summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorJens Axboe <axboe@kernel.dk>2024-06-19 08:02:34 -0600
committerJens Axboe <axboe@kernel.dk>2024-06-19 08:14:49 -0600
commit69c34f07e45f2d52d9a41991867a1e5a85bbaaf3 (patch)
treedc4779c7ed7a5f17ddf67182399111815da27100
parent465478bb00168a7620788990b1679c5067d421f2 (diff)
parent339d3948c07b4aa2940aeb874294a7d6782cec16 (diff)
Merge branch 'for-6.11/block-limits' into for-6.11/block
Merge in last round of queue limits changes from Christoph. * for-6.11/block-limits: (26 commits) block: move the bounce flag into the features field block: move the skip_tagset_quiesce flag to queue_limits block: move the pci_p2pdma flag to queue_limits block: move the zone_resetall flag to queue_limits block: move the zoned flag into the features field block: move the poll flag to queue_limits block: move the dax flag to queue_limits block: move the nowait flag to queue_limits block: move the synchronous flag to queue_limits block: move the stable_writes flag to queue_limits block: move the io_stat flag setting to queue_limits block: move the add_random flag to queue_limits block: move the nonrot flag to queue_limits block: move cache control settings out of queue->flags block: remove blk_flush_policy block: freeze the queue in queue_attr_store nbd: move setting the cache control flags to __nbd_set_size virtio_blk: remove virtblk_update_cache_mode loop: fold loop_update_rotational into loop_reconfigure_limits loop: also use the default block size from an underlying block device ... Signed-off-by: Jens Axboe <axboe@kernel.dk>
-rw-r--r--Documentation/block/writeback_cache_control.rst67
-rw-r--r--arch/m68k/emu/nfblock.c1
-rw-r--r--arch/um/drivers/ubd_kern.c3
-rw-r--r--arch/xtensa/platforms/iss/simdisk.c5
-rw-r--r--block/blk-core.c7
-rw-r--r--block/blk-flush.c36
-rw-r--r--block/blk-mq-debugfs.c13
-rw-r--r--block/blk-mq.c42
-rw-r--r--block/blk-settings.c46
-rw-r--r--block/blk-sysfs.c118
-rw-r--r--block/blk-wbt.c4
-rw-r--r--block/blk.h2
-rw-r--r--drivers/block/amiflop.c5
-rw-r--r--drivers/block/aoe/aoeblk.c1
-rw-r--r--drivers/block/ataflop.c5
-rw-r--r--drivers/block/brd.c6
-rw-r--r--drivers/block/drbd/drbd_main.c6
-rw-r--r--drivers/block/floppy.c3
-rw-r--r--drivers/block/loop.c79
-rw-r--r--drivers/block/mtip32xx/mtip32xx.c2
-rw-r--r--drivers/block/n64cart.c2
-rw-r--r--drivers/block/nbd.c24
-rw-r--r--drivers/block/null_blk/main.c13
-rw-r--r--drivers/block/null_blk/zoned.c3
-rw-r--r--drivers/block/pktcdvd.c1
-rw-r--r--drivers/block/ps3disk.c8
-rw-r--r--drivers/block/rbd.c12
-rw-r--r--drivers/block/rnbd/rnbd-clt.c14
-rw-r--r--drivers/block/sunvdc.c1
-rw-r--r--drivers/block/swim.c5
-rw-r--r--drivers/block/swim3.c5
-rw-r--r--drivers/block/ublk_drv.c21
-rw-r--r--drivers/block/virtio_blk.c37
-rw-r--r--drivers/block/xen-blkfront.c53
-rw-r--r--drivers/block/zram/zram_drv.c6
-rw-r--r--drivers/cdrom/gdrom.c1
-rw-r--r--drivers/md/bcache/super.c9
-rw-r--r--drivers/md/dm-table.c186
-rw-r--r--drivers/md/dm-zone.c5
-rw-r--r--drivers/md/dm-zoned-target.c2
-rw-r--r--drivers/md/dm.c13
-rw-r--r--drivers/md/md.c40
-rw-r--r--drivers/md/raid5.c6
-rw-r--r--drivers/mmc/core/block.c42
-rw-r--r--drivers/mmc/core/queue.c20
-rw-r--r--drivers/mmc/core/queue.h3
-rw-r--r--drivers/mtd/mtd_blkdevs.c9
-rw-r--r--drivers/nvdimm/btt.c4
-rw-r--r--drivers/nvdimm/pmem.c14
-rw-r--r--drivers/nvme/host/core.c33
-rw-r--r--drivers/nvme/host/multipath.c24
-rw-r--r--drivers/nvme/host/zns.c3
-rw-r--r--drivers/s390/block/dasd_genhd.c1
-rw-r--r--drivers/s390/block/dcssblk.c2
-rw-r--r--drivers/s390/block/scm_blk.c5
-rw-r--r--drivers/scsi/iscsi_tcp.c8
-rw-r--r--drivers/scsi/scsi_lib.c5
-rw-r--r--drivers/scsi/sd.c66
-rw-r--r--drivers/scsi/sd.h5
-rw-r--r--drivers/scsi/sd_zbc.c25
-rw-r--r--include/linux/blkdev.h119
61 files changed, 576 insertions, 730 deletions
diff --git a/Documentation/block/writeback_cache_control.rst b/Documentation/block/writeback_cache_control.rst
index b208488d0aae..c575e08beda8 100644
--- a/Documentation/block/writeback_cache_control.rst
+++ b/Documentation/block/writeback_cache_control.rst
@@ -46,41 +46,50 @@ worry if the underlying devices need any explicit cache flushing and how
the Forced Unit Access is implemented. The REQ_PREFLUSH and REQ_FUA flags
may both be set on a single bio.
+Feature settings for block drivers
+----------------------------------
-Implementation details for bio based block drivers
---------------------------------------------------------------
+For devices that do not support volatile write caches there is no driver
+support required, the block layer completes empty REQ_PREFLUSH requests before
+entering the driver and strips off the REQ_PREFLUSH and REQ_FUA bits from
+requests that have a payload.
-These drivers will always see the REQ_PREFLUSH and REQ_FUA bits as they sit
-directly below the submit_bio interface. For remapping drivers the REQ_FUA
-bits need to be propagated to underlying devices, and a global flush needs
-to be implemented for bios with the REQ_PREFLUSH bit set. For real device
-drivers that do not have a volatile cache the REQ_PREFLUSH and REQ_FUA bits
-on non-empty bios can simply be ignored, and REQ_PREFLUSH requests without
-data can be completed successfully without doing any work. Drivers for
-devices with volatile caches need to implement the support for these
-flags themselves without any help from the block layer.
+For devices with volatile write caches the driver needs to tell the block layer
+that it supports flushing caches by setting the
+ BLK_FEAT_WRITE_CACHE
-Implementation details for request_fn based block drivers
----------------------------------------------------------
+flag in the queue_limits feature field. For devices that also support the FUA
+bit the block layer needs to be told to pass on the REQ_FUA bit by also setting
+the
-For devices that do not support volatile write caches there is no driver
-support required, the block layer completes empty REQ_PREFLUSH requests before
-entering the driver and strips off the REQ_PREFLUSH and REQ_FUA bits from
-requests that have a payload. For devices with volatile write caches the
-driver needs to tell the block layer that it supports flushing caches by
-doing::
+ BLK_FEAT_FUA
+
+flag in the features field of the queue_limits structure.
+
+Implementation details for bio based block drivers
+--------------------------------------------------
+
+For bio based drivers the REQ_PREFLUSH and REQ_FUA bit are simplify passed on
+to the driver if the drivers sets the BLK_FEAT_WRITE_CACHE flag and the drivers
+needs to handle them.
+
+*NOTE*: The REQ_FUA bit also gets passed on when the BLK_FEAT_FUA flags is
+_not_ set. Any bio based driver that sets BLK_FEAT_WRITE_CACHE also needs to
+handle REQ_FUA.
- blk_queue_write_cache(sdkp->disk->queue, true, false);
+For remapping drivers the REQ_FUA bits need to be propagated to underlying
+devices, and a global flush needs to be implemented for bios with the
+REQ_PREFLUSH bit set.
-and handle empty REQ_OP_FLUSH requests in its prep_fn/request_fn. Note that
-REQ_PREFLUSH requests with a payload are automatically turned into a sequence
-of an empty REQ_OP_FLUSH request followed by the actual write by the block
-layer. For devices that also support the FUA bit the block layer needs
-to be told to pass through the REQ_FUA bit using::
+Implementation details for blk-mq drivers
+-----------------------------------------
- blk_queue_write_cache(sdkp->disk->queue, true, true);
+When the BLK_FEAT_WRITE_CACHE flag is set, REQ_OP_WRITE | REQ_PREFLUSH requests
+with a payload are automatically turned into a sequence of a REQ_OP_FLUSH
+request followed by the actual write by the block layer.
-and the driver must handle write requests that have the REQ_FUA bit set
-in prep_fn/request_fn. If the FUA bit is not natively supported the block
-layer turns it into an empty REQ_OP_FLUSH request after the actual write.
+When the BLK_FEAT_FUA flags is set, the REQ_FUA bit simplify passed on for the
+REQ_OP_WRITE request, else a REQ_OP_FLUSH request is sent by the block layer
+after the completion of the write request for bio submissions with the REQ_FUA
+bit set.
diff --git a/arch/m68k/emu/nfblock.c b/arch/m68k/emu/nfblock.c
index 642fb80c5c4e..8eea7ef91151 100644
--- a/arch/m68k/emu/nfblock.c
+++ b/arch/m68k/emu/nfblock.c
@@ -98,6 +98,7 @@ static int __init nfhd_init_one(int id, u32 blocks, u32 bsize)
{
struct queue_limits lim = {
.logical_block_size = bsize,
+ .features = BLK_FEAT_ROTATIONAL,
};
struct nfhd_device *dev;
int dev_id = id - NFHD_DEV_OFFSET;
diff --git a/arch/um/drivers/ubd_kern.c b/arch/um/drivers/ubd_kern.c
index cdcb75a68989..9f1e76ddda5a 100644
--- a/arch/um/drivers/ubd_kern.c
+++ b/arch/um/drivers/ubd_kern.c
@@ -835,6 +835,7 @@ static int ubd_add(int n, char **error_out)
struct queue_limits lim = {
.max_segments = MAX_SG,
.seg_boundary_mask = PAGE_SIZE - 1,
+ .features = BLK_FEAT_WRITE_CACHE,
};
struct gendisk *disk;
int err = 0;
@@ -881,8 +882,6 @@ static int ubd_add(int n, char **error_out)
goto out_cleanup_tags;
}
- blk_queue_flag_set(QUEUE_FLAG_NONROT, disk->queue);
- blk_queue_write_cache(disk->queue, true, false);
disk->major = UBD_MAJOR;
disk->first_minor = n << UBD_SHIFT;
disk->minors = 1 << UBD_SHIFT;
diff --git a/arch/xtensa/platforms/iss/simdisk.c b/arch/xtensa/platforms/iss/simdisk.c
index defc67909a9c..d6d2b533a574 100644
--- a/arch/xtensa/platforms/iss/simdisk.c
+++ b/arch/xtensa/platforms/iss/simdisk.c
@@ -263,6 +263,9 @@ static const struct proc_ops simdisk_proc_ops = {
static int __init simdisk_setup(struct simdisk *dev, int which,
struct proc_dir_entry *procdir)
{
+ struct queue_limits lim = {
+ .features = BLK_FEAT_ROTATIONAL,
+ };
char tmp[2] = { '0' + which, 0 };
int err;
@@ -271,7 +274,7 @@ static int __init simdisk_setup(struct simdisk *dev, int which,
spin_lock_init(&dev->lock);
dev->users = 0;
- dev->gd = blk_alloc_disk(NULL, NUMA_NO_NODE);
+ dev->gd = blk_alloc_disk(&lim, NUMA_NO_NODE);
if (IS_ERR(dev->gd)) {
err = PTR_ERR(dev->gd);
goto out;
diff --git a/block/blk-core.c b/block/blk-core.c
index 82c3ae22d76d..8d9fbd353fc7 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -782,7 +782,7 @@ void submit_bio_noacct(struct bio *bio)
if (WARN_ON_ONCE(bio_op(bio) != REQ_OP_WRITE &&
bio_op(bio) != REQ_OP_ZONE_APPEND))
goto end_io;
- if (!test_bit(QUEUE_FLAG_WC, &q->queue_flags)) {
+ if (!bdev_write_cache(bdev)) {
bio->bi_opf &= ~(REQ_PREFLUSH | REQ_FUA);
if (!bio_sectors(bio)) {
status = BLK_STS_OK;
@@ -791,7 +791,7 @@ void submit_bio_noacct(struct bio *bio)
}
}
- if (!test_bit(QUEUE_FLAG_POLL, &q->queue_flags))
+ if (!(q->limits.features & BLK_FEAT_POLL))
bio_clear_polled(bio);
switch (bio_op(bio)) {
@@ -915,8 +915,7 @@ int bio_poll(struct bio *bio, struct io_comp_batch *iob, unsigned int flags)
return 0;
q = bdev_get_queue(bdev);
- if (cookie == BLK_QC_T_NONE ||
- !test_bit(QUEUE_FLAG_POLL, &q->queue_flags))
+ if (cookie == BLK_QC_T_NONE || !(q->limits.features & BLK_FEAT_POLL))
return 0;
blk_flush_plug(current->plug, false);
diff --git a/block/blk-flush.c b/block/blk-flush.c
index c17cf8ed8113..30b9d5033a2b 100644
--- a/block/blk-flush.c
+++ b/block/blk-flush.c
@@ -100,23 +100,6 @@ blk_get_flush_queue(struct request_queue *q, struct blk_mq_ctx *ctx)
return blk_mq_map_queue(q, REQ_OP_FLUSH, ctx)->fq;
}
-static unsigned int blk_flush_policy(unsigned long fflags, struct request *rq)
-{
- unsigned int policy = 0;
-
- if (blk_rq_sectors(rq))
- policy |= REQ_FSEQ_DATA;
-
- if (fflags & (1UL << QUEUE_FLAG_WC)) {
- if (rq->cmd_flags & REQ_PREFLUSH)
- policy |= REQ_FSEQ_PREFLUSH;
- if (!(fflags & (1UL << QUEUE_FLAG_FUA)) &&
- (rq->cmd_flags & REQ_FUA))
- policy |= REQ_FSEQ_POSTFLUSH;
- }
- return policy;
-}
-
static unsigned int blk_flush_cur_seq(struct request *rq)
{
return 1 << ffz(rq->flush.seq);
@@ -398,19 +381,32 @@ static void blk_rq_init_flush(struct request *rq)
bool blk_insert_flush(struct request *rq)
{
struct request_queue *q = rq->q;
- unsigned long fflags = q->queue_flags; /* may change, cache */
- unsigned int policy = blk_flush_policy(fflags, rq);
struct blk_flush_queue *fq = blk_get_flush_queue(q, rq->mq_ctx);
+ bool supports_fua = q->limits.features & BLK_FEAT_FUA;
+ unsigned int policy = 0;
/* FLUSH/FUA request must never be merged */
WARN_ON_ONCE(rq->bio != rq->biotail);
+ if (blk_rq_sectors(rq))
+ policy |= REQ_FSEQ_DATA;
+
+ /*
+ * Check which flushes we need to sequence for this operation.
+ */
+ if (blk_queue_write_cache(q)) {
+ if (rq->cmd_flags & REQ_PREFLUSH)
+ policy |= REQ_FSEQ_PREFLUSH;
+ if ((rq->cmd_flags & REQ_FUA) && !supports_fua)
+ policy |= REQ_FSEQ_POSTFLUSH;
+ }
+
/*
* @policy now records what operations need to be done. Adjust
* REQ_PREFLUSH and FUA for the driver.
