On Mon, Apr 29, 2019 at 08:05:30AM +0200, Hannes Reinecke wrote:
> On 4/28/19 10:14 AM, Ming Lei wrote:
> > Split blk_mq_alloc_and_init_hctx into two parts, and one is
> > blk_mq_alloc_hctx() for allocating all hctx resources, another
> > is blk_mq_init_hctx() for initializing hctx, which serves as
> > counter-part of blk_mq_exit_hctx().
> >
> > Cc: Dongli Zhang <dongli.zhang@xxxxxxxxxx>
> > Cc: James Smart <james.smart@xxxxxxxxxxxx>
> > Cc: Bart Van Assche <bart.vanassche@xxxxxxx>
> > Cc: linux-scsi@xxxxxxxxxxxxxxx,
> > Cc: Martin K . Petersen <martin.petersen@xxxxxxxxxx>,
> > Cc: Christoph Hellwig <hch@xxxxxx>,
> > Cc: James E . J . Bottomley <jejb@xxxxxxxxxxxxxxxxxx>,
> > Reviewed-by: Hannes Reinecke <hare@xxxxxxxx>
> > Tested-by: James Smart <james.smart@xxxxxxxxxxxx>
> > Signed-off-by: Ming Lei <ming.lei@xxxxxxxxxx>
> > ---
> > block/blk-mq.c | 138 ++++++++++++++++++++++++++++++++-------------------------
> > 1 file changed, 77 insertions(+), 61 deletions(-)
> >
> > diff --git a/block/blk-mq.c b/block/blk-mq.c
> > index d98cb9614dfa..44ecca6b0cac 100644
> > --- a/block/blk-mq.c
> > +++ b/block/blk-mq.c
> > @@ -2284,15 +2284,70 @@ static void blk_mq_exit_hw_queues(struct request_queue *q,
> > }
> > }
> > +static int blk_mq_hw_ctx_size(struct blk_mq_tag_set *tag_set)
> > +{
> > + int hw_ctx_size = sizeof(struct blk_mq_hw_ctx);
> > +
> > + BUILD_BUG_ON(ALIGN(offsetof(struct blk_mq_hw_ctx, srcu),
> > + __alignof__(struct blk_mq_hw_ctx)) !=
> > + sizeof(struct blk_mq_hw_ctx));
> > +
> > + if (tag_set->flags & BLK_MQ_F_BLOCKING)
> > + hw_ctx_size += sizeof(struct srcu_struct);
> > +
> > + return hw_ctx_size;
> > +}
> > +
> > static int blk_mq_init_hctx(struct request_queue *q,
> > struct blk_mq_tag_set *set,
> > struct blk_mq_hw_ctx *hctx, unsigned hctx_idx)
> > {
> > - int node;
> > + hctx->queue_num = hctx_idx;
> > - node = hctx->numa_node;
> > + cpuhp_state_add_instance_nocalls(CPUHP_BLK_MQ_DEAD, &hctx->cpuhp_dead);
> > +
> > + hctx->tags = set->tags[hctx_idx];
> > +
> > + if (set->ops->init_hctx &&
> > + set->ops->init_hctx(hctx, set->driver_data, hctx_idx))
> > + goto unregister_cpu_notifier;
> > +
> > + if (blk_mq_init_request(set, hctx->fq->flush_rq, hctx_idx,
> > + hctx->numa_node))
> > + goto exit_hctx;
> > + return 0;
> > +
> > + exit_hctx:
> > + if (set->ops->exit_hctx)
> > + set->ops->exit_hctx(hctx, hctx_idx);
> > + unregister_cpu_notifier:
> > + blk_mq_remove_cpuhp(hctx);
> > + return -1;
> > +}
> > +
> > +static struct blk_mq_hw_ctx *
> > +blk_mq_alloc_hctx(struct request_queue *q,
> > + struct blk_mq_tag_set *set,
> > + unsigned hctx_idx, int node)
> > +{
> > + struct blk_mq_hw_ctx *hctx;
> > +
> > + hctx = kzalloc_node(blk_mq_hw_ctx_size(set),
> > + GFP_NOIO | __GFP_NOWARN | __GFP_NORETRY,
> > + node);
> > + if (!hctx)
> > + goto fail_alloc_hctx;
> > +
> > + if (!zalloc_cpumask_var_node(&hctx->cpumask,
> > + GFP_NOIO | __GFP_NOWARN | __GFP_NORETRY,
> > + node))
> > + goto free_hctx;
> > +
> > + atomic_set(&hctx->nr_active, 0);
> > + hctx->numa_node = node;
> > if (node == NUMA_NO_NODE)
> > - node = hctx->numa_node = set->numa_node;
> > + hctx->numa_node = set->numa_node;
> > + node = hctx->numa_node;
> > INIT_DELAYED_WORK(&hctx->run_work, blk_mq_run_work_fn);
> > spin_lock_init(&hctx->lock);
> The 'hctx_idx' argument is now unused, and should be removed from the
> function definition.
OK, will do it in V9.
Thanks,
Ming
