From: Arnaldo Carvalho de Melo <acme@kernel.org>
To: Jiri Olsa <jolsa@redhat.com>
Cc: linux-kernel@vger.kernel.org,
Arnaldo Carvalho de Melo <acme@redhat.com>,
Adrian Hunter <adrian.hunter@intel.com>,
Borislav Petkov <bp@suse.de>,
Corey Ashford <cjashfor@linux.vnet.ibm.com>,
David Ahern <dsahern@gmail.com>,
Frederic Weisbecker <fweisbec@gmail.com>,
Ingo Molnar <mingo@kernel.org>,
Jean Pihet <jean.pihet@linaro.org>, Jiri Olsa <jolsa@kernel.org>,
Namhyung Kim <namhyung@kernel.org>,
Paul Mackerras <paulus@samba.org>,
Peter Zijlstra <a.p.zijlstra@chello.nl>
Subject: [PATCH 12/14] perf evlist: Refcount mmaps
Date: Wed, 10 Sep 2014 11:08:47 -0300 [thread overview]
Message-ID: <1410358129-9965-13-git-send-email-acme@kernel.org> (raw)
In-Reply-To: <1410358129-9965-1-git-send-email-acme@kernel.org>
From: Arnaldo Carvalho de Melo <acme@redhat.com>
We need to know how many fds are using a perf mmap via
PERF_EVENT_IOC_SET_OUTPUT, so that we can know when to ditch an mmap,
refcount it.
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Borislav Petkov <bp@suse.de>
Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jean Pihet <jean.pihet@linaro.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/20140908153824.GG2773@kernel.org
Link: http://lkml.kernel.org/n/tip-9ymfcxmk52sb7u1g0i3aiovh@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/util/evlist.c | 21 ++++++++++++++++++++-
tools/perf/util/evlist.h | 6 ++++++
2 files changed, 26 insertions(+), 1 deletion(-)
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index 477ede5367ee..662057a44126 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -664,6 +664,7 @@ static void __perf_evlist__munmap(struct perf_evlist *evlist, int idx)
if (evlist->mmap[idx].base != NULL) {
munmap(evlist->mmap[idx].base, evlist->mmap_len);
evlist->mmap[idx].base = NULL;
+ evlist->mmap[idx].nfds = 0;
}
}
@@ -697,6 +698,7 @@ struct mmap_params {
static int __perf_evlist__mmap(struct perf_evlist *evlist, int idx,
struct mmap_params *mp, int fd)
{
+ evlist->mmap[idx].nfds = 1;
evlist->mmap[idx].prev = 0;
evlist->mmap[idx].mask = mp->mask;
evlist->mmap[idx].base = mmap(NULL, evlist->mmap_len, mp->prot,
@@ -711,6 +713,19 @@ static int __perf_evlist__mmap(struct perf_evlist *evlist, int idx,
return 0;
}
+static void perf_evlist__mmap_get(struct perf_evlist *evlist, int idx)
+{
+ ++evlist->mmap[idx].nfds;
+}
+
+static void perf_evlist__mmap_put(struct perf_evlist *evlist, int idx)
+{
+ BUG_ON(evlist->mmap[idx].nfds == 0);
+
+ if (--evlist->mmap[idx].nfds == 0)
+ __perf_evlist__munmap(evlist, idx);
+}
+
static int perf_evlist__mmap_per_evsel(struct perf_evlist *evlist, int idx,
struct mmap_params *mp, int cpu,
int thread, int *output)
@@ -732,10 +747,14 @@ static int perf_evlist__mmap_per_evsel(struct perf_evlist *evlist, int idx,
} else {
if (ioctl(fd, PERF_EVENT_IOC_SET_OUTPUT, *output) != 0)
return -1;
+
+ perf_evlist__mmap_get(evlist, idx);
}
- if (perf_evlist__add_pollfd(evlist, fd) < 0)
+ if (perf_evlist__add_pollfd(evlist, fd) < 0) {
+ perf_evlist__mmap_put(evlist, idx);
return -1;
+ }
if ((evsel->attr.read_format & PERF_FORMAT_ID) &&
perf_evlist__id_add_fd(evlist, evsel, cpu, thread, fd) < 0)
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index fc013704d903..19bbe0410827 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -18,9 +18,15 @@ struct record_opts;
#define PERF_EVLIST__HLIST_BITS 8
#define PERF_EVLIST__HLIST_SIZE (1 << PERF_EVLIST__HLIST_BITS)
+/**
+ * struct perf_mmap - perf's ring buffer mmap details
+ *
+ * @nfds - file descriptors pointing here via PERF_EVENT_IOC_SET_OUTPUT
+ */
struct perf_mmap {
void *base;
int mask;
+ int nfds;
unsigned int prev;
