Re: [PATCH] x86/signals: Fix lower/upper bound reporting in compat siginfo
On 04/04/2017 02:53 PM, Joerg Roedel wrote: > On Tue, Apr 04, 2017 at 09:56:45AM -0700, Dave Hansen wrote: >> On 04/04/2017 09:15 AM, Joerg Roedel wrote: >>> Put the right values from the original siginfo into the >>> userspace compat-siginfo. >>> >>> This fixes the 32-bit mpx tabletest on a 64-bit kernel. >> >> Ugh, thanks for finding that. > > Yeah, I was also looking at the vaddrexhaust test, but is that supposed > to work? It does pretty weird things at least, on 64 bit the function > effectivly does nothing because nr_to_fill evaluates to 0 there, and on > 32 bit it gets a (probably #BF) exception which is not caught, so that > the test fails. > > I am a bit confused, but maybe I just didn't stare long enough at it :-) > Hope you can sched some light on it. That code can probably just get removed from the tests. I haven't run it in a while and it's probably not worth refreshing.
Re: [PATCH] x86/signals: Fix lower/upper bound reporting in compat siginfo
On 04/04/2017 02:53 PM, Joerg Roedel wrote: > On Tue, Apr 04, 2017 at 09:56:45AM -0700, Dave Hansen wrote: >> On 04/04/2017 09:15 AM, Joerg Roedel wrote: >>> Put the right values from the original siginfo into the >>> userspace compat-siginfo. >>> >>> This fixes the 32-bit mpx tabletest on a 64-bit kernel. >> >> Ugh, thanks for finding that. > > Yeah, I was also looking at the vaddrexhaust test, but is that supposed > to work? It does pretty weird things at least, on 64 bit the function > effectivly does nothing because nr_to_fill evaluates to 0 there, and on > 32 bit it gets a (probably #BF) exception which is not caught, so that > the test fails. > > I am a bit confused, but maybe I just didn't stare long enough at it :-) > Hope you can sched some light on it. That code can probably just get removed from the tests. I haven't run it in a while and it's probably not worth refreshing.
Re: [PATCH] x86/signals: Fix lower/upper bound reporting in compat siginfo
On Tue, Apr 04, 2017 at 09:56:45AM -0700, Dave Hansen wrote: > On 04/04/2017 09:15 AM, Joerg Roedel wrote: > > Put the right values from the original siginfo into the > > userspace compat-siginfo. > > > > This fixes the 32-bit mpx tabletest on a 64-bit kernel. > > Ugh, thanks for finding that. Yeah, I was also looking at the vaddrexhaust test, but is that supposed to work? It does pretty weird things at least, on 64 bit the function effectivly does nothing because nr_to_fill evaluates to 0 there, and on 32 bit it gets a (probably #BF) exception which is not caught, so that the test fails. I am a bit confused, but maybe I just didn't stare long enough at it :-) Hope you can sched some light on it. Joerg
Re: [PATCH] x86/signals: Fix lower/upper bound reporting in compat siginfo
On Tue, Apr 04, 2017 at 09:56:45AM -0700, Dave Hansen wrote: > On 04/04/2017 09:15 AM, Joerg Roedel wrote: > > Put the right values from the original siginfo into the > > userspace compat-siginfo. > > > > This fixes the 32-bit mpx tabletest on a 64-bit kernel. > > Ugh, thanks for finding that. Yeah, I was also looking at the vaddrexhaust test, but is that supposed to work? It does pretty weird things at least, on 64 bit the function effectivly does nothing because nr_to_fill evaluates to 0 there, and on 32 bit it gets a (probably #BF) exception which is not caught, so that the test fails. I am a bit confused, but maybe I just didn't stare long enough at it :-) Hope you can sched some light on it. Joerg
Re: [PATCH] x86/signals: Fix lower/upper bound reporting in compat siginfo
On 04/04/2017 09:15 AM, Joerg Roedel wrote: > Put the right values from the original siginfo into the > userspace compat-siginfo. > > This fixes the 32-bit mpx tabletest on a 64-bit kernel. Ugh, thanks for finding that. Acked-by: Dave Hansen
Re: [PATCH] x86/signals: Fix lower/upper bound reporting in compat siginfo
On 04/04/2017 09:15 AM, Joerg Roedel wrote: > Put the right values from the original siginfo into the > userspace compat-siginfo. > > This fixes the 32-bit mpx tabletest on a 64-bit kernel. Ugh, thanks for finding that. Acked-by: Dave Hansen
[PATCH] x86/signals: Fix lower/upper bound reporting in compat siginfo
From: Joerg RoedelPut the right values from the original siginfo into the userspace compat-siginfo. This fixes the 32-bit mpx tabletest on a 64-bit kernel. Fixes: a4455082dc6f0 ('x86/signals: Add missing signal_compat code for x86 features') Cc: Dave Hansen Signed-off-by: Joerg Roedel --- arch/x86/kernel/signal_compat.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/x86/kernel/signal_compat.c b/arch/x86/kernel/signal_compat.c index ec1f756..71beb28 100644 --- a/arch/x86/kernel/signal_compat.c +++ b/arch/x86/kernel/signal_compat.c @@ -151,8 +151,8 @@ int __copy_siginfo_to_user32(compat_siginfo_t __user *to, const siginfo_t *from, if (from->si_signo == SIGSEGV) { if (from->si_code == SEGV_BNDERR) { - compat_uptr_t lower = (unsigned long)>si_lower; - compat_uptr_t upper = (unsigned long)>si_upper; + compat_uptr_t lower = (unsigned long)from->si_lower; + compat_uptr_t upper = (unsigned long)from->si_upper; put_user_ex(lower, >si_lower); put_user_ex(upper, >si_upper); } -- 1.9.1
[PATCH] x86/signals: Fix lower/upper bound reporting in compat siginfo
From: Joerg Roedel Put the right values from the original siginfo into the userspace compat-siginfo. This fixes the 32-bit mpx tabletest on a 64-bit kernel. Fixes: a4455082dc6f0 ('x86/signals: Add missing signal_compat code for x86 features') Cc: Dave Hansen Signed-off-by: Joerg Roedel --- arch/x86/kernel/signal_compat.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/x86/kernel/signal_compat.c b/arch/x86/kernel/signal_compat.c index ec1f756..71beb28 100644 --- a/arch/x86/kernel/signal_compat.c +++ b/arch/x86/kernel/signal_compat.c @@ -151,8 +151,8 @@ int __copy_siginfo_to_user32(compat_siginfo_t __user *to, const siginfo_t *from, if (from->si_signo == SIGSEGV) { if (from->si_code == SEGV_BNDERR) { - compat_uptr_t lower = (unsigned long)>si_lower; - compat_uptr_t upper = (unsigned long)>si_upper; + compat_uptr_t lower = (unsigned long)from->si_lower; + compat_uptr_t upper = (unsigned long)from->si_upper; put_user_ex(lower, >si_lower); put_user_ex(upper, >si_upper); } -- 1.9.1