notify_page_fault_chain
All,
I just noticed this addition to i386 and x86-64, conditionalized upon CONFIG_KPROBES. May I ask what the motivation for this compatibility breaking change is? Only performance? I consider it already questionable to split out a specific fault from the general die notification (previous users of the functionality all of the sudden won't get notifications for one of the most crucial faults anymore), but entirely hiding the functionality (unavailable without CONFIG_KPROBES, and even with it not getting exported) is really odd.
Thanks for any clarification,
Jan
Quoted 2 lines · Jan Beulich
I just noticed this addition to i386 and x86-64, conditionalized upon
CONFIG_KPROBES. May I ask what the motivation for this compatibility breaking change is?
It's normally policy to only care about in tree code regarding exports and hooks. But also no policy without exceptions.
Quoted 1 line
Only performance?
Christopher L. complained about it taking too long on IA64 I think (but that might have been some IA64 specific quirk)
I think I proposed to use a inline check of the chain and only then call the external function, but that might not have been implemented that way.
Quoted 4 lines
I consider it already questionable to split out a specific
fault from the general die notification (previous users of the functionality all of the sudden won't get notifications for one of the most crucial faults anymore), but entirely hiding the functionality (unavailable withoutCONFIG_KPROBES, and even with it not getting exported) is really odd.
You want to use it for your debugger?
-Andi
Quoted 2 lines
Quoted 2 lines
I consider it already questionable to split out a specific
fault from the general die notification (previous users of the functionality all of the sudden won't get
notifications
Quoted 1 line
Quoted 1 line
for one of the most crucial faults anymore), but entirely hiding the functionality (unavailable without
CONFIG_KPROBES,
Quoted 3 lines
Quoted 1 line
and even with it not getting exported) is really odd.
You want to use it for your debugger?
Yes, in its "light" form (i.e. without exception handling framework changes) it has to rely on this infrastructure.
Jan
Quoted 10 lines · Jan Beulich
Quoted 2 lines
Quoted 2 lines
I consider it already questionable to split out a specific
fault from the general die notification (previous users of the functionality all of the sudden won't getnotifications
Quoted 1 line
Quoted 1 line
for one of the most crucial faults anymore), but entirely hiding the functionality (unavailable without
CONFIG_KPROBES,Quoted 3 lines
Quoted 1 line
and even with it not getting exported) is really odd.
You want to use it for your debugger?
Yes, in its "light" form (i.e. without exception handling framework changes) it has to rely on this infrastructure.
Ok. I can make it unconditional and export it.
-Andi
Quoted 7 lines · "Jan Beulich" (on Mon, 07 Aug 2006 14:22:54 +0100) wrote:
All,
I just noticed this addition to i386 and x86-64, conditionalized upon
CONFIG_KPROBES. May I ask what the motivation for this compatibility breaking change is? Only performance? I consider it already questionable to split out a specific fault from the general die notification (previous users of the functionality all of the sudden won't get notifications for one of the most crucial faults anymore), but entirely hiding the functionality (unavailable withoutCONFIG_KPROBES, and even with it not getting exported) is really odd.
Running all callbacks on the notify_die chain for every page fault was causing a significant slowdown on large machines, especially when the callback chain included heartbeat monitors, kernel debuggers and cross partition NUMA access routines.
Only kprobes needs to know about page faults, none of the other callbacks care about page faults. So the notify_page_fault_chain chain was added just for kprobes use, and made conditional on CONFIG_KPROBES. That way only kprobed systems need to suffer the slowdown in page faulting.