[PATCH 11/13] bdi: replace BDI_CAP_STABLE_WRITES with a queue and a sb flag

From: Christoph Hellwig
Date: Thu Sep 24 2020 - 02:52:54 EST


The BDI_CAP_STABLE_WRITES is one of the few bits of information in the
backing_dev_info shared between the block drivers and the writeback code.
To help untangling the dependency replace it with a queue flag and a
superblock flag derived from it. This also helps with the case of e.g.
a file system requiring stable writes due to its own checksumming, but
not forcing it on other users of the block device like the swap code.

One downside is that we an't support the stable_pages_required bdi
attribute in sysfs anymore. It is replaced with a queue attribute which
also is writable for easier testing.

Signed-off-by: Christoph Hellwig <hch@xxxxxx>
Reviewed-by: Jan Kara <jack@xxxxxxx>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@xxxxxxx>
---
block/blk-integrity.c | 4 ++--
block/blk-mq-debugfs.c | 1 +
block/blk-sysfs.c | 3 +++
drivers/block/rbd.c | 2 +-
drivers/block/zram/zram_drv.c | 2 +-
drivers/md/dm-table.c | 6 +++---
drivers/md/raid5.c | 8 ++++----
drivers/mmc/core/queue.c | 3 +--
drivers/nvme/host/core.c | 3 +--
drivers/nvme/host/multipath.c | 10 +++-------
drivers/scsi/iscsi_tcp.c | 4 ++--
fs/super.c | 2 ++
include/linux/backing-dev.h | 6 ------
include/linux/blkdev.h | 3 +++
include/linux/fs.h | 1 +
mm/backing-dev.c | 7 +++----
mm/page-writeback.c | 2 +-
mm/swapfile.c | 2 +-
18 files changed, 33 insertions(+), 36 deletions(-)

diff --git a/block/blk-integrity.c b/block/blk-integrity.c
index c03705cbb9c9f2..2b36a8f9b81390 100644
--- a/block/blk-integrity.c
+++ b/block/blk-integrity.c
@@ -408,7 +408,7 @@ void blk_integrity_register(struct gendisk *disk, struct blk_integrity *template
bi->tuple_size = template->tuple_size;
bi->tag_size = template->tag_size;

- disk->queue->backing_dev_info->capabilities |= BDI_CAP_STABLE_WRITES;
+ blk_queue_flag_set(QUEUE_FLAG_STABLE_WRITES, disk->queue);

#ifdef CONFIG_BLK_INLINE_ENCRYPTION
if (disk->queue->ksm) {
@@ -428,7 +428,7 @@ EXPORT_SYMBOL(blk_integrity_register);
*/
void blk_integrity_unregister(struct gendisk *disk)
{
- disk->queue->backing_dev_info->capabilities &= ~BDI_CAP_STABLE_WRITES;
+ blk_queue_flag_clear(QUEUE_FLAG_STABLE_WRITES, disk->queue);
memset(&disk->queue->integrity, 0, sizeof(struct blk_integrity));
}
EXPORT_SYMBOL(blk_integrity_unregister);
diff --git a/block/blk-mq-debugfs.c b/block/blk-mq-debugfs.c
index 645b7f800cb827..3094542e12ae0f 100644
--- a/block/blk-mq-debugfs.c
+++ b/block/blk-mq-debugfs.c
@@ -116,6 +116,7 @@ static const char *const blk_queue_flag_name[] = {
QUEUE_FLAG_NAME(SAME_FORCE),
QUEUE_FLAG_NAME(DEAD),
QUEUE_FLAG_NAME(INIT_DONE),
+ QUEUE_FLAG_NAME(STABLE_WRITES),
QUEUE_FLAG_NAME(POLL),
QUEUE_FLAG_NAME(WC),
QUEUE_FLAG_NAME(FUA),
diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c
index 869ed21a9edcab..76b54c7750b07e 100644
--- a/block/blk-sysfs.c
+++ b/block/blk-sysfs.c
@@ -287,6 +287,7 @@ queue_##name##_store(struct request_queue *q, const char *page, size_t count) \
QUEUE_SYSFS_BIT_FNS(nonrot, NONROT, 1);
QUEUE_SYSFS_BIT_FNS(random, ADD_RANDOM, 0);
QUEUE_SYSFS_BIT_FNS(iostats, IO_STAT, 0);
+QUEUE_SYSFS_BIT_FNS(stable_writes, STABLE_WRITES, 0);
#undef QUEUE_SYSFS_BIT_FNS

