block: ublk: switch to ioctl command encoding

All ublk commands(control, IO) should have taken ioctl command encoding
from the beginning, because ioctl command encoding defines each code
uniquely, s

block: ublk: switch to ioctl command encoding

All ublk commands(control, IO) should have taken ioctl command encoding
from the beginning, because ioctl command encoding defines each code
uniquely, so driver can figure out wrong command sent from userspace
easily; 2) it might help security subsystem for audit uring cmd[1].

Unfortunately we didn't do that way, and it could be one lesson for
ublk driver.

So switch to ioctl command encoding now, we still support commands encoded
in old way, but they become legacy definition. Any new command should take
ioctl encoding.

See ublksrv code for switching to ioctl command encoding in [2].

[1] https://lore.kernel.org/io-uring/CAHC9VhSVzujW9LOj5Km80AjU0EfAuukoLrxO6BEfnXeK_s6bAg@mail.gmail.com/
[2] https://github.com/ming1/ubdsrv/commits/ioctl_cmd_encoding

Cc: Christoph Hellwig <hch@infradead.org>
Cc: Ken Kurematsu <k.kurematsu@nskint.co.jp>
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Link: https://lore.kernel.org/r/20230418131810.855959-1-ming.lei@redhat.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>

show more ...

drivers/block: Move PARIDE protocol modules to drivers/ata/pata_parport

Move PARIDE protocol modules out of drivers/block into
drivers/ata/pata_parport and update the CONFIG_ symbol names to
PATA_PA

drivers/block: Move PARIDE protocol modules to drivers/ata/pata_parport

Move PARIDE protocol modules out of drivers/block into
drivers/ata/pata_parport and update the CONFIG_ symbol names to
PATA_PARPORT.

[Damien]
The pata_parport driver file itsef is also moved together with the
protocol modules in drivers/ata/pata_parport.

Signed-off-by: Ondrej Zary <linux@zary.sk>
Acked-by: Jens Axboe <axboe@kernel.dk>
Signed-off-by: Damien Le Moal <damien.lemoal@opensource.wdc.com>

show more ...

drivers/block: Remove PARIDE core and high-level protocols

Remove PARIDE core and high level protocols, taking care not to break
low-level drivers (used by pata_parport). Also update documentation.

drivers/block: Remove PARIDE core and high-level protocols

Remove PARIDE core and high level protocols, taking care not to break
low-level drivers (used by pata_parport). Also update documentation.

Signed-off-by: Ondrej Zary <linux@zary.sk>
Acked-by: Jens Axboe <axboe@kernel.dk>
Signed-off-by: Damien Le Moal <damien.lemoal@opensource.wdc.com>

show more ...

Revert "pktcdvd: remove driver."

This reverts commit f40eb99897af665f11858dd7b56edcb62c3f3c67.

There are apparently still users out there of this driver. While we'd
love to remove it to ease the ma

Revert "pktcdvd: remove driver."

This reverts commit f40eb99897af665f11858dd7b56edcb62c3f3c67.

There are apparently still users out there of this driver. While we'd
love to remove it to ease the maintenance burden, let's reinstate it
for now until better (userspace) solutions can be developed.

Link: https://lore.kernel.org/lkml/20230104190115.ceglfefco475ev6c@pali/
Reported-by: Pali Rohár <pali@kernel.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

show more ...

pktcdvd: remove driver.

Way back in 2016 in commit 5a8b187c61e9 ("pktcdvd: mark as unmaintained
and deprecated") this driver was marked as "will be removed soon". 5
years seems long enough to have

pktcdvd: remove driver.

Way back in 2016 in commit 5a8b187c61e9 ("pktcdvd: mark as unmaintained
and deprecated") this driver was marked as "will be removed soon". 5
years seems long enough to have it stick around after that, so finally
remove the thing now.

