Re: [PATCH-v2 1/3] percpu_ida: Make percpu_ida_alloc + callers accept task state bitmask

[Peter Zijlstra <peterz@infradead.org>]

On Thu, Jan 23, 2014 at 05:22:54PM +0100, Peter Zijlstra wrote:
> On Thu, Jan 23, 2014 at 05:28:29AM -0800, Kent Overstreet wrote:
> > pool->lock is also going to be fairly badly contended in the worst case,
> > and that can get real bad real fast... now that I think about it we
> > probably want to avoid the __alloc_global_tag() double call just because
> > of that, pool->lock is going to be quite a bit more contended than the
> > waitlist lock just because fo the amount of work done under it.

> Now everything modifying percpu_ida_cpu state holds
> percpu_ida_cpu::lock

Almost that.

---
--- a/lib/percpu_ida.c
+++ b/lib/percpu_ida.c
@@ -51,6 +51,15 @@ static inline void move_tags(unsigned *d
 	*dst_nr += nr;
 }
 
+static inline void double_lock(spinlock_t *l1, spinlock_t *l2)
+{
+	if (l1 > l2)
+		swap(l1, l2);
+
+	spin_lock(l1);
+	spin_lock_nested(l2, SINGLE_DEPTH_NESTING);
+}
+
 /*
  * Try to steal tags from a remote cpu's percpu freelist.
  *
@@ -87,7 +96,7 @@ static inline void steal_tags(struct per
 		if (remote == tags)
 			continue;
 
-		spin_lock(&remote->lock);
+		double_lock(&tags->lock, &remote->lock);
 
 		if (remote->nr_free) {
 			memcpy(tags->freelist,
@@ -99,6 +108,7 @@ static inline void steal_tags(struct per
 		}
 
 		spin_unlock(&remote->lock);
+		spin_unlock(&tags->lock);
 
 		if (tags->nr_free)
 			break;