linux/block/blk-barrier.c

446 lines
11 KiB
C
Raw Normal View History

/*
* Functions related to barrier IO handling
*/
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/bio.h>
#include <linux/blkdev.h>
#include "blk.h"
/**
* blk_queue_ordered - does this queue support ordered writes
* @q: the request queue
* @ordered: one of QUEUE_ORDERED_*
* @prepare_flush_fn: rq setup helper for cache flush ordered writes
*
* Description:
* For journalled file systems, doing ordered writes on a commit
* block instead of explicitly doing wait_on_buffer (which is bad
* for performance) can be a big win. Block drivers supporting this
* feature should call this function and indicate so.
*
**/
int blk_queue_ordered(struct request_queue *q, unsigned ordered,
prepare_flush_fn *prepare_flush_fn)
{
if (!prepare_flush_fn && (ordered & (QUEUE_ORDERED_DO_PREFLUSH |
QUEUE_ORDERED_DO_POSTFLUSH))) {
printk(KERN_ERR "%s: prepare_flush_fn required\n", __func__);
return -EINVAL;
}
if (ordered != QUEUE_ORDERED_NONE &&
ordered != QUEUE_ORDERED_DRAIN &&
ordered != QUEUE_ORDERED_DRAIN_FLUSH &&
ordered != QUEUE_ORDERED_DRAIN_FUA &&
ordered != QUEUE_ORDERED_TAG &&
ordered != QUEUE_ORDERED_TAG_FLUSH &&
ordered != QUEUE_ORDERED_TAG_FUA) {
printk(KERN_ERR "blk_queue_ordered: bad value %d\n", ordered);
return -EINVAL;
}
q->ordered = ordered;
q->next_ordered = ordered;
q->prepare_flush_fn = prepare_flush_fn;
return 0;
}
EXPORT_SYMBOL(blk_queue_ordered);
/*
* Cache flushing for ordered writes handling
*/
unsigned blk_ordered_cur_seq(struct request_queue *q)
{
if (!q->ordseq)
return 0;
return 1 << ffz(q->ordseq);
}
unsigned blk_ordered_req_seq(struct request *rq)
{
struct request_queue *q = rq->q;
BUG_ON(q->ordseq == 0);
if (rq == &q->pre_flush_rq)
return QUEUE_ORDSEQ_PREFLUSH;
if (rq == &q->bar_rq)
return QUEUE_ORDSEQ_BAR;
if (rq == &q->post_flush_rq)
return QUEUE_ORDSEQ_POSTFLUSH;
/*
* !fs requests don't need to follow barrier ordering. Always
* put them at the front. This fixes the following deadlock.
*
* http://thread.gmane.org/gmane.linux.kernel/537473
*/
if (!blk_fs_request(rq))
return QUEUE_ORDSEQ_DRAIN;
if ((rq->cmd_flags & REQ_ORDERED_COLOR) ==
(q->orig_bar_rq->cmd_flags & REQ_ORDERED_COLOR))
return QUEUE_ORDSEQ_DRAIN;
else
return QUEUE_ORDSEQ_DONE;
}
bool blk_ordered_complete_seq(struct request_queue *q, unsigned seq, int error)
{
struct request *rq;
if (error && !q->orderr)
q->orderr = error;
BUG_ON(q->ordseq & seq);
q->ordseq |= seq;
if (blk_ordered_cur_seq(q) != QUEUE_ORDSEQ_DONE)
return false;
/*
* Okay, sequence complete.
