Re: [PATCH v4 tip/perf/core 2/4] mm: Introduce mmap_lock_speculation_{begin|end}

[Peter Zijlstra]

On Thu, Nov 21, 2024 at 03:44:42PM +0100, Peter Zijlstra wrote:

> But perhaps it makes even more sense to add this functionality to
> seqcount itself. The same argument can be made for seqcount_mutex and
> seqcount_rwlock users.

Something like so I suppose.

---
diff --git a/include/linux/seqlock.h b/include/linux/seqlock.h
index 5298765d6ca4..102afdf8c7db 100644
--- a/include/linux/seqlock.h
+++ b/include/linux/seqlock.h
@@ -318,6 +318,28 @@ SEQCOUNT_LOCKNAME(mutex,        struct mutex,    true,     mutex)
 	__seq;								\
 })
 
+/**
+ * raw_seqcount_try_begin() - begin a seqcount_t read critical section
+ *                            w/o lockdep and w/o counter stabilization
+ * @s: Pointer to seqcount_t or any of the seqcount_LOCKNAME_t variants
+ *
+ * Very like raw_seqcount_begin(), except it enables eliding the critical
+ * section entirely if odd, instead of doing the speculation knowing it will
+ * fail.
+ *
+ * Useful when counter stabilization is more or less equivalent to taking
+ * the lock and there is a slowpath that does that.
+ *
+ * If true, start will be set to the (even) sequence count read.
+ *
+ * Return: true when a read critical section is started.
+ */
+#define raw_seqcount_try_begin(s, start)				\
+({									\
+	start = raw_read_seqcount(s);					\
+	!(start & 1);							\
+})
+
 /**
  * raw_seqcount_begin() - begin a seqcount_t read critical section w/o
  *                        lockdep and w/o counter stabilization