Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]

Groups > linux.kernel > #1441393 > unrolled thread

Re: [PATCH 3/4] x86: Rewrite switch_to() code

Back to article view | Back to linux.kernel

This discussion starts older than the indexed window; earlier articles aren't shown. The article labeled Started by below is the oldest one visible, not the original post.

Contents

  Re: [PATCH 3/4] x86: Rewrite switch_to() code Josh Poimboeuf <jpoimboe@redhat.com> - 2016-07-12 16:20 +0200

#1441393 — Re: [PATCH 3/4] x86: Rewrite switch_to() code

On Mon, May 23, 2016 at 10:03:54AM -0700, Andy Lutomirski wrote:
> Do you have any understanding of why there are so many unwinder
> implementations?  Your reliable unwinder seems to be yet another copy
> of more or less the same code.
> 
> I'd like to see a single, high-quality unwinder implemented as a state
> machine, along the lines of:
> 
> struct unwind_state state;
> unwind_start_inactive_task(&state, ...); or
> unwind_start_pt_regs(&state, regs); or whatever.
> unwind_next_frame(&state);
> 
> where, after unwind_next_frame, state encodes whatever registers are
> known (at least bp and ip, but all the GPRs would be nice and are
> probably mandatory for DWARF) and an indication of whether this is a
> real frame or a guessed frame (the things that currently show up as
> '?').

FYI, I'm working on something very similar to this which replaces
dump_trace().  The frame pointer encoding patches were going to require
more changes to the unwinder than I expected, and more callback sprawl.
So it looks like it's going to be easier to just go ahead and rewrite
the unwinder first.

-- 
Josh

[toc] | [standalone]

Back to top | Article view | linux.kernel

csiph-web