block: force noio scope in blk_mq_freeze_queue

When block drivers or the core block code perform allocations with a
frozen queue, this could try to recurse into the block device to
reclaim memory an

block: force noio scope in blk_mq_freeze_queue

When block drivers or the core block code perform allocations with a
frozen queue, this could try to recurse into the block device to
reclaim memory and deadlock. Thus all allocations done by a process
that froze a queue need to be done without __GFP_IO and __GFP_FS.
Instead of tying to track all of them down, force a noio scope as
part of freezing the queue.

Note that nvme is a bit of a mess here due to the non-owner freezes,
and they will be addressed separately.

Signed-off-by: Christoph Hellwig <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Jens Axboe <[email protected]>

show more ...

block: remove BLK_MQ_F_SHOULD_MERGE

BLK_MQ_F_SHOULD_MERGE is set for all tag_sets except those that purely
process passthrough commands (bsg-lib, ufs tmf, various nvme admin
queues) and thus don't e

block: remove BLK_MQ_F_SHOULD_MERGE

BLK_MQ_F_SHOULD_MERGE is set for all tag_sets except those that purely
process passthrough commands (bsg-lib, ufs tmf, various nvme admin
queues) and thus don't even check the flag. Remove it to simplify the
driver interface.

Signed-off-by: Christoph Hellwig <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Jens Axboe <[email protected]>

show more ...

block: move the add_random flag to queue_limits

Move the add_random flag into the queue_limits feature field so that it
can be set atomically with the queue frozen.

Note that this also removes code

block: move the add_random flag to queue_limits

Move the add_random flag into the queue_limits feature field so that it
can be set atomically with the queue frozen.

Note that this also removes code from dm to clear the flag based on
the underlying devices, which can't be reached as dm devices will
always start out without the flag set.

Signed-off-by: Christoph Hellwig <[email protected]>
Reviewed-by: Damien Le Moal <[email protected]>
Reviewed-by: Hannes Reinecke <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Jens Axboe <[email protected]>

show more ...

block: move the nonrot flag to queue_limits

Move the nonrot flag into the queue_limits feature field so that it can
be set atomically with the queue frozen.

Use the chance to switch to defaulting t

block: move the nonrot flag to queue_limits

Move the nonrot flag into the queue_limits feature field so that it can
be set atomically with the queue frozen.

Use the chance to switch to defaulting to non-rotational and require
the driver to opt into rotational, which matches the polarity of the
sysfs interface.

For the z2ram, ps3vram, 2x memstick, ubiblock and dcssblk the new
rotational flag is not set as they clearly are not rotational despite
this being a behavior change. There are some other drivers that
unconditionally set the rotational flag to keep the existing behavior
as they arguably can be used on rotational devices even if that is
probably not their main use today (e.g. virtio_blk and drbd).

The flag is automatically inherited in blk_stack_limits matching the
existing behavior in dm and md.

Signed-off-by: Christoph Hellwig <[email protected]>
Reviewed-by: Damien Le Moal <[email protected]>
Reviewed-by: Hannes Reinecke <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Jens Axboe <[email protected]>

show more ...

block: move cache control settings out of queue->flags

Move the cache control settings into the queue_limits so that the flags
can be set atomically with the device queue frozen.

Add new features a

block: move cache control settings out of queue->flags

Move the cache control settings into the queue_limits so that the flags
can be set atomically with the device queue frozen.

Add new features and flags field for the driver set flags, and internal
(usually sysfs-controlled) flags in the block layer. Note that we'll
eventually remove enough field from queue_limits to bring it back to the
previous size.

The disable flag is inverted compared to the previous meaning, which
means it now survives a rescan, similar to the max_sectors and
max_discard_sectors user limits.

The FLUSH and FUA flags are now inherited by blk_stack_limits, which
simplified the code in dm a lot, but also causes a slight behavior
change in that dm-switch and dm-unstripe now advertise a write cache
despite setting num_flush_bios to 0. The I/O path will handle this
gracefully, but as far as I can tell the lack of num_flush_bios
and thus flush support is a pre-existing data integrity bug in those
targets that really needs fixing, after which a non-zero num_flush_bios
should be required in dm for targets that map to underlying devices.

