linux-kernel - [RFC 1/2] perf/pmu: Allow PMU providers to override system-wide security settings

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 for Android: free password hash cracker in your pocket

[<prev] [next>] [thread-next>] [day] [month] [year] [list]

Message-Id: <20171117135723.22235-1-tvrtko.ursulin@linux.intel.com>
Date:   Fri, 17 Nov 2017 13:57:22 +0000
From:   Tvrtko Ursulin <tursulin@...ulin.net>
To:     Intel-gfx@...ts.freedesktop.org
Cc:     linux-kernel@...r.kernel.org,
        Tvrtko Ursulin <tvrtko.ursulin@...el.com>,
        Peter Zijlstra <peterz@...radead.org>,
        Ingo Molnar <mingo@...hat.com>,
        Arnaldo Carvalho de Melo <acme@...nel.org>,
        Alexander Shishkin <alexander.shishkin@...ux.intel.com>,
        Jiri Olsa <jolsa@...hat.com>,
        Namhyung Kim <namhyung@...nel.org>,
        Dmitry Rogozhkin <dmitry.v.rogozhkin@...el.com>,
        Chris Wilson <chris@...is-wilson.co.uk>
Subject: [RFC 1/2] perf/pmu: Allow PMU providers to override system-wide security settings

From: Tvrtko Ursulin <tvrtko.ursulin@...el.com>

To allow system administrators finer-grained control over security
settings, we add an optional pmu->is_privileged(pmu, event) callback
which is consulted when unprivileged system-wide uncore event collection
is disabled.

Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@...el.com>
Cc: Peter Zijlstra <peterz@...radead.org>
Cc: Ingo Molnar <mingo@...hat.com>
Cc: Arnaldo Carvalho de Melo <acme@...nel.org>
Cc: Alexander Shishkin <alexander.shishkin@...ux.intel.com>
Cc: Jiri Olsa <jolsa@...hat.com>
Cc: Namhyung Kim <namhyung@...nel.org>
Cc: linux-kernel@...r.kernel.org
Cc: Dmitry Rogozhkin <dmitry.v.rogozhkin@...el.com>
Cc: Chris Wilson <chris@...is-wilson.co.uk>
---
 include/linux/perf_event.h |  6 ++++++
 kernel/events/core.c       | 12 +++++++++++-
 2 files changed, 17 insertions(+), 1 deletion(-)

diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 8e22f24ded6a..a93630cad6b9 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -446,6 +446,12 @@ struct pmu {
 	 * Filter events for PMU-specific reasons.
 	 */
 	int (*filter_match)		(struct perf_event *event); /* optional */
+
+	/*
+	 * Returns true if the event needs CAP_SYS_ADMIN privilege in system-
+	 * wide mode.
+	 */
+	bool (*is_privileged)		(struct perf_event *event); /* optional */
 };
 
 /**
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 1811dd5aa2e2..adec28c879e8 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -3847,6 +3847,16 @@ find_lively_task_by_vpid(pid_t vpid)
 	return task;
 }
 
+static bool cpu_is_privileged(struct pmu *pmu, struct perf_event *event)
+{
+	bool privileged = perf_paranoid_cpu();
+
+	if (privileged && pmu->is_privileged)
+		privileged = pmu->is_privileged(event);
+
+	return privileged;
+}
+
 /*
  * Returns a matching context with refcount and pincount.
  */
@@ -3863,7 +3873,7 @@ find_get_context(struct pmu *pmu, struct task_struct *task,
 
 	if (!task) {
 		/* Must be root to operate on a CPU event: */
-		if (perf_paranoid_cpu() && !capable(CAP_SYS_ADMIN))
+		if (cpu_is_privileged(pmu, event) && !capable(CAP_SYS_ADMIN))
 			return ERR_PTR(-EACCES);
 
 		cpuctx = per_cpu_ptr(pmu->pmu_cpu_context, cpu);
-- 
2.14.1