*/
q->ordseq = 0;
rq = q->orig_bar_rq;
__blk_end_request_all(rq, q->orderr);
return true;
}
static void pre_flush_end_io(struct request *rq, int error)
{
elv_completed_request(rq->q, rq);
blk_ordered_complete_seq(rq->q, QUEUE_ORDSEQ_PREFLUSH, error);
}
static void bar_end_io(struct request *rq, int error)
{
elv_completed_request(rq->q, rq);
blk_ordered_complete_seq(rq->q, QUEUE_ORDSEQ_BAR, error);
}
static void post_flush_end_io(struct request *rq, int error)
{
elv_completed_request(rq->q, rq);
blk_ordered_complete_seq(rq->q, QUEUE_ORDSEQ_POSTFLUSH, error);
}
static void queue_flush(struct request_queue *q, unsigned which)
{
struct request *rq;
rq_end_io_fn *end_io;
if (which == QUEUE_ORDERED_DO_PREFLUSH) {
rq = &q->pre_flush_rq;
end_io = pre_flush_end_io;
} else {
rq = &q->post_flush_rq;
end_io = post_flush_end_io;
}
blk_rq_init(q, rq);
rq->cmd_flags = REQ_HARDBARRIER;
rq->rq_disk = q->bar_rq.rq_disk;
rq->end_io = end_io;
q->prepare_flush_fn(q, rq);
elv_insert(q, rq, ELEVATOR_INSERT_FRONT);
}
static inline bool start_ordered(struct request_queue *q, struct request **rqp)
{
struct request *rq = *rqp;
unsigned skip = 0;
q->orderr = 0;
q->ordered = q->next_ordered;
q->ordseq |= QUEUE_ORDSEQ_STARTED;
/*
* For an empty barrier, there's no actual BAR request, which
* in turn makes POSTFLUSH unnecessary. Mask them off.
*/
if (!blk_rq_sectors(rq)) {
q->ordered &= ~(QUEUE_ORDERED_DO_BAR |
QUEUE_ORDERED_DO_POSTFLUSH);
/*
* Empty barrier on a write-through device w/ ordered
* tag has no command to issue and without any command
* to issue, ordering by tag can't be used. Drain
* instead.
*/
if ((q->ordered & QUEUE_ORDERED_BY_TAG) &&
!(q->ordered & QUEUE_ORDERED_DO_PREFLUSH)) {
q->ordered &= ~QUEUE_ORDERED_BY_TAG;
q->ordered |= QUEUE_ORDERED_BY_DRAIN;
}
}
/* stash away the original request */
block: implement and enforce request peek/start/fetch Till now block layer allowed two separate modes of request execution. A request is always acquired from the request queue via elv_next_request(). After that, drivers are free to either dequeue it or process it without dequeueing. Dequeue allows elv_next_request() to return the next request so that multiple requests can be in flight. Executing requests without dequeueing has its merits mostly in allowing drivers for simpler devices which can't do sg to deal with segments only without considering request boundary. However, the benefit this brings is dubious and declining while the cost of the API ambiguity is increasing. Segment based drivers are usually for very old or limited devices and as converting to dequeueing model isn't difficult, it doesn't justify the API overhead it puts on block layer and its more modern users. Previous patches converted all block low level drivers to dequeueing model. This patch completes the API transition by... * renaming elv_next_request() to blk_peek_request() * renaming blkdev_dequeue_request() to blk_start_request() * adding blk_fetch_request() which is combination of peek and start * disallowing completion of queued (not started) requests * applying new API to all LLDs Renamings are for consistency and to break out of tree code so that it's apparent that out of tree drivers need updating. [ Impact: block request issue API cleanup, no functional change ] Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: James Bottomley <James.Bottomley@HansenPartnership.com> Cc: Mike Miller <mike.miller@hp.com> Cc: unsik Kim <donari75@gmail.com> Cc: Paul Clements <paul.clements@steeleye.com> Cc: Tim Waugh <tim@cyberelk.net> Cc: Geert Uytterhoeven <Geert.Uytterhoeven@sonycom.com> Cc: David S. Miller <davem@davemloft.net> Cc: Laurent Vivier <Laurent@lvivier.info> Cc: Jeff Garzik <jgarzik@pobox.com> Cc: Jeremy Fitzhardinge <jeremy@xensource.com> Cc: Grant Likely <grant.likely@secretlab.ca> Cc: Adrian McMenamin <adrian@mcmen.demon.co.uk> Cc: Stephen Rothwell <sfr@canb.auug.org.au> Cc: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com> Cc: Borislav Petkov <petkovbb@googlemail.com> Cc: Sergei Shtylyov <sshtylyov@ru.mvista.com> Cc: Alex Dubov <oakad@yahoo.com> Cc: Pierre Ossman <drzeus@drzeus.cx> Cc: David Woodhouse <dwmw2@infradead.org> Cc: Markus Lidel <Markus.Lidel@shadowconnect.com> Cc: Stefan Weinhuber <wein@de.ibm.com> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Pete Zaitcev <zaitcev@redhat.com> Cc: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2009-05-08 02:54:16 +00:00
blk_dequeue_request(rq);
q->orig_bar_rq = rq;
rq = NULL;
/*
* Queue ordered sequence. As we stack them at the head, we
* need to queue in reverse order. Note that we rely on that
* no fs request uses ELEVATOR_INSERT_FRONT and thus no fs
* request gets inbetween ordered sequence.