Reported-by: Christoph Hellwig <hch@infradead.org>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Thomas Maier <balagi@justmail.de>
Cc: Peter Osterlund <petero2@telia.com>
Cc: linux-block@vger.kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Link: https://lore.kernel.org/r/20221202182758.1339039-1-gregkh@linuxfoundation.org
Signed-off-by: Jens Axboe <axboe@kernel.dk>

show more ...

ublk_drv: comment on ublk_driver entry of Kconfig

Add help info for choosing to build ublk_drv as module or builtin.

Signed-off-by: Ming Lei <ming.lei@redhat.com>
Reviewed-by: ZiyangZhang <ZiyangZh

ublk_drv: comment on ublk_driver entry of Kconfig

Add help info for choosing to build ublk_drv as module or builtin.

Signed-off-by: Ming Lei <ming.lei@redhat.com>
Reviewed-by: ZiyangZhang <ZiyangZhang@linux.alibaba.com>
Link: https://lore.kernel.org/r/20221029010432.598367-3-ming.lei@redhat.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>

show more ...

remove the sx8 block driver

This driver is for fairly obscure hardware, and has only seen random
drive-by changes after the maintainer stopped working on it in 2005
(about a year and a half after it

remove the sx8 block driver

This driver is for fairly obscure hardware, and has only seen random
drive-by changes after the maintainer stopped working on it in 2005
(about a year and a half after it was introduced). It has some
"interesting" block layer interactions, so let's just drop it unless
anyone complains.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Link: https://lore.kernel.org/r/20220721064102.1715460-1-hch@lst.de
[axboe: fix date typo, it was in 2005, not 2015]
Signed-off-by: Jens Axboe <axboe@kernel.dk>

show more ...

ublk_drv: add io_uring based userspace block driver

This is the driver part of userspace block driver(ublk driver), the other
part is userspace daemon part(ublksrv)[1].

The two parts communicate by

ublk_drv: add io_uring based userspace block driver

This is the driver part of userspace block driver(ublk driver), the other
part is userspace daemon part(ublksrv)[1].

The two parts communicate by io_uring's IORING_OP_URING_CMD with one
shared cmd buffer for storing io command, and the buffer is read only for
ublksrv, each io command is indexed by io request tag directly, and is
written by ublk driver.

For example, when one READ io request is submitted to ublk block driver,
ublk driver stores the io command into cmd buffer first, then completes
one IORING_OP_URING_CMD for notifying ublksrv, and the URING_CMD is issued
to ublk driver beforehand by ublksrv for getting notification of any new
io request, and each URING_CMD is associated with one io request by tag.

After ublksrv gets the io command, it translates and handles the ublk io
request, such as, for the ublk-loop target, ublksrv translates the request
into same request on another file or disk, like the kernel loop block
driver. In ublksrv's implementation, the io is still handled by io_uring,
and share same ring with IORING_OP_URING_CMD command. When the target io
request is done, the same IORING_OP_URING_CMD is issued to ublk driver for
both committing io request result and getting future notification of new
io request.

Another thing done by ublk driver is to copy data between kernel io
request and ublksrv's io buffer:

1) before ubsrv handles WRITE request, copy the request's data into
ublksrv's userspace io buffer, so that ublksrv can handle the write
request

2) after ubsrv handles READ request, copy ublksrv's userspace io buffer
into this READ request, then ublk driver can complete the READ request

Zero copy may be switched if mm is ready to support it.

ublk driver doesn't handle any logic of the specific user space driver,
so it is small/simple enough.

[1] ublksrv

https://github.com/ming1/ubdsrv

Signed-off-by: Ming Lei <ming.lei@redhat.com>
Link: https://lore.kernel.org/r/20220713140711.97356-2-ming.lei@redhat.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>

show more ...

floppy: disable FDRAWCMD by default

Minh Yuan reported a concurrency use-after-free issue in the floppy code
between raw_cmd_ioctl and seek_interrupt.

[ It turns out this has been around, and that

floppy: disable FDRAWCMD by default

Minh Yuan reported a concurrency use-after-free issue in the floppy code
between raw_cmd_ioctl and seek_interrupt.

