| Message ID | 20230220111215.27471-3-pierrick.bouvier@linaro.org |
|---|---|
| State | Superseded |
| Headers | show |
| Series | Adds support for running QEMU natively on windows-arm64 | expand |
Acked-by: Richard Henderson <richard.henderson@linaro.org> On 2/20/23 12:12, Pierrick Bouvier wrote: > Windows implementation of setjmp/longjmp is done in > C:/WINDOWS/system32/ucrtbase.dll. Alas, on arm64, it seems to *always* > perform stack unwinding, which crashes from generated code. > > By using alternative implementation built in mingw, we avoid doing stack > unwinding and this fixes crash when calling longjmp. > > Signed-off-by: Pierrick Bouvier <pierrick.bouvier@linaro.org> > --- > include/sysemu/os-win32.h | 25 +++++++++++++++++++++++-- > meson.build | 24 ++++++++++++++++++++++++ > 2 files changed, 47 insertions(+), 2 deletions(-) > > diff --git a/include/sysemu/os-win32.h b/include/sysemu/os-win32.h > index 5b38c7bd04..1f6c141d39 100644 > --- a/include/sysemu/os-win32.h > +++ b/include/sysemu/os-win32.h > @@ -51,14 +51,35 @@ typedef struct sockaddr_un { > extern "C" { > #endif > > -#if defined(_WIN64) > +#if defined(__aarch64__) > +#ifndef CONFIG_MINGW64_HAS_SETJMP_LONGJMP > +#error mingw must provide setjmp/longjmp for windows-arm64 > +#endif > +/* > + * On windows-arm64, setjmp is available in only one variant, and longjmp always > + * does stack unwinding. This crash with generated code. > + * Thus, we use another implementation of setjmp (not windows one), coming from > + * mingw, which never performs stack unwinding. > + */ > +#undef setjmp > +#undef longjmp > +/* > + * These functions are not declared in setjmp.h because __aarch64__ defines > + * setjmp to _setjmpex instead. However, they are still defined in libmingwex.a, > + * which gets linked automatically. > + */ > +extern int __mingw_setjmp(jmp_buf); > +extern void __attribute__((noreturn)) __mingw_longjmp(jmp_buf, int); > +#define setjmp(env) __mingw_setjmp(env) > +#define longjmp(env, val) __mingw_longjmp(env, val) > +#elif defined(_WIN64) > /* On w64, setjmp is implemented by _setjmp which needs a second parameter. > * If this parameter is NULL, longjump does no stack unwinding. > * That is what we need for QEMU. Passing the value of register rsp (default) > * lets longjmp try a stack unwinding which will crash with generated code. */ > # undef setjmp > # define setjmp(env) _setjmp(env, NULL) > -#endif > +#endif /* __aarch64__ */ > /* QEMU uses sigsetjmp()/siglongjmp() as the portable way to specify > * "longjmp and don't touch the signal masks". Since we know that the > * savemask parameter will always be zero we can safely define these > diff --git a/meson.build b/meson.build > index 4ba3bf3431..e968ed9e7a 100644 > --- a/meson.build > +++ b/meson.build > @@ -2450,6 +2450,30 @@ if targetos == 'windows' > }''', name: '_lock_file and _unlock_file')) > endif > > +if targetos == 'windows' > + mingw_has_setjmp_longjmp = cc.links(''' > + #include <setjmp.h> > + int main(void) { > + /* > + * These functions are not available in setjmp header, but may be > + * available at link time, from libmingwex.a. > + */ > + extern int __mingw_setjmp(jmp_buf); > + extern void __attribute__((noreturn)) __mingw_longjmp(jmp_buf, int); > + jmp_buf env; > + __mingw_setjmp(env); > + __mingw_longjmp(env, 0); > + } > + ''', name: 'mingw setjmp and longjmp') > + > + config_host_data.set('CONFIG_MINGW64_HAS_SETJMP_LONGJMP', > + mingw_has_setjmp_longjmp) > + > + if cpu == 'aarch64' and not mingw_has_setjmp_longjmp > + error('mingw must provide setjmp/longjmp for windows-arm64') > + endif > +endif > + > ######################## > # Target configuration # > ########################