static ssize_t queue_zoned_show(struct request_queue *q, char *page)
@@ -613,6 +614,7 @@ static struct queue_sysfs_entry queue_hw_sector_size_entry = {
QUEUE_RW_ENTRY(queue_nonrot, "rotational");
QUEUE_RW_ENTRY(queue_iostats, "iostats");
QUEUE_RW_ENTRY(queue_random, "add_random");
+QUEUE_RW_ENTRY(queue_stable_writes, "stable_writes");

static struct attribute *queue_attrs[] = {
&queue_requests_entry.attr,
@@ -645,6 +647,7 @@ static struct attribute *queue_attrs[] = {
&queue_nomerges_entry.attr,
&queue_rq_affinity_entry.attr,
&queue_iostats_entry.attr,
+ &queue_stable_writes_entry.attr,
&queue_random_entry.attr,
&queue_poll_entry.attr,
&queue_wc_entry.attr,
diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c
index 5d3923c0997ce0..cf5b016358cdab 100644
--- a/drivers/block/rbd.c
+++ b/drivers/block/rbd.c
@@ -5022,7 +5022,7 @@ static int rbd_init_disk(struct rbd_device *rbd_dev)
}

if (!ceph_test_opt(rbd_dev->rbd_client->client, NOCRC))
- q->backing_dev_info->capabilities |= BDI_CAP_STABLE_WRITES;
+ blk_queue_flag_set(QUEUE_FLAG_STABLE_WRITES, q);

/*
* disk_release() expects a queue ref from add_disk() and will
diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c
index e21ca844d7c291..bff3d4021c18e1 100644
--- a/drivers/block/zram/zram_drv.c
+++ b/drivers/block/zram/zram_drv.c
@@ -1955,7 +1955,7 @@ static int zram_add(void)
if (ZRAM_LOGICAL_BLOCK_SIZE == PAGE_SIZE)
blk_queue_max_write_zeroes_sectors(zram->disk->queue, UINT_MAX);

- zram->disk->queue->backing_dev_info->capabilities |= BDI_CAP_STABLE_WRITES;
+ blk_queue_flag_set(QUEUE_FLAG_STABLE_WRITES, zram->disk->queue);
device_add_disk(NULL, zram->disk, zram_disk_attr_groups);

strlcpy(zram->compressor, default_compressor, sizeof(zram->compressor));
diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c
index ef2757012f59d5..405d7cf10eb973 100644
--- a/drivers/md/dm-table.c
+++ b/drivers/md/dm-table.c
@@ -1815,7 +1815,7 @@ static int device_requires_stable_pages(struct dm_target *ti,
{
struct request_queue *q = bdev_get_queue(dev->bdev);

- return q && bdi_cap_stable_pages_required(q->backing_dev_info);
+ return q && blk_queue_stable_writes(q);
}

/*
@@ -1900,9 +1900,9 @@ void dm_table_set_restrictions(struct dm_table *t, struct request_queue *q,
* because they do their own checksumming.
*/
if (dm_table_requires_stable_pages(t))
- q->backing_dev_info->capabilities |= BDI_CAP_STABLE_WRITES;
+ blk_queue_flag_set(QUEUE_FLAG_STABLE_WRITES, q);
else
- q->backing_dev_info->capabilities &= ~BDI_CAP_STABLE_WRITES;
+ blk_queue_flag_clear(QUEUE_FLAG_STABLE_WRITES, q);

/*
* Determine whether or not this queue's I/O timings contribute
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 7ace1f76b14736..d589d26c86ea3f 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -6638,14 +6638,14 @@ raid5_store_skip_copy(struct mddev *mddev, const char *page, size_t len)
if (!conf)
err = -ENODEV;
else if (new != conf->skip_copy) {
+ struct request_queue *q = mddev->queue;
+
mddev_suspend(mddev);
conf->skip_copy = new;
if (new)
- mddev->queue->backing_dev_info->capabilities |=
- BDI_CAP_STABLE_WRITES;
+ blk_queue_flag_set(QUEUE_FLAG_STABLE_WRITES, q);
else
- mddev->queue->backing_dev_info->capabilities &=
- ~BDI_CAP_STABLE_WRITES;
+ blk_queue_flag_clear(QUEUE_FLAG_STABLE_WRITES, q);
mddev_resume(mddev);
}
mddev_unlock(mddev);
diff --git a/drivers/mmc/core/queue.c b/drivers/mmc/core/queue.c
index 6c022ef0f84d72..80fe3852ce0f75 100644
--- a/drivers/mmc/core/queue.c
+++ b/drivers/mmc/core/queue.c
@@ -472,8 +472,7 @@ int mmc_init_queue(struct mmc_queue *mq, struct mmc_card *card)
}

