[PATCH] bio walking code

Add bio traversal functionality. This is a prereq for doing ide
multiwrites safely and sanely. Patch was originally done by Suparna,
Bartlomiej picked it up and changed the design somewhat. From Bart:

Main idea is now reversed - instead of introducing rq->hard_bio as
pointer for bio to be completed and using rq->bio as pointer for bio
to be submitted, rq->cbio is introduced for submissions and rq->bio
is used for completions

This minimizes changes to block layer and assures that all existing
block users are not affected by this patch.

drivers/block/ll_rw_blk.c

@@ -1616,7 +1616,8 @@ static int __make_request(request_queue_t *q, struct bio *bio)
 
 	sector = bio->bi_sector;
 	nr_sectors = bio_sectors(bio);
-	cur_nr_sectors = bio_iovec(bio)->bv_len >> 9;
+	cur_nr_sectors = bio_cur_sectors(bio);
+
 	rw = bio_data_dir(bio);
 
 	/*
@@ -1672,7 +1673,10 @@ static int __make_request(request_queue_t *q, struct bio *bio)
 			}
 
 			bio->bi_next = req->bio;
-			req->bio = bio;
+			req->cbio = req->bio = bio;
+			req->nr_cbio_segments = bio_segments(bio);
+			req->nr_cbio_sectors = bio_sectors(bio);
+
 			/*
 			 * may not be valid. if the low level driver said
 			 * it didn't need a bounce buffer then it better
@@ -1740,9 +1744,11 @@ static int __make_request(request_queue_t *q, struct bio *bio)
 	req->current_nr_sectors = req->hard_cur_sectors = cur_nr_sectors;
 	req->nr_phys_segments = bio_phys_segments(q, bio);
 	req->nr_hw_segments = bio_hw_segments(q, bio);
+	req->nr_cbio_segments = bio_segments(bio);
+	req->nr_cbio_sectors = bio_sectors(bio);
 	req->buffer = bio_data(bio);	/* see ->buffer comment above */
 	req->waiting = NULL;
-	req->bio = req->biotail = bio;
+	req->cbio = req->bio = req->biotail = bio;
 	req->rq_disk = bio->bi_bdev->bd_disk;
 	req->start_time = jiffies;
 
@@ -1914,6 +1920,81 @@ int submit_bio(int rw, struct bio *bio)
 	return 1;
 }
 
+/**
+ * blk_rq_next_segment
+ * @rq:		the request being processed
+ *
+ * Description:
+ *	Points to the next segment in the request if the current segment
+ *	is complete. Leaves things unchanged if this segment is not over
+ *	or if no more segments are left in this request.
+ *
+ *	Meant to be used for bio traversal during I/O submission
+ *	Does not affect any I/O completions or update completion state
+ *	in the request, and does not modify any bio fields.
+ *
+ *	Decrementing rq->nr_sectors, rq->current_nr_sectors and
+ *	rq->nr_cbio_sectors as data is transferred is the caller's
+ *	responsibility and should be done before calling this routine.
+ **/
+void blk_rq_next_segment(struct request *rq)
+{
+	if (rq->current_nr_sectors > 0)
+		return;
+
+	if (rq->nr_cbio_sectors > 0) {
+		--rq->nr_cbio_segments;
+		rq->current_nr_sectors = blk_rq_vec(rq)->bv_len >> 9;
+	} else {
+		if ((rq->cbio = rq->cbio->bi_next)) {
+			rq->nr_cbio_segments = bio_segments(rq->cbio);
+			rq->nr_cbio_sectors = bio_sectors(rq->cbio);
+ 			rq->current_nr_sectors = bio_cur_sectors(rq->cbio);
+		}
+ 	}
+
+	/* remember the size of this segment before we start I/O */
+	rq->hard_cur_sectors = rq->current_nr_sectors;
+}
+
+/**
+ * process_that_request_first	-	process partial request submission
+ * @req:	the request being processed
+ * @nr_sectors:	number of sectors I/O has been submitted on
+ *
+ * Description:
+ *	May be used for processing bio's while submitting I/O without
+ *	signalling completion. Fails if more data is requested than is
+ *	available in the request in which case it doesn't advance any
+ *	pointers.
+ *
+ *	Assumes a request is correctly set up. No sanity checks.
+ *
+ * Return:
+ *	0 - no more data left to submit (not processed)
+ *	1 - data available to submit for this request (processed)
+ **/
+int process_that_request_first(struct request *req, unsigned int nr_sectors)
+{
+	unsigned int nsect;
+
+	if (req->nr_sectors < nr_sectors)
+		return 0;
+
+	req->nr_sectors -= nr_sectors;
+	req->sector += nr_sectors;
+	while (nr_sectors) {
+		nsect = min_t(unsigned, req->current_nr_sectors, nr_sectors);
+		req->current_nr_sectors -= nsect;
+		nr_sectors -= nsect;
+		if (req->cbio) {
+			req->nr_cbio_sectors -= nsect;
+			blk_rq_next_segment(req);
+		}
+	}
+	return 1;
+}
+
 void blk_recalc_rq_segments(struct request *rq)
 {
 	struct bio *bio;
@@ -1922,8 +2003,6 @@ void blk_recalc_rq_segments(struct request *rq)
 	if (!rq->bio)
 		return;
 