*/
rq->cmd_flags &= ~REQ_PREFLUSH;
- if (!(fflags & (1UL << QUEUE_FLAG_FUA)))
+ if (!supports_fua)
rq->cmd_flags &= ~REQ_FUA;
/*
diff --git a/block/blk-mq-debugfs.c b/block/blk-mq-debugfs.c
index 770c0c2b72fa..344f9e503bdb 100644
--- a/block/blk-mq-debugfs.c
+++ b/block/blk-mq-debugfs.c
@@ -84,28 +84,15 @@ static const char *const blk_queue_flag_name[] = {
QUEUE_FLAG_NAME(NOMERGES),
QUEUE_FLAG_NAME(SAME_COMP),
QUEUE_FLAG_NAME(FAIL_IO),
- QUEUE_FLAG_NAME(NONROT),
- QUEUE_FLAG_NAME(IO_STAT),
QUEUE_FLAG_NAME(NOXMERGES),
- QUEUE_FLAG_NAME(ADD_RANDOM),
- QUEUE_FLAG_NAME(SYNCHRONOUS),
QUEUE_FLAG_NAME(SAME_FORCE),
QUEUE_FLAG_NAME(INIT_DONE),
- QUEUE_FLAG_NAME(STABLE_WRITES),
- QUEUE_FLAG_NAME(POLL),
- QUEUE_FLAG_NAME(WC),
- QUEUE_FLAG_NAME(FUA),
- QUEUE_FLAG_NAME(DAX),
QUEUE_FLAG_NAME(STATS),
QUEUE_FLAG_NAME(REGISTERED),
QUEUE_FLAG_NAME(QUIESCED),
- QUEUE_FLAG_NAME(PCI_P2PDMA),
- QUEUE_FLAG_NAME(ZONE_RESETALL),
QUEUE_FLAG_NAME(RQ_ALLOC_TIME),
QUEUE_FLAG_NAME(HCTX_ACTIVE),
- QUEUE_FLAG_NAME(NOWAIT),
QUEUE_FLAG_NAME(SQ_SCHED),
- QUEUE_FLAG_NAME(SKIP_TAGSET_QUIESCE),
};
#undef QUEUE_FLAG_NAME
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 0d4cd39c3d25..e2b9710ddc5a 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -4109,6 +4109,12 @@ void blk_mq_release(struct request_queue *q)
blk_mq_sysfs_deinit(q);
}
+static bool blk_mq_can_poll(struct blk_mq_tag_set *set)
+{
+ return set->nr_maps > HCTX_TYPE_POLL &&
+ set->map[HCTX_TYPE_POLL].nr_queues;
+}
+
struct request_queue *blk_mq_alloc_queue(struct blk_mq_tag_set *set,
struct queue_limits *lim, void *queuedata)
{
@@ -4116,7 +4122,13 @@ struct request_queue *blk_mq_alloc_queue(struct blk_mq_tag_set *set,
struct request_queue *q;
int ret;
- q = blk_alloc_queue(lim ? lim : &default_lim, set->numa_node);
+ if (!lim)
+ lim = &default_lim;
+ lim->features |= BLK_FEAT_IO_STAT | BLK_FEAT_NOWAIT;
+ if (blk_mq_can_poll(set))
+ lim->features |= BLK_FEAT_POLL;
+
+ q = blk_alloc_queue(lim, set->numa_node);
if (IS_ERR(q))
return q;
q->queuedata = queuedata;
@@ -4269,17 +4281,6 @@ static void blk_mq_realloc_hw_ctxs(struct blk_mq_tag_set *set,
mutex_unlock(&q->sysfs_lock);
}
-static void blk_mq_update_poll_flag(struct request_queue *q)
-{
- struct blk_mq_tag_set *set = q->tag_set;
-
- if (set->nr_maps > HCTX_TYPE_POLL &&
- set->map[HCTX_TYPE_POLL].nr_queues)
- blk_queue_flag_set(QUEUE_FLAG_POLL, q);
- else
- blk_queue_flag_clear(QUEUE_FLAG_POLL, q);
-}
-
int blk_mq_init_allocated_queue(struct blk_mq_tag_set *set,
struct request_queue *q)
{
@@ -4307,7 +4308,6 @@ int blk_mq_init_allocated_queue(struct blk_mq_tag_set *set,
q->tag_set = set;
q->queue_flags |= QUEUE_FLAG_MQ_DEFAULT;
- blk_mq_update_poll_flag(q);
INIT_DELAYED_WORK(&q->requeue_work, blk_mq_requeue_work);
INIT_LIST_HEAD(&q->flush_list);
@@ -4631,13 +4631,15 @@ int blk_mq_update_nr_requests(struct request_queue *q, unsigned int nr)
int ret;
unsigned long i;
+ if (WARN_ON_ONCE(!q->mq_freeze_depth))
+ return -EINVAL;
+
if (!set)
return -EINVAL;
if (q->nr_requests == nr)
return 0;
- blk_mq_freeze_queue(q);
blk_mq_quiesce_queue(q);
ret = 0;
@@ -4671,7 +4673,6 @@ int blk_mq_update_nr_requests(struct request_queue *q, unsigned int nr)
}
blk_mq_unquiesce_queue(q);
- blk_mq_unfreeze_queue(q);
return ret;
}
@@ -4793,8 +4794,10 @@ static void __blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set,
fallback:
blk_mq_update_queue_map(set);
list_for_each_entry(q, &set->tag_list, tag_set_list) {
+ struct queue_limits lim;
+
blk_mq_realloc_hw_ctxs(set, q);
- blk_mq_update_poll_flag(q);
+
if (q->nr_hw_queues != set->nr_hw_queues) {
int i = prev_nr_hw_queues;
@@ -4806,6 +4809,13 @@ fallback:
set->nr_hw_queues = prev_nr_hw_queues;
goto fallback;
}
+ lim = queue_limits_start_update(q);
+ if (blk_mq_can_poll(set))
+ lim.features |= BLK_FEAT_POLL;
+ else
+ lim.features &= ~BLK_FEAT_POLL;
+ if (queue_limits_commit_update(q, &lim) < 0)
+ pr_warn("updating the poll flag failed\n");
blk_mq_map_swqueue(q);
}
diff --git a/block/blk-settings.c b/block/blk-settings.c
index 377a86fe0fcc..9c7f101aaf52 100644
--- a/block/blk-settings.c
+++ b/block/blk-settings.c
@@ -68,7 +68,7 @@ static void blk_apply_bdi_limits(struct backing_dev_info *bdi,
static int blk_validate_zoned_limits(struct queue_limits *lim)
{
- if (!lim->zoned) {
+ if (!(lim->features & BLK_FEAT_ZONED)) {
if (WARN_ON_ONCE(lim->max_open_zones) ||
WARN_ON_ONCE(lim->max_active_zones) ||
WARN_ON_ONCE(lim->zone_write_granularity) ||
@@ -269,6 +269,9 @@ static int blk_validate_limits(struct queue_limits *lim)
lim->misaligned = 0;
}
+ if (!(lim->features & BLK_FEAT_WRITE_CACHE))
+ lim->features &= ~BLK_FEAT_FUA;
+
err = blk_validate_integrity_limits(lim);
if (err)
return err;
@@ -461,6 +464,19 @@ int blk_stack_limits(struct queue_limits *t, struct queue_limits *b,
{
unsigned int top, bottom, alignment, ret = 0;
+ t->features |= (b->features & BLK_FEAT_INHERIT_MASK);
+
+ /*
+ * BLK_FEAT_NOWAIT and BLK_FEAT_POLL need to be supported both by the
+ * stacking driver and all underlying devices. The stacking driver sets
+ * the flags before stacking the limits, and this will clear the flags
+ * if any of the underlying devices does not support it.
+ */
+ if (!(b->features & BLK_FEAT_NOWAIT))
+ t->features &= ~BLK_FEAT_NOWAIT;
+ if (!(b->features & BLK_FEAT_POLL))
+ t->features &= ~BLK_FEAT_POLL;
+
t->max_sectors = min_not_zero(t->max_sectors, b->max_sectors);
t->max_user_sectors = min_not_zero(t->max_user_sectors,
b->max_user_sectors);
@@ -470,7 +486,6 @@ int blk_stack_limits(struct queue_limits *t, struct queue_limits *b,
b->max_write_zeroes_sectors);
t->max_zone_append_sectors = min(queue_limits_max_zone_append_sectors(t),
queue_limits_max_zone_append_sectors(b));
- t->bounce = max(t->bounce, b->bounce);
t->seg_boundary_mask = min_not_zero(t->seg_boundary_mask,
b->seg_boundary_mask);
@@ -593,8 +608,7 @@ int blk_stack_limits(struct queue_limits *t, struct queue_limits *b,
b->max_secure_erase_sectors);
t->zone_write_granularity = max(t->zone_write_granularity,
b->zone_write_granularity);
- t->zoned = max(t->zoned, b->zoned);
- if (!t->zoned) {
+ if (!(t->features & BLK_FEAT_ZONED)) {
t->zone_write_granularity = 0;
t->max_zone_append_sectors = 0;
}
@@ -718,30 +732,6 @@ void blk_set_queue_depth(struct request_queue *q, unsigned int depth)
}
EXPORT_SYMBOL(blk_set_queue_depth);
-/**
- * blk_queue_write_cache - configure queue's write cache
- * @q: the request queue for the device
- * @wc: write back cache on or off
- * @fua: device supports FUA writes, if true
- *
- * Tell the block layer about the write cache of @q.
- */
-void blk_queue_write_cache(struct request_queue *q, bool wc, bool fua)
-{
- if (wc) {
- blk_queue_flag_set(QUEUE_FLAG_HW_WC, q);
- blk_queue_flag_set(QUEUE_FLAG_WC, q);
- } else {
- blk_queue_flag_clear(QUEUE_FLAG_HW_WC, q);
- blk_queue_flag_clear(QUEUE_FLAG_WC, q);
- }
- if (fua)
- blk_queue_flag_set(QUEUE_FLAG_FUA, q);
- else
- blk_queue_flag_clear(QUEUE_FLAG_FUA, q);
-}
-EXPORT_SYMBOL_GPL(blk_queue_write_cache);
-
int bdev_alignment_offset(struct block_device *bdev)
{
struct request_queue *q = bdev_get_queue(bdev);
diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c
index f0f9314ab65c..da4e96d686f9 100644
--- a/block/blk-sysfs.c
+++ b/block/blk-sysfs.c
@@ -189,12 +189,9 @@ static ssize_t queue_discard_max_store(struct request_queue *q,
if ((max_discard_bytes >> SECTOR_SHIFT) > UINT_MAX)
return -EINVAL;
- blk_mq_freeze_queue(q);
lim = queue_limits_start_update(q);
lim.max_user_discard_sectors = max_discard_bytes >> SECTOR_SHIFT;
err = queue_limits_commit_update(q, &lim);
- blk_mq_unfreeze_queue(q);
-
if (err)
return err;
return ret;
@@ -241,11 +238,9 @@ queue_max_sectors_store(struct request_queue *q, const char *page, size_t count)
if (ret < 0)
return ret;
- blk_mq_freeze_queue(q);
lim = queue_limits_start_update(q);
lim.max_user_sectors = max_sectors_kb << 1;
err = queue_limits_commit_update(q, &lim);
- blk_mq_unfreeze_queue(q);
if (err)
return err;
return ret;
@@ -268,37 +263,43 @@ static ssize_t queue_dma_alignment_show(struct request_queue *q, char *page)
return queue_var_show(queue_dma_alignment(q), page);
}
-#define QUEUE_SYSFS_BIT_FNS(name, flag, neg) \
-static ssize_t \
-queue_##name##_show(struct request_queue *q, char *page) \
-{ \
- int bit; \
- bit = test_bit(QUEUE_FLAG_##flag, &q->queue_flags); \
- return queue_var_show(neg ? !bit : bit, page); \
-} \
-static ssize_t \
-queue_##name##_store(struct request_queue *q, const char *page, size_t count) \
-{ \
- unsigned long val; \
- ssize_t ret; \
- ret = queue_var_store(&val, page, count); \
- if (ret < 0) \
- return ret; \
- if (neg) \
- val = !val; \
- \
- if (val) \
- blk_queue_flag_set(QUEUE_FLAG_##flag, q); \
- else \
- blk_queue_flag_clear(QUEUE_FLAG_##flag, q); \
- return ret; \
-}
-
-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_feature_store(struct request_queue *q, const char *page,
+ size_t count, unsigned int feature)
+{
+ struct queue_limits lim;
+ unsigned long val;
+ ssize_t ret;
+
+ ret = queue_var_store(&val, page, count);
+ if (ret < 0)
+ return ret;
+
+ lim = queue_limits_start_update(q);
+ if (val)
+ lim.features |= feature;
+ else
+ lim.features &= ~feature;
+ ret = queue_limits_commit_update(q, &lim);
+ if (ret)
+ return ret;
+ return count;
+}
+
+#define QUEUE_SYSFS_FEATURE(_name, _feature) \
+static ssize_t queue_##_name##_show(struct request_queue *q, char *page) \
+{ \
+ return sprintf(page, "%u\n", !!(q->limits.features & _feature)); \
+} \
+static ssize_t queue_##_name##_store(struct request_queue *q, \
+ const char *page, size_t count) \
+{ \
+ return queue_feature_store(q, page, count, _feature); \
+}
+
+QUEUE_SYSFS_FEATURE(rotational, BLK_FEAT_ROTATIONAL)
+QUEUE_SYSFS_FEATURE(add_random, BLK_FEAT_ADD_RANDOM)
+QUEUE_SYSFS_FEATURE(iostats, BLK_FEAT_IO_STAT)
+QUEUE_SYSFS_FEATURE(stable_writes, BLK_FEAT_STABLE_WRITES);
static ssize_t queue_zoned_show(struct request_queue *q, char *page)
{
@@ -393,13 +394,13 @@ static ssize_t queue_poll_delay_store(struct request_queue *q, const char *page,
static ssize_t queue_poll_show(struct request_queue *q, char *page)
{
- return queue_var_show(test_bit(QUEUE_FLAG_POLL, &q->queue_flags), page);
+ return queue_var_show(q->limits.features & BLK_FEAT_POLL, page);
}
static ssize_t queue_poll_store(struct request_queue *q, const char *page,
size_t count)
{
- if (!test_bit(QUEUE_FLAG_POLL, &q->queue_flags))
+ if (!(q->limits.features & BLK_FEAT_POLL))
return -EINVAL;
pr_info_ratelimited("writes to the poll attribute are ignored.\n");
pr_info_ratelimited("please use driver specific parameters instead.\n");
@@ -428,32 +429,41 @@ static ssize_t queue_io_timeout_store(struct request_queue *q, const char *page,
static ssize_t queue_wc_show(struct request_queue *q, char *page)
{
- if (test_bit(QUEUE_FLAG_WC, &q->queue_flags))
- return sprintf(page, "write back\n");
-
- return sprintf(page, "write through\n");
+ if (q->limits.features & BLK_FLAGS_WRITE_CACHE_DISABLED)
+ return sprintf(page, "write through\n");
+ return sprintf(page, "write back\n");
}
static ssize_t queue_wc_store(struct request_queue *q, const char *page,
size_t count)
{
+ struct queue_limits lim;
+ bool disable;
+ int err;
+
if (!strncmp(page, "write back", 10)) {
- if (!test_bit(QUEUE_FLAG_HW_WC, &q->queue_flags))
- return -EINVAL;
- blk_queue_flag_set(QUEUE_FLAG_WC, q);
+ disable = false;
} else if (!strncmp(page, "write through", 13) ||
- !strncmp(page, "none", 4)) {
- blk_queue_flag_clear(QUEUE_FLAG_WC, q);
+ !strncmp(page, "none", 4)) {
+ disable = true;
} else {
return -EINVAL;
}
+ lim = queue_limits_start_update(q);
+ if (disable)
+ lim.flags |= BLK_FLAGS_WRITE_CACHE_DISABLED;
+ else
+ lim.flags &= ~BLK_FLAGS_WRITE_CACHE_DISABLED;
+ err = queue_limits_commit_update(q, &lim);
+ if (err)
+ return err;
return count;
}
static ssize_t queue_fua_show(struct request_queue *q, char *page)
{
- return sprintf(page, "%u\n", test_bit(QUEUE_FLAG_FUA, &q->queue_flags));
+ return sprintf(page, "%u\n", !!(q->limits.features & BLK_FEAT_FUA));
}
static ssize_t queue_dax_show(struct request_queue *q, char *page)
@@ -522,9 +532,9 @@ static struct queue_sysfs_entry queue_hw_sector_size_entry = {
.show = queue_logical_block_size_show,
};
-QUEUE_RW_ENTRY(queue_nonrot, "rotational");
+QUEUE_RW_ENTRY(queue_rotational, "rotational");
QUEUE_RW_ENTRY(queue_iostats, "iostats");
-QUEUE_RW_ENTRY(queue_random, "add_random");
+QUEUE_RW_ENTRY(queue_add_random, "add_random");
QUEUE_RW_ENTRY(queue_stable_writes, "stable_writes");
#ifdef CONFIG_BLK_WBT
@@ -585,13 +595,11 @@ static ssize_t queue_wb_lat_store(struct request_queue *q, const char *page,
* ends up either enabling or disabling wbt completely. We can't
* have IO inflight if that happens.