@Philippe Mathieu-Daudé, is that version satisfying for you, regarding your initial comments about setjmp/longjmp detection in meson? I can integrate more changes if needed. Thanks, Pierrick On 2/20/23 16:16, Pierrick Bouvier wrote: > Acked-by: Richard Henderson <richard.henderson@linaro.org> > > On 2/20/23 12:12, Pierrick Bouvier wrote: >> Windows implementation of setjmp/longjmp is done in >> C:/WINDOWS/system32/ucrtbase.dll. Alas, on arm64, it seems to *always* >> perform stack unwinding, which crashes from generated code. >> >> By using alternative implementation built in mingw, we avoid doing stack >> unwinding and this fixes crash when calling longjmp. >> >> Signed-off-by: Pierrick Bouvier <pierrick.bouvier@linaro.org> >> --- >> include/sysemu/os-win32.h | 25 +++++++++++++++++++++++-- >> meson.build | 24 ++++++++++++++++++++++++ >> 2 files changed, 47 insertions(+), 2 deletions(-) >> >> diff --git a/include/sysemu/os-win32.h b/include/sysemu/os-win32.h >> index 5b38c7bd04..1f6c141d39 100644 >> --- a/include/sysemu/os-win32.h >> +++ b/include/sysemu/os-win32.h >> @@ -51,14 +51,35 @@ typedef struct sockaddr_un { >> extern "C" { >> #endif >> >> -#if defined(_WIN64) >> +#if defined(__aarch64__) >> +#ifndef CONFIG_MINGW64_HAS_SETJMP_LONGJMP >> +#error mingw must provide setjmp/longjmp for windows-arm64 >> +#endif >> +/* >> + * On windows-arm64, setjmp is available in only one variant, and longjmp always >> + * does stack unwinding. This crash with generated code. >> + * Thus, we use another implementation of setjmp (not windows one), coming from >> + * mingw, which never performs stack unwinding. >> + */ >> +#undef setjmp >> +#undef longjmp >> +/* >> + * These functions are not declared in setjmp.h because __aarch64__ defines >> + * setjmp to _setjmpex instead. However, they are still defined in libmingwex.a, >> + * which gets linked automatically. >> + */ >> +extern int __mingw_setjmp(jmp_buf); >> +extern void __attribute__((noreturn)) __mingw_longjmp(jmp_buf, int); >> +#define setjmp(env) __mingw_setjmp(env) >> +#define longjmp(env, val) __mingw_longjmp(env, val) >> +#elif defined(_WIN64) >> /* On w64, setjmp is implemented by _setjmp which needs a second parameter. >> * If this parameter is NULL, longjump does no stack unwinding. >> * That is what we need for QEMU. Passing the value of register rsp (default) >> * lets longjmp try a stack unwinding which will crash with generated code. */ >> # undef setjmp >> # define setjmp(env) _setjmp(env, NULL) >> -#endif >> +#endif /* __aarch64__ */ >> /* QEMU uses sigsetjmp()/siglongjmp() as the portable way to specify >> * "longjmp and don't touch the signal masks". Since we know that the >> * savemask parameter will always be zero we can safely define these >> diff --git a/meson.build b/meson.build >> index 4ba3bf3431..e968ed9e7a 100644 >> --- a/meson.build >> +++ b/meson.build >> @@ -2450,6 +2450,30 @@ if targetos == 'windows' >> }''', name: '_lock_file and _unlock_file')) >> endif >> >> +if targetos == 'windows' >> + mingw_has_setjmp_longjmp = cc.links(''' >> + #include <setjmp.h> >> + int main(void) { >> + /* >> + * These functions are not available in setjmp header, but may be >> + * available at link time, from libmingwex.a. >> + */ >> + extern int __mingw_setjmp(jmp_buf); >> + extern void __attribute__((noreturn)) __mingw_longjmp(jmp_buf, int); >> + jmp_buf env; >> + __mingw_setjmp(env); >> + __mingw_longjmp(env, 0); >> + } >> + ''', name: 'mingw setjmp and longjmp') >> + >> + config_host_data.set('CONFIG_MINGW64_HAS_SETJMP_LONGJMP', >> + mingw_has_setjmp_longjmp) >> + >> + if cpu == 'aarch64' and not mingw_has_setjmp_longjmp >> + error('mingw must provide setjmp/longjmp for windows-arm64') >> + endif >> +endif >> + >> ######################## >> # Target configuration # >> ########################
