block: add task-context bio completion infrastructure

Some bio completion handlers need to run from preemptible task context,
but bio_endio() may be called from IRQ context (e.g., buffer_head
writeback). Callers need a way to ensure their callback eventually runs
from a sleepable context. Add infrastructure for that, in two forms:

  1. BIO_COMPLETE_IN_TASK, a bio flag the submitter sets when it knows
     in advance that its callback needs task context (e.g., dropbehind
     writeback). bio_endio() sees the flag and offloads completion to a
     worker automatically.

  2. bio_complete_in_task(), a helper that completion callbacks can
     invoke from within bi_end_io() when the deferral decision is
     dynamic (e.g., fserror reporting).

Both share a per-CPU list drained by a work item on a WQ_PERCPU
workqueue. Producers push the bio onto the local CPU's list and schedule
the work item, which then dispatches each bio's bi_end_io() from task
context.

Both methods are gated on bio_in_atomic(), which returns true in any
context where a sleeping bi_end_io() is unsafe, including
non-preemptible task context.

Two CPU hotplug callbacks are used to drain remaining bios from the
departing CPU's batch, while maintaining the per-CPU behavior. The
CPUHP_AP_ONLINE_DYN callback disables the per-CPU work item while the
CPU is still online, preventing it from running on an unbound worker
later. CPUHP_BP_PREPARE_DYN then drains any bios added between disabling
the work item and CPU offline.

Link: https://lore.kernel.org/all/20260409160243.1008358-1-hch@lst.de/
Suggested-by: Matthew Wilcox <willy@infradead.org>
Suggested-by: Christoph Hellwig <hch@infradead.org>
Signed-off-by: Tal Zussman <tz2294@columbia.edu>
Reviewed-by: Jan Kara <jack@suse.cz>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Link: https://patch.msgid.link/20260730-blk-dontcache-v7-2-3e8e6850068d@columbia.edu
Signed-off-by: Jens Axboe <axboe@kernel.dk>

block/bio.c

@@ -1791,6 +1791,61 @@ void bio_check_pages_dirty(struct bio *bio)
 	schedule_work(&bio_dirty_work);
 }
 
+/*
+ * Infrastructure for deferring bio completions to task-context via a per-CPU
+ * workqueue. Triggered either by the BIO_COMPLETE_IN_TASK bio flag (static
+ * decision at submit time) or by calling bio_complete_in_task() from
+ * bi_end_io() (dynamic decision at completion time).
+ */
+
+struct bio_complete_batch {
+	struct bio_list list;
+	struct work_struct work;
+	int cpu;
+};
+
+static DEFINE_PER_CPU(struct bio_complete_batch, bio_complete_batch);
+static struct workqueue_struct *bio_complete_wq;
+
+static void bio_complete_work_fn(struct work_struct *w)
+{
+	struct bio_complete_batch *batch =
+		container_of(w, struct bio_complete_batch, work);
+
+	while (1) {
+		struct bio_list list;
+		struct bio *bio;
+
+		local_irq_disable();
+		list = batch->list;
+		bio_list_init(&batch->list);
+		local_irq_enable();
+
+		if (bio_list_empty(&list))
+			break;
+
+		while ((bio = bio_list_pop(&list)))
+			bio->bi_end_io(bio);
+	}
+}
+
+void __bio_complete_in_task(struct bio *bio)
+{
+	struct bio_complete_batch *batch;
+	unsigned long flags;
+	bool was_empty;
+
+	local_irq_save(flags);
+	batch = this_cpu_ptr(&bio_complete_batch);
+	was_empty = bio_list_empty(&batch->list);
+	bio_list_add(&batch->list, bio);
+	local_irq_restore(flags);
+
+	if (was_empty)
+		queue_work_on(batch->cpu, bio_complete_wq, &batch->work);
+}
+EXPORT_SYMBOL_GPL(__bio_complete_in_task);
+
 static inline bool bio_remaining_done(struct bio *bio)
 {
 	/*
@@ -1865,7 +1920,9 @@ void bio_endio(struct bio *bio)
 	}
 #endif
 
-	if (bio->bi_end_io)
+	if (bio_flagged(bio, BIO_COMPLETE_IN_TASK) && bio_in_atomic())
+		__bio_complete_in_task(bio);
+	else if (bio->bi_end_io)
 		bio->bi_end_io(bio);
 }
 EXPORT_SYMBOL(bio_endio);
@@ -2051,6 +2108,55 @@ int bioset_init(struct bio_set *bs,
 }
 EXPORT_SYMBOL(bioset_init);
 