*/
- blk_mq_freeze_queue(q);
blk_mq_quiesce_queue(q);
wbt_set_min_lat(q, val);
blk_mq_unquiesce_queue(q);
- blk_mq_unfreeze_queue(q);
return count;
}
@@ -622,7 +630,7 @@ static struct attribute *queue_attrs[] = {
&queue_write_zeroes_max_entry.attr,
&queue_zone_append_max_entry.attr,
&queue_zone_write_granularity_entry.attr,
- &queue_nonrot_entry.attr,
+ &queue_rotational_entry.attr,
&queue_zoned_entry.attr,
&queue_nr_zones_entry.attr,
&queue_max_open_zones_entry.attr,
@@ -630,7 +638,7 @@ static struct attribute *queue_attrs[] = {
&queue_nomerges_entry.attr,
&queue_iostats_entry.attr,
&queue_stable_writes_entry.attr,
- &queue_random_entry.attr,
+ &queue_add_random_entry.attr,
&queue_poll_entry.attr,
&queue_wc_entry.attr,
&queue_fua_entry.attr,
@@ -722,9 +730,11 @@ queue_attr_store(struct kobject *kobj, struct attribute *attr,
if (!entry->store)
return -EIO;
+ blk_mq_freeze_queue(q);
mutex_lock(&q->sysfs_lock);
res = entry->store(q, page, length);
mutex_unlock(&q->sysfs_lock);
+ blk_mq_unfreeze_queue(q);
return res;
}
diff --git a/block/blk-wbt.c b/block/blk-wbt.c
index 64472134dd26..1a5e4b049ecd 100644
--- a/block/blk-wbt.c
+++ b/block/blk-wbt.c
@@ -206,8 +206,8 @@ static void wbt_rqw_done(struct rq_wb *rwb, struct rq_wait *rqw,
*/
if (wb_acct & WBT_DISCARD)
limit = rwb->wb_background;
- else if (test_bit(QUEUE_FLAG_WC, &rwb->rqos.disk->queue->queue_flags) &&
- !wb_recent_wait(rwb))
+ else if (blk_queue_write_cache(rwb->rqos.disk->queue) &&
+ !wb_recent_wait(rwb))
limit = 0;
else
limit = rwb->wb_normal;
diff --git a/block/blk.h b/block/blk.h
index 79e8d5d4fe0c..fa32f7fad5d7 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -394,7 +394,7 @@ struct bio *__blk_queue_bounce(struct bio *bio, struct request_queue *q);
static inline bool blk_queue_may_bounce(struct request_queue *q)
{
return IS_ENABLED(CONFIG_BOUNCE) &&
- q->limits.bounce == BLK_BOUNCE_HIGH &&
+ (q->limits.features & BLK_FEAT_BOUNCE_HIGH) &&
max_low_pfn >= max_pfn;
}
diff --git a/drivers/block/amiflop.c b/drivers/block/amiflop.c
index 310254c994aa..49ced65bef4c 100644
--- a/drivers/block/amiflop.c
+++ b/drivers/block/amiflop.c
@@ -1777,10 +1777,13 @@ static const struct blk_mq_ops amiflop_mq_ops = {
static int fd_alloc_disk(int drive, int system)
{
+ struct queue_limits lim = {
+ .features = BLK_FEAT_ROTATIONAL,
+ };
struct gendisk *disk;
int err;
- disk = blk_mq_alloc_disk(&unit[drive].tag_set, NULL, NULL);
+ disk = blk_mq_alloc_disk(&unit[drive].tag_set, &lim, NULL);
if (IS_ERR(disk))
return PTR_ERR(disk);
diff --git a/drivers/block/aoe/aoeblk.c b/drivers/block/aoe/aoeblk.c
index b6dac8cee70f..2028795ec61c 100644
--- a/drivers/block/aoe/aoeblk.c
+++ b/drivers/block/aoe/aoeblk.c
@@ -337,6 +337,7 @@ aoeblk_gdalloc(void *vp)
struct queue_limits lim = {
.max_hw_sectors = aoe_maxsectors,
.io_opt = SZ_2M,
+ .features = BLK_FEAT_ROTATIONAL,
};
ulong flags;
int late = 0;
diff --git a/drivers/block/ataflop.c b/drivers/block/ataflop.c
index b19884da4376..4ba98c6654be 100644
--- a/drivers/block/ataflop.c
+++ b/drivers/block/ataflop.c
@@ -1992,9 +1992,12 @@ static const struct blk_mq_ops ataflop_mq_ops = {
static int ataflop_alloc_disk(unsigned int drive, unsigned int type)
{
+ struct queue_limits lim = {
+ .features = BLK_FEAT_ROTATIONAL,
+ };
struct gendisk *disk;
- disk = blk_mq_alloc_disk(&unit[drive].tag_set, NULL, NULL);
+ disk = blk_mq_alloc_disk(&unit[drive].tag_set, &lim, NULL);
if (IS_ERR(disk))
return PTR_ERR(disk);
diff --git a/drivers/block/brd.c b/drivers/block/brd.c
index 558d8e670566..a300645cd9d4 100644
--- a/drivers/block/brd.c
+++ b/drivers/block/brd.c
@@ -335,6 +335,8 @@ static int brd_alloc(int i)
.max_hw_discard_sectors = UINT_MAX,
.max_discard_segments = 1,
.discard_granularity = PAGE_SIZE,
+ .features = BLK_FEAT_SYNCHRONOUS |
+ BLK_FEAT_NOWAIT,
};
list_for_each_entry(brd, &brd_devices, brd_list)
@@ -366,10 +368,6 @@ static int brd_alloc(int i)
strscpy(disk->disk_name, buf, DISK_NAME_LEN);
set_capacity(disk, rd_size * 2);
- /* Tell the block layer that this is not a rotational device */
- blk_queue_flag_set(QUEUE_FLAG_NONROT, disk->queue);
- blk_queue_flag_set(QUEUE_FLAG_SYNCHRONOUS, disk->queue);
- blk_queue_flag_set(QUEUE_FLAG_NOWAIT, disk->queue);
err = add_disk(disk);
if (err)
goto out_cleanup_disk;
diff --git a/drivers/block/drbd/drbd_main.c b/drivers/block/drbd/drbd_main.c
index 113b441d4d36..f92673f05c7a 100644
--- a/drivers/block/drbd/drbd_main.c
+++ b/drivers/block/drbd/drbd_main.c
@@ -2697,6 +2697,9 @@ enum drbd_ret_code drbd_create_device(struct drbd_config_context *adm_ctx, unsig
* connect.
*/
.max_hw_sectors = DRBD_MAX_BIO_SIZE_SAFE >> 8,
+ .features = BLK_FEAT_WRITE_CACHE | BLK_FEAT_FUA |
+ BLK_FEAT_ROTATIONAL |
+ BLK_FEAT_STABLE_WRITES,
};
device = minor_to_device(minor);
@@ -2735,9 +2738,6 @@ enum drbd_ret_code drbd_create_device(struct drbd_config_context *adm_ctx, unsig
sprintf(disk->disk_name, "drbd%d", minor);
disk->private_data = device;
- blk_queue_flag_set(QUEUE_FLAG_STABLE_WRITES, disk->queue);
- blk_queue_write_cache(disk->queue, true, true);
-
device->md_io.page = alloc_page(GFP_KERNEL);
if (!device->md_io.page)
goto out_no_io_page;
diff --git a/drivers/block/floppy.c b/drivers/block/floppy.c
index 25c9d85667f1..6d7f7df97c3a 100644
--- a/drivers/block/floppy.c
+++ b/drivers/block/floppy.c
@@ -4516,7 +4516,8 @@ static bool floppy_available(int drive)
static int floppy_alloc_disk(unsigned int drive, unsigned int type)
{
struct queue_limits lim = {
- .max_hw_sectors = 64,
+ .max_hw_sectors = 64,
+ .features = BLK_FEAT_ROTATIONAL,
};
struct gendisk *disk;
diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index 93780f41646b..86b5d956dc4e 100644
--- a/drivers/block/loop.c
+++ b/drivers/block/loop.c
@@ -916,24 +916,6 @@ static void loop_free_idle_workers_timer(struct timer_list *timer)
return loop_free_idle_workers(lo, false);
}
-static void loop_update_rotational(struct loop_device *lo)
-{
- struct file *file = lo->lo_backing_file;
- struct inode *file_inode = file->f_mapping->host;
- struct block_device *file_bdev = file_inode->i_sb->s_bdev;
- struct request_queue *q = lo->lo_queue;
- bool nonrot = true;
-
- /* not all filesystems (e.g. tmpfs) have a sb->s_bdev */
- if (file_bdev)
- nonrot = bdev_nonrot(file_bdev);
-
- if (nonrot)
- blk_queue_flag_set(QUEUE_FLAG_NONROT, q);
- else
- blk_queue_flag_clear(QUEUE_FLAG_NONROT, q);
-}
-
/**
* loop_set_status_from_info - configure device from loop_info
* @lo: struct loop_device to configure
@@ -975,17 +957,40 @@ loop_set_status_from_info(struct loop_device *lo,
return 0;
}
-static int loop_reconfigure_limits(struct loop_device *lo, unsigned short bsize,
- bool update_discard_settings)
+static unsigned short loop_default_blocksize(struct loop_device *lo,
+ struct block_device *backing_bdev)
+{
+ /* In case of direct I/O, match underlying block size */
+ if ((lo->lo_backing_file->f_flags & O_DIRECT) && backing_bdev)
+ return bdev_logical_block_size(backing_bdev);
+ return SECTOR_SIZE;
+}
+
+static int loop_reconfigure_limits(struct loop_device *lo, unsigned short bsize)
{
+ struct file *file = lo->lo_backing_file;
+ struct inode *inode = file->f_mapping->host;
+ struct block_device *backing_bdev = NULL;
struct queue_limits lim;
+ if (S_ISBLK(inode->i_mode))
+ backing_bdev = I_BDEV(inode);
+ else if (inode->i_sb->s_bdev)
+ backing_bdev = inode->i_sb->s_bdev;
+
+ if (!bsize)
+ bsize = loop_default_blocksize(lo, backing_bdev);
+
lim = queue_limits_start_update(lo->lo_queue);
lim.logical_block_size = bsize;
lim.physical_block_size = bsize;
lim.io_min = bsize;
- if (update_discard_settings)
- loop_config_discard(lo, &lim);
+ lim.features &= ~(BLK_FEAT_WRITE_CACHE | BLK_FEAT_ROTATIONAL);
+ if (file->f_op->fsync && !(lo->lo_flags & LO_FLAGS_READ_ONLY))
+ lim.features |= BLK_FEAT_WRITE_CACHE;
+ if (backing_bdev && !bdev_nonrot(backing_bdev))
+ lim.features |= BLK_FEAT_ROTATIONAL;
+ loop_config_discard(lo, &lim);
return queue_limits_commit_update(lo->lo_queue, &lim);
}
@@ -999,7 +1004,6 @@ static int loop_configure(struct loop_device *lo, blk_mode_t mode,
int error;
loff_t size;
bool partscan;
- unsigned short bsize;
bool is_loop;
if (!file)
@@ -1075,22 +1079,10 @@ static int loop_configure(struct loop_device *lo, blk_mode_t mode,
lo->old_gfp_mask = mapping_gfp_mask(mapping);
mapping_set_gfp_mask(mapping, lo->old_gfp_mask & ~(__GFP_IO|__GFP_FS));
- if (!(lo->lo_flags & LO_FLAGS_READ_ONLY) && file->f_op->fsync)
- blk_queue_write_cache(lo->lo_queue, true, false);
-
- if (config->block_size)
- bsize = config->block_size;
- else if ((lo->lo_backing_file->f_flags & O_DIRECT) && inode->i_sb->s_bdev)
- /* In case of direct I/O, match underlying block size */
- bsize = bdev_logical_block_size(inode->i_sb->s_bdev);
- else
- bsize = 512;
-
- error = loop_reconfigure_limits(lo, bsize, true);
+ error = loop_reconfigure_limits(lo, config->block_size);
if (WARN_ON_ONCE(error))
goto out_unlock;
- loop_update_rotational(lo);
loop_update_dio(lo);
loop_sysfs_init(lo);
@@ -1133,12 +1125,10 @@ out_putf:
static void __loop_clr_fd(struct loop_device *lo, bool release)
{
+ struct queue_limits lim;
struct file *filp;
gfp_t gfp = lo->old_gfp_mask;
- if (test_bit(QUEUE_FLAG_WC, &lo->lo_queue->queue_flags))
- blk_queue_write_cache(lo->lo_queue, false, false);
-
/*
* Freeze the request queue when unbinding on a live file descriptor and
* thus an open device. When called from ->release we are guaranteed
@@ -1156,7 +1146,14 @@ static void __loop_clr_fd(struct loop_device *lo, bool release)
lo->lo_offset = 0;
lo->lo_sizelimit = 0;
memset(lo->lo_file_name, 0, LO_NAME_SIZE);
- loop_reconfigure_limits(lo, 512, false);
+
+ /* reset the block size to the default */
+ lim = queue_limits_start_update(lo->lo_queue);
+ lim.logical_block_size = SECTOR_SIZE;
+ lim.physical_block_size = SECTOR_SIZE;
+ lim.io_min = SECTOR_SIZE;
+ queue_limits_commit_update(lo->lo_queue, &lim);
+
invalidate_disk(lo->lo_disk);
loop_sysfs_exit(lo);
/* let user-space know about this change */
@@ -1488,7 +1485,7 @@ static int loop_set_block_size(struct loop_device *lo, unsigned long arg)
invalidate_bdev(lo->lo_device);
blk_mq_freeze_queue(lo->lo_queue);
- err = loop_reconfigure_limits(lo, arg, false);
+ err = loop_reconfigure_limits(lo, arg);
loop_update_dio(lo);
blk_mq_unfreeze_queue(lo->lo_queue);
diff --git a/drivers/block/mtip32xx/mtip32xx.c b/drivers/block/mtip32xx/mtip32xx.c
index 43a187609ef7..c6ef0546ffc9 100644
--- a/drivers/block/mtip32xx/mtip32xx.c
+++ b/drivers/block/mtip32xx/mtip32xx.c
@@ -3485,8 +3485,6 @@ skip_create_disk:
goto start_service_thread;
/* Set device limits. */
- blk_queue_flag_set(QUEUE_FLAG_NONROT, dd->queue);
- blk_queue_flag_clear(QUEUE_FLAG_ADD_RANDOM, dd->queue);
dma_set_max_seg_size(&dd->pdev->dev, 0x400000);
/* Set the capacity of the device in 512 byte sectors. */
diff --git a/drivers/block/n64cart.c b/drivers/block/n64cart.c
index 27b2187e7a6d..b9fdeff31caf 100644
--- a/drivers/block/n64cart.c
+++ b/drivers/block/n64cart.c
@@ -150,8 +150,6 @@ static int __init n64cart_probe(struct platform_device *pdev)
set_capacity(disk, size >> SECTOR_SHIFT);
set_disk_ro(disk, 1);
- blk_queue_flag_set(QUEUE_FLAG_NONROT, disk->queue);
-
err = add_disk(disk);
if (err)
goto out_cleanup_disk;
diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c
index ad887d614d5b..6cddf5baffe0 100644
--- a/drivers/block/nbd.c
+++ b/drivers/block/nbd.c
@@ -342,6 +342,14 @@ static int __nbd_set_size(struct nbd_device *nbd, loff_t bytesize,
lim.max_hw_discard_sectors = UINT_MAX;
else
lim.max_hw_discard_sectors = 0;
+ if (!(nbd->config->flags & NBD_FLAG_SEND_FLUSH)) {
+ lim.features &= ~(BLK_FEAT_WRITE_CACHE | BLK_FEAT_FUA);
+ } else if (nbd->config->flags & NBD_FLAG_SEND_FUA) {
+ lim.features |= BLK_FEAT_WRITE_CACHE | BLK_FEAT_FUA;
+ } else {
+ lim.features |= BLK_FEAT_WRITE_CACHE;
+ lim.features &= ~BLK_FEAT_FUA;
+ }
lim.logical_block_size = blksize;
lim.physical_block_size = blksize;
error = queue_limits_commit_update(nbd->disk->queue, &lim);
@@ -1286,19 +1294,10 @@ static void nbd_bdev_reset(struct nbd_device *nbd)
static void nbd_parse_flags(struct nbd_device *nbd)
{
- struct nbd_config *config = nbd->config;
- if (config->flags & NBD_FLAG_READ_ONLY)
+ if (nbd->config->flags & NBD_FLAG_READ_ONLY)
set_disk_ro(nbd->disk, true);
else
set_disk_ro(nbd->disk, false);
- if (config->flags & NBD_FLAG_SEND_FLUSH) {
- if (config->flags & NBD_FLAG_SEND_FUA)
- blk_queue_write_cache(nbd->disk->queue, true, true);
- else
- blk_queue_write_cache(nbd->disk->queue, true, false);
- }
- else
- blk_queue_write_cache(nbd->disk->queue, false, false);
}
static void send_disconnects(struct nbd_device *nbd)
@@ -1868,11 +1867,6 @@ static struct nbd_device *nbd_dev_add(int index, unsigned int refs)
goto out_err_disk;
}
- /*
- * Tell the block layer that we are not a rotational device
- */
- blk_queue_flag_set(QUEUE_FLAG_NONROT, disk->queue);
-
mutex_init(&nbd->config_lock);
refcount_set(&nbd->config_refs, 0);
/*
diff --git a/drivers/block/null_blk/main.c b/drivers/block/null_blk/main.c
index 75f189e42f88..83a4ebe4763a 100644
--- a/drivers/block/null_blk/main.c
+++ b/drivers/block/null_blk/main.c
@@ -1928,6 +1928,13 @@ static int null_add_dev(struct nullb_device *dev)
goto out_cleanup_tags;
}
+ if (dev->cache_size > 0) {
+ set_bit(NULLB_DEV_FL_CACHE, &nullb->dev->flags);
+ lim.features |= BLK_FEAT_WRITE_CACHE;
+ if (dev->fua)
+ lim.features |= BLK_FEAT_FUA;
+ }
+
nullb->disk = blk_mq_alloc_disk(nullb->tag_set, &lim, nullb);
if (IS_ERR(nullb->disk)) {
rv = PTR_ERR(nullb->disk);
@@ -1940,13 +1947,7 @@ static int null_add_dev(struct nullb_device *dev)
nullb_setup_bwtimer(nullb);
}
- if (dev->cache_size > 0) {
- set_bit(NULLB_DEV_FL_CACHE, &nullb->dev->flags);
