$fdt -Dshared-lib=$shared_lib \ $cross_arg \ "$PWD" "$source_path"
meson.build +34 -6
@@ -1565,14 +1565,31 @@ foreach target : target_dirs arch_srcs += target_specific.sources() arch_deps += target_specific.dependencies() - lib = static_library('qemu-' + target, + if get_option('shared-lib') + build_lib_args = { + 'target_type': 'shared_library', + 'install': true, + 'dependencies': arch_deps + deps, + 'link_language': link_language, + 'link_depends': [block_syms, qemu_syms], + 'link_args': link_args + cc.get_supported_link_arguments(['-Wl,-U,_qemu_main']) + } + else + build_lib_args = { + 'target_type': 'static_library', + 'install': false, + 'dependencies': arch_deps, + 'name_suffix': 'fa' + } + endif + + lib = build_target('qemu-' + target, sources: arch_srcs + genh, - dependencies: arch_deps, objects: objects, include_directories: target_inc, c_args: c_args, build_by_default: false, - name_suffix: 'fa') + kwargs: build_lib_args) if target.endswith('-softmmu') execs = [{
@@ -1606,17 +1623,27 @@ foreach target : target_dirs 'dependencies': [] }] endif + if get_option('shared-lib') + build_exe_args = { + 'link_with': lib, + 'link_args': link_args + cc.get_supported_link_arguments(['-Wl,--exclude-libs,ALL']) + } + else + build_exe_args = { + 'objects': lib.extract_all_objects(recursive: true), + 'link_args': link_args + } + endif foreach exe: execs emulators += {exe['name']: executable(exe['name'], exe['sources'], install: true, c_args: c_args, dependencies: arch_deps + deps + exe['dependencies'], - objects: lib.extract_all_objects(recursive: true), link_language: link_language, link_depends: [block_syms, qemu_syms] + exe.get('link_depends', []), - link_args: link_args, - gui_app: exe['gui']) + gui_app: exe['gui'], + kwargs: build_exe_args) } if 'CONFIG_TRACE_SYSTEMTAP' in config_host
@@ -1758,6 +1785,7 @@ endif summary_info += {'Doc directory': get_option('docdir')} summary_info += {'Build directory': meson.current_build_dir()} summary_info += {'Source path': meson.current_source_dir()} +summary_info += {'build shared lib': get_option('shared-lib')} summary_info += {'GIT binary': config_host['GIT']} summary_info += {'GIT submodules': config_host['GIT_SUBMODULES']} summary_info += {'C compiler': meson.get_compiler('c').cmd_array()[0]}
meson_options.txt +2 -0
@@ -2,6 +2,8 @@ option('qemu_suffix', type : 'string', value: 'qemu', description: 'Suffix for QEMU data/modules/config directories (can be empty)') option('docdir', type : 'string', value : 'doc', description: 'Base directory for documentation installation (can be empty)') +option('shared-lib', type : 'boolean', value : false, + description: 'build QEMU as a shared library') option('gettext', type : 'boolean', value : true, description: 'Localization of the GTK+ user interface')
Signature · 1 line
2.24.3 (Apple Git-128)
Re: [PATCH 04/10] meson: option to build as shared library
Quoted 6 lines · Joelle van Dyne
From: osy <[email protected]>
On iOS, we cannot
fork()new processes, so the best way to load QEMU into an app is through a shared library. We add a new configure option--enable-shared-libthat will build the bulk of QEMU into a shared lib. The usual executables will then link to the library.
Note that QEMU as a combined work is licensed GPLv2-only, so if an app is linking to it as a shared library, the application's license has to be GPLv2 compatible. I fear that shipping as a shared library is an easy way for apps to get into a license violating situation without realizing.
Regards,
Daniel
Signature · 3 lines
|: https://berrange.com -o- https://www.flickr.com/photos/dberrange :| |: https://libvirt.org -o- https://fstop138.berrange.com :| |: https://entangle-photo.org -o- https://www.instagram.com/dberrange :|
Re: [PATCH 04/10] meson: option to build as shared library
Quoted 8 lines · Daniel P. Berrangé
Quoted 6 lines · Joelle van Dyne
From: osy <[email protected]>
On iOS, we cannot
fork()new processes, so the best way to load QEMU into an app is through a shared library. We add a new configure option--enable-shared-libthat will build the bulk of QEMU into a shared lib. The usual executables will then link to the library.
Quoted 4 lines
Note that QEMU as a combined work is licensed GPLv2-only, so if an app is linking to it as a shared library, the application's license has to be GPLv2 compatible. I fear that shipping as a shared library is an easy way for apps to get into a license violating situation without realizing.
Please don't let that be an obstacle in merging this series. They'll do it anyway as seen here so having it upstream is probably better than having a lot of different/divergent forks.
In case of UTM it seems to be licensed under Apache License 2.0:
https://github.com/utmapp/UTM/blob/master/LICENSE
which FSF says not compatible with GPLv2 but it is with GPLv3:
http://www.gnu.org/licenses/license-list.html#apache2
Not sure however if that's for using Apache licenced part in GPLv2 code or the other way around like in UTM in which case I think the whole work will effectively become GPLv3 as most parts of QEMU is probably GPLv2+ already or BSD like free that should be possible to combine with only files explicitely GPLv2 in QEMU remaining at that license and UTM parts are Apache 2.0 when separated from QEMU. I have no idea about legal stuff whatsoever but combining two free software components should be legal some way (otherwise it's not possible to combine GPLv2 with GPLv3 either).
I hope this does not turn into a legal bike shedding thread that results in finding out there are other than technical problems in the way to accept this series but the contrary, I'd say let the legal problems be handled by those using QEMU and don't reject patches based on maybe possible legal problems. Stating the licence clearly and maybe providing links to further resources to resolve licence problems in QEMU docs should be enough.
Regards,
BALATON Zoltan
Re: [PATCH 04/10] meson: option to build as shared library
Quoted 9 lines · BALATON Zoltan
Quoted 8 lines · Daniel P. Berrangé
Quoted 6 lines · Joelle van Dyne
From: osy <[email protected]>
On iOS, we cannot
fork()new processes, so the best way to load QEMU into an app is through a shared library. We add a new configure option--enable-shared-libthat will build the bulk of QEMU into a shared lib. The usual executables will then link to the library.
Quoted 8 lines
Quoted 4 lines
Note that QEMU as a combined work is licensed GPLv2-only, so if an app is linking to it as a shared library, the application's license has to be GPLv2 compatible. I fear that shipping as a shared library is an easy way for apps to get into a license violating situation without realizing.
Please don't let that be an obstacle in merging this series. They'll do it anyway as seen here so having it upstream is probably better than having a lot of different/divergent forks.
"They'll violate the license anyway" is not a compelling argument.
Quoted 8 lines
In case of UTM it seems to be licensed under Apache License 2.0:
https://github.com/utmapp/UTM/blob/master/LICENSE
which FSF says not compatible with GPLv2 but it is with GPLv3:
Quoted 8 lines
Not sure however if that's for using Apache licenced part in GPLv2 code or the other way around like in UTM in which case I think the whole work will effectively become GPLv3 as most parts of QEMU is probably GPLv2+ already or BSD like free that should be possible to combine with only files explicitely GPLv2 in QEMU remaining at that license and UTM parts are Apache 2.0 when separated from QEMU. I have no idea about legal stuff whatsoever but combining two free software components should be legal some way (otherwise it's not possible to combine GPLv2 with GPLv3 either).
You need to distinguish between GPLv2-only and GPLv2-or-later.
GPLv2-or-later is fine as that upgrades to GPLv3 when used in a combined work with Apache License or GPLv3 software.
GPLv2-only will, by design, *not* upgrade to newer GPL versions when combined - it is simply license incompatible.
QEMU unfortunately has a bunch a GPLv2-only code present that we cannot eliminate.
Regards,
Daniel
Signature · 3 lines
|: https://berrange.com -o- https://www.flickr.com/photos/dberrange :| |: https://libvirt.org -o- https://fstop138.berrange.com :| |: https://entangle-photo.org -o- https://www.instagram.com/dberrange :|
Re: [PATCH 04/10] meson: option to build as shared library
I will start a separate conversation of UTM's license compatibility.
Regarding the patch, would some sort of warning message in configure (if building as a shared library) regarding the license be wise? Or would it pollute the output logs?
-j
Quoted 57 lines · Daniel P. Berrangé
Quoted 9 lines · BALATON Zoltan
Quoted 8 lines · Daniel P. Berrangé
Quoted 6 lines · Joelle van Dyne
From: osy <[email protected]>
On iOS, we cannot
fork()new processes, so the best way to load QEMU into an app is through a shared library. We add a new configure option--enable-shared-libthat will build the bulk of QEMU into a shared lib. The usual executables will then link to the library.Quoted 8 lines
Quoted 4 lines
Note that QEMU as a combined work is licensed GPLv2-only, so if an app is linking to it as a shared library, the application's license has to be GPLv2 compatible. I fear that shipping as a shared library is an easy way for apps to get into a license violating situation without realizing.
Please don't let that be an obstacle in merging this series. They'll do it anyway as seen here so having it upstream is probably better than having a lot of different/divergent forks.
"They'll violate the license anyway" is not a compelling argument.
Quoted 8 lines
In case of UTM it seems to be licensed under Apache License 2.0:
https://github.com/utmapp/UTM/blob/master/LICENSE
which FSF says not compatible with GPLv2 but it is with GPLv3:
Quoted 8 lines
Not sure however if that's for using Apache licenced part in GPLv2 code or the other way around like in UTM in which case I think the whole work will effectively become GPLv3 as most parts of QEMU is probably GPLv2+ already or BSD like free that should be possible to combine with only files explicitely GPLv2 in QEMU remaining at that license and UTM parts are Apache 2.0 when separated from QEMU. I have no idea about legal stuff whatsoever but combining two free software components should be legal some way (otherwise it's not possible to combine GPLv2 with GPLv3 either).
You need to distinguish between GPLv2-only and GPLv2-or-later.
GPLv2-or-later is fine as that upgrades to GPLv3 when used in a combined work with Apache License or GPLv3 software.
GPLv2-only will, by design, *not* upgrade to newer GPL versions when combined - it is simply license incompatible.
QEMU unfortunately has a bunch a GPLv2-only code present that we cannot eliminate.
Regards,
Daniel
--|: https://berrange.com -o- https://www.flickr.com/photos/dberrange :| |: https://libvirt.org -o- https://fstop138.berrange.com :| |: https://entangle-photo.org -o- https://www.instagram.com/dberrange :|
Re: [PATCH 04/10] meson: option to build as shared library
Quoted 5 lines · Joelle van Dyne
I will start a separate conversation of UTM's license compatibility.
Regarding the patch, would some sort of warning message in configure (if building as a shared library) regarding the license be wise? Or would it pollute the output logs?
I think there's also a more fundamental question of whether this is a concept we actually want to support at all.
IIUC, this shared library just exposes a "qemu_main" method which the external app has to jump into. IOW, the "char **argv" parameter to qemu_main becomes the ELF library ABI. Declaring this a shared library interface is a non-negligible commitment for QEMU maintainers, especially given that there is alot about QMEU's command line parsing that maintainers do not like and wish to change.
There is a further question about whether we want to commit to an architectural model where fork() is not something we can use. A significant area of development for QEMU right now is around the modularization of the device model such that QEMU is no longer a single process, but rather a collection of processes, each proc responsible for some specific hardware emulation. Thus far all the device modularization stuff is strictly optional, but we have the freedom to make it mandatory and use it transparently behind the scenes. If we declare this shared library model supported in order to avoid use of fork, then we're restricting our future options wrt device modularization.
So including the license issue, that's three major questionmarks around desirability of supporting use of QEMU as a shared library.
Regards,
Daniel
Signature · 3 lines
|: https://berrange.com -o- https://www.flickr.com/photos/dberrange :| |: https://libvirt.org -o- https://fstop138.berrange.com :| |: https://entangle-photo.org -o- https://www.instagram.com/dberrange :|
Re: [PATCH 04/10] meson: option to build as shared library
Quoted 9 lines · Daniel P. Berrangé
Quoted 5 lines · Joelle van Dyne
I will start a separate conversation of UTM's license compatibility.
Regarding the patch, would some sort of warning message in configure (if building as a shared library) regarding the license be wise? Or would it pollute the output logs?
I think there's also a more fundamental question of whether this is a concept we actually want to support at all.
Discussing other compelling reasons for doubt is OK, just wanted to avoid having this dismissed on possible licensing problems only. I still think it would be a good idea to support QEMU on iOS but due to the (mostly security related) limitations of that platform some compromises my be needed. Please consider it instead of being quick to decide to avoid these problems by not taking the patches upstream which is a convenient solution from QEMU viewpoint but not helping other projects. (Other platforms may come up in the future with similar limitations that iOS has as more desktop OSes also move in the same direction to increase security so these may need to be handled anyway at one point, iOS is a good test case for that.)
Quoted 6 lines
IIUC, this shared library just exposes a "
qemu_main" method which the external app has to jump into. IOW, the "char **argv" parameter toqemu_mainbecomes the ELF library ABI. Declaring this a shared library interface is a non-negligible commitment for QEMU maintainers, especially given that there is alot about QMEU's command line parsing that maintainers do not like and wish to change.
Given that libvirt uses the command line instead of a proper API currently, this is not worse than that. If there was a better API or there will be one in the future, the shared lib API can be changed the same way as libvirt will need to be adapted for that but it's not reasonable to demand these patches to come up with that API now. So for now this seems to be acceptable and does not prevent cleaning it up later together with the planned changes you mentioned. Compatibility for the command line will have to be maintained until a better API is devised for use by other software like libvirt and anyone intending to use it as dll so this does not seem like added commitment.
Quoted 2 lines
There is a further question about whether we want to commit to an architectural model where
fork()is not something we can use. A
Does Windows support fork()? I think we're already committed to support Windows so any solution you'll come up with will have the same problem anyway. So I think this does not add additional restriction that we don't already have either.
Regards,
BALATON Zoltan
Re: [PATCH 04/10] meson: option to build as shared library
Since there seems to be some more push back on this one, I will remove this patch from the v2 submission and submit it as a separate patch
-j
Quoted 52 lines · BALATON Zoltan
Quoted 9 lines · Daniel P. Berrangé
Quoted 5 lines · Joelle van Dyne
I will start a separate conversation of UTM's license compatibility.
Regarding the patch, would some sort of warning message in configure (if building as a shared library) regarding the license be wise? Or would it pollute the output logs?
I think there's also a more fundamental question of whether this is a concept we actually want to support at all.
Discussing other compelling reasons for doubt is OK, just wanted to avoid having this dismissed on possible licensing problems only. I still think it would be a good idea to support QEMU on iOS but due to the (mostly security related) limitations of that platform some compromises my be needed. Please consider it instead of being quick to decide to avoid these problems by not taking the patches upstream which is a convenient solution from QEMU viewpoint but not helping other projects. (Other platforms may come up in the future with similar limitations that iOS has as more desktop OSes also move in the same direction to increase security so these may need to be handled anyway at one point, iOS is a good test case for that.)
Quoted 6 lines
IIUC, this shared library just exposes a "
qemu_main" method which the external app has to jump into. IOW, the "char **argv" parameter toqemu_mainbecomes the ELF library ABI. Declaring this a shared library interface is a non-negligible commitment for QEMU maintainers, especially given that there is alot about QMEU's command line parsing that maintainers do not like and wish to change.Given that libvirt uses the command line instead of a proper API currently, this is not worse than that. If there was a better API or there will be one in the future, the shared lib API can be changed the same way as libvirt will need to be adapted for that but it's not reasonable to demand these patches to come up with that API now. So for now this seems to be acceptable and does not prevent cleaning it up later together with the planned changes you mentioned. Compatibility for the command line will have to be maintained until a better API is devised for use by other software like libvirt and anyone intending to use it as dll so this does not seem like added commitment.
Quoted 2 lines
There is a further question about whether we want to commit to an architectural model where
fork()is not something we can use. ADoes Windows support
fork()? I think we're already committed to support Windows so any solution you'll come up with will have the same problem anyway. So I think this does not add additional restriction that we don't already have either.Regards,
BALATON Zoltan
Re: [PATCH 04/10] meson: option to build as shared library
In reply to Daniel P. BerrangéQuoted 15 lines · Daniel P. Berrangé
Quoted 14 lines · BALATON Zoltan
Quoted 12 lines · Daniel P. Berrangé
Quoted 6 lines · Joelle van Dyne
From: osy <[email protected]>
On iOS, we cannot
fork()new processes, so the best way to load QEMU into an app is through a shared library. We add a new configure option--enable-shared-libthat will build the bulk of QEMU into a shared lib. The usual executables will then link to the library.Note that QEMU as a combined work is licensed GPLv2-only, so if an app is linking to it as a shared library, the application's license has to be GPLv2 compatible. I fear that shipping as a shared library is an easy way for apps to get into a license violating situation without realizing.
Quoted 5 lines
Quoted 3 lines
Please don't let that be an obstacle in merging this series. They'll do it anyway as seen here so having it upstream is probably better than having a lot of different/divergent forks.
"They'll violate the license anyway" is not a compelling argument.
I meant they'll use it in other projects anyway and will maintain a fork instead of contributing to upstream so I think keeping this out of QEMU master does not help prevent that and would only promotes fragmentation. So avoiding possibly breaking license to not accept this series is not a compelling argument in my opinion.
Regards,
BALATON Zoltan
Quoted 32 lines
Quoted 9 lines
In case of UTM it seems to be licensed under Apache License 2.0:
https://github.com/utmapp/UTM/blob/master/LICENSE
which FSF says not compatible with GPLv2 but it is with GPLv3:
Quoted 8 lines
Not sure however if that's for using Apache licenced part in GPLv2 code or the other way around like in UTM in which case I think the whole work will effectively become GPLv3 as most parts of QEMU is probably GPLv2+ already or BSD like free that should be possible to combine with only files explicitely GPLv2 in QEMU remaining at that license and UTM parts are Apache 2.0 when separated from QEMU. I have no idea about legal stuff whatsoever but combining two free software components should be legal some way (otherwise it's not possible to combine GPLv2 with GPLv3 either).
You need to distinguish between GPLv2-only and GPLv2-or-later.
GPLv2-or-later is fine as that upgrades to GPLv3 when used in a combined work with Apache License or GPLv3 software.
GPLv2-only will, by design, *not* upgrade to newer GPL versions when combined - it is simply license incompatible.
QEMU unfortunately has a bunch a GPLv2-only code present that we cannot eliminate.
Regards,
Daniel
PATCH 5/10 slirp: update for iOS resolv fix
In reply to Joelle van DyneFrom: osy <[email protected]>
We cannot access /etc/resolv.conf on iOS so libslirp is modified to use libresolv instead.
--- .gitmodules | 2 +- meson.build | 2 ++ slirp | 2 +- 3 files changed, 4 insertions(+), 2 deletions(-)
.gitmodules +1 -1
@@ -51,7 +51,7 @@ url = https://git.qemu.org/git/edk2.git [submodule "slirp"] path = slirp - url = https://git.qemu.org/git/libslirp.git + url = https://github.com/utmapp/libslirp.git [submodule "roms/opensbi"] path = roms/opensbi url = https://git.qemu.org/git/opensbi.git
meson.build +2 -0
@@ -996,6 +996,8 @@ if have_system slirp_deps = [] if targetos == 'windows' slirp_deps = cc.find_library('iphlpapi') + elif targetos == 'darwin' + slirp_deps = cc.find_library('resolv') endif slirp_conf = configuration_data() slirp_conf.set('SLIRP_MAJOR_VERSION', meson.project_version().split('.')[0])
slirp +1 -1
@@ -1 +1 @@ -Subproject commit ce94eba2042d52a0ba3d9e252ebce86715e94275 +Subproject commit 452c389d8288f81ec9d59d983a047d4e54f3194e
Signature · 1 line
2.24.3 (Apple Git-128)
Re: [PATCH 05/10] slirp: update for iOS resolv fix
Quoted 17 lines · Joelle van Dyne
From: osy <[email protected]>
We cannot access
/etc/resolv.confon iOS so libslirp is modified to use libresolv instead.Signed-off-by Joelle van Dyne <[email protected]>--- .gitmodules | 2 +- meson.build | 2 ++ slirp | 2 +- 3 files changed, 4 insertions(+), 2 deletions(-).gitmodules +0
-0
.gitmodules line 54
Quoted 5 lines
.gitmodules +1
-1@@ -51,7 +51,7 @@ url = https://git.qemu.org/git/edk2.git [submodule "slirp"] path = slirp - url = https://git.qemu.org/git/libslirp.git + url = https://github.com/utmapp/libslirp.git
NAck.
You can not take over the SLiRP project submodule that way.
I suggest getting your SLiRP changes merged with mainstream instead, see:
https://gitlab.freedesktop.org/slirp/libslirp#contributing
Quoted 23 lines
.gitmodules +0
-0[submodule "roms/opensbi"] path = roms/opensbi url = https://git.qemu.org/git/opensbi.gitmeson.build +2
-0@@ -996,6 +996,8 @@ if have_system slirp_deps = [] if targetos == 'windows' slirp_deps = cc.find_library('iphlpapi') + elif targetos == 'darwin' + slirp_deps = cc.find_library('resolv') endif slirp_conf = configuration_data() slirp_conf.set('SLIRP_MAJOR_VERSION', meson.project_version().split('.')[0])slirp +1
-1@@ -1 +1 @@ -Subproject commit ce94eba2042d52a0ba3d9e252ebce86715e94275 +Subproject commit 452c389d8288f81ec9d59d983a047d4e54f3194e
Re: [PATCH 05/10] slirp: update for iOS resolv fix
Hi
Quoted 26 lines · Philippe Mathieu-Daudé
Quoted 17 lines · Joelle van Dyne
From: osy <[email protected]>
We cannot access
/etc/resolv.confon iOS so libslirp is modified to use libresolv instead.Signed-off-by Joelle van Dyne <[email protected]>--- .gitmodules | 2 +- meson.build | 2 ++ slirp | 2 +- 3 files changed, 4 insertions(+), 2 deletions(-).gitmodules +0
-0.gitmodules line 54
Quoted 5 lines
.gitmodules +1
-1@@ -51,7 +51,7 @@ url = https://git.qemu.org/git/edk2.git [submodule "slirp"] path = slirp - url = https://git.qemu.org/git/libslirp.git + url = https://github.com/utmapp/libslirp.gitNAck.
Quoted 7 lines
You can not take over the SLiRP project submodule that way.
I suggest getting your SLiRP changes merged with mainstream instead, see:
https://gitlab.freedesktop.org/slirp/libslirp#contributing
I think he did:
https://gitlab.freedesktop.org/slirp/libslirp/-/merge_requests/54
Btw, I also noticed the coroutine library submodule proposed in this series is a fork from the original library. Not sure what the upstream status is and whether this is fine.
Quoted 27 lines
[submodule "roms/opensbi"]
Quoted 7 lines
.gitmodules +0
-0path = roms/opensbi url = https://git.qemu.org/git/opensbi.gitmeson.build +0
-0meson.build if have_system · line 1003
Quoted 8 lines
meson.build +2
-0@@ -996,6 +996,8 @@ if have_system slirp_deps = [] if targetos == 'windows' slirp_deps = cc.find_library('iphlpapi') + elif targetos == 'darwin' + slirp_deps = cc.find_library('resolv') endif slirp_conf = configuration_data() slirp_conf.set('SLIRP_MAJOR_VERSION',meson.project_version().split('.')[0])
Quoted 7 lines
slirp +1
-1@@ -1 +1 @@ -Subproject commit ce94eba2042d52a0ba3d9e252ebce86715e94275 +Subproject commit 452c389d8288f81ec9d59d983a047d4e54f3194e
Signature · 1 line
Marc-André Lureau
Re: [PATCH 05/10] slirp: update for iOS resolv fix
Quoted 37 lines · Marc-André Lureau
Hi
On Tue, Oct 13, 2020 at 5:34 PM Philippe Mathieu-Daudé <[email protected] <mailto:[email protected]>> wrote:
On 10/13/20 1:29 AM, Joelle van Dyne wrote:
> From: osy <[email protected]
<mailto:[email protected]>>
>
> We cannot access/etc/resolv.confon iOS so libslirp is modified
to use
> libresolv instead.
>
> Signed-off-by: Joelle van Dyne <[email protected]>
> ---
> .gitmodules | 2 +-
> meson.build | 2 ++
> slirp | 2 +-
> 3 files changed, 4 insertions(+), 2 deletions(-)
>
> diff --git a/.gitmodules b/.gitmodules
> index2bdeeacef8..f23e859210100644
> --- a/.gitmodules
> +++ b/.gitmodules
> @@ -51,7 +51,7 @@
> url = https://git.qemu.org/git/edk2.git
<https://git.qemu.org/git/edk2.git>
> [submodule "slirp"]
> path = slirp
> - url = https://git.qemu.org/git/libslirp.git
<https://git.qemu.org/git/libslirp.git>
> + url = https://github.com/utmapp/libslirp.git
<https://github.com/utmapp/libslirp.git>NAck.
You can not take over the SLiRP project submodule that way.
Quoted 7 lines
I suggest getting your SLiRP changes merged with mainstream instead, see:
https://gitlab.freedesktop.org/slirp/libslirp#contributing
<https://gitlab.freedesktop.org/slirp/libslirp#contributing>I think he did: https://gitlab.freedesktop.org/slirp/libslirp/-/merge_requests/54 <https://gitlab.freedesktop.org/slirp/libslirp/-/merge_requests/54>
I am being wary because the series is not posted as RFC.
But from the cover it looks like a RFC series:
* slirp updated to support DNS resolving using libresolv; a separate patch will be submitted to the project. To allow for builds to succeed, the .gitmodule is temporarily changed. We're not entirely sure how cross-project patches should be handled here.
Quoted 34 lines
Btw, I also noticed the coroutine library submodule proposed in this series is a fork from the original library. Not sure what the upstream status is and whether this is fine.
> [submodule "roms/opensbi"] > path = roms/opensbi > url = https://git.qemu.org/git/opensbi.git <https://git.qemu.org/git/opensbi.git> > diff --git a/meson.build b/meson.build > index 32cf08619f..da96e296e0 100644 > --- a/meson.build > +++ b/meson.build > @@ -996,6 +996,8 @@ if have_system > slirp_deps = [] > if targetos == 'windows' > slirp_deps = cc.find_library('iphlpapi') > + elif targetos == 'darwin' > + slirp_deps = cc.find_library('resolv') > endif > slirp_conf = configuration_data() > slirp_conf.set('SLIRP_MAJOR_VERSION', meson.project_version().split('.')[0]) > diff --git a/slirp b/slirp > index ce94eba204..452c389d82 160000 > --- a/slirp > +++ b/slirp > @@ -1 +1 @@ > -Subproject commit ce94eba2042d52a0ba3d9e252ebce86715e94275 > +Subproject commit 452c389d8288f81ec9d59d983a047d4e54f3194eSignature · 1 line
Marc-André Lureau
Re: [PATCH 05/10] slirp: update for iOS resolv fix
Sorry, I was not aware of the rules for RFC. I will remove this one from the v2 patch set. If and when the libslirp changes are in, what are the procedures for sending the QEMU side changes?
-j
Quoted 97 lines · Philippe Mathieu-Daudé
Quoted 44 lines · Marc-André Lureau
Hi
On Tue, Oct 13, 2020 at 5:34 PM Philippe Mathieu-Daudé <[email protected] <mailto:[email protected]>> wrote:
On 10/13/20 1:29 AM, Joelle van Dyne wrote: > From: osy <[email protected] <mailto:[email protected]>> > > We cannot access /etc/resolv.conf on iOS so libslirp is modified to use > libresolv instead. > > Signed-off-by: Joelle van Dyne <[email protected]> > --- > .gitmodules | 2 +- > meson.build | 2 ++ > slirp | 2 +- > 3 files changed, 4 insertions(+), 2 deletions(-) > > diff --git a/.gitmodules b/.gitmodules > index 2bdeeacef8..f23e859210 100644 > --- a/.gitmodules > +++ b/.gitmodules > @@ -51,7 +51,7 @@ > url = https://git.qemu.org/git/edk2.git <https://git.qemu.org/git/edk2.git> > [submodule "slirp"] > path = slirp > - url = https://git.qemu.org/git/libslirp.git <https://git.qemu.org/git/libslirp.git> > + url = https://github.com/utmapp/libslirp.git <https://github.com/utmapp/libslirp.git> NAck. You can not take over the SLiRP project submodule that way. I suggest getting your SLiRP changes merged with mainstream instead, see: https://gitlab.freedesktop.org/slirp/libslirp#contributing <https://gitlab.freedesktop.org/slirp/libslirp#contributing>Quoted 3 lines
I think he did:
https://gitlab.freedesktop.org/slirp/libslirp/-/merge_requests/54
<https://gitlab.freedesktop.org/slirp/libslirp/-/merge_requests/54>I am being wary because the series is not posted as RFC.
But from the cover it looks like a RFC series:
* slirp updated to support DNS resolving using libresolv; a separate patch will be submitted to the project. To allow for builds to succeed, the .gitmodule is temporarily changed. We're not entirely sure how cross-project patches should be handled here.
Quoted 36 lines
Btw, I also noticed the coroutine library submodule proposed in this series is a fork from the original library. Not sure what the upstream status is and whether this is fine.
> [submodule "roms/opensbi"] > path = roms/opensbi > url = https://git.qemu.org/git/opensbi.git <https://git.qemu.org/git/opensbi.git> > diff --git a/meson.build b/meson.build > index 32cf08619f..da96e296e0 100644 > --- a/meson.build > +++ b/meson.build > @@ -996,6 +996,8 @@ if have_system > slirp_deps = [] > if targetos == 'windows' > slirp_deps = cc.find_library('iphlpapi') > + elif targetos == 'darwin' > + slirp_deps = cc.find_library('resolv') > endif > slirp_conf = configuration_data() > slirp_conf.set('SLIRP_MAJOR_VERSION', meson.project_version().split('.')[0]) > diff --git a/slirp b/slirp > index ce94eba204..452c389d82 160000 > --- a/slirp > +++ b/slirp > @@ -1 +1 @@ > -Subproject commit ce94eba2042d52a0ba3d9e252ebce86715e94275 > +Subproject commit 452c389d8288f81ec9d59d983a047d4e54f3194e--
Marc-André Lureau
PATCH 6/10 coroutine: add libucontext as external library
In reply to Joelle van DyneFrom: osy <[email protected]>
iOS does not support ucontext natively for aarch64 and the sigaltstack is also unsupported (even worse, it fails silently, see:
https://openradar.appspot.com/13002712 )
As a workaround we include a library implementation of ucontext and add it as a build option.
--- .gitmodules | 3 +++ configure | 23 ++++++++++++++++++++--- libucontext | 1 + meson.build | 29 ++++++++++++++++++++++++++++- meson_options.txt | 2 ++ util/coroutine-ucontext.c | 9 +++++++++ 6 files changed, 63 insertions(+), 4 deletions(-) create mode 160000 libucontext
.gitmodules +3 -0
@@ -64,3 +64,6 @@ [submodule "roms/vbootrom"] path = roms/vbootrom url = https://git.qemu.org/git/vbootrom.git +[submodule "libucontext"] + path = libucontext + url = https://github.com/utmapp/libucontext.git
configure +20 -3
@@ -1761,7 +1761,7 @@ Advanced options (experts only): --oss-lib path to OSS library --cpu=CPU Build for host CPU [$cpu] --with-coroutine=BACKEND coroutine backend. Supported options: - ucontext, sigaltstack, windows + ucontext, libucontext, sigaltstack, windows --enable-gcov enable test coverage analysis with gcov --disable-blobs disable installing provided firmware blobs --with-vss-sdk=SDK-path enable Windows VSS support in QEMU Guest Agent
@@ -5064,6 +5064,8 @@ if test "$coroutine" = ""; then coroutine=win32 elif test "$ucontext_works" = "yes"; then coroutine=ucontext + elif test "$ios" = "yes"; then + coroutine=libucontext else coroutine=sigaltstack fi
@@ -5087,12 +5089,27 @@ else error_exit "only the 'windows' coroutine backend is valid for Windows" fi ;; + libucontext) + ;; *) error_exit "unknown coroutine backend $coroutine" ;; esac fi +case $coroutine in +libucontext) + git_submodules="${git_submodules} libucontext" + mkdir -p libucontext + coroutine_impl=ucontext + libucontext="enabled" + ;; +*) + coroutine_impl=$coroutine + libucontext="disabled" + ;; +esac + if test "$coroutine_pool" = ""; then coroutine_pool=yes fi
@@ -6682,7 +6699,7 @@ if test "$rbd" = "yes" ; then echo "RBD_LIBS=$rbd_libs" >> $config_host_mak fi -echo "CONFIG_COROUTINE_BACKEND=$coroutine" >> $config_host_mak +echo "CONFIG_COROUTINE_BACKEND=$coroutine_impl" >> $config_host_mak if test "$coroutine_pool" = "yes" ; then echo "CONFIG_COROUTINE_POOL=1" >> $config_host_mak else
@@ -7282,7 +7299,7 @@ NINJA=${ninja:-$PWD/ninjatool} $meson setup \ -Dxen=$xen -Dxen_pci_passthrough=$xen_pci_passthrough -Dtcg=$tcg \ -Dcocoa=$cocoa -Dmpath=$mpath -Dsdl=$sdl -Dsdl_image=$sdl_image \ -Dvnc=$vnc -Dvnc_sasl=$vnc_sasl -Dvnc_jpeg=$vnc_jpeg -Dvnc_png=$vnc_png \ - -Dgettext=$gettext -Dxkbcommon=$xkbcommon -Du2f=$u2f \ + -Dgettext=$gettext -Dxkbcommon=$xkbcommon -Du2f=$u2f -Ducontext=$libucontext \ -Dcapstone=$capstone -Dslirp=$slirp -Dfdt=$fdt -Dshared-lib=$shared_lib \ $cross_arg \ "$PWD" "$source_path"
libucontext new file +1 -0
@@ -0,0 +1 @@ +Subproject commit 7094e4c42723b6178a4e2b60d4631d8a88f40719
meson.build +28 -1
@@ -1101,9 +1101,35 @@ if not fdt.found() and fdt_required.length() > 0 error('fdt not available but required by targets ' + ', '.join(fdt_required)) endif +ucontext = not_found +slirp_opt = 'disabled' +if get_option('ucontext').enabled() + if not fs.is_dir(meson.current_source_dir() / 'libucontext/arch' / cpu) + error('libucontext is wanted but not implemented for host ' + cpu) + endif + arch = host_machine.cpu() + ucontext_cargs = ['-DG_LOG_DOMAIN="ucontext"', '-DCUSTOM_IMPL'] + ucontext_files = [ + 'libucontext/arch' / arch / 'getcontext.S', + 'libucontext/arch' / arch / 'setcontext.S', + 'libucontext/arch' / arch / 'makecontext.c', + 'libucontext/arch' / arch / 'startcontext.S', + 'libucontext/arch' / arch / 'swapcontext.S', + ] + + ucontext_inc = include_directories('libucontext/include') + libucontext = static_library('ucontext', + sources: ucontext_files, + c_args: ucontext_cargs, + include_directories: ucontext_inc) + ucontext = declare_dependency(link_with: libucontext, + include_directories: ucontext_inc) +endif + config_host_data.set('CONFIG_CAPSTONE', capstone.found()) config_host_data.set('CONFIG_FDT', fdt.found()) config_host_data.set('CONFIG_SLIRP', slirp.found()) +config_host_data.set('CONFIG_LIBUCONTEXT', ucontext.found()) genh += configure_file(output: 'config-host.h', configuration: config_host_data)
@@ -1323,7 +1349,7 @@ util_ss.add_all(trace_ss) util_ss = util_ss.apply(config_all, strict: false) libqemuutil = static_library('qemuutil', sources: util_ss.sources() + stub_ss.sources() + genh, - dependencies: [util_ss.dependencies(), m, glib, socket, malloc]) + dependencies: [util_ss.dependencies(), m, glib, socket, malloc, ucontext]) qemuutil = declare_dependency(link_with: libqemuutil, sources: genh + version_res)
@@ -1946,6 +1972,7 @@ if targetos == 'windows' summary_info += {'QGA MSI support': config_host.has_key('CONFIG_QGA_MSI')} endif summary_info += {'seccomp support': config_host.has_key('CONFIG_SECCOMP')} +summary_info += {'libucontext support': ucontext.found()} summary_info += {'coroutine backend': config_host['CONFIG_COROUTINE_BACKEND']} summary_info += {'coroutine pool': config_host['CONFIG_COROUTINE_POOL'] == '1'} summary_info += {'debug stack usage': config_host.has_key('CONFIG_DEBUG_STACK_USAGE')}
meson_options.txt +2 -0
@@ -50,6 +50,8 @@ option('vnc_sasl', type : 'feature', value : 'auto', description: 'SASL authentication for VNC server') option('xkbcommon', type : 'feature', value : 'auto', description: 'xkbcommon support') +option('ucontext', type : 'feature', value : 'disabled', + description: 'libucontext support') option('capstone', type: 'combo', value: 'auto', choices: ['disabled', 'enabled', 'auto', 'system', 'internal'],
util/coroutine-ucontext.c +9 -0
@@ -23,7 +23,16 @@#undef _FORTIFY_SOURCE#endif #include "qemu/osdep.h" +#if defined(CONFIG_LIBUCONTEXT ) +#include <libucontext.h> +#define ucontext_t libucontext_ucontext_t +#define getcontext libucontext_getcontext +#define setcontext libucontext_setcontext +#define swapcontext libucontext_swapcontext +#define makecontext libucontext_makecontext +#else #include <ucontext.h> +#endif #include "qemu/coroutine_int.h" #ifdef CONFIG_VALGRIND_H
Signature · 1 line
2.24.3 (Apple Git-128)
Re: [PATCH 06/10] coroutine: add libucontext as external library
Quoted 10 lines · Joelle van Dyne
From: osy <[email protected]>
iOS does not support ucontext natively for aarch64 and the sigaltstack is also unsupported (even worse, it fails silently, see:
https://openradar.appspot.com/13002712 )As a workaround we include a library implementation of ucontext and add it as a build option.