+static int bio_complete_batch_cpu_online(unsigned int cpu)
+{
+	struct bio_complete_batch *batch = &per_cpu(bio_complete_batch, cpu);
+
+	enable_work(&batch->work);
+	if (!bio_list_empty(&batch->list))
+		queue_work_on(cpu, bio_complete_wq, &batch->work);
+	return 0;
+}
+
+/*
+ * Disable this CPU's work item so that it cannot run on an unbound worker
+ * after the CPU is offlined.
+ */
+static int bio_complete_batch_cpu_down_prep(unsigned int cpu)
+{
+	disable_work_sync(&per_cpu(bio_complete_batch, cpu).work);
+	return 0;
+}
+
+/*
+ * Drain a dead CPU's deferred bio completions. The CPU is dead and the worker
+ * is canceled so no locking is needed.
+ */
+static int bio_complete_batch_cpu_dead(unsigned int cpu)
+{
+	struct bio_complete_batch *batch =
+		per_cpu_ptr(&bio_complete_batch, cpu);
+	struct bio *bio;
+
+	while ((bio = bio_list_pop(&batch->list)))
+		bio->bi_end_io(bio);
+
+	return 0;
+}
+
+static void __init bio_complete_batch_init(int cpu)
+{
+	struct bio_complete_batch *batch =
+		per_cpu_ptr(&bio_complete_batch, cpu);
+
+	bio_list_init(&batch->list);
+	INIT_WORK(&batch->work, bio_complete_work_fn);
+	batch->cpu = cpu;
+
+	if (!cpu_online(cpu))
+		disable_work_sync(&batch->work);
+}
+
 static int __init init_bio(void)
 {
 	int i;
@@ -2065,6 +2171,30 @@ static int __init init_bio(void)
 				SLAB_HWCACHE_ALIGN | SLAB_PANIC, NULL);
 	}
 
+	for_each_possible_cpu(i)
+		bio_complete_batch_init(i);
+
+	bio_complete_wq = alloc_workqueue("bio_complete",
+					   WQ_MEM_RECLAIM | WQ_PERCPU, 0);
+	if (!bio_complete_wq)
+		panic("bio: can't allocate bio_complete workqueue\n");
+
+	/*
+	 * bio task-context completion draining on hot-unplugged CPUs:
+	 *
+	 *   1. Stop the per-CPU work item while the CPU is still online, so
+	 *      that it cannot run on an unbound worker later.
+	 *   2. Drain leftover bios added between worker disabling and CPU
+	 *      offlining.
+	 */
+	cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN,
+				  "block/bio:complete:online",
+				  bio_complete_batch_cpu_online,
+				  bio_complete_batch_cpu_down_prep);
+	cpuhp_setup_state_nocalls(CPUHP_BP_PREPARE_DYN,
+				  "block/bio:complete:dead",
+				  NULL, bio_complete_batch_cpu_dead);
+
 	cpuhp_setup_state_multi(CPUHP_BIO_DEAD, "block/bio:dead", NULL,
 					bio_cpu_dead);
 

include/linux/bio.h

@@ -383,6 +383,30 @@ static inline bool bio_in_atomic(void)
 	return !preemptible();
 }
 
+void __bio_complete_in_task(struct bio *bio);
+
+/**
+ * bio_complete_in_task - ensure a bio is completed in preemptible task context
+ * @bio: bio to complete
+ *
+ * If called from non-task context, offload the bio completion to a worker
+ * thread and return %true. Else return %false and do nothing.
+ *
+ * Uses BIO_COMPLETE_IN_TASK as a sentinel: if set, the bio was already
+ * deferred and we are running in the worker — return %false so the
+ * callback proceeds instead of re-deferring.
+ */
+static inline bool bio_complete_in_task(struct bio *bio)
+{
+	if (bio_flagged(bio, BIO_COMPLETE_IN_TASK))
+		return false;
+	if (!bio_in_atomic())
+		return false;
+	bio_set_flag(bio, BIO_COMPLETE_IN_TASK);
+	__bio_complete_in_task(bio);
+	return true;
+}
+
 extern void bio_endio(struct bio *);
 
 /**

include/linux/blk_types.h

@@ -322,6 +322,7 @@ enum {
 	BIO_REMAPPED,
 	BIO_ZONE_WRITE_PLUGGING, /* bio handled through zone write plugging */
 	BIO_EMULATES_ZONE_APPEND, /* bio emulates a zone append operation */
+	BIO_COMPLETE_IN_TASK, /* complete bi_end_io() in task context */
 	BIO_FLAG_LAST
 };