On 21/2/23 10:47, Pierrick Bouvier wrote: > @Philippe Mathieu-Daudé, is that version satisfying for you, regarding > your initial comments about setjmp/longjmp detection in meson? Yes, the meson check is what I had in mind. > I can integrate more changes if needed. > > Thanks, > Pierrick > > On 2/20/23 16:16, Pierrick Bouvier wrote: >> Acked-by: Richard Henderson <richard.henderson@linaro.org> >> >> On 2/20/23 12:12, Pierrick Bouvier wrote: >>> Windows implementation of setjmp/longjmp is done in >>> C:/WINDOWS/system32/ucrtbase.dll. Alas, on arm64, it seems to *always* >>> perform stack unwinding, which crashes from generated code. >>> >>> By using alternative implementation built in mingw, we avoid doing stack >>> unwinding and this fixes crash when calling longjmp. >>> >>> Signed-off-by: Pierrick Bouvier <pierrick.bouvier@linaro.org> >>> --- >>> include/sysemu/os-win32.h | 25 +++++++++++++++++++++++-- >>> meson.build | 24 ++++++++++++++++++++++++ >>> 2 files changed, 47 insertions(+), 2 deletions(-) >>> >>> diff --git a/include/sysemu/os-win32.h b/include/sysemu/os-win32.h >>> index 5b38c7bd04..1f6c141d39 100644 >>> --- a/include/sysemu/os-win32.h >>> +++ b/include/sysemu/os-win32.h >>> @@ -51,14 +51,35 @@ typedef struct sockaddr_un { >>> extern "C" { >>> #endif >>> -#if defined(_WIN64) >>> +#if defined(__aarch64__) >>> +#ifndef CONFIG_MINGW64_HAS_SETJMP_LONGJMP >>> +#error mingw must provide setjmp/longjmp for windows-arm64 Per the meson error [*], this now seems impossible, thus we can simply drop the CONFIG_MINGW64_HAS_SETJMP_LONGJMP definition? >>> +#endif >>> +/* >>> + * On windows-arm64, setjmp is available in only one variant, and >>> longjmp always >>> + * does stack unwinding. This crash with generated code. >>> + * Thus, we use another implementation of setjmp (not windows one), >>> coming from >>> + * mingw, which never performs stack unwinding. >>> + */ >>> +#undef setjmp >>> +#undef longjmp >>> +/* >>> + * These functions are not declared in setjmp.h because __aarch64__ >>> defines >>> + * setjmp to _setjmpex instead. However, they are still defined in >>> libmingwex.a, >>> + * which gets linked automatically. >>> + */ >>> +extern int __mingw_setjmp(jmp_buf); >>> +extern void __attribute__((noreturn)) __mingw_longjmp(jmp_buf, int); >>> +#define setjmp(env) __mingw_setjmp(env) >>> +#define longjmp(env, val) __mingw_longjmp(env, val) >>> +#elif defined(_WIN64) >>> /* On w64, setjmp is implemented by _setjmp which needs a second >>> parameter. >>> * If this parameter is NULL, longjump does no stack unwinding. >>> * That is what we need for QEMU. Passing the value of register >>> rsp (default) >>> * lets longjmp try a stack unwinding which will crash with >>> generated code. */ >>> # undef setjmp >>> # define setjmp(env) _setjmp(env, NULL) >>> -#endif >>> +#endif /* __aarch64__ */ This comment doesn't seem accurate. Maybe "64-bit"? >>> /* QEMU uses sigsetjmp()/siglongjmp() as the portable way to specify >>> * "longjmp and don't touch the signal masks". Since we know that the >>> * savemask parameter will always be zero we can safely define these >>> diff --git a/meson.build b/meson.build >>> index 4ba3bf3431..e968ed9e7a 100644 >>> --- a/meson.build >>> +++ b/meson.build >>> @@ -2450,6 +2450,30 @@ if targetos == 'windows' >>> }''', name: '_lock_file and _unlock_file')) >>> endif >>> +if targetos == 'windows' >>> + mingw_has_setjmp_longjmp = cc.links(''' >>> + #include <setjmp.h> >>> + int main(void) { >>> + /* >>> + * These functions are not available in setjmp header, but may be >>> + * available at link time, from libmingwex.a. >>> + */ >>> + extern int __mingw_setjmp(jmp_buf); >>> + extern void __attribute__((noreturn)) __mingw_longjmp(jmp_buf, >>> int); >>> + jmp_buf env; >>> + __mingw_setjmp(env); >>> + __mingw_longjmp(env, 0); >>> + } >>> + ''', name: 'mingw setjmp and longjmp') >>> + >>> + config_host_data.set('CONFIG_MINGW64_HAS_SETJMP_LONGJMP', >>> + mingw_has_setjmp_longjmp) >>> + >>> + if cpu == 'aarch64' and not mingw_has_setjmp_longjmp >>> + error('mingw must provide setjmp/longjmp for windows-arm64') (This is the [*] error I mentioned earlier). >>> + endif >>> +endif >>> + >>> ######################## >>> # Target configuration # >>> ########################
On 2/21/23 11:33, Philippe Mathieu-Daudé wrote: > On 21/2/23 10:47, Pierrick Bouvier wrote: >> @Philippe Mathieu-Daudé, is that version satisfying for you, regarding >> your initial comments about setjmp/longjmp detection in meson? > > Yes, the meson check is what I had in mind. > >> I can integrate more changes if needed. >> >> Thanks, >> Pierrick >> >> On 2/20/23 16:16, Pierrick Bouvier wrote: >>> Acked-by: Richard Henderson <richard.henderson@linaro.org> >>> >>> On 2/20/23 12:12, Pierrick Bouvier wrote: >>>> Windows implementation of setjmp/longjmp is done in >>>> C:/WINDOWS/system32/ucrtbase.dll. Alas, on arm64, it seems to *always* >>>> perform stack unwinding, which crashes from generated code. >>>> >>>> By using alternative implementation built in mingw, we avoid doing stack >>>> unwinding and this fixes crash when calling longjmp. >>>> >>>> Signed-off-by: Pierrick Bouvier <pierrick.bouvier@linaro.org> >>>> --- >>>> include/sysemu/os-win32.h | 25 +++++++++++++++++++++++-- >>>> meson.build | 24 ++++++++++++++++++++++++ >>>> 2 files changed, 47 insertions(+), 2 deletions(-) >>>> >>>> diff --git a/include/sysemu/os-win32.h b/include/sysemu/os-win32.h >>>> index 5b38c7bd04..1f6c141d39 100644 >>>> --- a/include/sysemu/os-win32.h >>>> +++ b/include/sysemu/os-win32.h >>>> @@ -51,14 +51,35 @@ typedef struct sockaddr_un { >>>> extern "C" { >>>> #endif >>>> -#if defined(_WIN64) >>>> +#if defined(__aarch64__) >>>> +#ifndef CONFIG_MINGW64_HAS_SETJMP_LONGJMP >>>> +#error mingw must provide setjmp/longjmp for windows-arm64 > > Per the meson error [*], this now seems impossible, thus we can > simply drop the CONFIG_MINGW64_HAS_SETJMP_LONGJMP definition? > I think it's redundant too. >>>> +#endif >>>> +/* >>>> + * On windows-arm64, setjmp is available in only one variant, and >>>> longjmp always >>>> + * does stack unwinding. This crash with generated code. >>>> + * Thus, we use another implementation of setjmp (not windows one), >>>> coming from >>>> + * mingw, which never performs stack unwinding. >>>> + */ >>>> +#undef setjmp >>>> +#undef longjmp >>>> +/* >>>> + * These functions are not declared in setjmp.h because __aarch64__ >>>> defines >>>> + * setjmp to _setjmpex instead. However, they are still defined in >>>> libmingwex.a, >>>> + * which gets linked automatically. >>>> + */ >>>> +extern int __mingw_setjmp(jmp_buf); >>>> +extern void __attribute__((noreturn)) __mingw_longjmp(jmp_buf, int); >>>> +#define setjmp(env) __mingw_setjmp(env) >>>> +#define longjmp(env, val) __mingw_longjmp(env, val) >>>> +#elif