[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: [Xen-devel] [PATCH v10 10/19] qspinlock, x86: Allow unfair spinlock in a virtual guest

On 05/08/2014 03:12 PM, Peter Zijlstra wrote:
On Wed, May 07, 2014 at 11:01:38AM -0400, Waiman Long wrote:

No, we want the unfair thing for VIRT, not PARAVIRT.

Yes, you are right. I will change that to VIRT.

diff --git a/kernel/locking/qspinlock.c b/kernel/locking/qspinlock.c
index 9e7659e..10e87e1 100644
--- a/kernel/locking/qspinlock.c
+++ b/kernel/locking/qspinlock.c
@@ -227,6 +227,14 @@ static __always_inline int get_qlock(struct qspinlock 
        struct __qspinlock *l = (void *)lock;

+       if (static_key_false(&paravirt_unfairlocks_enabled))
+               /*
+                * Need to use atomic operation to get the lock when
+                * lock stealing can happen.
+                */
+               return cmpxchg(&l->locked, 0, _Q_LOCKED_VAL) == 0;
That's missing {}.

It is a single statement which doesn't need braces according to kernel coding style. I could move the comments up a bit to make it easier to read.


        ACCESS_ONCE(l->locked) = _Q_LOCKED_VAL;

But no, what you want is:

static __always_inline bool virt_lock(struct qspinlock *lock)
        if (static_key_false(&virt_unfairlocks_enabled)) {
                while (!queue_spin_trylock(lock))

                return true;
        return false;

void queue_spin_lock_slowpath(struct qspinlock *lock, u32 val)
        if (virt_lock(lock))


This is a possible way of doing it. I can do that in the patch series to simplify it. Hopefully that will speed up the review process and get it done quicker.


Xen-devel mailing list



Lists.xenproject.org is hosted with RackSpace, monitoring our
servers 24x7x365 and backed by RackSpace's Fanatical Support®.