From 9f6dc633761006f974701d4c88da71ab68670749 Mon Sep 17 00:00:00 2001
From: Mike Snitzer <snitzer@redhat.com>
Date: Thu, 17 Feb 2022 23:40:02 -0500
Subject: [PATCH] dm: interlock pending dm_io and dm_wait_for_bios_completion
Git-commit: 9f6dc633761006f974701d4c88da71ab68670749
Patch-mainline: v5.18-rc1
References: git-fixes

Commit d208b89401e0 ("dm: fix mempool NULL pointer race when
completing IO") didn't go far enough.

When bio_end_io_acct ends the count of in-flight I/Os may reach zero
and the DM device may be suspended. There is a possibility that the
suspend races with dm_stats_account_io.

Fix this by adding percpu "pending_io" counters to track outstanding
dm_io. Move kicking of suspend queue to dm_io_dec_pending(). Also,
rename md_in_flight_bios() to dm_in_flight_bios() and update it to
iterate all pending_io counters.

(Coly Li: rebased for Linux v5.14 based SUSE kernel)

Fixes: d208b89401e0 ("dm: fix mempool NULL pointer race when completing IO")
Cc: stable@vger.kernel.org
Co-developed-by: Mikulas Patocka <mpatocka@redhat.com>
Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Signed-off-by: Coly Li <colyli@suse.de>

---
 drivers/md/dm-core.h |    4 ++++
 drivers/md/dm.c      |   35 +++++++++++++++++++++++------------
 2 files changed, 27 insertions(+), 12 deletions(-)

--- a/drivers/md/dm-core.h
+++ b/drivers/md/dm-core.h
@@ -119,6 +119,10 @@ struct mapped_device {
 	unsigned int nr_zones;
 	unsigned int *zwp_offset;
 #endif
+
+#ifndef __GENKSYMS__
+	unsigned long __percpu *pending_io;
+#endif
 };
 
 /*
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -503,10 +503,6 @@ static void end_io_acct(struct mapped_de
 		dm_stats_account_io(&md->stats, bio_data_dir(bio),
 				    bio->bi_iter.bi_sector, bio_sectors(bio),
 				    true, duration, stats_aux);
-
-	/* nudge anyone waiting on suspend queue */
-	if (unlikely(wq_has_sleeper(&md->wait)))
-		wake_up(&md->wait);
 }
 
 static struct dm_io *alloc_io(struct mapped_device *md, struct bio *bio)
@@ -527,6 +523,7 @@ static struct dm_io *alloc_io(struct map
 	io->magic = DM_IO_MAGIC;
 	io->status = 0;
 	atomic_set(&io->io_count, 1);
+	this_cpu_inc(*md->pending_io);
 	io->orig_bio = bio;
 	io->md = md;
 	spin_lock_init(&io->endio_lock);
@@ -822,6 +819,12 @@ void dm_io_dec_pending(struct dm_io *io,
 		stats_aux = io->stats_aux;
 		free_io(md, io);
 		end_io_acct(md, bio, start_time, &stats_aux);
+		smp_wmb();
+		this_cpu_dec(*md->pending_io);
+
+		/* nudge anyone waiting on suspend queue */
+		if (unlikely(wq_has_sleeper(&md->wait)))
+			wake_up(&md->wait);
 
 		if (io_error == BLK_STS_DM_REQUEUE)
 			return;
@@ -1691,6 +1694,11 @@ static void cleanup_mapped_device(struct
 	if (md->disk)
 		blk_cleanup_disk(md->disk);
 
+	if (md->pending_io) {
+		free_percpu(md->pending_io);
+		md->pending_io = NULL;
+	}
+
 	cleanup_srcu_struct(&md->io_barrier);
 
 	mutex_destroy(&md->suspend_lock);
@@ -1788,6 +1796,10 @@ static struct mapped_device *alloc_dev(i
 	if (!md->wq)
 		goto bad;
 
+	md->pending_io = alloc_percpu(unsigned long);
+	if (!md->pending_io)
+		goto bad;
+
 	dm_stats_init(&md->stats);
 
 	/* Populate the mapping, nobody knows we exist yet */
@@ -2193,16 +2205,13 @@ void dm_put(struct mapped_device *md)
 }
 EXPORT_SYMBOL_GPL(dm_put);
 
-static bool md_in_flight_bios(struct mapped_device *md)
+static bool dm_in_flight_bios(struct mapped_device *md)
 {
 	int cpu;
-	struct block_device *part = dm_disk(md)->part0;
-	long sum = 0;
+	unsigned long sum = 0;
 
-	for_each_possible_cpu(cpu) {
-		sum += part_stat_local_read_cpu(part, in_flight[0], cpu);
-		sum += part_stat_local_read_cpu(part, in_flight[1], cpu);
-	}
+	for_each_possible_cpu(cpu)
+		sum += *per_cpu_ptr(md->pending_io, cpu);
 
 	return sum != 0;
 }
@@ -2215,7 +2224,7 @@ static int dm_wait_for_bios_completion(s
 	while (true) {
 		prepare_to_wait(&md->wait, &wait, task_state);
 
-		if (!md_in_flight_bios(md))
+		if (!dm_in_flight_bios(md))
 			break;
 
 		if (signal_pending_state(task_state, current)) {
@@ -2227,6 +2236,8 @@ static int dm_wait_for_bios_completion(s
 	}
 	finish_wait(&md->wait, &wait);
 
+	smp_rmb();
+
 	return r;
 }