defined(_WIN64) >>>> /* On w64, setjmp is implemented by _setjmp which needs a second >>>> parameter. >>>> * If this parameter is NULL, longjump does no stack unwinding. >>>> * That is what we need for QEMU. Passing the value of register >>>> rsp (default) >>>> * lets longjmp try a stack unwinding which will crash with >>>> generated code. */ >>>> # undef setjmp >>>> # define setjmp(env) _setjmp(env, NULL) >>>> -#endif >>>> +#endif /* __aarch64__ */ > > This comment doesn't seem accurate. Maybe "64-bit"? > I'd like to use windows-x64. IMHO, it's clearer and on par with windows-arm64. But I know some people don't like x64 nomenclature. Alas, several projects are using w32 and w64 names, and there is no consensus yet on how win-arm64 should be named. >>>> /* QEMU uses sigsetjmp()/siglongjmp() as the portable way to specify >>>> * "longjmp and don't touch the signal masks". Since we know that the >>>> * savemask parameter will always be zero we can safely define these >>>> diff --git a/meson.build b/meson.build >>>> index 4ba3bf3431..e968ed9e7a 100644 >>>> --- a/meson.build >>>> +++ b/meson.build >>>> @@ -2450,6 +2450,30 @@ if targetos == 'windows' >>>> }''', name: '_lock_file and _unlock_file')) >>>> endif >>>> +if targetos == 'windows' >>>> + mingw_has_setjmp_longjmp = cc.links(''' >>>> + #include <setjmp.h> >>>> + int main(void) { >>>> + /* >>>> + * These functions are not available in setjmp header, but may be >>>> + * available at link time, from libmingwex.a. >>>> + */ >>>> + extern int __mingw_setjmp(jmp_buf); >>>> + extern void __attribute__((noreturn)) __mingw_longjmp(jmp_buf, >>>> int); >>>> + jmp_buf env; >>>> + __mingw_setjmp(env); >>>> + __mingw_longjmp(env, 0); >>>> + } >>>> + ''', name: 'mingw setjmp and longjmp') >>>> + >>>> + config_host_data.set('CONFIG_MINGW64_HAS_SETJMP_LONGJMP', >>>> + mingw_has_setjmp_longjmp) >>>> + >>>> + if cpu == 'aarch64' and not mingw_has_setjmp_longjmp >>>> + error('mingw must provide setjmp/longjmp for windows-arm64') > > (This is the [*] error I mentioned earlier). > >>>> + endif >>>> +endif >>>> + >>>> ######################## >>>> # Target configuration # >>>> ######################## >
On 21/2/23 14:16, Pierrick Bouvier wrote: > On 2/21/23 11:33, Philippe Mathieu-Daudé wrote: >> On 21/2/23 10:47, Pierrick Bouvier wrote: >>> @Philippe Mathieu-Daudé, is that version satisfying for you, regarding >>> your initial comments about setjmp/longjmp detection in meson? >> >> Yes, the meson check is what I had in mind. >> >>> I can integrate more changes if needed. >>> >>> Thanks, >>> Pierrick >>> >>> On 2/20/23 16:16, Pierrick Bouvier wrote: >>>> Acked-by: Richard Henderson <richard.henderson@linaro.org> >>>> >>>> On 2/20/23 12:12, Pierrick Bouvier wrote: >>>>> Windows implementation of setjmp/longjmp is done in >>>>> C:/WINDOWS/system32/ucrtbase.dll. Alas, on arm64, it seems to *always* >>>>> perform stack unwinding, which crashes from generated code. >>>>> >>>>> By using alternative implementation built in mingw, we avoid doing >>>>> stack >>>>> unwinding and this fixes crash when calling longjmp. >>>>> >>>>> Signed-off-by: Pierrick Bouvier <pierrick.bouvier@linaro.org> >>>>> --- >>>>> include/sysemu/os-win32.h | 25 +++++++++++++++++++++++-- >>>>> meson.build | 24 ++++++++++++++++++++++++ >>>>> 2 files changed, 47 insertions(+), 2 deletions(-) >>>>> -#if defined(_WIN64) >>>>> +#if defined(__aarch64__) >>>>> +#ifndef CONFIG_MINGW64_HAS_SETJMP_LONGJMP >>>>> +#error mingw must provide setjmp/longjmp for windows-arm64 >> >> Per the meson error [*], this now seems impossible, thus we can >> simply drop the CONFIG_MINGW64_HAS_SETJMP_LONGJMP definition? >> > > I think it's redundant too. >>>>> -#endif >>>>> +#endif /* __aarch64__ */ >> >> This comment doesn't seem accurate. Maybe "64-bit"? >> > > I'd like to use windows-x64. IMHO, it's clearer and on par with > windows-arm64. But I know some people don't like x64 nomenclature. Fine by me :)
