Enabling locking-selftest in a VM guest may cause the following
kernel panic:
kernel BUG at .../kernel/locking/qspinlock_paravirt.h:137!
This is due to the fact that the pvqspinlock unlock function is
expecting either a _Q_LOCKED_VAL or _Q_SLOW_VAL in the lock byte. This
patch prevents that bug report by ignoring it when debug_locks_silent
is set. Otherwise, a warning will be printed if it contains an
unexpected value.
With this patch applied, the kernel locking-selftest completed without
any noise.
Signed-off-by: Waiman Long <[email protected]>
---
kernel/locking/qspinlock_paravirt.h | 12 +++++++++++-
1 files changed, 11 insertions(+), 1 deletions(-)
diff --git a/kernel/locking/qspinlock_paravirt.h b/kernel/locking/qspinlock_paravirt.h
index 04ab181..15d3733 100644
--- a/kernel/locking/qspinlock_paravirt.h
+++ b/kernel/locking/qspinlock_paravirt.h
@@ -4,6 +4,7 @@
#include <linux/hash.h>
#include <linux/bootmem.h>
+#include <linux/debug_locks.h>
/*
* Implement paravirt qspinlocks; the general idea is to halt the vcpus instead
@@ -286,15 +287,24 @@ __visible void __pv_queued_spin_unlock(struct qspinlock *lock)
{
struct __qspinlock *l = (void *)lock;
struct pv_node *node;
+ u8 lockval = cmpxchg(&l->locked, _Q_LOCKED_VAL, 0);
/*
* We must not unlock if SLOW, because in that case we must first
* unhash. Otherwise it would be possible to have multiple @lock
* entries, which would be BAD.
*/
- if (likely(cmpxchg(&l->locked, _Q_LOCKED_VAL, 0) == _Q_LOCKED_VAL))
+ if (likely(lockval == _Q_LOCKED_VAL))
return;
+ if (unlikely(lockval != _Q_SLOW_VAL)) {
+ if (debug_locks_silent)
+ return;
+ WARN(1, "pvqspinlock: lock 0x%lx has corrupted value 0x%x!\n",
+ (unsigned long)lock, atomic_read(&lock->val));
+ return;
+ }
+
/*
* Since the above failed to release, this must be the SLOW path.
* Therefore start by looking up the blocked node and unhashing it.
--
1.7.1
On 2015/07/12 10:19, Waiman Long wrote:
> Enabling locking-selftest in a VM guest may cause the following
> kernel panic:
>
> kernel BUG at .../kernel/locking/qspinlock_paravirt.h:137!
>
> This is due to the fact that the pvqspinlock unlock function is
> expecting either a _Q_LOCKED_VAL or _Q_SLOW_VAL in the lock byte. This
> patch prevents that bug report by ignoring it when debug_locks_silent
> is set. Otherwise, a warning will be printed if it contains an
> unexpected value.
>
> With this patch applied, the kernel locking-selftest completed without
> any noise.
>
OK, I've tested this with make allmodconfig && make localmodconfig kernel.
(I've hit another issue to boot, but it seems not related to this issue)
Tested-by: Masami Hiramatsu <[email protected]>
Thank you!
> Signed-off-by: Waiman Long <[email protected]>
> ---
> kernel/locking/qspinlock_paravirt.h | 12 +++++++++++-
> 1 files changed, 11 insertions(+), 1 deletions(-)
>
> diff --git a/kernel/locking/qspinlock_paravirt.h b/kernel/locking/qspinlock_paravirt.h
> index 04ab181..15d3733 100644
> --- a/kernel/locking/qspinlock_paravirt.h
> +++ b/kernel/locking/qspinlock_paravirt.h
> @@ -4,6 +4,7 @@
>
> #include <linux/hash.h>
> #include <linux/bootmem.h>
> +#include <linux/debug_locks.h>
>
> /*
> * Implement paravirt qspinlocks; the general idea is to halt the vcpus instead
> @@ -286,15 +287,24 @@ __visible void __pv_queued_spin_unlock(struct qspinlock *lock)
> {
> struct __qspinlock *l = (void *)lock;
> struct pv_node *node;
> + u8 lockval = cmpxchg(&l->locked, _Q_LOCKED_VAL, 0);
>
> /*
> * We must not unlock if SLOW, because in that case we must first
> * unhash. Otherwise it would be possible to have multiple @lock
> * entries, which would be BAD.