Signed-off-by: Christoph Hellwig <[email protected]>
Acked-by: Ulf Hansson <[email protected]>
Reviewed-by: Damien Le Moal <[email protected]>
Reviewed-by: Hannes Reinecke <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Jens Axboe <[email protected]>

show more ...

mtd_blkdevs: pass queue_limits to blk_mq_alloc_disk

Pass the few limits mtd_blkdevs imposes directly to blk_mq_alloc_disk
instead of setting them one at a time.

Signed-off-by: Christoph Hellwig <hc

mtd_blkdevs: pass queue_limits to blk_mq_alloc_disk

Pass the few limits mtd_blkdevs imposes directly to blk_mq_alloc_disk
instead of setting them one at a time.

Signed-off-by: Christoph Hellwig <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Jens Axboe <[email protected]>

show more ...

block: pass a queue_limits argument to blk_mq_alloc_disk

Pass a queue_limits to blk_mq_alloc_disk and apply it if non-NULL. This
will allow allocating queues with valid queue limits instead of sett

block: pass a queue_limits argument to blk_mq_alloc_disk

Pass a queue_limits to blk_mq_alloc_disk and apply it if non-NULL. This
will allow allocating queues with valid queue limits instead of setting
the values one at a time later.

Signed-off-by: Christoph Hellwig <[email protected]>
Reviewed-by: Keith Busch <[email protected]>
Reviewed-by: John Garry <[email protected]>
Reviewed-by: Chaitanya Kulkarni <[email protected]>
Reviewed-by: Ming Lei <[email protected]>
Reviewed-by: Damien Le Moal <[email protected]>
Reviewed-by: Martin K. Petersen <[email protected]>
Reviewed-by: Hannes Reinecke <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Jens Axboe <[email protected]>

show more ...

mtd_blkdevs: use the default discard granularity

The discard granularity now defaults to a single sector, so don't set
that value explicitly.

Signed-off-by: Christoph Hellwig <[email protected]>
Acked-by:

mtd_blkdevs: use the default discard granularity

The discard granularity now defaults to a single sector, so don't set
that value explicitly.

Signed-off-by: Christoph Hellwig <[email protected]>
Acked-by: Richard Weinberger <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Jens Axboe <[email protected]>

show more ...

mtd: Fix gluebi NULL pointer dereference caused by ftl notifier

If both ftl.ko and gluebi.ko are loaded, the notifier of ftl
triggers NULL pointer dereference when trying to access
‘gluebi->desc’ in

mtd: Fix gluebi NULL pointer dereference caused by ftl notifier

If both ftl.ko and gluebi.ko are loaded, the notifier of ftl
triggers NULL pointer dereference when trying to access
‘gluebi->desc’ in gluebi_read().

ubi_gluebi_init
ubi_register_volume_notifier
ubi_enumerate_volumes
ubi_notify_all
gluebi_notify nb->notifier_call()
gluebi_create
mtd_device_register
mtd_device_parse_register
add_mtd_device
blktrans_notify_add not->add()
ftl_add_mtd tr->add_mtd()
scan_header
mtd_read
mtd_read_oob
mtd_read_oob_std
gluebi_read mtd->read()
gluebi->desc - NULL

Detailed reproduction information available at the Link [1],

In the normal case, obtain gluebi->desc in the gluebi_get_device(),
and access gluebi->desc in the gluebi_read(). However,
gluebi_get_device() is not executed in advance in the
ftl_add_mtd() process, which leads to NULL pointer dereference.

The solution for the gluebi module is to run jffs2 on the UBI
volume without considering working with ftl or mtdblock [2].
Therefore, this problem can be avoided by preventing gluebi from
creating the mtdblock device after creating mtd partition of the
type MTD_UBIVOLUME.

