From: Arnaldo Carvalho de Melo <acme@kernel.org>
To: Milian Wolff <milian.wolff@kdab.com>
Cc: Jiri Olsa <jolsa@kernel.org>, Jin Yao <yao.jin@linux.intel.com>,
Linux-kernel@vger.kernel.org, linux-perf-users@vger.kernel.org,
Arnaldo Carvalho de Melo <acme@redhat.com>,
David Ahern <dsahern@gmail.com>,
Namhyung Kim <namhyung@kernel.org>,
Peter Zijlstra <peterz@infradead.org>,
Ravi Bangoria <ravi.bangoria@linux.vnet.ibm.com>
Subject: Re: [PATCH v5 11/16] perf report: properly handle branch count in match_chain
Date: Fri, 13 Oct 2017 11:08:34 -0300 [thread overview]
Message-ID: <20171013140834.GO3503@kernel.org> (raw)
In-Reply-To: <20171013133903.GN3503@kernel.org>
Em Fri, Oct 13, 2017 at 10:39:03AM -0300, Arnaldo Carvalho de Melo escreveu:
> Em Mon, Oct 09, 2017 at 10:33:05PM +0200, Milian Wolff escreveu:
> > Some of the code paths I introduced before returned too early
> > without running the code to handle a node's branch count.
> > By refactoring match_chain to only have one exit point, this
> > can be remedied.
>
> Fixing up this one now.
Millian, this is all fresher in your mind, can you please take a look at
my perf/core branch and check if the change i made to ]PATCH v5 09/16]
"perf report: compare symbol name for inlined frames when matching" is
ok wrt Ravi's fix and then, please, rebase v5 on top of what is there?
Ravi, please take a look at this as well, to see if with these changes
your fix remains valid, ok?
Thanks,
- Arnaldo
> > Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
> > Cc: David Ahern <dsahern@gmail.com>
> > Cc: Namhyung Kim <namhyung@kernel.org>
> > Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
> > Cc: Yao Jin <yao.jin@linux.intel.com>
> > Signed-off-by: Milian Wolff <milian.wolff@kdab.com>
> > ---
> > tools/perf/util/callchain.c | 117 +++++++++++++++++++++++---------------------
> > 1 file changed, 60 insertions(+), 57 deletions(-)
> >
> > diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c
> > index 3f1431bf71bd..782de047c902 100644
> > --- a/tools/perf/util/callchain.c
> > +++ b/tools/perf/util/callchain.c
> > @@ -666,78 +666,81 @@ static enum match_result match_chain_strings(const char *left,
> > return ret;
> > }
> >
> > +static enum match_result match_address(u64 left, u64 right)
> > +{
> > + if (left == right)
> > + return MATCH_EQ;
> > + else if (left < right)
> > + return MATCH_LT;
> > + else
> > + return MATCH_GT;
> > +}
> > +
> > static enum match_result match_chain(struct callchain_cursor_node *node,
> > struct callchain_list *cnode)
> > {
> > - struct symbol *sym = node->sym;
> > - enum match_result match;
> > - u64 left, right;
> > + enum match_result match = MATCH_ERROR;
> >
> > - if (callchain_param.key == CCKEY_SRCLINE) {
> > + switch (callchain_param.key) {
> > + case CCKEY_SRCLINE:
> > match = match_chain_strings(cnode->srcline, node->srcline);
> > -
> > - /* if no srcline is available, fallback to symbol name */
> > - if (match == MATCH_ERROR && cnode->ms.sym && node->sym)
> > - match = match_chain_strings(cnode->ms.sym->name,
> > - node->sym->name);
> > -
> > if (match != MATCH_ERROR)
> > - return match;
> > -
> > - /* otherwise fall-back to IP-based comparison below */
> > - }
> > -
> > - if (cnode->ms.sym && sym && callchain_param.key == CCKEY_FUNCTION) {
> > - /* compare inlined frames based on their symbol name because
> > - * different inlined frames will have the same symbol start
> > - */
> > - if (cnode->ms.sym->inlined || node->sym->inlined)
> > - return match_chain_strings(cnode->ms.sym->name,
> > - node->sym->name);
> > -
> > - left = cnode->ms.sym->start;
> > - right = sym->start;
> > - } else {
> > - left = cnode->ip;
> > - right = node->ip;
> > + break;
> > + __fallthrough;
> > + case CCKEY_FUNCTION:
> > + if (node->sym && cnode->ms.sym) {
> > + /* compare inlined frames based on their symbol name
> > + * because different inlined frames will have the same
> > + * symbol start. otherwise do a faster comparison based
> > + * on the symbol start address
> > + */
> > + if (cnode->ms.sym->inlined || node->sym->inlined)
> > + match = match_chain_strings(cnode->ms.sym->name,
> > + node->sym->name);
> > + else
> > + match = match_address(cnode->ms.sym->start,
> > + node->sym->start);
> > + if (match != MATCH_ERROR)
> > + break;
> > + }
> > + __fallthrough;
> > + case CCKEY_ADDRESS:
> > + default:
> > + match = match_address(cnode->ip, node->ip);
> > + break;
> > }
> >
> > - if (left == right) {
> > - if (node->branch) {
> > - cnode->branch_count++;