- blk_queue_write_cache(nullb->q, true, dev->fua);
- }
-
nullb->q->queuedata = nullb;
- blk_queue_flag_set(QUEUE_FLAG_NONROT, nullb->q);
rv = ida_alloc(&nullb_indexes, GFP_KERNEL);
if (rv < 0)
diff --git a/drivers/block/null_blk/zoned.c b/drivers/block/null_blk/zoned.c
index f118d304f310..b42c00f13132 100644
--- a/drivers/block/null_blk/zoned.c
+++ b/drivers/block/null_blk/zoned.c
@@ -158,7 +158,7 @@ int null_init_zoned_dev(struct nullb_device *dev,
sector += dev->zone_size_sects;
}
- lim->zoned = true;
+ lim->features |= BLK_FEAT_ZONED | BLK_FEAT_ZONE_RESETALL;
lim->chunk_sectors = dev->zone_size_sects;
lim->max_zone_append_sectors = dev->zone_append_max_sectors;
lim->max_open_zones = dev->zone_max_open;
@@ -171,7 +171,6 @@ int null_register_zoned_dev(struct nullb *nullb)
struct request_queue *q = nullb->q;
struct gendisk *disk = nullb->disk;
- blk_queue_flag_set(QUEUE_FLAG_ZONE_RESETALL, q);
disk->nr_zones = bdev_nr_zones(disk->part0);
pr_info("%s: using %s zone append\n",
diff --git a/drivers/block/pktcdvd.c b/drivers/block/pktcdvd.c
index 8a2ce8070010..7cece5884b9c 100644
--- a/drivers/block/pktcdvd.c
+++ b/drivers/block/pktcdvd.c
@@ -2622,6 +2622,7 @@ static int pkt_setup_dev(dev_t dev, dev_t* pkt_dev)
struct queue_limits lim = {
.max_hw_sectors = PACKET_MAX_SECTORS,
.logical_block_size = CD_FRAMESIZE,
+ .features = BLK_FEAT_ROTATIONAL,
};
int idx;
int ret = -ENOMEM;
diff --git a/drivers/block/ps3disk.c b/drivers/block/ps3disk.c
index b810ac0a5c4b..ff45ed766469 100644
--- a/drivers/block/ps3disk.c
+++ b/drivers/block/ps3disk.c
@@ -388,9 +388,9 @@ static int ps3disk_probe(struct ps3_system_bus_device *_dev)
.max_segments = -1,
.max_segment_size = dev->bounce_size,
.dma_alignment = dev->blk_size - 1,
+ .features = BLK_FEAT_WRITE_CACHE |
+ BLK_FEAT_ROTATIONAL,
};
-
- struct request_queue *queue;
struct gendisk *gendisk;
if (dev->blk_size < 512) {
@@ -447,10 +447,6 @@ static int ps3disk_probe(struct ps3_system_bus_device *_dev)
goto fail_free_tag_set;
}
- queue = gendisk->queue;
-
- blk_queue_write_cache(queue, true, false);
-
priv->gendisk = gendisk;
gendisk->major = ps3disk_major;
gendisk->first_minor = devidx * PS3DISK_MINORS;
diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c
index 22ad704f81d8..008e850555f4 100644
--- a/drivers/block/rbd.c
+++ b/drivers/block/rbd.c
@@ -4949,7 +4949,6 @@ static const struct blk_mq_ops rbd_mq_ops = {
static int rbd_init_disk(struct rbd_device *rbd_dev)
{
struct gendisk *disk;
- struct request_queue *q;
unsigned int objset_bytes =
rbd_dev->layout.object_size * rbd_dev->layout.stripe_count;
struct queue_limits lim = {
@@ -4979,12 +4978,14 @@ static int rbd_init_disk(struct rbd_device *rbd_dev)
lim.max_write_zeroes_sectors = objset_bytes >> SECTOR_SHIFT;
}
+ if (!ceph_test_opt(rbd_dev->rbd_client->client, NOCRC))
+ lim.features |= BLK_FEAT_STABLE_WRITES;
+
disk = blk_mq_alloc_disk(&rbd_dev->tag_set, &lim, rbd_dev);
if (IS_ERR(disk)) {
err = PTR_ERR(disk);
goto out_tag_set;
}
- q = disk->queue;
snprintf(disk->disk_name, sizeof(disk->disk_name), RBD_DRV_NAME "%d",
rbd_dev->dev_id);
@@ -4996,13 +4997,6 @@ static int rbd_init_disk(struct rbd_device *rbd_dev)
disk->minors = RBD_MINORS_PER_MAJOR;
disk->fops = &rbd_bd_ops;
disk->private_data = rbd_dev;
-
- blk_queue_flag_set(QUEUE_FLAG_NONROT, q);
- /* QUEUE_FLAG_ADD_RANDOM is off by default for blk-mq */
-
- if (!ceph_test_opt(rbd_dev->rbd_client->client, NOCRC))
- blk_queue_flag_set(QUEUE_FLAG_STABLE_WRITES, q);
-
rbd_dev->disk = disk;
return 0;
diff --git a/drivers/block/rnbd/rnbd-clt.c b/drivers/block/rnbd/rnbd-clt.c
index b7ffe03c6160..4918b0f68b46 100644
--- a/drivers/block/rnbd/rnbd-clt.c
+++ b/drivers/block/rnbd/rnbd-clt.c
@@ -1352,10 +1352,6 @@ static int rnbd_clt_setup_gen_disk(struct rnbd_clt_dev *dev,
if (dev->access_mode == RNBD_ACCESS_RO)
set_disk_ro(dev->gd, true);
- /*
- * Network device does not need rotational
- */
- blk_queue_flag_set(QUEUE_FLAG_NONROT, dev->queue);
err = add_disk(dev->gd);
if (err)
put_disk(dev->gd);
@@ -1389,6 +1385,12 @@ static int rnbd_client_setup_device(struct rnbd_clt_dev *dev,
le32_to_cpu(rsp->max_discard_sectors);
}
+ if (rsp->cache_policy & RNBD_WRITEBACK) {
+ lim.features |= BLK_FEAT_WRITE_CACHE;
+ if (rsp->cache_policy & RNBD_FUA)
+ lim.features |= BLK_FEAT_FUA;
+ }
+
dev->gd = blk_mq_alloc_disk(&dev->sess->tag_set, &lim, dev);
if (IS_ERR(dev->gd))
return PTR_ERR(dev->gd);
@@ -1397,10 +1399,6 @@ static int rnbd_client_setup_device(struct rnbd_clt_dev *dev,
blk_queue_flag_set(QUEUE_FLAG_SAME_COMP, dev->queue);
blk_queue_flag_set(QUEUE_FLAG_SAME_FORCE, dev->queue);
- blk_queue_write_cache(dev->queue,
- !!(rsp->cache_policy & RNBD_WRITEBACK),
- !!(rsp->cache_policy & RNBD_FUA));
-
return rnbd_clt_setup_gen_disk(dev, rsp, idx);
}
diff --git a/drivers/block/sunvdc.c b/drivers/block/sunvdc.c
index 5286cb8e0824..2d38331ee667 100644
--- a/drivers/block/sunvdc.c
+++ b/drivers/block/sunvdc.c
@@ -791,6 +791,7 @@ static int probe_disk(struct vdc_port *port)
.seg_boundary_mask = PAGE_SIZE - 1,
.max_segment_size = PAGE_SIZE,
.max_segments = port->ring_cookies,
+ .features = BLK_FEAT_ROTATIONAL,
};
struct request_queue *q;
struct gendisk *g;
diff --git a/drivers/block/swim.c b/drivers/block/swim.c
index 6731678f3a41..126f151c4f2c 100644
--- a/drivers/block/swim.c
+++ b/drivers/block/swim.c
@@ -787,6 +787,9 @@ static void swim_cleanup_floppy_disk(struct floppy_state *fs)
static int swim_floppy_init(struct swim_priv *swd)
{
+ struct queue_limits lim = {
+ .features = BLK_FEAT_ROTATIONAL,
+ };
int err;
int drive;
struct swim __iomem *base = swd->base;
@@ -820,7 +823,7 @@ static int swim_floppy_init(struct swim_priv *swd)
goto exit_put_disks;
swd->unit[drive].disk =
- blk_mq_alloc_disk(&swd->unit[drive].tag_set, NULL,
+ blk_mq_alloc_disk(&swd->unit[drive].tag_set, &lim,
&swd->unit[drive]);
if (IS_ERR(swd->unit[drive].disk)) {
blk_mq_free_tag_set(&swd->unit[drive].tag_set);
diff --git a/drivers/block/swim3.c b/drivers/block/swim3.c
index a04756ac778e..90be1017f7bf 100644
--- a/drivers/block/swim3.c
+++ b/drivers/block/swim3.c
@@ -1189,6 +1189,9 @@ static int swim3_add_device(struct macio_dev *mdev, int index)
static int swim3_attach(struct macio_dev *mdev,
const struct of_device_id *match)
{
+ struct queue_limits lim = {
+ .features = BLK_FEAT_ROTATIONAL,
+ };
struct floppy_state *fs;
struct gendisk *disk;
int rc;
@@ -1210,7 +1213,7 @@ static int swim3_attach(struct macio_dev *mdev,
if (rc)
goto out_unregister;
- disk = blk_mq_alloc_disk(&fs->tag_set, NULL, fs);
+ disk = blk_mq_alloc_disk(&fs->tag_set, &lim, fs);
if (IS_ERR(disk)) {
rc = PTR_ERR(disk);
goto out_free_tag_set;
diff --git a/drivers/block/ublk_drv.c b/drivers/block/ublk_drv.c
index 4e159948c912..4fdff13fc23b 100644
--- a/drivers/block/ublk_drv.c
+++ b/drivers/block/ublk_drv.c
@@ -248,8 +248,6 @@ static int ublk_dev_param_zoned_validate(const struct ublk_device *ub)
static void ublk_dev_param_zoned_apply(struct ublk_device *ub)
{
- blk_queue_flag_set(QUEUE_FLAG_ZONE_RESETALL, ub->ub_disk->queue);
-
ub->ub_disk->nr_zones = ublk_get_nr_zones(ub);
}
@@ -484,16 +482,8 @@ static inline unsigned ublk_pos_to_tag(loff_t pos)
static void ublk_dev_param_basic_apply(struct ublk_device *ub)
{
- struct request_queue *q = ub->ub_disk->queue;
const struct ublk_param_basic *p = &ub->params.basic;
- blk_queue_write_cache(q, p->attrs & UBLK_ATTR_VOLATILE_CACHE,
- p->attrs & UBLK_ATTR_FUA);
- if (p->attrs & UBLK_ATTR_ROTATIONAL)
- blk_queue_flag_clear(QUEUE_FLAG_NONROT, q);
- else
- blk_queue_flag_set(QUEUE_FLAG_NONROT, q);
-
if (p->attrs & UBLK_ATTR_READ_ONLY)
set_disk_ro(ub->ub_disk, true);
@@ -2204,12 +2194,21 @@ static int ublk_ctrl_start_dev(struct ublk_device *ub, struct io_uring_cmd *cmd)
if (!IS_ENABLED(CONFIG_BLK_DEV_ZONED))
return -EOPNOTSUPP;
- lim.zoned = true;
+ lim.features |= BLK_FEAT_ZONED | BLK_FEAT_ZONE_RESETALL;
lim.max_active_zones = p->max_active_zones;
lim.max_open_zones = p->max_open_zones;
lim.max_zone_append_sectors = p->max_zone_append_sectors;
}
+ if (ub->params.basic.attrs & UBLK_ATTR_VOLATILE_CACHE) {
+ lim.features |= BLK_FEAT_WRITE_CACHE;
+ if (ub->params.basic.attrs & UBLK_ATTR_FUA)
+ lim.features |= BLK_FEAT_FUA;
+ }
+
+ if (ub->params.basic.attrs & UBLK_ATTR_ROTATIONAL)
+ lim.features |= BLK_FEAT_ROTATIONAL;
+
if (wait_for_completion_interruptible(&ub->completion) != 0)
return -EINTR;
diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c
index 2351f411fa46..6c64a67ab9c9 100644
--- a/drivers/block/virtio_blk.c
+++ b/drivers/block/virtio_blk.c
@@ -728,7 +728,7 @@ static int virtblk_read_zoned_limits(struct virtio_blk *vblk,
dev_dbg(&vdev->dev, "probing host-managed zoned device\n");
- lim->zoned = true;
+ lim->features |= BLK_FEAT_ZONED | BLK_FEAT_ZONE_RESETALL;
virtio_cread(vdev, struct virtio_blk_config,
zoned.max_open_zones, &v);
@@ -1089,14 +1089,6 @@ static int virtblk_get_cache_mode(struct virtio_device *vdev)
return writeback;
}
-static void virtblk_update_cache_mode(struct virtio_device *vdev)
-{
- u8 writeback = virtblk_get_cache_mode(vdev);
- struct virtio_blk *vblk = vdev->priv;
-
- blk_queue_write_cache(vblk->disk->queue, writeback, false);
-}
-
static const char *const virtblk_cache_types[] = {
"write through", "write back"
};
@@ -1108,6 +1100,7 @@ cache_type_store(struct device *dev, struct device_attribute *attr,
struct gendisk *disk = dev_to_disk(dev);
struct virtio_blk *vblk = disk->private_data;
struct virtio_device *vdev = vblk->vdev;
+ struct queue_limits lim;
int i;
BUG_ON(!virtio_has_feature(vblk->vdev, VIRTIO_BLK_F_CONFIG_WCE));
@@ -1116,7 +1109,17 @@ cache_type_store(struct device *dev, struct device_attribute *attr,
return i;
virtio_cwrite8(vdev, offsetof(struct virtio_blk_config, wce), i);
- virtblk_update_cache_mode(vdev);
+
+ lim = queue_limits_start_update(disk->queue);
+ if (virtblk_get_cache_mode(vdev))
+ lim.features |= BLK_FEAT_WRITE_CACHE;
+ else
+ lim.features &= ~BLK_FEAT_WRITE_CACHE;
+ blk_mq_freeze_queue(disk->queue);
+ i = queue_limits_commit_update(disk->queue, &lim);
+ blk_mq_unfreeze_queue(disk->queue);
+ if (i)
+ return i;
return count;
}
@@ -1448,7 +1451,9 @@ static int virtblk_read_limits(struct virtio_blk *vblk,
static int virtblk_probe(struct virtio_device *vdev)
{
struct virtio_blk *vblk;
- struct queue_limits lim = { };
+ struct queue_limits lim = {
+ .features = BLK_FEAT_ROTATIONAL,
+ };
int err, index;
unsigned int queue_depth;
@@ -1512,6 +1517,9 @@ static int virtblk_probe(struct virtio_device *vdev)
if (err)
goto out_free_tags;
+ if (virtblk_get_cache_mode(vdev))
+ lim.features |= BLK_FEAT_WRITE_CACHE;
+
vblk->disk = blk_mq_alloc_disk(&vblk->tag_set, &lim, vblk);
if (IS_ERR(vblk->disk)) {
err = PTR_ERR(vblk->disk);
@@ -1527,9 +1535,6 @@ static int virtblk_probe(struct virtio_device *vdev)
vblk->disk->fops = &virtblk_fops;
vblk->index = index;
- /* configure queue flush support */
- virtblk_update_cache_mode(vdev);
-
/* If disk is read-only in the host, the guest should obey */
if (virtio_has_feature(vdev, VIRTIO_BLK_F_RO))
set_disk_ro(vblk->disk, 1);
@@ -1541,8 +1546,8 @@ static int virtblk_probe(struct virtio_device *vdev)
* All steps that follow use the VQs therefore they need to be
* placed after the virtio_device_ready() call above.
*/
- if (IS_ENABLED(CONFIG_BLK_DEV_ZONED) && lim.zoned) {
- blk_queue_flag_set(QUEUE_FLAG_ZONE_RESETALL, vblk->disk->queue);
+ if (IS_ENABLED(CONFIG_BLK_DEV_ZONED) &&
+ (lim.features & BLK_FEAT_ZONED)) {
err = blk_revalidate_disk_zones(vblk->disk);
if (err)
goto out_cleanup_disk;
diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c
index 9b4ec3e4908c..fa3a2ba52545 100644
--- a/drivers/block/xen-blkfront.c
+++ b/drivers/block/xen-blkfront.c
@@ -788,6 +788,11 @@ static int blkif_queue_rw_req(struct request *req, struct blkfront_ring_info *ri
* A barrier request a superset of FUA, so we can
* implement it the same way. (It's also a FLUSH+FUA,
* since it is guaranteed ordered WRT previous writes.)
+ *
+ * Note that can end up here with a FUA write and the
+ * flags cleared. This happens when the flag was
+ * run-time disabled after a failing I/O, and we'll
+ * simplify submit it as a normal write.
*/
if (info->feature_flush && info->feature_fua)
ring_req->operation =
@@ -795,8 +800,6 @@ static int blkif_queue_rw_req(struct request *req, struct blkfront_ring_info *ri
else if (info->feature_flush)
ring_req->operation =
BLKIF_OP_FLUSH_DISKCACHE;
- else
- ring_req->operation = 0;
}
ring_req->u.rw.nr_segments = num_grant;
if (unlikely(require_extra_req)) {
@@ -887,16 +890,6 @@ static inline void flush_requests(struct blkfront_ring_info *rinfo)
notify_remote_via_irq(rinfo->irq);
}
-static inline bool blkif_request_flush_invalid(struct request *req,
- struct blkfront_info *info)
-{
- return (blk_rq_is_passthrough(req) ||
- ((req_op(req) == REQ_OP_FLUSH) &&
- !info->feature_flush) ||
- ((req->cmd_flags & REQ_FUA) &&
- !info->feature_fua));
-}
-
static blk_status_t blkif_queue_rq(struct blk_mq_hw_ctx *hctx,
const struct blk_mq_queue_data *qd)
{
@@ -908,12 +901,22 @@ static blk_status_t blkif_queue_rq(struct blk_mq_hw_ctx *hctx,
rinfo = get_rinfo(info, qid);
blk_mq_start_request(qd->rq);
spin_lock_irqsave(&rinfo->ring_lock, flags);
- if (RING_FULL(&rinfo->ring))
- goto out_busy;
- if (blkif_request_flush_invalid(qd->rq, rinfo->dev_info))
- goto out_err;
+ /*
+ * Check if the backend actually supports flushes.
+ *
+ * While the block layer won't send us flushes if we don't claim to
+ * support them, the Xen protocol allows the backend to revoke support
+ * at any time. That is of course a really bad idea and dangerous, but
+ * has been allowed for 10+ years. In that case we simply clear the
+ * flags, and directly return here for an empty flush and ignore the
+ * FUA flag later on.