Signed-off-by Joelle van Dyne <[email protected]>
Hi,
Thanks for sending posting this!
Please indicate what license libucontext is under, that it is compatible with QEMU's overall GPL v2 license, and update QEMU license documentation (LICENSE, etc), if necessary.
Please update .gitlab-ci.yml with build tests. Is there a way to test building QEMU for iOS? If not, then it's difficult for the upstream QEMU project to carry iOS-specific features since we cannot test them.
Thanks,
Stefan
Re: [PATCH 06/10] coroutine: add libucontext as external library
Quoted 10 lines · Stefan Hajnoczi
Quoted 9 lines · Joelle van Dyne
From: osy <[email protected]>
iOS does not support ucontext natively for aarch64 and the sigaltstack is also unsupported (even worse, it fails silently, see:
https://openradar.appspot.com/13002712 )As a workaround we include a library implementation of ucontext and add it as a build option.
Quoted 7 lines
Quoted 1 line
Signed-off-by Joelle van Dyne <[email protected]>Hi,
Thanks for sending posting this!Please indicate what license libucontext is under, that it is compatible with QEMU's overall GPL v2 license, and update QEMU license
https://github.com/utmapp/libucontext/blob/master/LICENSE
Maybe the submodule repo should be mirrored in qemu.git eventually.
Quoted 5 lines
documentation (LICENSE, etc), if necessary.
Please update .gitlab-ci.yml with build tests. Is there a way to test building QEMU for iOS? If not, then it's difficult for the upstream QEMU project to carry iOS-specific features since we cannot test them.
Build testing should be possible on OS X host that I think we already have provided it has the right XCode version installed. (Running it is difficult due to app deployment requirements of iOS devices.) But I don't know much about these, just trying to point at some possible directions to solve this.
Regards,
BALATON Zoltan
Re: [PATCH 06/10] coroutine: add libucontext as external library
Thanks for providing the link.
I'm not sure what license that is/if it is compatible with GPLv2. Can someone provide guidance on what to update in QEMU's license? I am not too familiar with all this license stuff.
Regarding building for iOS, as Balaton said it is possible with an OSX host. However, it does require some work to set up all the right environment variables (Apple does not follow standard conventions for cross compiling). You can see the build script we use for UTM:
https://github.com/utmapp/UTM/blob/master/scripts/build_dependencies.sh
However, a lot of the changes does work on other platforms (libucontext and bulletproof (mirror mapped) JIT are two major ones). We used iOS build to guard these features because they are only useful for iOS, but we can make it a configure option if that's desired?
-j
Quoted 38 lines · BALATON Zoltan
Quoted 10 lines · Stefan Hajnoczi
Quoted 9 lines · Joelle van Dyne
From: osy <[email protected]>
iOS does not support ucontext natively for aarch64 and the sigaltstack is also unsupported (even worse, it fails silently, see:
https://openradar.appspot.com/13002712 )As a workaround we include a library implementation of ucontext and add it as a build option.
Quoted 7 lines
Quoted 1 line
Signed-off-by Joelle van Dyne <[email protected]>Hi,
Thanks for sending posting this!Please indicate what license libucontext is under, that it is compatible with QEMU's overall GPL v2 license, and update QEMU license
https://github.com/utmapp/libucontext/blob/master/LICENSE
Maybe the submodule repo should be mirrored in qemu.git eventually.
Quoted 5 lines
documentation (LICENSE, etc), if necessary.
Please update .gitlab-ci.yml with build tests. Is there a way to test building QEMU for iOS? If not, then it's difficult for the upstream QEMU project to carry iOS-specific features since we cannot test them.
Build testing should be possible on OS X host that I think we already have provided it has the right XCode version installed. (Running it is difficult due to app deployment requirements of iOS devices.) But I don't know much about these, just trying to point at some possible directions to solve this.
Regards,
BALATON Zoltan
Re: [PATCH 06/10] coroutine: add libucontext as external library
In reply to BALATON Zoltan viaQuoted 13 lines · BALATON Zoltan via
Quoted 12 lines · Stefan Hajnoczi
Quoted 10 lines · Joelle van Dyne
From: osy <[email protected]>
iOS does not support ucontext natively for aarch64 and the sigaltstack is also unsupported (even worse, it fails silently, see:
https://openradar.appspot.com/13002712 )As a workaround we include a library implementation of ucontext and add it as a build option.
Signed-off-by Joelle van Dyne <[email protected]>
Quoted 7 lines
Quoted 5 lines
Hi,
Thanks for sending posting this!Please indicate what license libucontext is under, that it is compatible with QEMU's overall GPL v2 license, and update QEMU license
I don't recognise that license text as being an exact match for any common open source license.
As best I can tell, it is closest to being yet another variant of the MIT license, of which there are ridiculously many
https://fedoraproject.org/wiki/Licensing:MIT
Regards,
Daniel
Signature · 3 lines
|: https://berrange.com -o- https://www.flickr.com/photos/dberrange :| |: https://libvirt.org -o- https://fstop138.berrange.com :| |: https://entangle-photo.org -o- https://www.instagram.com/dberrange :|
PATCH 7/10 tcg: implement bulletproof JIT
In reply to Joelle van DyneFrom: osy <[email protected]>
On iOS, we cannot allocate RWX pages without special entitlements. As a workaround, we can a RX region and then mirror map it to a separate RX region. Then we can write to one region and execute from the other one.
To better keep track of pointers to RW/RX memory, we mark any tcg_insn_unit pointers as const if they will never be written to. We also define a new macro TCG_CODE_PTR_RW that returns a pointer to RW memory. Only the difference between the two regions is stored in the TCG context.
To ensure cache coherency, we flush the data cache in the RW mapping and then invalidate the instruction cache in the RX mapping (where applicable). Because data cache flush is OS defined on some architectures, we do not provide implementations for non iOS platforms (ARM/x86).
--- accel/tcg/cpu-exec.c | 7 +++- accel/tcg/translate-all.c | 78 ++++++++++++++++++++++++++++++++++-- configure | 1 + docs/devel/ios.rst | 40 ++++++++++++++++++ include/exec/exec-all.h | 8 ++++ include/tcg/tcg.h | 18 +++++++-- tcg/aarch64/tcg-target.c.inc | 48 +++++++++++++--------- tcg/aarch64/tcg-target.h | 13 +++++- tcg/arm/tcg-target.c.inc | 33 ++++++++------- tcg/arm/tcg-target.h | 9 ++++- tcg/i386/tcg-target.c.inc | 28 ++++++------- tcg/i386/tcg-target.h | 24 ++++++++++- tcg/mips/tcg-target.c.inc | 64 +++++++++++++++++------------ tcg/mips/tcg-target.h | 8 +++- tcg/ppc/tcg-target.c.inc | 55 ++++++++++++++++--------- tcg/ppc/tcg-target.h | 8 +++- tcg/riscv/tcg-target.c.inc | 51 +++++++++++++---------- tcg/riscv/tcg-target.h | 9 ++++- tcg/s390/tcg-target.c.inc | 25 ++++++------ tcg/s390/tcg-target.h | 13 +++++- tcg/sparc/tcg-target.c.inc | 33 +++++++++------ tcg/sparc/tcg-target.h | 8 +++- tcg/tcg-ldst.c.inc | 2 +- tcg/tcg-pool.c.inc | 9 +++-- tcg/tcg.c | 60 +++++++++++++++++---------- tcg/tci/tcg-target.c.inc | 8 ++-- tcg/tci/tcg-target.h | 9 ++++- 27 files changed, 481 insertions(+), 188 deletions(-) create mode 100644 docs/devel/ios.rst
accel/tcg/cpu-exec.c +6 -1
@@ -354,7 +354,12 @@ void tb_set_jmp_target(TranslationBlock *tb, int n, uintptr_t addr)if (TCG_TARGET_HAS_direct_jump) {uintptr_t offset = tb->jmp_target_arg[n];uintptr_t tc_ptr = (uintptr_t )tb->tc.ptr; -tb_target_set_jmp_target (tc_ptr, tc_ptr + offset, addr); +#if defined(CONFIG_IOS_JIT ) +uintptr_t wr_addr = tc_ptr + offset + tb->code_rw_mirror_diff; +#else +uintptr_t wr_addr = tc_ptr + offset; +#endif +tb_target_set_jmp_target (tc_ptr, tc_ptr + offset, addr, wr_addr); }else { tb->jmp_target_arg[n] = addr; }
accel/tcg/translate-all.c +75 -3
123 lines not on this page · raw message
configure +1 -0
@@ -6220,6 +6220,7 @@ fi if test "$ios" = "yes" ; then echo "CONFIG_IOS=y" >> $config_host_mak + echo "CONFIG_IOS_JIT=y" >> $config_host_mak fi if test "$solaris" = "yes" ; then
docs/devel/ios.rst new file +40 -0
@@ -0,0 +1,40 @@ +=========== +iOS Support +=========== + +To run qemu on the iOS platform, some modifications were required. Most of the +modifications are conditioned on the ``CONFIG_IOS`` and ``CONFIG_IOS_JIT`` +configuration variables. + +Build support +------------- + +For the code to compile, certain changes in the block driver and the slirp +driver had to be made. There is no ``system()`` call, so code requiring it had +to be disabled. + +``ucontext`` support is broken on iOS. The implementation from ``libucontext`` +is used instead. + +Because ``fork()`` is not allowed on iOS apps, the option to build qemu and the +utilities as shared libraries is added. Note that because qemu does not perform +resource cleanup in most cases (open files, allocated memory, etc), it is +advisable that the user implements a proxy layer for syscalls so resources can +be kept track by the app that uses qemu as a shared library. + +JIT support +----------- + +On iOS, allocating RWX pages require special entitlements not usually granted to +apps. However, it is possible to use `bulletproof JIT`_ with a development +certificate. This means that we need to allocate one chunk of memory with RX +permissions and then mirror map the same memory with RW permissions. We generate +code to the mirror mapping and execute the original mapping. + +With ``CONFIG_IOS_JIT`` defined, we store inside the TCG context the difference +between the two mappings. Then, we make sure that any writes to JIT memory is +done to the pointer + the difference (in order to get a pointer to the mirror +mapped space). Additionally, we make sure to flush the data cache before we +invalidate the instruction cache so the changes are seen in both mappings. + +.. _bulletproof JIT: https://www.blackhat.com/docs/us-16/materials/us-16-Krstic.pdf
include/exec/exec-all.h +8 -0
@@ -483,6 +483,14 @@ struct TranslationBlock {uintptr_t jmp_list_head;uintptr_t jmp_list_next[2 ];uintptr_t jmp_dest[2 ]; + +#if defined(CONFIG_IOS_JIT ) +/* +* Store difference to writable mirror +* We need this when patching the jump instructions +*/ +ptrdiff_t code_rw_mirror_diff; +#endif };extern bool parallel_cpus;
include/tcg/tcg.h +14 -4
@@ -261,7 +261,7 @@ struct TCGLabel { unsigned refs : 16;union {uintptr_t value; -tcg_insn_unit *value_ptr; +const tcg_insn_unit *value_ptr; } u; QSIMPLEQ_HEAD(, TCGRelocation) relocs;QSIMPLEQ_ENTRY (TCGLabel) next;
@@ -593,7 +593,7 @@ struct TCGContext {int nb_ops;/* goto_tb support */ -tcg_insn_unit *code_buf; +const tcg_insn_unit *code_buf;uint16_t *tb_jmp_reset_offset;/* tb->jmp_reset_offset */ uintptr_t *tb_jmp_insn_offset;/* tb->jmp_target_arg if direct_jump */ uintptr_t *tb_jmp_target_addr;/* tb->jmp_target_arg if !direct_jump */
@@ -627,6 +627,9 @@ struct TCGContext {size_t code_gen_buffer_size;void *code_gen_ptr;void *data_gen_ptr; +#if defined(CONFIG_IOS_JIT ) +ptrdiff_t code_rw_mirror_diff; +#endif /* Threshold to flush the translated code buffer. */ void *code_gen_highwater;
@@ -677,6 +680,13 @@ struct TCGContext {target_ulong gen_insn_data[TCG_MAX_INSNS ][TARGET_INSN_START_WORDS ]; }; +#if defined(CONFIG_IOS_JIT ) +# define TCG_CODE_PTR_RW (s, code_ptr) \ + (tcg_insn_unit *)((uintptr_t)(code_ptr) + (s)->code_rw_mirror_diff) +#else +# define TCG_CODE_PTR_RW (s, code_ptr) (code_ptr) +#endif +extern TCGContext tcg_init_ctx;extern __threadTCGContext *tcg_ctx;extern TCGv_env cpu_env;
@@ -1099,7 +1109,7 @@ static inline TCGLabel *arg_label(TCGArg i)* correct result. */ -static inline ptrdiff_t tcg_ptr_byte_diff (void *a,void *b) +static inline ptrdiff_t tcg_ptr_byte_diff (const void *a,const void *b) {return a - b; }
@@ -1113,7 +1123,7 @@ static inline ptrdiff_t tcg_ptr_byte_diff(void *a, void *b)* to the destination address. */ -static inline ptrdiff_t tcg_pcrel_diff (TCGContext *s,void *target) +static inline ptrdiff_t tcg_pcrel_diff (TCGContext *s,const void *target) {return tcg_ptr_byte_diff (target, s->code_ptr); }
tcg/aarch64/tcg-target.c.inc +29 -19
148 lines not on this page · raw message
tcg/aarch64/tcg-target.h +12 -1
@@ -150,6 +150,7 @@ typedef enum {#if defined(__APPLE__)void sys_icache_invalidate (void *start,size_t len); +void sys_dcache_flush (void *start,size_t len);#endif static inline void flush_icache_range (uintptr_t start,uintptr_t stop)
@@ -163,7 +164,17 @@ static inline void flush_icache_range(uintptr_t start, uintptr_t stop)#endif } -void tb_target_set_jmp_target (uintptr_t ,uintptr_t ,uintptr_t ); +void tb_target_set_jmp_target (uintptr_t ,uintptr_t ,uintptr_t ,uintptr_t ); +#if defined(CONFIG_IOS_JIT ) +static inline void flush_dcache_range (uintptr_t start,uintptr_t stop) +{ +#if defined(__APPLE__) +sys_dcache_flush ((char *)start, stop - start); +#else +#error "Missing function to flush data cache" +#endif +} +#endif #ifdef CONFIG_SOFTMMU #define TCG_TARGET_NEED_LDST_LABELS
tcg/arm/tcg-target.c.inc +19 -14
@@ -187,17 +187,22 @@ static const uint8_t tcg_cond_to_arm_cond[] = { [TCG_COND_GTU] = COND_HI, }; -static inline bool reloc_pc24(tcg_insn_unit *code_ptr, tcg_insn_unit *target) +static inline bool reloc_pc24(TCGContext *s, + tcg_insn_unit *code_ptr, + const tcg_insn_unit *target) { ptrdiff_t offset = (tcg_ptr_byte_diff(target, code_ptr) - 8) >> 2; if (offset == sextract32(offset, 0, 24)) { - *code_ptr = (*code_ptr & ~0xffffff) | (offset & 0xffffff); + *TCG_CODE_PTR_RW(s, code_ptr) = + (*TCG_CODE_PTR_RW(s, code_ptr) & ~0xffffff) | (offset & 0xffffff); return true; } return false; } -static inline bool reloc_pc13(tcg_insn_unit *code_ptr, tcg_insn_unit *target) +static inline bool reloc_pc13(TCGContext *s, + tcg_insn_unit *code_ptr, + const tcg_insn_unit *target) { ptrdiff_t offset = tcg_ptr_byte_diff(target, code_ptr) - 8;
@@ -209,21 +214,21 @@ static inline bool reloc_pc13(tcg_insn_unit *code_ptr, tcg_insn_unit *target) } insn = deposit32(insn, 23, 1, u); insn = deposit32(insn, 0, 12, offset); - *code_ptr = insn; + *TCG_CODE_PTR_RW(s, code_ptr) = insn; return true; } return false; } -static bool patch_reloc(tcg_insn_unit *code_ptr, int type, +static bool patch_reloc(TCGContext *s, tcg_insn_unit *code_ptr, int type, intptr_t value, intptr_t addend) { tcg_debug_assert(addend == 0); if (type == R_ARM_PC24) { - return reloc_pc24(code_ptr, (tcg_insn_unit *)value); + return reloc_pc24(s, code_ptr, (tcg_insn_unit *)value); } else if (type == R_ARM_PC13) { - return reloc_pc13(code_ptr, (tcg_insn_unit *)value); + return reloc_pc13(s, code_ptr, (tcg_insn_unit *)value); } else { g_assert_not_reached(); }
@@ -1019,7 +1024,7 @@ static inline void tcg_out_st8(TCGContext *s, int cond, * with the code buffer limited to 16MB we wouldn't need the long case. * But we also use it for the tail-call to the qemu_ld/st helpers, which does. */ -static void tcg_out_goto(TCGContext *s, int cond, tcg_insn_unit *addr) +static void tcg_out_goto(TCGContext *s, int cond, const tcg_insn_unit *addr) { intptr_t addri = (intptr_t)addr; ptrdiff_t disp = tcg_pcrel_diff(s, addr);
@@ -1033,7 +1038,7 @@ static void tcg_out_goto(TCGContext *s, int cond, tcg_insn_unit *addr) /* The call case is mostly used for helpers - so it's not unreasonable * for them to be beyond branch range */ -static void tcg_out_call(TCGContext *s, tcg_insn_unit *addr) +static void tcg_out_call(TCGContext *s, const tcg_insn_unit *addr) { intptr_t addri = (intptr_t)addr; ptrdiff_t disp = tcg_pcrel_diff(s, addr);
@@ -1326,7 +1331,7 @@ static TCGReg tcg_out_tlb_read(TCGContext *s, TCGReg addrlo, TCGReg addrhi, helper code. */ static void add_qemu_ldst_label(TCGContext *s, bool is_ld, TCGMemOpIdx oi, TCGReg datalo, TCGReg datahi, TCGReg addrlo, - TCGReg addrhi, tcg_insn_unit *raddr, + TCGReg addrhi, const tcg_insn_unit *raddr, tcg_insn_unit *label_ptr) { TCGLabelQemuLdst *label = new_ldst_label(s);
@@ -1348,7 +1353,7 @@ static bool tcg_out_qemu_ld_slow_path(TCGContext *s, TCGLabelQemuLdst *lb) MemOp opc = get_memop(oi); void *func; - if (!reloc_pc24(lb->label_ptr[0], s->code_ptr)) { + if (!reloc_pc24(s, lb->label_ptr[0], s->code_ptr)) { return false; }
@@ -1411,7 +1416,7 @@ static bool tcg_out_qemu_st_slow_path(TCGContext *s, TCGLabelQemuLdst *lb) TCGMemOpIdx oi = lb->oi; MemOp opc = get_memop(oi); - if (!reloc_pc24(lb->label_ptr[0], s->code_ptr)) { + if (!reloc_pc24(s, lb->label_ptr[0], s->code_ptr)) { return false; }
@@ -2255,11 +2260,11 @@ static inline void tcg_out_movi(TCGContext *s, TCGType type, tcg_out_movi32(s, COND_AL, ret, arg); } -static void tcg_out_nop_fill(tcg_insn_unit *p, int count) +static void tcg_out_nop_fill(TCGContext *s, tcg_insn_unit *p, int count) { int i; for (i = 0; i < count; ++i) { - p[i] = INSN_NOP; + (TCG_CODE_PTR_RW(s, p))[i] = INSN_NOP; } }
tcg/arm/tcg-target.h +8 -1
@@ -139,8 +139,15 @@ static inline void flush_icache_range(uintptr_t start, uintptr_t stop)__builtin___clear_cache ((char *) start, (char *) stop); } +#if defined(CONFIG_IOS_JIT ) +static inline void flush_dcache_range (uintptr_t start,uintptr_t stop) +{ +#error "Unimplemented dcache flush function" +} +#endif +/* not defined -- call should be eliminated at compile time */ -void tb_target_set_jmp_target (uintptr_t ,uintptr_t ,uintptr_t ); +void tb_target_set_jmp_target (uintptr_t ,uintptr_t ,uintptr_t ,uintptr_t );#ifdef CONFIG_SOFTMMU #define TCG_TARGET_NEED_LDST_LABELS
tcg/i386/tcg-target.c.inc +14 -14
@@ -165,9 +165,9 @@ static bool have_lzcnt; # define have_lzcnt 0 #endif -static tcg_insn_unit *tb_ret_addr; +static const tcg_insn_unit *tb_ret_addr; -static bool patch_reloc(tcg_insn_unit *code_ptr, int type, +static bool patch_reloc(TCGContext *s, tcg_insn_unit *code_ptr, int type, intptr_t value, intptr_t addend) { value += addend;
@@ -179,14 +179,14 @@ static bool patch_reloc(tcg_insn_unit *code_ptr, int type, } /* FALLTHRU */ case R_386_32: - tcg_patch32(code_ptr, value); + tcg_patch32(s, code_ptr, value); break; case R_386_PC8: value -= (uintptr_t)code_ptr; if (value != (int8_t)value) { return false; } - tcg_patch8(code_ptr, value); + tcg_patch8(s, code_ptr, value); break; default: tcg_abort();
@@ -1591,7 +1591,7 @@ static void tcg_out_clz(TCGContext *s, int rexw, TCGReg dest, TCGReg arg1, } } -static void tcg_out_branch(TCGContext *s, int call, tcg_insn_unit *dest) +static void tcg_out_branch(TCGContext *s, int call, const tcg_insn_unit *dest) { intptr_t disp = tcg_pcrel_diff(s, dest) - 5;
@@ -1610,12 +1610,12 @@ static void tcg_out_branch(TCGContext *s, int call, tcg_insn_unit *dest) } } -static inline void tcg_out_call(TCGContext *s, tcg_insn_unit *dest) +static inline void tcg_out_call(TCGContext *s, const tcg_insn_unit *dest) { tcg_out_branch(s, 1, dest); } -static void tcg_out_jmp(TCGContext *s, tcg_insn_unit *dest) +static void tcg_out_jmp(TCGContext *s, const tcg_insn_unit *dest) { tcg_out_branch(s, 0, dest); }
@@ -1774,7 +1774,7 @@ static void add_qemu_ldst_label(TCGContext *s, bool is_ld, bool is_64, TCGMemOpIdx oi, TCGReg datalo, TCGReg datahi, TCGReg addrlo, TCGReg addrhi, - tcg_insn_unit *raddr, + const tcg_insn_unit *raddr, tcg_insn_unit **label_ptr) { TCGLabelQemuLdst *label = new_ldst_label(s);
@@ -1805,9 +1805,9 @@ static bool tcg_out_qemu_ld_slow_path(TCGContext *s, TCGLabelQemuLdst *l) int rexw = (l->type == TCG_TYPE_I64 ? P_REXW : 0); /* resolve label address */ - tcg_patch32(label_ptr[0], s->code_ptr - label_ptr[0] - 4); + tcg_patch32(s, label_ptr[0], s->code_ptr - label_ptr[0] - 4); if (TARGET_LONG_BITS > TCG_TARGET_REG_BITS) { - tcg_patch32(label_ptr[1], s->code_ptr - label_ptr[1] - 4); + tcg_patch32(s, label_ptr[1], s->code_ptr - label_ptr[1] - 4); } if (TCG_TARGET_REG_BITS == 32) {
@@ -1890,9 +1890,9 @@ static bool tcg_out_qemu_st_slow_path(TCGContext *s, TCGLabelQemuLdst *l) TCGReg retaddr; /* resolve label address */ - tcg_patch32(label_ptr[0], s->code_ptr - label_ptr[0] - 4); + tcg_patch32(s, label_ptr[0], s->code_ptr - label_ptr[0] - 4); if (TARGET_LONG_BITS > TCG_TARGET_REG_BITS) { - tcg_patch32(label_ptr[1], s->code_ptr - label_ptr[1] - 4); + tcg_patch32(s, label_ptr[1], s->code_ptr - label_ptr[1] - 4); } if (TCG_TARGET_REG_BITS == 32) {
@@ -3842,9 +3842,9 @@ static void tcg_target_qemu_prologue(TCGContext *s) tcg_out_opc(s, OPC_RET, 0, 0, 0); } -static void tcg_out_nop_fill(tcg_insn_unit *p, int count) +static void tcg_out_nop_fill(TCGContext *s, tcg_insn_unit *p, int count) { - memset(p, 0x90, count); + memset(TCG_CODE_PTR_RW(s, p), 0x90, count); } static void tcg_target_init(TCGContext *s)
tcg/i386/tcg-target.h +22 -2
@@ -206,16 +206,36 @@ extern bool have_avx2;#define TCG_TARGET_extract_i64_valid (ofs, len) \ (((ofs) == 8 && (len) == 8) || ((ofs) + (len)) == 32) +#ifdef __APPLE__ +void sys_dcache_flush (void *start,size_t len); +#endif +static inline void flush_icache_range (uintptr_t start,uintptr_t stop) { } +#if defined(CONFIG_IOS_JIT ) +static inline void flush_dcache_range (uintptr_t start,uintptr_t stop) +{ +#if defined(__APPLE__) +sys_dcache_flush ((char *)start, stop - start); +#else +#error "Missing function to flush data cache" +#endif +} +#endif +static inline void tb_target_set_jmp_target (uintptr_t tc_ptr, -uintptr_t jmp_addr,uintptr_t addr) +uintptr_t jmp_addr,uintptr_t addr, +uintptr_t wr_addr) {/* patch the branch destination */ -qatomic_set ((int32_t *)jmp_addr, addr - (jmp_addr +4 )); +qatomic_set ((int32_t *)wr_addr, addr - (jmp_addr +4 ));/* no need to flush icache explicitly */ +#if defined(CONFIG_IOS_JIT ) +/* we do need to flush mirror dcache */ +flush_dcache_range (wr_addr, wr_addr +4 ); +#endif }/* This defines the natural memory order supported by this
tcg/mips/tcg-target.c.inc +38 -26
161 lines not on this page · raw message
tcg/mips/tcg-target.h +7 -1
@@ -212,7 +212,13 @@ static inline void flush_icache_range(uintptr_t start, uintptr_t stop)cacheflush ((void *)start, stop-start,ICACHE ); } -void tb_target_set_jmp_target (uintptr_t ,uintptr_t ,uintptr_t ); +void tb_target_set_jmp_target (uintptr_t ,uintptr_t ,uintptr_t ,uintptr_t ); +#if defined(CONFIG_IOS_JIT ) +static inline void flush_dcache_range (uintptr_t start,uintptr_t stop) +{ +#error "Unimplemented dcache flush function" +} +#endif #ifdef CONFIG_SOFTMMU #define TCG_TARGET_NEED_LDST_LABELS
tcg/ppc/tcg-target.c.inc +35 -20
156 lines not on this page · raw message
tcg/ppc/tcg-target.h +7 -1
@@ -176,7 +176,13 @@ extern bool have_vsx;#define TCG_TARGET_HAS_cmpsel_vec 0void flush_icache_range (uintptr_t start,uintptr_t stop); -void tb_target_set_jmp_target (uintptr_t ,uintptr_t ,uintptr_t ); +void tb_target_set_jmp_target (uintptr_t ,uintptr_t ,uintptr_t ,uintptr_t ); +#if defined(CONFIG_IOS_JIT ) +static inline void flush_dcache_range (uintptr_t start,uintptr_t stop) +{ +#error "Unimplemented dcache flush function" +} +#endif #define TCG_TARGET_DEFAULT_MO (0)#define TCG_TARGET_HAS_MEMORY_BSWAP 1
tcg/riscv/tcg-target.c.inc +29 -22
165 lines not on this page · raw message
tcg/riscv/tcg-target.h +8 -1
@@ -164,8 +164,15 @@ static inline void flush_icache_range(uintptr_t start, uintptr_t stop)__builtin___clear_cache ((char *)start, (char *)stop); } +#if defined(CONFIG_IOS_JIT ) +static inline void flush_dcache_range (uintptr_t start,uintptr_t stop) +{ +#error "Unimplemented dcache flush function" +} +#endif +/* not defined -- call should be eliminated at compile time */ -void tb_target_set_jmp_target (uintptr_t ,uintptr_t ,uintptr_t ); +void tb_target_set_jmp_target (uintptr_t ,uintptr_t ,uintptr_t ,uintptr_t );#define TCG_TARGET_DEFAULT_MO (0)
tcg/s390/tcg-target.c.inc +13 -12
@@ -363,10 +363,10 @@ static void * const qemu_st_helpers[16] = { }; #endif -static tcg_insn_unit *tb_ret_addr; +static const tcg_insn_unit *tb_ret_addr; uint64_t s390_facilities; -static bool patch_reloc(tcg_insn_unit *code_ptr, int type, +static bool patch_reloc(TCGContext *s, tcg_insn_unit *code_ptr, int type, intptr_t value, intptr_t addend) { intptr_t pcrel2;
@@ -378,13 +378,13 @@ static bool patch_reloc(tcg_insn_unit *code_ptr, int type, switch (type) { case R_390_PC16DBL: if (pcrel2 == (int16_t)pcrel2) { - tcg_patch16(code_ptr, pcrel2); + tcg_patch16(s, code_ptr, pcrel2); return true; } break; case R_390_PC32DBL: if (pcrel2 == (int32_t)pcrel2) { - tcg_patch32(code_ptr, pcrel2); + tcg_patch32(s, code_ptr, pcrel2); return true; } break;
@@ -392,7 +392,7 @@ static bool patch_reloc(tcg_insn_unit *code_ptr, int type, if (value == sextract64(value, 0, 20)) { old = *(uint32_t *)code_ptr & 0xf00000ff; old |= ((value & 0xfff) << 16) | ((value & 0xff000) >> 4); - tcg_patch32(code_ptr, old); + tcg_patch32(s, code_ptr, old); return true; } break;
@@ -1302,7 +1302,7 @@ static void tgen_extract(TCGContext *s, TCGReg dest, TCGReg src, tcg_out_risbg(s, dest, src, 64 - len, 63, 64 - ofs, 1); } -static void tgen_gotoi(TCGContext *s, int cc, tcg_insn_unit *dest) +static void tgen_gotoi(TCGContext *s, int cc, const tcg_insn_unit *dest) { ptrdiff_t off = dest - s->code_ptr; if (off == (int16_t)off) {
@@ -1415,7 +1415,7 @@ static void tgen_brcond(TCGContext *s, TCGType type, TCGCond c, tgen_branch(s, cc, l); } -static void tcg_out_call(TCGContext *s, tcg_insn_unit *dest) +static void tcg_out_call(TCGContext *s, const tcg_insn_unit *dest) { ptrdiff_t off = dest - s->code_ptr; if (off == (int32_t)off) {
@@ -1593,7 +1593,8 @@ static TCGReg tcg_out_tlb_read(TCGContext *s, TCGReg addr_reg, MemOp opc, static void add_qemu_ldst_label(TCGContext *s, bool is_ld, TCGMemOpIdx oi, TCGReg data, TCGReg addr, - tcg_insn_unit *raddr, tcg_insn_unit *label_ptr) + const tcg_insn_unit *raddr, + tcg_insn_unit *label_ptr) { TCGLabelQemuLdst *label = new_ldst_label(s);
@@ -1612,7 +1613,7 @@ static bool tcg_out_qemu_ld_slow_path(TCGContext *s, TCGLabelQemuLdst *lb) TCGMemOpIdx oi = lb->oi; MemOp opc = get_memop(oi); - if (!patch_reloc(lb->label_ptr[0], R_390_PC16DBL, + if (!patch_reloc(s, lb->label_ptr[0], R_390_PC16DBL, (intptr_t)s->code_ptr, 2)) { return false; }
@@ -1637,7 +1638,7 @@ static bool tcg_out_qemu_st_slow_path(TCGContext *s, TCGLabelQemuLdst *lb) TCGMemOpIdx oi = lb->oi; MemOp opc = get_memop(oi); - if (!patch_reloc(lb->label_ptr[0], R_390_PC16DBL, + if (!patch_reloc(s, lb->label_ptr[0], R_390_PC16DBL, (intptr_t)s->code_ptr, 2)) { return false; }
@@ -2575,9 +2576,9 @@ static void tcg_target_qemu_prologue(TCGContext *s) tcg_out_insn(s, RR, BCR, S390_CC_ALWAYS, TCG_REG_R14); } -static void tcg_out_nop_fill(tcg_insn_unit *p, int count) +static void tcg_out_nop_fill(TCGContext *s, tcg_insn_unit *p, int count) { - memset(p, 0x07, count * sizeof(tcg_insn_unit)); + memset(TCG_CODE_PTR_RW(s, p), 0x07, count * sizeof(tcg_insn_unit)); } typedef struct {
tcg/s390/tcg-target.h +12 -1
@@ -149,13 +149,24 @@ static inline void flush_icache_range(uintptr_t start, uintptr_t stop) { } +#if defined(CONFIG_IOS_JIT ) +static inline void flush_dcache_range (uintptr_t start,uintptr_t stop) +{ +#error "Unimplemented dcache flush function" +} +#endif +static inline void tb_target_set_jmp_target (uintptr_t tc_ptr, -uintptr_t jmp_addr,uintptr_t addr) +uintptr_t jmp_addr,uintptr_t addr, +uintptr_t wr_addr) {/* patch the branch destination */ intptr_t disp = addr - (jmp_addr -2 );qatomic_set ((int32_t *)jmp_addr, disp /2 );/* no need to flush icache explicitly */ +#if defined(CONFIG_IOS_JIT ) +flush_dcache_range (wr_addr, wr_addr +4 ); +#endif }#ifdef CONFIG_SOFTMMU
tcg/sparc/tcg-target.c.inc +20 -13
@@ -291,14 +291,14 @@ static inline int check_fit_i32(int32_t val, unsigned int bits) # define check_fit_ptr check_fit_i32 #endif -static bool patch_reloc(tcg_insn_unit *code_ptr, int type, +static bool patch_reloc(TCGContext *s, tcg_insn_unit *code_ptr, int type, intptr_t value, intptr_t addend) { uint32_t insn = *code_ptr; intptr_t pcrel; value += addend; - pcrel = tcg_ptr_byte_diff((tcg_insn_unit *)value, code_ptr); + pcrel = tcg_ptr_byte_diff((const tcg_insn_unit *)value, code_ptr); switch (type) { case R_SPARC_WDISP16:
@@ -840,7 +840,7 @@ static void tcg_out_addsub2_i64(TCGContext *s, TCGReg rl, TCGReg rh, tcg_out_mov(s, TCG_TYPE_I64, rl, tmp); } -static void tcg_out_call_nodelay(TCGContext *s, tcg_insn_unit *dest, +static void tcg_out_call_nodelay(TCGContext *s, const tcg_insn_unit *dest, bool in_prologue) { ptrdiff_t disp = tcg_pcrel_diff(s, dest);
@@ -855,7 +855,7 @@ static void tcg_out_call_nodelay(TCGContext *s, tcg_insn_unit *dest, } } -static void tcg_out_call(TCGContext *s, tcg_insn_unit *dest) +static void tcg_out_call(TCGContext *s, const tcg_insn_unit *dest) { tcg_out_call_nodelay(s, dest, false); tcg_out_nop(s);
@@ -868,8 +868,8 @@ static void tcg_out_mb(TCGContext *s, TCGArg a0) } #ifdef CONFIG_SOFTMMU -static tcg_insn_unit *qemu_ld_trampoline[16]; -static tcg_insn_unit *qemu_st_trampoline[16]; +static const tcg_insn_unit *qemu_ld_trampoline[16]; +static const tcg_insn_unit *qemu_st_trampoline[16]; static void emit_extend(TCGContext *s, TCGReg r, int op) {
@@ -1048,11 +1048,11 @@ static void tcg_target_qemu_prologue(TCGContext *s) #endif } -static void tcg_out_nop_fill(tcg_insn_unit *p, int count) +static void tcg_out_nop_fill(TCGContext *s, tcg_insn_unit *p, int count) { int i; for (i = 0; i < count; ++i) { - p[i] = NOP; + (TCG_CODE_PTR_RW(s, p))[i] = NOP; } }
@@ -1163,7 +1163,7 @@ static void tcg_out_qemu_ld(TCGContext *s, TCGReg data, TCGReg addr, #ifdef CONFIG_SOFTMMU unsigned memi = get_mmuidx(oi); TCGReg addrz, param; - tcg_insn_unit *func; + const tcg_insn_unit *func; tcg_insn_unit *label_ptr; addrz = tcg_out_tlb_load(s, addr, memi, memop,
@@ -1226,7 +1226,8 @@ static void tcg_out_qemu_ld(TCGContext *s, TCGReg data, TCGReg addr, } } - *label_ptr |= INSN_OFF19(tcg_ptr_byte_diff(s->code_ptr, label_ptr)); + *TCG_CODE_PTR_RW(s, label_ptr) |= + INSN_OFF19(tcg_ptr_byte_diff(s->code_ptr, label_ptr)); #else if (SPARC64 && TARGET_LONG_BITS == 32) { tcg_out_arithi(s, TCG_REG_T1, addr, 0, SHIFT_SRL);
@@ -1822,7 +1823,7 @@ void tcg_register_jit(void *buf, size_t buf_size) } void tb_target_set_jmp_target(uintptr_t tc_ptr, uintptr_t jmp_addr, - uintptr_t addr) + uintptr_t addr, uintptr_t wr_addr) { intptr_t tb_disp = addr - tc_ptr; intptr_t br_disp = addr - jmp_addr;
@@ -1834,8 +1835,11 @@ void tb_target_set_jmp_target(uintptr_t tc_ptr, uintptr_t jmp_addr, tcg_debug_assert(br_disp == (int32_t)br_disp); if (!USE_REG_TB) { - qatomic_set((uint32_t *)jmp_addr, + qatomic_set((uint32_t *)wr_addr, deposit32(CALL, 0, 30, br_disp >> 2)); +#if defined(CONFIG_IOS_JIT) + flush_dcache_range(wr_addr, wr_addr + 4); +#endif flush_icache_range(jmp_addr, jmp_addr + 4); return; }
@@ -1859,6 +1863,9 @@ void tb_target_set_jmp_target(uintptr_t tc_ptr, uintptr_t jmp_addr, | INSN_IMM13((tb_disp & 0x3ff) | -0x400)); } - qatomic_set((uint64_t *)jmp_addr, deposit64(i2, 32, 32, i1)); + qatomic_set((uint64_t *)wr_addr, deposit64(i2, 32, 32, i1)); +#if defined(CONFIG_IOS_JIT) + flush_dcache_range(wr_addr, wr_addr + 8); +#endif flush_icache_range(jmp_addr, jmp_addr + 8); }
tcg/sparc/tcg-target.h +7 -1
@@ -176,7 +176,13 @@ static inline void flush_icache_range(uintptr_t start, uintptr_t stop) } } -void tb_target_set_jmp_target (uintptr_t ,uintptr_t ,uintptr_t ); +void tb_target_set_jmp_target (uintptr_t ,uintptr_t ,uintptr_t ,uintptr_t ); +#if defined(CONFIG_IOS_JIT ) +static inline void flush_dcache_range (uintptr_t start,uintptr_t stop) +{ +#error "Unimplemented dcache flush function" +} +#endif #define TCG_TARGET_NEED_POOL_LABELS
tcg/tcg-ldst.c.inc +1 -1
@@ -28,7 +28,7 @@ typedef struct TCGLabelQemuLdst { TCGReg addrhi_reg; /* reg index for high word of guest virtual addr */ TCGReg datalo_reg; /* reg index for low word to be loaded or stored */ TCGReg datahi_reg; /* reg index for high word to be loaded or stored */ - tcg_insn_unit *raddr; /* gen code addr of the next IR of qemu_ld/st IR */ + const tcg_insn_unit *raddr; /* gen code addr of the next IR of qemu_ld/st */ tcg_insn_unit *label_ptr[2]; /* label pointers to be updated */ QSIMPLEQ_ENTRY(TCGLabelQemuLdst) next; } TCGLabelQemuLdst;
tcg/tcg-pool.c.inc +5 -4
@@ -119,7 +119,7 @@ static inline void new_pool_l8(TCGContext *s, int rtype, tcg_insn_unit *label, } /* To be provided by cpu/tcg-target.c.inc. */ -static void tcg_out_nop_fill(tcg_insn_unit *p, int count); +static void tcg_out_nop_fill(TCGContext *s, tcg_insn_unit *p, int count); static int tcg_out_pool_finalize(TCGContext *s) {
@@ -135,7 +135,7 @@ static int tcg_out_pool_finalize(TCGContext *s) again when allocating the next TranslationBlock structure. */ a = (void *)ROUND_UP((uintptr_t)s->code_ptr, sizeof(tcg_target_ulong) * p->nlong); - tcg_out_nop_fill(s->code_ptr, (tcg_insn_unit *)a - s->code_ptr); + tcg_out_nop_fill(s, s->code_ptr, (tcg_insn_unit *)a - s->code_ptr); s->data_gen_ptr = a; for (; p != NULL; p = p->next) {
@@ -144,11 +144,12 @@ static int tcg_out_pool_finalize(TCGContext *s) if (unlikely(a > s->code_gen_highwater)) { return -1; } - memcpy(a, p->data, size); + memcpy(TCG_CODE_PTR_RW(s, a), p->data, size); a += size; l = p; } - if (!patch_reloc(p->label, p->rtype, (intptr_t)a - size, p->addend)) { + if (!patch_reloc(s, p->label, p->rtype, + (intptr_t)a - size, p->addend)) { return -2; } }
tcg/tcg.c +39 -21
162 lines not on this page · raw message
tcg/tci/tcg-target.c.inc +4 -4
@@ -369,7 +369,7 @@ static const char *const tcg_target_reg_names[TCG_TARGET_NB_REGS] = { }; #endif -static bool patch_reloc(tcg_insn_unit *code_ptr, int type, +static bool patch_reloc(TCGContext *s, tcg_insn_unit *code_ptr, int type, intptr_t value, intptr_t addend) { /* tcg_out_reloc always uses the same type, addend. */
@@ -377,9 +377,9 @@ static bool patch_reloc(tcg_insn_unit *code_ptr, int type, tcg_debug_assert(addend == 0); tcg_debug_assert(value != 0); if (TCG_TARGET_REG_BITS == 32) { - tcg_patch32(code_ptr, value); + tcg_patch32(s, code_ptr, value); } else { - tcg_patch64(code_ptr, value); + tcg_patch64(s, code_ptr, value); } return true; }
@@ -545,7 +545,7 @@ static void tcg_out_movi(TCGContext *s, TCGType type, old_code_ptr[1] = s->code_ptr - old_code_ptr; } -static inline void tcg_out_call(TCGContext *s, tcg_insn_unit *arg) +static inline void tcg_out_call(TCGContext *s, const tcg_insn_unit *arg) { uint8_t *old_code_ptr = s->code_ptr; tcg_out_op_t(s, INDEX_op_call);
tcg/tci/tcg-target.h +8 -1
@@ -195,6 +195,12 @@ static inline void flush_icache_range(uintptr_t start, uintptr_t stop) { } +#if defined(CONFIG_IOS_JIT ) +static inline void flush_dcache_range (uintptr_t start,uintptr_t stop) +{ +} +#endif +/* We could notice __i386__ or __s390x__ and reduce the barriers depending on the host. But if you want performance, you use the normal backend. We prefer consistency across hosts on this. */
@@ -203,7 +209,8 @@ static inline void flush_icache_range(uintptr_t start, uintptr_t stop)#define TCG_TARGET_HAS_MEMORY_BSWAP 1static inline void tb_target_set_jmp_target (uintptr_t tc_ptr, -uintptr_t jmp_addr,uintptr_t addr) +uintptr_t jmp_addr,uintptr_t addr, +uintptr_t wr_addr) {/* patch the branch destination */ qatomic_set ((int32_t *)jmp_addr, addr - (jmp_addr +4 ));
Signature · 1 line
2.24.3 (Apple Git-128)
Re: [PATCH 07/10] tcg: implement bulletproof JIT
Hi Joelle,
Quoted 10 lines · Joelle van Dyne
From: osy <[email protected]>
On iOS, we cannot allocate RWX pages without special entitlements. As a workaround, we can a RX region and then mirror map it to a separate RX region. Then we can write to one region and execute from the other one.