-	rq->buffer = bio_data(rq->bio);
-
 	nr_phys_segs = nr_hw_segs = 0;
 	rq_for_each_bio(bio, rq) {
 		/* Force bio hw/phys segs to be recalculated. */
@@ -1941,11 +2020,24 @@ void blk_recalc_rq_sectors(struct request *rq, int nsect)
 {
 	if (blk_fs_request(rq)) {
 		rq->hard_sector += nsect;
-		rq->nr_sectors = rq->hard_nr_sectors -= nsect;
-		rq->sector = rq->hard_sector;
+		rq->hard_nr_sectors -= nsect;
 
-		rq->current_nr_sectors = bio_iovec(rq->bio)->bv_len >> 9;
-		rq->hard_cur_sectors = rq->current_nr_sectors;
+		/*
+		 * Move the I/O submission pointers ahead if required,
+		 * i.e. for drivers not aware of rq->cbio.
+		 */
+		if ((rq->nr_sectors >= rq->hard_nr_sectors) &&
+		    (rq->sector <= rq->hard_sector)) {
+			rq->sector = rq->hard_sector;
+			rq->nr_sectors = rq->hard_nr_sectors;
+			rq->hard_cur_sectors = bio_cur_sectors(rq->bio);
+			rq->current_nr_sectors = rq->hard_cur_sectors;
+			rq->nr_cbio_segments = bio_segments(rq->bio);
+			rq->nr_cbio_sectors = bio_sectors(rq->bio);
+			rq->buffer = bio_data(rq->bio);
+
+			rq->cbio = rq->bio;
+		}
 
 		/*
 		 * if total number of sectors is less than the first segment
@@ -2139,9 +2231,27 @@ void blk_rq_bio_prep(request_queue_t *q, struct request *rq, struct bio *bio)
 	rq->current_nr_sectors = bio_cur_sectors(bio);
 	rq->hard_cur_sectors = rq->current_nr_sectors;
 	rq->hard_nr_sectors = rq->nr_sectors = bio_sectors(bio);
+	rq->nr_cbio_segments = bio_segments(bio);
+	rq->nr_cbio_sectors = bio_sectors(bio);
 	rq->buffer = bio_data(bio);
 