+ */
+ if (unlikely(req_op(qd->rq) == REQ_OP_FLUSH && !info->feature_flush))
+ goto complete;
+ if (RING_FULL(&rinfo->ring))
+ goto out_busy;
if (blkif_queue_request(qd->rq, rinfo))
goto out_busy;
@@ -921,14 +924,14 @@ static blk_status_t blkif_queue_rq(struct blk_mq_hw_ctx *hctx,
spin_unlock_irqrestore(&rinfo->ring_lock, flags);
return BLK_STS_OK;
-out_err:
- spin_unlock_irqrestore(&rinfo->ring_lock, flags);
- return BLK_STS_IOERR;
-
out_busy:
blk_mq_stop_hw_queue(hctx);
spin_unlock_irqrestore(&rinfo->ring_lock, flags);
return BLK_STS_DEV_RESOURCE;
+complete:
+ spin_unlock_irqrestore(&rinfo->ring_lock, flags);
+ blk_mq_end_request(qd->rq, BLK_STS_OK);
+ return BLK_STS_OK;
}
static void blkif_complete_rq(struct request *rq)
@@ -956,6 +959,12 @@ static void blkif_set_queue_limits(const struct blkfront_info *info,
lim->max_secure_erase_sectors = UINT_MAX;
}
+ if (info->feature_flush) {
+ lim->features |= BLK_FEAT_WRITE_CACHE;
+ if (info->feature_fua)
+ lim->features |= BLK_FEAT_FUA;
+ }
+
/* Hard sector size and max sectors impersonate the equiv. hardware. */
lim->logical_block_size = info->sector_size;
lim->physical_block_size = info->physical_sector_size;
@@ -984,8 +993,6 @@ static const char *flush_info(struct blkfront_info *info)
static void xlvbd_flush(struct blkfront_info *info)
{
- blk_queue_write_cache(info->rq, info->feature_flush ? true : false,
- info->feature_fua ? true : false);
pr_info("blkfront: %s: %s %s %s %s %s %s %s\n",
info->gd->disk_name, flush_info(info),
"persistent grants:", info->feature_persistent ?
@@ -1139,7 +1146,6 @@ static int xlvbd_alloc_gendisk(blkif_sector_t capacity,
err = PTR_ERR(gd);
goto out_free_tag_set;
}
- blk_queue_flag_set(QUEUE_FLAG_VIRT, gd->queue);
strcpy(gd->disk_name, DEV_NAME);
ptr = encode_disk_name(gd->disk_name + sizeof(DEV_NAME) - 1, offset);
@@ -1627,7 +1633,6 @@ static irqreturn_t blkif_interrupt(int irq, void *dev_id)
blkif_req(req)->error = BLK_STS_OK;
info->feature_fua = 0;
info->feature_flush = 0;
- xlvbd_flush(info);
}
fallthrough;
case BLKIF_OP_READ:
diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c
index 3acd7006ad2c..efcb8d9d274c 100644
--- a/drivers/block/zram/zram_drv.c
+++ b/drivers/block/zram/zram_drv.c
@@ -2208,6 +2208,8 @@ static int zram_add(void)
#if ZRAM_LOGICAL_BLOCK_SIZE == PAGE_SIZE
.max_write_zeroes_sectors = UINT_MAX,
#endif
+ .features = BLK_FEAT_STABLE_WRITES |
+ BLK_FEAT_SYNCHRONOUS,
};
struct zram *zram;
int ret, device_id;
@@ -2245,10 +2247,6 @@ static int zram_add(void)
/* Actual capacity set using sysfs (/sys/block/zram<id>/disksize */
set_capacity(zram->disk, 0);
- /* zram devices sort of resembles non-rotational disks */
- blk_queue_flag_set(QUEUE_FLAG_NONROT, zram->disk->queue);
- blk_queue_flag_set(QUEUE_FLAG_SYNCHRONOUS, zram->disk->queue);
- blk_queue_flag_set(QUEUE_FLAG_STABLE_WRITES, zram->disk->queue);
ret = device_add_disk(NULL, zram->disk, zram_disk_groups);
if (ret)
goto out_cleanup_disk;
diff --git a/drivers/cdrom/gdrom.c b/drivers/cdrom/gdrom.c
index eefdd422ad8e..71cfe7a85913 100644
--- a/drivers/cdrom/gdrom.c
+++ b/drivers/cdrom/gdrom.c
@@ -744,6 +744,7 @@ static int probe_gdrom(struct platform_device *devptr)
.max_segments = 1,
/* set a large max size to get most from DMA */
.max_segment_size = 0x40000,
+ .features = BLK_FEAT_ROTATIONAL,
};
int err;
diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c
index 4d11fc664cb0..baa364eedd00 100644
--- a/drivers/md/bcache/super.c
+++ b/drivers/md/bcache/super.c
@@ -897,7 +897,6 @@ static int bcache_device_init(struct bcache_device *d, unsigned int block_size,
sector_t sectors, struct block_device *cached_bdev,
const struct block_device_operations *ops)
{
- struct request_queue *q;
const size_t max_stripes = min_t(size_t, INT_MAX,
SIZE_MAX / sizeof(atomic_t));
struct queue_limits lim = {
@@ -909,6 +908,7 @@ static int bcache_device_init(struct bcache_device *d, unsigned int block_size,
.io_min = block_size,
.logical_block_size = block_size,
.physical_block_size = block_size,
+ .features = BLK_FEAT_WRITE_CACHE | BLK_FEAT_FUA,
};
uint64_t n;
int idx;
@@ -974,13 +974,6 @@ static int bcache_device_init(struct bcache_device *d, unsigned int block_size,
d->disk->minors = BCACHE_MINORS;
d->disk->fops = ops;
d->disk->private_data = d;
-
- q = d->disk->queue;
-
- blk_queue_flag_set(QUEUE_FLAG_NONROT, d->disk->queue);
-
- blk_queue_write_cache(q, true, true);
-
return 0;
out_bioset_exit:
diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c
index 2805cd2b7c8b..29e4c6e970e3 100644
--- a/drivers/md/dm-table.c
+++ b/drivers/md/dm-table.c
@@ -579,6 +579,12 @@ int dm_split_args(int *argc, char ***argvp, char *input)
return 0;
}
+static void dm_set_stacking_limits(struct queue_limits *limits)
+{
+ blk_set_stacking_limits(limits);
+ limits->features |= BLK_FEAT_IO_STAT | BLK_FEAT_NOWAIT | BLK_FEAT_POLL;
+}
+
/*
* Impose necessary and sufficient conditions on a devices's table such
* that any incoming bio which respects its logical_block_size can be
@@ -617,7 +623,7 @@ static int validate_hardware_logical_block_alignment(struct dm_table *t,
for (i = 0; i < t->num_targets; i++) {
ti = dm_table_get_target(t, i);
- blk_set_stacking_limits(&ti_limits);
+ dm_set_stacking_limits(&ti_limits);
/* combine all target devices' limits */
if (ti->type->iterate_devices)
@@ -1018,14 +1024,13 @@ bool dm_table_request_based(struct dm_table *t)
return __table_type_request_based(dm_table_get_type(t));
}
-static bool dm_table_supports_poll(struct dm_table *t);
-
static int dm_table_alloc_md_mempools(struct dm_table *t, struct mapped_device *md)
{
enum dm_queue_mode type = dm_table_get_type(t);
unsigned int per_io_data_size = 0, front_pad, io_front_pad;
unsigned int min_pool_size = 0, pool_size;
struct dm_md_mempools *pools;
+ unsigned int bioset_flags = 0;
if (unlikely(type == DM_TYPE_NONE)) {
DMERR("no table type is set, can't allocate mempools");
@@ -1042,6 +1047,9 @@ static int dm_table_alloc_md_mempools(struct dm_table *t, struct mapped_device *
goto init_bs;
}
+ if (md->queue->limits.features & BLK_FEAT_POLL)
+ bioset_flags |= BIOSET_PERCPU_CACHE;
+
for (unsigned int i = 0; i < t->num_targets; i++) {
struct dm_target *ti = dm_table_get_target(t, i);
@@ -1054,8 +1062,7 @@ static int dm_table_alloc_md_mempools(struct dm_table *t, struct mapped_device *
io_front_pad = roundup(per_io_data_size,
__alignof__(struct dm_io)) + DM_IO_BIO_OFFSET;
- if (bioset_init(&pools->io_bs, pool_size, io_front_pad,
- dm_table_supports_poll(t) ? BIOSET_PERCPU_CACHE : 0))
+ if (bioset_init(&pools->io_bs, pool_size, io_front_pad, bioset_flags))
goto out_free_pools;
if (t->integrity_supported &&
bioset_integrity_create(&pools->io_bs, pool_size))
@@ -1398,14 +1405,6 @@ struct dm_target *dm_table_find_target(struct dm_table *t, sector_t sector)
return &t->targets[(KEYS_PER_NODE * n) + k];
}
-static int device_not_poll_capable(struct dm_target *ti, struct dm_dev *dev,
- sector_t start, sector_t len, void *data)
-{
- struct request_queue *q = bdev_get_queue(dev->bdev);
-
- return !test_bit(QUEUE_FLAG_POLL, &q->queue_flags);
-}
-
/*
* type->iterate_devices() should be called when the sanity check needs to
* iterate and check all underlying data devices. iterate_devices() will
@@ -1453,19 +1452,6 @@ static int count_device(struct dm_target *ti, struct dm_dev *dev,
return 0;
}
-static bool dm_table_supports_poll(struct dm_table *t)
-{
- for (unsigned int i = 0; i < t->num_targets; i++) {
- struct dm_target *ti = dm_table_get_target(t, i);
-
- if (!ti->type->iterate_devices ||
- ti->type->iterate_devices(ti, device_not_poll_capable, NULL))
- return false;
- }
-
- return true;
-}
-
/*
* Check whether a table has no data devices attached using each
* target's iterate_devices method.
@@ -1591,7 +1577,7 @@ int dm_calculate_queue_limits(struct dm_table *t,
unsigned int zone_sectors = 0;
bool zoned = false;
- blk_set_stacking_limits(limits);
+ dm_set_stacking_limits(limits);
t->integrity_supported = true;
for (unsigned int i = 0; i < t->num_targets; i++) {
@@ -1604,7 +1590,7 @@ int dm_calculate_queue_limits(struct dm_table *t,
for (unsigned int i = 0; i < t->num_targets; i++) {
struct dm_target *ti = dm_table_get_target(t, i);
- blk_set_stacking_limits(&ti_limits);
+ dm_set_stacking_limits(&ti_limits);
if (!ti->type->iterate_devices) {
/* Set I/O hints portion of queue limits */
@@ -1619,12 +1605,12 @@ int dm_calculate_queue_limits(struct dm_table *t,
ti->type->iterate_devices(ti, dm_set_device_limits,
&ti_limits);
- if (!zoned && ti_limits.zoned) {
+ if (!zoned && (ti_limits.features & BLK_FEAT_ZONED)) {
/*
* After stacking all limits, validate all devices
* in table support this zoned model and zone sectors.
*/
- zoned = ti_limits.zoned;
+ zoned = (ti_limits.features & BLK_FEAT_ZONED);
zone_sectors = ti_limits.chunk_sectors;
}
@@ -1672,12 +1658,12 @@ combine_limits:
* zoned model on host-managed zoned block devices.
* BUT...
*/
- if (limits->zoned) {
+ if (limits->features & BLK_FEAT_ZONED) {
/*
* ...IF the above limits stacking determined a zoned model
* validate that all of the table's devices conform to it.
*/
- zoned = limits->zoned;
+ zoned = limits->features & BLK_FEAT_ZONED;
zone_sectors = limits->chunk_sectors;
}
if (validate_hardware_zoned(t, zoned, zone_sectors))
@@ -1686,34 +1672,16 @@ combine_limits:
return validate_hardware_logical_block_alignment(t, limits);
}
-static int device_flush_capable(struct dm_target *ti, struct dm_dev *dev,
- sector_t start, sector_t len, void *data)
-{
- unsigned long flush = (unsigned long) data;
- struct request_queue *q = bdev_get_queue(dev->bdev);
-
- return (q->queue_flags & flush);
-}
-
-static bool dm_table_supports_flush(struct dm_table *t, unsigned long flush)
+/*
+ * Check if a target requires flush support even if none of the underlying
+ * devices need it (e.g. to persist target-specific metadata).
+ */
+static bool dm_table_supports_flush(struct dm_table *t)
{
- /*
- * Require at least one underlying device to support flushes.
- * t->devices includes internal dm devices such as mirror logs
- * so we need to use iterate_devices here, which targets
- * supporting flushes must provide.
- */
for (unsigned int i = 0; i < t->num_targets; i++) {
struct dm_target *ti = dm_table_get_target(t, i);
- if (!ti->num_flush_bios)
- continue;
-
- if (ti->flush_supported)
- return true;
-
- if (ti->type->iterate_devices &&
- ti->type->iterate_devices(ti, device_flush_capable, (void *) flush))
+ if (ti->num_flush_bios && ti->flush_supported)
return true;
}
@@ -1734,20 +1702,6 @@ static int device_dax_write_cache_enabled(struct dm_target *ti,
return false;
}
-static int device_is_rotational(struct dm_target *ti, struct dm_dev *dev,
- sector_t start, sector_t len, void *data)
-{
- return !bdev_nonrot(dev->bdev);
-}
-
-static int device_is_not_random(struct dm_target *ti, struct dm_dev *dev,
- sector_t start, sector_t len, void *data)
-{
- struct request_queue *q = bdev_get_queue(dev->bdev);
-
- return !blk_queue_add_random(q);
-}
-
static int device_not_write_zeroes_capable(struct dm_target *ti, struct dm_dev *dev,
sector_t start, sector_t len, void *data)
{
@@ -1772,12 +1726,6 @@ static bool dm_table_supports_write_zeroes(struct dm_table *t)
return true;
}
-static int device_not_nowait_capable(struct dm_target *ti, struct dm_dev *dev,
- sector_t start, sector_t len, void *data)
-{
- return !bdev_nowait(dev->bdev);
-}
-
static bool dm_table_supports_nowait(struct dm_table *t)
{
for (unsigned int i = 0; i < t->num_targets; i++) {
@@ -1785,10 +1733,6 @@ static bool dm_table_supports_nowait(struct dm_table *t)
if (!dm_target_supports_nowait(ti->type))
return false;
-
- if (!ti->type->iterate_devices ||
- ti->type->iterate_devices(ti, device_not_nowait_capable, NULL))
- return false;
}
return true;
@@ -1845,23 +1789,20 @@ static bool dm_table_supports_secure_erase(struct dm_table *t)
return true;
}
-static int device_requires_stable_pages(struct dm_target *ti,
- struct dm_dev *dev, sector_t start,
- sector_t len, void *data)
-{
- return bdev_stable_writes(dev->bdev);
-}
-
int dm_table_set_restrictions(struct dm_table *t, struct request_queue *q,
struct queue_limits *limits)
{
- bool wc = false, fua = false;
int r;
- if (dm_table_supports_nowait(t))
- blk_queue_flag_set(QUEUE_FLAG_NOWAIT, q);
- else
- blk_queue_flag_clear(QUEUE_FLAG_NOWAIT, q);
+ if (!dm_table_supports_nowait(t))
+ limits->features &= ~BLK_FEAT_NOWAIT;
+
+ /*
+ * The current polling impementation does not support request based
+ * stacking.
+ */
+ if (!__table_type_bio_based(t->type))
+ limits->features &= ~BLK_FEAT_POLL;
if (!dm_table_supports_discards(t)) {
limits->max_hw_discard_sectors = 0;
@@ -1876,53 +1817,22 @@ int dm_table_set_restrictions(struct dm_table *t, struct request_queue *q,
if (!dm_table_supports_secure_erase(t))
limits->max_secure_erase_sectors = 0;
- if (dm_table_supports_flush(t, (1UL << QUEUE_FLAG_WC))) {
- wc = true;
- if (dm_table_supports_flush(t, (1UL << QUEUE_FLAG_FUA)))
- fua = true;
- }
- blk_queue_write_cache(q, wc, fua);
+ if (dm_table_supports_flush(t))
+ limits->features |= BLK_FEAT_WRITE_CACHE | BLK_FEAT_FUA;
if (dm_table_supports_dax(t, device_not_dax_capable)) {
- blk_queue_flag_set(QUEUE_FLAG_DAX, q);
+ limits->features |= BLK_FEAT_DAX;
if (dm_table_supports_dax(t, device_not_dax_synchronous_capable))
set_dax_synchronous(t->md->dax_dev);
} else
- blk_queue_flag_clear(QUEUE_FLAG_DAX, q);
+ limits->features &= ~BLK_FEAT_DAX;
if (dm_table_any_dev_attr(t, device_dax_write_cache_enabled, NULL))
dax_write_cache(t->md->dax_dev, true);
- /* Ensure that all underlying devices are non-rotational. */
- if (dm_table_any_dev_attr(t, device_is_rotational, NULL))
- blk_queue_flag_clear(QUEUE_FLAG_NONROT, q);
- else
- blk_queue_flag_set(QUEUE_FLAG_NONROT, q);
-
- /*
- * Some devices don't use blk_integrity but still want stable pages
- * because they do their own checksumming.
- * If any underlying device requires stable pages, a table must require
- * them as well. Only targets that support iterate_devices are considered:
- * don't want error, zero, etc to require stable pages.
- */
- if (dm_table_any_dev_attr(t, device_requires_stable_pages, NULL))
- blk_queue_flag_set(QUEUE_FLAG_STABLE_WRITES, q);
- else
- blk_queue_flag_clear(QUEUE_FLAG_STABLE_WRITES, q);
-
- /*
- * Determine whether or not this queue's I/O timings contribute
- * to the entropy pool, Only request-based targets use this.
- * Clear QUEUE_FLAG_ADD_RANDOM if any underlying device does not
- * have it set.
- */
- if (blk_queue_add_random(q) &&
- dm_table_any_dev_attr(t, device_is_not_random, NULL))
- blk_queue_flag_clear(QUEUE_FLAG_ADD_RANDOM, q);
-
/* For a zoned table, setup the zone related queue attributes. */
- if (IS_ENABLED(CONFIG_BLK_DEV_ZONED) && limits->zoned) {
+ if (IS_ENABLED(CONFIG_BLK_DEV_ZONED) &&
+ (limits->features & BLK_FEAT_ZONED)) {
r = dm_set_zones_restrictions(t, q, limits);
if (r)
return r;
@@ -1936,28 +1846,14 @@ int dm_table_set_restrictions(struct dm_table *t, struct request_queue *q,
* Now that the limits are set, check the zones mapped by the table
* and setup the resources for zone append emulation if necessary.
