linux-stable.git/drivers/block/brd.c, branch v6.12

brd: add missing MODULE_DESCRIPTION() macro

2024-06-24T14:38:52+00:00

make allmodconfig && make W=1 C=1 reports:
modpost: missing MODULE_DESCRIPTION() in drivers/block/brd.o

Add the missing invocation of the MODULE_DESCRIPTION() macro.

Signed-off-by: Jeff Johnson 
Link: https://lore.kernel.org/r/20240602-md-block-brd-v1-1-e71338e131b6@quicinc.com
Signed-off-by: Jens Axboe

block: move the nowait flag to queue_limits

2024-06-19T13:58:28+00:00

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

Stacking drivers are simplified in that they now can simply set the
flag, and blk_stack_limits will clear it when the features is not
supported by any of the underlying devices.

Signed-off-by: Christoph Hellwig 
Reviewed-by: Damien Le Moal 
Reviewed-by: Hannes Reinecke 
Link: https://lore.kernel.org/r/20240617060532.127975-20-hch@lst.de
Signed-off-by: Jens Axboe

block: move the synchronous flag to queue_limits

2024-06-19T13:58:28+00:00

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

Signed-off-by: Christoph Hellwig 
Reviewed-by: Damien Le Moal 
Reviewed-by: Hannes Reinecke 
Link: https://lore.kernel.org/r/20240617060532.127975-19-hch@lst.de
Signed-off-by: Jens Axboe

block: move the nonrot flag to queue_limits

2024-06-19T13:58:28+00:00

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 
Reviewed-by: Damien Le Moal 
Reviewed-by: Hannes Reinecke 
Link: https://lore.kernel.org/r/20240617060532.127975-15-hch@lst.de
Signed-off-by: Jens Axboe

brd: implement discard support

2024-05-14T03:47:51+00:00

The ramdisk memory utilization can only go up when data is written to
new pages. Implement discard to provide the possibility to reduce memory
usage for pages no longer in use. Aligned discards will free the
associated pages, if any, and determinisitically return zeroed data
until written again.

Signed-off-by: Keith Busch 
Link: https://lore.kernel.org/r/20240429102308.147627-1-kbusch@meta.com
Signed-off-by: Jens Axboe

brd: Remove use of page->index

2024-04-01T17:53:36+00:00

This debugging check will become more costly in the future when we shrink
struct page.  It has not proven to be useful, so simply remove it.

This lets us use __xa_insert instead of __xa_cmpxchg() as we no longer
need to know about the page that is currently stored in the XArray.

Signed-off-by: Matthew Wilcox (Oracle) 
Reviewed-by: Hannes Reinecke 
Reviewed-by: Keith Busch 
Link: https://lore.kernel.org/r/20240315181212.2573753-1-willy@infradead.org
Signed-off-by: Jens Axboe

brd: pass queue_limits to blk_mq_alloc_disk

2024-02-19T23:58:23+00:00

Pass the queue limits directly to blk_alloc_disk instead of setting them
one at a time.

Signed-off-by: Christoph Hellwig 
Reviewed-by: Chaitanya Kulkarni 
Reviewed-by: Dan Williams 
Reviewed-by: Himanshu Madhani 
Link: https://lore.kernel.org/r/20240215071055.2201424-4-hch@lst.de
Signed-off-by: Jens Axboe

block: pass a queue_limits argument to blk_alloc_disk

2024-02-19T23:58:23+00:00

Pass a queue_limits to blk_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.

Also change blk_alloc_disk to return an ERR_PTR instead of just NULL
which can't distinguish errors.

Signed-off-by: Christoph Hellwig 
Reviewed-by: Dan Williams 
Reviewed-by: Himanshu Madhani 
Link: https://lore.kernel.org/r/20240215071055.2201424-2-hch@lst.de
Signed-off-by: Jens Axboe

brd: use cond_resched instead of cond_resched_rcu

2023-06-14T17:13:07+00:00

The body of the loop is run without RCU lock held. Use the regular
cond_resched() instead of cond_resched_rcu().

Fixes: 786bb0245881 ("brd: use XArray instead of radix-tree to index backing pages")
Suggested-by: Matthew Wilcox (Oracle) 
Signed-off-by: Pankaj Raghav 
Reviewed-by: Hannes Reinecke 
Link: https://lore.kernel.org/r/20230614133538.1279369-1-p.raghav@samsung.com
Signed-off-by: Jens Axboe

brd: use XArray instead of radix-tree to index backing pages

2023-05-16T15:03:23+00:00

XArray was introduced to hold large array of pointers with a simple API.
XArray API also provides array semantics which simplifies the way we store
and access the backing pages, and the code becomes significantly easier
to understand.

No performance difference was noticed between the two implementation
using fio with direct=1 [1].

[1] Performance in KIOPS:

          |  radix-tree |    XArray  |   Diff
          |             |            |
write     |    315      |     313    |   -0.6%
randwrite |    286      |     290    |   +1.3%
read      |    330      |     335    |   +1.5%
randread  |    309      |     312    |   +0.9%

Signed-off-by: Pankaj Raghav 
Reviewed-by: Hannes Reinecke 
Link: https://lore.kernel.org/r/20230511121544.111648-1-p.raghav@samsung.com
Signed-off-by: Jens Axboe