To better keep track of pointers to RW/RX memory, we mark any
tcg_insn_unitpointers asconstif they will never be written to. We also define a new macroTCG_CODE_PTR_RWthat returns a pointer to RW memory. Only the difference between the two regions is stored in the TCG context.
^ one change,
v another change. Consider splitting in 2 patches to ease review.
Quoted 36 lines
To ensure cache coherency, we flush the data cache in the RW mapping and then invalidate the instruction cache in the RX mapping (where applicable). Because data cache flush is OS defined on some architectures, we do not provide implementations for non iOS platforms (ARM/x86).
Signed-off-by Joelle van Dyne <[email protected]>--- accel/tcg/cpu-exec.c | 7 +++- accel/tcg/translate-all.c | 78 ++++++++++++++++++++++++++++++++++-- configure | 1 + docs/devel/ios.rst | 40 ++++++++++++++++++ include/exec/exec-all.h | 8 ++++ include/tcg/tcg.h | 18 +++++++-- tcg/aarch64/tcg-target.c.inc | 48 +++++++++++++--------- tcg/aarch64/tcg-target.h | 13 +++++- tcg/arm/tcg-target.c.inc | 33 ++++++++------- tcg/arm/tcg-target.h | 9 ++++- tcg/i386/tcg-target.c.inc | 28 ++++++------- tcg/i386/tcg-target.h | 24 ++++++++++- tcg/mips/tcg-target.c.inc | 64 +++++++++++++++++------------ tcg/mips/tcg-target.h | 8 +++- tcg/ppc/tcg-target.c.inc | 55 ++++++++++++++++--------- tcg/ppc/tcg-target.h | 8 +++- tcg/riscv/tcg-target.c.inc | 51 +++++++++++++---------- tcg/riscv/tcg-target.h | 9 ++++- tcg/s390/tcg-target.c.inc | 25 ++++++------ tcg/s390/tcg-target.h | 13 +++++- tcg/sparc/tcg-target.c.inc | 33 +++++++++------ tcg/sparc/tcg-target.h | 8 +++- tcg/tcg-ldst.c.inc | 2 +- tcg/tcg-pool.c.inc | 9 +++-- tcg/tcg.c | 60 +++++++++++++++++---------- tcg/tci/tcg-target.c.inc | 8 ++-- tcg/tci/tcg-target.h | 9 ++++- 27 files changed, 481 insertions(+), 188 deletions(-)
Quoted 1 line
create mode 100644
docs/devel/ios.rst
When posting big series, consider using scripts/git.orderfile.
Regards,
Phil.
Re: [PATCH 07/10] tcg: implement bulletproof JIT
In reply to Joelle van DyneQuoted 4 lines · Joelle van Dyne
From: osy <[email protected]>
On iOS, we cannot allocate RWX pages without special entitlements. As a workaround, we can a RX region and then mirror map it to a separate RX
Missing a verb here: "we can a RX region"
Quoted 6 lines
region. Then we can write to one region and execute from the other one.
To better keep track of pointers to RW/RX memory, we mark any
tcg_insn_unitpointers asconstif they will never be written to. We also define a new macroTCG_CODE_PTR_RWthat returns a pointer to RW memory. Only the difference between the two regions is stored in the TCG context.
Maybe it's easier to review if constification is split off as separate patch before other changes.
Quoted 85 lines
To ensure cache coherency, we flush the data cache in the RW mapping and then invalidate the instruction cache in the RX mapping (where applicable). Because data cache flush is OS defined on some architectures, we do not provide implementations for non iOS platforms (ARM/x86).
Signed-off-by Joelle van Dyne <[email protected]>---
accel/tcg/cpu-exec.c | 7 +++- accel/tcg/translate-all.c | 78 ++++++++++++++++++++++++++++++++++-- configure | 1 + docs/devel/ios.rst | 40 ++++++++++++++++++ include/exec/exec-all.h | 8 ++++ include/tcg/tcg.h | 18 +++++++-- tcg/aarch64/tcg-target.c.inc | 48 +++++++++++++--------- tcg/aarch64/tcg-target.h | 13 +++++- tcg/arm/tcg-target.c.inc | 33 ++++++++------- tcg/arm/tcg-target.h | 9 ++++- tcg/i386/tcg-target.c.inc | 28 ++++++------- tcg/i386/tcg-target.h | 24 ++++++++++- tcg/mips/tcg-target.c.inc | 64 +++++++++++++++++------------ tcg/mips/tcg-target.h | 8 +++- tcg/ppc/tcg-target.c.inc | 55 ++++++++++++++++--------- tcg/ppc/tcg-target.h | 8 +++- tcg/riscv/tcg-target.c.inc | 51 +++++++++++++---------- tcg/riscv/tcg-target.h | 9 ++++- tcg/s390/tcg-target.c.inc | 25 ++++++------ tcg/s390/tcg-target.h | 13 +++++- tcg/sparc/tcg-target.c.inc | 33 +++++++++------ tcg/sparc/tcg-target.h | 8 +++- tcg/tcg-ldst.c.inc | 2 +- tcg/tcg-pool.c.inc | 9 +++-- tcg/tcg.c | 60 +++++++++++++++++---------- tcg/tci/tcg-target.c.inc | 8 ++-- tcg/tci/tcg-target.h | 9 ++++- 27 files changed, 481 insertions(+), 188 deletions(-)create mode 100644
docs/devel/ios.rstaccel/tcg/cpu-exec.c +6
-1@@ -354,7 +354,12 @@ void tb_set_jmp_target(TranslationBlock *tb, int n, uintptr_t addr)if (TCG_TARGET_HAS_direct_jump) {uintptr_t offset = tb->jmp_target_arg[n];uintptr_t tc_ptr = (uintptr_t )tb->tc.ptr; -tb_target_set_jmp_target (tc_ptr, tc_ptr + offset, addr); +#if defined(CONFIG_IOS_JIT ) +uintptr_t wr_addr = tc_ptr + offset + tb->code_rw_mirror_diff; +#else +uintptr_t wr_addr = tc_ptr + offset; +#endif +tb_target_set_jmp_target (tc_ptr, tc_ptr + offset, addr, wr_addr); }else { tb->jmp_target_arg[n] = addr; }accel/tcg/translate-all.c +16
-0@@ -60,6 +60,22 @@#include "sysemu/cpu-timers.h" #include "sysemu/tcg.h" +#if defined(CONFIG_IOS_JIT ) +#include <mach/mach.h> +extern kern_return_t mach_vm_remap (vm_map_t target_task, +mach_vm_address_t *target_address, +mach_vm_size_t size, +mach_vm_offset_t mask, +int flags, +vm_map_t src_task, +mach_vm_address_t src_address, +boolean_t copy, +vm_prot_t *cur_protection, +vm_prot_t *max_protection, +vm_inherit_t inheritance + ); +#endif +/* #define DEBUG_TB_INVALIDATE */ /* #define DEBUG_TB_FLUSH */ /* make various TB consistency checks */ @@ -302,10 +318,13 @@ static target_long decode_sleb128(uint8_t **pp)static int encode_search (TranslationBlock *tb,uint8_t *block)
accel/tcg/translate-all.c static target_long decode_sleb128(uint8_t **pp) · line 327
Quoted 10 lines
accel/tcg/translate-all.c +5
-2{ -uint8_t *highwater = tcg_ctx->code_gen_highwater; -uint8_t *p = block; +uint8_t *highwater; +uint8_t *p;int i, j, n; + highwater = (uint8_t *)TCG_CODE_PTR_RW (tcg_ctx, + tcg_ctx->code_gen_highwater); + p = (uint8_t *)TCG_CODE_PTR_RW (tcg_ctx, block);
Why do you need explicit casts here? Can this be avoided by using appropriate type or within the macro (I haven't checked this at all just dislike casts as they can hide problems otherwise caught by the compiler).
Regards,
BALATON Zoltan
Quoted 1,853 lines
accel/tcg/translate-all.c +54
-1for (i =0 , n = tb->icount; i < n; ++i) {target_ulong prev;@@ -329,7 +348,7 @@ static int encode_search(TranslationBlock *tb, uint8_t *block) } } -return p - block; +return p - (uint8_t *)TCG_CODE_PTR_RW (tcg_ctx, block); }/* The cpu state corresponding to 'searched_pc' is restored. @@ -1067,7 +1086,11 @@ static inline void *alloc_code_gen_buffer(void)#else static inline void *alloc_code_gen_buffer (void ) { +#if defined(CONFIG_IOS_JIT ) +int prot =PROT_READ |PROT_EXEC ; +#else int prot =PROT_WRITE |PROT_READ |PROT_EXEC ; +#endif int flags =MAP_PRIVATE |MAP_ANONYMOUS ;size_t size = tcg_ctx->code_gen_buffer_size;void *buf;@@ -1118,6 +1141,39 @@ static inline void *alloc_code_gen_buffer(void) }#endif /* USE_STATIC_CODE_GEN_BUFFER, WIN32, POSIX */ +#if defined(CONFIG_IOS_JIT ) +static inline void *alloc_jit_rw_mirror (void *base,size_t size) +{ +kern_return_t ret; +mach_vm_address_t mirror; +vm_prot_t cur_prot, max_prot; + + mirror =0 ; + ret =mach_vm_remap (mach_task_self (), + &mirror, + size, +0 , +VM_FLAGS_ANYWHERE |VM_FLAGS_RANDOM_ADDR , +mach_task_self (), + (mach_vm_address_t )base, + false, + &cur_prot, + &max_prot, +VM_INHERIT_NONE + ); +if (ret !=KERN_SUCCESS ) { +return NULL ; + } + +if (mprotect ((void *)mirror, size,PROT_READ |PROT_WRITE ) !=0 ) { +munmap ((void *)mirror, size); +return NULL ; + } + +return (void *)mirror; +} +#endif /* CONFIG_IOS_JIT */ +static inline void code_gen_alloc (size_t tb_size) { tcg_ctx->code_gen_buffer_size =size_code_gen_buffer (tb_size);@@ -1126,6 +1182,19 @@ static inline void code_gen_alloc(size_t tb_size)fprintf (stderr,"Could not allocate dynamic translator buffer\n" );exit (1 ); } +#if defined(CONFIG_IOS_JIT ) +void *mirror; + +/* For iOS JIT we need a mirror mapping for code execution */ + mirror =alloc_jit_rw_mirror (tcg_ctx->code_gen_buffer, + tcg_ctx->code_gen_buffer_size + ); +if (mirror ==NULL ) { +fprintf (stderr,"Could not remap code buffer mirror\n" ); +exit (1 ); + } + tcg_ctx->code_rw_mirror_diff = mirror - tcg_ctx->code_gen_buffer; +#endif /* CONFIG_IOS_JIT */ }static bool tb_cmp (const void *ap,const void *bp)@@ -1721,6 +1790,9 @@ TranslationBlock *tb_gen_code(CPUState *cpu,cpu_loop_exit (cpu); } +#if defined(CONFIG_IOS_JIT ) + tb->code_rw_mirror_diff = tcg_ctx->code_rw_mirror_diff; +#endif gen_code_buf = tcg_ctx->code_gen_ptr; tb->tc.ptr = gen_code_buf; tb->pc = pc;configure +0
-0@@ -6220,6 +6220,7 @@ fiif test "$ios" = "yes" ; then
echo "CONFIG_IOS=y" >> $config_host_mak
+ echo "CONFIG_IOS_JIT=y" >> $config_host_mak
fiif test "$solaris" = "yes" ; then
docs/devel/ios.rst new file +40
-0@@ -0,0 +1,40 @@ +=========== +iOS Support +=========== + +To run qemu on the iOS platform, some modifications were required. Most of the +modifications are conditioned on the ``CONFIG_IOS`` and ``CONFIG_IOS_JIT`` +configuration variables. + +Build support +------------- + +For the code to compile, certain changes in the block driver and the slirp +driver had to be made. There is no ``system()`` call, so code requiring it had +to be disabled. + +``ucontext`` support is broken on iOS. The implementation from ``libucontext`` +is used instead. + +Because ``fork()`` is not allowed on iOS apps, the option to build qemu and the +utilities as shared libraries is added. Note that because qemu does not perform +resource cleanup in most cases (open files, allocated memory, etc), it is +advisable that the user implements a proxy layer for syscalls so resources can +be kept track by the app that uses qemu as a shared library. + +JIT support +----------- + +On iOS, allocating RWX pages require special entitlements not usually granted to +apps. However, it is possible to use `bulletproof JIT`_ with a development +certificate. This means that we need to allocate one chunk of memory with RX +permissions and then mirror map the same memory with RW permissions. We generate +code to the mirror mapping and execute the original mapping. + +With ``CONFIG_IOS_JIT`` defined, we store inside the TCG context the difference +between the two mappings. Then, we make sure that any writes to JIT memory is +done to the pointer + the difference (in order to get a pointer to the mirror +mapped space). Additionally, we make sure to flush the data cache before we +invalidate the instruction cache so the changes are seen in both mappings. + +.. _bulletproof JIT: https://www.blackhat.com/docs/us-16/materials/us-16-Krstic.pdfinclude/exec/exec-all.h +8
-0@@ -483,6 +483,14 @@ struct TranslationBlock {uintptr_t jmp_list_head;uintptr_t jmp_list_next[2 ];uintptr_t jmp_dest[2 ]; + +#if defined(CONFIG_IOS_JIT ) +/* +* Store difference to writable mirror +* We need this when patching the jump instructions +*/ +ptrdiff_t code_rw_mirror_diff; +#endif };extern bool parallel_cpus;include/tcg/tcg.h +14
-4@@ -261,7 +261,7 @@ struct TCGLabel { unsigned refs : 16;union {uintptr_t value; -tcg_insn_unit *value_ptr; +const tcg_insn_unit *value_ptr; } u; QSIMPLEQ_HEAD(, TCGRelocation) relocs;QSIMPLEQ_ENTRY (TCGLabel) next;@@ -593,7 +593,7 @@ struct TCGContext {int nb_ops;/* goto_tb support */ -tcg_insn_unit *code_buf; +const tcg_insn_unit *code_buf;uint16_t *tb_jmp_reset_offset;/* tb->jmp_reset_offset */ uintptr_t *tb_jmp_insn_offset;/* tb->jmp_target_arg if direct_jump */ uintptr_t *tb_jmp_target_addr;/* tb->jmp_target_arg if !direct_jump */ @@ -627,6 +627,9 @@ struct TCGContext {size_t code_gen_buffer_size;void *code_gen_ptr;void *data_gen_ptr; +#if defined(CONFIG_IOS_JIT ) +ptrdiff_t code_rw_mirror_diff; +#endif /* Threshold to flush the translated code buffer. */ void *code_gen_highwater;@@ -677,6 +680,13 @@ struct TCGContext {target_ulong gen_insn_data[TCG_MAX_INSNS ][TARGET_INSN_START_WORDS ]; }; +#if defined(CONFIG_IOS_JIT ) +# define TCG_CODE_PTR_RW (s, code_ptr) \ + (tcg_insn_unit *)((uintptr_t)(code_ptr) + (s)->code_rw_mirror_diff) +#else +# define TCG_CODE_PTR_RW (s, code_ptr) (code_ptr) +#endif +extern TCGContext tcg_init_ctx;extern __threadTCGContext *tcg_ctx;extern TCGv_env cpu_env;@@ -1099,7 +1109,7 @@ static inline TCGLabel *arg_label(TCGArg i)* correct result. */ -static inline ptrdiff_t tcg_ptr_byte_diff (void *a,void *b) +static inline ptrdiff_t tcg_ptr_byte_diff (const void *a,const void *b) {return a - b; }@@ -1113,7 +1123,7 @@ static inline ptrdiff_t tcg_ptr_byte_diff(void *a, void *b)* to the destination address. */ -static inline ptrdiff_t tcg_pcrel_diff (TCGContext *s,void *target) +static inline ptrdiff_t tcg_pcrel_diff (TCGContext *s,const void *target) {return tcg_ptr_byte_diff (target, s->code_ptr); }tcg/aarch64/tcg-target.c.inc +29
-19@@ -78,38 +78,44 @@ static const int tcg_target_call_oarg_regs[1] = { #define TCG_REG_GUEST_BASE TCG_REG_X28 #endif -static inline bool reloc_pc26(tcg_insn_unit *code_ptr, tcg_insn_unit *target) +static inline bool reloc_pc26(TCGContext *s, + tcg_insn_unit *code_ptr, + const tcg_insn_unit *target) { ptrdiff_t offset = target - code_ptr; if (offset == sextract64(offset, 0, 26)) { /* read instruction, mask away previous PC_REL26 parameter contents, set the proper offset, then write back the instruction. */ - *code_ptr = deposit32(*code_ptr, 0, 26, offset); + *TCG_CODE_PTR_RW(s, code_ptr) = + deposit32(*TCG_CODE_PTR_RW(s, code_ptr), 0, 26, offset); return true; } return false; } -static inline bool reloc_pc19(tcg_insn_unit *code_ptr, tcg_insn_unit *target) +static inline bool reloc_pc19(TCGContext *s, + tcg_insn_unit *code_ptr, + const tcg_insn_unit *target) { ptrdiff_t offset = target - code_ptr; if (offset == sextract64(offset, 0, 19)) { - *code_ptr = deposit32(*code_ptr, 5, 19, offset); + *TCG_CODE_PTR_RW(s, code_ptr) = + deposit32(*TCG_CODE_PTR_RW(s, code_ptr), 5, 19, offset); return true; } return false; } -static inline bool patch_reloc(tcg_insn_unit *code_ptr, int type, +static inline bool patch_reloc(TCGContext *s, tcg_insn_unit *code_ptr, int type, intptr_t value, intptr_t addend) { tcg_debug_assert(addend == 0); switch (type) { case R_AARCH64_JUMP26: case R_AARCH64_CALL26: - return reloc_pc26(code_ptr, (tcg_insn_unit *)value); + return reloc_pc26(s, code_ptr, (tcg_insn_unit *)value); case R_AARCH64_CONDBR19: - return reloc_pc19(code_ptr, (tcg_insn_unit *)value); + return reloc_pc19(s, code_ptr, (tcg_insn_unit *)value); default: g_assert_not_reached(); }@@ -1306,14 +1312,14 @@ static void tcg_out_cmp(TCGContext *s, TCGType ext, TCGReg a, } } -static inline void tcg_out_goto(TCGContext *s, tcg_insn_unit *target) +static inline void tcg_out_goto(TCGContext *s, const tcg_insn_unit *target) { ptrdiff_t offset = target - s->code_ptr; tcg_debug_assert(offset == sextract64(offset, 0, 26)); tcg_out_insn(s, 3206, B, offset); } -static inline void tcg_out_goto_long(TCGContext *s, tcg_insn_unit *target) +static inline void tcg_out_goto_long(TCGContext *s, const tcg_insn_unit *target) { ptrdiff_t offset = target - s->code_ptr; if (offset == sextract64(offset, 0, 26)) {@@ -1329,7 +1335,7 @@ static inline void tcg_out_callr(TCGContext *s, TCGReg reg) tcg_out_insn(s, 3207, BLR, reg); } -static inline void tcg_out_call(TCGContext *s, tcg_insn_unit *target) +static inline void tcg_out_call(TCGContext *s, const tcg_insn_unit *target) { ptrdiff_t offset = target - s->code_ptr; if (offset == sextract64(offset, 0, 26)) {@@ -1341,7 +1347,7 @@ static inline void tcg_out_call(TCGContext *s, tcg_insn_unit *target) } void tb_target_set_jmp_target(uintptr_t tc_ptr, uintptr_t jmp_addr, - uintptr_t addr) + uintptr_t addr, uintptr_t wr_addr) { tcg_insn_unit i1, i2; TCGType rt = TCG_TYPE_I64;@@ -1362,7 +1368,10 @@ void tb_target_set_jmp_target(uintptr_t tc_ptr, uintptr_t jmp_addr, i2 = I3401_ADDI | rt << 31 | (addr & 0xfff) << 10 | rd << 5 | rd; } pair = (uint64_t)i2 << 32 | i1; - qatomic_set((uint64_t *)jmp_addr, pair); + qatomic_set((uint64_t *)wr_addr, pair); +#if defined(CONFIG_IOS_JIT) + flush_dcache_range(wr_addr, wr_addr + 8); +#endif flush_icache_range(jmp_addr, jmp_addr + 8); }@@ -1568,7 +1577,7 @@ static void * const qemu_st_helpers[16] = { [MO_BEQ] = helper_be_stq_mmu, }; -static inline void tcg_out_adr(TCGContext *s, TCGReg rd, void *target) +static inline void tcg_out_adr(TCGContext *s, TCGReg rd, const void *target) { ptrdiff_t offset = tcg_pcrel_diff(s, target); tcg_debug_assert(offset == sextract64(offset, 0, 21));@@ -1581,7 +1590,7 @@ static bool tcg_out_qemu_ld_slow_path(TCGContext *s, TCGLabelQemuLdst *lb) MemOp opc = get_memop(oi); MemOp size = opc & MO_SIZE; - if (!reloc_pc19(lb->label_ptr[0], s->code_ptr)) { + if (!reloc_pc19(s, lb->label_ptr[0], s->code_ptr)) { return false; }@@ -1606,7 +1615,7 @@ static bool tcg_out_qemu_st_slow_path(TCGContext *s, TCGLabelQemuLdst *lb) MemOp opc = get_memop(oi); MemOp size = opc & MO_SIZE; - if (!reloc_pc19(lb->label_ptr[0], s->code_ptr)) { + if (!reloc_pc19(s, lb->label_ptr[0], s->code_ptr)) { return false; }@@ -1622,7 +1631,8 @@ static bool tcg_out_qemu_st_slow_path(TCGContext *s, TCGLabelQemuLdst *lb) static void add_qemu_ldst_label(TCGContext *s, bool is_ld, TCGMemOpIdx oi, TCGType ext, TCGReg data_reg, TCGReg addr_reg, - tcg_insn_unit *raddr, tcg_insn_unit *label_ptr) + const tcg_insn_unit *raddr, + tcg_insn_unit *label_ptr) { TCGLabelQemuLdst *label = new_ldst_label(s);@@ -1849,7 +1859,7 @@ static void tcg_out_qemu_st(TCGContext *s, TCGReg data_reg, TCGReg addr_reg, #endif /* CONFIG_SOFTMMU */ } -static tcg_insn_unit *tb_ret_addr; +static const tcg_insn_unit *tb_ret_addr; static void tcg_out_op(TCGContext *s, TCGOpcode opc, const TCGArg args[TCG_MAX_OP_ARGS],@@ -2916,11 +2926,11 @@ static void tcg_target_qemu_prologue(TCGContext *s) tcg_out_insn(s, 3207, RET, TCG_REG_LR); } -static void tcg_out_nop_fill(tcg_insn_unit *p, int count) +static void tcg_out_nop_fill(TCGContext *s, tcg_insn_unit *p, int count) { int i; for (i = 0; i < count; ++i) { - p[i] = NOP; + (TCG_CODE_PTR_RW(s, p))[i] = NOP; } }tcg/aarch64/tcg-target.h +12
-1@@ -150,6 +150,7 @@ typedef enum {#if defined(__APPLE__)void sys_icache_invalidate (void *start,size_t len); +void sys_dcache_flush (void *start,size_t len);#endif static inline void flush_icache_range (uintptr_t start,uintptr_t stop)@@ -163,7 +164,17 @@ static inline void flush_icache_range(uintptr_t start, uintptr_t stop)#endif } -void tb_target_set_jmp_target (uintptr_t ,uintptr_t ,uintptr_t ); +void tb_target_set_jmp_target (uintptr_t ,uintptr_t ,uintptr_t ,uintptr_t ); +#if defined(CONFIG_IOS_JIT ) +static inline void flush_dcache_range (uintptr_t start,uintptr_t stop) +{ +#if defined(__APPLE__) +sys_dcache_flush ((char *)start, stop - start); +#else +#error "Missing function to flush data cache" +#endif +} +#endif #ifdef CONFIG_SOFTMMU #define TCG_TARGET_NEED_LDST_LABELS tcg/arm/tcg-target.c.inc +19
-14@@ -187,17 +187,22 @@ static const uint8_t tcg_cond_to_arm_cond[] = { [TCG_COND_GTU] = COND_HI, }; -static inline bool reloc_pc24(tcg_insn_unit *code_ptr, tcg_insn_unit *target) +static inline bool reloc_pc24(TCGContext *s, + tcg_insn_unit *code_ptr, + const tcg_insn_unit *target) { ptrdiff_t offset = (tcg_ptr_byte_diff(target, code_ptr) - 8) >> 2; if (offset == sextract32(offset, 0, 24)) { - *code_ptr = (*code_ptr & ~0xffffff) | (offset & 0xffffff); + *TCG_CODE_PTR_RW(s, code_ptr) = + (*TCG_CODE_PTR_RW(s, code_ptr) & ~0xffffff) | (offset & 0xffffff); return true; } return false; } -static inline bool reloc_pc13(tcg_insn_unit *code_ptr, tcg_insn_unit *target) +static inline bool reloc_pc13(TCGContext *s, + tcg_insn_unit *code_ptr, + const tcg_insn_unit *target) { ptrdiff_t offset = tcg_ptr_byte_diff(target, code_ptr) - 8;@@ -209,21 +214,21 @@ static inline bool reloc_pc13(tcg_insn_unit *code_ptr, tcg_insn_unit *target) } insn = deposit32(insn, 23, 1, u); insn = deposit32(insn, 0, 12, offset); - *code_ptr = insn; + *TCG_CODE_PTR_RW(s, code_ptr) = insn; return true; } return false; } -static bool patch_reloc(tcg_insn_unit *code_ptr, int type, +static bool patch_reloc(TCGContext *s, tcg_insn_unit *code_ptr, int type, intptr_t value, intptr_t addend) { tcg_debug_assert(addend == 0); if (type == R_ARM_PC24) { - return reloc_pc24(code_ptr, (tcg_insn_unit *)value); + return reloc_pc24(s, code_ptr, (tcg_insn_unit *)value); } else if (type == R_ARM_PC13) { - return reloc_pc13(code_ptr, (tcg_insn_unit *)value); + return reloc_pc13(s, code_ptr, (tcg_insn_unit *)value); } else { g_assert_not_reached(); }@@ -1019,7 +1024,7 @@ static inline void tcg_out_st8(TCGContext *s, int cond, * with the code buffer limited to 16MB we wouldn't need the long case. * But we also use it for the tail-call to the qemu_ld/st helpers, which does. */ -static void tcg_out_goto(TCGContext *s, int cond, tcg_insn_unit *addr) +static void tcg_out_goto(TCGContext *s, int cond, const tcg_insn_unit *addr) { intptr_t addri = (intptr_t)addr; ptrdiff_t disp = tcg_pcrel_diff(s, addr);@@ -1033,7 +1038,7 @@ static void tcg_out_goto(TCGContext *s, int cond, tcg_insn_unit *addr) /* The call case is mostly used for helpers - so it's not unreasonable * for them to be beyond branch range */ -static void tcg_out_call(TCGContext *s, tcg_insn_unit *addr) +static void tcg_out_call(TCGContext *s, const tcg_insn_unit *addr) { intptr_t addri = (intptr_t)addr; ptrdiff_t disp = tcg_pcrel_diff(s, addr);@@ -1326,7 +1331,7 @@ static TCGReg tcg_out_tlb_read(TCGContext *s, TCGReg addrlo, TCGReg addrhi, helper code. */ static void add_qemu_ldst_label(TCGContext *s, bool is_ld, TCGMemOpIdx oi, TCGReg datalo, TCGReg datahi, TCGReg addrlo, - TCGReg addrhi, tcg_insn_unit *raddr, + TCGReg addrhi, const tcg_insn_unit *raddr, tcg_insn_unit *label_ptr) { TCGLabelQemuLdst *label = new_ldst_label(s);@@ -1348,7 +1353,7 @@ static bool tcg_out_qemu_ld_slow_path(TCGContext *s, TCGLabelQemuLdst *lb) MemOp opc = get_memop(oi); void *func; - if (!reloc_pc24(lb->label_ptr[0], s->code_ptr)) { + if (!reloc_pc24(s, lb->label_ptr[0], s->code_ptr)) { return false; }@@ -1411,7 +1416,7 @@ static bool tcg_out_qemu_st_slow_path(TCGContext *s, TCGLabelQemuLdst *lb) TCGMemOpIdx oi = lb->oi; MemOp opc = get_memop(oi); - if (!reloc_pc24(lb->label_ptr[0], s->code_ptr)) { + if (!reloc_pc24(s, lb->label_ptr[0], s->code_ptr)) { return false; }@@ -2255,11 +2260,11 @@ static inline void tcg_out_movi(TCGContext *s, TCGType type, tcg_out_movi32(s, COND_AL, ret, arg); } -static void tcg_out_nop_fill(tcg_insn_unit *p, int count) +static void tcg_out_nop_fill(TCGContext *s, tcg_insn_unit *p, int count) { int i; for (i = 0; i < count; ++i) { - p[i] = INSN_NOP; + (TCG_CODE_PTR_RW(s, p))[i] = INSN_NOP; } }tcg/arm/tcg-target.h +8
-1@@ -139,8 +139,15 @@ static inline void flush_icache_range(uintptr_t start, uintptr_t stop)__builtin___clear_cache ((char *) start, (char *) stop); } +#if defined(CONFIG_IOS_JIT ) +static inline void flush_dcache_range (uintptr_t start,uintptr_t stop) +{ +#error "Unimplemented dcache flush function" +} +#endif +/* not defined -- call should be eliminated at compile time */ -void tb_target_set_jmp_target (uintptr_t ,uintptr_t ,uintptr_t ); +void tb_target_set_jmp_target (uintptr_t ,uintptr_t ,uintptr_t ,uintptr_t );#ifdef CONFIG_SOFTMMU #define TCG_TARGET_NEED_LDST_LABELS tcg/i386/tcg-target.c.inc +14
-14@@ -165,9 +165,9 @@ static bool have_lzcnt; # define have_lzcnt 0 #endif -static tcg_insn_unit *tb_ret_addr; +static const tcg_insn_unit *tb_ret_addr; -static bool patch_reloc(tcg_insn_unit *code_ptr, int type, +static bool patch_reloc(TCGContext *s, tcg_insn_unit *code_ptr, int type, intptr_t value, intptr_t addend) { value += addend;@@ -179,14 +179,14 @@ static bool patch_reloc(tcg_insn_unit *code_ptr, int type, } /* FALLTHRU */ case R_386_32: - tcg_patch32(code_ptr, value); + tcg_patch32(s, code_ptr, value); break; case R_386_PC8: value -= (uintptr_t)code_ptr; if (value != (int8_t)value) { return false; } - tcg_patch8(code_ptr, value); + tcg_patch8(s, code_ptr, value); break; default: tcg_abort();@@ -1591,7 +1591,7 @@ static void tcg_out_clz(TCGContext *s, int rexw, TCGReg dest, TCGReg arg1, } } -static void tcg_out_branch(TCGContext *s, int call, tcg_insn_unit *dest) +static void tcg_out_branch(TCGContext *s, int call, const tcg_insn_unit *dest) { intptr_t disp = tcg_pcrel_diff(s, dest) - 5;@@ -1610,12 +1610,12 @@ static void tcg_out_branch(TCGContext *s, int call, tcg_insn_unit *dest) } } -static inline void tcg_out_call(TCGContext *s, tcg_insn_unit *dest) +static inline void tcg_out_call(TCGContext *s, const tcg_insn_unit *dest) { tcg_out_branch(s, 1, dest); } -static void tcg_out_jmp(TCGContext *s, tcg_insn_unit *dest) +static void tcg_out_jmp(TCGContext *s, const tcg_insn_unit *dest) { tcg_out_branch(s, 0, dest); }@@ -1774,7 +1774,7 @@ static void add_qemu_ldst_label(TCGContext *s, bool is_ld, bool is_64, TCGMemOpIdx oi, TCGReg datalo, TCGReg datahi, TCGReg addrlo, TCGReg addrhi, - tcg_insn_unit *raddr, + const tcg_insn_unit *raddr, tcg_insn_unit **label_ptr) { TCGLabelQemuLdst *label = new_ldst_label(s);@@ -1805,9 +1805,9 @@ static bool tcg_out_qemu_ld_slow_path(TCGContext *s, TCGLabelQemuLdst *l) int rexw = (l->type == TCG_TYPE_I64 ? P_REXW : 0); /* resolve label address */ - tcg_patch32(label_ptr[0], s->code_ptr - label_ptr[0] - 4); + tcg_patch32(s, label_ptr[0], s->code_ptr - label_ptr[0] - 4); if (TARGET_LONG_BITS > TCG_TARGET_REG_BITS) { - tcg_patch32(label_ptr[1], s->code_ptr - label_ptr[1] - 4); + tcg_patch32(s, label_ptr[1], s->code_ptr - label_ptr[1] - 4); } if (TCG_TARGET_REG_BITS == 32) {@@ -1890,9 +1890,9 @@ static bool tcg_out_qemu_st_slow_path(TCGContext *s, TCGLabelQemuLdst *l) TCGReg retaddr; /* resolve label address */ - tcg_patch32(label_ptr[0], s->code_ptr - label_ptr[0] - 4); + tcg_patch32(s, label_ptr[0], s->code_ptr - label_ptr[0] - 4); if (TARGET_LONG_BITS > TCG_TARGET_REG_BITS) { - tcg_patch32(label_ptr[1], s->code_ptr - label_ptr[1] - 4); + tcg_patch32(s, label_ptr[1], s->code_ptr - label_ptr[1] - 4); } if (TCG_TARGET_REG_BITS == 32) {@@ -3842,9 +3842,9 @@ static void tcg_target_qemu_prologue(TCGContext *s) tcg_out_opc(s, OPC_RET, 0, 0, 0); } -static void tcg_out_nop_fill(tcg_insn_unit *p, int count) +static void tcg_out_nop_fill(TCGContext *s, tcg_insn_unit *p, int count) { - memset(p, 0x90, count); + memset(TCG_CODE_PTR_RW(s, p), 0x90, count); } static void tcg_target_init(TCGContext *s)tcg/i386/tcg-target.h +22
-2@@ -206,16 +206,36 @@ extern bool have_avx2;#define TCG_TARGET_extract_i64_valid (ofs, len) \ (((ofs) == 8 && (len) == 8) || ((ofs) + (len)) == 32) +#ifdef __APPLE__ +void sys_dcache_flush (void *start,size_t len); +#endif +static inline void flush_icache_range (uintptr_t start,uintptr_t stop) { } +#if defined(CONFIG_IOS_JIT ) +static inline void flush_dcache_range (uintptr_t start,uintptr_t stop) +{ +#if defined(__APPLE__) +sys_dcache_flush ((char *)start, stop - start); +#else +#error "Missing function to flush data cache" +#endif +} +#endif +static inline void tb_target_set_jmp_target (uintptr_t tc_ptr, -uintptr_t jmp_addr,uintptr_t addr) +uintptr_t jmp_addr,uintptr_t addr, +uintptr_t wr_addr) {/* patch the branch destination */ -qatomic_set ((int32_t *)jmp_addr, addr - (jmp_addr +4 )); +qatomic_set ((int32_t *)wr_addr, addr - (jmp_addr +4 ));/* no need to flush icache explicitly */ +#if defined(CONFIG_IOS_JIT ) +/* we do need to flush mirror dcache */ +flush_dcache_range (wr_addr, wr_addr +4 ); +#endif }/* This defines the natural memory order supported by this tcg/mips/tcg-target.c.inc +38
