[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20170217150552.GA14510@krava>
Date: Fri, 17 Feb 2017 16:05:52 +0100
From: Jiri Olsa <jolsa@...hat.com>
To: Jan Stancek <jstancek@...hat.com>
Cc: linux-kernel@...r.kernel.org, peterz@...radead.org,
mingo@...hat.com, acme@...nel.org,
alexander.shishkin@...ux.intel.com, jolsa@...nel.org,
mhiramat@...nel.org
Subject: Re: [PATCH v3 3/3] perf: replace _SC_NPROCESSORS_CONF with
max_present_cpu in cpu_topology_map
On Fri, Feb 17, 2017 at 12:10:26PM +0100, Jan Stancek wrote:
SNIP
> - int cpu_nr = ph->env.nr_cpus_online;
> + int cpu_nr = ph->env.nr_cpus_avail;
>
> nr = ph->env.nr_sibling_cores;
> str = ph->env.sibling_cores;
> @@ -1792,7 +1786,7 @@ static int process_cpu_topology(struct perf_file_section *section,
> u32 nr, i;
> char *str;
> struct strbuf sb;
> - int cpu_nr = ph->env.nr_cpus_online;
> + int cpu_nr = ph->env.nr_cpus_avail;
> u64 size = 0;
>
> ph->env.cpu = calloc(cpu_nr, sizeof(*ph->env.cpu));
> @@ -1873,7 +1867,7 @@ static int process_cpu_topology(struct perf_file_section *section,
> if (ph->needs_swap)
> nr = bswap_32(nr);
>
> - if (nr > (u32)cpu_nr) {
> + if (nr != (u32)-1 && nr > (u32)cpu_nr) {
could you please add a comment here exaplaining the reason
for possible -1 in here.. other than that it's ok,
for the series:
Acked-by: Jiri Olsa <jolsa@...nel.org>
thanks,
jirka
Powered by blists - more mailing lists