Thread (109 messages) 109 messages, 19 authors, 2011-01-14

Re: [PATCH 03/11] block: deprecate barrier and replace blk_queue_ordered() with blk_queue_flush()

From: Jeremy Fitzhardinge <hidden>
Date: 2010-08-14 01:07:13
Also in: dm-devel, linux-fsdevel, linux-ide, linux-scsi

 On 08/12/2010 05:41 AM, Tejun Heo wrote:
Barrier is deemed too heavy and will soon be replaced by FLUSH/FUA
requests.  Deprecate barrier.  All REQ_HARDBARRIERs are failed with
-EOPNOTSUPP and blk_queue_ordered() is replaced with simpler
blk_queue_flush().

blk_queue_flush() takes combinations of REQ_FLUSH and FUA.  If a
device has write cache and can flush it, it should set REQ_FLUSH.  If
the device can handle FUA writes, it should also set REQ_FUA.
Christoph, do these two patches (parts 2 and 3) make xen-blkfront
correct WRT barriers/flushing as far as your concerned?

Thanks,
    J
quoted hunk ↗ jump to hunk
All blk_queue_ordered() users are converted.

* ORDERED_DRAIN is mapped to 0 which is the default value.
* ORDERED_DRAIN_FLUSH is mapped to REQ_FLUSH.
* ORDERED_DRAIN_FLUSH_FUA is mapped to REQ_FLUSH | REQ_FUA.

Signed-off-by: Tejun Heo <tj@kernel.org>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: Nick Piggin <redacted>
Cc: Michael S. Tsirkin <mst@redhat.com>
Cc: Jeremy Fitzhardinge <redacted>
Cc: Chris Wright <redacted>
Cc: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp>
Cc: Boaz Harrosh <redacted>
Cc: Geert Uytterhoeven <redacted>
Cc: David S. Miller <davem@davemloft.net>
Cc: Alasdair G Kergon <agk@redhat.com>
Cc: Pierre Ossman <redacted>
Cc: Stefan Weinhuber <redacted>
---
 block/blk-barrier.c          |   29 ----------------------------
 block/blk-core.c             |    6 +++-
 block/blk-settings.c         |   20 +++++++++++++++++++
 drivers/block/brd.c          |    1 -
 drivers/block/loop.c         |    2 +-
 drivers/block/osdblk.c       |    2 +-
 drivers/block/ps3disk.c      |    2 +-
 drivers/block/virtio_blk.c   |   25 ++++++++---------------
 drivers/block/xen-blkfront.c |   43 +++++++++++------------------------------
 drivers/ide/ide-disk.c       |   13 +++++------
 drivers/md/dm.c              |    2 +-
 drivers/mmc/card/queue.c     |    1 -
 drivers/s390/block/dasd.c    |    1 -
 drivers/scsi/sd.c            |   16 +++++++-------
 include/linux/blkdev.h       |    6 +++-
 15 files changed, 67 insertions(+), 102 deletions(-)
diff --git a/block/blk-barrier.c b/block/blk-barrier.c
index c807e9c..ed0aba5 100644
--- a/block/blk-barrier.c
+++ b/block/blk-barrier.c
@@ -9,35 +9,6 @@

 #include "blk.h"

-/**
- * blk_queue_ordered - does this queue support ordered writes
- * @q:        the request queue
- * @ordered:  one of QUEUE_ORDERED_*
- *
- * 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)
-{
-       if (ordered != QUEUE_ORDERED_NONE &&
-           ordered != QUEUE_ORDERED_DRAIN &&
-           ordered != QUEUE_ORDERED_DRAIN_FLUSH &&
-           ordered != QUEUE_ORDERED_DRAIN_FUA) {
-               printk(KERN_ERR "blk_queue_ordered: bad value %d\n", ordered);
-               return -EINVAL;
-       }
-
-       q->ordered = ordered;
-       q->next_ordered = ordered;
-
-       return 0;
-}
-EXPORT_SYMBOL(blk_queue_ordered);
-
 /*
  * Cache flushing for ordered writes handling
  */
diff --git a/block/blk-core.c b/block/blk-core.c
index 5ab3ac2..3f802dd 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -1203,11 +1203,13 @@ static int __make_request(struct request_queue *q, struct bio *bio)
        const unsigned int ff = bio->bi_rw & REQ_FAILFAST_MASK;
        int rw_flags;