-26@@ -139,12 +139,13 @@ static const TCGReg tcg_target_call_oarg_regs[2] = { TCG_REG_V1 }; -static tcg_insn_unit *tb_ret_addr; -static tcg_insn_unit *bswap32_addr; -static tcg_insn_unit *bswap32u_addr; -static tcg_insn_unit *bswap64_addr; +static const tcg_insn_unit *tb_ret_addr; +static const tcg_insn_unit *bswap32_addr; +static const tcg_insn_unit *bswap32u_addr; +static const tcg_insn_unit *bswap64_addr; -static inline uint32_t reloc_pc16_val(tcg_insn_unit *pc, tcg_insn_unit *target) +static inline uint32_t reloc_pc16_val(const tcg_insn_unit *pc, + const tcg_insn_unit *target) { /* Let the compiler perform the right-shift as part of the arithmetic. */ ptrdiff_t disp = target - (pc + 1);@@ -152,28 +153,35 @@ static inline uint32_t reloc_pc16_val(tcg_insn_unit *pc, tcg_insn_unit *target) return disp & 0xffff; } -static inline void reloc_pc16(tcg_insn_unit *pc, tcg_insn_unit *target) +static inline void reloc_pc16(TCGContext *s, + tcg_insn_unit *pc, + const tcg_insn_unit *target) { - *pc = deposit32(*pc, 0, 16, reloc_pc16_val(pc, target)); + *TCG_CODE_PTR_RW(s, pc) = + deposit32(*TCG_CODE_PTR_RW(s, pc), 0, 16, reloc_pc16_val(pc, target)); } -static inline uint32_t reloc_26_val(tcg_insn_unit *pc, tcg_insn_unit *target) +static inline uint32_t reloc_26_val(const tcg_insn_unit *pc, + const tcg_insn_unit *target) { tcg_debug_assert((((uintptr_t)pc ^ (uintptr_t)target) & 0xf0000000) == 0); return ((uintptr_t)target >> 2) & 0x3ffffff; } -static inline void reloc_26(tcg_insn_unit *pc, tcg_insn_unit *target) +static inline void reloc_26(TCGContext *s, + tcg_insn_unit *pc, + const tcg_insn_unit *target) { - *pc = deposit32(*pc, 0, 26, reloc_26_val(pc, target)); + *TCG_CODE_PTR_RW(s, pc) = + deposit32(*TCG_CODE_PTR_RW(s, pc), 0, 26, reloc_26_val(pc, target)); } -static bool patch_reloc(tcg_insn_unit *code_ptr, int type, +static bool patch_reloc(TCGContext *s, tcg_insn_unit *code_ptr, int type, intptr_t value, intptr_t addend) { tcg_debug_assert(type == R_MIPS_PC16); tcg_debug_assert(addend == 0); - reloc_pc16(code_ptr, (tcg_insn_unit *)value); + reloc_pc16(s, code_ptr, (tcg_insn_unit *)value); return true; }@@ -516,7 +524,7 @@ static void tcg_out_opc_sa64(TCGContext *s, MIPSInsn opc1, MIPSInsn opc2, * Type jump. * Returns true if the branch was in range and the insn was emitted. */ -static bool tcg_out_opc_jmp(TCGContext *s, MIPSInsn opc, void *target) +static bool tcg_out_opc_jmp(TCGContext *s, MIPSInsn opc, const void *target) { uintptr_t dest = (uintptr_t)target; uintptr_t from = (uintptr_t)s->code_ptr + 4;@@ -631,7 +639,7 @@ static inline void tcg_out_bswap16s(TCGContext *s, TCGReg ret, TCGReg arg) } } -static void tcg_out_bswap_subr(TCGContext *s, tcg_insn_unit *sub) +static void tcg_out_bswap_subr(TCGContext *s, const tcg_insn_unit *sub) { bool ok = tcg_out_opc_jmp(s, OPC_JAL, sub); tcg_debug_assert(ok);@@ -925,7 +933,7 @@ static void tcg_out_brcond(TCGContext *s, TCGCond cond, TCGReg arg1, tcg_out_opc_br(s, b_opc, arg1, arg2); if (l->has_value) { - reloc_pc16(s->code_ptr - 1, l->u.value_ptr); + reloc_pc16(s, s->code_ptr - 1, l->u.value_ptr); } else { tcg_out_reloc(s, s->code_ptr - 1, R_MIPS_PC16, l, 0); }@@ -1079,7 +1087,7 @@ static void tcg_out_movcond(TCGContext *s, TCGCond cond, TCGReg ret, } } -static void tcg_out_call_int(TCGContext *s, tcg_insn_unit *arg, bool tail) +static void tcg_out_call_int(TCGContext *s, const tcg_insn_unit *arg, bool tail) { /* Note that the ABI requires the called function's address to be loaded into T9, even if a direct branch is in range. */@@ -1097,7 +1105,7 @@ static void tcg_out_call_int(TCGContext *s, tcg_insn_unit *arg, bool tail) } } -static void tcg_out_call(TCGContext *s, tcg_insn_unit *arg) +static void tcg_out_call(TCGContext *s, const tcg_insn_unit *arg) { tcg_out_call_int(s, arg, false); tcg_out_nop(s);@@ -1289,7 +1297,8 @@ static void add_qemu_ldst_label(TCGContext *s, int is_ld, TCGMemOpIdx oi, TCGType ext, TCGReg datalo, TCGReg datahi, TCGReg addrlo, TCGReg addrhi, - void *raddr, tcg_insn_unit *label_ptr[2]) + const tcg_insn_unit *raddr, + tcg_insn_unit *label_ptr[2]) { TCGLabelQemuLdst *label = new_ldst_label(s);@@ -1315,9 +1324,9 @@ static bool tcg_out_qemu_ld_slow_path(TCGContext *s, TCGLabelQemuLdst *l) int i; /* resolve label address */ - reloc_pc16(l->label_ptr[0], s->code_ptr); + reloc_pc16(s, l->label_ptr[0], s->code_ptr); if (TCG_TARGET_REG_BITS < TARGET_LONG_BITS) { - reloc_pc16(l->label_ptr[1], s->code_ptr); + reloc_pc16(s, l->label_ptr[1], s->code_ptr); } i = 1;@@ -1345,7 +1354,7 @@ static bool tcg_out_qemu_ld_slow_path(TCGContext *s, TCGLabelQemuLdst *l) } tcg_out_opc_br(s, OPC_BEQ, TCG_REG_ZERO, TCG_REG_ZERO); - reloc_pc16(s->code_ptr - 1, l->raddr); + reloc_pc16(s, s->code_ptr - 1, l->raddr); /* delay slot */ if (TCG_TARGET_REG_BITS == 64 && l->type == TCG_TYPE_I32) {@@ -1365,9 +1374,9 @@ static bool tcg_out_qemu_st_slow_path(TCGContext *s, TCGLabelQemuLdst *l) int i; /* resolve label address */ - reloc_pc16(l->label_ptr[0], s->code_ptr); + reloc_pc16(s, l->label_ptr[0], s->code_ptr); if (TCG_TARGET_REG_BITS < TARGET_LONG_BITS) { - reloc_pc16(l->label_ptr[1], s->code_ptr); + reloc_pc16(s, l->label_ptr[1], s->code_ptr); } i = 1;@@ -2430,7 +2439,7 @@ static void tcg_target_detect_isa(void) sigaction(SIGILL, &sa_old, NULL); } -static tcg_insn_unit *align_code_ptr(TCGContext *s) +static const tcg_insn_unit *align_code_ptr(TCGContext *s) { uintptr_t p = (uintptr_t)s->code_ptr; if (p & 15) {@@ -2657,9 +2666,12 @@ static void tcg_target_init(TCGContext *s) } void tb_target_set_jmp_target(uintptr_t tc_ptr, uintptr_t jmp_addr, - uintptr_t addr) + uintptr_t addr, uintptr_t wr_addr) { - qatomic_set((uint32_t *)jmp_addr, deposit32(OPC_J, 0, 26, addr >> 2)); + qatomic_set((uint32_t *)wr_addr, deposit32(OPC_J, 0, 26, addr >> 2)); +#if defined(CONFIG_IOS_JIT) + flush_dcache_range(wr_addr, wr_addr + 4); +#endif flush_icache_range(jmp_addr, jmp_addr + 4); }tcg/mips/tcg-target.h +7
-1@@ -212,7 +212,13 @@ static inline void flush_icache_range(uintptr_t start, uintptr_t stop)cacheflush ((void *)start, stop-start,ICACHE ); } -void tb_target_set_jmp_target (uintptr_t ,uintptr_t ,uintptr_t ); +void tb_target_set_jmp_target (uintptr_t ,uintptr_t ,uintptr_t ,uintptr_t ); +#if defined(CONFIG_IOS_JIT ) +static inline void flush_dcache_range (uintptr_t start,uintptr_t stop) +{ +#error "Unimplemented dcache flush function" +} +#endif #ifdef CONFIG_SOFTMMU #define TCG_TARGET_NEED_LDST_LABELS tcg/ppc/tcg-target.c.inc +35
-20@@ -62,7 +62,7 @@ #define TCG_CT_CONST_MONE 0x2000 #define TCG_CT_CONST_WSZ 0x4000 -static tcg_insn_unit *tb_ret_addr; +static const tcg_insn_unit *tb_ret_addr; TCGPowerISA have_isa; static bool have_isel;@@ -184,35 +184,43 @@ static inline bool in_range_b(tcg_target_long target) return target == sextract64(target, 0, 26); } -static uint32_t reloc_pc24_val(tcg_insn_unit *pc, tcg_insn_unit *target) +static uint32_t reloc_pc24_val(const tcg_insn_unit *pc, + const tcg_insn_unit *target) { ptrdiff_t disp = tcg_ptr_byte_diff(target, pc); tcg_debug_assert(in_range_b(disp)); return disp & 0x3fffffc; } -static bool reloc_pc24(tcg_insn_unit *pc, tcg_insn_unit *target) +static bool reloc_pc24(TCGContext *s, + tcg_insn_unit *pc, + const tcg_insn_unit *target) { ptrdiff_t disp = tcg_ptr_byte_diff(target, pc); if (in_range_b(disp)) { - *pc = (*pc & ~0x3fffffc) | (disp & 0x3fffffc); + *TCG_CODE_PTR_RW(s, pc) = + (*TCG_CODE_PTR_RW(s, pc) & ~0x3fffffc) | (disp & 0x3fffffc); return true; } return false; } -static uint16_t reloc_pc14_val(tcg_insn_unit *pc, tcg_insn_unit *target) +static uint16_t reloc_pc14_val(const tcg_insn_unit *pc, + const tcg_insn_unit *target) { ptrdiff_t disp = tcg_ptr_byte_diff(target, pc); tcg_debug_assert(disp == (int16_t) disp); return disp & 0xfffc; } -static bool reloc_pc14(tcg_insn_unit *pc, tcg_insn_unit *target) +static bool reloc_pc14(TCGContext *s, + tcg_insn_unit *pc, + const tcg_insn_unit *target) { ptrdiff_t disp = tcg_ptr_byte_diff(target, pc); if (disp == (int16_t) disp) { - *pc = (*pc & ~0xfffc) | (disp & 0xfffc); + *TCG_CODE_PTR_RW(s, pc) = + (*TCG_CODE_PTR_RW(s, pc) & ~0xfffc) | (disp & 0xfffc); return true; } return false;@@ -670,7 +678,7 @@ static const uint32_t tcg_to_isel[] = { [TCG_COND_GTU] = ISEL | BC_(7, CR_GT), }; -static bool patch_reloc(tcg_insn_unit *code_ptr, int type, +static bool patch_reloc(TCGContext *s, tcg_insn_unit *code_ptr, int type, intptr_t value, intptr_t addend) { tcg_insn_unit *target;@@ -682,9 +690,9 @@ static bool patch_reloc(tcg_insn_unit *code_ptr, int type, switch (type) { case R_PPC_REL14: - return reloc_pc14(code_ptr, target); + return reloc_pc14(s, code_ptr, target); case R_PPC_REL24: - return reloc_pc24(code_ptr, target); + return reloc_pc24(s, code_ptr, target); case R_PPC_ADDR16: /* * We are (slightly) abusing this relocation type. In particular,@@ -1106,7 +1114,7 @@ static void tcg_out_xori32(TCGContext *s, TCGReg dst, TCGReg src, uint32_t c) tcg_out_zori32(s, dst, src, c, XORI, XORIS); } -static void tcg_out_b(TCGContext *s, int mask, tcg_insn_unit *target) +static void tcg_out_b(TCGContext *s, int mask, const tcg_insn_unit *target) { ptrdiff_t disp = tcg_pcrel_diff(s, target); if (in_range_b(disp)) {@@ -1723,7 +1731,7 @@ static void tcg_out_mb(TCGContext *s, TCGArg a0) } void tb_target_set_jmp_target(uintptr_t tc_ptr, uintptr_t jmp_addr, - uintptr_t addr) + uintptr_t addr, uintptr_t wr_addr) { if (TCG_TARGET_REG_BITS == 64) { tcg_insn_unit i1, i2;@@ -1752,17 +1760,23 @@ void tb_target_set_jmp_target(uintptr_t tc_ptr, uintptr_t jmp_addr, /* As per the enclosing if, this is ppc64. Avoid the _Static_assert within qatomic_set that would fail to build a ppc32 host. */ - qatomic_set__nocheck((uint64_t *)jmp_addr, pair); + qatomic_set__nocheck((uint64_t *)wr_addr, pair); +#if defined(CONFIG_IOS_JIT) + flush_dcache_range(wr_addr, wr_addr + 8); +#endif flush_icache_range(jmp_addr, jmp_addr + 8); } else { intptr_t diff = addr - jmp_addr; tcg_debug_assert(in_range_b(diff)); - qatomic_set((uint32_t *)jmp_addr, B | (diff & 0x3fffffc)); + qatomic_set((uint32_t *)wr_addr, B | (diff & 0x3fffffc)); +#if defined(CONFIG_IOS_JIT) + flush_dcache_range(wr_addr, wr_addr + 8); +#endif flush_icache_range(jmp_addr, jmp_addr + 4); } } -static void tcg_out_call(TCGContext *s, tcg_insn_unit *target) +static void tcg_out_call(TCGContext *s, const tcg_insn_unit *target) { #ifdef _CALL_AIX /* Look through the descriptor. If the branch is in range, and we@@ -1987,7 +2001,8 @@ static TCGReg tcg_out_tlb_read(TCGContext *s, MemOp opc, static void add_qemu_ldst_label(TCGContext *s, bool is_ld, TCGMemOpIdx oi, TCGReg datalo_reg, TCGReg datahi_reg, TCGReg addrlo_reg, TCGReg addrhi_reg, - tcg_insn_unit *raddr, tcg_insn_unit *lptr) + const tcg_insn_unit *raddr, + tcg_insn_unit *lptr) { TCGLabelQemuLdst *label = new_ldst_label(s);@@ -2007,7 +2022,7 @@ static bool tcg_out_qemu_ld_slow_path(TCGContext *s, TCGLabelQemuLdst *lb) MemOp opc = get_memop(oi); TCGReg hi, lo, arg = TCG_REG_R3; - if (!reloc_pc14(lb->label_ptr[0], s->code_ptr)) { + if (!reloc_pc14(s, lb->label_ptr[0], s->code_ptr)) { return false; }@@ -2055,7 +2070,7 @@ static bool tcg_out_qemu_st_slow_path(TCGContext *s, TCGLabelQemuLdst *lb) MemOp s_bits = opc & MO_SIZE; TCGReg hi, lo, arg = TCG_REG_R3; - if (!reloc_pc14(lb->label_ptr[0], s->code_ptr)) { + if (!reloc_pc14(s, lb->label_ptr[0], s->code_ptr)) { return false; }@@ -2252,11 +2267,11 @@ static void tcg_out_qemu_st(TCGContext *s, const TCGArg *args, bool is_64) #endif } -static void tcg_out_nop_fill(tcg_insn_unit *p, int count) +static void tcg_out_nop_fill(TCGContext *s, tcg_insn_unit *p, int count) { int i; for (i = 0; i < count; ++i) { - p[i] = NOP; + (TCG_CODE_PTR_RW(s, p))[i] = NOP; } }tcg/ppc/tcg-target.h +7
-1@@ -176,7 +176,13 @@ extern bool have_vsx;#define TCG_TARGET_HAS_cmpsel_vec 0void flush_icache_range (uintptr_t start,uintptr_t stop); -void tb_target_set_jmp_target (uintptr_t ,uintptr_t ,uintptr_t ); +void tb_target_set_jmp_target (uintptr_t ,uintptr_t ,uintptr_t ,uintptr_t ); +#if defined(CONFIG_IOS_JIT ) +static inline void flush_dcache_range (uintptr_t start,uintptr_t stop) +{ +#error "Unimplemented dcache flush function" +} +#endif #define TCG_TARGET_DEFAULT_MO (0)#define TCG_TARGET_HAS_MEMORY_BSWAP 1tcg/riscv/tcg-target.c.inc +29
-22@@ -413,11 +413,11 @@ static void tcg_out_opc_jump(TCGContext *s, RISCVInsn opc, tcg_out32(s, encode_uj(opc, rd, imm)); } -static void tcg_out_nop_fill(tcg_insn_unit *p, int count) +static void tcg_out_nop_fill(TCGContext *s, tcg_insn_unit *p, int count) { int i; for (i = 0; i < count; ++i) { - p[i] = encode_i(OPC_ADDI, TCG_REG_ZERO, TCG_REG_ZERO, 0); + (TCG_CODE_PTR_RW(s, p))[i] = encode_i(OPC_ADDI, TCG_REG_ZERO, TCG_REG_ZERO, 0); } }@@ -425,46 +425,52 @@ static void tcg_out_nop_fill(tcg_insn_unit *p, int count) * Relocations */ -static bool reloc_sbimm12(tcg_insn_unit *code_ptr, tcg_insn_unit *target) +static bool reloc_sbimm12(TCGContext *s, + tcg_insn_unit *code_ptr, + const tcg_insn_unit *target) { intptr_t offset = (intptr_t)target - (intptr_t)code_ptr; if (offset == sextreg(offset, 1, 12) << 1) { - code_ptr[0] |= encode_sbimm12(offset); + (TCG_CODE_PTR_RW(s, code_ptr))[0] |= encode_sbimm12(offset); return true; } return false; } -static bool reloc_jimm20(tcg_insn_unit *code_ptr, tcg_insn_unit *target) +static bool reloc_jimm20(TCGContext *s, + tcg_insn_unit *code_ptr, + const tcg_insn_unit *target) { intptr_t offset = (intptr_t)target - (intptr_t)code_ptr; if (offset == sextreg(offset, 1, 20) << 1) { - code_ptr[0] |= encode_ujimm20(offset); + (TCG_CODE_PTR_RW(s, code_ptr))[0] |= encode_ujimm20(offset); return true; } return false; } -static bool reloc_call(tcg_insn_unit *code_ptr, tcg_insn_unit *target) +static bool reloc_call(TCGContext *s, + tcg_insn_unit *code_ptr, + const tcg_insn_unit *target) { intptr_t offset = (intptr_t)target - (intptr_t)code_ptr; int32_t lo = sextreg(offset, 0, 12); int32_t hi = offset - lo; if (offset == hi + lo) { - code_ptr[0] |= encode_uimm20(hi); - code_ptr[1] |= encode_imm12(lo); + (TCG_CODE_PTR_RW(s, code_ptr))[0] |= encode_uimm20(hi); + (TCG_CODE_PTR_RW(s, code_ptr))[1] |= encode_imm12(lo); return true; } return false; } -static bool patch_reloc(tcg_insn_unit *code_ptr, int type, +static bool patch_reloc(TCGContext *s, tcg_insn_unit *code_ptr, int type, intptr_t value, intptr_t addend) { uint32_t insn = *code_ptr;@@ -478,7 +484,7 @@ static bool patch_reloc(tcg_insn_unit *code_ptr, int type, diff = value - (uintptr_t)code_ptr; short_jmp = diff == sextreg(diff, 0, 12); if (short_jmp) { - return reloc_sbimm12(code_ptr, (tcg_insn_unit *)value); + return reloc_sbimm12(s, code_ptr, (tcg_insn_unit *)value); } else { /* Invert the condition */ insn = insn ^ (1 << 12);@@ -499,9 +505,9 @@ static bool patch_reloc(tcg_insn_unit *code_ptr, int type, } break; case R_RISCV_JAL: - return reloc_jimm20(code_ptr, (tcg_insn_unit *)value); + return reloc_jimm20(s, code_ptr, (tcg_insn_unit *)value); case R_RISCV_CALL: - return reloc_call(code_ptr, (tcg_insn_unit *)value); + return reloc_call(s, code_ptr, (tcg_insn_unit *)value); default: tcg_abort(); }@@ -557,7 +563,7 @@ static void tcg_out_movi(TCGContext *s, TCGType type, TCGReg rd, if (tmp == (int32_t)tmp) { tcg_out_opc_upper(s, OPC_AUIPC, rd, 0); tcg_out_opc_imm(s, OPC_ADDI, rd, rd, 0); - ret = reloc_call(s->code_ptr - 2, (tcg_insn_unit *)val); + ret = reloc_call(s, s->code_ptr - 2, (tcg_insn_unit *)val); tcg_debug_assert(ret == true); return; }@@ -854,14 +860,14 @@ static void tcg_out_setcond2(TCGContext *s, TCGCond cond, TCGReg ret, g_assert_not_reached(); } -static inline void tcg_out_goto(TCGContext *s, tcg_insn_unit *target) +static inline void tcg_out_goto(TCGContext *s, const tcg_insn_unit *target) { ptrdiff_t offset = tcg_pcrel_diff(s, target); tcg_debug_assert(offset == sextreg(offset, 1, 20) << 1); tcg_out_opc_jump(s, OPC_JAL, TCG_REG_ZERO, offset); } -static void tcg_out_call_int(TCGContext *s, tcg_insn_unit *arg, bool tail) +static void tcg_out_call_int(TCGContext *s, const tcg_insn_unit *arg, bool tail) { TCGReg link = tail ? TCG_REG_ZERO : TCG_REG_RA; ptrdiff_t offset = tcg_pcrel_diff(s, arg);@@ -875,7 +881,7 @@ static void tcg_out_call_int(TCGContext *s, tcg_insn_unit *arg, bool tail) /* long jump: -2147483646 to 2147483648 */ tcg_out_opc_upper(s, OPC_AUIPC, TCG_REG_TMP0, 0); tcg_out_opc_imm(s, OPC_JALR, link, TCG_REG_TMP0, 0); - ret = reloc_call(s->code_ptr - 2, arg);\ + ret = reloc_call(s, s->code_ptr - 2, arg);\ tcg_debug_assert(ret == true); } else if (TCG_TARGET_REG_BITS == 64) { /* far jump: 64-bit */@@ -888,7 +894,7 @@ static void tcg_out_call_int(TCGContext *s, tcg_insn_unit *arg, bool tail) } } -static void tcg_out_call(TCGContext *s, tcg_insn_unit *arg) +static void tcg_out_call(TCGContext *s, const tcg_insn_unit *arg) { tcg_out_call_int(s, arg, false); }@@ -1022,7 +1028,8 @@ static void add_qemu_ldst_label(TCGContext *s, int is_ld, TCGMemOpIdx oi, TCGType ext, TCGReg datalo, TCGReg datahi, TCGReg addrlo, TCGReg addrhi, - void *raddr, tcg_insn_unit **label_ptr) + const tcg_insn_unit *raddr, + tcg_insn_unit **label_ptr) { TCGLabelQemuLdst *label = new_ldst_label(s);@@ -1052,7 +1059,7 @@ static bool tcg_out_qemu_ld_slow_path(TCGContext *s, TCGLabelQemuLdst *l) } /* resolve label address */ - if (!patch_reloc(l->label_ptr[0], R_RISCV_BRANCH, + if (!patch_reloc(s, l->label_ptr[0], R_RISCV_BRANCH, (intptr_t) s->code_ptr, 0)) { return false; }@@ -1087,7 +1094,7 @@ static bool tcg_out_qemu_st_slow_path(TCGContext *s, TCGLabelQemuLdst *l) } /* resolve label address */ - if (!patch_reloc(l->label_ptr[0], R_RISCV_BRANCH, + if (!patch_reloc(s, l->label_ptr[0], R_RISCV_BRANCH, (intptr_t) s->code_ptr, 0)) { return false; }@@ -1274,7 +1281,7 @@ static void tcg_out_qemu_st(TCGContext *s, const TCGArg *args, bool is_64) #endif } -static tcg_insn_unit *tb_ret_addr; +static const tcg_insn_unit *tb_ret_addr; static void tcg_out_op(TCGContext *s, TCGOpcode opc, const TCGArg *args, const int *const_args)tcg/riscv/tcg-target.h +8
-1@@ -164,8 +164,15 @@ static inline void flush_icache_range(uintptr_t start, uintptr_t stop)__builtin___clear_cache ((char *)start, (char *)stop); } +#if defined(CONFIG_IOS_JIT ) +static inline void flush_dcache_range (uintptr_t start,uintptr_t stop) +{ +#error "Unimplemented dcache flush function" +} +#endif +/* not defined -- call should be eliminated at compile time */ -void tb_target_set_jmp_target (uintptr_t ,uintptr_t ,uintptr_t ); +void tb_target_set_jmp_target (uintptr_t ,uintptr_t ,uintptr_t ,uintptr_t );#define TCG_TARGET_DEFAULT_MO (0)tcg/s390/tcg-target.c.inc +13
-12@@ -363,10 +363,10 @@ static void * const qemu_st_helpers[16] = { }; #endif -static tcg_insn_unit *tb_ret_addr; +static const tcg_insn_unit *tb_ret_addr; uint64_t s390_facilities; -static bool patch_reloc(tcg_insn_unit *code_ptr, int type, +static bool patch_reloc(TCGContext *s, tcg_insn_unit *code_ptr, int type, intptr_t value, intptr_t addend) { intptr_t pcrel2;@@ -378,13 +378,13 @@ static bool patch_reloc(tcg_insn_unit *code_ptr, int type, switch (type) { case R_390_PC16DBL: if (pcrel2 == (int16_t)pcrel2) { - tcg_patch16(code_ptr, pcrel2); + tcg_patch16(s, code_ptr, pcrel2); return true; } break; case R_390_PC32DBL: if (pcrel2 == (int32_t)pcrel2) { - tcg_patch32(code_ptr, pcrel2); + tcg_patch32(s, code_ptr, pcrel2); return true; } break;@@ -392,7 +392,7 @@ static bool patch_reloc(tcg_insn_unit *code_ptr, int type, if (value == sextract64(value, 0, 20)) { old = *(uint32_t *)code_ptr & 0xf00000ff; old |= ((value & 0xfff) << 16) | ((value & 0xff000) >> 4); - tcg_patch32(code_ptr, old); + tcg_patch32(s, code_ptr, old); return true; } break;@@ -1302,7 +1302,7 @@ static void tgen_extract(TCGContext *s, TCGReg dest, TCGReg src, tcg_out_risbg(s, dest, src, 64 - len, 63, 64 - ofs, 1); } -static void tgen_gotoi(TCGContext *s, int cc, tcg_insn_unit *dest) +static void tgen_gotoi(TCGContext *s, int cc, const tcg_insn_unit *dest) { ptrdiff_t off = dest - s->code_ptr; if (off == (int16_t)off) {@@ -1415,7 +1415,7 @@ static void tgen_brcond(TCGContext *s, TCGType type, TCGCond c, tgen_branch(s, cc, l); } -static void tcg_out_call(TCGContext *s, tcg_insn_unit *dest) +static void tcg_out_call(TCGContext *s, const tcg_insn_unit *dest) { ptrdiff_t off = dest - s->code_ptr; if (off == (int32_t)off) {@@ -1593,7 +1593,8 @@ static TCGReg tcg_out_tlb_read(TCGContext *s, TCGReg addr_reg, MemOp opc, static void add_qemu_ldst_label(TCGContext *s, bool is_ld, TCGMemOpIdx oi, TCGReg data, TCGReg addr, - tcg_insn_unit *raddr, tcg_insn_unit *label_ptr) + const tcg_insn_unit *raddr, + tcg_insn_unit *label_ptr) { TCGLabelQemuLdst *label = new_ldst_label(s);@@ -1612,7 +1613,7 @@ static bool tcg_out_qemu_ld_slow_path(TCGContext *s, TCGLabelQemuLdst *lb) TCGMemOpIdx oi = lb->oi; MemOp opc = get_memop(oi); - if (!patch_reloc(lb->label_ptr[0], R_390_PC16DBL, + if (!patch_reloc(s, lb->label_ptr[0], R_390_PC16DBL, (intptr_t)s->code_ptr, 2)) { return false; }@@ -1637,7 +1638,7 @@ static bool tcg_out_qemu_st_slow_path(TCGContext *s, TCGLabelQemuLdst *lb) TCGMemOpIdx oi = lb->oi; MemOp opc = get_memop(oi); - if (!patch_reloc(lb->label_ptr[0], R_390_PC16DBL, + if (!patch_reloc(s, lb->label_ptr[0], R_390_PC16DBL, (intptr_t)s->code_ptr, 2)) { return false; }@@ -2575,9 +2576,9 @@ static void tcg_target_qemu_prologue(TCGContext *s) tcg_out_insn(s, RR, BCR, S390_CC_ALWAYS, TCG_REG_R14); } -static void tcg_out_nop_fill(tcg_insn_unit *p, int count) +static void tcg_out_nop_fill(TCGContext *s, tcg_insn_unit *p, int count) { - memset(p, 0x07, count * sizeof(tcg_insn_unit)); + memset(TCG_CODE_PTR_RW(s, p), 0x07, count * sizeof(tcg_insn_unit)); } typedef struct {tcg/s390/tcg-target.h +12
-1@@ -149,13 +149,24 @@ static inline void flush_icache_range(uintptr_t start, uintptr_t stop) { } +#if defined(CONFIG_IOS_JIT ) +static inline void flush_dcache_range (uintptr_t start,uintptr_t stop) +{ +#error "Unimplemented dcache flush function" +} +#endif +static inline void tb_target_set_jmp_target (uintptr_t tc_ptr, -uintptr_t jmp_addr,uintptr_t addr) +uintptr_t jmp_addr,uintptr_t addr, +uintptr_t wr_addr) {/* patch the branch destination */ intptr_t disp = addr - (jmp_addr -2 );qatomic_set ((int32_t *)jmp_addr, disp /2 );/* no need to flush icache explicitly */ +#if defined(CONFIG_IOS_JIT ) +flush_dcache_range (wr_addr, wr_addr +4 ); +#endif }#ifdef CONFIG_SOFTMMU tcg/sparc/tcg-target.c.inc +20
-13@@ -291,14 +291,14 @@ static inline int check_fit_i32(int32_t val, unsigned int bits) # define check_fit_ptr check_fit_i32 #endif -static bool patch_reloc(tcg_insn_unit *code_ptr, int type, +static bool patch_reloc(TCGContext *s, tcg_insn_unit *code_ptr, int type, intptr_t value, intptr_t addend) { uint32_t insn = *code_ptr; intptr_t pcrel; value += addend; - pcrel = tcg_ptr_byte_diff((tcg_insn_unit *)value, code_ptr); + pcrel = tcg_ptr_byte_diff((const tcg_insn_unit *)value, code_ptr); switch (type) { case R_SPARC_WDISP16:@@ -840,7 +840,7 @@ static void tcg_out_addsub2_i64(TCGContext *s, TCGReg rl, TCGReg rh, tcg_out_mov(s, TCG_TYPE_I64, rl, tmp); } -static void tcg_out_call_nodelay(TCGContext *s, tcg_insn_unit *dest, +static void tcg_out_call_nodelay(TCGContext *s, const tcg_insn_unit *dest, bool in_prologue) { ptrdiff_t disp = tcg_pcrel_diff(s, dest);@@ -855,7 +855,7 @@ static void tcg_out_call_nodelay(TCGContext *s, tcg_insn_unit *dest, } } -static void tcg_out_call(TCGContext *s, tcg_insn_unit *dest) +static void tcg_out_call(TCGContext *s, const tcg_insn_unit *dest) { tcg_out_call_nodelay(s, dest, false); tcg_out_nop(s);@@ -868,8 +868,8 @@ static void tcg_out_mb(TCGContext *s, TCGArg a0) } #ifdef CONFIG_SOFTMMU -static tcg_insn_unit *qemu_ld_trampoline[16]; -static tcg_insn_unit *qemu_st_trampoline[16]; +static const tcg_insn_unit *qemu_ld_trampoline[16]; +static const tcg_insn_unit *qemu_st_trampoline[16]; static void emit_extend(TCGContext *s, TCGReg r, int op) {@@ -1048,11 +1048,11 @@ static void tcg_target_qemu_prologue(TCGContext *s) #endif } -static void tcg_out_nop_fill(tcg_insn_unit *p, int count) +static void tcg_out_nop_fill(TCGContext *s, tcg_insn_unit *p, int count) { int i; for (i = 0; i < count; ++i) { - p[i] = NOP; + (TCG_CODE_PTR_RW(s, p))[i] = NOP; } }@@ -1163,7 +1163,7 @@ static void tcg_out_qemu_ld(TCGContext *s, TCGReg data, TCGReg addr, #ifdef CONFIG_SOFTMMU unsigned memi = get_mmuidx(oi); TCGReg addrz, param; - tcg_insn_unit *func; + const tcg_insn_unit *func; tcg_insn_unit *label_ptr; addrz = tcg_out_tlb_load(s, addr, memi, memop,@@ -1226,7 +1226,8 @@ static void tcg_out_qemu_ld(TCGContext *s, TCGReg data, TCGReg addr, } } - *label_ptr |= INSN_OFF19(tcg_ptr_byte_diff(s->code_ptr, label_ptr)); + *TCG_CODE_PTR_RW(s, label_ptr) |= + INSN_OFF19(tcg_ptr_byte_diff(s->code_ptr, label_ptr)); #else if (SPARC64 && TARGET_LONG_BITS == 32) { tcg_out_arithi(s, TCG_REG_T1, addr, 0, SHIFT_SRL);@@ -1822,7 +1823,7 @@ void tcg_register_jit(void *buf, size_t buf_size) } void tb_target_set_jmp_target(uintptr_t tc_ptr, uintptr_t jmp_addr, - uintptr_t addr) + uintptr_t addr, uintptr_t wr_addr) { intptr_t tb_disp = addr - tc_ptr; intptr_t br_disp = addr - jmp_addr;@@ -1834,8 +1835,11 @@ void tb_target_set_jmp_target(uintptr_t tc_ptr, uintptr_t jmp_addr, tcg_debug_assert(br_disp == (int32_t)br_disp); if (!USE_REG_TB) { - qatomic_set((uint32_t *)jmp_addr, + qatomic_set((uint32_t *)wr_addr, deposit32(CALL, 0, 30, br_disp >> 2)); +#if defined(CONFIG_IOS_JIT) + flush_dcache_range(wr_addr, wr_addr + 4); +#endif flush_icache_range(jmp_addr, jmp_addr + 4); return; }@@ -1859,6 +1863,9 @@ void tb_target_set_jmp_target(uintptr_t tc_ptr, uintptr_t jmp_addr, | INSN_IMM13((tb_disp & 0x3ff) | -0x400)); } - qatomic_set((uint64_t *)jmp_addr, deposit64(i2, 32, 32, i1)); + qatomic_set((uint64_t *)wr_addr, deposit64(i2, 32, 32, i1)); +#if defined(CONFIG_IOS_JIT) + flush_dcache_range(wr_addr, wr_addr + 8); +#endif flush_icache_range(jmp_addr, jmp_addr + 8); }tcg/sparc/tcg-target.h +7
-1@@ -176,7 +176,13 @@ static inline void flush_icache_range(uintptr_t start, uintptr_t stop) } } -void tb_target_set_jmp_target (uintptr_t ,uintptr_t ,uintptr_t ); +void tb_target_set_jmp_target (uintptr_t ,uintptr_t ,uintptr_t ,uintptr_t ); +#if defined(CONFIG_IOS_JIT ) +static inline void flush_dcache_range (uintptr_t start,uintptr_t stop) +{ +#error "Unimplemented dcache flush function" +} +#endif #define TCG_TARGET_NEED_POOL_LABELS tcg/tcg-ldst.c.inc +1
