oprofile, x86: Fix race in nmi handler while starting counters

In some rare cases, nmis are generated immediately after the nmi
handler of the cpu was started. This causes the counter not to be
enabled. Before enabling the nmi handlers we need to set variable
ctr_running first and make sure its value is written to memory.

Also, the patch makes all existing barriers a memory barrier instead
of a compiler barrier only.

Reported-by: Suravee Suthikulpanit <suravee.suthikulpanit@amd.com>
Cc: <stable@kernel.org> # .35+
Signed-off-by: Robert Richter <robert.richter@amd.com>

diff --git a/arch/x86/oprofile/nmi_int.c b/arch/x86/oprofile/nmi_int.c
index cf9750004a08fe673eb312414090c7b0c7759b09..68894fdc034bc3cb01cd79b66ec995dadc7b7c67 100644 (file)
--- a/arch/x86/oprofile/nmi_int.c
+++ b/arch/x86/oprofile/nmi_int.c
@@ -112,8 +112,10 @@ static void nmi_cpu_start(void *dummy)
 static int nmi_start(void)
 {
        get_online_cpus();
-       on_each_cpu(nmi_cpu_start, NULL, 1);
        ctr_running = 1;
+       /* make ctr_running visible to the nmi handler: */
+       smp_mb();
+       on_each_cpu(nmi_cpu_start, NULL, 1);
        put_online_cpus();
        return 0;
 }
@@ -504,15 +506,18 @@ static int nmi_setup(void)
 
        nmi_enabled = 0;
        ctr_running = 0;
-       barrier();
+       /* make variables visible to the nmi handler: */
+       smp_mb();
        err = register_die_notifier(&profile_exceptions_nb);
        if (err)
                goto fail;
 
        get_online_cpus();
        register_cpu_notifier(&oprofile_cpu_nb);
-       on_each_cpu(nmi_cpu_setup, NULL, 1);
        nmi_enabled = 1;
+       /* make nmi_enabled visible to the nmi handler: */
+       smp_mb();
+       on_each_cpu(nmi_cpu_setup, NULL, 1);
        put_online_cpus();
 
        return 0;
@@ -531,7 +536,8 @@ static void nmi_shutdown(void)
        nmi_enabled = 0;
        ctr_running = 0;
        put_online_cpus();
-       barrier();
+       /* make variables visible to the nmi handler: */
+       smp_mb();
        unregister_die_notifier(&profile_exceptions_nb);
        msrs = &get_cpu_var(cpu_msrs);
        model->shutdown(msrs);