dm: interlock pending dm_io and dm_wait_for_bios_completion

commit 9f6dc633761006f974701d4c88da71ab68670749 upstream.

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.

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: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

diff --git a/drivers/md/dm-core.h b/drivers/md/dm-core.h
index 55dccdfbcb22ee27e4098e6aeb5cbd07807c9614..5a7d270b32c01f7edd11b1db07dbf788a64cc5d9 100644 (file)
--- a/drivers/md/dm-core.h
+++ b/drivers/md/dm-core.h
@@ -65,6 +65,8 @@ struct mapped_device {
        struct gendisk *disk;
        struct dax_device *dax_dev;
 
+       unsigned long __percpu *pending_io;
+
        /*
         * A list of ios that arrived while we were suspended.
         */

diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 0da6b9aea201f343fcd6caf8a49b84353d83073d..3b927c26d62aac60925d92b670356a9bcb537769 100644 (file)
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -507,10 +507,6 @@ static void end_io_acct(struct mapped_device *md, struct bio *bio,
                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)
@@ -531,6 +527,7 @@ static struct dm_io *alloc_io(struct mapped_device *md, struct bio *bio)
        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);
@@ -828,6 +825,12 @@ void dm_io_dec_pending(struct dm_io *io, blk_status_t error)
                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;
@@ -1697,6 +1700,11 @@ static void cleanup_mapped_device(struct mapped_device *md)
                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);
@@ -1794,6 +1802,10 @@ static struct mapped_device *alloc_dev(int minor)
        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 */
@@ -2209,16 +2221,13 @@ 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;
 }
@@ -2231,7 +2240,7 @@ static int dm_wait_for_bios_completion(struct mapped_device *md, unsigned int ta
        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)) {
@@ -2243,6 +2252,8 @@ static int dm_wait_for_bios_completion(struct mapped_device *md, unsigned int ta
        }
        finish_wait(&md->wait, &wait);
 
+       smp_rmb();
+
        return r;
 }