if (mmc_host_is_spi(host) && host->use_spi_crc)
- mq->queue->backing_dev_info->capabilities |=
- BDI_CAP_STABLE_WRITES;
+ blk_queue_flag_set(QUEUE_FLAG_STABLE_WRITES, mq->queue);

mq->queue->queuedata = mq;
blk_queue_rq_timeout(mq->queue, 60 * HZ);
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 741c9bfa8e14c7..c190c56bf7020d 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -3926,8 +3926,7 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid)
goto out_free_ns;

if (ctrl->opts && ctrl->opts->data_digest)
- ns->queue->backing_dev_info->capabilities
- |= BDI_CAP_STABLE_WRITES;
+ blk_queue_flag_set(QUEUE_FLAG_STABLE_WRITES, ns->queue);

blk_queue_flag_set(QUEUE_FLAG_NONROT, ns->queue);
if (ctrl->ops->flags & NVME_F_PCI_P2PDMA)
diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c
index d4ba736c6c8905..74896be40c1769 100644
--- a/drivers/nvme/host/multipath.c
+++ b/drivers/nvme/host/multipath.c
@@ -673,13 +673,9 @@ void nvme_mpath_add_disk(struct nvme_ns *ns, struct nvme_id_ns *id)
nvme_mpath_set_live(ns);
}

- if (bdi_cap_stable_pages_required(ns->queue->backing_dev_info)) {
- struct gendisk *disk = ns->head->disk;
-
- if (disk)
- disk->queue->backing_dev_info->capabilities |=
- BDI_CAP_STABLE_WRITES;
- }
+ if (blk_queue_stable_writes(ns->queue) && ns->head->disk)
+ blk_queue_flag_set(QUEUE_FLAG_STABLE_WRITES,
+ ns->head->disk->queue);
}

void nvme_mpath_remove_disk(struct nvme_ns_head *head)
diff --git a/drivers/scsi/iscsi_tcp.c b/drivers/scsi/iscsi_tcp.c
index b5dd1caae5e92d..a622f334c933f5 100644
--- a/drivers/scsi/iscsi_tcp.c
+++ b/drivers/scsi/iscsi_tcp.c
@@ -962,8 +962,8 @@ static int iscsi_sw_tcp_slave_configure(struct scsi_device *sdev)
struct iscsi_conn *conn = session->leadconn;

if (conn->datadgst_en)
- sdev->request_queue->backing_dev_info->capabilities
- |= BDI_CAP_STABLE_WRITES;
+ blk_queue_flag_set(QUEUE_FLAG_STABLE_WRITES,
+ sdev->request_queue);
blk_queue_dma_alignment(sdev->request_queue, 0);
return 0;
}
diff --git a/fs/super.c b/fs/super.c
index 904459b3511995..a51c2083cd6b18 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -1256,6 +1256,8 @@ static int set_bdev_super(struct super_block *s, void *data)
s->s_dev = s->s_bdev->bd_dev;
s->s_bdi = bdi_get(s->s_bdev->bd_bdi);

+ if (blk_queue_stable_writes(s->s_bdev->bd_disk->queue))
+ s->s_iflags |= SB_I_STABLE_WRITES;
return 0;
}

diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h
index 860ea33571bce5..5da4ea3dd0cc5c 100644
--- a/include/linux/backing-dev.h
+++ b/include/linux/backing-dev.h
@@ -126,7 +126,6 @@ int bdi_set_max_ratio(struct backing_dev_info *bdi, unsigned int max_ratio);
#define BDI_CAP_NO_ACCT_DIRTY 0x00000001
#define BDI_CAP_NO_WRITEBACK 0x00000002
#define BDI_CAP_NO_ACCT_WB 0x00000004
-#define BDI_CAP_STABLE_WRITES 0x00000008
#define BDI_CAP_STRICTLIMIT 0x00000010
#define BDI_CAP_CGROUP_WRITEBACK 0x00000020

@@ -170,11 +169,6 @@ static inline int wb_congested(struct bdi_writeback *wb, int cong_bits)
long congestion_wait(int sync, long timeout);
long wait_iff_congested(int sync, long timeout);