-1@@ -28,7 +28,7 @@ typedef struct TCGLabelQemuLdst { TCGReg addrhi_reg; /* reg index for high word of guest virtual addr */ TCGReg datalo_reg; /* reg index for low word to be loaded or stored */ TCGReg datahi_reg; /* reg index for high word to be loaded or stored */ - tcg_insn_unit *raddr; /* gen code addr of the next IR of qemu_ld/st IR */ + const tcg_insn_unit *raddr; /* gen code addr of the next IR of qemu_ld/st */ tcg_insn_unit *label_ptr[2]; /* label pointers to be updated */ QSIMPLEQ_ENTRY(TCGLabelQemuLdst) next; } TCGLabelQemuLdst;tcg/tcg-pool.c.inc +5
-4@@ -119,7 +119,7 @@ static inline void new_pool_l8(TCGContext *s, int rtype, tcg_insn_unit *label, } /* To be provided by cpu/tcg-target.c.inc. */ -static void tcg_out_nop_fill(tcg_insn_unit *p, int count); +static void tcg_out_nop_fill(TCGContext *s, tcg_insn_unit *p, int count); static int tcg_out_pool_finalize(TCGContext *s) {@@ -135,7 +135,7 @@ static int tcg_out_pool_finalize(TCGContext *s) again when allocating the next TranslationBlock structure. */ a = (void *)ROUND_UP((uintptr_t)s->code_ptr, sizeof(tcg_target_ulong) * p->nlong); - tcg_out_nop_fill(s->code_ptr, (tcg_insn_unit *)a - s->code_ptr); + tcg_out_nop_fill(s, s->code_ptr, (tcg_insn_unit *)a - s->code_ptr); s->data_gen_ptr = a; for (; p != NULL; p = p->next) {@@ -144,11 +144,12 @@ static int tcg_out_pool_finalize(TCGContext *s) if (unlikely(a > s->code_gen_highwater)) { return -1; } - memcpy(a, p->data, size); + memcpy(TCG_CODE_PTR_RW(s, a), p->data, size); a += size; l = p; } - if (!patch_reloc(p->label, p->rtype, (intptr_t)a - size, p->addend)) { + if (!patch_reloc(s, p->label, p->rtype, + (intptr_t)a - size, p->addend)) { return -2; } }tcg/tcg.c +39
-21@@ -70,7 +70,7 @@static void tcg_target_init (TCGContext *s);static const TCGTargetOpDef *tcg_target_op_def (TCGOpcode );static void tcg_target_qemu_prologue (TCGContext *s); -static bool patch_reloc (tcg_insn_unit *code_ptr,int type, +static bool patch_reloc (TCGContext *s,tcg_insn_unit *code_ptr,int type,intptr_t value,intptr_t addend);/* The CIE and FDE header definitions will be common to all hosts. */ @@ -148,7 +148,7 @@ static void tcg_out_st(TCGContext *s, TCGType type, TCGReg arg, TCGReg arg1, intptr_t arg2);static bool tcg_out_sti (TCGContext *s,TCGType type,TCGArg val,TCGReg base,intptr_t ofs); -static void tcg_out_call (TCGContext *s,tcg_insn_unit *target); +static void tcg_out_call (TCGContext *s,const tcg_insn_unit *target);static int tcg_target_const_match (tcg_target_long val,TCGType type,const TCGArgConstraint *arg_ct);#ifdef TCG_TARGET_NEED_LDST_LABELS @@ -203,13 +203,15 @@ static TCGRegSet tcg_target_call_clobber_regs;#if TCG_TARGET_INSN_UNIT_SIZE ==1 static __attribute__((unused))inline void tcg_out8 (TCGContext *s,uint8_t v) { - *s->code_ptr++ = v; + *TCG_CODE_PTR_RW (s, s->code_ptr) = v; + s->code_ptr++; } -static __attribute__((unused))inline void tcg_patch8 (tcg_insn_unit *p, +static __attribute__((unused))inline void tcg_patch8 (TCGContext *s, +tcg_insn_unit *p,uint8_t v) { - *p = v; + *TCG_CODE_PTR_RW (s, p) = v; }#endif @@ -217,21 +219,23 @@ static __attribute__((unused)) inline void tcg_patch8(tcg_insn_unit *p,static __attribute__((unused))inline void tcg_out16 (TCGContext *s,uint16_t v) {if (TCG_TARGET_INSN_UNIT_SIZE ==2 ) { - *s->code_ptr++ = v; + *TCG_CODE_PTR_RW (s, s->code_ptr) = v; + s->code_ptr++; }else {tcg_insn_unit *p = s->code_ptr; -memcpy (p, &v,sizeof (v)); +memcpy (TCG_CODE_PTR_RW (s, p), &v,sizeof (v)); s->code_ptr = p + (2 /TCG_TARGET_INSN_UNIT_SIZE ); } } -static __attribute__((unused))inline void tcg_patch16 (tcg_insn_unit *p, +static __attribute__((unused))inline void tcg_patch16 (TCGContext *s, +tcg_insn_unit *p,uint16_t v) {if (TCG_TARGET_INSN_UNIT_SIZE ==2 ) { - *p = v; + *TCG_CODE_PTR_RW (s, p) = v; }else { -memcpy (p, &v,sizeof (v)); +memcpy (TCG_CODE_PTR_RW (s, p), &v,sizeof (v)); } }#endif @@ -240,21 +244,23 @@ static __attribute__((unused)) inline void tcg_patch16(tcg_insn_unit *p,static __attribute__((unused))inline void tcg_out32 (TCGContext *s,uint32_t v) {if (TCG_TARGET_INSN_UNIT_SIZE ==4 ) { - *s->code_ptr++ = v; + *TCG_CODE_PTR_RW (s, s->code_ptr) = v; + s->code_ptr++; }else {tcg_insn_unit *p = s->code_ptr; -memcpy (p, &v,sizeof (v)); +memcpy (TCG_CODE_PTR_RW (s, p), &v,sizeof (v)); s->code_ptr = p + (4 /TCG_TARGET_INSN_UNIT_SIZE ); } } -static __attribute__((unused))inline void tcg_patch32 (tcg_insn_unit *p, +static __attribute__((unused))inline void tcg_patch32 (TCGContext *s, +tcg_insn_unit *p,uint32_t v) {if (TCG_TARGET_INSN_UNIT_SIZE ==4 ) { *p = v; }else { -memcpy (p, &v,sizeof (v)); +memcpy (TCG_CODE_PTR_RW (s, p), &v,sizeof (v)); } }#endif @@ -263,21 +269,23 @@ static __attribute__((unused)) inline void tcg_patch32(tcg_insn_unit *p,static __attribute__((unused))inline void tcg_out64 (TCGContext *s,uint64_t v) {if (TCG_TARGET_INSN_UNIT_SIZE ==8 ) { - *s->code_ptr++ = v; + *TCG_CODE_PTR_RW (s, s->code_ptr) = v; + s->code_ptr++; }else {tcg_insn_unit *p = s->code_ptr; -memcpy (p, &v,sizeof (v)); +memcpy (TCG_CODE_PTR_RW (s, p), &v,sizeof (v)); s->code_ptr = p + (8 /TCG_TARGET_INSN_UNIT_SIZE ); } } -static __attribute__((unused))inline void tcg_patch64 (tcg_insn_unit *p, +static __attribute__((unused))inline void tcg_patch64 (TCGContext *s, +tcg_insn_unit *p,uint64_t v) {if (TCG_TARGET_INSN_UNIT_SIZE ==8 ) { *p = v; }else { -memcpy (p, &v,sizeof (v)); +memcpy (TCG_CODE_PTR_RW (s, p), &v,sizeof (v)); } }#endif @@ -295,7 +303,7 @@ static void tcg_out_reloc(TCGContext *s, tcg_insn_unit *code_ptr, int type,QSIMPLEQ_INSERT_TAIL (&l->relocs, r, next); } -static void tcg_out_label (TCGContext *s,TCGLabel *l,tcg_insn_unit *ptr) +static void tcg_out_label (TCGContext *s,TCGLabel *l,const tcg_insn_unit *ptr) {tcg_debug_assert (!l->has_value); l->has_value =1 ;@@ -325,7 +333,7 @@ static bool tcg_resolve_relocs(TCGContext *s)uintptr_t value = l->u.value; QSIMPLEQ_FOREACH(r, &l->relocs, next) { -if (!patch_reloc (r->ptr, r->type, value, r->addend)) { +if (!patch_reloc (s, r->ptr, r->type, value, r->addend)) {return false; } }@@ -1039,7 +1047,7 @@ TranslationBlock *tcg_tb_alloc(TCGContext *s) }qatomic_set (&s->code_gen_ptr, next); s->data_gen_ptr =NULL ; -return tb; +return (TranslationBlock *)TCG_CODE_PTR_RW (s, tb); }void tcg_prologue_init (TCGContext *s)@@ -1076,6 +1084,10 @@ void tcg_prologue_init(TCGContext *s)#endif buf1 = s->code_ptr; +#if defined(CONFIG_IOS_JIT ) +flush_dcache_range ((uintptr_t )TCG_CODE_PTR_RW (s, buf0), + (uintptr_t )TCG_CODE_PTR_RW (s, buf1)); +#endif flush_icache_range ((uintptr_t )buf0, (uintptr_t )buf1);/* Deduct the prologue from the buffer. */ @@ -4267,6 +4279,12 @@ int tcg_gen_code(TCGContext *s, TranslationBlock *tb)return -2 ; } +#if defined(CONFIG_IOS_JIT ) +/* flush data cache on mirror */ +flush_dcache_range ((uintptr_t )TCG_CODE_PTR_RW (s, s->code_buf), + (uintptr_t )TCG_CODE_PTR_RW (s, s->code_ptr)); +#endif +/* flush instruction cache */ flush_icache_range ((uintptr_t )s->code_buf, (uintptr_t )s->code_ptr);tcg/tci/tcg-target.c.inc +4
-4@@ -369,7 +369,7 @@ static const char *const tcg_target_reg_names[TCG_TARGET_NB_REGS] = { }; #endif -static bool patch_reloc(tcg_insn_unit *code_ptr, int type, +static bool patch_reloc(TCGContext *s, tcg_insn_unit *code_ptr, int type, intptr_t value, intptr_t addend) { /* tcg_out_reloc always uses the same type, addend. */@@ -377,9 +377,9 @@ static bool patch_reloc(tcg_insn_unit *code_ptr, int type, tcg_debug_assert(addend == 0); tcg_debug_assert(value != 0); if (TCG_TARGET_REG_BITS == 32) { - tcg_patch32(code_ptr, value); + tcg_patch32(s, code_ptr, value); } else { - tcg_patch64(code_ptr, value); + tcg_patch64(s, code_ptr, value); } return true; }@@ -545,7 +545,7 @@ static void tcg_out_movi(TCGContext *s, TCGType type, old_code_ptr[1] = s->code_ptr - old_code_ptr; } -static inline void tcg_out_call(TCGContext *s, tcg_insn_unit *arg) +static inline void tcg_out_call(TCGContext *s, const tcg_insn_unit *arg) { uint8_t *old_code_ptr = s->code_ptr; tcg_out_op_t(s, INDEX_op_call);tcg/tci/tcg-target.h +8
-1@@ -195,6 +195,12 @@ static inline void flush_icache_range(uintptr_t start, uintptr_t stop) { } +#if defined(CONFIG_IOS_JIT ) +static inline void flush_dcache_range (uintptr_t start,uintptr_t stop) +{ +} +#endif +/* We could notice __i386__ or __s390x__ and reduce the barriers depending on the host. But if you want performance, you use the normal backend. We prefer consistency across hosts on this. */ @@ -203,7 +209,8 @@ static inline void flush_icache_range(uintptr_t start, uintptr_t stop)#define TCG_TARGET_HAS_MEMORY_BSWAP 1static inline void tb_target_set_jmp_target (uintptr_t tc_ptr, -uintptr_t jmp_addr,uintptr_t addr) +uintptr_t jmp_addr,uintptr_t addr, +uintptr_t wr_addr) {/* patch the branch destination */ qatomic_set ((int32_t *)jmp_addr, addr - (jmp_addr +4 ));
Re: [PATCH 07/10] tcg: implement bulletproof JIT
Hi Philippe,
Will work on splitting the patch for v2. Thanks for the tip on git.orderfile
Hi Balaton,
Reply inline.
-j
Quoted 8 lines · BALATON Zoltan
Quoted 4 lines · Joelle van Dyne
From: osy <[email protected]>
On iOS, we cannot allocate RWX pages without special entitlements. As a workaround, we can a RX region and then mirror map it to a separate RX
Missing a verb here: "we can a RX region"
Good catch.
Quoted 10 lines
Quoted 7 lines
region. Then we can write to one region and execute from the other one.
To better keep track of pointers to RW/RX memory, we mark any
tcg_insn_unitpointers asconstif they will never be written to. We also define a new macroTCG_CODE_PTR_RWthat returns a pointer to RW memory. Only the difference between the two regions is stored in the TCG context.Maybe it's easier to review if constification is split off as separate patch before other changes.
Will do.
Quoted 93 lines
Quoted 93 lines
To ensure cache coherency, we flush the data cache in the RW mapping and then invalidate the instruction cache in the RX mapping (where applicable). Because data cache flush is OS defined on some architectures, we do not provide implementations for non iOS platforms (ARM/x86).
Signed-off-by Joelle van Dyne <[email protected]>---
accel/tcg/cpu-exec.c | 7 +++- accel/tcg/translate-all.c | 78 ++++++++++++++++++++++++++++++++++-- configure | 1 + docs/devel/ios.rst | 40 ++++++++++++++++++ include/exec/exec-all.h | 8 ++++ include/tcg/tcg.h | 18 +++++++-- tcg/aarch64/tcg-target.c.inc | 48 +++++++++++++--------- tcg/aarch64/tcg-target.h | 13 +++++- tcg/arm/tcg-target.c.inc | 33 ++++++++------- tcg/arm/tcg-target.h | 9 ++++- tcg/i386/tcg-target.c.inc | 28 ++++++------- tcg/i386/tcg-target.h | 24 ++++++++++- tcg/mips/tcg-target.c.inc | 64 +++++++++++++++++------------ tcg/mips/tcg-target.h | 8 +++- tcg/ppc/tcg-target.c.inc | 55 ++++++++++++++++--------- tcg/ppc/tcg-target.h | 8 +++- tcg/riscv/tcg-target.c.inc | 51 +++++++++++++---------- tcg/riscv/tcg-target.h | 9 ++++- tcg/s390/tcg-target.c.inc | 25 ++++++------ tcg/s390/tcg-target.h | 13 +++++- tcg/sparc/tcg-target.c.inc | 33 +++++++++------ tcg/sparc/tcg-target.h | 8 +++- tcg/tcg-ldst.c.inc | 2 +- tcg/tcg-pool.c.inc | 9 +++-- tcg/tcg.c | 60 +++++++++++++++++---------- tcg/tci/tcg-target.c.inc | 8 ++-- tcg/tci/tcg-target.h | 9 ++++- 27 files changed, 481 insertions(+), 188 deletions(-)create mode 100644
docs/devel/ios.rstaccel/tcg/cpu-exec.c +6
-1@@ -354,7 +354,12 @@ void tb_set_jmp_target(TranslationBlock *tb, int n, uintptr_t addr)if (TCG_TARGET_HAS_direct_jump) {uintptr_t offset = tb->jmp_target_arg[n];uintptr_t tc_ptr = (uintptr_t )tb->tc.ptr; -tb_target_set_jmp_target (tc_ptr, tc_ptr + offset, addr); +#if defined(CONFIG_IOS_JIT ) +uintptr_t wr_addr = tc_ptr + offset + tb->code_rw_mirror_diff; +#else +uintptr_t wr_addr = tc_ptr + offset; +#endif +tb_target_set_jmp_target (tc_ptr, tc_ptr + offset, addr, wr_addr); }else { tb->jmp_target_arg[n] = addr; }accel/tcg/translate-all.c +18
-2@@ -60,6 +60,22 @@#include "sysemu/cpu-timers.h" #include "sysemu/tcg.h" +#if defined(CONFIG_IOS_JIT ) +#include <mach/mach.h> +extern kern_return_t mach_vm_remap (vm_map_t target_task, +mach_vm_address_t *target_address, +mach_vm_size_t size, +mach_vm_offset_t mask, +int flags, +vm_map_t src_task, +mach_vm_address_t src_address, +boolean_t copy, +vm_prot_t *cur_protection, +vm_prot_t *max_protection, +vm_inherit_t inheritance + ); +#endif +/* #define DEBUG_TB_INVALIDATE */ /* #define DEBUG_TB_FLUSH */ /* make various TB consistency checks */ @@ -302,10 +318,13 @@ static target_long decode_sleb128(uint8_t **pp)static int encode_search (TranslationBlock *tb,uint8_t *block) { -uint8_t *highwater = tcg_ctx->code_gen_highwater; -uint8_t *p = block; +uint8_t *highwater; +uint8_t *p;int i, j, n;
Quoted 7 lines
accel/tcg/translate-all.c static target_long decode_sleb128(uint8_t **pp) · line 327
Quoted 3 lines
accel/tcg/translate-all.c +3
-0+ highwater = (uint8_t *)TCG_CODE_PTR_RW (tcg_ctx, + tcg_ctx->code_gen_highwater); + p = (uint8_t *)TCG_CODE_PTR_RW (tcg_ctx, block);Why do you need explicit casts here? Can this be avoided by using appropriate type or within the macro (I haven't checked this at all just dislike casts as they can hide problems otherwise caught by the compiler).
There's the choice between tcg_insn_unit * and uint8_t *. Since it's used much more widely in tcg-target.inc.c, it seemed like tcg_insn_unit * was a better choice.
Quoted 1,858 lines
Regards,
BALATON ZoltanQuoted 1,853 lines
accel/tcg/translate-all.c +54
-1for (i =0 , n = tb->icount; i < n; ++i) {target_ulong prev;@@ -329,7 +348,7 @@ static int encode_search(TranslationBlock *tb, uint8_t *block) } } -return p - block; +return p - (uint8_t *)TCG_CODE_PTR_RW (tcg_ctx, block); }/* The cpu state corresponding to 'searched_pc' is restored. @@ -1067,7 +1086,11 @@ static inline void *alloc_code_gen_buffer(void)#else static inline void *alloc_code_gen_buffer (void ) { +#if defined(CONFIG_IOS_JIT ) +int prot =PROT_READ |PROT_EXEC ; +#else int prot =PROT_WRITE |PROT_READ |PROT_EXEC ; +#endif int flags =MAP_PRIVATE |MAP_ANONYMOUS ;size_t size = tcg_ctx->code_gen_buffer_size;void *buf;@@ -1118,6 +1141,39 @@ static inline void *alloc_code_gen_buffer(void) }#endif /* USE_STATIC_CODE_GEN_BUFFER, WIN32, POSIX */ +#if defined(CONFIG_IOS_JIT ) +static inline void *alloc_jit_rw_mirror (void *base,size_t size) +{ +kern_return_t ret; +mach_vm_address_t mirror; +vm_prot_t cur_prot, max_prot; + + mirror =0 ; + ret =mach_vm_remap (mach_task_self (), + &mirror, + size, +0 , +VM_FLAGS_ANYWHERE |VM_FLAGS_RANDOM_ADDR , +mach_task_self (), + (mach_vm_address_t )base, + false, + &cur_prot, + &max_prot, +VM_INHERIT_NONE + ); +if (ret !=KERN_SUCCESS ) { +return NULL ; + } + +if (mprotect ((void *)mirror, size,PROT_READ |PROT_WRITE ) !=0 ) { +munmap ((void *)mirror, size); +return NULL ; + } + +return (void *)mirror; +} +#endif /* CONFIG_IOS_JIT */ +static inline void code_gen_alloc (size_t tb_size) { tcg_ctx->code_gen_buffer_size =size_code_gen_buffer (tb_size);@@ -1126,6 +1182,19 @@ static inline void code_gen_alloc(size_t tb_size)fprintf (stderr,"Could not allocate dynamic translator buffer\n" );exit (1 ); } +#if defined(CONFIG_IOS_JIT ) +void *mirror; + +/* For iOS JIT we need a mirror mapping for code execution */ + mirror =alloc_jit_rw_mirror (tcg_ctx->code_gen_buffer, + tcg_ctx->code_gen_buffer_size + ); +if (mirror ==NULL ) { +fprintf (stderr,"Could not remap code buffer mirror\n" ); +exit (1 ); + } + tcg_ctx->code_rw_mirror_diff = mirror - tcg_ctx->code_gen_buffer; +#endif /* CONFIG_IOS_JIT */ }static bool tb_cmp (const void *ap,const void *bp)@@ -1721,6 +1790,9 @@ TranslationBlock *tb_gen_code(CPUState *cpu,cpu_loop_exit (cpu); } +#if defined(CONFIG_IOS_JIT ) + tb->code_rw_mirror_diff = tcg_ctx->code_rw_mirror_diff; +#endif gen_code_buf = tcg_ctx->code_gen_ptr; tb->tc.ptr = gen_code_buf; tb->pc = pc;configure +0
-0@@ -6220,6 +6220,7 @@ fiif test "$ios" = "yes" ; then
echo "CONFIG_IOS=y" >> $config_host_mak
+ echo "CONFIG_IOS_JIT=y" >> $config_host_mak
fiif test "$solaris" = "yes" ; then
docs/devel/ios.rst new file +40
-0@@ -0,0 +1,40 @@ +=========== +iOS Support +=========== + +To run qemu on the iOS platform, some modifications were required. Most of the +modifications are conditioned on the ``CONFIG_IOS`` and ``CONFIG_IOS_JIT`` +configuration variables. + +Build support +------------- + +For the code to compile, certain changes in the block driver and the slirp +driver had to be made. There is no ``system()`` call, so code requiring it had +to be disabled. + +``ucontext`` support is broken on iOS. The implementation from ``libucontext`` +is used instead. + +Because ``fork()`` is not allowed on iOS apps, the option to build qemu and the +utilities as shared libraries is added. Note that because qemu does not perform +resource cleanup in most cases (open files, allocated memory, etc), it is +advisable that the user implements a proxy layer for syscalls so resources can +be kept track by the app that uses qemu as a shared library. + +JIT support +----------- + +On iOS, allocating RWX pages require special entitlements not usually granted to +apps. However, it is possible to use `bulletproof JIT`_ with a development +certificate. This means that we need to allocate one chunk of memory with RX +permissions and then mirror map the same memory with RW permissions. We generate +code to the mirror mapping and execute the original mapping. + +With ``CONFIG_IOS_JIT`` defined, we store inside the TCG context the difference +between the two mappings. Then, we make sure that any writes to JIT memory is +done to the pointer + the difference (in order to get a pointer to the mirror +mapped space). Additionally, we make sure to flush the data cache before we +invalidate the instruction cache so the changes are seen in both mappings. + +.. _bulletproof JIT: https://www.blackhat.com/docs/us-16/materials/us-16-Krstic.pdfinclude/exec/exec-all.h +8
-0@@ -483,6 +483,14 @@ struct TranslationBlock {uintptr_t jmp_list_head;uintptr_t jmp_list_next[2 ];uintptr_t jmp_dest[2 ]; + +#if defined(CONFIG_IOS_JIT ) +/* +* Store difference to writable mirror +* We need this when patching the jump instructions +*/ +ptrdiff_t code_rw_mirror_diff; +#endif };extern bool parallel_cpus;include/tcg/tcg.h +14
-4@@ -261,7 +261,7 @@ struct TCGLabel { unsigned refs : 16;union {uintptr_t value; -tcg_insn_unit *value_ptr; +const tcg_insn_unit *value_ptr; } u; QSIMPLEQ_HEAD(, TCGRelocation) relocs;QSIMPLEQ_ENTRY (TCGLabel) next;@@ -593,7 +593,7 @@ struct TCGContext {int nb_ops;/* goto_tb support */ -tcg_insn_unit *code_buf; +const tcg_insn_unit *code_buf;uint16_t *tb_jmp_reset_offset;/* tb->jmp_reset_offset */ uintptr_t *tb_jmp_insn_offset;/* tb->jmp_target_arg if direct_jump */ uintptr_t *tb_jmp_target_addr;/* tb->jmp_target_arg if !direct_jump */ @@ -627,6 +627,9 @@ struct TCGContext {size_t code_gen_buffer_size;void *code_gen_ptr;void *data_gen_ptr; +#if defined(CONFIG_IOS_JIT ) +ptrdiff_t code_rw_mirror_diff; +#endif /* Threshold to flush the translated code buffer. */ void *code_gen_highwater;@@ -677,6 +680,13 @@ struct TCGContext {target_ulong gen_insn_data[TCG_MAX_INSNS ][TARGET_INSN_START_WORDS ]; }; +#if defined(CONFIG_IOS_JIT ) +# define TCG_CODE_PTR_RW (s, code_ptr) \ + (tcg_insn_unit *)((uintptr_t)(code_ptr) + (s)->code_rw_mirror_diff) +#else +# define TCG_CODE_PTR_RW (s, code_ptr) (code_ptr) +#endif +extern TCGContext tcg_init_ctx;extern __threadTCGContext *tcg_ctx;extern TCGv_env cpu_env;@@ -1099,7 +1109,7 @@ static inline TCGLabel *arg_label(TCGArg i)* correct result. */ -static inline ptrdiff_t tcg_ptr_byte_diff (void *a,void *b) +static inline ptrdiff_t tcg_ptr_byte_diff (const void *a,const void *b) {return a - b; }@@ -1113,7 +1123,7 @@ static inline ptrdiff_t tcg_ptr_byte_diff(void *a, void *b)* to the destination address. */ -static inline ptrdiff_t tcg_pcrel_diff (TCGContext *s,void *target) +static inline ptrdiff_t tcg_pcrel_diff (TCGContext *s,const void *target) {return tcg_ptr_byte_diff (target, s->code_ptr); }tcg/aarch64/tcg-target.c.inc +29
-19@@ -78,38 +78,44 @@ static const int tcg_target_call_oarg_regs[1] = { #define TCG_REG_GUEST_BASE TCG_REG_X28 #endif -static inline bool reloc_pc26(tcg_insn_unit *code_ptr, tcg_insn_unit *target) +static inline bool reloc_pc26(TCGContext *s, + tcg_insn_unit *code_ptr, + const tcg_insn_unit *target) { ptrdiff_t offset = target - code_ptr; if (offset == sextract64(offset, 0, 26)) { /* read instruction, mask away previous PC_REL26 parameter contents, set the proper offset, then write back the instruction. */ - *code_ptr = deposit32(*code_ptr, 0, 26, offset); + *TCG_CODE_PTR_RW(s, code_ptr) = + deposit32(*TCG_CODE_PTR_RW(s, code_ptr), 0, 26, offset); return true; } return false; } -static inline bool reloc_pc19(tcg_insn_unit *code_ptr, tcg_insn_unit *target) +static inline bool reloc_pc19(TCGContext *s, + tcg_insn_unit *code_ptr, + const tcg_insn_unit *target) { ptrdiff_t offset = target - code_ptr; if (offset == sextract64(offset, 0, 19)) { - *code_ptr = deposit32(*code_ptr, 5, 19, offset); + *TCG_CODE_PTR_RW(s, code_ptr) = + deposit32(*TCG_CODE_PTR_RW(s, code_ptr), 5, 19, offset); return true; } return false; } -static inline bool patch_reloc(tcg_insn_unit *code_ptr, int type, +static inline bool patch_reloc(TCGContext *s, tcg_insn_unit *code_ptr, int type, intptr_t value, intptr_t addend) { tcg_debug_assert(addend == 0); switch (type) { case R_AARCH64_JUMP26: case R_AARCH64_CALL26: - return reloc_pc26(code_ptr, (tcg_insn_unit *)value); + return reloc_pc26(s, code_ptr, (tcg_insn_unit *)value); case R_AARCH64_CONDBR19: - return reloc_pc19(code_ptr, (tcg_insn_unit *)value); + return reloc_pc19(s, code_ptr, (tcg_insn_unit *)value); default: g_assert_not_reached(); }@@ -1306,14 +1312,14 @@ static void tcg_out_cmp(TCGContext *s, TCGType ext, TCGReg a, } } -static inline void tcg_out_goto(TCGContext *s, tcg_insn_unit *target) +static inline void tcg_out_goto(TCGContext *s, const tcg_insn_unit *target) { ptrdiff_t offset = target - s->code_ptr; tcg_debug_assert(offset == sextract64(offset, 0, 26)); tcg_out_insn(s, 3206, B, offset); } -static inline void tcg_out_goto_long(TCGContext *s, tcg_insn_unit *target) +static inline void tcg_out_goto_long(TCGContext *s, const tcg_insn_unit *target) { ptrdiff_t offset = target - s->code_ptr; if (offset == sextract64(offset, 0, 26)) {@@ -1329,7 +1335,7 @@ static inline void tcg_out_callr(TCGContext *s, TCGReg reg) tcg_out_insn(s, 3207, BLR, reg); } -static inline void tcg_out_call(TCGContext *s, tcg_insn_unit *target) +static inline void tcg_out_call(TCGContext *s, const tcg_insn_unit *target) { ptrdiff_t offset = target - s->code_ptr; if (offset == sextract64(offset, 0, 26)) {@@ -1341,7 +1347,7 @@ static inline void tcg_out_call(TCGContext *s, tcg_insn_unit *target) } void tb_target_set_jmp_target(uintptr_t tc_ptr, uintptr_t jmp_addr, - uintptr_t addr) + uintptr_t addr, uintptr_t wr_addr) { tcg_insn_unit i1, i2; TCGType rt = TCG_TYPE_I64;@@ -1362,7 +1368,10 @@ void tb_target_set_jmp_target(uintptr_t tc_ptr, uintptr_t jmp_addr, i2 = I3401_ADDI | rt << 31 | (addr & 0xfff) << 10 | rd << 5 | rd; } pair = (uint64_t)i2 << 32 | i1; - qatomic_set((uint64_t *)jmp_addr, pair); + qatomic_set((uint64_t *)wr_addr, pair); +#if defined(CONFIG_IOS_JIT) + flush_dcache_range(wr_addr, wr_addr + 8); +#endif flush_icache_range(jmp_addr, jmp_addr + 8); }@@ -1568,7 +1577,7 @@ static void * const qemu_st_helpers[16] = { [MO_BEQ] = helper_be_stq_mmu, }; -static inline void tcg_out_adr(TCGContext *s, TCGReg rd, void *target) +static inline void tcg_out_adr(TCGContext *s, TCGReg rd, const void *target) { ptrdiff_t offset = tcg_pcrel_diff(s, target); tcg_debug_assert(offset == sextract64(offset, 0, 21));@@ -1581,7 +1590,7 @@ static bool tcg_out_qemu_ld_slow_path(TCGContext *s, TCGLabelQemuLdst *lb) MemOp opc = get_memop(oi); MemOp size = opc & MO_SIZE; - if (!reloc_pc19(lb->label_ptr[0], s->code_ptr)) { + if (!reloc_pc19(s, lb->label_ptr[0], s->code_ptr)) { return false; }@@ -1606,7 +1615,7 @@ static bool tcg_out_qemu_st_slow_path(TCGContext *s, TCGLabelQemuLdst *lb) MemOp opc = get_memop(oi); MemOp size = opc & MO_SIZE; - if (!reloc_pc19(lb->label_ptr[0], s->code_ptr)) { + if (!reloc_pc19(s, lb->label_ptr[0], s->code_ptr)) { return false; }@@ -1622,7 +1631,8 @@ static bool tcg_out_qemu_st_slow_path(TCGContext *s, TCGLabelQemuLdst *lb) static void add_qemu_ldst_label(TCGContext *s, bool is_ld, TCGMemOpIdx oi, TCGType ext, TCGReg data_reg, TCGReg addr_reg, - tcg_insn_unit *raddr, tcg_insn_unit *label_ptr) + const tcg_insn_unit *raddr, + tcg_insn_unit *label_ptr) { TCGLabelQemuLdst *label = new_ldst_label(s);@@ -1849,7 +1859,7 @@ static void tcg_out_qemu_st(TCGContext *s, TCGReg data_reg, TCGReg addr_reg, #endif /* CONFIG_SOFTMMU */ } -static tcg_insn_unit *tb_ret_addr; +static const tcg_insn_unit *tb_ret_addr; static void tcg_out_op(TCGContext *s, TCGOpcode opc, const TCGArg args[TCG_MAX_OP_ARGS],@@ -2916,11 +2926,11 @@ static void tcg_target_qemu_prologue(TCGContext *s) tcg_out_insn(s, 3207, RET, TCG_REG_LR); } -static void tcg_out_nop_fill(tcg_insn_unit *p, int count) +static void tcg_out_nop_fill(TCGContext *s, tcg_insn_unit *p, int count) { int i; for (i = 0; i < count; ++i) { - p[i] = NOP; + (TCG_CODE_PTR_RW(s, p))[i] = NOP; } }tcg/aarch64/tcg-target.h +12
-1@@ -150,6 +150,7 @@ typedef enum {#if defined(__APPLE__)void sys_icache_invalidate (void *start,size_t len); +void sys_dcache_flush (void *start,size_t len);#endif static inline void flush_icache_range (uintptr_t start,uintptr_t stop)@@ -163,7 +164,17 @@ static inline void flush_icache_range(uintptr_t start, uintptr_t stop)#endif } -void tb_target_set_jmp_target (uintptr_t ,uintptr_t ,uintptr_t ); +void tb_target_set_jmp_target (uintptr_t ,uintptr_t ,uintptr_t ,uintptr_t ); +#if defined(CONFIG_IOS_JIT ) +static inline void flush_dcache_range (uintptr_t start,uintptr_t stop) +{ +#if defined(__APPLE__) +sys_dcache_flush ((char *)start, stop - start); +#else +#error "Missing function to flush data cache" +#endif +} +#endif #ifdef CONFIG_SOFTMMU #define TCG_TARGET_NEED_LDST_LABELS tcg/arm/tcg-target.c.inc +19