-       if ((bio->bi_rw & REQ_HARDBARRIER) &&
-           (q->next_ordered == QUEUE_ORDERED_NONE)) {
+       /* REQ_HARDBARRIER is no more */
+       if (WARN_ONCE(bio->bi_rw & REQ_HARDBARRIER,
+               "block: HARDBARRIER is deprecated, use FLUSH/FUA instead\n")) {
                bio_endio(bio, -EOPNOTSUPP);
                return 0;
        }
+
        /*
         * low level driver can indicate that it wants pages above a
         * certain limit bounced to low memory (ie for highmem, or even
diff --git a/block/blk-settings.c b/block/blk-settings.c
index a234f4b..9b18afc 100644
--- a/block/blk-settings.c
+++ b/block/blk-settings.c
@@ -794,6 +794,26 @@ void blk_queue_update_dma_alignment(struct request_queue *q, int mask)
 }
 EXPORT_SYMBOL(blk_queue_update_dma_alignment);

+/**
+ * blk_queue_flush - configure queue's cache flush capability
+ * @q:         the request queue for the device
+ * @flush:     0, REQ_FLUSH or REQ_FLUSH | REQ_FUA
+ *
+ * Tell block layer cache flush capability of @q.  If it supports
+ * flushing, REQ_FLUSH should be set.  If it supports bypassing
+ * write cache for individual writes, REQ_FUA should be set.
+ */
+void blk_queue_flush(struct request_queue *q, unsigned int flush)
+{
+       WARN_ON_ONCE(flush & ~(REQ_FLUSH | REQ_FUA));
+
+       if (WARN_ON_ONCE(!(flush & REQ_FLUSH) && (flush & REQ_FUA)))
+               flush &= ~REQ_FUA;
+
+       q->flush_flags = flush & (REQ_FLUSH | REQ_FUA);
+}
+EXPORT_SYMBOL_GPL(blk_queue_flush);
+
 static int __init blk_settings_init(void)
 {
        blk_max_low_pfn = max_low_pfn - 1;
diff --git a/drivers/block/brd.c b/drivers/block/brd.c
index 47a4127..fa33f97 100644
--- a/drivers/block/brd.c
+++ b/drivers/block/brd.c
@@ -482,7 +482,6 @@ static struct brd_device *brd_alloc(int i)
        if (!brd->brd_queue)
                goto out_free_dev;
        blk_queue_make_request(brd->brd_queue, brd_make_request);
-       blk_queue_ordered(brd->brd_queue, QUEUE_ORDERED_DRAIN);
        blk_queue_max_hw_sectors(brd->brd_queue, 1024);
        blk_queue_bounce_limit(brd->brd_queue, BLK_BOUNCE_ANY);
diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index c3a4a2e..953d1e1 100644
--- a/drivers/block/loop.c
+++ b/drivers/block/loop.c
@@ -832,7 +832,7 @@ static int loop_set_fd(struct loop_device *lo, fmode_t mode,
        lo->lo_queue->unplug_fn = loop_unplug;

        if (!(lo_flags & LO_FLAGS_READ_ONLY) && file->f_op->fsync)
-               blk_queue_ordered(lo->lo_queue, QUEUE_ORDERED_DRAIN_FLUSH);
+               blk_queue_flush(lo->lo_queue, REQ_FLUSH);

        set_capacity(lo->lo_disk, size);
        bd_set_size(bdev, size << 9);
diff --git a/drivers/block/osdblk.c b/drivers/block/osdblk.c
index 2284b4f..72d6246 100644
--- a/drivers/block/osdblk.c
+++ b/drivers/block/osdblk.c
@@ -439,7 +439,7 @@ static int osdblk_init_disk(struct osdblk_device *osdev)
        blk_queue_stack_limits(q, osd_request_queue(osdev->osd));