> > + if (match == MATCH_EQ && node->branch) {
> > + cnode->branch_count++;
> >
> > - if (node->branch_from) {
> > - /*
> > - * It's "to" of a branch
> > - */
> > - cnode->brtype_stat.branch_to = true;
> > + if (node->branch_from) {
> > + /*
> > + * It's "to" of a branch
> > + */
> > + cnode->brtype_stat.branch_to = true;
> >
> > - if (node->branch_flags.predicted)
> > - cnode->predicted_count++;
> > + if (node->branch_flags.predicted)
> > + cnode->predicted_count++;
> >
> > - if (node->branch_flags.abort)
> > - cnode->abort_count++;
> > + if (node->branch_flags.abort)
> > + cnode->abort_count++;
> >
> > - branch_type_count(&cnode->brtype_stat,
> > - &node->branch_flags,
> > - node->branch_from,
> > - node->ip);
> > - } else {
> > - /*
> > - * It's "from" of a branch
> > - */
> > - cnode->brtype_stat.branch_to = false;
> > - cnode->cycles_count +=
> > - node->branch_flags.cycles;
> > - cnode->iter_count += node->nr_loop_iter;
> > - cnode->iter_cycles += node->iter_cycles;
> > - }
> > + branch_type_count(&cnode->brtype_stat,
> > + &node->branch_flags,
> > + node->branch_from,
> > + node->ip);
> > + } else {
> > + /*
> > + * It's "from" of a branch
> > + */
> > + cnode->brtype_stat.branch_to = false;
> > + cnode->cycles_count += node->branch_flags.cycles;
> > + cnode->iter_count += node->nr_loop_iter;
> > + cnode->iter_cycles += node->iter_cycles;
> > }
> > -
> > - return MATCH_EQ;
> > }
> >
> > - return left > right ? MATCH_GT : MATCH_LT;
> > + return match;
> > }
> >
> > /*
> > --
> > 2.14.2
next prev parent reply other threads:[~2017-10-13 14:08 UTC|newest]
Thread overview: 30+ messages / expand[flat|nested] mbox.gz Atom feed top
2017-10-09 20:32 [PATCH v5 00/16] generate full callchain cursor entries for inlined frames Milian Wolff
2017-10-09 20:32 ` [PATCH v5 01/16] perf report: remove code to handle inline frames from browsers Milian Wolff
2017-10-09 20:32 ` [PATCH v5 02/16] perf util: store srcline in callchain_cursor_node Milian Wolff
2017-10-09 20:32 ` [PATCH v5 03/16] perf util: refactor inline_list to operate on symbols Milian Wolff
2017-10-09 20:32 ` [PATCH v5 04/16] perf util: refactor inline_list to store srcline string directly Milian Wolff
2017-10-09 20:32 ` [PATCH v5 05/16] perf report: create real callchain entries for inlined frames Milian Wolff
2017-10-09 20:33 ` [PATCH v5 06/16] perf report: fall-back to function name comparison for -g srcline Milian Wolff
2017-10-09 20:33 ` [PATCH v5 07/16] perf report: mark inlined frames in output by " (inlined)" suffix Milian Wolff
2017-10-09 20:33 ` [PATCH v5 08/16] perf script: mark inlined frames and do not print DSO for them Milian Wolff
2017-10-09 20:33 ` [PATCH v5 09/16] perf report: compare symbol name for inlined frames when matching Milian Wolff
2017-10-13 13:28 ` Arnaldo Carvalho de Melo
2017-10-09 20:33 ` [PATCH v5 10/16] perf report: compare symbol name for inlined frames when sorting Milian Wolff
2017-10-09 20:33 ` [PATCH v5 11/16] perf report: properly handle branch count in match_chain Milian Wolff
2017-10-13 13:39 ` Arnaldo Carvalho de Melo
2017-10-13 14:08 ` Arnaldo Carvalho de Melo [this message]
2017-10-14 19:30 ` Milian Wolff
2017-10-16 14:17 ` Arnaldo Carvalho de Melo
2017-10-16 4:18 ` ravi
2017-10-16 8:27 ` Milian Wolff
2017-10-16 14:19 ` Arnaldo Carvalho de Melo
2017-10-09 20:33 ` [PATCH v5 12/16] perf report: cache failed lookups of inlined frames Milian Wolff
2017-10-09 20:33 ` [PATCH v5 13/16] perf report: cache srclines for callchain nodes Milian Wolff
2017-10-09 20:33 ` [PATCH v5 14/16] perf report: use srcline from callchain for hist entries Milian Wolff
2017-10-09 20:33 ` [PATCH v5 15/16] perf util: enable handling of inlined frames by default Milian Wolff
2017-10-09 20:33 ` [PATCH v5 16/16] perf util: use correct IP mapping to find srcline for hist entry Milian Wolff
2017-10-10 4:49 ` Namhyung Kim
2017-10-12 18:22 ` Milian Wolff
2017-10-12 18:52 ` Jiri Olsa
2017-10-13 11:03 ` Jiri Olsa
2017-10-13 1:19 ` Namhyung Kim
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20171013140834.GO3503@kernel.org \
--to=acme@kernel.org \
--cc=Linux-kernel@vger.kernel.org \
--cc=acme@redhat.com \
--cc=dsahern@gmail.com \
--cc=jolsa@kernel.org \
--cc=linux-perf-users@vger.kernel.org \
--cc=milian.wolff@kdab.com \
--cc=namhyung@kernel.org \
--cc=peterz@infradead.org \
--cc=ravi.bangoria@linux.vnet.ibm.com \
--cc=yao.jin@linux.intel.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
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 NNTP newsgroup(s).