From: Nicholas Bellinger <nab@xxxxxxxxxxxxxxx> This patch makes the failure case in srpt_map_sg_to_ib_sge() for ib_dma_map_sg() return -EAGAIN so that this failure will trigger target-core QUEUE_FULL logic from srpt_xfer_data() for srpt_write_pending() WRITEs and srpt_queue_response() for READs. Reported-by: Bart Van Assche <bvanassche@xxxxxxx> Cc: Bart Van Assche <bvanassche@xxxxxxx> Cc: Christoph Hellwig <hch@xxxxxx> Cc: Roland Dreier <roland@xxxxxxxxxxxxxxx> Signed-off-by: Nicholas A. Bellinger <nab@xxxxxxxxxxxxxxx> --- drivers/infiniband/ulp/srpt/ib_srpt.c | 2 +- 1 files changed, 1 insertions(+), 1 deletions(-) diff --git a/drivers/infiniband/ulp/srpt/ib_srpt.c b/drivers/infiniband/ulp/srpt/ib_srpt.c index f7174b3..7892efc 100644 --- a/drivers/infiniband/ulp/srpt/ib_srpt.c +++ b/drivers/infiniband/ulp/srpt/ib_srpt.c @@ -1112,7 +1112,7 @@ static int srpt_map_sg_to_ib_sge(struct srpt_rdma_ch *ch, count = ib_dma_map_sg(ch->sport->sdev->device, sg, sg_cnt, opposite_dma_dir(dir)); if (unlikely(!count)) - return -EBUSY; + return -EAGAIN; ioctx->mapped_sg_count = count; -- 1.7.2.5 -- To unsubscribe from this list: send the line "unsubscribe linux-scsi" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
