public inbox for systemtap@sourceware.org
 help / color / mirror / Atom feed
* [Bug kprobes/2945] New: cannot probe vgettimeofday on x86_64
@ 2006-07-20 18:30 hunt at redhat dot com
  2006-07-21  6:19 ` [Bug kprobes/2945] " bibo dot mao at intel dot com
                   ` (3 more replies)
  0 siblings, 4 replies; 5+ messages in thread
From: hunt at redhat dot com @ 2006-07-20 18:30 UTC (permalink / raw)
  To: systemtap

> uname -a
Linux tiger 2.6.9-42.ELsmp #1 SMP Wed Jul 12 23:32:02 EDT 2006 x86_64 x86_64
x86_64 GNU/Linux

> stap -e 'probe kernel.function("vgettimeofday") {}'
ERROR: probe 0 registration failed, rc=1,
kernel.function("vgettimeofday@arch/x86_64/kernel/vsyscall.c:126")

-- 
           Summary: cannot probe vgettimeofday on x86_64
           Product: systemtap
           Version: unspecified
            Status: NEW
          Severity: normal
          Priority: P2
         Component: kprobes
        AssignedTo: systemtap at sources dot redhat dot com
        ReportedBy: hunt at redhat dot com


http://sourceware.org/bugzilla/show_bug.cgi?id=2945

------- You are receiving this mail because: -------
You are the assignee for the bug, or are watching the assignee.

^ permalink raw reply	[flat|nested] 5+ messages in thread

* [Bug kprobes/2945] cannot probe vgettimeofday on x86_64
  2006-07-20 18:30 [Bug kprobes/2945] New: cannot probe vgettimeofday on x86_64 hunt at redhat dot com
@ 2006-07-21  6:19 ` bibo dot mao at intel dot com
  2006-11-16 16:11 ` jkenisto at us dot ibm dot com
                   ` (2 subsequent siblings)
  3 siblings, 0 replies; 5+ messages in thread
From: bibo dot mao at intel dot com @ 2006-07-21  6:19 UTC (permalink / raw)
  To: systemtap


------- Additional Comments From bibo dot mao at intel dot com  2006-07-21 06:19 -------
vgettimeofday can be called by application in user mode, now in x86_64 function 
address of vgettimeofday is outside of kernel_text_address() scope, so it 
failed to register kprobe for this function.

-- 


http://sourceware.org/bugzilla/show_bug.cgi?id=2945

------- You are receiving this mail because: -------
You are the assignee for the bug, or are watching the assignee.

^ permalink raw reply	[flat|nested] 5+ messages in thread

* [Bug kprobes/2945] cannot probe vgettimeofday on x86_64
  2006-07-20 18:30 [Bug kprobes/2945] New: cannot probe vgettimeofday on x86_64 hunt at redhat dot com
  2006-07-21  6:19 ` [Bug kprobes/2945] " bibo dot mao at intel dot com
@ 2006-11-16 16:11 ` jkenisto at us dot ibm dot com
  2006-11-16 20:15 ` jkenisto at us dot ibm dot com
  2006-11-17  1:44 ` fche at redhat dot com
  3 siblings, 0 replies; 5+ messages in thread
From: jkenisto at us dot ibm dot com @ 2006-11-16 16:11 UTC (permalink / raw)
  To: systemtap


------- Additional Comments From jkenisto at us dot ibm dot com  2006-11-16 01:25 -------
Consider allowing probes on weird locations like i386 vtoc page, x86_64
.vsyscall_ section, etc.

-- 


http://sourceware.org/bugzilla/show_bug.cgi?id=2945

------- You are receiving this mail because: -------
You are the assignee for the bug, or are watching the assignee.

^ permalink raw reply	[flat|nested] 5+ messages in thread

* [Bug kprobes/2945] cannot probe vgettimeofday on x86_64
  2006-07-20 18:30 [Bug kprobes/2945] New: cannot probe vgettimeofday on x86_64 hunt at redhat dot com
  2006-07-21  6:19 ` [Bug kprobes/2945] " bibo dot mao at intel dot com
  2006-11-16 16:11 ` jkenisto at us dot ibm dot com
@ 2006-11-16 20:15 ` jkenisto at us dot ibm dot com
  2006-11-17  1:44 ` fche at redhat dot com
  3 siblings, 0 replies; 5+ messages in thread
From: jkenisto at us dot ibm dot com @ 2006-11-16 20:15 UTC (permalink / raw)
  To: systemtap


------- Additional Comments From jkenisto at us dot ibm dot com  2006-11-16 18:07 -------
Further thoughts:
- vdso, not vtoc. (Haste and advanced age are a bad combo. :-})
- Since a kprobed instruction is copied into a kernel-space buffer and
single-stepped there, we do NOT want to allow kprobes on instructions that are
executed in user mode, such as on the vdso page.

-- 


http://sourceware.org/bugzilla/show_bug.cgi?id=2945

------- You are receiving this mail because: -------
You are the assignee for the bug, or are watching the assignee.

^ permalink raw reply	[flat|nested] 5+ messages in thread

* [Bug kprobes/2945] cannot probe vgettimeofday on x86_64
  2006-07-20 18:30 [Bug kprobes/2945] New: cannot probe vgettimeofday on x86_64 hunt at redhat dot com
                   ` (2 preceding siblings ...)
  2006-11-16 20:15 ` jkenisto at us dot ibm dot com
@ 2006-11-17  1:44 ` fche at redhat dot com
  3 siblings, 0 replies; 5+ messages in thread
From: fche at redhat dot com @ 2006-11-17  1:44 UTC (permalink / raw)
  To: systemtap


------- Additional Comments From fche at redhat dot com  2006-11-16 23:37 -------
(In reply to comment #3)
> [...]
> - Since a kprobed instruction is copied into a kernel-space buffer and
> single-stepped there, we do NOT want to allow kprobes on instructions that are
> executed in user mode, such as on the vdso page.

Good point.  We should leave vdso type probes to user-space probing.

-- 
           What    |Removed                     |Added
----------------------------------------------------------------------------
             Status|NEW                         |RESOLVED
         Resolution|                            |INVALID


http://sourceware.org/bugzilla/show_bug.cgi?id=2945

------- You are receiving this mail because: -------
You are the assignee for the bug, or are watching the assignee.

^ permalink raw reply	[flat|nested] 5+ messages in thread

end of thread, other threads:[~2006-11-16 23:37 UTC | newest]

Thread overview: 5+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2006-07-20 18:30 [Bug kprobes/2945] New: cannot probe vgettimeofday on x86_64 hunt at redhat dot com
2006-07-21  6:19 ` [Bug kprobes/2945] " bibo dot mao at intel dot com
2006-11-16 16:11 ` jkenisto at us dot ibm dot com
2006-11-16 20:15 ` jkenisto at us dot ibm dot com
2006-11-17  1:44 ` 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).