        blk_queue_prep_rq(q, blk_queue_start_tag);
-       blk_queue_ordered(q, QUEUE_ORDERED_DRAIN_FLUSH);
+       blk_queue_flush(q, REQ_FLUSH);

        disk->queue = q;
diff --git a/drivers/block/ps3disk.c b/drivers/block/ps3disk.c
index e9da874..4911f9e 100644
--- a/drivers/block/ps3disk.c
+++ b/drivers/block/ps3disk.c
@@ -468,7 +468,7 @@ static int __devinit ps3disk_probe(struct ps3_system_bus_device *_dev)
        blk_queue_dma_alignment(queue, dev->blk_size-1);
        blk_queue_logical_block_size(queue, dev->blk_size);

-       blk_queue_ordered(queue, QUEUE_ORDERED_DRAIN_FLUSH);
+       blk_queue_flush(queue, REQ_FLUSH);

        blk_queue_max_segments(queue, -1);
        blk_queue_max_segment_size(queue, dev->bounce_size);
diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c
index 7965280..d10b635 100644
--- a/drivers/block/virtio_blk.c
+++ b/drivers/block/virtio_blk.c
@@ -388,22 +388,15 @@ static int __devinit virtblk_probe(struct virtio_device *vdev)
        vblk->disk->driverfs_dev = &vdev->dev;
        index++;

-       if (virtio_has_feature(vdev, VIRTIO_BLK_F_FLUSH)) {
-               /*
-                * If the FLUSH feature is supported we do have support for
-                * flushing a volatile write cache on the host.  Use that
-                * to implement write barrier support.
-                */
-               blk_queue_ordered(q, QUEUE_ORDERED_DRAIN_FLUSH);
-       } else {
-               /*
-                * If the FLUSH feature is not supported we must assume that
-                * the host does not perform any kind of volatile write
-                * caching. We still need to drain the queue to provider
-                * proper barrier semantics.
-                */
-               blk_queue_ordered(q, QUEUE_ORDERED_DRAIN);
-       }
+       /*
+        * If the FLUSH feature is supported we do have support for
+        * flushing a volatile write cache on the host.  Use that to
+        * implement write barrier support; otherwise, we must assume
+        * that the host does not perform any kind of volatile write
+        * caching.
+        */
+       if (virtio_has_feature(vdev, VIRTIO_BLK_F_FLUSH))
+               blk_queue_flush(q, REQ_FLUSH);

        /* If disk is read-only in the host, the guest should obey */
        if (virtio_has_feature(vdev, VIRTIO_BLK_F_RO))
diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c
index 25ffbf9..1d48f3a 100644
--- a/drivers/block/xen-blkfront.c
+++ b/drivers/block/xen-blkfront.c
@@ -95,7 +95,7 @@ struct blkfront_info
        struct gnttab_free_callback callback;
        struct blk_shadow shadow[BLK_RING_SIZE];
        unsigned long shadow_free;
-       int feature_barrier;
+       unsigned int feature_flush;
        int is_ready;
 };
@@ -418,25 +418,12 @@ static int xlvbd_init_blk_queue(struct gendisk *gd, u16 sector_size)
 }


-static int xlvbd_barrier(struct blkfront_info *info)
+static void xlvbd_flush(struct blkfront_info *info)
 {
-       int err;
-       const char *barrier;
-
-       switch (info->feature_barrier) {
-       case QUEUE_ORDERED_DRAIN:       barrier = "enabled"; break;
-       case QUEUE_ORDERED_NONE:        barrier = "disabled"; break;
-       default:                        return -EINVAL;
-       }
-
-       err = blk_queue_ordered(info->rq, info->feature_barrier);
-
-       if (err)
-               return err;
-
+       blk_queue_flush(info->rq, info->feature_flush);
        printk(KERN_INFO "blkfront: %s: barriers %s\n",
-              info->gd->disk_name, barrier);
-       return 0;
+              info->gd->disk_name,
+              info->feature_flush ? "enabled" : "disabled");
 }

@@ -515,7 +502,7 @@ static int xlvbd_alloc_gendisk(blkif_sector_t capacity,
        info->rq = gd->queue;
        info->gd = gd;

