Merge branch 'for-linus' of git://git.kernel.dk/linux-2.6-block

* 'for-linus' of git://git.kernel.dk/linux-2.6-block:
  block: fix blkdev_issue_flush() not detecting and passing EOPNOTSUPP back
  block: fix shadowed variable warning in blk-map.c
  block: remove extern on function definition
  cciss: remove READ_AHEAD define and use block layer defaults
  make cdrom.c:check_for_audio_disc() static
  block/genhd.c: proper externs
  unexport blk_rq_map_user_iov
  unexport blk_{get,put}_queue
  block/genhd.c: cleanups
  proper prototype for blk_dev_init()
  block/blk-tag.c should #include "blk.h"
  Fix DMA access of block device in 64-bit kernel on some non-x86 systems with 4GB or upper 4GB memory
  block: separate out padding from alignment
  block: restore the meaning of rq->data_len to the true data length
  resubmit: cciss: procfs updates to display info about many
  splice: only return -EAGAIN if there's hope of more data
  block: fix kernel-docbook parameters and files

10 files changed, 61 insertions, 32 deletions

diff --git a/block/blk-barrier.c b/block/blk-barrier.c
index 6901eedeffc..55c5f1fc4f1 100644
--- a/block/blk-barrier.c
+++ b/block/blk-barrier.c
@@ -259,8 +259,11 @@ int blk_do_ordered(struct request_queue *q, struct request **rqp)
 
 static void bio_end_empty_barrier(struct bio *bio, int err)
 {
-	if (err)
+	if (err) {
+		if (err == -EOPNOTSUPP)
+			set_bit(BIO_EOPNOTSUPP, &bio->bi_flags);
 		clear_bit(BIO_UPTODATE, &bio->bi_flags);
+	}
 
 	complete(bio->bi_private);
 }
@@ -309,7 +312,9 @@ int blkdev_issue_flush(struct block_device *bdev, sector_t *error_sector)
 		*error_sector = bio->bi_sector;
 
 	ret = 0;
-	if (!bio_flagged(bio, BIO_UPTODATE))
+	if (bio_flagged(bio, BIO_EOPNOTSUPP))
+		ret = -EOPNOTSUPP;
+	else if (!bio_flagged(bio, BIO_UPTODATE))
 		ret = -EIO;
 
 	bio_put(bio);
diff --git a/block/blk-core.c b/block/blk-core.c
index 775c8516abf..2a438a93f72 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -127,7 +127,6 @@ 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;
@@ -135,6 +134,7 @@ void rq_init(struct request_queue *q, struct request *rq)
 	rq->cmd_len = 0;
 	memset(rq->cmd, 0, sizeof(rq->cmd));
 	rq->data_len = 0;
+	rq->extra_len = 0;
 	rq->sense_len = 0;
 	rq->data = NULL;
 	rq->sense = NULL;
@@ -424,7 +424,6 @@ void blk_put_queue(struct request_queue *q)
 {
 	kobject_put(&q->kobj);
 }
-EXPORT_SYMBOL(blk_put_queue);
 
 void blk_cleanup_queue(struct request_queue *q)
 {
@@ -592,7 +591,6 @@ int blk_get_queue(struct request_queue *q)
 
 	return 1;
 }
-EXPORT_SYMBOL(blk_get_queue);
 
 static inline void blk_free_request(struct request_queue *q, struct request *rq)
 {
@@ -1768,6 +1766,7 @@ static inline void __end_request(struct request *rq, int uptodate,
 
 /**
  * blk_rq_bytes - Returns bytes left to complete in the entire request
+ * @rq: the request being processed
  **/
 unsigned int blk_rq_bytes(struct request *rq)
 {
@@ -1780,6 +1779,7 @@ EXPORT_SYMBOL_GPL(blk_rq_bytes);
 
 /**
  * blk_rq_cur_bytes - Returns bytes left to complete in the current segment
+ * @rq: the request being processed
  **/
 unsigned int blk_rq_cur_bytes(struct request *rq)
 {
@@ -2016,7 +2016,6 @@ 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 09f7fd0bcb7..c07d9c8317f 100644
--- a/block/blk-map.c
+++ b/block/blk-map.c
@@ -19,7 +19,6 @@ 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;
@@ -44,6 +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;
 
@@ -54,8 +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);
@@ -142,20 +142,22 @@ 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;
-		struct bio *bio = rq->biotail;
+	if (len & q->dma_pad_mask) {
+		unsigned int pad_len = (q->dma_pad_mask & ~len) + 1;
+		struct bio *tail = rq->biotail;
 
-		bio->bi_io_vec[bio->bi_vcnt - 1].bv_len += pad_len;
-		bio->bi_size += pad_len;
-		rq->data_len += pad_len;
+		tail->bi_io_vec[tail->bi_vcnt - 1].bv_len += pad_len;
+		tail->bi_size += pad_len;
+
+		rq->extra_len += pad_len;
 	}
 
 	rq->buffer = rq->data = NULL;
@@ -215,7 +217,6 @@ int blk_rq_map_user_iov(struct request_queue *q, struct request *rq,
 	rq->buffer = rq->data = NULL;
 	return 0;
 }
-EXPORT_SYMBOL(blk_rq_map_user_iov);
 