-14@@ -187,17 +187,22 @@ static const uint8_t tcg_cond_to_arm_cond[] = { [TCG_COND_GTU] = COND_HI, }; -static inline bool reloc_pc24(tcg_insn_unit *code_ptr, tcg_insn_unit *target) +static inline bool reloc_pc24(TCGContext *s, + tcg_insn_unit *code_ptr, + const tcg_insn_unit *target) { ptrdiff_t offset = (tcg_ptr_byte_diff(target, code_ptr) - 8) >> 2; if (offset == sextract32(offset, 0, 24)) { - *code_ptr = (*code_ptr & ~0xffffff) | (offset & 0xffffff); + *TCG_CODE_PTR_RW(s, code_ptr) = + (*TCG_CODE_PTR_RW(s, code_ptr) & ~0xffffff) | (offset & 0xffffff); return true; } return false; } -static inline bool reloc_pc13(tcg_insn_unit *code_ptr, tcg_insn_unit *target) +static inline bool reloc_pc13(TCGContext *s, + tcg_insn_unit *code_ptr, + const tcg_insn_unit *target) { ptrdiff_t offset = tcg_ptr_byte_diff(target, code_ptr) - 8;@@ -209,21 +214,21 @@ static inline bool reloc_pc13(tcg_insn_unit *code_ptr, tcg_insn_unit *target) } insn = deposit32(insn, 23, 1, u); insn = deposit32(insn, 0, 12, offset); - *code_ptr = insn; + *TCG_CODE_PTR_RW(s, code_ptr) = insn; return true; } return false; } -static bool patch_reloc(tcg_insn_unit *code_ptr, int type, +static bool patch_reloc(TCGContext *s, tcg_insn_unit *code_ptr, int type, intptr_t value, intptr_t addend) { tcg_debug_assert(addend == 0); if (type == R_ARM_PC24) { - return reloc_pc24(code_ptr, (tcg_insn_unit *)value); + return reloc_pc24(s, code_ptr, (tcg_insn_unit *)value); } else if (type == R_ARM_PC13) { - return reloc_pc13(code_ptr, (tcg_insn_unit *)value); + return reloc_pc13(s, code_ptr, (tcg_insn_unit *)value); } else { g_assert_not_reached(); }@@ -1019,7 +1024,7 @@ static inline void tcg_out_st8(TCGContext *s, int cond, * with the code buffer limited to 16MB we wouldn't need the long case. * But we also use it for the tail-call to the qemu_ld/st helpers, which does. */ -static void tcg_out_goto(TCGContext *s, int cond, tcg_insn_unit *addr) +static void tcg_out_goto(TCGContext *s, int cond, const tcg_insn_unit *addr) { intptr_t addri = (intptr_t)addr; ptrdiff_t disp = tcg_pcrel_diff(s, addr);@@ -1033,7 +1038,7 @@ static void tcg_out_goto(TCGContext *s, int cond, tcg_insn_unit *addr) /* The call case is mostly used for helpers - so it's not unreasonable * for them to be beyond branch range */ -static void tcg_out_call(TCGContext *s, tcg_insn_unit *addr) +static void tcg_out_call(TCGContext *s, const tcg_insn_unit *addr) { intptr_t addri = (intptr_t)addr; ptrdiff_t disp = tcg_pcrel_diff(s, addr);@@ -1326,7 +1331,7 @@ static TCGReg tcg_out_tlb_read(TCGContext *s, TCGReg addrlo, TCGReg addrhi, helper code. */ static void add_qemu_ldst_label(TCGContext *s, bool is_ld, TCGMemOpIdx oi, TCGReg datalo, TCGReg datahi, TCGReg addrlo, - TCGReg addrhi, tcg_insn_unit *raddr, + TCGReg addrhi, const tcg_insn_unit *raddr, tcg_insn_unit *label_ptr) { TCGLabelQemuLdst *label = new_ldst_label(s);@@ -1348,7 +1353,7 @@ static bool tcg_out_qemu_ld_slow_path(TCGContext *s, TCGLabelQemuLdst *lb) MemOp opc = get_memop(oi); void *func; - if (!reloc_pc24(lb->label_ptr[0], s->code_ptr)) { + if (!reloc_pc24(s, lb->label_ptr[0], s->code_ptr)) { return false; }@@ -1411,7 +1416,7 @@ static bool tcg_out_qemu_st_slow_path(TCGContext *s, TCGLabelQemuLdst *lb) TCGMemOpIdx oi = lb->oi; MemOp opc = get_memop(oi); - if (!reloc_pc24(lb->label_ptr[0], s->code_ptr)) { + if (!reloc_pc24(s, lb->label_ptr[0], s->code_ptr)) { return false; }@@ -2255,11 +2260,11 @@ static inline void tcg_out_movi(TCGContext *s, TCGType type, tcg_out_movi32(s, COND_AL, ret, arg); } -static void tcg_out_nop_fill(tcg_insn_unit *p, int count) +static void tcg_out_nop_fill(TCGContext *s, tcg_insn_unit *p, int count) { int i; for (i = 0; i < count; ++i) { - p[i] = INSN_NOP; + (TCG_CODE_PTR_RW(s, p))[i] = INSN_NOP; } }tcg/arm/tcg-target.h +8
-1@@ -139,8 +139,15 @@ static inline void flush_icache_range(uintptr_t start, uintptr_t stop)__builtin___clear_cache ((char *) start, (char *) stop); } +#if defined(CONFIG_IOS_JIT ) +static inline void flush_dcache_range (uintptr_t start,uintptr_t stop) +{ +#error "Unimplemented dcache flush function" +} +#endif +/* not defined -- call should be eliminated at compile time */ -void tb_target_set_jmp_target (uintptr_t ,uintptr_t ,uintptr_t ); +void tb_target_set_jmp_target (uintptr_t ,uintptr_t ,uintptr_t ,uintptr_t );#ifdef CONFIG_SOFTMMU #define TCG_TARGET_NEED_LDST_LABELS tcg/i386/tcg-target.c.inc +14
-14@@ -165,9 +165,9 @@ static bool have_lzcnt; # define have_lzcnt 0 #endif -static tcg_insn_unit *tb_ret_addr; +static const tcg_insn_unit *tb_ret_addr; -static bool patch_reloc(tcg_insn_unit *code_ptr, int type, +static bool patch_reloc(TCGContext *s, tcg_insn_unit *code_ptr, int type, intptr_t value, intptr_t addend) { value += addend;@@ -179,14 +179,14 @@ static bool patch_reloc(tcg_insn_unit *code_ptr, int type, } /* FALLTHRU */ case R_386_32: - tcg_patch32(code_ptr, value); + tcg_patch32(s, code_ptr, value); break; case R_386_PC8: value -= (uintptr_t)code_ptr; if (value != (int8_t)value) { return false; } - tcg_patch8(code_ptr, value); + tcg_patch8(s, code_ptr, value); break; default: tcg_abort();@@ -1591,7 +1591,7 @@ static void tcg_out_clz(TCGContext *s, int rexw, TCGReg dest, TCGReg arg1, } } -static void tcg_out_branch(TCGContext *s, int call, tcg_insn_unit *dest) +static void tcg_out_branch(TCGContext *s, int call, const tcg_insn_unit *dest) { intptr_t disp = tcg_pcrel_diff(s, dest) - 5;@@ -1610,12 +1610,12 @@ static void tcg_out_branch(TCGContext *s, int call, tcg_insn_unit *dest) } } -static inline void tcg_out_call(TCGContext *s, tcg_insn_unit *dest) +static inline void tcg_out_call(TCGContext *s, const tcg_insn_unit *dest) { tcg_out_branch(s, 1, dest); } -static void tcg_out_jmp(TCGContext *s, tcg_insn_unit *dest) +static void tcg_out_jmp(TCGContext *s, const tcg_insn_unit *dest) { tcg_out_branch(s, 0, dest); }@@ -1774,7 +1774,7 @@ static void add_qemu_ldst_label(TCGContext *s, bool is_ld, bool is_64, TCGMemOpIdx oi, TCGReg datalo, TCGReg datahi, TCGReg addrlo, TCGReg addrhi, - tcg_insn_unit *raddr, + const tcg_insn_unit *raddr, tcg_insn_unit **label_ptr) { TCGLabelQemuLdst *label = new_ldst_label(s);@@ -1805,9 +1805,9 @@ static bool tcg_out_qemu_ld_slow_path(TCGContext *s, TCGLabelQemuLdst *l) int rexw = (l->type == TCG_TYPE_I64 ? P_REXW : 0); /* resolve label address */ - tcg_patch32(label_ptr[0], s->code_ptr - label_ptr[0] - 4); + tcg_patch32(s, label_ptr[0], s->code_ptr - label_ptr[0] - 4); if (TARGET_LONG_BITS > TCG_TARGET_REG_BITS) { - tcg_patch32(label_ptr[1], s->code_ptr - label_ptr[1] - 4); + tcg_patch32(s, label_ptr[1], s->code_ptr - label_ptr[1] - 4); } if (TCG_TARGET_REG_BITS == 32) {@@ -1890,9 +1890,9 @@ static bool tcg_out_qemu_st_slow_path(TCGContext *s, TCGLabelQemuLdst *l) TCGReg retaddr; /* resolve label address */ - tcg_patch32(label_ptr[0], s->code_ptr - label_ptr[0] - 4); + tcg_patch32(s, label_ptr[0], s->code_ptr - label_ptr[0] - 4); if (TARGET_LONG_BITS > TCG_TARGET_REG_BITS) { - tcg_patch32(label_ptr[1], s->code_ptr - label_ptr[1] - 4); + tcg_patch32(s, label_ptr[1], s->code_ptr - label_ptr[1] - 4); } if (TCG_TARGET_REG_BITS == 32) {@@ -3842,9 +3842,9 @@ static void tcg_target_qemu_prologue(TCGContext *s) tcg_out_opc(s, OPC_RET, 0, 0, 0); } -static void tcg_out_nop_fill(tcg_insn_unit *p, int count) +static void tcg_out_nop_fill(TCGContext *s, tcg_insn_unit *p, int count) { - memset(p, 0x90, count); + memset(TCG_CODE_PTR_RW(s, p), 0x90, count); } static void tcg_target_init(TCGContext *s)tcg/i386/tcg-target.h +22
-2@@ -206,16 +206,36 @@ extern bool have_avx2;#define TCG_TARGET_extract_i64_valid (ofs, len) \ (((ofs) == 8 && (len) == 8) || ((ofs) + (len)) == 32) +#ifdef __APPLE__ +void sys_dcache_flush (void *start,size_t len); +#endif +static inline void flush_icache_range (uintptr_t start,uintptr_t stop) { } +#if defined(CONFIG_IOS_JIT ) +static inline void flush_dcache_range (uintptr_t start,uintptr_t stop) +{ +#if defined(__APPLE__) +sys_dcache_flush ((char *)start, stop - start); +#else +#error "Missing function to flush data cache" +#endif +} +#endif +static inline void tb_target_set_jmp_target (uintptr_t tc_ptr, -uintptr_t jmp_addr,uintptr_t addr) +uintptr_t jmp_addr,uintptr_t addr, +uintptr_t wr_addr) {/* patch the branch destination */ -qatomic_set ((int32_t *)jmp_addr, addr - (jmp_addr +4 )); +qatomic_set ((int32_t *)wr_addr, addr - (jmp_addr +4 ));/* no need to flush icache explicitly */ +#if defined(CONFIG_IOS_JIT ) +/* we do need to flush mirror dcache */ +flush_dcache_range (wr_addr, wr_addr +4 ); +#endif }/* This defines the natural memory order supported by this tcg/mips/tcg-target.c.inc +38
-26@@ -139,12 +139,13 @@ static const TCGReg tcg_target_call_oarg_regs[2] = { TCG_REG_V1 }; -static tcg_insn_unit *tb_ret_addr; -static tcg_insn_unit *bswap32_addr; -static tcg_insn_unit *bswap32u_addr; -static tcg_insn_unit *bswap64_addr; +static const tcg_insn_unit *tb_ret_addr; +static const tcg_insn_unit *bswap32_addr; +static const tcg_insn_unit *bswap32u_addr; +static const tcg_insn_unit *bswap64_addr; -static inline uint32_t reloc_pc16_val(tcg_insn_unit *pc, tcg_insn_unit *target) +static inline uint32_t reloc_pc16_val(const tcg_insn_unit *pc, + const tcg_insn_unit *target) { /* Let the compiler perform the right-shift as part of the arithmetic. */ ptrdiff_t disp = target - (pc + 1);@@ -152,28 +153,35 @@ static inline uint32_t reloc_pc16_val(tcg_insn_unit *pc, tcg_insn_unit *target) return disp & 0xffff; } -static inline void reloc_pc16(tcg_insn_unit *pc, tcg_insn_unit *target) +static inline void reloc_pc16(TCGContext *s, + tcg_insn_unit *pc, + const tcg_insn_unit *target) { - *pc = deposit32(*pc, 0, 16, reloc_pc16_val(pc, target)); + *TCG_CODE_PTR_RW(s, pc) = + deposit32(*TCG_CODE_PTR_RW(s, pc), 0, 16, reloc_pc16_val(pc, target)); } -static inline uint32_t reloc_26_val(tcg_insn_unit *pc, tcg_insn_unit *target) +static inline uint32_t reloc_26_val(const tcg_insn_unit *pc, + const tcg_insn_unit *target) { tcg_debug_assert((((uintptr_t)pc ^ (uintptr_t)target) & 0xf0000000) == 0); return ((uintptr_t)target >> 2) & 0x3ffffff; } -static inline void reloc_26(tcg_insn_unit *pc, tcg_insn_unit *target) +static inline void reloc_26(TCGContext *s, + tcg_insn_unit *pc, + const tcg_insn_unit *target) { - *pc = deposit32(*pc, 0, 26, reloc_26_val(pc, target)); + *TCG_CODE_PTR_RW(s, pc) = + deposit32(*TCG_CODE_PTR_RW(s, pc), 0, 26, reloc_26_val(pc, target)); } -static bool patch_reloc(tcg_insn_unit *code_ptr, int type, +static bool patch_reloc(TCGContext *s, tcg_insn_unit *code_ptr, int type, intptr_t value, intptr_t addend) { tcg_debug_assert(type == R_MIPS_PC16); tcg_debug_assert(addend == 0); - reloc_pc16(code_ptr, (tcg_insn_unit *)value); + reloc_pc16(s, code_ptr, (tcg_insn_unit *)value); return true; }@@ -516,7 +524,7 @@ static void tcg_out_opc_sa64(TCGContext *s, MIPSInsn opc1, MIPSInsn opc2, * Type jump. * Returns true if the branch was in range and the insn was emitted. */ -static bool tcg_out_opc_jmp(TCGContext *s, MIPSInsn opc, void *target) +static bool tcg_out_opc_jmp(TCGContext *s, MIPSInsn opc, const void *target) { uintptr_t dest = (uintptr_t)target; uintptr_t from = (uintptr_t)s->code_ptr + 4;@@ -631,7 +639,7 @@ static inline void tcg_out_bswap16s(TCGContext *s, TCGReg ret, TCGReg arg) } } -static void tcg_out_bswap_subr(TCGContext *s, tcg_insn_unit *sub) +static void tcg_out_bswap_subr(TCGContext *s, const tcg_insn_unit *sub) { bool ok = tcg_out_opc_jmp(s, OPC_JAL, sub); tcg_debug_assert(ok);@@ -925,7 +933,7 @@ static void tcg_out_brcond(TCGContext *s, TCGCond cond, TCGReg arg1, tcg_out_opc_br(s, b_opc, arg1, arg2); if (l->has_value) { - reloc_pc16(s->code_ptr - 1, l->u.value_ptr); + reloc_pc16(s, s->code_ptr - 1, l->u.value_ptr); } else { tcg_out_reloc(s, s->code_ptr - 1, R_MIPS_PC16, l, 0); }@@ -1079,7 +1087,7 @@ static void tcg_out_movcond(TCGContext *s, TCGCond cond, TCGReg ret, } } -static void tcg_out_call_int(TCGContext *s, tcg_insn_unit *arg, bool tail) +static void tcg_out_call_int(TCGContext *s, const tcg_insn_unit *arg, bool tail) { /* Note that the ABI requires the called function's address to be loaded into T9, even if a direct branch is in range. */@@ -1097,7 +1105,7 @@ static void tcg_out_call_int(TCGContext *s, tcg_insn_unit *arg, bool tail) } } -static void tcg_out_call(TCGContext *s, tcg_insn_unit *arg) +static void tcg_out_call(TCGContext *s, const tcg_insn_unit *arg) { tcg_out_call_int(s, arg, false); tcg_out_nop(s);@@ -1289,7 +1297,8 @@ static void add_qemu_ldst_label(TCGContext *s, int is_ld, TCGMemOpIdx oi, TCGType ext, TCGReg datalo, TCGReg datahi, TCGReg addrlo, TCGReg addrhi, - void *raddr, tcg_insn_unit *label_ptr[2]) + const tcg_insn_unit *raddr, + tcg_insn_unit *label_ptr[2]) { TCGLabelQemuLdst *label = new_ldst_label(s);@@ -1315,9 +1324,9 @@ static bool tcg_out_qemu_ld_slow_path(TCGContext *s, TCGLabelQemuLdst *l) int i; /* resolve label address */ - reloc_pc16(l->label_ptr[0], s->code_ptr); + reloc_pc16(s, l->label_ptr[0], s->code_ptr); if (TCG_TARGET_REG_BITS < TARGET_LONG_BITS) { - reloc_pc16(l->label_ptr[1], s->code_ptr); + reloc_pc16(s, l->label_ptr[1], s->code_ptr); } i = 1;@@ -1345,7 +1354,7 @@ static bool tcg_out_qemu_ld_slow_path(TCGContext *s, TCGLabelQemuLdst *l) } tcg_out_opc_br(s, OPC_BEQ, TCG_REG_ZERO, TCG_REG_ZERO); - reloc_pc16(s->code_ptr - 1, l->raddr); + reloc_pc16(s, s->code_ptr - 1, l->raddr); /* delay slot */ if (TCG_TARGET_REG_BITS == 64 && l->type == TCG_TYPE_I32) {@@ -1365,9 +1374,9 @@ static bool tcg_out_qemu_st_slow_path(TCGContext *s, TCGLabelQemuLdst *l) int i; /* resolve label address */ - reloc_pc16(l->label_ptr[0], s->code_ptr); + reloc_pc16(s, l->label_ptr[0], s->code_ptr); if (TCG_TARGET_REG_BITS < TARGET_LONG_BITS) { - reloc_pc16(l->label_ptr[1], s->code_ptr); + reloc_pc16(s, l->label_ptr[1], s->code_ptr); } i = 1;@@ -2430,7 +2439,7 @@ static void tcg_target_detect_isa(void) sigaction(SIGILL, &sa_old, NULL); } -static tcg_insn_unit *align_code_ptr(TCGContext *s) +static const tcg_insn_unit *align_code_ptr(TCGContext *s) { uintptr_t p = (uintptr_t)s->code_ptr; if (p & 15) {@@ -2657,9 +2666,12 @@ static void tcg_target_init(TCGContext *s) } void tb_target_set_jmp_target(uintptr_t tc_ptr, uintptr_t jmp_addr, - uintptr_t addr) + uintptr_t addr, uintptr_t wr_addr) { - qatomic_set((uint32_t *)jmp_addr, deposit32(OPC_J, 0, 26, addr >> 2)); + qatomic_set((uint32_t *)wr_addr, deposit32(OPC_J, 0, 26, addr >> 2)); +#if defined(CONFIG_IOS_JIT) + flush_dcache_range(wr_addr, wr_addr + 4); +#endif flush_icache_range(jmp_addr, jmp_addr + 4); }tcg/mips/tcg-target.h +7
-1@@ -212,7 +212,13 @@ static inline void flush_icache_range(uintptr_t start, uintptr_t stop)cacheflush ((void *)start, stop-start,ICACHE ); } -void tb_target_set_jmp_target (uintptr_t ,uintptr_t ,uintptr_t ); +void tb_target_set_jmp_target (uintptr_t ,uintptr_t ,uintptr_t ,uintptr_t ); +#if defined(CONFIG_IOS_JIT ) +static inline void flush_dcache_range (uintptr_t start,uintptr_t stop) +{ +#error "Unimplemented dcache flush function" +} +#endif #ifdef CONFIG_SOFTMMU #define TCG_TARGET_NEED_LDST_LABELS tcg/ppc/tcg-target.c.inc +35
-20@@ -62,7 +62,7 @@ #define TCG_CT_CONST_MONE 0x2000 #define TCG_CT_CONST_WSZ 0x4000 -static tcg_insn_unit *tb_ret_addr; +static const tcg_insn_unit *tb_ret_addr; TCGPowerISA have_isa; static bool have_isel;@@ -184,35 +184,43 @@ static inline bool in_range_b(tcg_target_long target) return target == sextract64(target, 0, 26); } -static uint32_t reloc_pc24_val(tcg_insn_unit *pc, tcg_insn_unit *target) +static uint32_t reloc_pc24_val(const tcg_insn_unit *pc, + const tcg_insn_unit *target) { ptrdiff_t disp = tcg_ptr_byte_diff(target, pc); tcg_debug_assert(in_range_b(disp)); return disp & 0x3fffffc; } -static bool reloc_pc24(tcg_insn_unit *pc, tcg_insn_unit *target) +static bool reloc_pc24(TCGContext *s, + tcg_insn_unit *pc, + const tcg_insn_unit *target) { ptrdiff_t disp = tcg_ptr_byte_diff(target, pc); if (in_range_b(disp)) { - *pc = (*pc & ~0x3fffffc) | (disp & 0x3fffffc); + *TCG_CODE_PTR_RW(s, pc) = + (*TCG_CODE_PTR_RW(s, pc) & ~0x3fffffc) | (disp & 0x3fffffc); return true; } return false; } -static uint16_t reloc_pc14_val(tcg_insn_unit *pc, tcg_insn_unit *target) +static uint16_t reloc_pc14_val(const tcg_insn_unit *pc, + const tcg_insn_unit *target) { ptrdiff_t disp = tcg_ptr_byte_diff(target, pc); tcg_debug_assert(disp == (int16_t) disp); return disp & 0xfffc; } -static bool reloc_pc14(tcg_insn_unit *pc, tcg_insn_unit *target) +static bool reloc_pc14(TCGContext *s, + tcg_insn_unit *pc, + const tcg_insn_unit *target) { ptrdiff_t disp = tcg_ptr_byte_diff(target, pc); if (disp == (int16_t) disp) { - *pc = (*pc & ~0xfffc) | (disp & 0xfffc); + *TCG_CODE_PTR_RW(s, pc) = + (*TCG_CODE_PTR_RW(s, pc) & ~0xfffc) | (disp & 0xfffc); return true; } return false;@@ -670,7 +678,7 @@ static const uint32_t tcg_to_isel[] = { [TCG_COND_GTU] = ISEL | BC_(7, CR_GT), }; -static bool patch_reloc(tcg_insn_unit *code_ptr, int type, +static bool patch_reloc(TCGContext *s, tcg_insn_unit *code_ptr, int type, intptr_t value, intptr_t addend) { tcg_insn_unit *target;@@ -682,9 +690,9 @@ static bool patch_reloc(tcg_insn_unit *code_ptr, int type, switch (type) { case R_PPC_REL14: - return reloc_pc14(code_ptr, target); + return reloc_pc14(s, code_ptr, target); case R_PPC_REL24: - return reloc_pc24(code_ptr, target); + return reloc_pc24(s, code_ptr, target); case R_PPC_ADDR16: /* * We are (slightly) abusing this relocation type. In particular,@@ -1106,7 +1114,7 @@ static void tcg_out_xori32(TCGContext *s, TCGReg dst, TCGReg src, uint32_t c) tcg_out_zori32(s, dst, src, c, XORI, XORIS); } -static void tcg_out_b(TCGContext *s, int mask, tcg_insn_unit *target) +static void tcg_out_b(TCGContext *s, int mask, const tcg_insn_unit *target) { ptrdiff_t disp = tcg_pcrel_diff(s, target); if (in_range_b(disp)) {@@ -1723,7 +1731,7 @@ static void tcg_out_mb(TCGContext *s, TCGArg a0) } void tb_target_set_jmp_target(uintptr_t tc_ptr, uintptr_t jmp_addr, - uintptr_t addr) + uintptr_t addr, uintptr_t wr_addr) { if (TCG_TARGET_REG_BITS == 64) { tcg_insn_unit i1, i2;@@ -1752,17 +1760,23 @@ void tb_target_set_jmp_target(uintptr_t tc_ptr, uintptr_t jmp_addr, /* As per the enclosing if, this is ppc64. Avoid the _Static_assert within qatomic_set that would fail to build a ppc32 host. */ - qatomic_set__nocheck((uint64_t *)jmp_addr, pair); + qatomic_set__nocheck((uint64_t *)wr_addr, pair); +#if defined(CONFIG_IOS_JIT) + flush_dcache_range(wr_addr, wr_addr + 8); +#endif flush_icache_range(jmp_addr, jmp_addr + 8); } else { intptr_t diff = addr - jmp_addr; tcg_debug_assert(in_range_b(diff)); - qatomic_set((uint32_t *)jmp_addr, B | (diff & 0x3fffffc)); + qatomic_set((uint32_t *)wr_addr, B | (diff & 0x3fffffc)); +#if defined(CONFIG_IOS_JIT) + flush_dcache_range(wr_addr, wr_addr + 8); +#endif flush_icache_range(jmp_addr, jmp_addr + 4); } } -static void tcg_out_call(TCGContext *s, tcg_insn_unit *target) +static void tcg_out_call(TCGContext *s, const tcg_insn_unit *target) { #ifdef _CALL_AIX /* Look through the descriptor. If the branch is in range, and we@@ -1987,7 +2001,8 @@ static TCGReg tcg_out_tlb_read(TCGContext *s, MemOp opc, static void add_qemu_ldst_label(TCGContext *s, bool is_ld, TCGMemOpIdx oi, TCGReg datalo_reg, TCGReg datahi_reg, TCGReg addrlo_reg, TCGReg addrhi_reg, - tcg_insn_unit *raddr, tcg_insn_unit *lptr) + const tcg_insn_unit *raddr, + tcg_insn_unit *lptr) { TCGLabelQemuLdst *label = new_ldst_label(s);@@ -2007,7 +2022,7 @@ static bool tcg_out_qemu_ld_slow_path(TCGContext *s, TCGLabelQemuLdst *lb) MemOp opc = get_memop(oi); TCGReg hi, lo, arg = TCG_REG_R3; - if (!reloc_pc14(lb->label_ptr[0], s->code_ptr)) { + if (!reloc_pc14(s, lb->label_ptr[0], s->code_ptr)) { return false; }@@ -2055,7 +2070,7 @@ static bool tcg_out_qemu_st_slow_path(TCGContext *s, TCGLabelQemuLdst *lb) MemOp s_bits = opc & MO_SIZE; TCGReg hi, lo, arg = TCG_REG_R3; - if (!reloc_pc14(lb->label_ptr[0], s->code_ptr)) { + if (!reloc_pc14(s, lb->label_ptr[0], s->code_ptr)) { return false; }@@ -2252,11 +2267,11 @@ static void tcg_out_qemu_st(TCGContext *s, const TCGArg *args, bool is_64) #endif } -static void tcg_out_nop_fill(tcg_insn_unit *p, int count) +static void tcg_out_nop_fill(TCGContext *s, tcg_insn_unit *p, int count) { int i; for (i = 0; i < count; ++i) { - p[i] = NOP; + (TCG_CODE_PTR_RW(s, p))[i] = NOP; } }tcg/ppc/tcg-target.h +7
-1@@ -176,7 +176,13 @@ extern bool have_vsx;#define TCG_TARGET_HAS_cmpsel_vec 0void flush_icache_range (uintptr_t start,uintptr_t stop); -void tb_target_set_jmp_target (uintptr_t ,uintptr_t ,uintptr_t ); +void tb_target_set_jmp_target (uintptr_t ,uintptr_t ,uintptr_t ,uintptr_t ); +#if defined(CONFIG_IOS_JIT ) +static inline void flush_dcache_range (uintptr_t start,uintptr_t stop) +{ +#error "Unimplemented dcache flush function" +} +#endif #define TCG_TARGET_DEFAULT_MO (0)#define TCG_TARGET_HAS_MEMORY_BSWAP 1tcg/riscv/tcg-target.c.inc +29
-22@@ -413,11 +413,11 @@ static void tcg_out_opc_jump(TCGContext *s, RISCVInsn opc, tcg_out32(s, encode_uj(opc, rd, imm)); } -static void tcg_out_nop_fill(tcg_insn_unit *p, int count) +static void tcg_out_nop_fill(TCGContext *s, tcg_insn_unit *p, int count) { int i; for (i = 0; i < count; ++i) { - p[i] = encode_i(OPC_ADDI, TCG_REG_ZERO, TCG_REG_ZERO, 0); + (TCG_CODE_PTR_RW(s, p))[i] = encode_i(OPC_ADDI, TCG_REG_ZERO, TCG_REG_ZERO, 0); } }@@ -425,46 +425,52 @@ static void tcg_out_nop_fill(tcg_insn_unit *p, int count) * Relocations */ -static bool reloc_sbimm12(tcg_insn_unit *code_ptr, tcg_insn_unit *target) +static bool reloc_sbimm12(TCGContext *s, + tcg_insn_unit *code_ptr, + const tcg_insn_unit *target) { intptr_t offset = (intptr_t)target - (intptr_t)code_ptr; if (offset == sextreg(offset, 1, 12) << 1) { - code_ptr[0] |= encode_sbimm12(offset); + (TCG_CODE_PTR_RW(s, code_ptr))[0] |= encode_sbimm12(offset); return true; } return false; } -static bool reloc_jimm20(tcg_insn_unit *code_ptr, tcg_insn_unit *target) +static bool reloc_jimm20(TCGContext *s, + tcg_insn_unit *code_ptr, + const tcg_insn_unit *target) { intptr_t offset = (intptr_t)target - (intptr_t)code_ptr; if (offset == sextreg(offset, 1, 20) << 1) { - code_ptr[0] |= encode_ujimm20(offset); + (TCG_CODE_PTR_RW(s, code_ptr))[0] |= encode_ujimm20(offset); return true; } return false; } -static bool reloc_call(tcg_insn_unit *code_ptr, tcg_insn_unit *target) +static bool reloc_call(TCGContext *s, + tcg_insn_unit *code_ptr, + const tcg_insn_unit *target) { intptr_t offset = (intptr_t)target - (intptr_t)code_ptr; int32_t lo = sextreg(offset, 0, 12); int32_t hi = offset - lo; if (offset == hi + lo) { - code_ptr[0] |= encode_uimm20(hi); - code_ptr[1] |= encode_imm12(lo); + (TCG_CODE_PTR_RW(s, code_ptr))[0] |= encode_uimm20(hi); + (TCG_CODE_PTR_RW(s, code_ptr))[1] |= encode_imm12(lo); return true; } return false; } -static bool patch_reloc(tcg_insn_unit *code_ptr, int type, +static bool patch_reloc(TCGContext *s, tcg_insn_unit *code_ptr, int type, intptr_t value, intptr_t addend) { uint32_t insn = *code_ptr;@@ -478,7 +484,7 @@ static bool patch_reloc(tcg_insn_unit *code_ptr, int type, diff = value - (uintptr_t)code_ptr; short_jmp = diff == sextreg(diff, 0, 12); if (short_jmp) { - return reloc_sbimm12(code_ptr, (tcg_insn_unit *)value); + return reloc_sbimm12(s, code_ptr, (tcg_insn_unit *)value); } else { /* Invert the condition */ insn = insn ^ (1 << 12);@@ -499,9 +505,9 @@ static bool patch_reloc(tcg_insn_unit *code_ptr, int type, } break; case R_RISCV_JAL: - return reloc_jimm20(code_ptr, (tcg_insn_unit *)value); + return reloc_jimm20(s, code_ptr, (tcg_insn_unit *)value); case R_RISCV_CALL: - return reloc_call(code_ptr, (tcg_insn_unit *)value); + return reloc_call(s, code_ptr, (tcg_insn_unit *)value); default: tcg_abort(); }@@ -557,7 +563,7 @@ static void tcg_out_movi(TCGContext *s, TCGType type, TCGReg rd, if (tmp == (int32_t)tmp) { tcg_out_opc_upper(s, OPC_AUIPC, rd, 0); tcg_out_opc_imm(s, OPC_ADDI, rd, rd, 0); - ret = reloc_call(s->code_ptr - 2, (tcg_insn_unit *)val); + ret = reloc_call(s, s->code_ptr - 2, (tcg_insn_unit *)val); tcg_debug_assert(ret == true); return; }@@ -854,14 +860,14 @@ static void tcg_out_setcond2(TCGContext *s, TCGCond cond, TCGReg ret, g_assert_not_reached(); } -static inline void tcg_out_goto(TCGContext *s, tcg_insn_unit *target) +static inline void tcg_out_goto(TCGContext *s, const tcg_insn_unit *target) { ptrdiff_t offset = tcg_pcrel_diff(s, target); tcg_debug_assert(offset == sextreg(offset, 1, 20) << 1); tcg_out_opc_jump(s, OPC_JAL, TCG_REG_ZERO, offset); } -static void tcg_out_call_int(TCGContext *s, tcg_insn_unit *arg, bool tail) +static void tcg_out_call_int(TCGContext *s, const tcg_insn_unit *arg, bool tail) { TCGReg link = tail ? TCG_REG_ZERO : TCG_REG_RA; ptrdiff_t offset = tcg_pcrel_diff(s, arg);@@ -875,7 +881,7 @@ static void tcg_out_call_int(TCGContext *s, tcg_insn_unit *arg, bool tail) /* long jump: -2147483646 to 2147483648 */ tcg_out_opc_upper(s, OPC_AUIPC, TCG_REG_TMP0, 0); tcg_out_opc_imm(s, OPC_JALR, link, TCG_REG_TMP0, 0); - ret = reloc_call(s->code_ptr - 2, arg);\ + ret = reloc_call(s, s->code_ptr - 2, arg);\ tcg_debug_assert(ret == true); } else if (TCG_TARGET_REG_BITS == 64) { /* far jump: 64-bit */@@ -888,7 +894,7 @@ static void tcg_out_call_int(TCGContext *s, tcg_insn_unit *arg, bool tail) } } -static void tcg_out_call(TCGContext *s, tcg_insn_unit *arg) +static void tcg_out_call(TCGContext *s, const tcg_insn_unit *arg) { tcg_out_call_int(s, arg, false); }@@ -1022,7 +1028,8 @@ static void add_qemu_ldst_label(TCGContext *s, int is_ld, TCGMemOpIdx oi, TCGType ext, TCGReg datalo, TCGReg datahi, TCGReg addrlo, TCGReg addrhi, - void *raddr, tcg_insn_unit **label_ptr) + const tcg_insn_unit *raddr, + tcg_insn_unit **label_ptr) { TCGLabelQemuLdst *label = new_ldst_label(s);@@ -1052,7 +1059,7 @@ static bool tcg_out_qemu_ld_slow_path(TCGContext *s, TCGLabelQemuLdst *l) } /* resolve label address */ - if (!patch_reloc(l->label_ptr[0], R_RISCV_BRANCH, + if (!patch_reloc(s, l->label_ptr[0], R_RISCV_BRANCH, (intptr_t) s->code_ptr, 0)) { return false; }@@ -1087,7 +1094,7 @@ static bool tcg_out_qemu_st_slow_path(TCGContext *s, TCGLabelQemuLdst *l) } /* resolve label address */ - if (!patch_reloc(l->label_ptr[0], R_RISCV_BRANCH, + if (!patch_reloc(s, l->label_ptr[0], R_RISCV_BRANCH, (intptr_t) s->code_ptr, 0)) { return false; }@@ -1274,7 +1281,7 @@ static void tcg_out_qemu_st(TCGContext *s, const TCGArg *args, bool is_64) #endif } -static tcg_insn_unit *tb_ret_addr; +static const tcg_insn_unit *tb_ret_addr; static void tcg_out_op(TCGContext *s, TCGOpcode opc, const TCGArg *args, const int *const_args)tcg/riscv/tcg-target.h +8
-1@@ -164,8 +164,15 @@ static inline void flush_icache_range(uintptr_t start, uintptr_t stop)__builtin___clear_cache ((char *)start, (char *)stop); } +#if defined(CONFIG_IOS_JIT ) +static inline void flush_dcache_range (uintptr_t start,uintptr_t stop) +{ +#error "Unimplemented dcache flush function" +} +#endif +/* not defined -- call should be eliminated at compile time */ -void tb_target_set_jmp_target (uintptr_t ,uintptr_t ,uintptr_t ); +void tb_target_set_jmp_target (uintptr_t ,uintptr_t ,uintptr_t ,uintptr_t );#define TCG_TARGET_DEFAULT_MO (0)tcg/s390/tcg-target.c.inc +13