*/
if (q->ordered & QUEUE_ORDERED_DO_POSTFLUSH) {
queue_flush(q, QUEUE_ORDERED_DO_POSTFLUSH);
rq = &q->post_flush_rq;
} else
skip |= QUEUE_ORDSEQ_POSTFLUSH;
if (q->ordered & QUEUE_ORDERED_DO_BAR) {
rq = &q->bar_rq;
/* initialize proxy request and queue it */
blk_rq_init(q, rq);
if (bio_data_dir(q->orig_bar_rq->bio) == WRITE)
rq->cmd_flags |= REQ_RW;
if (q->ordered & QUEUE_ORDERED_DO_FUA)
rq->cmd_flags |= REQ_FUA;
init_request_from_bio(rq, q->orig_bar_rq->bio);
rq->end_io = bar_end_io;
elv_insert(q, rq, ELEVATOR_INSERT_FRONT);
} else
skip |= QUEUE_ORDSEQ_BAR;
if (q->ordered & QUEUE_ORDERED_DO_PREFLUSH) {
queue_flush(q, QUEUE_ORDERED_DO_PREFLUSH);
rq = &q->pre_flush_rq;
} else
skip |= QUEUE_ORDSEQ_PREFLUSH;
if ((q->ordered & QUEUE_ORDERED_BY_DRAIN) && queue_in_flight(q))
rq = NULL;
else
skip |= QUEUE_ORDSEQ_DRAIN;
*rqp = rq;
/*
* Complete skipped sequences. If whole sequence is complete,
* return false to tell elevator that this request is gone.
*/
return !blk_ordered_complete_seq(q, skip, 0);
}
bool blk_do_ordered(struct request_queue *q, struct request **rqp)
{
struct request *rq = *rqp;
const int is_barrier = blk_fs_request(rq) && blk_barrier_rq(rq);
if (!q->ordseq) {
if (!is_barrier)
return true;
if (q->next_ordered != QUEUE_ORDERED_NONE)
return start_ordered(q, rqp);
else {
/*
* Queue ordering not supported. Terminate
* with prejudice.
*/
block: implement and enforce request peek/start/fetch Till now block layer allowed two separate modes of request execution. A request is always acquired from the request queue via elv_next_request(). After that, drivers are free to either dequeue it or process it without dequeueing. Dequeue allows elv_next_request() to return the next request so that multiple requests can be in flight. Executing requests without dequeueing has its merits mostly in allowing drivers for simpler devices which can't do sg to deal with segments only without considering request boundary. However, the benefit this brings is dubious and declining while the cost of the API ambiguity is increasing. Segment based drivers are usually for very old or limited devices and as converting to dequeueing model isn't difficult, it doesn't justify the API overhead it puts on block layer and its more modern users. Previous patches converted all block low level drivers to dequeueing model. This patch completes the API transition by... * renaming elv_next_request() to blk_peek_request() * renaming blkdev_dequeue_request() to blk_start_request() * adding blk_fetch_request() which is combination of peek and start * disallowing completion of queued (not started) requests * applying new API to all LLDs Renamings are for consistency and to break out of tree code so that it's apparent that out of tree drivers need updating. [ Impact: block request issue API cleanup, no functional change ] Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: James Bottomley <James.Bottomley@HansenPartnership.com> Cc: Mike Miller <mike.miller@hp.com> Cc: unsik Kim <donari75@gmail.com> Cc: Paul Clements <paul.clements@steeleye.com> Cc: Tim Waugh <tim@cyberelk.net> Cc: Geert Uytterhoeven <Geert.Uytterhoeven@sonycom.com> Cc: David S. Miller <davem@davemloft.net> Cc: Laurent Vivier <Laurent@lvivier.info> Cc: Jeff Garzik <jgarzik@pobox.com> Cc: Jeremy Fitzhardinge <jeremy@xensource.com> Cc: Grant Likely <grant.likely@secretlab.ca> Cc: Adrian McMenamin <adrian@mcmen.demon.co.uk> Cc: Stephen Rothwell <sfr@canb.auug.org.au> Cc: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com> Cc: Borislav Petkov <petkovbb@googlemail.com> Cc: Sergei Shtylyov <sshtylyov@ru.mvista.com> Cc: Alex Dubov <oakad@yahoo.com> Cc: Pierre Ossman <drzeus@drzeus.cx> Cc: David Woodhouse <dwmw2@infradead.org> Cc: Markus Lidel <Markus.Lidel@shadowconnect.com> Cc: Stefan Weinhuber <wein@de.ibm.com> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Pete Zaitcev <zaitcev@redhat.com> Cc: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2009-05-08 02:54:16 +00:00