[ It turns out this has been around, and that others have reported the
KASAN splats over the years, but Minh Yuan had a reproducer for it and
so gets primary credit for reporting it for this fix - Linus ]

The problem is, this driver tends to break very easily and nowadays,
nobody is expected to use FDRAWCMD anyway since it was used to
manipulate non-standard formats. The risk of breaking the driver is
higher than the risk presented by this race, and accessing the device
requires privileges anyway.

Let's just add a config option to completely disable this ioctl and
leave it disabled by default. Distros shouldn't use it, and only those
running on antique hardware might need to enable it.

Link: https://lore.kernel.org/all/000000000000b71cdd05d703f6bf@google.com/
Link: https://lore.kernel.org/lkml/CAKcFiNC=MfYVW-Jt9A3=FPJpTwCD2PL_ULNCpsCVE5s8ZeBQgQ@mail.gmail.com
Link: https://lore.kernel.org/all/CAEAjamu1FRhz6StCe_55XY5s389ZP_xmCF69k987En+1z53=eg@mail.gmail.com
Reported-by: Minh Yuan <yuanmingbuaa@gmail.com>
Reported-by: syzbot+8e8958586909d62b6840@syzkaller.appspotmail.com
Reported-by: cruise k <cruise4k@gmail.com>
Reported-by: Kyungtae Kim <kt0755@gmail.com>
Suggested-by: Linus Torvalds <torvalds@linuxfoundation.org>
Tested-by: Denis Efremov <efremov@linux.com>
Signed-off-by: Willy Tarreau <w@1wt.eu>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

show more ...

block: remove the rsxx driver

This driver was for rare and shortlived high end enterprise hardware
and hasn't been maintained since 2014, which also means it never got
converted to use blk-mq.

Sign

block: remove the rsxx driver

This driver was for rare and shortlived high end enterprise hardware
and hasn't been maintained since 2014, which also means it never got
converted to use blk-mq.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

show more ...

virtio-blk: avoid preallocating big SGL for data

No need to pre-allocate a big buffer for the IO SGL anymore. If a device
has lots of deep queues, preallocation for the sg list can consume
substanti

virtio-blk: avoid preallocating big SGL for data

No need to pre-allocate a big buffer for the IO SGL anymore. If a device
has lots of deep queues, preallocation for the sg list can consume
substantial amounts of memory. For HW virtio-blk device, nr_hw_queues
can be 64 or 128 and each queue's depth might be 128. This means the
resulting preallocation for the data SGLs is big.

Switch to runtime allocation for SGL for lists longer than 2 entries.
This is the approach used by NVMe drivers so it should be reasonable for
virtio block as well. Runtime SGL allocation has always been the case
for the legacy I/O path so this is nothing new.

The preallocated small SGL depends on SG_CHAIN so if the ARCH doesn't
support SG_CHAIN, use only runtime allocation for the SGL.

Re-organize the setup of the IO request to fit the new sg chain
mechanism.

No performance degradation was seen (fio libaio engine with 16 jobs and
128 iodepth):

IO size IOPs Rand Read (before/after) IOPs Rand Write (before/after)
-------- --------------------------------- ----------------------------------
512B 318K/316K 329K/325K

4KB 323K/321K 353K/349K

16KB 199K/208K 250K/275K

128KB 36K/36.1K 39.2K/41.7K

Signed-off-by: Max Gurtovoy <mgurtovoy@nvidia.com>
Reviewed-by: Israel Rukshin <israelr@nvidia.com>
Link: https://lore.kernel.org/r/20210901131434.31158-1-mgurtovoy@nvidia.com
Reviewed-by: Feng Li <lifeng1519@gmail.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Tested-by: Stefan Hajnoczi <stefanha@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Arnd Bergmann <arnd@arndb.de> # kconfig fixups
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>

show more ...