-12@@ -363,10 +363,10 @@ static void * const qemu_st_helpers[16] = { }; #endif -static tcg_insn_unit *tb_ret_addr; +static const tcg_insn_unit *tb_ret_addr; uint64_t s390_facilities; -static bool patch_reloc(tcg_insn_unit *code_ptr, int type, +static bool patch_reloc(TCGContext *s, tcg_insn_unit *code_ptr, int type, intptr_t value, intptr_t addend) { intptr_t pcrel2;@@ -378,13 +378,13 @@ static bool patch_reloc(tcg_insn_unit *code_ptr, int type, switch (type) { case R_390_PC16DBL: if (pcrel2 == (int16_t)pcrel2) { - tcg_patch16(code_ptr, pcrel2); + tcg_patch16(s, code_ptr, pcrel2); return true; } break; case R_390_PC32DBL: if (pcrel2 == (int32_t)pcrel2) { - tcg_patch32(code_ptr, pcrel2); + tcg_patch32(s, code_ptr, pcrel2); return true; } break;@@ -392,7 +392,7 @@ static bool patch_reloc(tcg_insn_unit *code_ptr, int type, if (value == sextract64(value, 0, 20)) { old = *(uint32_t *)code_ptr & 0xf00000ff; old |= ((value & 0xfff) << 16) | ((value & 0xff000) >> 4); - tcg_patch32(code_ptr, old); + tcg_patch32(s, code_ptr, old); return true; } break;@@ -1302,7 +1302,7 @@ static void tgen_extract(TCGContext *s, TCGReg dest, TCGReg src, tcg_out_risbg(s, dest, src, 64 - len, 63, 64 - ofs, 1); } -static void tgen_gotoi(TCGContext *s, int cc, tcg_insn_unit *dest) +static void tgen_gotoi(TCGContext *s, int cc, const tcg_insn_unit *dest) { ptrdiff_t off = dest - s->code_ptr; if (off == (int16_t)off) {@@ -1415,7 +1415,7 @@ static void tgen_brcond(TCGContext *s, TCGType type, TCGCond c, tgen_branch(s, cc, l); } -static void tcg_out_call(TCGContext *s, tcg_insn_unit *dest) +static void tcg_out_call(TCGContext *s, const tcg_insn_unit *dest) { ptrdiff_t off = dest - s->code_ptr; if (off == (int32_t)off) {@@ -1593,7 +1593,8 @@ static TCGReg tcg_out_tlb_read(TCGContext *s, TCGReg addr_reg, MemOp opc, static void add_qemu_ldst_label(TCGContext *s, bool is_ld, TCGMemOpIdx oi, TCGReg data, TCGReg addr, - tcg_insn_unit *raddr, tcg_insn_unit *label_ptr) + const tcg_insn_unit *raddr, + tcg_insn_unit *label_ptr) { TCGLabelQemuLdst *label = new_ldst_label(s);@@ -1612,7 +1613,7 @@ static bool tcg_out_qemu_ld_slow_path(TCGContext *s, TCGLabelQemuLdst *lb) TCGMemOpIdx oi = lb->oi; MemOp opc = get_memop(oi); - if (!patch_reloc(lb->label_ptr[0], R_390_PC16DBL, + if (!patch_reloc(s, lb->label_ptr[0], R_390_PC16DBL, (intptr_t)s->code_ptr, 2)) { return false; }@@ -1637,7 +1638,7 @@ static bool tcg_out_qemu_st_slow_path(TCGContext *s, TCGLabelQemuLdst *lb) TCGMemOpIdx oi = lb->oi; MemOp opc = get_memop(oi); - if (!patch_reloc(lb->label_ptr[0], R_390_PC16DBL, + if (!patch_reloc(s, lb->label_ptr[0], R_390_PC16DBL, (intptr_t)s->code_ptr, 2)) { return false; }@@ -2575,9 +2576,9 @@ static void tcg_target_qemu_prologue(TCGContext *s) tcg_out_insn(s, RR, BCR, S390_CC_ALWAYS, TCG_REG_R14); } -static void tcg_out_nop_fill(tcg_insn_unit *p, int count) +static void tcg_out_nop_fill(TCGContext *s, tcg_insn_unit *p, int count) { - memset(p, 0x07, count * sizeof(tcg_insn_unit)); + memset(TCG_CODE_PTR_RW(s, p), 0x07, count * sizeof(tcg_insn_unit)); } typedef struct {tcg/s390/tcg-target.h +12
-1@@ -149,13 +149,24 @@ static inline void flush_icache_range(uintptr_t start, uintptr_t stop) { } +#if defined(CONFIG_IOS_JIT ) +static inline void flush_dcache_range (uintptr_t start,uintptr_t stop) +{ +#error "Unimplemented dcache flush function" +} +#endif +static inline void tb_target_set_jmp_target (uintptr_t tc_ptr, -uintptr_t jmp_addr,uintptr_t addr) +uintptr_t jmp_addr,uintptr_t addr, +uintptr_t wr_addr) {/* patch the branch destination */ intptr_t disp = addr - (jmp_addr -2 );qatomic_set ((int32_t *)jmp_addr, disp /2 );/* no need to flush icache explicitly */ +#if defined(CONFIG_IOS_JIT ) +flush_dcache_range (wr_addr, wr_addr +4 ); +#endif }#ifdef CONFIG_SOFTMMU tcg/sparc/tcg-target.c.inc +20
-13@@ -291,14 +291,14 @@ static inline int check_fit_i32(int32_t val, unsigned int bits) # define check_fit_ptr check_fit_i32 #endif -static bool patch_reloc(tcg_insn_unit *code_ptr, int type, +static bool patch_reloc(TCGContext *s, tcg_insn_unit *code_ptr, int type, intptr_t value, intptr_t addend) { uint32_t insn = *code_ptr; intptr_t pcrel; value += addend; - pcrel = tcg_ptr_byte_diff((tcg_insn_unit *)value, code_ptr); + pcrel = tcg_ptr_byte_diff((const tcg_insn_unit *)value, code_ptr); switch (type) { case R_SPARC_WDISP16:@@ -840,7 +840,7 @@ static void tcg_out_addsub2_i64(TCGContext *s, TCGReg rl, TCGReg rh, tcg_out_mov(s, TCG_TYPE_I64, rl, tmp); } -static void tcg_out_call_nodelay(TCGContext *s, tcg_insn_unit *dest, +static void tcg_out_call_nodelay(TCGContext *s, const tcg_insn_unit *dest, bool in_prologue) { ptrdiff_t disp = tcg_pcrel_diff(s, dest);@@ -855,7 +855,7 @@ static void tcg_out_call_nodelay(TCGContext *s, tcg_insn_unit *dest, } } -static void tcg_out_call(TCGContext *s, tcg_insn_unit *dest) +static void tcg_out_call(TCGContext *s, const tcg_insn_unit *dest) { tcg_out_call_nodelay(s, dest, false); tcg_out_nop(s);@@ -868,8 +868,8 @@ static void tcg_out_mb(TCGContext *s, TCGArg a0) } #ifdef CONFIG_SOFTMMU -static tcg_insn_unit *qemu_ld_trampoline[16]; -static tcg_insn_unit *qemu_st_trampoline[16]; +static const tcg_insn_unit *qemu_ld_trampoline[16]; +static const tcg_insn_unit *qemu_st_trampoline[16]; static void emit_extend(TCGContext *s, TCGReg r, int op) {@@ -1048,11 +1048,11 @@ static void tcg_target_qemu_prologue(TCGContext *s) #endif } -static void tcg_out_nop_fill(tcg_insn_unit *p, int count) +static void tcg_out_nop_fill(TCGContext *s, tcg_insn_unit *p, int count) { int i; for (i = 0; i < count; ++i) { - p[i] = NOP; + (TCG_CODE_PTR_RW(s, p))[i] = NOP; } }@@ -1163,7 +1163,7 @@ static void tcg_out_qemu_ld(TCGContext *s, TCGReg data, TCGReg addr, #ifdef CONFIG_SOFTMMU unsigned memi = get_mmuidx(oi); TCGReg addrz, param; - tcg_insn_unit *func; + const tcg_insn_unit *func; tcg_insn_unit *label_ptr; addrz = tcg_out_tlb_load(s, addr, memi, memop,@@ -1226,7 +1226,8 @@ static void tcg_out_qemu_ld(TCGContext *s, TCGReg data, TCGReg addr, } } - *label_ptr |= INSN_OFF19(tcg_ptr_byte_diff(s->code_ptr, label_ptr)); + *TCG_CODE_PTR_RW(s, label_ptr) |= + INSN_OFF19(tcg_ptr_byte_diff(s->code_ptr, label_ptr)); #else if (SPARC64 && TARGET_LONG_BITS == 32) { tcg_out_arithi(s, TCG_REG_T1, addr, 0, SHIFT_SRL);@@ -1822,7 +1823,7 @@ void tcg_register_jit(void *buf, size_t buf_size) } void tb_target_set_jmp_target(uintptr_t tc_ptr, uintptr_t jmp_addr, - uintptr_t addr) + uintptr_t addr, uintptr_t wr_addr) { intptr_t tb_disp = addr - tc_ptr; intptr_t br_disp = addr - jmp_addr;@@ -1834,8 +1835,11 @@ void tb_target_set_jmp_target(uintptr_t tc_ptr, uintptr_t jmp_addr, tcg_debug_assert(br_disp == (int32_t)br_disp); if (!USE_REG_TB) { - qatomic_set((uint32_t *)jmp_addr, + qatomic_set((uint32_t *)wr_addr, deposit32(CALL, 0, 30, br_disp >> 2)); +#if defined(CONFIG_IOS_JIT) + flush_dcache_range(wr_addr, wr_addr + 4); +#endif flush_icache_range(jmp_addr, jmp_addr + 4); return; }@@ -1859,6 +1863,9 @@ void tb_target_set_jmp_target(uintptr_t tc_ptr, uintptr_t jmp_addr, | INSN_IMM13((tb_disp & 0x3ff) | -0x400)); } - qatomic_set((uint64_t *)jmp_addr, deposit64(i2, 32, 32, i1)); + qatomic_set((uint64_t *)wr_addr, deposit64(i2, 32, 32, i1)); +#if defined(CONFIG_IOS_JIT) + flush_dcache_range(wr_addr, wr_addr + 8); +#endif flush_icache_range(jmp_addr, jmp_addr + 8); }tcg/sparc/tcg-target.h +7
-1@@ -176,7 +176,13 @@ static inline void flush_icache_range(uintptr_t start, uintptr_t stop) } } -void tb_target_set_jmp_target (uintptr_t ,uintptr_t ,uintptr_t ); +void tb_target_set_jmp_target (uintptr_t ,uintptr_t ,uintptr_t ,uintptr_t ); +#if defined(CONFIG_IOS_JIT ) +static inline void flush_dcache_range (uintptr_t start,uintptr_t stop) +{ +#error "Unimplemented dcache flush function" +} +#endif #define TCG_TARGET_NEED_POOL_LABELS tcg/tcg-ldst.c.inc +1
-1@@ -28,7 +28,7 @@ typedef struct TCGLabelQemuLdst { TCGReg addrhi_reg; /* reg index for high word of guest virtual addr */ TCGReg datalo_reg; /* reg index for low word to be loaded or stored */ TCGReg datahi_reg; /* reg index for high word to be loaded or stored */ - tcg_insn_unit *raddr; /* gen code addr of the next IR of qemu_ld/st IR */ + const tcg_insn_unit *raddr; /* gen code addr of the next IR of qemu_ld/st */ tcg_insn_unit *label_ptr[2]; /* label pointers to be updated */ QSIMPLEQ_ENTRY(TCGLabelQemuLdst) next; } TCGLabelQemuLdst;tcg/tcg-pool.c.inc +5
-4@@ -119,7 +119,7 @@ static inline void new_pool_l8(TCGContext *s, int rtype, tcg_insn_unit *label, } /* To be provided by cpu/tcg-target.c.inc. */ -static void tcg_out_nop_fill(tcg_insn_unit *p, int count); +static void tcg_out_nop_fill(TCGContext *s, tcg_insn_unit *p, int count); static int tcg_out_pool_finalize(TCGContext *s) {@@ -135,7 +135,7 @@ static int tcg_out_pool_finalize(TCGContext *s) again when allocating the next TranslationBlock structure. */ a = (void *)ROUND_UP((uintptr_t)s->code_ptr, sizeof(tcg_target_ulong) * p->nlong); - tcg_out_nop_fill(s->code_ptr, (tcg_insn_unit *)a - s->code_ptr); + tcg_out_nop_fill(s, s->code_ptr, (tcg_insn_unit *)a - s->code_ptr); s->data_gen_ptr = a; for (; p != NULL; p = p->next) {@@ -144,11 +144,12 @@ static int tcg_out_pool_finalize(TCGContext *s) if (unlikely(a > s->code_gen_highwater)) { return -1; } - memcpy(a, p->data, size); + memcpy(TCG_CODE_PTR_RW(s, a), p->data, size); a += size; l = p; } - if (!patch_reloc(p->label, p->rtype, (intptr_t)a - size, p->addend)) { + if (!patch_reloc(s, p->label, p->rtype, + (intptr_t)a - size, p->addend)) { return -2; } }tcg/tcg.c +39
-21@@ -70,7 +70,7 @@static void tcg_target_init (TCGContext *s);static const TCGTargetOpDef *tcg_target_op_def (TCGOpcode );static void tcg_target_qemu_prologue (TCGContext *s); -static bool patch_reloc (tcg_insn_unit *code_ptr,int type, +static bool patch_reloc (TCGContext *s,tcg_insn_unit *code_ptr,int type,intptr_t value,intptr_t addend);/* The CIE and FDE header definitions will be common to all hosts. */ @@ -148,7 +148,7 @@ static void tcg_out_st(TCGContext *s, TCGType type, TCGReg arg, TCGReg arg1, intptr_t arg2);static bool tcg_out_sti (TCGContext *s,TCGType type,TCGArg val,TCGReg base,intptr_t ofs); -static void tcg_out_call (TCGContext *s,tcg_insn_unit *target); +static void tcg_out_call (TCGContext *s,const tcg_insn_unit *target);static int tcg_target_const_match (tcg_target_long val,TCGType type,const TCGArgConstraint *arg_ct);#ifdef TCG_TARGET_NEED_LDST_LABELS @@ -203,13 +203,15 @@ static TCGRegSet tcg_target_call_clobber_regs;#if TCG_TARGET_INSN_UNIT_SIZE ==1 static __attribute__((unused))inline void tcg_out8 (TCGContext *s,uint8_t v) { - *s->code_ptr++ = v; + *TCG_CODE_PTR_RW (s, s->code_ptr) = v; + s->code_ptr++; } -static __attribute__((unused))inline void tcg_patch8 (tcg_insn_unit *p, +static __attribute__((unused))inline void tcg_patch8 (TCGContext *s, +tcg_insn_unit *p,uint8_t v) { - *p = v; + *TCG_CODE_PTR_RW (s, p) = v; }#endif @@ -217,21 +219,23 @@ static __attribute__((unused)) inline void tcg_patch8(tcg_insn_unit *p,static __attribute__((unused))inline void tcg_out16 (TCGContext *s,uint16_t v) {if (TCG_TARGET_INSN_UNIT_SIZE ==2 ) { - *s->code_ptr++ = v; + *TCG_CODE_PTR_RW (s, s->code_ptr) = v; + s->code_ptr++; }else {tcg_insn_unit *p = s->code_ptr; -memcpy (p, &v,sizeof (v)); +memcpy (TCG_CODE_PTR_RW (s, p), &v,sizeof (v)); s->code_ptr = p + (2 /TCG_TARGET_INSN_UNIT_SIZE ); } } -static __attribute__((unused))inline void tcg_patch16 (tcg_insn_unit *p, +static __attribute__((unused))inline void tcg_patch16 (TCGContext *s, +tcg_insn_unit *p,uint16_t v) {if (TCG_TARGET_INSN_UNIT_SIZE ==2 ) { - *p = v; + *TCG_CODE_PTR_RW (s, p) = v; }else { -memcpy (p, &v,sizeof (v)); +memcpy (TCG_CODE_PTR_RW (s, p), &v,sizeof (v)); } }#endif @@ -240,21 +244,23 @@ static __attribute__((unused)) inline void tcg_patch16(tcg_insn_unit *p,static __attribute__((unused))inline void tcg_out32 (TCGContext *s,uint32_t v) {if (TCG_TARGET_INSN_UNIT_SIZE ==4 ) { - *s->code_ptr++ = v; + *TCG_CODE_PTR_RW (s, s->code_ptr) = v; + s->code_ptr++; }else {tcg_insn_unit *p = s->code_ptr; -memcpy (p, &v,sizeof (v)); +memcpy (TCG_CODE_PTR_RW (s, p), &v,sizeof (v)); s->code_ptr = p + (4 /TCG_TARGET_INSN_UNIT_SIZE ); } } -static __attribute__((unused))inline void tcg_patch32 (tcg_insn_unit *p, +static __attribute__((unused))inline void tcg_patch32 (TCGContext *s, +tcg_insn_unit *p,uint32_t v) {if (TCG_TARGET_INSN_UNIT_SIZE ==4 ) { *p = v; }else { -memcpy (p, &v,sizeof (v)); +memcpy (TCG_CODE_PTR_RW (s, p), &v,sizeof (v)); } }#endif @@ -263,21 +269,23 @@ static __attribute__((unused)) inline void tcg_patch32(tcg_insn_unit *p,static __attribute__((unused))inline void tcg_out64 (TCGContext *s,uint64_t v) {if (TCG_TARGET_INSN_UNIT_SIZE ==8 ) { - *s->code_ptr++ = v; + *TCG_CODE_PTR_RW (s, s->code_ptr) = v; + s->code_ptr++; }else {tcg_insn_unit *p = s->code_ptr; -memcpy (p, &v,sizeof (v)); +memcpy (TCG_CODE_PTR_RW (s, p), &v,sizeof (v)); s->code_ptr = p + (8 /TCG_TARGET_INSN_UNIT_SIZE ); } } -static __attribute__((unused))inline void tcg_patch64 (tcg_insn_unit *p, +static __attribute__((unused))inline void tcg_patch64 (TCGContext *s, +tcg_insn_unit *p,uint64_t v) {if (TCG_TARGET_INSN_UNIT_SIZE ==8 ) { *p = v; }else { -memcpy (p, &v,sizeof (v)); +memcpy (TCG_CODE_PTR_RW (s, p), &v,sizeof (v)); } }#endif @@ -295,7 +303,7 @@ static void tcg_out_reloc(TCGContext *s, tcg_insn_unit *code_ptr, int type,QSIMPLEQ_INSERT_TAIL (&l->relocs, r, next); } -static void tcg_out_label (TCGContext *s,TCGLabel *l,tcg_insn_unit *ptr) +static void tcg_out_label (TCGContext *s,TCGLabel *l,const tcg_insn_unit *ptr) {tcg_debug_assert (!l->has_value); l->has_value =1 ;@@ -325,7 +333,7 @@ static bool tcg_resolve_relocs(TCGContext *s)uintptr_t value = l->u.value; QSIMPLEQ_FOREACH(r, &l->relocs, next) { -if (!patch_reloc (r->ptr, r->type, value, r->addend)) { +if (!patch_reloc (s, r->ptr, r->type, value, r->addend)) {return false; } }@@ -1039,7 +1047,7 @@ TranslationBlock *tcg_tb_alloc(TCGContext *s) }qatomic_set (&s->code_gen_ptr, next); s->data_gen_ptr =NULL ; -return tb; +return (TranslationBlock *)TCG_CODE_PTR_RW (s, tb); }void tcg_prologue_init (TCGContext *s)@@ -1076,6 +1084,10 @@ void tcg_prologue_init(TCGContext *s)#endif buf1 = s->code_ptr; +#if defined(CONFIG_IOS_JIT ) +flush_dcache_range ((uintptr_t )TCG_CODE_PTR_RW (s, buf0), + (uintptr_t )TCG_CODE_PTR_RW (s, buf1)); +#endif flush_icache_range ((uintptr_t )buf0, (uintptr_t )buf1);/* Deduct the prologue from the buffer. */ @@ -4267,6 +4279,12 @@ int tcg_gen_code(TCGContext *s, TranslationBlock *tb)return -2 ; } +#if defined(CONFIG_IOS_JIT ) +/* flush data cache on mirror */ +flush_dcache_range ((uintptr_t )TCG_CODE_PTR_RW (s, s->code_buf), + (uintptr_t )TCG_CODE_PTR_RW (s, s->code_ptr)); +#endif +/* flush instruction cache */ flush_icache_range ((uintptr_t )s->code_buf, (uintptr_t )s->code_ptr);tcg/tci/tcg-target.c.inc +4
-4@@ -369,7 +369,7 @@ static const char *const tcg_target_reg_names[TCG_TARGET_NB_REGS] = { }; #endif -static bool patch_reloc(tcg_insn_unit *code_ptr, int type, +static bool patch_reloc(TCGContext *s, tcg_insn_unit *code_ptr, int type, intptr_t value, intptr_t addend) { /* tcg_out_reloc always uses the same type, addend. */@@ -377,9 +377,9 @@ static bool patch_reloc(tcg_insn_unit *code_ptr, int type, tcg_debug_assert(addend == 0); tcg_debug_assert(value != 0); if (TCG_TARGET_REG_BITS == 32) { - tcg_patch32(code_ptr, value); + tcg_patch32(s, code_ptr, value); } else { - tcg_patch64(code_ptr, value); + tcg_patch64(s, code_ptr, value); } return true; }@@ -545,7 +545,7 @@ static void tcg_out_movi(TCGContext *s, TCGType type, old_code_ptr[1] = s->code_ptr - old_code_ptr; } -static inline void tcg_out_call(TCGContext *s, tcg_insn_unit *arg) +static inline void tcg_out_call(TCGContext *s, const tcg_insn_unit *arg) { uint8_t *old_code_ptr = s->code_ptr; tcg_out_op_t(s, INDEX_op_call);tcg/tci/tcg-target.h +8
-1@@ -195,6 +195,12 @@ static inline void flush_icache_range(uintptr_t start, uintptr_t stop) { } +#if defined(CONFIG_IOS_JIT ) +static inline void flush_dcache_range (uintptr_t start,uintptr_t stop) +{ +} +#endif +/* We could notice __i386__ or __s390x__ and reduce the barriers depending on the host. But if you want performance, you use the normal backend. We prefer consistency across hosts on this. */ @@ -203,7 +209,8 @@ static inline void flush_icache_range(uintptr_t start, uintptr_t stop)#define TCG_TARGET_HAS_MEMORY_BSWAP 1static inline void tb_target_set_jmp_target (uintptr_t tc_ptr, -uintptr_t jmp_addr,uintptr_t addr) +uintptr_t jmp_addr,uintptr_t addr, +uintptr_t wr_addr) {/* patch the branch destination */ qatomic_set ((int32_t *)jmp_addr, addr - (jmp_addr +4 ));
Re: [PATCH 07/10] tcg: implement bulletproof JIT
Quoted 12 lines · Joelle van Dyne
Quoted 12 lines
Quoted 11 lines
static int
encode_search(TranslationBlock *tb, uint8_t *block){accel/tcg/translate-all.c +5
-2-uint8_t *highwater = tcg_ctx->code_gen_highwater; -uint8_t *p = block; +uint8_t *highwater; +uint8_t *p;int i, j, n; + highwater = (uint8_t *)TCG_CODE_PTR_RW (tcg_ctx, + tcg_ctx->code_gen_highwater); + p = (uint8_t *)TCG_CODE_PTR_RW (tcg_ctx, block);
Quoted 6 lines
Quoted 3 lines
Why do you need explicit casts here? Can this be avoided by using appropriate type or within the macro (I haven't checked this at all just dislike casts as they can hide problems otherwise caught by the compiler).
There's the choice between
tcg_insn_unit* anduint8_t*. Since it's used much more widely intcg-target.inc.c, it seemed liketcg_insn_unit* was a better choice.
False choice. This is why tcg_ctx->code_gen_highwater is void*.
Quoted 3 lines
Quoted 3 lines
include/tcg/tcg.h struct TCGContext { · line 685
Quoted 3 lines
include/tcg/tcg.h +3
-0+#if defined(CONFIG_IOS_JIT ) +# define TCG_CODE_PTR_RW (s, code_ptr) \ + (tcg_insn_unit *)((uintptr_t)(code_ptr) + (s)->code_rw_mirror_diff)
Better as
static inline void *tcg_code_ptr_rw(TCGContext *s, void *rx) {
#ifdef CONFIG_IOS_JIT
return rx + s->code_rw_mirror_diff;
#else
return rx;#endif
}
r~
Re: [PATCH 07/10] tcg: implement bulletproof JIT
Quoted 28 lines · Richard Henderson
Quoted 12 lines · Joelle van Dyne
Quoted 12 lines
Quoted 11 lines
static int
encode_search(TranslationBlock *tb, uint8_t *block){accel/tcg/translate-all.c +5
-2-uint8_t *highwater = tcg_ctx->code_gen_highwater; -uint8_t *p = block; +uint8_t *highwater; +uint8_t *p;int i, j, n; + highwater = (uint8_t *)TCG_CODE_PTR_RW (tcg_ctx, + tcg_ctx->code_gen_highwater); + p = (uint8_t *)TCG_CODE_PTR_RW (tcg_ctx, block);Quoted 6 lines
Quoted 3 lines
Why do you need explicit casts here? Can this be avoided by using appropriate type or within the macro (I haven't checked this at all just dislike casts as they can hide problems otherwise caught by the compiler).
There's the choice between
tcg_insn_unit* anduint8_t*. Since it's used much more widely intcg-target.inc.c, it seemed liketcg_insn_unit* was a better choice.False choice. This is why
tcg_ctx->code_gen_highwateris void*.Quoted 3 lines
Quoted 3 lines
include/tcg/tcg.h struct TCGContext { · line 685
Quoted 3 lines
include/tcg/tcg.h +3
-0+#if defined(CONFIG_IOS_JIT ) +# define TCG_CODE_PTR_RW (s, code_ptr) \ + (tcg_insn_unit *)((uintptr_t)(code_ptr) + (s)->code_rw_mirror_diff)Better as
Quoted 4 lines
static inline void *tcg_code_ptr_rw(TCGContext *s, void *rx) {
#ifdef CONFIG_IOS_JIT return rx + s->code_rw_mirror_diff;
This looks better but can you add to void *? I think some compilers may complain about that so may need to cast here to uint8_t * then back to void * but that's at least within this func or maybe declare rx as uint_t * and return void *? Or is rx promoted to the type of s->code_rw_mirror_diff and that avoids the warning? If the gcc and clang versions we care about don't mind then it's simpler without a cast as you suggest.
Regards,
BALATON Zoltan
Quoted 9 lines
#else return rx;#endif
}r~
Re: [PATCH 07/10] tcg: implement bulletproof JIT
Quoted 7 lines · BALATON Zoltan
Quoted 4 lines
static inline void *tcg_code_ptr_rw(TCGContext *s, void *rx) {
#ifdefCONFIG_IOS_JIT
return rx +s->code_rw_mirror_diff;This looks better but can you add to void *? I think some compilers may complain about that so may need to cast here to
uint8_t* then back to void *
We already rely on void* arithmetic all over the code base.
r~
Re: [PATCH 07/10] tcg: implement bulletproof JIT
In reply to Richard HendersonMuch of the code that uses the macro is like the following (from aarch64/tcg-include.inc.c)
*TCG_CODE_PTR_RW(s, code_ptr) =
deposit32(*TCG_CODE_PTR_RW(s, code_ptr), 0, 26, offset);Before the change, it was just *code_ptr. I'm saying the alternative was to have to write "tcg_insn_unit *rw_code_ptr = (tcg_insn_unit *)TCG_CODE_PTR_RW(s, code_ptr)" everywhere or else inline cast it. Whereas making it return tcg_insn_unit * means only three instances of casting to uint8_t *. Using void * means casting at every instance.
Not opposed to using an inline function over a macro but "inline" is not ANSI C. Not sure what this project thinks about that considering the style checker prohibits C99 style comments. Personally I don't care much.
-j
Quoted 40 lines · Richard Henderson
Quoted 12 lines · Joelle van Dyne
Quoted 12 lines
Quoted 11 lines
static int
encode_search(TranslationBlock *tb, uint8_t *block){accel/tcg/translate-all.c +5
-2-uint8_t *highwater = tcg_ctx->code_gen_highwater; -uint8_t *p = block; +uint8_t *highwater; +uint8_t *p;int i, j, n; + highwater = (uint8_t *)TCG_CODE_PTR_RW (tcg_ctx, + tcg_ctx->code_gen_highwater); + p = (uint8_t *)TCG_CODE_PTR_RW (tcg_ctx, block);Quoted 6 lines
Quoted 3 lines
Why do you need explicit casts here? Can this be avoided by using appropriate type or within the macro (I haven't checked this at all just dislike casts as they can hide problems otherwise caught by the compiler).
There's the choice between
tcg_insn_unit* anduint8_t*. Since it's used much more widely intcg-target.inc.c, it seemed liketcg_insn_unit* was a better choice.False choice. This is why
tcg_ctx->code_gen_highwateris void*.Quoted 3 lines
Quoted 3 lines
include/tcg/tcg.h struct TCGContext { · line 685
Quoted 3 lines
include/tcg/tcg.h +3
-0+#if defined(CONFIG_IOS_JIT ) +# define TCG_CODE_PTR_RW (s, code_ptr) \ + (tcg_insn_unit *)((uintptr_t)(code_ptr) + (s)->code_rw_mirror_diff)Better as
static inline void *tcg_code_ptr_rw(TCGContext *s, void *rx) {
#ifdef CONFIG_IOS_JIT return rx + s->code_rw_mirror_diff; #else return rx;#endif
}r~
Re: [PATCH 07/10] tcg: implement bulletproof JIT
Quoted 11 lines · Joelle van Dyne
Much of the code that uses the macro is like the following (from
aarch64/tcg-include.inc.c)*TCG_CODE_PTR_RW(s, code_ptr) = deposit32(*TCG_CODE_PTR_RW(s, code_ptr), 0, 26, offset);Before the change, it was just
*code_ptr. I'm saying the alternative was to have to write "tcg_insn_unit*rw_code_ptr= (tcg_insn_unit*)TCG_CODE_PTR_RW(s,code_ptr)" everywhere or else inline cast it. Whereas making it returntcg_insn_unit* means only three instances of casting touint8_t*. Using void * means casting at every instance.
It's not C++ so void * does not need to be cast when assigned to some other pointer.
Quoted 4 lines
Not opposed to using an inline function over a macro but "inline" is not ANSI C. Not sure what this project thinks about that considering the style checker prohibits C99 style comments. Personally I don't care much.
QEMU has some compiler dependencies, I think only some recent versions of gcc and clang are supported and static inline is used elsewhere in the code. Richard is an expert on TCG so you can take his advice.
Regards,
BALATON Zoltan
Quoted 47 lines
-j
Quoted 40 lines · Richard Henderson
Quoted 12 lines · Joelle van Dyne
Quoted 12 lines
Quoted 11 lines
static int
encode_search(TranslationBlock *tb, uint8_t *block){accel/tcg/translate-all.c +5
-2-uint8_t *highwater = tcg_ctx->code_gen_highwater; -uint8_t *p = block; +uint8_t *highwater; +uint8_t *p;int i, j, n; + highwater = (uint8_t *)TCG_CODE_PTR_RW (tcg_ctx, + tcg_ctx->code_gen_highwater); + p = (uint8_t *)TCG_CODE_PTR_RW (tcg_ctx, block);Quoted 6 lines
Quoted 3 lines
Why do you need explicit casts here? Can this be avoided by using appropriate type or within the macro (I haven't checked this at all just dislike casts as they can hide problems otherwise caught by the compiler).
There's the choice between
tcg_insn_unit* anduint8_t*. Since it's used much more widely intcg-target.inc.c, it seemed liketcg_insn_unit* was a better choice.False choice. This is why
tcg_ctx->code_gen_highwateris void*.Quoted 3 lines
Quoted 3 lines
include/tcg/tcg.h struct TCGContext { · line 685
Quoted 3 lines
include/tcg/tcg.h +3
-0+#if defined(CONFIG_IOS_JIT ) +# define TCG_CODE_PTR_RW (s, code_ptr) \ + (tcg_insn_unit *)((uintptr_t)(code_ptr) + (s)->code_rw_mirror_diff)Better as
static inline void *tcg_code_ptr_rw(TCGContext *s, void *rx) {
#ifdef CONFIG_IOS_JIT return rx + s->code_rw_mirror_diff; #else return rx;#endif
}r~
Re: [PATCH 07/10] tcg: implement bulletproof JIT
In reply to Joelle van DyneQuoted 11 lines · Joelle van Dyne
Much of the code that uses the macro is like the following (from
aarch64/tcg-include.inc.c)*TCG_CODE_PTR_RW(s, code_ptr) = deposit32(*TCG_CODE_PTR_RW(s, code_ptr), 0, 26, offset);Before the change, it was just
*code_ptr. I'm saying the alternative was to have to write "tcg_insn_unit*rw_code_ptr= (tcg_insn_unit*)TCG_CODE_PTR_RW(s,code_ptr)" everywhere or else inline cast it. Whereas making it returntcg_insn_unit* means only three instances of casting touint8_t*. Using void * means casting at every instance.
I should have done more than skim, I suppose.
Well, without going back to look, how many of these are there, really? Virtually all of the writes should be via tcg_out32().
If there's < 5 of the above per tcg/foo/ -- particularly if they're all restricted to relocations as in the above -- then I'm ok with local variable assignment to "rw_ptr". Especially since the replacement isn't exactly small, and you're having to split to two separate lines anyway.
I'll have a real look when you've split this into parts, because otherwise it's just too big.
r~
Re: [PATCH 07/10] tcg: implement bulletproof JIT
There's about 40 instances of *code_ptr or code_ptr[i] changed to TCG_CODE_PTR_RW(s, code_ptr). It's around 2 instances per function, so if I go with a local variable, that would be ~20 extra LOC.
Another alternative is two separate functions: tcg_code_ptr_insn_rw() which returns tcg_insn_unit * and tcg_code_ptr_rw() which returns void *. I'll go that route unless there's any objections?
-j
Quoted 29 lines · Richard Henderson
Quoted 11 lines · Joelle van Dyne
Much of the code that uses the macro is like the following (from
aarch64/tcg-include.inc.c)*TCG_CODE_PTR_RW(s, code_ptr) = deposit32(*TCG_CODE_PTR_RW(s, code_ptr), 0, 26, offset);Before the change, it was just
*code_ptr. I'm saying the alternative was to have to write "tcg_insn_unit*rw_code_ptr= (tcg_insn_unit*)TCG_CODE_PTR_RW(s,code_ptr)" everywhere or else inline cast it. Whereas making it returntcg_insn_unit* means only three instances of casting touint8_t*. Using void * means casting at every instance.I should have done more than skim, I suppose.
Well, without going back to look, how many of these are there, really? Virtually all of the writes should be via
tcg_out32().If there's < 5 of the above per tcg/foo/ -- particularly if they're all restricted to relocations as in the above -- then I'm ok with local variable assignment to "
rw_ptr". Especially since the replacement isn't exactly small, and you're having to split to two separate lines anyway.I'll have a real look when you've split this into parts, because otherwise it's just too big.
r~
PATCH 8/10 tcg: mirror mapping RWX pages for iOS optional
In reply to Joelle van DyneFrom: osy <[email protected]>
This allows jailbroken devices with entitlements to switch the option off.
