* [Bug tapsets/3634] New: scheduler.ctxswitch doesn't resolve on x86_64
@ 2006-12-04 18:59 mmlnx at us dot ibm dot com
2006-12-04 21:51 ` [Bug tapsets/3634] " joshua dot i dot stone at intel dot com
2010-08-16 19:17 ` fche at redhat dot com
0 siblings, 2 replies; 3+ messages in thread
From: mmlnx at us dot ibm dot com @ 2006-12-04 18:59 UTC (permalink / raw)
To: systemtap
The scheduler.ctxswitch alias in scheduler.stp doesn't work on x86_64. This
alias probes __switch_to, which is marked with __kprobes in x86_64 and thus
cannot be probed.
--
Summary: scheduler.ctxswitch doesn't resolve on x86_64
Product: systemtap
Version: unspecified
Status: NEW
Severity: normal
Priority: P2
Component: tapsets
AssignedTo: systemtap at sources dot redhat dot com
ReportedBy: mmlnx at us dot ibm dot com
http://sourceware.org/bugzilla/show_bug.cgi?id=3634
------- You are receiving this mail because: -------
You are the assignee for the bug, or are watching the assignee.
^ permalink raw reply [flat|nested] 3+ messages in thread
* [Bug tapsets/3634] scheduler.ctxswitch doesn't resolve on x86_64
2006-12-04 18:59 [Bug tapsets/3634] New: scheduler.ctxswitch doesn't resolve on x86_64 mmlnx at us dot ibm dot com
@ 2006-12-04 21:51 ` joshua dot i dot stone at intel dot com
2010-08-16 19:17 ` fche at redhat dot com
1 sibling, 0 replies; 3+ messages in thread
From: joshua dot i dot stone at intel dot com @ 2006-12-04 21:51 UTC (permalink / raw)
To: systemtap
------- Additional Comments From joshua dot i dot stone at intel dot com 2006-12-04 20:09 -------
This is known -- __switch_to was blocked on x86_64 due to bug #2068. It also
fails on IA64, where __switch_to is a macro.
The only reason that scheduler.ctxswitch exists is because there are still some
problems with accessing parameters in inline functions. (See bug #1155)
Otherwise, scheduler.cpu_on and scheduler.cpu_off are the preferred, portable
probe points.
If you only need 'prev', use cpu_off, which fires in the context of the previous
task. If you need 'next', use cpu_on, which fires in the context of the new task.
If you need both, then unfortunately you'll have to put two probes. Once bug
#1155 is resolved, then either cpu_on or cpu_off will give you access to both
'prev' and 'next', but until then you'll have to kludge something together.
--
http://sourceware.org/bugzilla/show_bug.cgi?id=3634
------- You are receiving this mail because: -------
You are the assignee for the bug, or are watching the assignee.
^ permalink raw reply [flat|nested] 3+ messages in thread
* [Bug tapsets/3634] scheduler.ctxswitch doesn't resolve on x86_64
2006-12-04 18:59 [Bug tapsets/3634] New: scheduler.ctxswitch doesn't resolve on x86_64 mmlnx at us dot ibm dot com
2006-12-04 21:51 ` [Bug tapsets/3634] " joshua dot i dot stone at intel dot com
@ 2010-08-16 19:17 ` fche at redhat dot com
1 sibling, 0 replies; 3+ messages in thread
From: fche at redhat dot com @ 2010-08-16 19:17 UTC (permalink / raw)
To: systemtap
------- Additional Comments From fche at redhat dot com 2010-08-16 19:17 -------
works on fedora13 / rhel5
--
What |Removed |Added
----------------------------------------------------------------------------
Status|NEW |RESOLVED
Resolution| |WORKSFORME
http://sourceware.org/bugzilla/show_bug.cgi?id=3634
------- You are receiving this mail because: -------
You are the assignee for the bug, or are watching the assignee.
^ permalink raw reply [flat|nested] 3+ messages in thread
end of thread, other threads:[~2010-08-16 19:17 UTC | newest]
Thread overview: 3+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2006-12-04 18:59 [Bug tapsets/3634] New: scheduler.ctxswitch doesn't resolve on x86_64 mmlnx at us dot ibm dot com
2006-12-04 21:51 ` [Bug tapsets/3634] " joshua dot i dot stone at intel dot com
2010-08-16 19:17 ` fche at redhat dot com
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for read-only IMAP folder(s) and NNTP newsgroup(s).