UBUNTU: SAUCE: (namespace) fuse: Support fuse filesystems outside of init_user_ns

[mirror_ubuntu-zesty-kernel.git] / block / blk-flush.c

diff --git a/block/blk-flush.c b/block/blk-flush.c
index d308def812db9b3794fc10e07da9a303dd31eb70..20b7c7a02f1cbdfe5a63c5918d3abd356bd4265b 100644 (file)
--- a/block/blk-flush.c
+++ b/block/blk-flush.c
@@ -56,7 +56,7 @@
  * Once while executing DATA and again after the whole sequence is
  * complete.  The first completion updates the contained bio but doesn't
  * finish it so that the bio submitter is notified only after the whole
- * sequence is complete.  This is implemented by testing REQ_FLUSH_SEQ in
+ * sequence is complete.  This is implemented by testing RQF_FLUSH_SEQ in
  * req_bio_endio().
  *
  * The above peculiarity requires that each FLUSH/FUA request has only one
@@ -127,17 +127,14 @@ static void blk_flush_restore_request(struct request *rq)
        rq->bio = rq->biotail;
 
        /* make @rq a normal request */
-       rq->cmd_flags &= ~REQ_FLUSH_SEQ;
+       rq->rq_flags &= ~RQF_FLUSH_SEQ;
        rq->end_io = rq->flush.saved_end_io;
 }
 
 static bool blk_flush_queue_rq(struct request *rq, bool add_front)
 {
        if (rq->q->mq_ops) {
-               struct request_queue *q = rq->q;
-
-               blk_mq_add_to_requeue_list(rq, add_front);
-               blk_mq_kick_requeue_list(q);
+               blk_mq_add_to_requeue_list(rq, add_front, true);
                return false;
        } else {
                if (add_front)
@@ -232,7 +229,7 @@ static void flush_end_io(struct request *flush_rq, int error)
 
                /* release the tag's ownership to the req cloned from */
                spin_lock_irqsave(&fq->mq_flush_lock, flags);
-               hctx = q->mq_ops->map_queue(q, flush_rq->mq_ctx->cpu);
+               hctx = blk_mq_map_queue(q, flush_rq->mq_ctx->cpu);
                blk_mq_tag_set_rq(hctx, flush_rq->tag, fq->orig_rq);
                flush_rq->tag = -1;
        }
@@ -325,12 +322,13 @@ static bool blk_kick_flush(struct request_queue *q, struct blk_flush_queue *fq)
                flush_rq->tag = first_rq->tag;
                fq->orig_rq = first_rq;
 
-               hctx = q->mq_ops->map_queue(q, first_rq->mq_ctx->cpu);
+               hctx = blk_mq_map_queue(q, first_rq->mq_ctx->cpu);
                blk_mq_tag_set_rq(hctx, first_rq->tag, flush_rq);
        }
 
        flush_rq->cmd_type = REQ_TYPE_FS;
-       req_set_op_attrs(flush_rq, REQ_OP_FLUSH, WRITE_FLUSH | REQ_FLUSH_SEQ);
+       flush_rq->cmd_flags = REQ_OP_FLUSH | REQ_PREFLUSH;
+       flush_rq->rq_flags |= RQF_FLUSH_SEQ;
        flush_rq->rq_disk = first_rq->rq_disk;
        flush_rq->end_io = flush_end_io;
 
@@ -342,6 +340,34 @@ static void flush_data_end_io(struct request *rq, int error)
        struct request_queue *q = rq->q;
        struct blk_flush_queue *fq = blk_get_flush_queue(q, NULL);
 
+       /*
+        * Updating q->in_flight[] here for making this tag usable
+        * early. Because in blk_queue_start_tag(),
+        * q->in_flight[BLK_RW_ASYNC] is used to limit async I/O and
+        * reserve tags for sync I/O.
+        *
+        * More importantly this way can avoid the following I/O
+        * deadlock:
+        *
+        * - suppose there are 40 fua requests comming to flush queue
+        *   and queue depth is 31
+        * - 30 rqs are scheduled then blk_queue_start_tag() can't alloc
+        *   tag for async I/O any more
+        * - all the 30 rqs are completed before FLUSH_PENDING_TIMEOUT
+        *   and flush_data_end_io() is called
+        * - the other rqs still can't go ahead if not updating
+        *   q->in_flight[BLK_RW_ASYNC] here, meantime these rqs
+        *   are held in flush data queue and make no progress of
+        *   handling post flush rq
+        * - only after the post flush rq is handled, all these rqs
+        *   can be completed
+        */
+
+       elv_completed_request(q, rq);
+
+       /* for avoiding double accounting */
+       rq->rq_flags &= ~RQF_STARTED;
+
        /*
         * After populating an empty queue, kick it to avoid stall.  Read
         * the comment in flush_end_io().
@@ -358,7 +384,7 @@ static void mq_flush_data_end_io(struct request *rq, int error)
        unsigned long flags;
        struct blk_flush_queue *fq = blk_get_flush_queue(q, ctx);
 
-       hctx = q->mq_ops->map_queue(q, ctx->cpu);
+       hctx = blk_mq_map_queue(q, ctx->cpu);
 
        /*
         * After populating an empty queue, kick it to avoid stall.  Read
@@ -397,6 +423,13 @@ void blk_insert_flush(struct request *rq)
        if (!(fflags & (1UL << QUEUE_FLAG_FUA)))
                rq->cmd_flags &= ~REQ_FUA;
 
+       /*
+        * REQ_PREFLUSH|REQ_FUA implies REQ_SYNC, so if we clear any
+        * of those flags, we have to set REQ_SYNC to avoid skewing
+        * the request accounting.
+        */
+       rq->cmd_flags |= REQ_SYNC;
+
        /*
         * An empty flush handed down from a stacking driver may
         * translate into nothing if the underlying device does not
@@ -421,7 +454,7 @@ void blk_insert_flush(struct request *rq)
        if ((policy & REQ_FSEQ_DATA) &&
            !(policy & (REQ_FSEQ_PREFLUSH | REQ_FSEQ_POSTFLUSH))) {
                if (q->mq_ops) {
-                       blk_mq_insert_request(rq, false, false, true);
+                       blk_mq_insert_request(rq, false, true, false);
                } else
                        list_add_tail(&rq->queuelist, &q->queue_head);
                return;
@@ -433,7 +466,7 @@ void blk_insert_flush(struct request *rq)
         */
        memset(&rq->flush, 0, sizeof(rq->flush));
        INIT_LIST_HEAD(&rq->flush.list);
-       rq->cmd_flags |= REQ_FLUSH_SEQ;
+       rq->rq_flags |= RQF_FLUSH_SEQ;
        rq->flush.saved_end_io = rq->end_io; /* Usually NULL */
        if (q->mq_ops) {
                rq->end_io = mq_flush_data_end_io;
@@ -485,7 +518,7 @@ int blkdev_issue_flush(struct block_device *bdev, gfp_t gfp_mask,
 
        bio = bio_alloc(gfp_mask, 0);
        bio->bi_bdev = bdev;
-       bio_set_op_attrs(bio, REQ_OP_WRITE, WRITE_FLUSH);
+       bio->bi_opf = REQ_OP_WRITE | REQ_PREFLUSH;
 
        ret = submit_bio_wait(bio);