kexec_prepare_cpus_wait() calls get_cpu() internally to obtain the
current CPU id. kexec_prepare_cpus() calls kexec_prepare_cpus_wait()
twice -- once for KEXEC_STATE_IRQS_OFF and once for
KEXEC_STATE_REAL_MODE -- but only issues a single put_cpu() at the end,
leaving preempt_count elevated by one extra nesting level.
In practice the imbalance does not trigger a 'scheduling while atomic'
splat because the kexec path is a one-way trip: IRQs are already
disabled, no schedule() occurs after the leak, and
default_machine_kexec() overwrites preempt_count with HARDIRQ_OFFSET
before jumping into kexec_sequence() which never returns. However the
bookkeeping is still wrong.
Lift the get_cpu()/put_cpu() pair into kexec_prepare_cpus() so it is
called exactly once, and pass the CPU id to kexec_prepare_cpus_wait()
as a parameter. This keeps preempt_count correctly balanced.
Fixes: 1fc711f7ffb01 ("powerpc/kexec: Fix race in kexec shutdown")
Signed-off-by: Aboorva Devarajan <[email protected]>
---
arch/powerpc/kexec/core_64.c | 15 ++++++++-------
1 file changed, 8 insertions(+), 7 deletions(-)
diff --git a/arch/powerpc/kexec/core_64.c b/arch/powerpc/kexec/core_64.c
index 825ab8a88f18e..9d7e5a1e6e5b8 100644
--- a/arch/powerpc/kexec/core_64.c
+++ b/arch/powerpc/kexec/core_64.c
@@ -164,12 +164,11 @@ static void kexec_smp_down(void *arg)
/* NOTREACHED */
}
-static void kexec_prepare_cpus_wait(int wait_state)
+static void kexec_prepare_cpus_wait(int wait_state, int my_cpu)
{
- int my_cpu, i, notified=-1;
+ int i, notified = -1;
hw_breakpoint_disable();
- my_cpu = get_cpu();
/* Make sure each CPU has at least made it to the state we need.
*
* FIXME: There is a (slim) chance of a problem if not all of the CPUs
@@ -246,6 +245,8 @@ static void wake_offline_cpus(void)
static void kexec_prepare_cpus(void)
{
+ int my_cpu;
+
wake_offline_cpus();
smp_call_function(kexec_smp_down, NULL, /* wait */0);
local_irq_disable();
@@ -254,7 +255,8 @@ static void kexec_prepare_cpus(void)
mb(); /* make sure IRQs are disabled before we say they are */
get_paca()->kexec_state = KEXEC_STATE_IRQS_OFF;
- kexec_prepare_cpus_wait(KEXEC_STATE_IRQS_OFF);
+ my_cpu = get_cpu();
+ kexec_prepare_cpus_wait(KEXEC_STATE_IRQS_OFF, my_cpu);
/* we are sure every CPU has IRQs off at this point */
kexec_all_irq_disabled = 1;
@@ -262,13 +264,12 @@ static void kexec_prepare_cpus(void)
* Before removing MMU mappings make sure all CPUs have entered real
* mode:
*/
- kexec_prepare_cpus_wait(KEXEC_STATE_REAL_MODE);
+ kexec_prepare_cpus_wait(KEXEC_STATE_REAL_MODE, my_cpu);
+ put_cpu();
/* after we tell the others to go down */
if (ppc_md.kexec_cpu_down)
ppc_md.kexec_cpu_down(0, 0);
-
- put_cpu();
}
#else /* ! SMP */
--
2.54.0
