All of lore.kernel.org
 help / color / mirror / Atom feed
From: tip-bot for Arnaldo Carvalho de Melo <tipbot@zytor.com>
To: linux-tip-commits@vger.kernel.org
Cc: linux-kernel@vger.kernel.org, paulus@samba.org, acme@redhat.com,
	hpa@zytor.com, mingo@kernel.org, jolsa@kernel.org,
	a.p.zijlstra@chello.nl, jean.pihet@linaro.org,
	namhyung@kernel.org, fweisbec@gmail.com, adrian.hunter@intel.com,
	dsahern@gmail.com, tglx@linutronix.de, bp@suse.de,
	cjashfor@linux.vnet.ibm.com
Subject: [tip:perf/core] perf evlist: Refcount mmaps
Date: Fri, 26 Sep 2014 02:21:35 -0700	[thread overview]
Message-ID: <tip-cpv7v2lw0g74ucmxa39xdpms@git.kernel.org> (raw)
In-Reply-To: <20140908153824.GG2773@kernel.org>

Commit-ID:  82396986032915c1572bfb74b224fcc2e4e8ba7c
Gitweb:     http://git.kernel.org/tip/82396986032915c1572bfb74b224fcc2e4e8ba7c
Author:     Arnaldo Carvalho de Melo <acme@redhat.com>
AuthorDate: Mon, 8 Sep 2014 13:26:35 -0300
Committer:  Arnaldo Carvalho de Melo <acme@redhat.com>
CommitDate: Thu, 25 Sep 2014 16:46:55 -0300

perf evlist: Refcount mmaps

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.

v2: Automatically unmap it when the refcount hits one, which will happen
when all fds are filtered by perf_evlist__filter_pollfd(), in later
patches.

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-cpv7v2lw0g74ucmxa39xdpms@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/evlist.c | 47 +++++++++++++++++++++++++++++++++++++++++++++--
 tools/perf/util/evlist.h |  6 ++++++
 2 files changed, 51 insertions(+), 2 deletions(-)

diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index 398dab1..efddee5 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -28,6 +28,8 @@
 #define FD(e, x, y) (*(int *)xyarray__entry(e->fd, x, y))
 #define SID(e, x, y) xyarray__entry(e->sample_id, x, y)
 
+static void __perf_evlist__munmap(struct perf_evlist *evlist, int idx);
+
 void perf_evlist__init(struct perf_evlist *evlist, struct cpu_map *cpus,
 		       struct thread_map *threads)
 {
@@ -651,14 +653,36 @@ union perf_event *perf_evlist__mmap_read(struct perf_evlist *evlist, int idx)
 	return event;
 }
 
+static bool perf_mmap__empty(struct perf_mmap *md)
+{
+	return perf_mmap__read_head(md) != md->prev;
+}
+
+static void perf_evlist__mmap_get(struct perf_evlist *evlist, int idx)
+{
+	++evlist->mmap[idx].refcnt;
+}
+
+static void perf_evlist__mmap_put(struct perf_evlist *evlist, int idx)
+{
+	BUG_ON(evlist->mmap[idx].refcnt == 0);
+
+	if (--evlist->mmap[idx].refcnt == 0)
+		__perf_evlist__munmap(evlist, idx);
+}
+
 void perf_evlist__mmap_consume(struct perf_evlist *evlist, int idx)
 {
+	struct perf_mmap *md = &evlist->mmap[idx];
+
 	if (!evlist->overwrite) {
-		struct perf_mmap *md = &evlist->mmap[idx];
 		unsigned int old = md->prev;
 
 		perf_mmap__write_tail(md, old);
 	}
+
+	if (md->refcnt == 1 && perf_mmap__empty(md))
+		perf_evlist__mmap_put(evlist, idx);
 }
 
 static void __perf_evlist__munmap(struct perf_evlist *evlist, int idx)
@@ -666,6 +690,7 @@ 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].refcnt = 0;
 	}
 }
 
