Re: [PATCH v8 3/5] locking/qspinlock: Introduce CNA into the slow path of qspinlock
From: Peter Zijlstra <peterz@infradead.org>
Date: 2020-01-21 14:42:46
Also in:
linux-arch, lkml
On Mon, Dec 30, 2019 at 02:40:40PM -0500, Alex Kogan wrote:
+#define pv_wait_head_or_lock cna_pre_scan
Also inconsitent naming.
+__always_inline u32 cna_pre_scan(struct qspinlock *lock,
+ struct mcs_spinlock *node)
+{
+ struct cna_node *cn = (struct cna_node *)node;
+
+ cn->pre_scan_result = cna_scan_main_queue(node, node);
+
+ return 0;
+}The thinking here is that we're trying to make use of the time otherwise spend spinning on atomic_cond_read_acquire(), to search for a potential unlock candidate? Surely that deserves a comment. _______________________________________________ linux-arm-kernel mailing list linux-arm-kernel@lists.infradead.org http://lists.infradead.org/mailman/listinfo/linux-arm-kernel