diff --git a/include/sysemu/os-win32.h b/include/sysemu/os-win32.h index 5b38c7bd04..1f6c141d39 100644 --- a/include/sysemu/os-win32.h +++ b/include/sysemu/os-win32.h @@ -51,14 +51,35 @@ typedef struct sockaddr_un { extern "C" { #endif -#if defined(_WIN64) +#if defined(__aarch64__) +#ifndef CONFIG_MINGW64_HAS_SETJMP_LONGJMP +#error mingw must provide setjmp/longjmp for windows-arm64 +#endif +/* + * On windows-arm64, setjmp is available in only one variant, and longjmp always + * does stack unwinding. This crash with generated code. + * Thus, we use another implementation of setjmp (not windows one), coming from + * mingw, which never performs stack unwinding. + */ +#undef setjmp +#undef longjmp +/* + * These functions are not declared in setjmp.h because __aarch64__ defines + * setjmp to _setjmpex instead. However, they are still defined in libmingwex.a, + * which gets linked automatically. + */ +extern int __mingw_setjmp(jmp_buf); +extern void __attribute__((noreturn)) __mingw_longjmp(jmp_buf, int); +#define setjmp(env) __mingw_setjmp(env) +#define longjmp(env, val) __mingw_longjmp(env, val) +#elif defined(_WIN64) /* On w64, setjmp is implemented by _setjmp which needs a second parameter. * If this parameter is NULL, longjump does no stack unwinding. * That is what we need for QEMU. Passing the value of register rsp (default) * lets longjmp try a stack unwinding which will crash with generated code. */ # undef setjmp # define setjmp(env) _setjmp(env, NULL) -#endif +#endif /* __aarch64__ */ /* QEMU uses sigsetjmp()/siglongjmp() as the portable way to specify * "longjmp and don't touch the signal masks". Since we know that the * savemask parameter will always be zero we can safely define these diff --git a/meson.build b/meson.build index 4ba3bf3431..e968ed9e7a 100644 --- a/meson.build +++ b/meson.build @@ -2450,6 +2450,30 @@ if targetos == 'windows' }''', name: '_lock_file and _unlock_file')) endif +if targetos == 'windows' + mingw_has_setjmp_longjmp = cc.links(''' + #include <setjmp.h> + int main(void) { + /* + * These functions are not available in setjmp header, but may be + * available at link time, from libmingwex.a. + */ + extern int __mingw_setjmp(jmp_buf); + extern void __attribute__((noreturn)) __mingw_longjmp(jmp_buf, int); + jmp_buf env; + __mingw_setjmp(env); + __mingw_longjmp(env, 0); + } + ''', name: 'mingw setjmp and longjmp') + + config_host_data.set('CONFIG_MINGW64_HAS_SETJMP_LONGJMP', + mingw_has_setjmp_longjmp) + + if cpu == 'aarch64' and not mingw_has_setjmp_longjmp + error('mingw must provide setjmp/longjmp for windows-arm64') + endif +endif + ######################## # Target configuration # ########################
Windows implementation of setjmp/longjmp is done in C:/WINDOWS/system32/ucrtbase.dll. Alas, on arm64, it seems to *always* perform stack unwinding, which crashes from generated code. By using alternative implementation built in mingw, we avoid doing stack unwinding and this fixes crash when calling longjmp. Signed-off-by: Pierrick Bouvier <pierrick.bouvier@linaro.org> --- include/sysemu/os-win32.h | 25 +++++++++++++++++++++++-- meson.build | 24 ++++++++++++++++++++++++ 2 files changed, 47 insertions(+), 2 deletions(-)