linux-perf-users.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Jiri Olsa <jolsa@redhat.com>
To: Arnaldo Carvalho de Melo <arnaldo.melo@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>, Namhyung Kim <namhyung@kernel.org>,
	Ingo Molnar <mingo@kernel.org>,
	Thomas Gleixner <tglx@linutronix.de>,
	Clark Williams <williams@redhat.com>,
	linux-kernel@vger.kernel.org, linux-perf-users@vger.kernel.org,
	Arnaldo Carvalho de Melo <acme@redhat.com>,
	Adrian Hunter <adrian.hunter@intel.com>
Subject: Re: [PATCH 12/12] perf maps: Set maps pointer in the kmap area for kernel maps
Date: Thu, 19 Dec 2019 10:24:14 +0100	[thread overview]
Message-ID: <20191219092414.GC8141@krava> (raw)
In-Reply-To: <20191218190120.GB13282@kernel.org>

On Wed, Dec 18, 2019 at 04:01:20PM -0300, Arnaldo Carvalho de Melo wrote:
> Em Wed, Dec 18, 2019 at 03:22:54PM -0300, Arnaldo Carvalho de Melo escreveu:
> > Em Wed, Dec 18, 2019 at 10:05:04AM +0100, Jiri Olsa escreveu:
> > After looking at this some more, I retract this patch and instead the
> > two-liner at the end of this message seems enough.
> 
> So here is the full cset, I have not made changes to the other patches,
> 
> - Arnaldo
> 
> commit 178427a192bcbe3ad93dd0637c3dceaa3ccef31e
> Author: Arnaldo Carvalho de Melo <acme@redhat.com>
> Date:   Wed Dec 18 15:23:14 2019 -0300
> 
>     perf map: Set kmap->kmaps backpointer for main kernel map chunks
>     
>     When a map is create to represent the main kernel area (vmlinux) with
>     map__new2() we allocate an extra area to store a pointer to the 'struct
>     maps' for the kernel maps, so that we can access that struct when
>     loading ELF files or kallsyms, as we will need to split it in multiple
>     maps, one per kernel module or ELF section (such as ".init.text").
>     
>     So when map->dso->kernel is non-zero, it is expected that
>     map__kmap(map)->kmaps to be set to the tree of kernel maps (modules,
>     chunks of the main kernel, bpf progs put in place via
>     PERF_RECORD_KSYMBOL, the main kernel).
>     
>     This was not the case when we were splitting the main kernel into chunks
>     for its ELF sections, which ended up making 'perf report --children'
>     processing a perf.data file with callchains to trip on
>     __map__is_kernel(), when we press ENTER to see the popup menu for main
>     histogram entries that starts at a symbol in the ".init.text" ELF
>     section, e.g.:
>     
>     -    8.83%     0.00%  swapper     [kernel.vmlinux].init.text  [k] start_kernel
>          start_kernel
>          cpu_startup_entry
>          do_idle
>          cpuidle_enter
>          cpuidle_enter_state
>          intel_idle
>     
>     Fix it.
>     
>     Cc: Adrian Hunter <adrian.hunter@intel.com>
>     Cc: Jiri Olsa <jolsa@kernel.org>
>     Cc: Namhyung Kim <namhyung@kernel.org>
>     Link: https://lkml.kernel.org/n/tip-vcokue57w4goyzweg2rr5i80@git.kernel.org
>     Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
> 
> diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c
> index 6658fbf196e6..1965aefccb02 100644
> --- a/tools/perf/util/symbol-elf.c
> +++ b/tools/perf/util/symbol-elf.c
> @@ -920,6 +920,9 @@ static int dso__process_kernel_symbol(struct dso *dso, struct map *map,
>  		if (curr_map == NULL)
>  			return -1;
>  
> +		if (curr_dso->kernel)
> +			map__kmap(curr_map)->kmaps = kmaps;
> +
>  		if (adjust_kernel_syms) {
>  			curr_map->start  = shdr->sh_addr + ref_reloc(kmap);
>  			curr_map->end	 = curr_map->start + shdr->sh_size;
> 

looks good ;-)

jirka

  reply	other threads:[~2019-12-19  9:24 UTC|newest]

Thread overview: 28+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-12-17 14:48 [RFC] perf report/top with callchain fixes improvements Arnaldo Carvalho de Melo
2019-12-17 14:48 ` [PATCH 01/12] perf hists browser: Restore ESC as "Zoom out" of DSO/thread/etc Arnaldo Carvalho de Melo
2019-12-17 14:48 ` [PATCH 02/12] perf report/top: Make ENTER consistently bring up menu Arnaldo Carvalho de Melo
2019-12-17 14:48 ` [PATCH 03/12] perf report/top: Add menu entry for toggling callchain expansion Arnaldo Carvalho de Melo
2019-12-17 14:48 ` [PATCH 04/12] perf report/top: Improve toggle callchain menu option Arnaldo Carvalho de Melo
2019-12-17 14:48 ` [PATCH 05/12] perf hists browser: Generalize the do_zoom_dso() function Arnaldo Carvalho de Melo
2019-12-17 14:48 ` [PATCH 06/12] perf report/top: Add 'k' hotkey to zoom directly into the kernel map Arnaldo Carvalho de Melo
2019-12-20  6:48   ` Namhyung Kim
2019-12-20 12:17     ` Arnaldo Carvalho de Melo
2019-12-21  7:20       ` Namhyung Kim
2019-12-17 14:48 ` [PATCH 07/12] perf hists browser: Allow passing an initial hotkey Arnaldo Carvalho de Melo
2019-12-18  8:08   ` Jiri Olsa
2019-12-18 14:08     ` Arnaldo Carvalho de Melo
2019-12-18 14:23       ` Jiri Olsa
2019-12-19 17:26         ` Arnaldo Carvalho de Melo
2019-12-19 21:44           ` Jiri Olsa
2019-12-17 14:48 ` [PATCH 08/12] tools ui popup: Allow returning hotkeys Arnaldo Carvalho de Melo
2019-12-17 14:48 ` [PATCH 09/12] perf report/top: Allow pressing hotkeys in the options popup menu Arnaldo Carvalho de Melo
2019-12-17 14:48 ` [PATCH 10/12] perf report/top: Do not offer annotation for symbols without samples Arnaldo Carvalho de Melo
2019-12-17 14:48 ` [PATCH 11/12] perf report/top: Make 'e' visible in the help and make it toggle showing callchains Arnaldo Carvalho de Melo
2019-12-17 14:48 ` [PATCH 12/12] perf maps: Set maps pointer in the kmap area for kernel maps Arnaldo Carvalho de Melo
2019-12-18  9:05   ` Jiri Olsa
2019-12-18 14:24     ` Arnaldo Carvalho de Melo
2019-12-18 18:22     ` Arnaldo Carvalho de Melo
2019-12-18 19:01       ` Arnaldo Carvalho de Melo
2019-12-19  9:24         ` Jiri Olsa [this message]
2019-12-18  9:07   ` Jiri Olsa
2019-12-18 14:20     ` Arnaldo Carvalho de Melo

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=20191219092414.GC8141@krava \
    --to=jolsa@redhat.com \
    --cc=acme@redhat.com \
    --cc=adrian.hunter@intel.com \
    --cc=arnaldo.melo@gmail.com \
    --cc=jolsa@kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-perf-users@vger.kernel.org \
    --cc=mingo@kernel.org \
    --cc=namhyung@kernel.org \
    --cc=tglx@linutronix.de \
    --cc=williams@redhat.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).