-       xlvbd_barrier(info);
+       xlvbd_flush(info);

        if (vdisk_info & VDISK_READONLY)
                set_disk_ro(gd, 1);
@@ -661,8 +648,8 @@ static irqreturn_t blkif_interrupt(int irq, void *dev_id)
                                printk(KERN_WARNING "blkfront: %s: write barrier op failed\n",
                                       info->gd->disk_name);
                                error = -EOPNOTSUPP;
-                               info->feature_barrier = QUEUE_ORDERED_NONE;
-                               xlvbd_barrier(info);
+                               info->feature_flush = 0;
+                               xlvbd_flush(info);
                        }
                        /* fall through */
                case BLKIF_OP_READ:
@@ -1075,19 +1062,13 @@ static void blkfront_connect(struct blkfront_info *info)
        /*
         * If there's no "feature-barrier" defined, then it means
         * we're dealing with a very old backend which writes
-        * synchronously; draining will do what needs to get done.
+        * synchronously; nothing to do.
         *
         * If there are barriers, then we use flush.
-        *
-        * If barriers are not supported, then there's no much we can
-        * do, so just set ordering to NONE.
         */
-       if (err)
-               info->feature_barrier = QUEUE_ORDERED_DRAIN;
-       else if (barrier)
-               info->feature_barrier = QUEUE_ORDERED_DRAIN_FLUSH;
-       else
-               info->feature_barrier = QUEUE_ORDERED_NONE;
+       info->feature_flush = 0;
+       if (!err && barrier)
+               info->feature_flush = REQ_FLUSH;

        err = xlvbd_alloc_gendisk(sectors, info, binfo, sector_size);
        if (err) {
diff --git a/drivers/ide/ide-disk.c b/drivers/ide/ide-disk.c
index 7433e07..7c5b01c 100644
--- a/drivers/ide/ide-disk.c
+++ b/drivers/ide/ide-disk.c
@@ -516,10 +516,10 @@ static int ide_do_setfeature(ide_drive_t *drive, u8 feature, u8 nsect)
        return ide_no_data_taskfile(drive, &cmd);
 }

-static void update_ordered(ide_drive_t *drive)
+static void update_flush(ide_drive_t *drive)
 {
        u16 *id = drive->id;
-       unsigned ordered = QUEUE_ORDERED_NONE;
+       unsigned flush = 0;

        if (drive->dev_flags & IDE_DFLAG_WCACHE) {
                unsigned long long capacity;
@@ -543,13 +543,12 @@ static void update_ordered(ide_drive_t *drive)
                       drive->name, barrier ? "" : "not ");

                if (barrier) {
-                       ordered = QUEUE_ORDERED_DRAIN_FLUSH;
+                       flush = REQ_FLUSH;
                        blk_queue_prep_rq(drive->queue, idedisk_prep_fn);
                }
-       } else
-               ordered = QUEUE_ORDERED_DRAIN;
+       }

-       blk_queue_ordered(drive->queue, ordered);
+       blk_queue_flush(drive->queue, flush);
 }

 ide_devset_get_flag(wcache, IDE_DFLAG_WCACHE);
@@ -572,7 +571,7 @@ static int set_wcache(ide_drive_t *drive, int arg)
                }
        }

-       update_ordered(drive);
+       update_flush(drive);

        return err;
 }
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index a3f21dc..b71cc9e 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -1908,7 +1908,7 @@ static struct mapped_device *alloc_dev(int minor)
        blk_queue_softirq_done(md->queue, dm_softirq_done);
        blk_queue_prep_rq(md->queue, dm_prep_fn);
        blk_queue_lld_busy(md->queue, dm_lld_busy);
-       blk_queue_ordered(md->queue, QUEUE_ORDERED_DRAIN_FLUSH);
+       blk_queue_flush(md->queue, REQ_FLUSH);

        md->disk = alloc_disk(1);
        if (!md->disk)
diff --git a/drivers/mmc/card/queue.c b/drivers/mmc/card/queue.c
index c77eb49..d791772 100644
--- a/drivers/mmc/card/queue.c
+++ b/drivers/mmc/card/queue.c
@@ -128,7 +128,6 @@ int mmc_init_queue(struct mmc_queue *mq, struct mmc_card *card, spinlock_t *lock
        mq->req = NULL;

        blk_queue_prep_rq(mq->queue, mmc_prep_request);
-       blk_queue_ordered(mq->queue, QUEUE_ORDERED_DRAIN);
        queue_flag_set_unlocked(QUEUE_FLAG_NONROT, mq->queue);

