On Fri, Jun 14, 2019 at 08:31:53AM -0700, Alexei Starovoitov wrote:
> On Fri, Jun 14, 2019 at 6:34 AM Josh Poimboeuf wrote:
> >
> > On Thu, Jun 13, 2019 at 11:00:09PM -0700, Alexei Starovoitov wrote:
> > > > + if (src_reg == BPF_REG_FP) {
> > > > + /*
> > > > +* If the valu
On Fri, Jun 14, 2019 at 6:34 AM Josh Poimboeuf wrote:
>
> On Thu, Jun 13, 2019 at 11:00:09PM -0700, Alexei Starovoitov wrote:
> > > + if (src_reg == BPF_REG_FP) {
> > > + /*
> > > +* If the value was copied from RBP (real frame pointer),
> > > +* adjust it to th
On Fri, Jun 14, 2019 at 12:41 AM Peter Zijlstra wrote:
>
> On Thu, Jun 13, 2019 at 11:00:09PM -0700, Alexei Starovoitov wrote:
>
> > There is something wrong with
> > commit d15d356887e7 ("perf/x86: Make perf callchains work without
> > CONFIG_FRAME_POINTER")
>
> It assumes we can always unwind s
On Thu, Jun 13, 2019 at 11:00:09PM -0700, Alexei Starovoitov wrote:
> > + if (src_reg == BPF_REG_FP) {
> > + /*
> > +* If the value was copied from RBP (real frame pointer),
> > +* adjust it to the BPF program's frame pointer value.
> > +*
> > +
On Fri, Jun 14, 2019 at 09:41:37AM +0200, Peter Zijlstra wrote:
> On Thu, Jun 13, 2019 at 11:00:09PM -0700, Alexei Starovoitov wrote:
>
> > There is something wrong with
> > commit d15d356887e7 ("perf/x86: Make perf callchains work without
> > CONFIG_FRAME_POINTER")
>
> It assumes we can always
On Thu, Jun 13, 2019 at 11:00:09PM -0700, Alexei Starovoitov wrote:
> There is something wrong with
> commit d15d356887e7 ("perf/x86: Make perf callchains work without
> CONFIG_FRAME_POINTER")
It assumes we can always unwind stack, which is, imo, not a weird thing.
> If I simply revert it and h
On Thu, Jun 13, 2019 at 11:50:37PM -0500, Josh Poimboeuf wrote:
> On Thu, Jun 13, 2019 at 09:28:48PM -0500, Josh Poimboeuf wrote:
> > On Thu, Jun 13, 2019 at 08:58:48PM -0500, Josh Poimboeuf wrote:
> > > On Thu, Jun 13, 2019 at 06:42:45PM -0700, Alexei Starovoitov wrote:
> > > > On Thu, Jun 13, 201
On Thu, Jun 13, 2019 at 09:28:48PM -0500, Josh Poimboeuf wrote:
> On Thu, Jun 13, 2019 at 08:58:48PM -0500, Josh Poimboeuf wrote:
> > On Thu, Jun 13, 2019 at 06:42:45PM -0700, Alexei Starovoitov wrote:
> > > On Thu, Jun 13, 2019 at 08:30:51PM -0500, Josh Poimboeuf wrote:
> > > > On Thu, Jun 13, 201
On Thu, Jun 13, 2019 at 08:58:48PM -0500, Josh Poimboeuf wrote:
> On Thu, Jun 13, 2019 at 06:42:45PM -0700, Alexei Starovoitov wrote:
> > On Thu, Jun 13, 2019 at 08:30:51PM -0500, Josh Poimboeuf wrote:
> > > On Thu, Jun 13, 2019 at 03:00:55PM -0700, Alexei Starovoitov wrote:
> > > > > @@ -392,8 +40
On Thu, Jun 13, 2019 at 06:42:45PM -0700, Alexei Starovoitov wrote:
> On Thu, Jun 13, 2019 at 08:30:51PM -0500, Josh Poimboeuf wrote:
> > On Thu, Jun 13, 2019 at 03:00:55PM -0700, Alexei Starovoitov wrote:
> > > > @@ -392,8 +402,16 @@ bool unwind_next_frame(struct unwind_state *state)
> > > >
On Thu, Jun 13, 2019 at 08:30:51PM -0500, Josh Poimboeuf wrote:
> On Thu, Jun 13, 2019 at 03:00:55PM -0700, Alexei Starovoitov wrote:
> > > @@ -392,8 +402,16 @@ bool unwind_next_frame(struct unwind_state *state)
> > >* calls and calls to noreturn functions.
> > >*/
> > > orc = orc_find(st
On Thu, Jun 13, 2019 at 03:00:55PM -0700, Alexei Starovoitov wrote:
> > @@ -392,8 +402,16 @@ bool unwind_next_frame(struct unwind_state *state)
> > * calls and calls to noreturn functions.
> > */
> > orc = orc_find(state->signal ? state->ip : state->ip - 1);
> > - if (!orc)
> > -
On Thu, Jun 13, 2019 at 08:21:04AM -0500, Josh Poimboeuf wrote:
> The ORC unwinder can't unwind through BPF JIT generated code because
> there are no ORC entries associated with the code.
>
> If an ORC entry isn't available, try to fall back to frame pointers. If
> BPF and other generated code al
The ORC unwinder can't unwind through BPF JIT generated code because
there are no ORC entries associated with the code.
If an ORC entry isn't available, try to fall back to frame pointers. If
BPF and other generated code always do frame pointer setup (even with
CONFIG_FRAME_POINTERS=n) then this
14 matches
Mail list logo