block: remove support for cryptoloop and the xor transfer

Support for cyrptoloop has been officially marked broken and deprecated
in favor of dm-crypt (which supports the same broken algorithms if
n

block: remove support for cryptoloop and the xor transfer

Support for cyrptoloop has been officially marked broken and deprecated
in favor of dm-crypt (which supports the same broken algorithms if
needed) in Linux 2.6.4 (released in March 2004), and support for it has
been entirely removed from losetup in util-linux 2.23 (released in April
2013). The XOR transfer has never been more than a toy to demonstrate
the transfer in the bad old times of crypto export restrictions.
Remove them as they have some nasty interactions with loop device life
times due to the iteration over all loop devices in
loop_unregister_transfer.

Suggested-by: Milan Broz <gmazyland@gmail.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Link: https://lore.kernel.org/r/20211019075639.2333969-1-hch@lst.de
Signed-off-by: Jens Axboe <axboe@kernel.dk>

show more ...

scsi: add a scsi_alloc_request helper

Add a new helper that calls blk_get_request and initializes the
scsi_request to avoid the indirect call through ->.initialize_rq_fn.

Note that this makes the p

scsi: add a scsi_alloc_request helper

Add a new helper that calls blk_get_request and initializes the
scsi_request to avoid the indirect call through ->.initialize_rq_fn.

Note that this makes the pktcdvd driver depend on the SCSI core, but
given that only SCSI devices support SCSI passthrough requests that
is not a functional change.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Link: https://lore.kernel.org/r/20211021060607.264371-6-hch@lst.de
Signed-off-by: Jens Axboe <axboe@kernel.dk>

show more ...

virtio-blk: avoid preallocating big SGL for data

[ Upstream commit 02746e26c39ee473b975e0f68d1295abc92672ed ]

No need to pre-allocate a big buffer for the IO SGL anymore. If a device
has lots of de

virtio-blk: avoid preallocating big SGL for data

[ Upstream commit 02746e26c39ee473b975e0f68d1295abc92672ed ]

No need to pre-allocate a big buffer for the IO SGL anymore. If a device
has lots of deep queues, preallocation for the sg list can consume
substantial amounts of memory. For HW virtio-blk device, nr_hw_queues
can be 64 or 128 and each queue's depth might be 128. This means the
resulting preallocation for the data SGLs is big.

Switch to runtime allocation for SGL for lists longer than 2 entries.
This is the approach used by NVMe drivers so it should be reasonable for
virtio block as well. Runtime SGL allocation has always been the case
for the legacy I/O path so this is nothing new.

The preallocated small SGL depends on SG_CHAIN so if the ARCH doesn't
support SG_CHAIN, use only runtime allocation for the SGL.

Re-organize the setup of the IO request to fit the new sg chain
mechanism.

No performance degradation was seen (fio libaio engine with 16 jobs and
128 iodepth):

IO size IOPs Rand Read (before/after) IOPs Rand Write (before/after)
-------- --------------------------------- ----------------------------------
512B 318K/316K 329K/325K

4KB 323K/321K 353K/349K

16KB 199K/208K 250K/275K

128KB 36K/36.1K 39.2K/41.7K

Signed-off-by: Max Gurtovoy <mgurtovoy@nvidia.com>
Reviewed-by: Israel Rukshin <israelr@nvidia.com>
Link: https://lore.kernel.org/r/20210901131434.31158-1-mgurtovoy@nvidia.com
Reviewed-by: Feng Li <lifeng1519@gmail.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Tested-by: Stefan Hajnoczi <stefanha@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Arnd Bergmann <arnd@arndb.de> # kconfig fixups
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>

show more ...

virtio-blk: avoid preallocating big SGL for data

[ Upstream commit 02746e26c39ee473b975e0f68d1295abc92672ed ]

No need to pre-allocate a big buffer for the IO SGL anymore. If a device
has lots of de

virtio-blk: avoid preallocating big SGL for data

[ Upstream commit 02746e26c39ee473b975e0f68d1295abc92672ed ]

No need to pre-allocate a big buffer for the IO SGL anymore. If a device
has lots of deep queues, preallocation for the sg list can consume
substantial amounts of memory. For HW virtio-blk device, nr_hw_queues
can be 64 or 128 and each queue's depth might be 128. This means the
resulting preallocation for the data SGLs is big.

