block: add request->raw_data_len

With padding and draining moved into it, block layer now may extend
requests as directed by queue parameters, so now a request has two
sizes - the original request size and the extended size which matches
the size of area pointed to by bios and later by sgs.  The latter size
is what lower layers are primarily interested in when allocating,
filling up DMA tables and setting up the controller.

Both padding and draining extend the data area to accomodate
controller characteristics.  As any controller which speaks SCSI can
handle underflows, feeding larger data area is safe.

So, this patch makes the primary data length field, request->data_len,
indicate the size of full data area and add a separate length field,
request->raw_data_len, for the unmodified request size.  The latter is
used to report to higher layer (userland) and where the original
request size should be fed to the controller or device.

Signed-off-by: Tejun Heo <htejun@gmail.com>
Cc: James Bottomley <James.Bottomley@HansenPartnership.com>
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>

5 files changed, 11 insertions, 5 deletions

diff --git a/block/blk-core.c b/block/blk-core.c
index c013ca2..775c851 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -127,6 +127,7 @@ void rq_init(struct request_queue *q, struct request *rq)
 	rq->nr_hw_segments = 0;
 	rq->ioprio = 0;
 	rq->special = NULL;
+	rq->raw_data_len = 0;
 	rq->buffer = NULL;
 	rq->tag = -1;
 	rq->errors = 0;
@@ -2015,6 +2016,7 @@ void blk_rq_bio_prep(struct request_queue *q, struct request *rq,
 	rq->hard_cur_sectors = rq->current_nr_sectors;
 	rq->hard_nr_sectors = rq->nr_sectors = bio_sectors(bio);
 	rq->buffer = bio_data(bio);
+	rq->raw_data_len = bio->bi_size;
 	rq->data_len = bio->bi_size;
 
 	rq->bio = rq->biotail = bio;
diff --git a/block/blk-map.c b/block/blk-map.c
index a7cf63c..09f7fd0 100644
--- a/block/blk-map.c
+++ b/block/blk-map.c
@@ -19,6 +19,7 @@ int blk_rq_append_bio(struct request_queue *q, struct request *rq,
 		rq->biotail->bi_next = bio;
 		rq->biotail = bio;
 
+		rq->raw_data_len += bio->bi_size;
 		rq->data_len += bio->bi_size;
 	}
 	return 0;
@@ -154,6 +155,7 @@ int blk_rq_map_user(struct request_queue *q, struct request *rq,
 
 		bio->bi_io_vec[bio->bi_vcnt - 1].bv_len += pad_len;
 		bio->bi_size += pad_len;
+		rq->data_len += pad_len;
 	}
 
 	rq->buffer = rq->data = NULL;
diff --git a/block/blk-merge.c b/block/blk-merge.c
index d3b84bb..39f2e07 100644
--- a/block/blk-merge.c
+++ b/block/blk-merge.c
@@ -228,6 +228,7 @@ new_segment:
 			    ((unsigned long)q->dma_drain_buffer) &
 			    (PAGE_SIZE - 1));
 		nsegs++;
+		rq->data_len += q->dma_drain_size;
 	}
 
 	if (sg)
diff --git a/block/bsg.c b/block/bsg.c
index 8917c51..7f3c095 100644
--- a/block/bsg.c
+++ b/block/bsg.c
@@ -437,14 +437,14 @@ static int blk_complete_sgv4_hdr_rq(struct request *rq, struct sg_io_v4 *hdr,
 	}
 
 	if (rq->next_rq) {
-		hdr->dout_resid = rq->data_len;
-		hdr->din_resid = rq->next_rq->data_len;
+		hdr->dout_resid = rq->raw_data_len;
+		hdr->din_resid = rq->next_rq->raw_data_len;
 		blk_rq_unmap_user(bidi_bio);
 		blk_put_request(rq->next_rq);
 	} else if (rq_data_dir(rq) == READ)
-		hdr->din_resid = rq->data_len;
+		hdr->din_resid = rq->raw_data_len;
 	else
-		hdr->dout_resid = rq->data_len;
+		hdr->dout_resid = rq->raw_data_len;
 
 	/*
 	 * If the request generated a negative error number, return it
diff --git a/block/scsi_ioctl.c b/block/scsi_ioctl.c
index 9675b34..e993cac 100644
--- a/block/scsi_ioctl.c
+++ b/block/scsi_ioctl.c
@@ -266,7 +266,7 @@ static int blk_complete_sghdr_rq(struct request *rq, struct sg_io_hdr *hdr,
 	hdr->info = 0;
 	if (hdr->masked_status || hdr->host_status || hdr->driver_status)
 		hdr->info |= SG_INFO_CHECK;
-	hdr->resid = rq->data_len;
+	hdr->resid = rq->raw_data_len;
 	hdr->sb_len_wr = 0;
 
 	if (rq->sense_len && hdr->sbp) {
@@ -528,6 +528,7 @@ static int __blk_send_generic(struct request_queue *q, struct gendisk *bd_disk,
 	rq = blk_get_request(q, WRITE, __GFP_WAIT);
 	rq->cmd_type = REQ_TYPE_BLOCK_PC;
 	rq->data = NULL;
+	rq->raw_data_len = 0;
 	rq->data_len = 0;
 	rq->timeout = BLK_DEFAULT_SG_TIMEOUT;
 	memset(rq->cmd, 0, sizeof(rq->cmd));