block: separate out padding from alignment

Block layer alignment was used for two different purposes - memory
alignment and padding.  This causes problems in lower layers because
drivers which only require memory alignment ends up with adjusted
rq->data_len.  Separate out padding such that padding occurs iff
driver explicitly requests it.

Tomo: restorethe code to update bio in blk_rq_map_user
      introduced by the commit 40b01b9bbdf51ae543a04744283bf2d56c4a6afa
      according to padding alignment.

Signed-off-by: Tejun Heo <htejun@gmail.com>
Signed-off-by: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp>
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>

4 files changed, 34 insertions, 8 deletions

diff --git a/block/blk-map.c b/block/blk-map.c
index f5598322954d..4e17dfd0035d 100644
--- a/block/blk-map.c
+++ b/block/blk-map.c
@@ -43,6 +43,7 @@ static int __blk_rq_map_user(struct request_queue *q, struct request *rq,
                              void __user *ubuf, unsigned int len)
 {
         unsigned long uaddr;
+        unsigned int alignment;
         struct bio *bio, *orig_bio;
         int reading, ret;
 
@@ -53,8 +54,8 @@ static int __blk_rq_map_user(struct request_queue *q, struct request *rq,
          * direct dma. else, set up kernel bounce buffers
          */
         uaddr = (unsigned long) ubuf;
-        if (!(uaddr & queue_dma_alignment(q)) &&
-            !(len & queue_dma_alignment(q)))
+        alignment = queue_dma_alignment(q) | q->dma_pad_mask;
+        if (!(uaddr & alignment) && !(len & alignment))
                 bio = bio_map_user(q, NULL, uaddr, len, reading);
         else
                 bio = bio_copy_user(q, uaddr, len, reading);
@@ -141,15 +142,20 @@ int blk_rq_map_user(struct request_queue *q, struct request *rq,
 
         /*
          * __blk_rq_map_user() copies the buffers if starting address
-         * or length isn't aligned.  As the copied buffer is always
-         * page aligned, we know that there's enough room for padding.
-         * Extend the last bio and update rq->data_len accordingly.
+         * or length isn't aligned to dma_pad_mask.  As the copied
+         * buffer is always page aligned, we know that there's enough
+         * room for padding.  Extend the last bio and update
+         * rq->data_len accordingly.
          *
          * On unmap, bio_uncopy_user() will use unmodified
          * bio_map_data pointed to by bio->bi_private.
          */
-        if (len & queue_dma_alignment(q)) {
-                unsigned int pad_len = (queue_dma_alignment(q) & ~len) + 1;
+        if (len & q->dma_pad_mask) {
+                unsigned int pad_len = (q->dma_pad_mask & ~len) + 1;
+                struct bio *bio = rq->biotail;
+
+                bio->bi_io_vec[bio->bi_vcnt - 1].bv_len += pad_len;
+                bio->bi_size += pad_len;
 
                 rq->extra_len += pad_len;
         }
diff --git a/block/blk-settings.c b/block/blk-settings.c
index da923fed1f2c..a9f37f530b15 100644
--- a/block/blk-settings.c
+++ b/block/blk-settings.c
@@ -293,6 +293,23 @@ void blk_queue_stack_limits(struct request_queue *t, struct request_queue *b)
 EXPORT_SYMBOL(blk_queue_stack_limits);
 
 /**
+ * blk_queue_dma_pad - set pad mask
+ * @q:     the request queue for the device
+ * @mask:  pad mask
+ *
+ * Set pad mask.  Direct IO requests are padded to the mask specified.
+ *
+ * Appending pad buffer to a request modifies ->data_len such that it
+ * includes the pad buffer.  The original requested data length can be
+ * obtained using blk_rq_raw_data_len().
+ **/
+void blk_queue_dma_pad(struct request_queue *q, unsigned int mask)
+{
+        q->dma_pad_mask = mask;
+}
+EXPORT_SYMBOL(blk_queue_dma_pad);
+
+/**
  * blk_queue_dma_drain - Set up a drain buffer for excess dma.
  * @q:  the request queue for the device
  * @dma_drain_needed: fn which returns non-zero if drain is necessary
diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c
index fe47922dd69e..8f0e8f2bc628 100644
--- a/drivers/ata/libata-scsi.c
+++ b/drivers/ata/libata-scsi.c
@@ -862,9 +862,10 @@ static int ata_scsi_dev_config(struct scsi_device *sdev,
                 struct request_queue *q = sdev->request_queue;
                 void *buf;
 
-                /* set the min alignment */
+                /* set the min alignment and padding */
                 blk_queue_update_dma_alignment(sdev->request_queue,
                                                ATA_DMA_PAD_SZ - 1);
+                blk_queue_dma_pad(sdev->request_queue, ATA_DMA_PAD_SZ - 1);
 
                 /* configure draining */
                 buf = kmalloc(ATAPI_MAX_DRAIN, q->bounce_gfp | GFP_KERNEL);
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index b72526c13ca0..6f79d40dd3c0 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -362,6 +362,7 @@ struct request_queue
         unsigned long           seg_boundary_mask;
         void                    *dma_drain_buffer;
         unsigned int            dma_drain_size;
+        unsigned int            dma_pad_mask;
         unsigned int            dma_alignment;
 
         struct blk_queue_tag    *queue_tags;
@@ -701,6 +702,7 @@ extern void blk_queue_max_hw_segments(struct request_queue *, unsigned short);
 extern void blk_queue_max_segment_size(struct request_queue *, unsigned int);
 extern void blk_queue_hardsect_size(struct request_queue *, unsigned short);
 extern void blk_queue_stack_limits(struct request_queue *t, struct request_queue *b);
+extern void blk_queue_dma_pad(struct request_queue *, unsigned int);
 extern int blk_queue_dma_drain(struct request_queue *q,
                                dma_drain_needed_fn *dma_drain_needed,
                                void *buf, unsigned int size);