-	rq->bio = rq->biotail = bio;
+	rq->cbio = rq->bio = rq->biotail = bio;
+}
+
+void blk_rq_prep_restart(struct request *rq)
+{
+	struct bio *bio;
+
+	bio = rq->cbio = rq->bio;
+	if (bio) {
+		rq->nr_cbio_segments = bio_segments(bio);
+		rq->nr_cbio_sectors = bio_sectors(bio);
+		rq->hard_cur_sectors = bio_cur_sectors(bio);
+		rq->buffer = bio_data(bio);
+	}
+	rq->sector = rq->hard_sector;
+	rq->nr_sectors = rq->hard_nr_sectors;
+	rq->current_nr_sectors = rq->hard_cur_sectors;
 }
 
 int __init blk_dev_init(void)
@@ -2169,6 +2279,7 @@ int __init blk_dev_init(void)
 	return 0;
 };
 
+EXPORT_SYMBOL(process_that_request_first);
 EXPORT_SYMBOL(end_that_request_first);
 EXPORT_SYMBOL(end_that_request_chunk);
 EXPORT_SYMBOL(end_that_request_last);

include/linux/bio.h

@@ -131,6 +131,7 @@ struct bio {
 #define bio_iovec(bio)		bio_iovec_idx((bio), (bio)->bi_idx)
 #define bio_page(bio)		bio_iovec((bio))->bv_page
 #define bio_offset(bio)		bio_iovec((bio))->bv_offset
+#define bio_segments(bio)	((bio)->bi_vcnt - (bio)->bi_idx)
 #define bio_sectors(bio)	((bio)->bi_size >> 9)
 #define bio_cur_sectors(bio)	(bio_iovec(bio)->bv_len >> 9)
 #define bio_data(bio)		(page_address(bio_page((bio))) + bio_offset((bio)))
@@ -226,12 +227,12 @@ extern void bio_check_pages_dirty(struct bio *bio);
 #ifdef CONFIG_HIGHMEM
 /*
  * remember to add offset! and never ever reenable interrupts between a
- * bio_kmap_irq and bio_kunmap_irq!!
+ * bvec_kmap_irq and bvec_kunmap_irq!!
  *
  * This function MUST be inlined - it plays with the CPU interrupt flags.
  * Hence the `extern inline'.
  */
-extern inline char *bio_kmap_irq(struct bio *bio, unsigned long *flags)
+extern inline char *bvec_kmap_irq(struct bio_vec *bvec, unsigned long *flags)
 {
 	unsigned long addr;
 
@@ -240,15 +241,15 @@ extern inline char *bio_kmap_irq(struct bio *bio, unsigned long *flags)
 	 * balancing is a lot nicer this way
 	 */
 	local_irq_save(*flags);
-	addr = (unsigned long) kmap_atomic(bio_page(bio), KM_BIO_SRC_IRQ);
+	addr = (unsigned long) kmap_atomic(bvec->bv_page, KM_BIO_SRC_IRQ);
 
 	if (addr & ~PAGE_MASK)
 		BUG();
 
-	return (char *) addr + bio_offset(bio);
+	return (char *) addr + bvec->bv_offset;
 }
 
-extern inline void bio_kunmap_irq(char *buffer, unsigned long *flags)
+extern inline void bvec_kunmap_irq(char *buffer, unsigned long *flags)
 {
 	unsigned long ptr = (unsigned long) buffer & PAGE_MASK;
 
@@ -257,8 +258,19 @@ extern inline void bio_kunmap_irq(char *buffer, unsigned long *flags)
 }
 
 #else
-#define bio_kmap_irq(bio, flags)	(bio_data(bio))
-#define bio_kunmap_irq(buf, flags)	do { *(flags) = 0; } while (0)
+#define bvec_kmap_irq(bvec, flags)	(page_address((bvec)->bv_page) + (bvec)->bv_offset)
+#define bvec_kunmap_irq(buf, flags)	do { *(flags) = 0; } while (0)
 #endif
 
