linux-kernel - [PATCH v2] perf/core: fix userpage->time

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-next>] [day] [month] [year] [list]

Date:   Thu, 23 Sep 2021 18:28:00 -0700
From:   Song Liu <songliubraving@...com>
To:     <linux-kernel@...r.kernel.org>
CC:     <acme@...nel.org>, <peterz@...radead.org>, <mingo@...hat.com>,
        <kernel-team@...com>, <eranian@...gle.com>,
        Song Liu <songliubraving@...com>,
        Lucian Grijincu <lucian@...com>
Subject: [PATCH v2] perf/core: fix userpage->time_enabled of inactive events

Users of rdpmc rely on the mmapped user page to calculate accurate
time_enabled. Currently, userpage->time_enabled is only updated when the
event is added to the pmu. As a result, inactive event (due to counter
multiplexing) does not have accurate userpage->time_enabled. This can
be reproduced with something like:

   /* open 20 task perf_event "cycles", to create multiplexing */

   fd = perf_event_open();  /* open task perf_event "cycles" */
   userpage = mmap(fd);     /* use mmap and rdmpc */

   while (true) {
     time_enabled_mmap = xxx; /* use logic in perf_event_mmap_page */
     time_enabled_read = read(fd).time_enabled;
     if (time_enabled_mmap > time_enabled_read)
         BUG();
   }

Fix this by updating userpage for inactive events in merge_sched_in.

Suggested-by: Peter Zijlstra (Intel) <peterz@...radead.org>
Reported-and-tested-by: Lucian Grijincu <lucian@...com>
Signed-off-by: Song Liu <songliubraving@...com>
---
 include/linux/perf_event.h |  4 +++-
 kernel/events/core.c       | 49 ++++++++++++++++++++++++++++++++++----
 2 files changed, 48 insertions(+), 5 deletions(-)

diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 2d510ad750edc..4aa52f7a48c16 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -683,7 +683,9 @@ struct perf_event {
 	/*
 	 * timestamp shadows the actual context timing but it can
 	 * be safely used in NMI interrupt context. It reflects the
-	 * context time as it was when the event was last scheduled in.
+	 * context time as it was when the event was last scheduled in,
+	 * or when ctx_sched_in failed to schedule the event because we
+	 * run out of PMC.
 	 *
 	 * ctx_time already accounts for ctx->timestamp. Therefore to
 	 * compute ctx_time for a sample, simply add perf_clock().
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 1cb1f9b8392e2..d73f986eef7b3 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -3707,6 +3707,46 @@ static noinline int visit_groups_merge(struct perf_cpu_context *cpuctx,
 	return 0;
 }
 
+static inline bool event_update_userpage(struct perf_event *event)
+{
+	/*
+	 * Checking mmap_count to avoid unnecessary work. This does leave a
+	 * corner case: if the event is enabled before mmap(), the first
+	 * time the event gets scheduled is via:
+	 *
+	 *  __perf_event_enable (or __perf_install_in_context)
+	 *      -> ctx_resched
+	 *         -> perf_event_sched_in
+	 *            -> ctx_sched_in
+	 *
+	 * with mmap_count of 0, so we will skip here. As a result,
+	 * userpage->offset is not accurate after mmap and before the
+	 * first rotation.
+	 *
+	 * To avoid the discrepancy of this window, the user space should
+	 * mmap the event before enabling it.
+	 */
+	if (likely(!atomic_read(&event->mmap_count)))
+		return false;
+
+	perf_event_update_time(event);
+	perf_set_shadow_time(event, event->ctx);
+	perf_event_update_userpage(event);
+
+	return true;
+}
+
+static inline void group_update_userpage(struct perf_event *group_event)
+{
+	struct perf_event *event;
+
+	if (!event_update_userpage(group_event))
+		return;
+
+	for_each_sibling_event(event, group_event)
+		event_update_userpage(event);
+}
+
 static int merge_sched_in(struct perf_event *event, void *data)
 {
 	struct perf_event_context *ctx = event->ctx;
@@ -3725,14 +3765,15 @@ static int merge_sched_in(struct perf_event *event, void *data)
 	}
 
 	if (event->state == PERF_EVENT_STATE_INACTIVE) {
+		*can_add_hw = 0;
 		if (event->attr.pinned) {
 			perf_cgroup_event_disable(event, ctx);
 			perf_event_set_state(event, PERF_EVENT_STATE_ERROR);
+		} else {
+			ctx->rotate_necessary = 1;
+			perf_mux_hrtimer_restart(cpuctx);
+			group_update_userpage(event);
 		}
-
-		*can_add_hw = 0;
-		ctx->rotate_necessary = 1;
-		perf_mux_hrtimer_restart(cpuctx);
 	}
 
 	return 0;
-- 
2.30.2