*/
- if (IS_ENABLED(CONFIG_BLK_DEV_ZONED) && limits->zoned) {
+ if (IS_ENABLED(CONFIG_BLK_DEV_ZONED) &&
+ (limits->features & BLK_FEAT_ZONED)) {
r = dm_revalidate_zones(t, q);
if (r)
return r;
}
dm_update_crypto_profile(q, t);
-
- /*
- * Check for request-based device is left to
- * dm_mq_init_request_queue()->blk_mq_init_allocated_queue().
- *
- * For bio-based device, only set QUEUE_FLAG_POLL when all
- * underlying devices supporting polling.
- */
- if (__table_type_bio_based(t->type)) {
- if (dm_table_supports_poll(t))
- blk_queue_flag_set(QUEUE_FLAG_POLL, q);
- else
- blk_queue_flag_clear(QUEUE_FLAG_POLL, q);
- }
-
return 0;
}
diff --git a/drivers/md/dm-zone.c b/drivers/md/dm-zone.c
index 70719bf32a2e..4d37e53b50ee 100644
--- a/drivers/md/dm-zone.c
+++ b/drivers/md/dm-zone.c
@@ -372,7 +372,7 @@ int dm_set_zones_restrictions(struct dm_table *t, struct request_queue *q,
lim->max_zone_append_sectors = 0;
lim->zone_write_granularity = 0;
lim->chunk_sectors = 0;
- lim->zoned = false;
+ lim->features &= ~BLK_FEAT_ZONED;
clear_bit(DMF_EMULATE_ZONE_APPEND, &md->flags);
md->nr_zones = 0;
disk->nr_zones = 0;
@@ -392,7 +392,8 @@ int dm_set_zones_restrictions(struct dm_table *t, struct request_queue *q,
DMWARN("%s zone resource limits may be unreliable",
disk->disk_name);
- if (lim->zoned && !static_key_enabled(&zoned_enabled.key))
+ if (lim->features & BLK_FEAT_ZONED &&
+ !static_key_enabled(&zoned_enabled.key))
static_branch_enable(&zoned_enabled);
return 0;
}
diff --git a/drivers/md/dm-zoned-target.c b/drivers/md/dm-zoned-target.c
index 12236e6f46f3..cd0ee144973f 100644
--- a/drivers/md/dm-zoned-target.c
+++ b/drivers/md/dm-zoned-target.c
@@ -1009,7 +1009,7 @@ static void dmz_io_hints(struct dm_target *ti, struct queue_limits *limits)
limits->max_sectors = chunk_sectors;
/* We are exposing a drive-managed zoned block device */
- limits->zoned = false;
+ limits->features &= ~BLK_FEAT_ZONED;
}
/*
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 13037d6a6f62..8a976cee448b 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -2386,22 +2386,15 @@ int dm_setup_md_queue(struct mapped_device *md, struct dm_table *t)
struct table_device *td;
int r;
- switch (type) {
- case DM_TYPE_REQUEST_BASED:
+ WARN_ON_ONCE(type == DM_TYPE_NONE);
+
+ if (type == DM_TYPE_REQUEST_BASED) {
md->disk->fops = &dm_rq_blk_dops;
r = dm_mq_init_request_queue(md, t);
if (r) {
DMERR("Cannot initialize queue for request-based dm mapped device");
return r;
}
- break;
- case DM_TYPE_BIO_BASED:
- case DM_TYPE_DAX_BIO_BASED:
- blk_queue_flag_set(QUEUE_FLAG_IO_STAT, md->queue);
- break;
- case DM_TYPE_NONE:
- WARN_ON_ONCE(true);
- break;
}
r = dm_calculate_queue_limits(t, &limits);
diff --git a/drivers/md/md.c b/drivers/md/md.c
index cf510a68705f..69ea54aedd99 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -5870,7 +5870,11 @@ struct mddev *md_alloc(dev_t dev, char *name)
int partitioned;
int shift;
int unit;
- int error ;
+ int error;
+ struct queue_limits lim = {
+ .features = BLK_FEAT_WRITE_CACHE | BLK_FEAT_FUA |
+ BLK_FEAT_IO_STAT | BLK_FEAT_NOWAIT,
+ };
/*
* Wait for any previous instance of this device to be completely
@@ -5910,7 +5914,7 @@ struct mddev *md_alloc(dev_t dev, char *name)
*/
mddev->hold_active = UNTIL_STOP;
- disk = blk_alloc_disk(NULL, NUMA_NO_NODE);
+ disk = blk_alloc_disk(&lim, NUMA_NO_NODE);
if (IS_ERR(disk)) {
error = PTR_ERR(disk);
goto out_free_mddev;
@@ -5928,7 +5932,6 @@ struct mddev *md_alloc(dev_t dev, char *name)
disk->fops = &md_fops;
disk->private_data = mddev;
- blk_queue_write_cache(disk->queue, true, true);
disk->events |= DISK_EVENT_MEDIA_CHANGE;
mddev->gendisk = disk;
error = add_disk(disk);
@@ -6232,28 +6235,6 @@ int md_run(struct mddev *mddev)
}
}
- if (!mddev_is_dm(mddev)) {
- struct request_queue *q = mddev->gendisk->queue;
- bool nonrot = true;
-
- rdev_for_each(rdev, mddev) {
- if (rdev->raid_disk >= 0 && !bdev_nonrot(rdev->bdev)) {
- nonrot = false;
- break;
- }
- }
- if (mddev->degraded)
- nonrot = false;
- if (nonrot)
- blk_queue_flag_set(QUEUE_FLAG_NONROT, q);
- else
- blk_queue_flag_clear(QUEUE_FLAG_NONROT, q);
- blk_queue_flag_set(QUEUE_FLAG_IO_STAT, q);
-
- /* Set the NOWAIT flags if all underlying devices support it */
- if (nowait)
- blk_queue_flag_set(QUEUE_FLAG_NOWAIT, q);
- }
if (pers->sync_request) {
if (mddev->kobj.sd &&
sysfs_create_group(&mddev->kobj, &md_redundancy_group))
@@ -7213,15 +7194,6 @@ static int hot_add_disk(struct mddev *mddev, dev_t dev)
if (!mddev->thread)
md_update_sb(mddev, 1);
/*
- * If the new disk does not support REQ_NOWAIT,
- * disable on the whole MD.
- */
- if (!bdev_nowait(rdev->bdev)) {
- pr_info("%s: Disabling nowait because %pg does not support nowait\n",
- mdname(mddev), rdev->bdev);
- blk_queue_flag_clear(QUEUE_FLAG_NOWAIT, mddev->gendisk->queue);
- }
- /*
* Kick recovery, maybe this spare has to be added to the
* array immediately.
*/
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index c62c4122942a..2668f9a962e9 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -7086,12 +7086,14 @@ raid5_store_skip_copy(struct mddev *mddev, const char *page, size_t len)
err = -ENODEV;
else if (new != conf->skip_copy) {
struct request_queue *q = mddev->gendisk->queue;
+ struct queue_limits lim = queue_limits_start_update(q);
conf->skip_copy = new;
if (new)
- blk_queue_flag_set(QUEUE_FLAG_STABLE_WRITES, q);
+ lim.features |= BLK_FEAT_STABLE_WRITES;
else
- blk_queue_flag_clear(QUEUE_FLAG_STABLE_WRITES, q);
+ lim.features &= ~BLK_FEAT_STABLE_WRITES;
+ err = queue_limits_commit_update(q, &lim);
}
mddev_unlock_and_resume(mddev);
return err ?: len;
diff --git a/drivers/mmc/core/block.c b/drivers/mmc/core/block.c
index 367509b5b646..2c9963248fcb 100644
--- a/drivers/mmc/core/block.c
+++ b/drivers/mmc/core/block.c
@@ -2466,8 +2466,7 @@ static struct mmc_blk_data *mmc_blk_alloc_req(struct mmc_card *card,
struct mmc_blk_data *md;
int devidx, ret;
char cap_str[10];
- bool cache_enabled = false;
- bool fua_enabled = false;
+ unsigned int features = 0;
devidx = ida_alloc_max(&mmc_blk_ida, max_devices - 1, GFP_KERNEL);
if (devidx < 0) {
@@ -2499,7 +2498,24 @@ static struct mmc_blk_data *mmc_blk_alloc_req(struct mmc_card *card,
*/
md->read_only = mmc_blk_readonly(card);
- md->disk = mmc_init_queue(&md->queue, card);
+ if (mmc_host_cmd23(card->host)) {
+ if ((mmc_card_mmc(card) &&
+ card->csd.mmca_vsn >= CSD_SPEC_VER_3) ||
+ (mmc_card_sd(card) &&
+ card->scr.cmds & SD_SCR_CMD23_SUPPORT))
+ md->flags |= MMC_BLK_CMD23;
+ }
+
+ if (md->flags & MMC_BLK_CMD23 &&
+ ((card->ext_csd.rel_param & EXT_CSD_WR_REL_PARAM_EN) ||
+ card->ext_csd.rel_sectors)) {
+ md->flags |= MMC_BLK_REL_WR;
+ features |= (BLK_FEAT_WRITE_CACHE | BLK_FEAT_FUA);
+ } else if (mmc_cache_enabled(card->host)) {
+ features |= BLK_FEAT_WRITE_CACHE;
+ }
+
+ md->disk = mmc_init_queue(&md->queue, card, features);
if (IS_ERR(md->disk)) {
ret = PTR_ERR(md->disk);
goto err_kfree;
@@ -2539,26 +2555,6 @@ static struct mmc_blk_data *mmc_blk_alloc_req(struct mmc_card *card,
set_capacity(md->disk, size);
- if (mmc_host_cmd23(card->host)) {
- if ((mmc_card_mmc(card) &&
- card->csd.mmca_vsn >= CSD_SPEC_VER_3) ||
- (mmc_card_sd(card) &&
- card->scr.cmds & SD_SCR_CMD23_SUPPORT))
- md->flags |= MMC_BLK_CMD23;
- }
-
- if (md->flags & MMC_BLK_CMD23 &&
- ((card->ext_csd.rel_param & EXT_CSD_WR_REL_PARAM_EN) ||
- card->ext_csd.rel_sectors)) {
- md->flags |= MMC_BLK_REL_WR;
- fua_enabled = true;
- cache_enabled = true;
- }
- if (mmc_cache_enabled(card->host))
- cache_enabled = true;
-
- blk_queue_write_cache(md->queue.queue, cache_enabled, fua_enabled);
-
string_get_size((u64)size, 512, STRING_UNITS_2,
cap_str, sizeof(cap_str));
pr_info("%s: %s %s %s%s\n",
diff --git a/drivers/mmc/core/queue.c b/drivers/mmc/core/queue.c
index 241cdc2b2a2a..d0b3ca8a11f0 100644
--- a/drivers/mmc/core/queue.c
+++ b/drivers/mmc/core/queue.c
@@ -344,10 +344,12 @@ static const struct blk_mq_ops mmc_mq_ops = {
};
static struct gendisk *mmc_alloc_disk(struct mmc_queue *mq,
- struct mmc_card *card)
+ struct mmc_card *card, unsigned int features)
{
struct mmc_host *host = card->host;
- struct queue_limits lim = { };
+ struct queue_limits lim = {
+ .features = features,
+ };
struct gendisk *disk;
if (mmc_can_erase(card))
@@ -376,18 +378,16 @@ static struct gendisk *mmc_alloc_disk(struct mmc_queue *mq,
lim.max_segments = host->max_segs;
}
+ if (mmc_host_is_spi(host) && host->use_spi_crc)
+ lim.features |= BLK_FEAT_STABLE_WRITES;
+
disk = blk_mq_alloc_disk(&mq->tag_set, &lim, mq);
if (IS_ERR(disk))
return disk;
mq->queue = disk->queue;
- if (mmc_host_is_spi(host) && host->use_spi_crc)
- blk_queue_flag_set(QUEUE_FLAG_STABLE_WRITES, mq->queue);
blk_queue_rq_timeout(mq->queue, 60 * HZ);
- blk_queue_flag_set(QUEUE_FLAG_NONROT, mq->queue);
- blk_queue_flag_clear(QUEUE_FLAG_ADD_RANDOM, mq->queue);
-
dma_set_max_seg_size(mmc_dev(host), queue_max_segment_size(mq->queue));
INIT_WORK(&mq->recovery_work, mmc_mq_recovery_handler);
@@ -413,10 +413,12 @@ static inline bool mmc_merge_capable(struct mmc_host *host)
* mmc_init_queue - initialise a queue structure.
* @mq: mmc queue
* @card: mmc card to attach this queue
+ * @features: block layer features (BLK_FEAT_*)
*
* Initialise a MMC card request queue.
