Bug 931 - Kprobes: separate stacks for kprobes handlers
Summary: Kprobes: separate stacks for kprobes handlers
Alias: None
Product: systemtap
Classification: Unclassified
Component: kprobes (show other bugs)
Version: unspecified
: P3 enhancement
Target Milestone: ---
Assignee: Jim Keniston
Depends on:
Blocks: 912
  Show dependency treegraph
Reported: 2005-05-05 17:33 UTC by Frank Ch. Eigler
Modified: 2007-05-08 19:24 UTC (History)
0 users

See Also:
Last reconfirmed:

Run kprobes handlers on a separate stack - i386 (1017 bytes, patch)
2005-05-11 19:49 UTC, Jim Keniston
Details | Diff

Note You need to log in before you can comment on or make changes to this bug.
Description Frank Ch. Eigler 2005-05-05 17:33:44 UTC
separate per-cpu stacks for executing kprobes handlers
arrange to disable interrupts during handler execution
Comment 1 Jim Keniston 2005-05-11 19:49:13 UTC
Created attachment 484 [details]
Run kprobes handlers on a separate stack - i386

This patch is described in my SystemTap posting of 5/11/05 and in CVS:
patches/kprobe_stack (sic).
Comment 2 Jim Keniston 2005-05-11 19:50:52 UTC
I've attached a working prototype for i386.
Comment 3 Jim Keniston 2005-11-17 22:58:12 UTC
The necessity for this feature is diminished significantly by the SystemTap
translator's practice of statically allocating space for the handler's "local"
Comment 4 Frank Ch. Eigler 2005-11-18 17:47:38 UTC
That practice was factored in at the time this suggestion was initially raised.
 We still use probably a few hundred bytes of stack, just with kprobes and
translator artifacts.  The question was whether even those few hundred could
pose a problem.
Comment 5 Frank Ch. Eigler 2007-05-08 20:24:20 UTC
Systemtap probe handlers now check for a minimum of available stack space upon
entry, so maybe we don't need to pursue this any more.