Fixes: 2ba3d76a1e29 ("UBI: make gluebi a separate module")
Link: https://bugzilla.kernel.org/show_bug.cgi?id=217992 [1]
Link: https://lore.kernel.org/lkml/[email protected]/ [2]
Signed-off-by: ZhaoLong Wang <[email protected]>
Reviewed-by: Zhihao Cheng <[email protected]>
Acked-by: Richard Weinberger <[email protected]>
Signed-off-by: Miquel Raynal <[email protected]>
Link: https://lore.kernel.org/linux-mtd/[email protected]

show more ...

block: replace fmode_t with a block-specific type for block open flags

The only overlap between the block open flags mapped into the fmode_t and
other uses of fmode_t are FMODE_READ and FMODE_WRITE.

block: replace fmode_t with a block-specific type for block open flags

The only overlap between the block open flags mapped into the fmode_t and
other uses of fmode_t are FMODE_READ and FMODE_WRITE. Define a new
blk_mode_t instead for use in blkdev_get_by_{dev,path}, ->open and
->ioctl and stop abusing fmode_t.

Signed-off-by: Christoph Hellwig <[email protected]>
Acked-by: Jack Wang <[email protected]> [rnbd]
Reviewed-by: Hannes Reinecke <[email protected]>
Reviewed-by: Christian Brauner <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Jens Axboe <[email protected]>

show more ...

mtd: block: use a simple bool to track open for write

Instead of propagating the fmode_t, just use a bool to track if a mtd
block device was opened for writing.

Signed-off-by: Christoph Hellwig <hc

mtd: block: use a simple bool to track open for write

Instead of propagating the fmode_t, just use a bool to track if a mtd
block device was opened for writing.

Signed-off-by: Christoph Hellwig <[email protected]>
Reviewed-by: Hannes Reinecke <[email protected]>
Acked-by: Christian Brauner <[email protected]>
Acked-by: Richard Weinberger <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Jens Axboe <[email protected]>

show more ...

block: remove the unused mode argument to ->release

The mode argument to the ->release block_device_operation is never used,
so remove it.

Signed-off-by: Christoph Hellwig <[email protected]>
Reviewed-by:

block: remove the unused mode argument to ->release

The mode argument to the ->release block_device_operation is never used,
so remove it.

Signed-off-by: Christoph Hellwig <[email protected]>
Reviewed-by: Hannes Reinecke <[email protected]>
Acked-by: Christian Brauner <[email protected]>
Acked-by: Jack Wang <[email protected]> [rnbd]
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Jens Axboe <[email protected]>

show more ...

block: pass a gendisk to ->open

->open is only called on the whole device. Make that explicit by
passing a gendisk instead of the block_device.

Signed-off-by: Christoph Hellwig <[email protected]>
Review

block: pass a gendisk to ->open

->open is only called on the whole device. Make that explicit by
passing a gendisk instead of the block_device.

Signed-off-by: Christoph Hellwig <[email protected]>
Reviewed-by: Hannes Reinecke <[email protected]>
Acked-by: Christian Brauner <[email protected]>
Acked-by: Jack Wang <[email protected]> [rnbd]
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Jens Axboe <[email protected]>

show more ...

block: remove blk_cleanup_disk

blk_cleanup_disk is nothing but a trivial wrapper for put_disk now,
so remove it.

Signed-off-by: Christoph Hellwig <[email protected]>
Reviewed-by: Hannes Reinecke <hare@sus

block: remove blk_cleanup_disk

blk_cleanup_disk is nothing but a trivial wrapper for put_disk now,
so remove it.

Signed-off-by: Christoph Hellwig <[email protected]>
Reviewed-by: Hannes Reinecke <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Jens Axboe <[email protected]>

show more ...

block: remove QUEUE_FLAG_DISCARD

Just use a non-zero max_discard_sectors as an indicator for discard
support, similar to what is done for write zeroes.

The only places where needs special attention

block: remove QUEUE_FLAG_DISCARD

Just use a non-zero max_discard_sectors as an indicator for discard
support, similar to what is done for write zeroes.

The only places where needs special attention is the RAID5 driver,
which must clear discard support for security reasons by default,
even if the default stacking rules would allow for it.