char event_copy[PERF_SAMPLE_MAX_SIZE];
};
--
1.9.3
next prev parent reply other threads:[~2014-09-10 14:10 UTC|newest]
Thread overview: 47+ messages / expand[flat|nested] mbox.gz Atom feed top
2014-09-10 14:08 [RFC 00/14] perf pollfd v3 Arnaldo Carvalho de Melo
2014-09-10 14:08 ` [PATCH 01/14] perf evlist: Introduce perf_evlist__filter_pollfd method Arnaldo Carvalho de Melo
2014-09-10 14:08 ` [PATCH 02/14] perf tests: Add test for perf_evlist__filter_pollfd() Arnaldo Carvalho de Melo
2014-09-10 14:08 ` [PATCH 03/14] perf evlist: Monitor POLLERR and POLLHUP events too Arnaldo Carvalho de Melo
2014-09-10 14:08 ` [PATCH 04/14] perf evlist: We need to poll all event file descriptors Arnaldo Carvalho de Melo
2014-09-10 14:08 ` [PATCH 05/14] perf record: Filter out POLLHUP'ed " Arnaldo Carvalho de Melo
2014-09-10 14:08 ` [PATCH 06/14] perf trace: " Arnaldo Carvalho de Melo
2014-09-10 14:08 ` [PATCH 07/14] perf evlist: Allow growing pollfd on add method Arnaldo Carvalho de Melo
2014-09-10 14:08 ` [PATCH 08/14] perf tests: Add pollfd growing test Arnaldo Carvalho de Melo
2014-09-10 14:08 ` [PATCH 09/14] perf kvm stat live: Use perf_evlist__add_pollfd() instead of local equivalent Arnaldo Carvalho de Melo
2014-09-10 14:08 ` [PATCH 10/14] perf evlist: Introduce poll method for common code idiom Arnaldo Carvalho de Melo
2014-09-10 14:08 ` [PATCH 11/14] tools lib api: Adopt fdarray class from perf's evlist Arnaldo Carvalho de Melo
2014-09-11 15:09 ` [PATCH] tools lib fd array: Do not set fd as non blocking evlist Jiri Olsa
2014-09-11 15:27 ` Arnaldo Carvalho de Melo
2014-09-11 15:53 ` Arnaldo Carvalho de Melo
2014-09-12 12:58 ` [PATCH 11/14] tools lib api: Adopt fdarray class from perf's evlist Jiri Olsa
2014-09-12 13:44 ` Arnaldo Carvalho de Melo
2014-09-12 14:16 ` Jiri Olsa
2014-09-12 14:22 ` Arnaldo Carvalho de Melo
2014-09-12 16:54 ` Borislav Petkov
2014-09-12 20:48 ` Arnaldo Carvalho de Melo
2014-09-12 22:12 ` Borislav Petkov
2014-09-22 12:29 ` Jiri Olsa
2014-09-10 14:08 ` Arnaldo Carvalho de Melo [this message]
2014-09-10 14:08 ` [PATCH 13/14] tools lib fd array: Allow associating an integer cookie with each entry Arnaldo Carvalho de Melo
2014-09-11 10:33 ` Jiri Olsa
2014-09-11 13:29 ` Arnaldo Carvalho de Melo
2014-09-11 14:59 ` Jiri Olsa
2014-09-11 15:23 ` Arnaldo Carvalho de Melo
2014-09-11 15:35 ` Jiri Olsa
2014-09-11 15:49 ` Arnaldo Carvalho de Melo
2014-09-11 16:07 ` Jiri Olsa
2014-09-10 14:08 ` [PATCH 14/14] perf evlist: Unmap ring buffer when fd is nuked Arnaldo Carvalho de Melo
2014-09-11 12:27 ` Jiri Olsa
2014-09-11 13:40 ` Arnaldo Carvalho de Melo
2014-09-11 11:33 ` [RFC 00/14] perf pollfd v3 Jiri Olsa
2014-09-11 11:48 ` Jiri Olsa
2014-09-11 13:30 ` Arnaldo Carvalho de Melo
2014-09-11 21:36 ` Arnaldo Carvalho de Melo
2014-09-18 16:04 ` Arnaldo Carvalho de Melo
2014-09-22 13:35 ` Jiri Olsa
2014-09-22 14:49 ` Arnaldo Carvalho de Melo
2014-09-22 14:51 ` Jiri Olsa
2014-09-22 21:10 ` Arnaldo Carvalho de Melo
2014-09-23 9:26 ` Jiri Olsa
2014-09-23 12:46 ` Arnaldo Carvalho de Melo
2014-09-23 12:52 ` Jiri Olsa
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=1410358129-9965-13-git-send-email-acme@kernel.org \
--to=acme@kernel.org \
--cc=a.p.zijlstra@chello.nl \
--cc=acme@redhat.com \
--cc=adrian.hunter@intel.com \
--cc=bp@suse.de \
--cc=cjashfor@linux.vnet.ibm.com \
--cc=dsahern@gmail.com \
--cc=fweisbec@gmail.com \
--cc=jean.pihet@linaro.org \
--cc=jolsa@kernel.org \
--cc=jolsa@redhat.com \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@kernel.org \
--cc=namhyung@kernel.org \
--cc=paulus@samba.org \
/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
Powered by JetHome