Switch to runtime allocation for SGL for lists longer than 2 entries.
This is the approach used by NVMe drivers so it should be reasonable for
virtio block as well. Runtime SGL allocation has always been the case
for the legacy I/O path so this is nothing new.

The preallocated small SGL depends on SG_CHAIN so if the ARCH doesn't
support SG_CHAIN, use only runtime allocation for the SGL.

Re-organize the setup of the IO request to fit the new sg chain
mechanism.

No performance degradation was seen (fio libaio engine with 16 jobs and
128 iodepth):

IO size IOPs Rand Read (before/after) IOPs Rand Write (before/after)
-------- --------------------------------- ----------------------------------
512B 318K/316K 329K/325K

4KB 323K/321K 353K/349K

16KB 199K/208K 250K/275K

128KB 36K/36.1K 39.2K/41.7K

Signed-off-by: Max Gurtovoy <mgurtovoy@nvidia.com>
Reviewed-by: Israel Rukshin <israelr@nvidia.com>
Link: https://lore.kernel.org/r/20210901131434.31158-1-mgurtovoy@nvidia.com
Reviewed-by: Feng Li <lifeng1519@gmail.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Tested-by: Stefan Hajnoczi <stefanha@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Arnd Bergmann <arnd@arndb.de> # kconfig fixups
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>

show more ...

virtio-blk: avoid preallocating big SGL for data

[ Upstream commit 02746e26c39ee473b975e0f68d1295abc92672ed ]

No need to pre-allocate a big buffer for the IO SGL anymore. If a device
has lots of de

virtio-blk: avoid preallocating big SGL for data

[ Upstream commit 02746e26c39ee473b975e0f68d1295abc92672ed ]

No need to pre-allocate a big buffer for the IO SGL anymore. If a device
has lots of deep queues, preallocation for the sg list can consume
substantial amounts of memory. For HW virtio-blk device, nr_hw_queues
can be 64 or 128 and each queue's depth might be 128. This means the
resulting preallocation for the data SGLs is big.

Switch to runtime allocation for SGL for lists longer than 2 entries.
This is the approach used by NVMe drivers so it should be reasonable for
virtio block as well. Runtime SGL allocation has always been the case
for the legacy I/O path so this is nothing new.

The preallocated small SGL depends on SG_CHAIN so if the ARCH doesn't
support SG_CHAIN, use only runtime allocation for the SGL.

Re-organize the setup of the IO request to fit the new sg chain
mechanism.

No performance degradation was seen (fio libaio engine with 16 jobs and
128 iodepth):

IO size IOPs Rand Read (before/after) IOPs Rand Write (before/after)
-------- --------------------------------- ----------------------------------
512B 318K/316K 329K/325K

4KB 323K/321K 353K/349K

16KB 199K/208K 250K/275K

128KB 36K/36.1K 39.2K/41.7K

Signed-off-by: Max Gurtovoy <mgurtovoy@nvidia.com>
Reviewed-by: Israel Rukshin <israelr@nvidia.com>
Link: https://lore.kernel.org/r/20210901131434.31158-1-mgurtovoy@nvidia.com
Reviewed-by: Feng Li <lifeng1519@gmail.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Tested-by: Stefan Hajnoczi <stefanha@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Arnd Bergmann <arnd@arndb.de> # kconfig fixups
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>

show more ...

virtio-blk: avoid preallocating big SGL for data

[ Upstream commit 02746e26c39ee473b975e0f68d1295abc92672ed ]

No need to pre-allocate a big buffer for the IO SGL anymore. If a device
has lots of de

virtio-blk: avoid preallocating big SGL for data

[ Upstream commit 02746e26c39ee473b975e0f68d1295abc92672ed ]

No need to pre-allocate a big buffer for the IO SGL anymore. If a device
has lots of deep queues, preallocation for the sg list can consume
substantial amounts of memory. For HW virtio-blk device, nr_hw_queues
can be 64 or 128 and each queue's depth might be 128. This means the
resulting preallocation for the data SGLs is big.