Signed-off-by: Christoph Hellwig <[email protected]>
Reviewed-by: Martin K. Petersen <[email protected]>
Acked-by: Christoph Böhmwalder <[email protected]> [drbd]
Acked-by: Jan Höppner <[email protected]> [s390]
Acked-by: Coly Li <[email protected]> [bcache]
Acked-by: David Sterba <[email protected]> [btrfs]
Reviewed-by: Chaitanya Kulkarni <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Jens Axboe <[email protected]>

show more ...

mtd_blkdevs: avoid soft lockups with some mtd/spi devices

With some spi devices, the heavy cpu usage due to polling the spi
registers may lead to netdev timeouts, RCU complaints, etc. This can
be ac

mtd_blkdevs: avoid soft lockups with some mtd/spi devices

With some spi devices, the heavy cpu usage due to polling the spi
registers may lead to netdev timeouts, RCU complaints, etc. This can
be acute in the absence of CONFIG_PREEMPT. This patch allows to give
enough breathing room to avoid those incorrectly detected netdev
timeouts for example.

Example splat on 5.10.92:
[ 828.399306] rcu: INFO: rcu_sched self-detected stall on CPU
...
[ 828.419245] Task dump for CPU 1:
[ 828.422465] task:kworker/1:1H state:R running task on cpu 1 stack: 0 pid: 76 ppid: 2 flags:0x0000002a
[ 828.433132] Workqueue: kblockd blk_mq_run_work_fn
[ 828.437820] Call trace:
...
[ 828.512267] spi_mem_exec_op+0x4d0/0xde0
[ 828.516184] spi_mem_dirmap_read+0x180/0x39c
[ 828.520443] spi_nor_read_data+0x428/0x7e8
[ 828.524523] spi_nor_read+0x154/0x214
[ 828.528172] mtd_read_oob+0x440/0x714
[ 828.531815] mtd_read+0xac/0x120
[ 828.535030] mtdblock_readsect+0x178/0x230
[ 828.539102] mtd_blktrans_work+0x9fc/0xf28
[ 828.543177] mtd_queue_rq+0x1ac/0x2e4
[ 828.546827] blk_mq_dispatch_rq_list+0x2cc/0xa44
[ 828.551419] blk_mq_do_dispatch_sched+0xb0/0x7cc
[ 828.556010] __blk_mq_sched_dispatch_requests+0x350/0x494
[ 828.561372] blk_mq_sched_dispatch_requests+0xac/0xe4
[ 828.566387] __blk_mq_run_hw_queue+0x130/0x254
[ 828.570806] blk_mq_run_work_fn+0x50/0x60
[ 828.574814] process_one_work+0x578/0xf1c
[ 828.578814] worker_thread+0x5dc/0xea0
[ 828.582547] kthread+0x270/0x2d4
[ 828.585765] ret_from_fork+0x10/0x30

Signed-off-by: David Decotigny <[email protected]>
Reviewed-by: Richard Weinberger <[email protected]>
Signed-off-by: Miquel Raynal <[email protected]>
Link: https://lore.kernel.org/linux-mtd/[email protected]

show more ...

mtd_blkdevs: don't scan partitions for plain mtdblock

mtdblock / mtdblock_ro set part_bits to 0 and thus nevever scanned
partitions. Restore that behavior by setting the GENHD_FL_NO_PART flag.

Fix

mtd_blkdevs: don't scan partitions for plain mtdblock

mtdblock / mtdblock_ro set part_bits to 0 and thus nevever scanned
partitions. Restore that behavior by setting the GENHD_FL_NO_PART flag.

Fixes: 1ebe2e5f9d68e94c ("block: remove GENHD_FL_EXT_DEVT")
Reported-by: Geert Uytterhoeven <[email protected]>
Signed-off-by: Christoph Hellwig <[email protected]>
Tested-by: Geert Uytterhoeven <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Jens Axboe <[email protected]>

show more ...

Revert "mtd_blkdevs: don't scan partitions for plain mtdblock"

This reverts commit 776b54e97a7d993ba23696e032426d5dea5bbe70.

Looks like a last minute edit snuck into this patch, and as a result,
it

Revert "mtd_blkdevs: don't scan partitions for plain mtdblock"

This reverts commit 776b54e97a7d993ba23696e032426d5dea5bbe70.

Looks like a last minute edit snuck into this patch, and as a result,
it doesn't even compile. Revert the change for now.

Signed-off-by: Jens Axboe <[email protected]>

show more ...

mtd_blkdevs: don't scan partitions for plain mtdblock

mtdblock / mtdblock_ro set part_bits to 0 and thus nevever scanned
partitions. Restore that behavior by setting the GENHD_FL_NO_PART flag.