+extern inline char *__bio_kmap_irq(struct bio *bio, unsigned short idx,
+				   unsigned long *flags)
+{
+	return bvec_kmap_irq(bio_iovec_idx(bio, idx), flags);
+}
+#define __bio_kunmap_irq(buf, flags)	bvec_kunmap_irq(buf, flags)
+
+#define bio_kmap_irq(bio, flags) \
+	__bio_kmap_irq((bio), (bio)->bi_idx, (flags))
+#define bio_kunmap_irq(buf,flags)	__bio_kunmap_irq(buf, flags)
+
 #endif /* __LINUX_BIO_H */

include/linux/blkdev.h

@@ -11,6 +11,7 @@
 #include <linux/backing-dev.h>
 #include <linux/wait.h>
 #include <linux/mempool.h>
+#include <linux/bio.h>
 
 #include <asm/scatterlist.h>
 
@@ -36,25 +37,35 @@ struct request {
 				     * blkdev_dequeue_request! */
 	unsigned long flags;		/* see REQ_ bits below */
 
-	sector_t sector;
-	unsigned long nr_sectors;
+	/* Maintain bio traversal state for part by part I/O submission.
+	 * hard_* are block layer internals, no driver should touch them!
+	 */
+
+	sector_t sector;		/* next sector to submit */
+	unsigned long nr_sectors;	/* no. of sectors left to submit */
+	/* no. of sectors left to submit in the current segment */
 	unsigned int current_nr_sectors;
 
+	sector_t hard_sector;		/* next sector to complete */
+	unsigned long hard_nr_sectors;	/* no. of sectors left to complete */
+	/* no. of sectors left to complete in the current segment */
+	unsigned int hard_cur_sectors;
+
+	/* no. of segments left to submit in the current bio */
+	unsigned short nr_cbio_segments;
+	/* no. of sectors left to submit in the current bio */
+	unsigned long nr_cbio_sectors;
+
+	struct bio *cbio;		/* next bio to submit */
+	struct bio *bio;		/* next unfinished bio to complete */
+	struct bio *biotail;
+
 	void *elevator_private;
 
 	int rq_status;	/* should split this into a few status bits */
 	struct gendisk *rq_disk;
 	int errors;
 	unsigned long start_time;
-	sector_t hard_sector;		/* the hard_* are block layer
-					 * internals, no driver should
-					 * touch them
-					 */
-	unsigned long hard_nr_sectors;
-	unsigned int hard_cur_sectors;
-
-	struct bio *bio;
-	struct bio *biotail;
 
 	/* Number of scatter-gather DMA addr+len pairs after
 	 * physical address coalescing is performed.
@@ -284,6 +295,32 @@ struct request_queue
  */
 #define blk_queue_headactive(q, head_active)
 
+/* current index into bio being processed for submission */
+#define blk_rq_idx(rq)	((rq)->cbio->bi_vcnt - (rq)->nr_cbio_segments)
+
+/* current bio vector being processed */
+#define blk_rq_vec(rq)	(bio_iovec_idx((rq)->cbio, blk_rq_idx(rq)))
+
+/* current offset with respect to start of the segment being submitted */
+#define blk_rq_offset(rq) \
+	(((rq)->hard_cur_sectors - (rq)->current_nr_sectors) << 9)
+
+/*
+ * temporarily mapping a (possible) highmem bio (typically for PIO transfer)
+ */
+
+/* Assumes rq->cbio != NULL */
+static inline char * rq_map_buffer(struct request *rq, unsigned long *flags)
+{
+	return (__bio_kmap_irq(rq->cbio, blk_rq_idx(rq), flags)
+		+ blk_rq_offset(rq));
+}
+
+static inline void rq_unmap_buffer(char *buffer, unsigned long *flags)
+{
+	__bio_kunmap_irq(buffer, flags);
+}
+
 /*
  * q->prep_rq_fn return values
  */
@@ -362,6 +399,7 @@ static inline request_queue_t *bdev_get_queue(struct block_device *bdev)
 extern int end_that_request_first(struct request *, int, int);
 extern int end_that_request_chunk(struct request *, int, int);
 extern void end_that_request_last(struct request *);
+extern int process_that_request_first(struct request *, unsigned int);
 extern void end_request(struct request *req, int uptodate);
 
 static inline void blkdev_dequeue_request(struct request *req)