Switch to runtime allocation for SGL for lists longer than 2 entries.
This is the approach used by NVMe drivers so it should be reasonable for
virtio block as well. Runtime SGL allocation has always been the case
for the legacy I/O path so this is nothing new.

The preallocated small SGL depends on SG_CHAIN so if the ARCH doesn't
support SG_CHAIN, use only runtime allocation for the SGL.

Re-organize the setup of the IO request to fit the new sg chain
mechanism.

No performance degradation was seen (fio libaio engine with 16 jobs and
128 iodepth):

IO size IOPs Rand Read (before/after) IOPs Rand Write (before/after)
-------- --------------------------------- ----------------------------------
512B 318K/316K 329K/325K

4KB 323K/321K 353K/349K

16KB 199K/208K 250K/275K

128KB 36K/36.1K 39.2K/41.7K

Signed-off-by: Max Gurtovoy <mgurtovoy@nvidia.com>
Reviewed-by: Israel Rukshin <israelr@nvidia.com>
Link: https://lore.kernel.org/r/20210901131434.31158-1-mgurtovoy@nvidia.com
Reviewed-by: Feng Li <lifeng1519@gmail.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Tested-by: Stefan Hajnoczi <stefanha@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Arnd Bergmann <arnd@arndb.de> # kconfig fixups
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>

show more ...

virtio-blk: avoid preallocating big SGL for data

[ Upstream commit 02746e26c39ee473b975e0f68d1295abc92672ed ]

No need to pre-allocate a big buffer for the IO SGL anymore. If a device
has lots of de

virtio-blk: avoid preallocating big SGL for data

[ Upstream commit 02746e26c39ee473b975e0f68d1295abc92672ed ]

No need to pre-allocate a big buffer for the IO SGL anymore. If a device
has lots of deep queues, preallocation for the sg list can consume
substantial amounts of memory. For HW virtio-blk device, nr_hw_queues
can be 64 or 128 and each queue's depth might be 128. This means the
resulting preallocation for the data SGLs is big.

Switch to runtime allocation for SGL for lists longer than 2 entries.
This is the approach used by NVMe drivers so it should be reasonable for
virtio block as well. Runtime SGL allocation has always been the case
for the legacy I/O path so this is nothing new.

The preallocated small SGL depends on SG_CHAIN so if the ARCH doesn't
support SG_CHAIN, use only runtime allocation for the SGL.

Re-organize the setup of the IO request to fit the new sg chain
mechanism.

No performance degradation was seen (fio libaio engine with 16 jobs and
128 iodepth):

IO size IOPs Rand Read (before/after) IOPs Rand Write (before/after)
-------- --------------------------------- ----------------------------------
512B 318K/316K 329K/325K

4KB 323K/321K 353K/349K

16KB 199K/208K 250K/275K

128KB 36K/36.1K 39.2K/41.7K

Signed-off-by: Max Gurtovoy <mgurtovoy@nvidia.com>
Reviewed-by: Israel Rukshin <israelr@nvidia.com>
Link: https://lore.kernel.org/r/20210901131434.31158-1-mgurtovoy@nvidia.com
Reviewed-by: Feng Li <lifeng1519@gmail.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Tested-by: Stefan Hajnoczi <stefanha@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Arnd Bergmann <arnd@arndb.de> # kconfig fixups
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>

show more ...

virtio-blk: avoid preallocating big SGL for data

[ Upstream commit 02746e26c39ee473b975e0f68d1295abc92672ed ]

No need to pre-allocate a big buffer for the IO SGL anymore. If a device
has lots of de

virtio-blk: avoid preallocating big SGL for data

[ Upstream commit 02746e26c39ee473b975e0f68d1295abc92672ed ]

No need to pre-allocate a big buffer for the IO SGL anymore. If a device
has lots of deep queues, preallocation for the sg list can consume
substantial amounts of memory. For HW virtio-blk device, nr_hw_queues
can be 64 or 128 and each queue's depth might be 128. This means the
resulting preallocation for the data SGLs is big.