blk_dequeue_request(rq);
__blk_end_request_all(rq, -EOPNOTSUPP);
*rqp = NULL;
return false;
}
}
/*
* Ordered sequence in progress
*/
/* Special requests are not subject to ordering rules. */
if (!blk_fs_request(rq) &&
rq != &q->pre_flush_rq && rq != &q->post_flush_rq)
return true;
if (q->ordered & QUEUE_ORDERED_BY_TAG) {
/* Ordered by tag. Blocking the next barrier is enough. */
if (is_barrier && rq != &q->bar_rq)
*rqp = NULL;
} else {
/* Ordered by draining. Wait for turn. */
WARN_ON(blk_ordered_req_seq(rq) < blk_ordered_cur_seq(q));
if (blk_ordered_req_seq(rq) > blk_ordered_cur_seq(q))
*rqp = NULL;
}
return true;
}
static void bio_end_empty_barrier(struct bio *bio, int err)
{
if (err) {
if (err == -EOPNOTSUPP)
set_bit(BIO_EOPNOTSUPP, &bio->bi_flags);
clear_bit(BIO_UPTODATE, &bio->bi_flags);
}
complete(bio->bi_private);
}
/**
* blkdev_issue_flush - queue a flush
* @bdev: blockdev to issue flush for
* @error_sector: error sector
*
* Description:
* Issue a flush for the block device in question. Caller can supply
* room for storing the error offset in case of a flush error, if they
* wish to.
*/
int blkdev_issue_flush(struct block_device *bdev, sector_t *error_sector)
{
DECLARE_COMPLETION_ONSTACK(wait);
struct request_queue *q;
struct bio *bio;
int ret;
if (bdev->bd_disk == NULL)
return -ENXIO;
q = bdev_get_queue(bdev);
if (!q)
return -ENXIO;
bio = bio_alloc(GFP_KERNEL, 0);
bio->bi_end_io = bio_end_empty_barrier;
bio->bi_private = &wait;
bio->bi_bdev = bdev;
submit_bio(WRITE_BARRIER, bio);
wait_for_completion(&wait);
/*
* The driver must store the error location in ->bi_sector, if
* it supports it. For non-stacked drivers, this should be copied
block: convert to pos and nr_sectors accessors With recent cleanups, there is no place where low level driver directly manipulates request fields. This means that the 'hard' request fields always equal the !hard fields. Convert all rq->sectors, nr_sectors and current_nr_sectors references to accessors. While at it, drop superflous blk_rq_pos() < 0 test in swim.c. [ Impact: use pos and nr_sectors accessors ] Signed-off-by: Tejun Heo <tj@kernel.org> Acked-by: Geert Uytterhoeven <Geert.Uytterhoeven@sonycom.com> Tested-by: Grant Likely <grant.likely@secretlab.ca> Acked-by: Grant Likely <grant.likely@secretlab.ca> Tested-by: Adrian McMenamin <adrian@mcmen.demon.co.uk> Acked-by: Adrian McMenamin <adrian@mcmen.demon.co.uk> Acked-by: Mike Miller <mike.miller@hp.com> Cc: James Bottomley <James.Bottomley@HansenPartnership.com> Cc: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com> Cc: Borislav Petkov <petkovbb@googlemail.com> Cc: Sergei Shtylyov <sshtylyov@ru.mvista.com> Cc: Eric Moore <Eric.Moore@lsi.com> Cc: Alan Stern <stern@rowland.harvard.edu> Cc: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp> Cc: Pete Zaitcev <zaitcev@redhat.com> Cc: Stephen Rothwell <sfr@canb.auug.org.au> Cc: Paul Clements <paul.clements@steeleye.com> Cc: Tim Waugh <tim@cyberelk.net> Cc: Jeff Garzik <jgarzik@pobox.com> Cc: Jeremy Fitzhardinge <jeremy@xensource.com> Cc: Alex Dubov <oakad@yahoo.com> Cc: David Woodhouse <dwmw2@infradead.org> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Dario Ballabio <ballabio_dario@emc.com> Cc: David S. Miller <davem@davemloft.net> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: unsik Kim <donari75@gmail.com> Cc: Laurent Vivier <Laurent@lvivier.info> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2009-05-07 13:24:39 +00:00
* from blk_rq_pos(rq).
