Re: [PATCH 02/11] mm/page_alloc: Convert per-cpu list protection to local_lock

[Thomas Gleixner]

On Mon, Apr 12 2021 at 12:56, Mel Gorman wrote:
> On Fri, Apr 09, 2021 at 08:55:39PM +0200, Peter Zijlstra wrote:
> I'll update the changelog and comment accordingly. I'll decide later
> whether to leave it or move the location of the lock at the end of the
> series. If the patch is added, it'll either incur the double lookup (not
> that expensive, might be optimised by the compiler) or come up with a
> helper that takes the lock and returns the per-cpu structure. The double
> lookup probably makes more sense initially because there are multiple
> potential users of a helper that says "pin to CPU, lookup, lock and return
> a per-cpu structure" for both IRQ-safe and IRQ-unsafe variants with the
> associated expansion of the local_lock API. It might be better to introduce
> such a helper with multiple users converted at the same time and there are
> other local_lock users in preempt-rt that could do with upstreaming first.

We had such helpers in RT a while ago but it turned into an helper
explosion pretty fast. But that was one of the early versions of local
locks which could not be embedded into a per CPU data structure due to
raisins (my stupidity).

But with the more thought out approach of today we can have (+/- the
obligatory naming bikeshedding):

--- a/include/linux/local_lock.h
+++ b/include/linux/local_lock.h
@@ -51,4 +51,35 @@
 #define local_unlock_irqrestore(lock, flags)			\
 	__local_unlock_irqrestore(lock, flags)
 
+/**
+ * local_lock_get_cpu_ptr - Acquire a per CPU local lock and return
+ *			    a pointer to the per CPU data which
+ *			    contains the local lock.
+ * @pcp:	Per CPU data structure
+ * @lock:	The local lock member of @pcp
+ */
+#define local_lock_get_cpu_ptr(pcp, lock)			\
+	__local_lock_get_cpu_ptr(pcp, typeof(*(pcp)), lock)
+
+/**
+ * local_lock_irq_get_cpu_ptr - Acquire a per CPU local lock, disable
+ *				interrupts and return a pointer to the
+ *				per CPU data which contains the local lock.
+ * @pcp:	Per CPU data structure
+ * @lock:	The local lock member of @pcp
+ */
+#define local_lock_irq_get_cpu_ptr(pcp, lock)			\
+	__local_lock_irq_get_cpu_ptr(pcp, typeof(*(pcp)), lock)
+
+/**
+ * local_lock_irqsave_get_cpu_ptr - Acquire a per CPU local lock, save and
+ *				    disable interrupts and return a pointer to
+ *				    the CPU data which contains the local lock.
+ * @pcp:	Per CPU data structure
+ * @lock:	The local lock member of @pcp
+ * @flags:	Storage for interrupt flags
+ */
+#define local_lock_irqsave_get_cpu_ptr(pcp, lock, flags)	\
+	__local_lock_irqsave_get_cpu_ptr(pcp, typeof(*(pcp)), lock, flags)
+
 #endif
--- a/include/linux/local_lock_internal.h
+++ b/include/linux/local_lock_internal.h
@@ -91,3 +91,33 @@ static inline void local_lock_release(lo
 		local_lock_release(this_cpu_ptr(lock));		\
 		local_irq_restore(flags);			\
 	} while (0)
+
+#define __local_lock_get_cpu_ptr(pcp, type, lock)		\
+	({							\
+		type *__pcp;					\
+								\
+		preempt_disable();				\
+		__pcp = this_cpu_ptr(pcp);			\
+		local_lock_acquire(&__pcp->lock);		\
+		__pcp;						\
+	})
+
+#define __local_lock_irq_get_cpu_ptr(pcp, type, lock)		\
+	({							\
+		type *__pcp;					\
+								\
+		local_irq_disable();				\
+		__pcp = this_cpu_ptr(pcp);			\
+		local_lock_acquire(&__pcp->lock);		\
+		__pcp;						\
+	})
+
+#define __local_lock_irqsave_get_cpu_ptr(pcp, type, lock, flags)\
+	({							\
+		type *__pcp;					\
+								\
+		local_irq_save(flags);				\
+		__pcp = this_cpu_ptr(pcp);			\
+		local_lock_acquire(&__pcp->lock);		\
+		__pcp;						\
+	})


and RT will then change that to:

--- a/include/linux/local_lock_internal.h
+++ b/include/linux/local_lock_internal.h
@@ -96,7 +96,7 @@ static inline void local_lock_release(lo
 	({							\
 		type *__pcp;					\
 								\
-		preempt_disable();				\
+		ll_preempt_disable();				\
 		__pcp = this_cpu_ptr(pcp);			\
 		local_lock_acquire(&__pcp->lock);		\
 		__pcp;						\
@@ -106,7 +106,7 @@ static inline void local_lock_release(lo
 	({							\
 		type *__pcp;					\
 								\
-		local_irq_disable();				\
+		ll_local_irq_disable();				\
 		__pcp = this_cpu_ptr(pcp);			\
 		local_lock_acquire(&__pcp->lock);		\
 		__pcp;						\
@@ -116,7 +116,7 @@ static inline void local_lock_release(lo
 	({							\
 		type *__pcp;					\
 								\
-		local_irq_save(flags);				\
+		ll_local_irq_save(flags);			\
 		__pcp = this_cpu_ptr(pcp);			\
 		local_lock_acquire(&__pcp->lock);		\
 		__pcp;						\


where ll_xxx is defined as xxx for non-RT and on RT all of them
get mapped to migrate_disable().

Thoughts?

Thanks,

        tglx