@@ -699,6 +724,20 @@ struct mmap_params {
 static int __perf_evlist__mmap(struct perf_evlist *evlist, int idx,
 			       struct mmap_params *mp, int fd)
 {
+	/*
+	 * The last one will be done at perf_evlist__mmap_consume(), so that we
+	 * make sure we don't prevent tools from consuming every last event in
+	 * the ring buffer.
+	 *
+	 * I.e. we can get the POLLHUP meaning that the fd doesn't exist
+	 * anymore, but the last events for it are still in the ring buffer,
+	 * waiting to be consumed.
+	 *
+	 * Tools can chose to ignore this at their own discretion, but the
+	 * evlist layer can't just drop it when filtering events in
+	 * perf_evlist__filter_pollfd().
+	 */
+	evlist->mmap[idx].refcnt = 2;
 	evlist->mmap[idx].prev = 0;
 	evlist->mmap[idx].mask = mp->mask;
 	evlist->mmap[idx].base = mmap(NULL, evlist->mmap_len, mp->prot,
@@ -734,10 +773,14 @@ 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 fc01370..bd312b0 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
+ *
+ * @refcnt - e.g. code using PERF_EVENT_IOC_SET_OUTPUT to share this
+ */
 struct perf_mmap {
 	void		 *base;
 	int		 mask;
+	int		 refcnt;
 	unsigned int	 prev;
 	char		 event_copy[PERF_SAMPLE_MAX_SIZE];
 };

  parent reply	other threads:[~2014-09-26  9:22 UTC|newest]

Thread overview: 24+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2014-09-03 21:59 [RFC 00/10] perf pollfd series v2 Arnaldo Carvalho de Melo
2014-09-03 21:59 ` [PATCH 01/10] perf evlist: Introduce perf_evlist__filter_pollfd method Arnaldo Carvalho de Melo
2014-09-03 21:59 ` [PATCH 02/10] perf tests: Add test for perf_evlist__filter_pollfd() Arnaldo Carvalho de Melo
2014-09-03 21:59 ` [PATCH 03/10] perf evlist: Monitor POLLERR and POLLHUP events too Arnaldo Carvalho de Melo
2014-09-03 21:59 ` [PATCH 04/10] perf record: Filter out POLLHUP'ed file descriptors Arnaldo Carvalho de Melo
2014-09-04 12:32   ` Adrian Hunter
2014-09-04 15:19     ` Arnaldo Carvalho de Melo
2014-09-05  8:42       ` Adrian Hunter
2014-09-05 14:07         ` Arnaldo Carvalho de Melo
2014-09-06 20:39           ` Jiri Olsa
2014-09-08 13:46             ` Arnaldo Carvalho de Melo
2014-09-08 14:04               ` Jiri Olsa
2014-09-08 14:33                 ` Arnaldo Carvalho de Melo
2014-09-08 15:10                   ` Jiri Olsa
2014-09-08 15:38                     ` Arnaldo Carvalho de Melo
2014-09-08 17:07                       ` Arnaldo Carvalho de Melo
2014-09-26  9:21                       ` tip-bot for Arnaldo Carvalho de Melo [this message]
2014-09-26  9:20                     ` [tip:perf/core] perf evlist: We need to poll all event " tip-bot for Arnaldo Carvalho de Melo
2014-09-03 21:59 ` [PATCH 05/10] perf trace: Filter out POLLHUP'ed " Arnaldo Carvalho de Melo
2014-09-03 22:00 ` [PATCH 06/10] perf evlist: Allow growing pollfd on add method Arnaldo Carvalho de Melo
2014-09-03 22:00 ` [PATCH 07/10] perf tests: Add pollfd growing test Arnaldo Carvalho de Melo
2014-09-03 22:00 ` [PATCH 08/10] perf kvm stat live: Use perf_evlist__add_pollfd() instead of local equivalent Arnaldo Carvalho de Melo
2014-09-03 22:00 ` [PATCH 09/10] perf evlist: Introduce poll method for common code idiom Arnaldo Carvalho de Melo
2014-09-03 22:00 ` [PATCH 10/10] tools lib api: Adopt fdarray class from perf's evlist 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=tip-cpv7v2lw0g74ucmxa39xdpms@git.kernel.org \
    --to=tipbot@zytor.com \
    --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=hpa@zytor.com \
    --cc=jean.pihet@linaro.org \
    --cc=jolsa@kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-tip-commits@vger.kernel.org \
    --cc=mingo@kernel.org \
    --cc=namhyung@kernel.org \
    --cc=paulus@samba.org \
    --cc=tglx@linutronix.de \
    /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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.