Re: [RFC PATCH 8/8] perf probe powerpc: Fixup function entry if using kallsyms lookup
From: Arnaldo Carvalho de Melo <acme@kernel.org>
Date: 2014-12-09 21:14:07
Also in:
lkml
Em Tue, Dec 09, 2014 at 11:04:06PM +0530, Naveen N. Rao escreveu:
On powerpc ABIv2, if no debug-info is found and we use kallsyms, we need to fixup the function entry to point to the local entry point. Use offset of 8 since current toolchains always generate 2 instructions (8 bytes).
Hi Michael and Ananth, may I have your Acked-by or Reviewed-by for these patches? The ones, like this, that are affects only ppc I'm can assume was tested and applying it won't break other arch users, but having a/rev-by from ppc developers should speed up this process. Thanks, - Arnaldo
quoted hunk ↗ jump to hunk
Signed-off-by: Naveen N. Rao <redacted> --- tools/perf/util/probe-event.c | 9 +++++++++ 1 file changed, 9 insertions(+)diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c index adcdbd2..0970e2a 100644 --- a/tools/perf/util/probe-event.c +++ b/tools/perf/util/probe-event.c@@ -2318,6 +2318,15 @@ static int find_probe_trace_events_from_map(struct perf_probe_event *pev, } /* Add one probe point */ tp->address = map->unmap_ip(map, sym->start) + pp->offset; +#if defined(__powerpc64__) && defined(_CALL_ELF) && _CALL_ELF == 2 + /* + * If we used kallsyms, we should fixup the function entry address here. + * ppc64le ABIv2 local entry point is currently always 2 instructions (8 bytes) + * after the global entry point. Fix this if it ever changes. + */ + if (!pev->uprobes && map->dso->symtab_type == DSO_BINARY_TYPE__KALLSYMS) + tp->address += 8; +#endif if (reloc_sym) { tp->symbol = strdup_or_goto(reloc_sym->name, nomem_out); tp->offset = tp->address - reloc_sym->addr;-- 2.1.3