irq_work, smp: Allow irq_work on call_single_queue

Currently irq_work_queue_on() will issue an unconditional
arch_send_call_function_single_ipi() and has the handler do
irq_work_run().

This is unfortunate in that it makes the IPI handler look at a second
cacheline and it misses the opportunity to avoid the IPI. Instead note
that struct irq_work and struct __call_single_data are very similar in
layout, so use a few bits in the flags word to encode a type and stick
the irq_work on the call_single_queue list.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20200526161908.011635912@infradead.org

1 files changed, 22 insertions, 1 deletions

diff --git a/include/linux/smp.h b/include/linux/smp.h
index cbc9162689d0..45ad6e30f398 100644
--- a/include/linux/smp.h
+++ b/include/linux/smp.h
@@ -16,17 +16,38 @@
 
 typedef void (*smp_call_func_t)(void *info);
 typedef bool (*smp_cond_func_t)(int cpu, void *info);
+
+enum {
+	CSD_FLAG_LOCK		= 0x01,
+
+	/* IRQ_WORK_flags */
+
+	CSD_TYPE_ASYNC		= 0x00,
+	CSD_TYPE_SYNC		= 0x10,
+	CSD_TYPE_IRQ_WORK	= 0x20,
+	CSD_FLAG_TYPE_MASK	= 0xF0,
+};
+
+/*
+ * structure shares (partial) layout with struct irq_work
+ */
 struct __call_single_data {
 	struct llist_node llist;
+	unsigned int flags;
 	smp_call_func_t func;
 	void *info;
-	unsigned int flags;
 };
 
 /* Use __aligned() to avoid to use 2 cache lines for 1 csd */
 typedef struct __call_single_data call_single_data_t
 	__aligned(sizeof(struct __call_single_data));
 
+/*
+ * Enqueue a llist_node on the call_single_queue; be very careful, read
+ * flush_smp_call_function_queue() in detail.
+ */
+extern void __smp_call_single_queue(int cpu, struct llist_node *node);
+
 /* total number of cpus in this system (may exceed NR_CPUS) */
 extern unsigned int total_cpus;