blk-mq: merge blk-softirq.c into blk-mq.c

__blk_complete_request is only called from the blk-mq code, and
duplicates a lot of code from blk-mq.c.  Move it there to prepare
for better code sharing and simplifications.

Signed-off-by: Christoph Hellwig <[email protected]>
Reviewed-by: Daniel Wagner <[email protected]>
Signed-off-by: Jens Axboe <[email protected]>

block/Makefile

@@ -5,7 +5,7 @@
 
 obj-$(CONFIG_BLOCK) := bio.o elevator.o blk-core.o blk-sysfs.o \
 			blk-flush.o blk-settings.o blk-ioc.o blk-map.o \
-			blk-exec.o blk-merge.o blk-softirq.o blk-timeout.o \
+			blk-exec.o blk-merge.o blk-timeout.o \
 			blk-lib.o blk-mq.o blk-mq-tag.o blk-stat.o \
 			blk-mq-sysfs.o blk-mq-cpumap.o blk-mq-sched.o ioctl.o \
 			genhd.o ioprio.o badblocks.o partitions/ blk-rq-qos.o

block/blk-mq.c

@@ -41,6 +41,8 @@
 #include "blk-mq-sched.h"
 #include "blk-rq-qos.h"
 
+static DEFINE_PER_CPU(struct list_head, blk_cpu_done);
+
 static void blk_mq_poll_stats_start(struct request_queue *q);
 static void blk_mq_poll_stats_fn(struct blk_stat_callback *cb);
 
@@ -574,6 +576,130 @@ void blk_mq_end_request(struct request *rq, blk_status_t error)
 }
 EXPORT_SYMBOL(blk_mq_end_request);
 
+/*
+ * Softirq action handler - move entries to local list and loop over them
+ * while passing them to the queue registered handler.
+ */
+static __latent_entropy void blk_done_softirq(struct softirq_action *h)
+{
+	struct list_head *cpu_list, local_list;
+
+	local_irq_disable();
+	cpu_list = this_cpu_ptr(&blk_cpu_done);
+	list_replace_init(cpu_list, &local_list);
+	local_irq_enable();
+
+	while (!list_empty(&local_list)) {
+		struct request *rq;
+
+		rq = list_entry(local_list.next, struct request, ipi_list);
+		list_del_init(&rq->ipi_list);
+		rq->q->mq_ops->complete(rq);
+	}
+}
+
+#ifdef CONFIG_SMP
+static void trigger_softirq(void *data)
+{
+	struct request *rq = data;
+	struct list_head *list;
+
+	list = this_cpu_ptr(&blk_cpu_done);
+	list_add_tail(&rq->ipi_list, list);
+
+	if (list->next == &rq->ipi_list)
+		raise_softirq_irqoff(BLOCK_SOFTIRQ);
+}
+
+/*
+ * Setup and invoke a run of 'trigger_softirq' on the given cpu.
+ */
+static int raise_blk_irq(int cpu, struct request *rq)
+{
+	if (cpu_online(cpu)) {
+		call_single_data_t *data = &rq->csd;
+
+		data->func = trigger_softirq;
+		data->info = rq;
+		data->flags = 0;
+
+		smp_call_function_single_async(cpu, data);
+		return 0;
+	}
+
+	return 1;
+}
+#else /* CONFIG_SMP */
+static int raise_blk_irq(int cpu, struct request *rq)
+{
+	return 1;
+}
+#endif
+
+static int blk_softirq_cpu_dead(unsigned int cpu)
+{
+	/*
+	 * If a CPU goes away, splice its entries to the current CPU
+	 * and trigger a run of the softirq
+	 */
+	local_irq_disable();
+	list_splice_init(&per_cpu(blk_cpu_done, cpu),
+			 this_cpu_ptr(&blk_cpu_done));
+	raise_softirq_irqoff(BLOCK_SOFTIRQ);
+	local_irq_enable();
+
+	return 0;
+}
+
+static void __blk_complete_request(struct request *req)
+{
+	struct request_queue *q = req->q;
+	int cpu, ccpu = req->mq_ctx->cpu;
+	unsigned long flags;
+	bool shared = false;
+
+	BUG_ON(!q->mq_ops->complete);
+
+	local_irq_save(flags);
+	cpu = smp_processor_id();
+
+	/*
+	 * Select completion CPU
+	 */
+	if (test_bit(QUEUE_FLAG_SAME_COMP, &q->queue_flags) && ccpu != -1) {
+		if (!test_bit(QUEUE_FLAG_SAME_FORCE, &q->queue_flags))
+			shared = cpus_share_cache(cpu, ccpu);
+	} else
+		ccpu = cpu;
+
+	/*
+	 * If current CPU and requested CPU share a cache, run the softirq on
+	 * the current CPU. One might concern this is just like
+	 * QUEUE_FLAG_SAME_FORCE, but actually not. blk_complete_request() is
+	 * running in interrupt handler, and currently I/O controller doesn't
+	 * support multiple interrupts, so current CPU is unique actually. This
+	 * avoids IPI sending from current CPU to the first CPU of a group.
+	 */
+	if (ccpu == cpu || shared) {
+		struct list_head *list;
+do_local:
+		list = this_cpu_ptr(&blk_cpu_done);
+		list_add_tail(&req->ipi_list, list);
+
+		/*
+		 * if the list only contains our just added request,
+		 * signal a raise of the softirq. If there are already
+		 * entries there, someone already raised the irq but it
+		 * hasn't run yet.
+		 */
+		if (list->next == &req->ipi_list)
+			raise_softirq_irqoff(BLOCK_SOFTIRQ);
+	} else if (raise_blk_irq(ccpu, req))
+		goto do_local;
+
+	local_irq_restore(flags);
+}
+
 static void __blk_mq_complete_request_remote(void *data)
 {
 	struct request *rq = data;
@@ -3760,6 +3886,15 @@ EXPORT_SYMBOL(blk_mq_rq_cpu);
 
 static int __init blk_mq_init(void)
 {
+	int i;
+
+	for_each_possible_cpu(i)
+		INIT_LIST_HEAD(&per_cpu(blk_cpu_done, i));
+	open_softirq(BLOCK_SOFTIRQ, blk_done_softirq);
+
+	cpuhp_setup_state_nocalls(CPUHP_BLOCK_SOFTIRQ_DEAD,
+				  "block/softirq:dead", NULL,
+				  blk_softirq_cpu_dead);
 	cpuhp_setup_state_multi(CPUHP_BLK_MQ_DEAD, "block/mq:dead", NULL,
 				blk_mq_hctx_notify_dead);
 	cpuhp_setup_state_multi(CPUHP_AP_BLK_MQ_ONLINE, "block/mq:online",

include/linux/blkdev.h

@@ -1078,7 +1078,6 @@ void blk_steal_bios(struct bio_list *list, struct request *rq);
 extern bool blk_update_request(struct request *rq, blk_status_t error,
 			       unsigned int nr_bytes);
 
-extern void __blk_complete_request(struct request *);
 extern void blk_abort_request(struct request *);
 
 /*