 /**
  * blk_rq_unmap_user - unmap a request with user data
diff --git a/block/blk-merge.c b/block/blk-merge.c
index 7506c4fe026..0f58616bcd7 100644
--- a/block/blk-merge.c
+++ b/block/blk-merge.c
@@ -231,7 +231,7 @@ new_segment:
 			    ((unsigned long)q->dma_drain_buffer) &
 			    (PAGE_SIZE - 1));
 		nsegs++;
-		rq->data_len += q->dma_drain_size;
+		rq->extra_len += q->dma_drain_size;
 	}
 
 	if (sg)
diff --git a/block/blk-settings.c b/block/blk-settings.c
index 9a8ffdd0ce3..1344a0ea5cc 100644
--- a/block/blk-settings.c
+++ b/block/blk-settings.c
@@ -140,7 +140,7 @@ void blk_queue_bounce_limit(struct request_queue *q, u64 dma_addr)
 	/* Assume anything <= 4GB can be handled by IOMMU.
 	   Actually some IOMMUs can handle everything, but I don't
 	   know of a way to test this here. */
-	if (b_pfn < (min_t(u64, 0xffffffff, BLK_BOUNCE_HIGH) >> PAGE_SHIFT))
+	if (b_pfn <= (min_t(u64, 0xffffffff, BLK_BOUNCE_HIGH) >> PAGE_SHIFT))
 		dma = 1;
 	q->bounce_pfn = max_low_pfn;
 #else
@@ -293,8 +293,24 @@ void blk_queue_stack_limits(struct request_queue *t, struct request_queue *b)
 EXPORT_SYMBOL(blk_queue_stack_limits);
 
 /**
- * blk_queue_dma_drain - Set up a drain buffer for excess dma.
+ * 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
  * @buf:	physically contiguous buffer
@@ -316,7 +332,7 @@ EXPORT_SYMBOL(blk_queue_stack_limits);
  * device can support otherwise there won't be room for the drain
  * buffer.
  */
-extern int blk_queue_dma_drain(struct request_queue *q,
+int blk_queue_dma_drain(struct request_queue *q,
 			       dma_drain_needed_fn *dma_drain_needed,
 			       void *buf, unsigned int size)
 {
diff --git a/block/blk-tag.c b/block/blk-tag.c
index a8c37d4bbb3..4780a46ce23 100644
--- a/block/blk-tag.c
+++ b/block/blk-tag.c
@@ -6,6 +6,8 @@
 #include <linux/bio.h>
 #include <linux/blkdev.h>
 
+#include "blk.h"
+
 /**
  * blk_queue_find_tag - find a request by its tag and queue
  * @q:	 The request queue for the device
diff --git a/block/blk.h b/block/blk.h
index ec898dd0c65..ec9120fb789 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -32,6 +32,8 @@ void blk_recalc_rq_sectors(struct request *rq, int nsect);
 
 void blk_queue_congestion_threshold(struct request_queue *q);
 
+int blk_dev_init(void);
+
 /*
  * Return the threshold (number of used requests) at which the queue is
  * considered to be congested.  It include a little hysteresis to keep the
diff --git a/block/bsg.c b/block/bsg.c
index 7f3c09549e4..8917c5174dc 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->raw_data_len;
-		hdr->din_resid = rq->next_rq->raw_data_len;
+		hdr->dout_resid = rq->data_len;
+		hdr->din_resid = rq->next_rq->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->raw_data_len;
+		hdr->din_resid = rq->data_len;
 	else
-		hdr->dout_resid = rq->raw_data_len;
+		hdr->dout_resid = rq->data_len;
 
 	/*
 	 * If the request generated a negative error number, return it
diff --git a/block/genhd.c b/block/genhd.c
index 53f2238e69c..c44527d16c5 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -17,11 +17,15 @@
 #include <linux/buffer_head.h>
 #include <linux/mutex.h>
 
+#include "blk.h"
+
 static DEFINE_MUTEX(block_class_lock);
 #ifndef CONFIG_SYSFS_DEPRECATED
 struct kobject *block_depr;
 #endif
 
+static struct device_type disk_type;
+
 /*
  * Can be deleted altogether. Later.
  *
@@ -346,8 +350,6 @@ const struct seq_operations partitions_op = {
 #endif
 
 
-extern int blk_dev_init(void);
-
 static struct kobject *base_probe(dev_t devt, int *part, void *data)
 {
 	if (request_module("block-major-%d-%d", MAJOR(devt), MINOR(devt)) > 0)
@@ -502,7 +504,7 @@ struct class block_class = {
 	.name		= "block",
 };
 
-struct device_type disk_type = {
+static struct device_type disk_type = {
 	.name		= "disk",
 	.groups		= disk_attr_groups,
 	.release	= disk_release,
@@ -632,12 +634,14 @@ static void media_change_notify_thread(struct work_struct *work)
 	put_device(gd->driverfs_dev);
 }
 
+#if 0
 void genhd_media_change_notify(struct gendisk *disk)
 {
 	get_device(disk->driverfs_dev);
 	schedule_work(&disk->async_notify);
 }
 EXPORT_SYMBOL_GPL(genhd_media_change_notify);
+#endif  /*  0  */
 
 dev_t blk_lookup_devt(const char *name)
 {
diff --git a/block/scsi_ioctl.c b/block/scsi_ioctl.c
index e993cac4911..a2c3a936ebf 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->raw_data_len;
+	hdr->resid = rq->data_len;
 	hdr->sb_len_wr = 0;
 
 	if (rq->sense_len && hdr->sbp) {
@@ -528,8 +528,8 @@ 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->extra_len = 0;
 	rq->timeout = BLK_DEFAULT_SG_TIMEOUT;
 	memset(rq->cmd, 0, sizeof(rq->cmd));
 	rq->cmd[0] = cmd;