linux-kernel - Re: [PATCH V2 02/22] perf evlist: Add initial support for mmapping an Instruction Trace buffer

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Date:	Tue, 9 Dec 2014 10:24:14 -0300
From:	Arnaldo Carvalho de Melo <acme@...nel.org>
To:	Adrian Hunter <adrian.hunter@...el.com>
Cc:	Jiri Olsa <jolsa@...hat.com>,
	Peter Zijlstra <peterz@...radead.org>,
	linux-kernel@...r.kernel.org, David Ahern <dsahern@...il.com>,
	Frederic Weisbecker <fweisbec@...il.com>,
	Namhyung Kim <namhyung@...il.com>,
	Paul Mackerras <paulus@...ba.org>,
	Stephane Eranian <eranian@...gle.com>
Subject: Re: [PATCH V2 02/22] perf evlist: Add initial support for mmapping
 an Instruction Trace buffer

Em Wed, Nov 26, 2014 at 03:11:16PM +0200, Adrian Hunter escreveu:
> On 25/11/14 18:57, Jiri Olsa wrote:
> > On Thu, Nov 20, 2014 at 03:23:08PM +0200, Adrian Hunter wrote:
> > 
> > SNIP
> > 
> >> +			bool per_cpu __maybe_unused)
> >> +{
> >> +}
> >> +
> >>  static void __perf_evlist__munmap(struct perf_evlist *evlist, int idx)
> >>  {
> >>  	if (evlist->mmap[idx].base != NULL) {
> >> @@ -731,6 +759,7 @@ static void __perf_evlist__munmap(struct perf_evlist *evlist, int idx)
> >>  		evlist->mmap[idx].base = NULL;
> >>  		evlist->mmap[idx].refcnt = 0;
> >>  	}
> >> +	itrace_mmap__munmap(&evlist->mmap[idx].itrace_mmap);
> >>  }
> >>  
> >>  void perf_evlist__munmap(struct perf_evlist *evlist)
> >> @@ -758,6 +787,7 @@ static int perf_evlist__alloc_mmap(struct perf_evlist *evlist)
> >>  struct mmap_params {
> >>  	int prot;
> >>  	int mask;
> >> +	struct itrace_mmap_params itrace_mp;
> >>  };
> >>  
> >>  static int __perf_evlist__mmap(struct perf_evlist *evlist, int idx,
> >> @@ -788,6 +818,10 @@ static int __perf_evlist__mmap(struct perf_evlist *evlist, int idx,
> >>  		return -1;
> >>  	}
> >>  
> >> +	if (itrace_mmap__mmap(&evlist->mmap[idx].itrace_mmap,
> >> +			      &mp->itrace_mp, evlist->mmap[idx].base, fd))
> >> +		return -1;
> >> +
> > 
> > so the itrace mmap is mmaped with right after event mmap for event fd..?
> 
> The AUX area support is not implemented yet.  The AUX mmap size and offset
> are set through the mmap page via aux_offset and aux_size.

>From a quick look the user bits looks nicely done, step by step
introducing stuff, but I would like to try it all together, where can I
get the kernel bits so that I can try to find some machine where to test
the whole thing?

- Arnaldo
 
> > is there any latest version of kernel changes, so I could check with
> > kernel's perf_mmap? hum.. or you just use the same mmap?
> 
> I re-based and pushed to:
> 
> 	git://git.infradead.org/users/ahunter/linux-perf.git
> 
> The missing AUX bits are added in this patch:
> 
> 	http://git.infradead.org/users/ahunter/linux-perf.git/commitdiff/f1be40371b5600a5c4a20f88adff9595bdf5e7ec
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/