Switch to runtime allocation for SGL for lists longer than 2 entries.
This is the approach used by NVMe drivers so it should be reasonable for
virtio block as well. Runtime SGL allocation has always been the case
for the legacy I/O path so this is nothing new.

The preallocated small SGL depends on SG_CHAIN so if the ARCH doesn't
support SG_CHAIN, use only runtime allocation for the SGL.

Re-organize the setup of the IO request to fit the new sg chain
mechanism.

No performance degradation was seen (fio libaio engine with 16 jobs and
128 iodepth):

IO size IOPs Rand Read (before/after) IOPs Rand Write (before/after)
-------- --------------------------------- ----------------------------------
512B 318K/316K 329K/325K

4KB 323K/321K 353K/349K

16KB 199K/208K 250K/275K

128KB 36K/36.1K 39.2K/41.7K

Signed-off-by: Max Gurtovoy <mgurtovoy@nvidia.com>
Reviewed-by: Israel Rukshin <israelr@nvidia.com>
Link: https://lore.kernel.org/r/20210901131434.31158-1-mgurtovoy@nvidia.com
Reviewed-by: Feng Li <lifeng1519@gmail.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Tested-by: Stefan Hajnoczi <stefanha@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Arnd Bergmann <arnd@arndb.de> # kconfig fixups
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>

show more ...

virtio-blk: avoid preallocating big SGL for data

[ Upstream commit 02746e26c39ee473b975e0f68d1295abc92672ed ]

No need to pre-allocate a big buffer for the IO SGL anymore. If a device
has lots of de

virtio-blk: avoid preallocating big SGL for data

[ Upstream commit 02746e26c39ee473b975e0f68d1295abc92672ed ]

No need to pre-allocate a big buffer for the IO SGL anymore. If a device
has lots of deep queues, preallocation for the sg list can consume
substantial amounts of memory. For HW virtio-blk device, nr_hw_queues
can be 64 or 128 and each queue's depth might be 128. This means the
resulting preallocation for the data SGLs is big.

Switch to runtime allocation for SGL for lists longer than 2 entries.
This is the approach used by NVMe drivers so it should be reasonable for
virtio block as well. Runtime SGL allocation has always been the case
for the legacy I/O path so this is nothing new.

The preallocated small SGL depends on SG_CHAIN so if the ARCH doesn't
support SG_CHAIN, use only runtime allocation for the SGL.

Re-organize the setup of the IO request to fit the new sg chain
mechanism.

No performance degradation was seen (fio libaio engine with 16 jobs and
128 iodepth):

IO size IOPs Rand Read (before/after) IOPs Rand Write (before/after)
-------- --------------------------------- ----------------------------------
512B 318K/316K 329K/325K

4KB 323K/321K 353K/349K

16KB 199K/208K 250K/275K

128KB 36K/36.1K 39.2K/41.7K

Signed-off-by: Max Gurtovoy <mgurtovoy@nvidia.com>
Reviewed-by: Israel Rukshin <israelr@nvidia.com>
Link: https://lore.kernel.org/r/20210901131434.31158-1-mgurtovoy@nvidia.com
Reviewed-by: Feng Li <lifeng1519@gmail.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Tested-by: Stefan Hajnoczi <stefanha@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Arnd Bergmann <arnd@arndb.de> # kconfig fixups
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>

show more ...