> */
> - if (likely(cmpxchg(&l->locked, _Q_LOCKED_VAL, 0) == _Q_LOCKED_VAL))
> + if (likely(lockval == _Q_LOCKED_VAL))
> return;
>
> + if (unlikely(lockval != _Q_SLOW_VAL)) {
> + if (debug_locks_silent)
> + return;
> + WARN(1, "pvqspinlock: lock 0x%lx has corrupted value 0x%x!\n",
> + (unsigned long)lock, atomic_read(&lock->val));
> + return;
> + }
> +
> /*
> * Since the above failed to release, this must be the SLOW path.
> * Therefore start by looking up the blocked node and unhashing it.
>
--
Masami HIRAMATSU
Linux Technology Research Center, System Productivity Research Dept.
Center for Technology Innovation - Systems Engineering
Hitachi, Ltd., Research & Development Group
E-mail: [email protected]
Commit-ID: cba77f03f2c7b6cc0b0a44a3c679e0abade7da62
Gitweb: http://git.kernel.org/tip/cba77f03f2c7b6cc0b0a44a3c679e0abade7da62
Author: Waiman Long <[email protected]>
AuthorDate: Sat, 11 Jul 2015 21:19:19 -0400
Committer: Ingo Molnar <[email protected]>
CommitDate: Tue, 21 Jul 2015 10:18:07 +0200
locking/pvqspinlock: Fix kernel panic in locking-selftest
Enabling locking-selftest in a VM guest may cause the following
kernel panic:
kernel BUG at .../kernel/locking/qspinlock_paravirt.h:137!
This is due to the fact that the pvqspinlock unlock function is
expecting either a _Q_LOCKED_VAL or _Q_SLOW_VAL in the lock
byte. This patch prevents that bug report by ignoring it when
debug_locks_silent is set. Otherwise, a warning will be printed
if it contains an unexpected value.
With this patch applied, the kernel locking-selftest completed
without any noise.
Tested-by: Masami Hiramatsu <[email protected]>
Signed-off-by: Waiman Long <[email protected]>
Cc: Linus Torvalds <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: Thomas Gleixner <[email protected]>
Link: http://lkml.kernel.org/r/[email protected]
Signed-off-by: Ingo Molnar <[email protected]>
---
kernel/locking/qspinlock_paravirt.h | 11 ++++++++++-
1 file changed, 10 insertions(+), 1 deletion(-)
diff --git a/kernel/locking/qspinlock_paravirt.h b/kernel/locking/qspinlock_paravirt.h
index 04ab181..df19ae4 100644
--- a/kernel/locking/qspinlock_paravirt.h
+++ b/kernel/locking/qspinlock_paravirt.h
@@ -4,6 +4,7 @@
#include <linux/hash.h>
#include <linux/bootmem.h>
+#include <linux/debug_locks.h>
/*
* Implement paravirt qspinlocks; the general idea is to halt the vcpus instead
@@ -286,15 +287,23 @@ __visible void __pv_queued_spin_unlock(struct qspinlock *lock)
{
struct __qspinlock *l = (void *)lock;
struct pv_node *node;
+ u8 lockval = cmpxchg(&l->locked, _Q_LOCKED_VAL, 0);
/*
* We must not unlock if SLOW, because in that case we must first
* unhash. Otherwise it would be possible to have multiple @lock
* entries, which would be BAD.
*/
- if (likely(cmpxchg(&l->locked, _Q_LOCKED_VAL, 0) == _Q_LOCKED_VAL))
+ if (likely(lockval == _Q_LOCKED_VAL))
return;
+ if (unlikely(lockval != _Q_SLOW_VAL)) {
+ if (debug_locks_silent)
+ return;
+ WARN(1, "pvqspinlock: lock %p has corrupted value 0x%x!\n", lock, atomic_read(&lock->val));
+ return;
+ }
+
/*
* Since the above failed to release, this must be the SLOW path.
* Therefore start by looking up the blocked node and unhashing it.