-static inline bool bdi_cap_stable_pages_required(struct backing_dev_info *bdi)
-{
- return bdi->capabilities & BDI_CAP_STABLE_WRITES;
-}
-
static inline bool bdi_cap_writeback_dirty(struct backing_dev_info *bdi)
{
return !(bdi->capabilities & BDI_CAP_NO_WRITEBACK);
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 282f5ca424f14a..8e77f12de52214 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -606,6 +606,7 @@ struct request_queue {
#define QUEUE_FLAG_SAME_FORCE 12 /* force complete on same CPU */
#define QUEUE_FLAG_DEAD 13 /* queue tear-down finished */
#define QUEUE_FLAG_INIT_DONE 14 /* queue is initialized */
+#define QUEUE_FLAG_STABLE_WRITES 15 /* don't modify blks until WB is done */
#define QUEUE_FLAG_POLL 16 /* IO polling enabled if set */
#define QUEUE_FLAG_WC 17 /* Write back caching */
#define QUEUE_FLAG_FUA 18 /* device supports FUA writes */
@@ -635,6 +636,8 @@ bool blk_queue_flag_test_and_set(unsigned int flag, struct request_queue *q);
#define blk_queue_noxmerges(q) \
test_bit(QUEUE_FLAG_NOXMERGES, &(q)->queue_flags)
#define blk_queue_nonrot(q) test_bit(QUEUE_FLAG_NONROT, &(q)->queue_flags)
+#define blk_queue_stable_writes(q) \
+ test_bit(QUEUE_FLAG_STABLE_WRITES, &(q)->queue_flags)
#define blk_queue_io_stat(q) test_bit(QUEUE_FLAG_IO_STAT, &(q)->queue_flags)
#define blk_queue_add_random(q) test_bit(QUEUE_FLAG_ADD_RANDOM, &(q)->queue_flags)
#define blk_queue_discard(q) test_bit(QUEUE_FLAG_DISCARD, &(q)->queue_flags)
diff --git a/include/linux/fs.h b/include/linux/fs.h
index fbd74df5ce5f34..222465b7cf4178 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1385,6 +1385,7 @@ extern int send_sigurg(struct fown_struct *fown);
#define SB_I_CGROUPWB 0x00000001 /* cgroup-aware writeback enabled */
#define SB_I_NOEXEC 0x00000002 /* Ignore executables on this fs */
#define SB_I_NODEV 0x00000004 /* Ignore devices on this fs */
+#define SB_I_STABLE_WRITES 0x00000008 /* don't modify blks until WB is done */

/* sb->s_iflags to limit user namespace mounts */
#define SB_I_USERNS_VISIBLE 0x00000010 /* fstype already mounted */
diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index 2dac3be6127127..8e3802bf03a968 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -204,10 +204,9 @@ static ssize_t stable_pages_required_show(struct device *dev,
struct device_attribute *attr,
char *page)
{
- struct backing_dev_info *bdi = dev_get_drvdata(dev);
-
- return snprintf(page, PAGE_SIZE-1, "%d\n",
- bdi_cap_stable_pages_required(bdi) ? 1 : 0);
+ dev_warn_once(dev,
+ "the stable_pages_required attribute has been removed. Use the stable_writes queue attribute instead.\n");
+ return snprintf(page, PAGE_SIZE-1, "%d\n", 0);
}
static DEVICE_ATTR_RO(stable_pages_required);

diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 4e4ddd67b71e58..e9c36521461aaa 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -2849,7 +2849,7 @@ EXPORT_SYMBOL_GPL(wait_on_page_writeback);
*/
void wait_for_stable_page(struct page *page)
{
- if (bdi_cap_stable_pages_required(inode_to_bdi(page->mapping->host)))
+ if (page->mapping->host->i_sb->s_iflags & SB_I_STABLE_WRITES)
wait_on_page_writeback(page);
}
EXPORT_SYMBOL_GPL(wait_for_stable_page);
diff --git a/mm/swapfile.c b/mm/swapfile.c
index 96a7c47dd533e4..65ef407512b5b0 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -3237,7 +3237,7 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags)
goto bad_swap_unlock_inode;
}

- if (bdi_cap_stable_pages_required(inode_to_bdi(inode)))
+ if (p->bdev && blk_queue_stable_writes(p->bdev->bd_disk->queue))
p->flags |= SWP_STABLE_WRITES;

if (p->bdev && p->bdev->bd_disk->fops->rw_page)
--
2.28.0