--- accel/tcg/tcg-all.c | 27 +++++++++++++++++- accel/tcg/translate-all.c | 60 +++++++++++++++++++++++++-------------- bsd-user/main.c | 2 +- include/sysemu/tcg.h | 2 +- linux-user/main.c | 2 +- qemu-options.hx | 11 +++++++ 6 files changed, 79 insertions(+), 25 deletions(-)
accel/tcg/tcg-all.c +26 -1
@@ -39,6 +39,7 @@ struct TCGState {bool mttcg_enabled;unsigned long tb_size; +bool mirror_rwx; };typedef struct TCGState TCGState ;
@@ -94,6 +95,7 @@ static void tcg_accel_instance_init(Object *obj)TCGState *s =TCG_STATE (obj); s->mttcg_enabled =default_mttcg_enabled (); + s->mirror_rwx = false; }bool mttcg_enabled;
@@ -102,7 +104,7 @@ static int tcg_init(MachineState *ms) {TCGState *s =TCG_STATE (current_accel ()); -tcg_exec_init (s->tb_size *1024 *1024 ); +tcg_exec_init (s->tb_size *1024 *1024 , s->mirror_rwx); mttcg_enabled = s->mttcg_enabled;cpus_register_accel (&tcg_cpus);
@@ -168,6 +170,22 @@ static void tcg_set_tb_size(Object *obj, Visitor *v, s->tb_size = value; } +#ifdef CONFIG_IOS_JIT +static bool tcg_get_mirror_rwx (Object *obj,Error **errp) +{ +TCGState *s =TCG_STATE (obj); + +return s->mirror_rwx; +} + +static void tcg_set_mirror_rwx (Object *obj,bool value,Error **errp) +{ +TCGState *s =TCG_STATE (obj); + + s->mirror_rwx = value; +} +#endif +static void tcg_accel_class_init (ObjectClass *oc,void *data) {AccelClass *ac =ACCEL_CLASS (oc);
@@ -185,6 +203,13 @@ static void tcg_accel_class_init(ObjectClass *oc, void *data)object_class_property_set_description (oc,"tb-size" ,"TCG translation block cache size" ); +#ifdef CONFIG_IOS_JIT +object_class_property_add_bool (oc,"mirror-rwx" , + tcg_get_mirror_rwx, tcg_set_mirror_rwx); +object_class_property_set_description (oc,"mirror-rwx" , +"mirror map executable pages for TCG on iOS" ); +#endif + }static const TypeInfo tcg_accel_type = {
accel/tcg/translate-all.c +39 -21
114 lines not on this page · raw message
bsd-user/main.c +1 -1
@@ -910,7 +910,7 @@ int main(int argc, char **argv) }/* init tcg before creating CPUs and to get qemu_host_page_size */ -tcg_exec_init (0 ); +tcg_exec_init (0 , false); cpu_type =parse_cpu_option (cpu_model); cpu =cpu_create (cpu_type);
include/sysemu/tcg.h +1 -1
@@ -8,7 +8,7 @@#ifndef SYSEMU_TCG_H #define SYSEMU_TCG_H -void tcg_exec_init (unsigned long tb_size); +void tcg_exec_init (unsigned long tb_size,bool mirror_rwx);#ifdef CONFIG_TCG extern bool tcg_allowed;#define tcg_enabled () (tcg_allowed)
linux-user/main.c +1 -1
@@ -705,7 +705,7 @@ int main(int argc, char **argv, char **envp) cpu_type =parse_cpu_option (cpu_model);/* init tcg before creating CPUs and to get qemu_host_page_size */ -tcg_exec_init (0 ); +tcg_exec_init (0 , false); cpu =cpu_create (cpu_type); env = cpu->env_ptr;
qemu-options.hx +11 -0
@@ -123,6 +123,9 @@ DEF("accel", HAS_ARG, QEMU_OPTION_accel, " igd-passthru=on|off (enable Xen integrated Intel graphics passthrough, default=off)\n" " kernel-irqchip=on|off|split controls accelerated irqchip support (default=on)\n" " kvm-shadow-mem=size of KVM shadow MMU in bytes\n" +#ifdef CONFIG_IOS_JIT + " mirror-rwx=on|off (mirror map executable pages for TCG on iOS)\n" +#endif " tb-size=n (TCG translation block cache size)\n" " thread=single|multi (enable multi-threaded TCG)\n", QEMU_ARCH_ALL) SRST
@@ -148,6 +151,14 @@ SRST ``kvm-shadow-mem=size`` Defines the size of the KVM shadow MMU. +#ifdef CONFIG_IOS_JIT + + ``mirror-rwx=on|off`` + Only applicable to TCG running on iOS hosts. When enabled, TB code + is written to a mirror mapped address separate from the address that is + executed. By default, this is disabled. +#endif + ``tb-size=n`` Controls the size (in MiB) of the TCG translation block cache.
Signature · 1 line
2.24.3 (Apple Git-128)
Re: [PATCH 08/10] tcg: mirror mapping RWX pages for iOS optional
Quoted 6 lines · Joelle van Dyne
From: osy <[email protected]>
This allows jailbroken devices with entitlements to switch the option off.
Signed-off-by Joelle van Dyne <[email protected]>---
What is the advantage in doing so?
Paolo
Re: [PATCH 08/10] tcg: mirror mapping RWX pages for iOS optional
There is a slight performance penalty for using "bulletproof JIT". Since that is not required if you have the proper entitlements (only if you're Apple or jailbroken on iOS; available to regular developers on Apple Silicon macOS), we want the flexibility to disable it.
-j
Quoted 13 lines · Paolo Bonzini
Quoted 6 lines · Joelle van Dyne
From: osy <[email protected]>
This allows jailbroken devices with entitlements to switch the option off.
Signed-off-by Joelle van Dyne <[email protected]>---
What is the advantage in doing so?
Paolo
PATCH 9/10 tcg: support JIT on Apple Silicon
In reply to Joelle van DyneFrom: osy <[email protected]>
For < iOS 14, reverse engineered functions from libsystem_pthread.dylib is implemented to handle APRR supported SoCs.
The following rules apply for JIT write protect:
* JIT write-protect is enabled before tcg_qemu_tb_exec()
* JIT write-protect is disabled after tcg_qemu_tb_exec() returns
* JIT write-protect is disabled inside do_tb_phys_invalidate() but if it is called inside of tcg_qemu_tb_exec() then write-protect will be enabled again before returning.
* JIT write-protect is disabled by cpu_loop_exit() for interrupt handling.
* JIT write-protect is disabled everywhere else.
--- accel/tcg/cpu-exec-common.c | 2 + accel/tcg/cpu-exec.c | 2 + accel/tcg/translate-all.c | 51 ++++++++++++++++++++++ configure | 20 +++++++++ include/exec/exec-all.h | 2 + include/tcg/tcg-apple-jit.h | 85 +++++++++++++++++++++++++++++++++++++ include/tcg/tcg.h | 3 ++ tcg/tcg.c | 4 ++ 8 files changed, 169 insertions(+) create mode 100644 include/tcg/tcg-apple-jit.h
accel/tcg/cpu-exec-common.c +2 -0
@@ -64,6 +64,8 @@ void cpu_reloading_memory_map(void)void cpu_loop_exit (CPUState *cpu) { +/* Unlock JIT write protect if applicable. */ +tb_exec_unlock ();/* Undo the setting in cpu_tb_exec. */ cpu->can_do_io =1 ;siglongjmp (cpu->jmp_env,1 );
accel/tcg/cpu-exec.c +2 -0
@@ -175,7 +175,9 @@ static inline tcg_target_ulong cpu_tb_exec(CPUState *cpu, TranslationBlock *itb) }#endif /* DEBUG_DISAS */ +tb_exec_lock (); ret =tcg_qemu_tb_exec (env, tb_ptr); +tb_exec_unlock (); cpu->can_do_io =1 ; last_tb = (TranslationBlock *)(ret & ~TB_EXIT_MASK ); tb_exit = ret &TB_EXIT_MASK ;
accel/tcg/translate-all.c +51 -0
92 lines not on this page · raw message
configure +20 -0
@@ -5874,6 +5874,22 @@ but not implemented on your system" fi fi +########################################## +# check for Apple Silicon JIT function + +if [ "$darwin" = "yes" ] ; then + cat > $TMPC << EOF +#include <pthread.h> +int main() { pthread_jit_write_protect_np(0); return 0; } +EOF + if ! compile_prog ""; then + have_pthread_jit_protect='no' + else + have_pthread_jit_protect='yes' + fi +fi + + ########################################## # End of CC checks # After here, no more $cc or $ld runs
@@ -6994,6 +7010,10 @@ if test "$secret_keyring" = "yes" ; then echo "CONFIG_SECRET_KEYRING=y" >> $config_host_mak fi +if test "$have_pthread_jit_protect" = "yes" ; then + echo "HAVE_PTHREAD_JIT_PROTECT=y" >> $config_host_mak +fi + if test "$tcg_interpreter" = "yes"; then QEMU_INCLUDES="-iquote ${source_path}/tcg/tci $QEMU_INCLUDES" elif test "$ARCH" = "sparc64" ; then
include/exec/exec-all.h +2 -0
@@ -521,6 +521,8 @@ TranslationBlock *tb_htable_lookup(CPUState *cpu, target_ulong pc, target_ulong cs_base, uint32_t flags, uint32_t cf_mask);void tb_set_jmp_target (TranslationBlock *tb,int n,uintptr_t addr); +void tb_exec_lock (void ); +void tb_exec_unlock (void );/* GETPC is the true target of the return instruction that we'll execute. */ #if defined(CONFIG_TCG_INTERPRETER )
include/tcg/tcg-apple-jit.h new file +85 -0
85 lines not on this page · raw message
include/tcg/tcg.h +3 -0
@@ -630,6 +630,9 @@ struct TCGContext {#if defined(CONFIG_IOS_JIT )ptrdiff_t code_rw_mirror_diff;#endif +#if defined(CONFIG_DARWIN ) && !defined(CONFIG_TCG_INTERPRETER ) +bool code_gen_locked;/* on Darwin each thread tracks W^X flags */ +#endif /* Threshold to flush the translated code buffer. */ void *code_gen_highwater;
tcg/tcg.c +4 -0
@@ -781,6 +781,8 @@ static void alloc_tcg_plugin_context(TCGContext *s)void tcg_register_thread (void ) { tcg_ctx = &tcg_init_ctx; + +tb_exec_unlock (); }#else void tcg_register_thread (void )
@@ -815,6 +817,8 @@ void tcg_register_thread(void) err =tcg_region_initial_alloc__locked (tcg_ctx);g_assert (!err);qemu_mutex_unlock (®ion.lock); + + tb_exec_unlock(); }#endif /* !CONFIG_USER_ONLY */
Signature · 1 line
2.24.3 (Apple Git-128)
Re: [PATCH 09/10] tcg: support JIT on Apple Silicon
Quoted 16 lines · Joelle van Dyne
From: osy <[email protected]>
For < iOS 14, reverse engineered functions from libsystem_pthread.dylib is implemented to handle APRR supported SoCs.
The following rules apply for JIT write protect:
* JIT write-protect is enabled beforetcg_qemu_tb_exec()
* JIT write-protect is disabled aftertcg_qemu_tb_exec()returns
* JIT write-protect is disabled insidedo_tb_phys_invalidate()but if it is called inside oftcg_qemu_tb_exec()then write-protect will be enabled again before returning.
* JIT write-protect is disabled bycpu_loop_exit()for interrupt handling.
* JIT write-protect is disabled everywhere else.
Quoted 1 line
Signed-off-by Joelle van Dyne <[email protected]>
Can this be emulated somehow on other platforms (such as Linux) so that it does not bitrot?
Paolo
Quoted 321 lines
--- accel/tcg/cpu-exec-common.c | 2 + accel/tcg/cpu-exec.c | 2 + accel/tcg/translate-all.c | 51 ++++++++++++++++++++++ configure | 20 +++++++++ include/exec/exec-all.h | 2 + include/tcg/tcg-apple-jit.h | 85 +++++++++++++++++++++++++++++++++++++ include/tcg/tcg.h | 3 ++ tcg/tcg.c | 4 ++ 8 files changed, 169 insertions(+) create mode 100644 include/tcg/tcg-apple-jit.haccel/tcg/cpu-exec-common.c +2
-0@@ -64,6 +64,8 @@ void cpu_reloading_memory_map(void)void cpu_loop_exit (CPUState *cpu) { +/* Unlock JIT write protect if applicable. */ +tb_exec_unlock ();/* Undo the setting in cpu_tb_exec. */ cpu->can_do_io =1 ;siglongjmp (cpu->jmp_env,1 );accel/tcg/cpu-exec.c +2
-0@@ -175,7 +175,9 @@ static inline tcg_target_ulong cpu_tb_exec(CPUState *cpu, TranslationBlock *itb) }#endif /* DEBUG_DISAS */ +tb_exec_lock (); ret =tcg_qemu_tb_exec (env, tb_ptr); +tb_exec_unlock (); cpu->can_do_io =1 ; last_tb = (TranslationBlock *)(ret & ~TB_EXIT_MASK ); tb_exit = ret &TB_EXIT_MASK ;accel/tcg/translate-all.c +51
-0@@ -27,6 +27,9 @@#include "disas/disas.h" #include "exec/exec-all.h" #include "tcg/tcg.h" +#if defined(CONFIG_DARWIN ) +#include "tcg/tcg-apple-jit.h" +#endif #if defined(CONFIG_USER_ONLY )#include "qemu.h" #if defined(__FreeBSD__) || defined(__FreeBSD_kernel__)@@ -76,6 +79,9 @@ extern kern_return_t mach_vm_remap(vm_map_t target_task, );#endif +static bool tb_exec_is_locked (void ); +static void tb_exec_change (bool locked); +/* #define DEBUG_TB_INVALIDATE */ /* #define DEBUG_TB_FLUSH */ /* make various TB consistency checks */ @@ -1246,6 +1252,7 @@ void tcg_exec_init(unsigned long tb_size, bool mirror_rwx)page_init ();tb_htable_init ();code_gen_alloc (tb_size, mirror_rwx); +tb_exec_unlock ();#if defined(CONFIG_SOFTMMU )/* There's no guest base to take into account, so go ahead and initialize the prologue now. */ @@ -1522,8 +1529,11 @@ static void do_tb_phys_invalidate(TranslationBlock *tb, bool rm_from_page_list)PageDesc *p;uint32_t h;tb_page_addr_t phys_pc; +bool code_gen_locked;assert_memory_lock (); + code_gen_locked =tb_exec_is_locked (); +tb_exec_unlock ();/* make sure no further incoming jumps will be chained to this TB */ qemu_spin_lock (&tb->jmp_lock);@@ -1536,6 +1546,7 @@ static void do_tb_phys_invalidate(TranslationBlock *tb, bool rm_from_page_list) tb->trace_vcpu_dstate);if (!(tb->cflags &CF_NOCACHE ) && !qht_remove (&tb_ctx.htable, tb, h)) { +tb_exec_change (code_gen_locked);return ; }@@ -1568,6 +1579,8 @@ static void do_tb_phys_invalidate(TranslationBlock *tb, bool rm_from_page_list)qatomic_set (&tcg_ctx->tb_phys_invalidate_count, tcg_ctx->tb_phys_invalidate_count +1 ); + +tb_exec_change (code_gen_locked); }static void tb_phys_invalidate__locked (TranslationBlock *tb)@@ -2808,3 +2821,41 @@ void tcg_flush_softmmu_tlb(CPUState *cs)tlb_flush (cs);#endif } + +#if defined(CONFIG_DARWIN ) && !defined(CONFIG_TCG_INTERPRETER ) +static bool tb_exec_is_locked (void ) +{ +return tcg_ctx->code_gen_locked; +} + +static void tb_exec_change (bool locked) +{ +#if defined(HAVE_PTHREAD_JIT_PROTECT ) + if (__builtin_available(macOS 11, iOS 14, watchOS 7, tvOS 14, *)) { +pthread_jit_write_protect_np (locked); + } else +#endif +if (jit_write_protect_supported ()) { +jit_write_protect (locked); + } + tcg_ctx->code_gen_locked = locked; +} +#else /* not needed on non-Darwin platforms */ +static bool tb_exec_is_locked (void ) +{ +return false; +} + +static void tb_exec_change (bool locked) {} +#endif + +void tb_exec_lock (void ) +{ +/* assumes sys_icache_invalidate already called */ +tb_exec_change (true); +} + +void tb_exec_unlock (void ) +{ +tb_exec_change (false); +}configure +20
-0@@ -5874,6 +5874,22 @@ but not implemented on your system" fi fi +########################################## +# check for Apple Silicon JIT function + +if [ "$darwin" = "yes" ] ; then + cat > $TMPC << EOF +#include <pthread.h> +int main() { pthread_jit_write_protect_np(0); return 0; } +EOF + if ! compile_prog ""; then + have_pthread_jit_protect='no' + else + have_pthread_jit_protect='yes' + fi +fi + + ########################################## # End of CC checks # After here, no more $cc or $ld runs@@ -6994,6 +7010,10 @@ if test "$secret_keyring" = "yes" ; then echo "CONFIG_SECRET_KEYRING=y" >> $config_host_mak fi +if test "$have_pthread_jit_protect" = "yes" ; then + echo "HAVE_PTHREAD_JIT_PROTECT=y" >> $config_host_mak +fi + if test "$tcg_interpreter" = "yes"; then QEMU_INCLUDES="-iquote ${source_path}/tcg/tci $QEMU_INCLUDES" elif test "$ARCH" = "sparc64" ; theninclude/exec/exec-all.h +2
-0@@ -521,6 +521,8 @@ TranslationBlock *tb_htable_lookup(CPUState *cpu, target_ulong pc, target_ulong cs_base, uint32_t flags, uint32_t cf_mask);void tb_set_jmp_target (TranslationBlock *tb,int n,uintptr_t addr); +void tb_exec_lock (void ); +void tb_exec_unlock (void );/* GETPC is the true target of the return instruction that we'll execute. */ #if defined(CONFIG_TCG_INTERPRETER )include/tcg/tcg-apple-jit.h new file +85
-0@@ -0,0 +1,85 @@ +/* +* Apple Silicon APRR functions for JIT handling +* +* Copyright (c) 2020 osy +* +* This library is free software; you can redistribute it and/or +* modify it under the terms of the GNU Lesser General Public +* License as published by the Free Software Foundation; either +* version 2.1 of the License, or (at your option) any later version. +* +* This library is distributed in the hope that it will be useful, +* but WITHOUT ANY WARRANTY; without even the implied warranty of +* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU +* Lesser General Public License for more details. +* +* You should have received a copy of the GNU Lesser General Public +* License along with this library; if not, see <http://www.gnu.org/licenses/>. +*/ + +/* +* Credits to: https://siguza.github.io/APRR/ +* Reversed from /usr/lib/system/libsystem_pthread.dylib +*/ + +#ifndef TCG_APPLE_JIT_H +#define TCG_APPLE_JIT_H + +#if defined(__aarch64__) && defined(CONFIG_DARWIN ) + +#define _COMM_PAGE_START_ADDRESS (0x0000000FFFFFC000ULL)/* In TTBR0 */ +#define _COMM_PAGE_APRR_SUPPORT (_COMM_PAGE_START_ADDRESS + 0x10C) +#define _COMM_PAGE_APPR_WRITE_ENABLE (_COMM_PAGE_START_ADDRESS + 0x110) +#define _COMM_PAGE_APRR_WRITE_DISABLE (_COMM_PAGE_START_ADDRESS + 0x118) + +static __attribute__((__always_inline__))bool jit_write_protect_supported (void ) +{ +/* Access shared kernel page at fixed memory location. */ +uint8_t aprr_support = *(volatile uint8_t *)_COMM_PAGE_APRR_SUPPORT; +return aprr_support >0 ; +} + +/* write protect enable = write disable */ +static __attribute__((__always_inline__))void jit_write_protect (int enabled) +{ +/* Access shared kernel page at fixed memory location. */ +uint8_t aprr_support = *(volatile uint8_t *)_COMM_PAGE_APRR_SUPPORT; +if (aprr_support ==0 || aprr_support >3 ) { +return ; + }else if (aprr_support ==1 ) { + __asm__ __volatile__ ( +"mov x0, %0\n" +"ldr x0, [x0]\n" +"msr S3_4_c15_c2_7, x0\n" +"isb sy\n" + ::"r" (enabled ? _COMM_PAGE_APRR_WRITE_DISABLE + : _COMM_PAGE_APPR_WRITE_ENABLE) + :"memory" ,"x0" + ); + }else { + __asm__ __volatile__ ( +"mov x0, %0\n" +"ldr x0, [x0]\n" +"msr S3_6_c15_c1_5, x0\n" +"isb sy\n" + ::"r" (enabled ? _COMM_PAGE_APRR_WRITE_DISABLE + : _COMM_PAGE_APPR_WRITE_ENABLE) + :"memory" ,"x0" + ); + } +} + +#else /* defined(__aarch64__) && defined(CONFIG_DARWIN) */ + +static __attribute__((__always_inline__))bool jit_write_protect_supported (void ) +{ +return false; +} + +static __attribute__((__always_inline__))void jit_write_protect (int enabled) +{ +} + +#endif + +#endif /* define TCG_APPLE_JIT_H */ include/tcg/tcg.h +3
-0@@ -630,6 +630,9 @@ struct TCGContext {#if defined(CONFIG_IOS_JIT )ptrdiff_t code_rw_mirror_diff;#endif +#if defined(CONFIG_DARWIN ) && !defined(CONFIG_TCG_INTERPRETER ) +bool code_gen_locked;/* on Darwin each thread tracks W^X flags */ +#endif /* Threshold to flush the translated code buffer. */ void *code_gen_highwater;tcg/tcg.c +4
-0@@ -781,6 +781,8 @@ static void alloc_tcg_plugin_context(TCGContext *s)void tcg_register_thread (void ) { tcg_ctx = &tcg_init_ctx; + +tb_exec_unlock (); }#else void tcg_register_thread (void )@@ -815,6 +817,8 @@ void tcg_register_thread(void) err =tcg_region_initial_alloc__locked (tcg_ctx);g_assert (!err);qemu_mutex_unlock (®ion.lock); + + tb_exec_unlock(); }#endif /* !CONFIG_USER_ONLY */
Re: [PATCH 09/10] tcg: support JIT on Apple Silicon
Quoted 18 lines · Paolo Bonzini
Quoted 16 lines · Joelle van Dyne
From: osy <[email protected]>
For < iOS 14, reverse engineered functions from libsystem_pthread.dylib is implemented to handle APRR supported SoCs.
The following rules apply for JIT write protect:
* JIT write-protect is enabled beforetcg_qemu_tb_exec()
* JIT write-protect is disabled aftertcg_qemu_tb_exec()returns
* JIT write-protect is disabled insidedo_tb_phys_invalidate()but if it is called inside oftcg_qemu_tb_exec()then write-protect will be enabled again before returning.
* JIT write-protect is disabled bycpu_loop_exit()for interrupt handling.
* JIT write-protect is disabled everywhere else.
Quoted 4 lines
Quoted 1 line
Signed-off-by Joelle van Dyne <[email protected]>Can this be emulated somehow on other platforms (such as Linux) so that it does not bitrot?
Some of it is write^execute, which we could test via OpenBSD I think if we updated our VM image not to mount the disk with that protection disabled. Having "generically support w^x" be separate from "iOS specifics" might be useful.
The apple.com webpage linked above suggests also that we could test some at least of these APIs on our OSX builds if we enable the "hardened runtime" on x86 (though that might also enable other stuff we don't want to deal with? no idea)
thanks
-- PMM
Re: [PATCH 09/10] tcg: support JIT on Apple Silicon
The APIs link correctly but are NOPs on Intel machines. I think full testing would require Apple Silicon or emulation. Is there precedent for any other platform/feature that requires hardware specific features?
-j
Quoted 37 lines · Peter Maydell
Quoted 18 lines · Paolo Bonzini
Quoted 16 lines · Joelle van Dyne
From: osy <[email protected]>
For < iOS 14, reverse engineered functions from libsystem_pthread.dylib is implemented to handle APRR supported SoCs.
The following rules apply for JIT write protect:
* JIT write-protect is enabled beforetcg_qemu_tb_exec()
* JIT write-protect is disabled aftertcg_qemu_tb_exec()returns
* JIT write-protect is disabled insidedo_tb_phys_invalidate()but if it is called inside oftcg_qemu_tb_exec()then write-protect will be enabled again before returning.
* JIT write-protect is disabled bycpu_loop_exit()for interrupt handling.
* JIT write-protect is disabled everywhere else.Quoted 4 lines
Quoted 1 line
Signed-off-by Joelle van Dyne <[email protected]>Can this be emulated somehow on other platforms (such as Linux) so that it does not bitrot?
Some of it is write^execute, which we could test via OpenBSD I think if we updated our VM image not to mount the disk with that protection disabled. Having "generically support w^x" be separate from "iOS specifics" might be useful.
The apple.com webpage linked above suggests also that we could test some at least of these APIs on our OSX builds if we enable the "hardened runtime" on x86 (though that might also enable other stuff we don't want to deal with? no idea)
thanks
-- PMM
PATCH 10/10 block: check availablity for preadv/pwritev on mac
In reply to Joelle van DyneFrom: osy <[email protected]>
macOS 11/iOS 14 added preadv/pwritev APIs. Due to weak linking, configure will succeed with CONFIG_PREADV even when targeting a lower OS version. We therefore need to check at run time if we can actually use these APIs.
--- block/file-posix.c | 12 ++++++++++++ 1 file changed, 12 insertions(+)
block/file-posix.c +12 -0
@@ -1393,12 +1393,24 @@ static bool preadv_present = true;static ssize_t qemu_preadv (int fd,const struct iovec *iov,int nr_iov,off_t offset) { +#ifdef CONFIG_DARWIN /* preadv introduced in macOS 11 */ + if (!__builtin_available(macOS 11, iOS 14, watchOS 7, tvOS 14, *)) { + preadv_present = false; +return -ENOSYS ; + } else +#endif return preadv (fd, iov, nr_iov, offset); }static ssize_t qemu_pwritev (int fd,const struct iovec *iov,int nr_iov,off_t offset) { +#ifdef CONFIG_DARWIN /* pwritev introduced in macOS 11 */ + if (!__builtin_available(macOS 11, iOS 14, watchOS 7, tvOS 14, *)) { + preadv_present = false; +return -ENOSYS ; + } else +#endif return pwritev (fd, iov, nr_iov, offset); }
Signature · 1 line
2.24.3 (Apple Git-128)
Patchew URL: https://patchew.org/QEMU/[email protected]/
Patchew URL: https://patchew.org/QEMU/[email protected]/
Hi,
This series seems to have some coding style problems. See output below for more information:
Type: series
Message-id: [email protected]
Subject: [PATCH 00/10] iOS and Apple Silicon host support
=== TEST SCRIPT BEGIN ===
#!/bin/bash
git rev-parse base > /dev/null || exit 0
git config --local diff.renamelimit 0
git config --local diff.renames True
git config --local diff.algorithm histogram./scripts/checkpatch.pl --mailback base..
=== TEST SCRIPT END ===
Updating 3c8cf5a9c21ff8782164d1def7f44bd888713384 From https://github.com/patchew-project/qemu
* [new tag] patchew/[email protected] -> patchew/[email protected]
Switched to a new branch 'test'
b6c449f block: check availablity for preadv/pwritev on mac 86f3837 tcg: support JIT on Apple Silicon
6389bee tcg: mirror mapping RWX pages for iOS optional 8727db6 tcg: implement bulletproof JIT
e655897 coroutine: add libucontext as external library e43d59a slirp: update for iOS resolv fix
715f3bd meson: option to build as shared library 7276968 qemu: add support for iOS host
9f6bafb configure: cross-compiling without cross_prefix 9187922 configure: option to disable host block devices
=== OUTPUT BEGIN ===
1/10 Checking commit 9187922c6d93 (configure: option to disable host block devices)
WARNING: architecture specific defines should be avoided
#22: FILE: block/file-posix.c:44:
+#if defined(CONFIG_HOST_BLOCK_DEVICE) && defined(__APPLE__) && (__MACH__)
total: 0 errors, 1 warnings, 61 lines checked
Patch 1/10 has style problems, please review. If any of these errors are false positives report them to the maintainer, see
CHECKPATCH in MAINTAINERS.
2/10 Checking commit 9f6bafb19c1d (configure: cross-compiling without cross_prefix) 3/10 Checking commit 72769683dd9c (qemu: add support for iOS host)
WARNING: architecture specific defines should be avoided
#27: FILE: block.c:56:
+#if !defined(__DragonFly__) && !defined(CONFIG_IOS)
ERROR: braces {} are necessary for all arms of this statement #45: FILE: block/file-posix.c:189:
+ if (s->fd >= 0)
[...]
WARNING: architecture specific defines should be avoided #79: FILE: block/file-posix.c:2325:
+#if !defined(CONFIG_IOS) && defined(__APPLE__) && defined(__MACH__)
WARNING: architecture specific defines should be avoided #363: FILE: tcg/aarch64/tcg-target.h:151:
+#if defined(__APPLE__)
WARNING: architecture specific defines should be avoided #369: FILE: tcg/aarch64/tcg-target.h:157:
+#if defined(__APPLE__)
total: 1 errors, 4 warnings, 316 lines checked
Patch 3/10 has style problems, please review. If any of these errors are false positives report them to the maintainer, see CHECKPATCH in MAINTAINERS.
4/10 Checking commit 715f3bddd393 (meson: option to build as shared library) 5/10 Checking commit e43d59afc25c (slirp: update for iOS resolv fix) 6/10 Checking commit e655897c7ab2 (coroutine: add libucontext as external library)
WARNING: added, moved or deleted file(s), does MAINTAINERS need updating? #97:
new file mode 160000
total: 0 errors, 1 warnings, 140 lines checked
Patch 6/10 has style problems, please review. If any of these errors are false positives report them to the maintainer, see CHECKPATCH in MAINTAINERS.
7/10 Checking commit 8727db6cfd2d (tcg: implement bulletproof JIT)
ERROR: externs should be avoided in .c files
#52: FILE: accel/tcg/translate-all.c:65:
+extern kern_return_t mach_vm_remap(vm_map_t target_task,
WARNING: added, moved or deleted file(s), does MAINTAINERS need updating? #189:
new file mode 100644
WARNING: architecture specific defines should be avoided #501: FILE: tcg/aarch64/tcg-target.h:171:
+#if defined(__APPLE__)
WARNING: architecture specific defines should be avoided #757: FILE: tcg/i386/tcg-target.h:209:
+#ifdef __APPLE__
WARNING: architecture specific defines should be avoided #768: FILE: tcg/i386/tcg-target.h:220:
+#if defined(__APPLE__)
total: 1 errors, 4 warnings, 1673 lines checked
Patch 7/10 has style problems, please review. If any of these errors are false positives report them to the maintainer, see CHECKPATCH in MAINTAINERS.
8/10 Checking commit 6389bee4f3d0 (tcg: mirror mapping RWX pages for iOS optional) 9/10 Checking commit 86f3837d7074 (tcg: support JIT on Apple Silicon)
WARNING: added, moved or deleted file(s), does MAINTAINERS need updating? #206:
new file mode 100644
WARNING: architecture specific defines should be avoided #238: FILE: include/tcg/tcg-apple-jit.h:28:
+#if defined(__aarch64__) && defined(CONFIG_DARWIN)
total: 0 errors, 2 warnings, 259 lines checked
Patch 9/10 has style problems, please review. If any of these errors
are false positives report them to the maintainer, see
CHECKPATCH in MAINTAINERS.
10/10 Checking commit b6c449ff37a3 (block: check availablity for preadv/pwritev on mac) === OUTPUT END ===
Test command exited with code: 1
The full log is available at
http://patchew.org/logs/[email protected]/testing.checkpatch/?type=message.
---
Email generated automatically by Patchew [https://patchew.org/].
Please send your feedback to [email protected]
I did run the style check tool. Of the errors/warnings, a few are from code moved from one place to another, re-formatting the moved code seems to break another rule (don't include irrelevant changes).
Quoted 143 lines · On Mon, Oct 12, 2020 at 6:21 PM <[email protected]> wrote:
Patchew URL: https://patchew.org/QEMU/[email protected]/
Hi,
This series seems to have some coding style problems. See output below for more information:
Type: series
Message-id: [email protected]
Subject: [PATCH 00/10] iOS and Apple Silicon host support=== TEST SCRIPT BEGIN ===
#!/bin/bash
git rev-parse base >/dev/null|| exit 0
git config --local diff.renamelimit 0
git config --local diff.renames True
git config --local diff.algorithm histogram./scripts/checkpatch.pl--mailback base..
=== TEST SCRIPT END ===Updating
3c8cf5a9c21ff8782164d1def7f44bd888713384From https://github.com/patchew-project/qemu
* [new tag] patchew/[email protected] -> patchew/[email protected]
Switched to a new branch 'test'
b6c449f block: check availablity for preadv/pwritev on mac 86f3837 tcg: support JIT on Apple Silicon
6389bee tcg: mirror mapping RWX pages for iOS optional 8727db6 tcg: implement bulletproof JIT
e655897 coroutine: add libucontext as external library e43d59a slirp: update for iOS resolv fix
715f3bd meson: option to build as shared library 7276968 qemu: add support for iOS host
9f6bafb configure: cross-compiling withoutcross_prefix9187922 configure: option to disable host block devices=== OUTPUT BEGIN ===
1/10 Checking commit9187922c6d93(configure: option to disable host block devices)
WARNING: architecture specific defines should be avoided
#22: FILE:block/file-posix.c:44:
+#ifdefined(CONFIG_HOST_BLOCK_DEVICE)&&defined(__APPLE__)&& (__MACH__)total: 0 errors, 1 warnings, 61 lines checked
Patch 1/10 has style problems, please review. If any of these errors are false positives report them to the maintainer, see
CHECKPATCH inMAINTAINERS.
2/10 Checking commit9f6bafb19c1d(configure: cross-compiling withoutcross_prefix) 3/10 Checking commit72769683dd9c(qemu: add support for iOS host)
WARNING: architecture specific defines should be avoided
#27: FILE: block.c:56:
+#if !defined(__DragonFly__) && !defined(CONFIG_IOS)ERROR: braces {} are necessary for all arms of this statement #45: FILE:
block/file-posix.c:189:
+ if (s->fd>= 0)
[...]WARNING: architecture specific defines should be avoided #79: FILE:
block/file-posix.c:2325:
+#if !defined(CONFIG_IOS) &&defined(__APPLE__)&&defined(__MACH__)WARNING: architecture specific defines should be avoided #363: FILE:
tcg/aarch64/tcg-target.h:151:
+#ifdefined(__APPLE__)WARNING: architecture specific defines should be avoided #369: FILE:
tcg/aarch64/tcg-target.h:157:
+#ifdefined(__APPLE__)total: 1 errors, 4 warnings, 316 lines checked
Patch 3/10 has style problems, please review. If any of these errors are false positives report them to the maintainer, see CHECKPATCH in
MAINTAINERS.4/10 Checking commit
715f3bddd393(meson: option to build as shared library) 5/10 Checking commite43d59afc25c(slirp: update for iOS resolv fix) 6/10 Checking commite655897c7ab2(coroutine: add libucontext as external library)
WARNING: added, moved or deleted file(s), doesMAINTAINERSneed updating? #97:
new file mode 160000total: 0 errors, 1 warnings, 140 lines checked
Patch 6/10 has style problems, please review. If any of these errors are false positives report them to the maintainer, see CHECKPATCH in
MAINTAINERS.
7/10 Checking commit8727db6cfd2d(tcg: implement bulletproof JIT)
ERROR: externs should be avoided in .c files
#52: FILE:accel/tcg/translate-all.c:65:
+externkern_return_tmach_vm_remap(vm_map_ttarget_task,WARNING: added, moved or deleted file(s), does
MAINTAINERSneed updating? #189:
new file mode 100644WARNING: architecture specific defines should be avoided #501: FILE:
tcg/aarch64/tcg-target.h:171:
+#ifdefined(__APPLE__)WARNING: architecture specific defines should be avoided #757: FILE:
tcg/i386/tcg-target.h:209:
+#ifdef__APPLE__WARNING: architecture specific defines should be avoided #768: FILE:
tcg/i386/tcg-target.h:220:
+#ifdefined(__APPLE__)total: 1 errors, 4 warnings, 1673 lines checked
Patch 7/10 has style problems, please review. If any of these errors are false positives report them to the maintainer, see CHECKPATCH in
MAINTAINERS.8/10 Checking commit
6389bee4f3d0(tcg: mirror mapping RWX pages for iOS optional) 9/10 Checking commit86f3837d7074(tcg: support JIT on Apple Silicon)
WARNING: added, moved or deleted file(s), doesMAINTAINERSneed updating? #206:
new file mode 100644WARNING: architecture specific defines should be avoided #238: FILE:
include/tcg/tcg-apple-jit.h:28:
+#ifdefined(__aarch64__)&&defined(CONFIG_DARWIN)total: 0 errors, 2 warnings, 259 lines checked
Patch 9/10 has style problems, please review. If any of these errors
are false positives report them to the maintainer, see
CHECKPATCH inMAINTAINERS.
10/10 Checking commitb6c449ff37a3(block: check availablity for preadv/pwritev on mac) === OUTPUT END ===Test command exited with code: 1
The full log is available at
http://patchew.org/logs/[email protected]/testing.checkpatch/?type=message.
---
Email generated automatically by Patchew [https://patchew.org/].
Please send your feedback to [email protected]