[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20240610124406.359476013@linutronix.de>
Date: Mon, 10 Jun 2024 14:46:35 +0200 (CEST)
From: Thomas Gleixner <tglx@...utronix.de>
To: LKML <linux-kernel@...r.kernel.org>
Cc: Steven Rostedt <rostedt@...dmis.org>,
Sam Sun <samsun1006219@...il.com>,
x86@...nel.org,
syzkaller-bugs@...glegroups.com,
xrivendell7@...il.com
Subject: [patch 1/4] perf/x86: Serialize set_attr_rdpmc()
Yue and Xingwei reported a jump label failure. It's caused by the lack of
serialization in set_attr_rdpmc():
CPU0 CPU1
Assume: x86_pmu.attr_rdpmc == 0
if (val != x86_pmu.attr_rdpmc) {
if (val == 0)
...
else if (x86_pmu.attr_rdpmc == 0)
static_branch_dec(&rdpmc_never_available_key);
if (val != x86_pmu.attr_rdpmc) {
if (val == 0)
...
else if (x86_pmu.attr_rdpmc == 0)
FAIL, due to imbalance ---> static_branch_dec(&rdpmc_never_available_key);
The reported BUG() is a consequence of the above and of another bug in the
jump label core code. The core code needs a separate fix, but that cannot
prevent the imbalance problem caused by set_attr_rdpmc().
Prevent this by serializing set_attr_rdpmc() locally.
Fixes: a66734297f78 ("perf/x86: Add /sys/devices/cpu/rdpmc=2 to allow rdpmc for all tasks")
Reported-by: Yue Sun <samsun1006219@...il.com>
Reported-by: Xingwei Lee <xrivendell7@...il.com>
Signed-off-by: Thomas Gleixner <tglx@...utronix.de>
Closes: https://lore.kernel.org/r/CAEkJfYNzfW1vG=ZTMdz_Weoo=RXY1NDunbxnDaLyj8R4kEoE_w@mail.gmail.com
---
arch/x86/events/core.c | 3 +++
1 file changed, 3 insertions(+)
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -2547,6 +2547,7 @@ static ssize_t set_attr_rdpmc(struct dev
struct device_attribute *attr,
const char *buf, size_t count)
{
+ static DEFINE_MUTEX(rdpmc_mutex);
unsigned long val;
ssize_t ret;
@@ -2560,6 +2561,8 @@ static ssize_t set_attr_rdpmc(struct dev
if (x86_pmu.attr_rdpmc_broken)
return -ENOTSUPP;
+ guard(mutex)(&rdpmc_mutex);
+
if (val != x86_pmu.attr_rdpmc) {
/*
* Changing into or out of never available or always available,
Powered by blists - more mailing lists