 #ifdef CONFIG_MMC_BLOCK_BOUNCE
diff --git a/drivers/s390/block/dasd.c b/drivers/s390/block/dasd.c
index 1a84fae..29046b7 100644
--- a/drivers/s390/block/dasd.c
+++ b/drivers/s390/block/dasd.c
@@ -2197,7 +2197,6 @@ static void dasd_setup_queue(struct dasd_block *block)
         */
        blk_queue_max_segment_size(block->request_queue, PAGE_SIZE);
        blk_queue_segment_boundary(block->request_queue, PAGE_SIZE - 1);
-       blk_queue_ordered(block->request_queue, QUEUE_ORDERED_DRAIN);
 }

 /*
diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c
index 05a15b0..7f6aca2 100644
--- a/drivers/scsi/sd.c
+++ b/drivers/scsi/sd.c
@@ -2109,7 +2109,7 @@ static int sd_revalidate_disk(struct gendisk *disk)
        struct scsi_disk *sdkp = scsi_disk(disk);
        struct scsi_device *sdp = sdkp->device;
        unsigned char *buffer;
-       unsigned ordered;
+       unsigned flush = 0;

        SCSI_LOG_HLQUEUE(3, sd_printk(KERN_INFO, sdkp,
                                      "sd_revalidate_disk\n"));
@@ -2151,15 +2151,15 @@ static int sd_revalidate_disk(struct gendisk *disk)

        /*
         * We now have all cache related info, determine how we deal
-        * with ordered requests.
+        * with flush requests.
         */
-       if (sdkp->WCE)
-               ordered = sdkp->DPOFUA
-                       ? QUEUE_ORDERED_DRAIN_FUA : QUEUE_ORDERED_DRAIN_FLUSH;
-       else
-               ordered = QUEUE_ORDERED_DRAIN;
+       if (sdkp->WCE) {
+               flush |= REQ_FLUSH;
+               if (sdkp->DPOFUA)
+                       flush |= REQ_FUA;
+       }

-       blk_queue_ordered(sdkp->disk->queue, ordered);
+       blk_queue_flush(sdkp->disk->queue, flush);

        set_capacity(disk, sdkp->capacity);
        kfree(buffer);
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 96ef5f1..6003f7c 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -355,8 +355,10 @@ struct request_queue
        struct blk_trace        *blk_trace;
 #endif
        /*
-        * reserved for flush operations
+        * for flush operations
         */
+       unsigned int            flush_flags;
+
        unsigned int            ordered, next_ordered, ordseq;
        int                     orderr, ordcolor;
        struct request          pre_flush_rq, bar_rq, post_flush_rq;
@@ -863,8 +865,8 @@ extern void blk_queue_update_dma_alignment(struct request_queue *, int);
 extern void blk_queue_softirq_done(struct request_queue *, softirq_done_fn *);
 extern void blk_queue_rq_timed_out(struct request_queue *, rq_timed_out_fn *);
 extern void blk_queue_rq_timeout(struct request_queue *, unsigned int);
+extern void blk_queue_flush(struct request_queue *q, unsigned int flush);
 extern struct backing_dev_info *blk_get_backing_dev_info(struct block_device *bdev);
-extern int blk_queue_ordered(struct request_queue *, unsigned);
 extern bool blk_do_ordered(struct request_queue *, struct request **);
 extern unsigned blk_ordered_cur_seq(struct request_queue *);
 extern unsigned blk_ordered_req_seq(struct request *);
--
1.7.1
Keyboard shortcuts
hback out one level
jnext message in thread
kprevious message in thread
ldrill in
Escclose help / fold thread tree
?toggle this help