*/
-struct gendisk *mmc_init_queue(struct mmc_queue *mq, struct mmc_card *card)
+struct gendisk *mmc_init_queue(struct mmc_queue *mq, struct mmc_card *card,
+ unsigned int features)
{
struct mmc_host *host = card->host;
struct gendisk *disk;
@@ -460,7 +462,7 @@ struct gendisk *mmc_init_queue(struct mmc_queue *mq, struct mmc_card *card)
return ERR_PTR(ret);
- disk = mmc_alloc_disk(mq, card);
+ disk = mmc_alloc_disk(mq, card, features);
if (IS_ERR(disk))
blk_mq_free_tag_set(&mq->tag_set);
return disk;
diff --git a/drivers/mmc/core/queue.h b/drivers/mmc/core/queue.h
index 9ade3bcbb714..1498840a4ea0 100644
--- a/drivers/mmc/core/queue.h
+++ b/drivers/mmc/core/queue.h
@@ -94,7 +94,8 @@ struct mmc_queue {
struct work_struct complete_work;
};
-struct gendisk *mmc_init_queue(struct mmc_queue *mq, struct mmc_card *card);
+struct gendisk *mmc_init_queue(struct mmc_queue *mq, struct mmc_card *card,
+ unsigned int features);
extern void mmc_cleanup_queue(struct mmc_queue *);
extern void mmc_queue_suspend(struct mmc_queue *);
extern void mmc_queue_resume(struct mmc_queue *);
diff --git a/drivers/mtd/mtd_blkdevs.c b/drivers/mtd/mtd_blkdevs.c
index 3caa0717d46c..47ead84407cd 100644
--- a/drivers/mtd/mtd_blkdevs.c
+++ b/drivers/mtd/mtd_blkdevs.c
@@ -336,6 +336,8 @@ int add_mtd_blktrans_dev(struct mtd_blktrans_dev *new)
lim.logical_block_size = tr->blksize;
if (tr->discard)
lim.max_hw_discard_sectors = UINT_MAX;
+ if (tr->flush)
+ lim.features |= BLK_FEAT_WRITE_CACHE;
/* Create gendisk */
gd = blk_mq_alloc_disk(new->tag_set, &lim, new);
@@ -372,13 +374,6 @@ int add_mtd_blktrans_dev(struct mtd_blktrans_dev *new)
/* Create the request queue */
spin_lock_init(&new->queue_lock);
INIT_LIST_HEAD(&new->rq_list);
-
- if (tr->flush)
- blk_queue_write_cache(new->rq, true, false);
-
- blk_queue_flag_set(QUEUE_FLAG_NONROT, new->rq);
- blk_queue_flag_clear(QUEUE_FLAG_ADD_RANDOM, new->rq);
-
gd->queue = new->rq;
if (new->readonly)
diff --git a/drivers/nvdimm/btt.c b/drivers/nvdimm/btt.c
index c5f8451b494d..e79c06d65bb7 100644
--- a/drivers/nvdimm/btt.c
+++ b/drivers/nvdimm/btt.c
@@ -1501,6 +1501,7 @@ static int btt_blk_init(struct btt *btt)
.logical_block_size = btt->sector_size,
.max_hw_sectors = UINT_MAX,
.max_integrity_segments = 1,
+ .features = BLK_FEAT_SYNCHRONOUS,
};
int rc;
@@ -1518,9 +1519,6 @@ static int btt_blk_init(struct btt *btt)
btt->btt_disk->fops = &btt_fops;
btt->btt_disk->private_data = btt;
- blk_queue_flag_set(QUEUE_FLAG_NONROT, btt->btt_disk->queue);
- blk_queue_flag_set(QUEUE_FLAG_SYNCHRONOUS, btt->btt_disk->queue);
-
set_capacity(btt->btt_disk, btt->nlba * btt->sector_size >> 9);
rc = device_add_disk(&btt->nd_btt->dev, btt->btt_disk, NULL);
if (rc)
diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c
index 598fe2e89bda..1dd74c969d5a 100644
--- a/drivers/nvdimm/pmem.c
+++ b/drivers/nvdimm/pmem.c
@@ -455,6 +455,8 @@ static int pmem_attach_disk(struct device *dev,
.logical_block_size = pmem_sector_size(ndns),
.physical_block_size = PAGE_SIZE,
.max_hw_sectors = UINT_MAX,
+ .features = BLK_FEAT_WRITE_CACHE |
+ BLK_FEAT_SYNCHRONOUS,
};
int nid = dev_to_node(dev), fua;
struct resource *res = &nsio->res;
@@ -463,7 +465,6 @@ static int pmem_attach_disk(struct device *dev,
struct dax_device *dax_dev;
struct nd_pfn_sb *pfn_sb;
struct pmem_device *pmem;
- struct request_queue *q;
struct gendisk *disk;
void *addr;
int rc;
@@ -495,6 +496,10 @@ static int pmem_attach_disk(struct device *dev,
dev_warn(dev, "unable to guarantee persistence of writes\n");
fua = 0;
}
+ if (fua)
+ lim.features |= BLK_FEAT_FUA;
+ if (is_nd_pfn(dev))
+ lim.features |= BLK_FEAT_DAX;
if (!devm_request_mem_region(dev, res->start, resource_size(res),
dev_name(&ndns->dev))) {
@@ -505,7 +510,6 @@ static int pmem_attach_disk(struct device *dev,
disk = blk_alloc_disk(&lim, nid);
if (IS_ERR(disk))
return PTR_ERR(disk);
- q = disk->queue;
pmem->disk = disk;
pmem->pgmap.owner = pmem;
@@ -543,12 +547,6 @@ static int pmem_attach_disk(struct device *dev,
}
pmem->virt_addr = addr;
- blk_queue_write_cache(q, true, fua);
- blk_queue_flag_set(QUEUE_FLAG_NONROT, q);
- blk_queue_flag_set(QUEUE_FLAG_SYNCHRONOUS, q);
- if (pmem->pfn_flags & PFN_MAP)
- blk_queue_flag_set(QUEUE_FLAG_DAX, q);
-
disk->fops = &pmem_fops;
disk->private_data = pmem;
nvdimm_namespace_disk_name(ndns, disk->disk_name);
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 5a673fa5cb26..bf410d10b120 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -2056,7 +2056,6 @@ static int nvme_update_ns_info_generic(struct nvme_ns *ns,
static int nvme_update_ns_info_block(struct nvme_ns *ns,
struct nvme_ns_info *info)
{
- bool vwc = ns->ctrl->vwc & NVME_CTRL_VWC_PRESENT;
struct queue_limits lim;
struct nvme_id_ns_nvm *nvm = NULL;
struct nvme_zone_info zi = {};
@@ -2106,6 +2105,11 @@ static int nvme_update_ns_info_block(struct nvme_ns *ns,
ns->head->ids.csi == NVME_CSI_ZNS)
nvme_update_zone_info(ns, &lim, &zi);
+ if (ns->ctrl->vwc & NVME_CTRL_VWC_PRESENT)
+ lim.features |= BLK_FEAT_WRITE_CACHE | BLK_FEAT_FUA;
+ else
+ lim.features &= ~(BLK_FEAT_WRITE_CACHE | BLK_FEAT_FUA);
+
/*
* Register a metadata profile for PI, or the plain non-integrity NVMe
* metadata masquerading as Type 0 if supported, otherwise reject block
@@ -2132,7 +2136,6 @@ static int nvme_update_ns_info_block(struct nvme_ns *ns,
if ((id->dlfeat & 0x7) == 0x1 && (id->dlfeat & (1 << 3)))
ns->head->features |= NVME_NS_DEAC;
set_disk_ro(ns->disk, nvme_ns_is_readonly(ns, info));
- blk_queue_write_cache(ns->disk->queue, vwc, vwc);
set_bit(NVME_NS_READY, &ns->flags);
blk_mq_unfreeze_queue(ns->disk->queue);
@@ -3721,6 +3724,7 @@ static void nvme_ns_add_to_ctrl_list(struct nvme_ns *ns)
static void nvme_alloc_ns(struct nvme_ctrl *ctrl, struct nvme_ns_info *info)
{
+ struct queue_limits lim = { };
struct nvme_ns *ns;
struct gendisk *disk;
int node = ctrl->numa_node;
@@ -3729,7 +3733,13 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, struct nvme_ns_info *info)
if (!ns)
return;
- disk = blk_mq_alloc_disk(ctrl->tagset, NULL, ns);
+ if (ctrl->opts && ctrl->opts->data_digest)
+ lim.features |= BLK_FEAT_STABLE_WRITES;
+ if (ctrl->ops->supports_pci_p2pdma &&
+ ctrl->ops->supports_pci_p2pdma(ctrl))
+ lim.features |= BLK_FEAT_PCI_P2PDMA;
+
+ disk = blk_mq_alloc_disk(ctrl->tagset, &lim, ns);
if (IS_ERR(disk))
goto out_free_ns;
disk->fops = &nvme_bdev_ops;
@@ -3737,15 +3747,6 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, struct nvme_ns_info *info)
ns->disk = disk;
ns->queue = disk->queue;
-
- if (ctrl->opts && ctrl->opts->data_digest)
- blk_queue_flag_set(QUEUE_FLAG_STABLE_WRITES, ns->queue);
-
- blk_queue_flag_set(QUEUE_FLAG_NONROT, ns->queue);
- if (ctrl->ops->supports_pci_p2pdma &&
- ctrl->ops->supports_pci_p2pdma(ctrl))
- blk_queue_flag_set(QUEUE_FLAG_PCI_P2PDMA, ns->queue);
-
ns->ctrl = ctrl;
kref_init(&ns->kref);
@@ -4488,13 +4489,15 @@ int nvme_alloc_io_tag_set(struct nvme_ctrl *ctrl, struct blk_mq_tag_set *set,
return ret;
if (ctrl->ops->flags & NVME_F_FABRICS) {
- ctrl->connect_q = blk_mq_alloc_queue(set, NULL, NULL);
+ struct queue_limits lim = {
+ .features = BLK_FEAT_SKIP_TAGSET_QUIESCE,
+ };
+
+ ctrl->connect_q = blk_mq_alloc_queue(set, &lim, NULL);
if (IS_ERR(ctrl->connect_q)) {
ret = PTR_ERR(ctrl->connect_q);
goto out_free_tag_set;
}
- blk_queue_flag_set(QUEUE_FLAG_SKIP_TAGSET_QUIESCE,
- ctrl->connect_q);
}
ctrl->tagset = set;
diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c
index 12c59db02539..4933194d00e5 100644
--- a/drivers/nvme/host/multipath.c
+++ b/drivers/nvme/host/multipath.c
@@ -521,7 +521,6 @@ static void nvme_requeue_work(struct work_struct *work)
int nvme_mpath_alloc_disk(struct nvme_ctrl *ctrl, struct nvme_ns_head *head)
{
struct queue_limits lim;
- bool vwc = false;
mutex_init(&head->lock);
bio_list_init(&head->requeue_list);
@@ -539,6 +538,7 @@ int nvme_mpath_alloc_disk(struct nvme_ctrl *ctrl, struct nvme_ns_head *head)
blk_set_stacking_limits(&lim);
lim.dma_alignment = 3;
+ lim.features |= BLK_FEAT_IO_STAT | BLK_FEAT_NOWAIT | BLK_FEAT_POLL;
if (head->ids.csi != NVME_CSI_ZNS)
lim.max_zone_append_sectors = 0;
@@ -549,24 +549,6 @@ int nvme_mpath_alloc_disk(struct nvme_ctrl *ctrl, struct nvme_ns_head *head)
head->disk->private_data = head;
sprintf(head->disk->disk_name, "nvme%dn%d",
ctrl->subsys->instance, head->instance);
-
- blk_queue_flag_set(QUEUE_FLAG_NONROT, head->disk->queue);
- blk_queue_flag_set(QUEUE_FLAG_NOWAIT, head->disk->queue);
- blk_queue_flag_set(QUEUE_FLAG_IO_STAT, head->disk->queue);
- /*
- * This assumes all controllers that refer to a namespace either
- * support poll queues or not. That is not a strict guarantee,
- * but if the assumption is wrong the effect is only suboptimal
- * performance but not correctness problem.
- */
- if (ctrl->tagset->nr_maps > HCTX_TYPE_POLL &&
- ctrl->tagset->map[HCTX_TYPE_POLL].nr_queues)
- blk_queue_flag_set(QUEUE_FLAG_POLL, head->disk->queue);
-
- /* we need to propagate up the VMC settings */
- if (ctrl->vwc & NVME_CTRL_VWC_PRESENT)
- vwc = true;
- blk_queue_write_cache(head->disk->queue, vwc, vwc);
return 0;
}
@@ -875,10 +857,6 @@ void nvme_mpath_add_disk(struct nvme_ns *ns, __le32 anagrpid)
nvme_mpath_set_live(ns);
}
- if (test_bit(QUEUE_FLAG_STABLE_WRITES, &ns->queue->queue_flags) &&
- ns->head->disk)
- blk_queue_flag_set(QUEUE_FLAG_STABLE_WRITES,
- ns->head->disk->queue);
#ifdef CONFIG_BLK_DEV_ZONED
if (blk_queue_is_zoned(ns->queue) && ns->head->disk)
ns->head->disk->nr_zones = ns->disk->nr_zones;
diff --git a/drivers/nvme/host/zns.c b/drivers/nvme/host/zns.c
index 77aa0f440a6d..99bb89c2495a 100644
--- a/drivers/nvme/host/zns.c
+++ b/drivers/nvme/host/zns.c
@@ -108,13 +108,12 @@ free_data:
void nvme_update_zone_info(struct nvme_ns *ns, struct queue_limits *lim,
struct nvme_zone_info *zi)
{
- lim->zoned = 1;
+ lim->features |= BLK_FEAT_ZONED | BLK_FEAT_ZONE_RESETALL;
lim->max_open_zones = zi->max_open_zones;
lim->max_active_zones = zi->max_active_zones;
lim->max_zone_append_sectors = ns->ctrl->max_zone_append;
lim->chunk_sectors = ns->head->zsze =
nvme_lba_to_sect(ns->head, zi->zone_size);
- blk_queue_flag_set(QUEUE_FLAG_ZONE_RESETALL, ns->queue);
}
static void *nvme_zns_alloc_report_buffer(struct nvme_ns *ns,
diff --git a/drivers/s390/block/dasd_genhd.c b/drivers/s390/block/dasd_genhd.c
index 4533dd055ca8..1aa426b1dedd 100644
--- a/drivers/s390/block/dasd_genhd.c
+++ b/drivers/s390/block/dasd_genhd.c
@@ -68,7 +68,6 @@ int dasd_gendisk_alloc(struct dasd_block *block)
blk_mq_free_tag_set(&block->tag_set);
return PTR_ERR(gdp);
}
- blk_queue_flag_set(QUEUE_FLAG_NONROT, gdp->queue);
/* Initialize gendisk structure. */
gdp->major = DASD_MAJOR;
diff --git a/drivers/s390/block/dcssblk.c b/drivers/s390/block/dcssblk.c
index 6d1689a2717e..d5a5d11ae0dc 100644
--- a/drivers/s390/block/dcssblk.c
+++ b/drivers/s390/block/dcssblk.c
@@ -548,6 +548,7 @@ dcssblk_add_store(struct device *dev, struct device_attribute *attr, const char
{
struct queue_limits lim = {
.logical_block_size = 4096,
+ .features = BLK_FEAT_DAX,
};
int rc, i, j, num_of_segments;
struct dcssblk_dev_info *dev_info;
@@ -643,7 +644,6 @@ dcssblk_add_store(struct device *dev, struct device_attribute *attr, const char
dev_info->gd->fops = &dcssblk_devops;
dev_info->gd->private_data = dev_info;
dev_info->gd->flags |= GENHD_FL_NO_PART;
- blk_queue_flag_set(QUEUE_FLAG_DAX, dev_info->gd->queue);
seg_byte_size = (dev_info->end - dev_info->start + 1);
set_capacity(dev_info->gd, seg_byte_size >> 9); // size in sectors
diff --git a/drivers/s390/block/scm_blk.c b/drivers/s390/block/scm_blk.c
index 1d456a5a3bfb..3fcfe029db1b 100644
--- a/drivers/s390/block/scm_blk.c
+++ b/drivers/s390/block/scm_blk.c
@@ -439,7 +439,6 @@ int scm_blk_dev_setup(struct scm_blk_dev *bdev, struct scm_device *scmdev)
.logical_block_size = 1 << 12,
};
unsigned int devindex;
- struct request_queue *rq;
int len, ret;
lim.max_segments = min(scmdev->nr_max_block,
@@ -474,10 +473,6 @@ int scm_blk_dev_setup(struct scm_blk_dev *bdev, struct scm_device *scmdev)
ret = PTR_ERR(bdev->gendisk);
goto out_tag;
}
- rq = bdev->rq = bdev->gendisk->queue;
- blk_queue_flag_set(QUEUE_FLAG_NONROT, rq);
- blk_queue_flag_clear(QUEUE_FLAG_ADD_RANDOM, rq);
-
bdev->gendisk->private_data = scmdev;
bdev->gendisk->fops = &scm_blk_devops;
bdev->gendisk->major = scm_major;
diff --git a/drivers/scsi/iscsi_tcp.c b/drivers/scsi/iscsi_tcp.c
index 60688f18fac6..c708e1059638 100644
--- a/drivers/scsi/iscsi_tcp.c
+++ b/drivers/scsi/iscsi_tcp.c
@@ -1057,15 +1057,15 @@ static umode_t iscsi_sw_tcp_attr_is_visible(int param_type, int param)
return 0;
}
-static int iscsi_sw_tcp_slave_configure(struct scsi_device *sdev)
+static int iscsi_sw_tcp_device_configure(struct scsi_device *sdev,
+ struct queue_limits *lim)
{
struct iscsi_sw_tcp_host *tcp_sw_host = iscsi_host_priv(sdev->host);
struct iscsi_session *session = tcp_sw_host->session;
struct iscsi_conn *conn = session->leadconn;
if (conn->datadgst_en)
- blk_queue_flag_set(QUEUE_FLAG_STABLE_WRITES,
- sdev->request_queue);
+ lim->features |= BLK_FEAT_STABLE_WRITES;
return 0;
}
@@ -1083,7 +1083,7 @@ static const struct scsi_host_template iscsi_sw_tcp_sht = {
.eh_device_reset_handler= iscsi_eh_device_reset,
.eh_target_reset_handler = iscsi_eh_recover_target,
.dma_boundary = PAGE_SIZE - 1,
- .slave_configure = iscsi_sw_tcp_slave_configure,
+ .device_configure = iscsi_sw_tcp_device_configure,
.proc_name = "iscsi_tcp",
.this_id = -1,
.track_queue_depth = 1,
diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
index ec39acc986d6..e2f7bfb2b9e4 100644
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -631,8 +631,7 @@ static bool scsi_end_request(struct request *req, blk_status_t error,
if (blk_update_request(req, error, bytes))
return true;
- // XXX:
- if (blk_queue_add_random(q))
+ if (q->limits.features & BLK_FEAT_ADD_RANDOM)
add_disk_randomness(req->q->disk);
WARN_ON_ONCE(!blk_rq_is_passthrough(req) &&
@@ -1987,7 +1986,7 @@ void scsi_init_limits(struct Scsi_Host *shost, struct queue_limits *lim)
shost->dma_alignment, dma_get_cache_alignment() - 1);
if (shost->no_highmem)
- lim->bounce = BLK_BOUNCE_HIGH;
+ lim->features |= BLK_FEAT_BOUNCE_HIGH;
dma_set_seg_boundary(dev, shost->dma_boundary);
dma_set_max_seg_size(dev, shost->max_segment_size);
diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c
index e01393ed4207..a27f1c7f1b61 100644
--- a/drivers/scsi/sd.c
+++ b/drivers/scsi/sd.c
@@ -120,17 +120,18 @@ static const char *sd_cache_types[] = {
"write back, no read (daft)"
};
-static void sd_set_flush_flag(struct scsi_disk *sdkp)
+static void sd_set_flush_flag(struct scsi_disk *sdkp,
+ struct queue_limits *lim)
{
- bool wc = false, fua = false;
-
if (sdkp->WCE) {
- wc = true;
+ lim->features |= BLK_FEAT_WRITE_CACHE;
if (sdkp->DPOFUA)
- fua = true;
+ lim->features |= BLK_FEAT_FUA;
+ else
+ lim->features &= ~BLK_FEAT_FUA;
+ } else {
+ lim->features &= ~(BLK_FEAT_WRITE_CACHE | BLK_FEAT_FUA);
}
-
- blk_queue_write_cache(sdkp->disk->queue, wc, fua);
}
static ssize_t
@@ -168,9 +169,18 @@ cache_type_store(struct device *dev, struct device_attribute *attr,
wce = (ct & 0x02) && !sdkp->write_prot ? 1 : 0;
if (sdkp->cache_override) {
+ struct queue_limits lim;
+
sdkp->WCE = wce;
sdkp->RCD = rcd;
- sd_set_flush_flag(sdkp);
+
+ lim = queue_limits_start_update(sdkp->disk->queue);
+ sd_set_flush_flag(sdkp, &lim);
+ blk_mq_freeze_queue(sdkp->disk->queue);
+ ret = queue_limits_commit_update(sdkp->disk->queue, &lim);
+ blk_mq_unfreeze_queue(sdkp->disk->queue);
+ if (ret)
+ return ret;
return count;
}
@@ -466,10 +476,6 @@ provisioning_mode_store(struct device *dev, struct device_attribute *attr,
if (sdp->type != TYPE_DISK)
return -EINVAL;
- /* ignore the provisioning mode for ZBC devices */
- if (sd_is_zoned(sdkp))
- return count;
-
mode = sysfs_match_string(lbp_mode, buf);
if (mode < 0)
return -EINVAL;
@@ -2288,7 +2294,7 @@ static int sd_done(struct scsi_cmnd *SCpnt)
}
out:
- if (sd_is_zoned(sdkp))
+ if (sdkp->device->type == TYPE_ZBC)
good_bytes = sd_zbc_complete(SCpnt, good_bytes, &sshdr);
SCSI_LOG_HLCOMPLETE(1, scmd_printk(KERN_INFO, SCpnt,
@@ -3295,7 +3301,6 @@ static void sd_read_block_limits_ext(struct scsi_disk *sdkp)
static void sd_read_block_characteristics(struct scsi_disk *sdkp,
struct queue_limits *lim)
{
- struct request_queue *q = sdkp->disk->queue;
struct scsi_vpd *vpd;
u16 rot;
@@ -3311,34 +3316,13 @@ static void sd_read_block_characteristics(struct scsi_disk *sdkp,
sdkp->zoned = (vpd->data[8] >> 4) & 3;
rcu_read_unlock();
- if (rot == 1) {
- blk_queue_flag_set(QUEUE_FLAG_NONROT, q);
- blk_queue_flag_clear(QUEUE_FLAG_ADD_RANDOM, q);
- }
-
-
-#ifdef CONFIG_BLK_DEV_ZONED /* sd_probe rejects ZBD devices early otherwise */
- if (sdkp->device->type == TYPE_ZBC) {
- lim->zoned = true;
-
- /*
- * Per ZBC and ZAC specifications, writes in sequential write
- * required zones of host-managed devices must be aligned to
- * the device physical block size.