Fix

mtd_blkdevs: don't scan partitions for plain mtdblock

mtdblock / mtdblock_ro set part_bits to 0 and thus nevever scanned
partitions. Restore that behavior by setting the GENHD_FL_NO_PART flag.

Fixes: 1ebe2e5f9d68e94c ("block: remove GENHD_FL_EXT_DEVT")
Reported-by: Geert Uytterhoeven <[email protected]>
Signed-off-by: Christoph Hellwig <[email protected]>
Tested-by: Geert Uytterhoeven <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Jens Axboe <[email protected]>

show more ...

mtd_blkdevs: remove the sector out of range check in do_blktrans_request

The block layer already performs this check, no need to duplicate it in
the driver.

Signed-off-by: Christoph Hellwig <hch@ls

mtd_blkdevs: remove the sector out of range check in do_blktrans_request

The block layer already performs this check, no need to duplicate it in
the driver.

Signed-off-by: Christoph Hellwig <[email protected]>
Reviewed-by: Miquel Raynal <[email protected]>
Reviewed-by: Martin K. Petersen <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Jens Axboe <[email protected]>

show more ...

block: remove rq_flush_dcache_pages

This function is trivial, and flush_dcache_page is always defined, so
just open code it in the 2.5 callers.

Signed-off-by: Christoph Hellwig <[email protected]>
Reviewe

block: remove rq_flush_dcache_pages

This function is trivial, and flush_dcache_page is always defined, so
just open code it in the 2.5 callers.

Signed-off-by: Christoph Hellwig <[email protected]>
Reviewed-by: Johannes Thumshirn <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Jens Axboe <[email protected]>

show more ...

mtd: add add_disk() error handling

We never checked for errors on add_disk() as this function
returned void. Now that this is fixed, use the shiny new
error handling.

Acked-by: Miquel Raynal <mique

mtd: add add_disk() error handling

We never checked for errors on add_disk() as this function
returned void. Now that this is fixed, use the shiny new
error handling.

Acked-by: Miquel Raynal <[email protected]>
Signed-off-by: Luis Chamberlain <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Jens Axboe <[email protected]>

show more ...

mtd_blkdevs: simplify the refcounting in blktrans_{open, release}

Always grab a reference to the mtd_blktrans_dev in ->open instead of
just on the first open, and do away with the additional tempora

mtd_blkdevs: simplify the refcounting in blktrans_{open, release}

Always grab a reference to the mtd_blktrans_dev in ->open instead of
just on the first open, and do away with the additional temporary
references in ->open and ->release.

Signed-off-by: Christoph Hellwig <[email protected]>
Signed-off-by: Miquel Raynal <[email protected]>
Link: https://lore.kernel.org/linux-mtd/[email protected]

show more ...

mtd_blkdevs: simplify blktrans_getgeo

No need to grab a mtd_blktrans_dev given that ->open already holds one
and ->getgeo can only be called on an open disk.

Signed-off-by: Christoph Hellwig <hch@l

mtd_blkdevs: simplify blktrans_getgeo

No need to grab a mtd_blktrans_dev given that ->open already holds one
and ->getgeo can only be called on an open disk.

Signed-off-by: Christoph Hellwig <[email protected]>
Signed-off-by: Miquel Raynal <[email protected]>
Link: https://lore.kernel.org/linux-mtd/[email protected]

show more ...

mtd_blkdevs: remove blktrans_ref_mutex

blktrans_ref_mutex is not actually needed. The kref is serialized
internally, and devnum assignment in add_mtd_blktrans_dev happens before
the disk is added a

mtd_blkdevs: remove blktrans_ref_mutex

blktrans_ref_mutex is not actually needed. The kref is serialized
internally, and devnum assignment in add_mtd_blktrans_dev happens before
the disk is added and thus any of the block_device_operations methods
otherwise using it are called. It is also already serialized by the
global mtd_table_mutex.

Signed-off-by: Christoph Hellwig <[email protected]>
Signed-off-by: Miquel Raynal <[email protected]>
Link: https://lore.kernel.org/linux-mtd/[email protected]

show more ...