lightnvm: pblk: fail gracefully on irrec. error

Due to user writes being decoupled from media writes because of the need
of an intermediate write buffer, irrecoverable media write errors lead
to pblk stalling; user writes fill up the buffer and end up in an
infinite retry loop.

In order to let user writes fail gracefully, it is necessary for pblk to
keep track of its own internal state and prevent further writes from
being placed into the write buffer.

This patch implements a state machine to keep track of internal errors
and, in case of failure, fail further user writes in an standard way.
Depending on the type of error, pblk will do its best to persist
buffered writes (which are already acknowledged) and close down on a
graceful manner. This way, data might be recovered by re-instantiating
pblk. Such state machine paves out the way for a state-based FTL log.

Signed-off-by: Javier González <javier@cnexlabs.com>
Signed-off-by: Matias Bjørling <matias@cnexlabs.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

1 files changed, 20 insertions, 5 deletions

diff --git a/drivers/lightnvm/pblk-rb.c b/drivers/lightnvm/pblk-rb.c
index 50886878568b..665a4ccfe7f5 100644
--- a/drivers/lightnvm/pblk-rb.c
+++ b/drivers/lightnvm/pblk-rb.c
@@ -369,6 +369,9 @@ static int pblk_rb_sync_point_set(struct pblk_rb *rb, struct bio *bio,
 	/* Protect syncs */
 	smp_store_release(&rb->sync_point, sync_point);
 
+	if (!bio)
+		return 0;
+
 	spin_lock_irq(&rb->s_lock);
 	bio_list_add(&entry->w_ctx.bios, bio);
 	spin_unlock_irq(&rb->s_lock);
@@ -407,6 +410,17 @@ static int pblk_rb_may_write(struct pblk_rb *rb, unsigned int nr_entries,
 	return 1;
 }
 
+void pblk_rb_flush(struct pblk_rb *rb)
+{
+	struct pblk *pblk = container_of(rb, struct pblk, rwb);
+	unsigned int mem = READ_ONCE(rb->mem);
+
+	if (pblk_rb_sync_point_set(rb, NULL, mem))
+		return;
+
+	pblk_write_should_kick(pblk);
+}
+
 static int pblk_rb_may_write_flush(struct pblk_rb *rb, unsigned int nr_entries,
 				   unsigned int *pos, struct bio *bio,
 				   int *io_ret)
@@ -443,15 +457,16 @@ int pblk_rb_may_write_user(struct pblk_rb *rb, struct bio *bio,
 			   unsigned int nr_entries, unsigned int *pos)
 {
 	struct pblk *pblk = container_of(rb, struct pblk, rwb);
-	int flush_done;
+	int io_ret;
 
 	spin_lock(&rb->w_lock);
-	if (!pblk_rl_user_may_insert(&pblk->rl, nr_entries)) {
+	io_ret = pblk_rl_user_may_insert(&pblk->rl, nr_entries);
+	if (io_ret) {
 		spin_unlock(&rb->w_lock);
-		return NVM_IO_REQUEUE;
+		return io_ret;
 	}
 
-	if (!pblk_rb_may_write_flush(rb, nr_entries, pos, bio, &flush_done)) {
+	if (!pblk_rb_may_write_flush(rb, nr_entries, pos, bio, &io_ret)) {
 		spin_unlock(&rb->w_lock);
 		return NVM_IO_REQUEUE;
 	}
@@ -459,7 +474,7 @@ int pblk_rb_may_write_user(struct pblk_rb *rb, struct bio *bio,
 	pblk_rl_user_in(&pblk->rl, nr_entries);
 	spin_unlock(&rb->w_lock);
 
-	return flush_done;
+	return io_ret;
 }
 
 /*