- */
- lim->zone_write_granularity = sdkp->physical_block_size;
- } else {
- /*
- * Host-aware devices are treated as conventional.
- */
- lim->zoned = false;
- }
-#endif /* CONFIG_BLK_DEV_ZONED */
+ if (rot == 1)
+ lim->features &= ~(BLK_FEAT_ROTATIONAL | BLK_FEAT_ADD_RANDOM);
if (!sdkp->first_scan)
return;
- if (lim->zoned)
+ if (sdkp->device->type == TYPE_ZBC)
sd_printk(KERN_NOTICE, sdkp, "Host-managed zoned block device\n");
else if (sdkp->zoned == 1)
sd_printk(KERN_NOTICE, sdkp, "Host-aware SMR disk used as regular disk\n");
@@ -3612,7 +3596,6 @@ static int sd_revalidate_disk(struct gendisk *disk)
{
struct scsi_disk *sdkp = scsi_disk(disk);
struct scsi_device *sdp = sdkp->device;
- struct request_queue *q = sdkp->disk->queue;
sector_t old_capacity = sdkp->capacity;
struct queue_limits lim;
unsigned char *buffer;
@@ -3659,8 +3642,7 @@ static int sd_revalidate_disk(struct gendisk *disk)
* cause this to be updated correctly and any device which
* doesn't support it should be treated as rotational.
*/
- blk_queue_flag_clear(QUEUE_FLAG_NONROT, q);
- blk_queue_flag_set(QUEUE_FLAG_ADD_RANDOM, q);
+ lim.features |= (BLK_FEAT_ROTATIONAL | BLK_FEAT_ADD_RANDOM);
if (scsi_device_supports_vpd(sdp)) {
sd_read_block_provisioning(sdkp);
@@ -3686,7 +3668,7 @@ static int sd_revalidate_disk(struct gendisk *disk)
* We now have all cache related info, determine how we deal
* with flush requests.
*/
- sd_set_flush_flag(sdkp);
+ sd_set_flush_flag(sdkp, &lim);
/* Initial block count limit based on CDB TRANSFER LENGTH field size. */
dev_max = sdp->use_16_for_rw ? SD_MAX_XFER_BLOCKS : SD_DEF_XFER_BLOCKS;
diff --git a/drivers/scsi/sd.h b/drivers/scsi/sd.h
index 726f1613f6cb..7603b3c67b23 100644
--- a/drivers/scsi/sd.h
+++ b/drivers/scsi/sd.h
@@ -222,11 +222,6 @@ static inline sector_t sectors_to_logical(struct scsi_device *sdev, sector_t sec
void sd_dif_config_host(struct scsi_disk *sdkp, struct queue_limits *lim);
-static inline int sd_is_zoned(struct scsi_disk *sdkp)
-{
- return sdkp->zoned == 1 || sdkp->device->type == TYPE_ZBC;
-}
-
#ifdef CONFIG_BLK_DEV_ZONED
int sd_zbc_read_zones(struct scsi_disk *sdkp, struct queue_limits *lim,
diff --git a/drivers/scsi/sd_zbc.c b/drivers/scsi/sd_zbc.c
index f685838d9ed2..f7067afac79c 100644
--- a/drivers/scsi/sd_zbc.c
+++ b/drivers/scsi/sd_zbc.c
@@ -232,7 +232,7 @@ int sd_zbc_report_zones(struct gendisk *disk, sector_t sector,
int zone_idx = 0;
int ret;
- if (!sd_is_zoned(sdkp))
+ if (sdkp->device->type != TYPE_ZBC)
/* Not a zoned device */
return -EOPNOTSUPP;
@@ -300,7 +300,7 @@ static blk_status_t sd_zbc_cmnd_checks(struct scsi_cmnd *cmd)
struct scsi_disk *sdkp = scsi_disk(rq->q->disk);
sector_t sector = blk_rq_pos(rq);
- if (!sd_is_zoned(sdkp))
+ if (sdkp->device->type != TYPE_ZBC)
/* Not a zoned device */
return BLK_STS_IOERR;
@@ -521,7 +521,7 @@ static int sd_zbc_check_capacity(struct scsi_disk *sdkp, unsigned char *buf,
static void sd_zbc_print_zones(struct scsi_disk *sdkp)
{
- if (!sd_is_zoned(sdkp) || !sdkp->capacity)
+ if (sdkp->device->type != TYPE_ZBC || !sdkp->capacity)
return;
if (sdkp->capacity & (sdkp->zone_info.zone_blocks - 1))
@@ -592,19 +592,21 @@ int sd_zbc_revalidate_zones(struct scsi_disk *sdkp)
int sd_zbc_read_zones(struct scsi_disk *sdkp, struct queue_limits *lim,
u8 buf[SD_BUF_SIZE])
{
- struct gendisk *disk = sdkp->disk;
- struct request_queue *q = disk->queue;
unsigned int nr_zones;
u32 zone_blocks = 0;
int ret;
- if (!sd_is_zoned(sdkp)) {
- /*
- * Device managed or normal SCSI disk, no special handling
- * required.
- */
+ if (sdkp->device->type != TYPE_ZBC)
return 0;
- }
+
+ lim->features |= BLK_FEAT_ZONED | BLK_FEAT_ZONE_RESETALL;
+
+ /*
+ * Per ZBC and ZAC specifications, writes in sequential write required
+ * zones of host-managed devices must be aligned to the device physical
+ * block size.
+ */
+ lim->zone_write_granularity = sdkp->physical_block_size;
/* READ16/WRITE16/SYNC16 is mandatory for ZBC devices */
sdkp->device->use_16_for_rw = 1;
@@ -626,7 +628,6 @@ int sd_zbc_read_zones(struct scsi_disk *sdkp, struct queue_limits *lim,
sdkp->early_zone_info.zone_blocks = zone_blocks;
/* The drive satisfies the kernel restrictions: set it up */
- blk_queue_flag_set(QUEUE_FLAG_ZONE_RESETALL, q);
if (sdkp->zones_max_open == U32_MAX)
lim->max_open_zones = 0;
else
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 83af6ac5aa48..bc8d17b7f29d 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -282,6 +282,67 @@ static inline bool blk_op_is_passthrough(blk_opf_t op)
return op == REQ_OP_DRV_IN || op == REQ_OP_DRV_OUT;
}
+/* flags set by the driver in queue_limits.features */
+enum {
+ /* supports a volatile write cache */
+ BLK_FEAT_WRITE_CACHE = (1u << 0),
+
+ /* supports passing on the FUA bit */
+ BLK_FEAT_FUA = (1u << 1),
+
+ /* rotational device (hard drive or floppy) */
+ BLK_FEAT_ROTATIONAL = (1u << 2),
+
+ /* contributes to the random number pool */
+ BLK_FEAT_ADD_RANDOM = (1u << 3),
+
+ /* do disk/partitions IO accounting */
+ BLK_FEAT_IO_STAT = (1u << 4),
+
+ /* don't modify data until writeback is done */
+ BLK_FEAT_STABLE_WRITES = (1u << 5),
+
+ /* always completes in submit context */
+ BLK_FEAT_SYNCHRONOUS = (1u << 6),
+
+ /* supports REQ_NOWAIT */
+ BLK_FEAT_NOWAIT = (1u << 7),
+
+ /* supports DAX */
+ BLK_FEAT_DAX = (1u << 8),
+
+ /* supports I/O polling */
+ BLK_FEAT_POLL = (1u << 9),
+
+ /* is a zoned device */
+ BLK_FEAT_ZONED = (1u << 10),
+
+ /* supports Zone Reset All */
+ BLK_FEAT_ZONE_RESETALL = (1u << 11),
+
+ /* supports PCI(e) p2p requests */
+ BLK_FEAT_PCI_P2PDMA = (1u << 12),
+
+ /* skip this queue in blk_mq_(un)quiesce_tagset */
+ BLK_FEAT_SKIP_TAGSET_QUIESCE = (1u << 13),
+
+ /* bounce all highmem pages */
+ BLK_FEAT_BOUNCE_HIGH = (1u << 14),
+};
+
+/*
+ * Flags automatically inherited when stacking limits.
+ */
+#define BLK_FEAT_INHERIT_MASK \
+ (BLK_FEAT_WRITE_CACHE | BLK_FEAT_FUA | BLK_FEAT_ROTATIONAL | \
+ BLK_FEAT_STABLE_WRITES | BLK_FEAT_ZONED | BLK_FEAT_BOUNCE_HIGH)
+
+/* internal flags in queue_limits.flags */
+enum {
+ /* do not send FLUSH or FUA command despite advertised write cache */
+ BLK_FLAGS_WRITE_CACHE_DISABLED = (1u << 31),
+};
+
/*
* BLK_BOUNCE_NONE: never bounce (default)
* BLK_BOUNCE_HIGH: bounce all highmem pages
@@ -292,7 +353,8 @@ enum blk_bounce {
};
struct queue_limits {
- enum blk_bounce bounce;
+ unsigned int features;
+ unsigned int flags;
unsigned long seg_boundary_mask;
unsigned long virt_boundary_mask;
@@ -324,7 +386,6 @@ struct queue_limits {
unsigned char misaligned;
unsigned char discard_misaligned;
unsigned char raid_partial_stripes_expensive;
- bool zoned;
unsigned int max_open_zones;
unsigned int max_active_zones;
@@ -529,34 +590,17 @@ struct request_queue {
#define QUEUE_FLAG_NOMERGES 3 /* disable merge attempts */
#define QUEUE_FLAG_SAME_COMP 4 /* complete on same CPU-group */
#define QUEUE_FLAG_FAIL_IO 5 /* fake timeout */
-#define QUEUE_FLAG_NONROT 6 /* non-rotational device (SSD) */
-#define QUEUE_FLAG_VIRT QUEUE_FLAG_NONROT /* paravirt device */
-#define QUEUE_FLAG_IO_STAT 7 /* do disk/partitions IO accounting */
#define QUEUE_FLAG_NOXMERGES 9 /* No extended merges */
-#define QUEUE_FLAG_ADD_RANDOM 10 /* Contributes to random pool */
-#define QUEUE_FLAG_SYNCHRONOUS 11 /* always completes in submit context */
#define QUEUE_FLAG_SAME_FORCE 12 /* force complete on same CPU */
-#define QUEUE_FLAG_HW_WC 13 /* Write back caching supported */
#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 */
-#define QUEUE_FLAG_DAX 19 /* device supports DAX */
#define QUEUE_FLAG_STATS 20 /* track IO start and completion times */
#define QUEUE_FLAG_REGISTERED 22 /* queue has been registered to a disk */
#define QUEUE_FLAG_QUIESCED 24 /* queue has been quiesced */
-#define QUEUE_FLAG_PCI_P2PDMA 25 /* device supports PCI p2p requests */
-#define QUEUE_FLAG_ZONE_RESETALL 26 /* supports Zone Reset All */
#define QUEUE_FLAG_RQ_ALLOC_TIME 27 /* record rq->alloc_time_ns */
#define QUEUE_FLAG_HCTX_ACTIVE 28 /* at least one blk-mq hctx is active */
-#define QUEUE_FLAG_NOWAIT 29 /* device supports NOWAIT */
#define QUEUE_FLAG_SQ_SCHED 30 /* single queue style io dispatch */
-#define QUEUE_FLAG_SKIP_TAGSET_QUIESCE 31 /* quiesce_tagset skip the queue*/
-#define QUEUE_FLAG_MQ_DEFAULT ((1UL << QUEUE_FLAG_IO_STAT) | \
- (1UL << QUEUE_FLAG_SAME_COMP) | \
- (1UL << QUEUE_FLAG_NOWAIT))
+#define QUEUE_FLAG_MQ_DEFAULT (1UL << QUEUE_FLAG_SAME_COMP)
void blk_queue_flag_set(unsigned int flag, struct request_queue *q);
void blk_queue_flag_clear(unsigned int flag, struct request_queue *q);
@@ -568,14 +612,12 @@ bool blk_queue_flag_test_and_set(unsigned int flag, struct request_queue *q);
#define blk_queue_nomerges(q) test_bit(QUEUE_FLAG_NOMERGES, &(q)->queue_flags)
#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_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_nonrot(q) ((q)->limits.features & BLK_FEAT_ROTATIONAL)
+#define blk_queue_io_stat(q) ((q)->limits.features & BLK_FEAT_IO_STAT)
#define blk_queue_zone_resetall(q) \
- test_bit(QUEUE_FLAG_ZONE_RESETALL, &(q)->queue_flags)
-#define blk_queue_dax(q) test_bit(QUEUE_FLAG_DAX, &(q)->queue_flags)
-#define blk_queue_pci_p2pdma(q) \
- test_bit(QUEUE_FLAG_PCI_P2PDMA, &(q)->queue_flags)
+ ((q)->limits.features & BLK_FEAT_ZONE_RESETALL)
+#define blk_queue_dax(q) ((q)->limits.features & BLK_FEAT_DAX)
+#define blk_queue_pci_p2pdma(q) ((q)->limits.features & BLK_FEAT_PCI_P2PDMA)
#ifdef CONFIG_BLK_RQ_ALLOC_TIME
#define blk_queue_rq_alloc_time(q) \
test_bit(QUEUE_FLAG_RQ_ALLOC_TIME, &(q)->queue_flags)
@@ -591,7 +633,7 @@ bool blk_queue_flag_test_and_set(unsigned int flag, struct request_queue *q);
#define blk_queue_registered(q) test_bit(QUEUE_FLAG_REGISTERED, &(q)->queue_flags)
#define blk_queue_sq_sched(q) test_bit(QUEUE_FLAG_SQ_SCHED, &(q)->queue_flags)
#define blk_queue_skip_tagset_quiesce(q) \
- test_bit(QUEUE_FLAG_SKIP_TAGSET_QUIESCE, &(q)->queue_flags)
+ ((q)->limits.features & BLK_FEAT_SKIP_TAGSET_QUIESCE)
extern void blk_set_pm_only(struct request_queue *q);
extern void blk_clear_pm_only(struct request_queue *q);
@@ -621,7 +663,8 @@ static inline enum rpm_status queue_rpm_status(struct request_queue *q)
static inline bool blk_queue_is_zoned(struct request_queue *q)
{
- return IS_ENABLED(CONFIG_BLK_DEV_ZONED) && q->limits.zoned;
+ return IS_ENABLED(CONFIG_BLK_DEV_ZONED) &&
+ (q->limits.features & BLK_FEAT_ZONED);
}
#ifdef CONFIG_BLK_DEV_ZONED
@@ -950,7 +993,6 @@ void queue_limits_stack_bdev(struct queue_limits *t, struct block_device *bdev,
sector_t offset, const char *pfx);
extern void blk_queue_update_dma_pad(struct request_queue *, unsigned int);
extern void blk_queue_rq_timeout(struct request_queue *, unsigned int);
-extern void blk_queue_write_cache(struct request_queue *q, bool enabled, bool fua);
struct blk_independent_access_ranges *
disk_alloc_independent_access_ranges(struct gendisk *disk, int nr_ia_ranges);
@@ -1289,8 +1331,7 @@ static inline bool bdev_nonrot(struct block_device *bdev)
static inline bool bdev_synchronous(struct block_device *bdev)
{
- return test_bit(QUEUE_FLAG_SYNCHRONOUS,
- &bdev_get_queue(bdev)->queue_flags);
+ return bdev->bd_disk->queue->limits.features & BLK_FEAT_SYNCHRONOUS;
}
static inline bool bdev_stable_writes(struct block_device *bdev)
@@ -1300,22 +1341,28 @@ static inline bool bdev_stable_writes(struct block_device *bdev)
if (IS_ENABLED(CONFIG_BLK_DEV_INTEGRITY) &&
q->limits.integrity.csum_type != BLK_INTEGRITY_CSUM_NONE)
return true;
- return test_bit(QUEUE_FLAG_STABLE_WRITES, &q->queue_flags);
+ return q->limits.features & BLK_FEAT_STABLE_WRITES;
+}
+
+static inline bool blk_queue_write_cache(struct request_queue *q)
+{
+ return (q->limits.features & BLK_FEAT_WRITE_CACHE) &&
+ !(q->limits.flags & BLK_FLAGS_WRITE_CACHE_DISABLED);
}
static inline bool bdev_write_cache(struct block_device *bdev)
{
- return test_bit(QUEUE_FLAG_WC, &bdev_get_queue(bdev)->queue_flags);
+ return blk_queue_write_cache(bdev_get_queue(bdev));
}
static inline bool bdev_fua(struct block_device *bdev)
{
- return test_bit(QUEUE_FLAG_FUA, &bdev_get_queue(bdev)->queue_flags);
+ return bdev_get_queue(bdev)->limits.features & BLK_FEAT_FUA;
}
static inline bool bdev_nowait(struct block_device *bdev)
{
- return test_bit(QUEUE_FLAG_NOWAIT, &bdev_get_queue(bdev)->queue_flags);
+ return bdev->bd_disk->queue->limits.features & BLK_FEAT_NOWAIT;
}
static inline bool bdev_is_zoned(struct block_device *bdev)