*/
if (error_sector)
*error_sector = bio->bi_sector;
ret = 0;
if (bio_flagged(bio, BIO_EOPNOTSUPP))
ret = -EOPNOTSUPP;
else if (!bio_flagged(bio, BIO_UPTODATE))
ret = -EIO;
bio_put(bio);
return ret;
}
EXPORT_SYMBOL(blkdev_issue_flush);
static void blkdev_discard_end_io(struct bio *bio, int err)
{
if (err) {
if (err == -EOPNOTSUPP)
set_bit(BIO_EOPNOTSUPP, &bio->bi_flags);
clear_bit(BIO_UPTODATE, &bio->bi_flags);
}
if (bio->bi_private)
complete(bio->bi_private);
__free_page(bio_page(bio));
bio_put(bio);
}
/**
* blkdev_issue_discard - queue a discard
* @bdev: blockdev to issue discard for
* @sector: start sector
* @nr_sects: number of sectors to discard
* @gfp_mask: memory allocation flags (for bio_alloc)
* @flags: DISCARD_FL_* flags to control behaviour
*
* Description:
* Issue a discard request for the sectors in question.
*/
int blkdev_issue_discard(struct block_device *bdev, sector_t sector,
sector_t nr_sects, gfp_t gfp_mask, int flags)
{
DECLARE_COMPLETION_ONSTACK(wait);
struct request_queue *q = bdev_get_queue(bdev);
int type = flags & DISCARD_FL_BARRIER ?
DISCARD_BARRIER : DISCARD_NOBARRIER;
struct bio *bio;
struct page *page;
int ret = 0;
if (!q)
return -ENXIO;
if (!blk_queue_discard(q))
return -EOPNOTSUPP;
while (nr_sects && !ret) {
unsigned int sector_size = q->limits.logical_block_size;
unsigned int max_discard_sectors =
min(q->limits.max_discard_sectors, UINT_MAX >> 9);
bio = bio_alloc(gfp_mask, 1);
if (!bio)
goto out;
bio->bi_sector = sector;
bio->bi_end_io = blkdev_discard_end_io;
bio->bi_bdev = bdev;
if (flags & DISCARD_FL_WAIT)
bio->bi_private = &wait;
/*
* Add a zeroed one-sector payload as that's what
* our current implementations need. If we'll ever need
* more the interface will need revisiting.
*/
page = alloc_page(gfp_mask | __GFP_ZERO);
if (!page)
goto out_free_bio;
if (bio_add_pc_page(q, bio, page, sector_size, 0) < sector_size)
goto out_free_page;
/*
* And override the bio size - the way discard works we
* touch many more blocks on disk than the actual payload
* length.
*/
if (nr_sects > max_discard_sectors) {
bio->bi_size = max_discard_sectors << 9;
nr_sects -= max_discard_sectors;
sector += max_discard_sectors;
} else {
bio->bi_size = nr_sects << 9;
nr_sects = 0;
}
bio_get(bio);
submit_bio(type, bio);
if (flags & DISCARD_FL_WAIT)
wait_for_completion(&wait);
if (bio_flagged(bio, BIO_EOPNOTSUPP))
ret = -EOPNOTSUPP;
else if (!bio_flagged(bio, BIO_UPTODATE))
ret = -EIO;
bio_put(bio);
}
return ret;
out_free_page:
__free_page(page);
out_free_bio:
bio_put(bio);
out:
return -ENOMEM;
}
EXPORT_SYMBOL(blkdev_issue_discard);