linux-kernel - [PATCH 3.16 053/294] perf/core: Invert perf_read

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:   Mon, 06 Nov 2017 23:03:02 +0000
From:   Ben Hutchings <ben@...adent.org.uk>
To:     linux-kernel@...r.kernel.org, stable@...r.kernel.org
CC:     akpm@...ux-foundation.org,
        "Arnaldo Carvalho de Melo" <acme@...nel.org>,
        "Michael Ellerman" <mpe@...erman.id.au>,
        "Linus Torvalds" <torvalds@...ux-foundation.org>,
        "Ingo Molnar" <mingo@...nel.org>, "Jiri Olsa" <jolsa@...hat.com>,
        "Thomas Gleixner" <tglx@...utronix.de>,
        "Sukadev Bhattiprolu" <sukadev@...ux.vnet.ibm.com>,
        "Vince Weaver" <vincent.weaver@...ne.edu>,
        "Stephane Eranian" <eranian@...gle.com>,
        "Arnaldo Carvalho de Melo" <acme@...hat.com>,
        "Peter Zijlstra" <peterz@...radead.org>
Subject: [PATCH 3.16 053/294] perf/core: Invert perf_read_group() loops

3.16.50-rc1 review patch.  If anyone has any objections, please let me know.

------------------

From: Peter Zijlstra <peterz@...radead.org>

commit fa8c269353d560b7c28119ad7617029f92e40b15 upstream.

In order to enable the use of perf_event_read(.group = true), we need
to invert the sibling-child loop nesting of perf_read_group().

Currently we iterate the child list for each sibling, this precludes
using group reads. Flip things around so we iterate each group for
each child.

Signed-off-by: Peter Zijlstra (Intel) <peterz@...radead.org>
[ Made the patch compile and things. ]
Signed-off-by: Sukadev Bhattiprolu <sukadev@...ux.vnet.ibm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@...radead.org>
Cc: Arnaldo Carvalho de Melo <acme@...nel.org>
Cc: Arnaldo Carvalho de Melo <acme@...hat.com>
Cc: Jiri Olsa <jolsa@...hat.com>
Cc: Linus Torvalds <torvalds@...ux-foundation.org>
Cc: Michael Ellerman <mpe@...erman.id.au>
Cc: Peter Zijlstra <peterz@...radead.org>
Cc: Stephane Eranian <eranian@...gle.com>
Cc: Thomas Gleixner <tglx@...utronix.de>
Cc: Vince Weaver <vincent.weaver@...ne.edu>
Link: http://lkml.kernel.org/r/1441336073-22750-7-git-send-email-sukadev@linux.vnet.ibm.com
Signed-off-by: Ingo Molnar <mingo@...nel.org>
[bwh: Backported to 3.16 as a dependency of commit 2aeb18835476 ("perf/core: Fix
 locking for children siblings group read"):
 - Keep the function name perf_event_read_group()
 - Keep using perf_event_read_value()]
Signed-off-by: Ben Hutchings <ben@...adent.org.uk>
---
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -3565,50 +3565,71 @@ u64 perf_event_read_value(struct perf_ev
 }
 EXPORT_SYMBOL_GPL(perf_event_read_value);
 
-static int perf_event_read_group(struct perf_event *event,
-				   u64 read_format, char __user *buf)
+static void __perf_read_group_add(struct perf_event *leader,
+					u64 read_format, u64 *values)
 {
-	struct perf_event *leader = event->group_leader, *sub;
-	struct perf_event_context *ctx = leader->ctx;
-	int n = 0, size = 0, ret;
+	struct perf_event *sub;
+	int n = 1; /* skip @nr */
 	u64 count, enabled, running;
-	u64 values[5];
-
-	lockdep_assert_held(&ctx->mutex);
 
 	count = perf_event_read_value(leader, &enabled, &running);
 
-	values[n++] = 1 + leader->nr_siblings;
+	/*
+	 * Since we co-schedule groups, {enabled,running} times of siblings
+	 * will be identical to those of the leader, so we only publish one
+	 * set.
+	 */
 	if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED)
 		values[n++] = enabled;
 	if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING)
 		values[n++] = running;
-	values[n++] = count;
+
+	/*
+	 * Write {count,id} tuples for every sibling.
+	 */
+	values[n++] += count;
 	if (read_format & PERF_FORMAT_ID)
 		values[n++] = primary_event_id(leader);
 
-	size = n * sizeof(u64);
-
-	if (copy_to_user(buf, values, size))
-		return -EFAULT;
-
-	ret = size;
-
 	list_for_each_entry(sub, &leader->sibling_list, group_entry) {
-		n = 0;
-
 		values[n++] = perf_event_read_value(sub, &enabled, &running);
 		if (read_format & PERF_FORMAT_ID)
 			values[n++] = primary_event_id(sub);
+	}
+}
 
-		size = n * sizeof(u64);
+static int perf_event_read_group(struct perf_event *event,
+				   u64 read_format, char __user *buf)
+{
+	struct perf_event *leader = event->group_leader, *child;
+	struct perf_event_context *ctx = leader->ctx;
+	int ret = event->read_size;
+	u64 *values;
 
-		if (copy_to_user(buf + ret, values, size)) {
-			return -EFAULT;
-		}
+	lockdep_assert_held(&ctx->mutex);
 
-		ret += size;
-	}
+	values = kzalloc(event->read_size, GFP_KERNEL);
+	if (!values)
+		return -ENOMEM;
+
+	values[0] = 1 + leader->nr_siblings;
+
+	/*
+	 * By locking the child_mutex of the leader we effectively
+	 * lock the child list of all siblings.. XXX explain how.
+	 */
+	mutex_lock(&leader->child_mutex);
+
+	__perf_read_group_add(leader, read_format, values);
+	list_for_each_entry(child, &leader->child_list, child_list)
+		__perf_read_group_add(child, read_format, values);
+
+	mutex_unlock(&leader->child_mutex);
+
+	if (copy_to_user(buf, values, event->read_size))
+		ret = -EFAULT;
+
+	kfree(values);
 
 	return ret;
 }