virtio-blk: avoid preallocating big SGL for data

[ Upstream commit 02746e26c39ee473b975e0f68d1295abc92672ed ]

No need to pre-allocate a big buffer for the IO SGL anymore. If a device
has lots of de

virtio-blk: avoid preallocating big SGL for data

[ Upstream commit 02746e26c39ee473b975e0f68d1295abc92672ed ]

No need to pre-allocate a big buffer for the IO SGL anymore. If a device
has lots of deep queues, preallocation for the sg list can consume
substantial amounts of memory. For HW virtio-blk device, nr_hw_queues
can be 64 or 128 and each queue's depth might be 128. This means the
resulting preallocation for the data SGLs is big.

Switch to runtime allocation for SGL for lists longer than 2 entries.
This is the approach used by NVMe drivers so it should be reasonable for
virtio block as well. Runtime SGL allocation has always been the case
for the legacy I/O path so this is nothing new.

The preallocated small SGL depends on SG_CHAIN so if the ARCH doesn't
support SG_CHAIN, use only runtime allocation for the SGL.

Re-organize the setup of the IO request to fit the new sg chain
mechanism.

No performance degradation was seen (fio libaio engine with 16 jobs and
128 iodepth):

IO size IOPs Rand Read (before/after) IOPs Rand Write (before/after)
-------- --------------------------------- ----------------------------------
512B 318K/316K 329K/325K

4KB 323K/321K 353K/349K

16KB 199K/208K 250K/275K

128KB 36K/36.1K 39.2K/41.7K

Signed-off-by: Max Gurtovoy <mgurtovoy@nvidia.com>
Reviewed-by: Israel Rukshin <israelr@nvidia.com>
Link: https://lore.kernel.org/r/20210901131434.31158-1-mgurtovoy@nvidia.com
Reviewed-by: Feng Li <lifeng1519@gmail.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Tested-by: Stefan Hajnoczi <stefanha@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Arnd Bergmann <arnd@arndb.de> # kconfig fixups
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>

show more ...

virtio-blk: avoid preallocating big SGL for data

[ Upstream commit 02746e26c39ee473b975e0f68d1295abc92672ed ]

No need to pre-allocate a big buffer for the IO SGL anymore. If a device
has lots of de

virtio-blk: avoid preallocating big SGL for data

[ Upstream commit 02746e26c39ee473b975e0f68d1295abc92672ed ]

No need to pre-allocate a big buffer for the IO SGL anymore. If a device
has lots of deep queues, preallocation for the sg list can consume
substantial amounts of memory. For HW virtio-blk device, nr_hw_queues
can be 64 or 128 and each queue's depth might be 128. This means the
resulting preallocation for the data SGLs is big.

Switch to runtime allocation for SGL for lists longer than 2 entries.
This is the approach used by NVMe drivers so it should be reasonable for
virtio block as well. Runtime SGL allocation has always been the case
for the legacy I/O path so this is nothing new.

The preallocated small SGL depends on SG_CHAIN so if the ARCH doesn't
support SG_CHAIN, use only runtime allocation for the SGL.

Re-organize the setup of the IO request to fit the new sg chain
mechanism.

No performance degradation was seen (fio libaio engine with 16 jobs and
128 iodepth):

IO size IOPs Rand Read (before/after) IOPs Rand Write (before/after)
-------- --------------------------------- ----------------------------------
512B 318K/316K 329K/325K

4KB 323K/321K 353K/349K

16KB 199K/208K 250K/275K

128KB 36K/36.1K 39.2K/41.7K

Signed-off-by: Max Gurtovoy <mgurtovoy@nvidia.com>
Reviewed-by: Israel Rukshin <israelr@nvidia.com>
Link: https://lore.kernel.org/r/20210901131434.31158-1-mgurtovoy@nvidia.com
Reviewed-by: Feng Li <lifeng1519@gmail.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Tested-by: Stefan Hajnoczi <stefanha@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Arnd Bergmann <arnd@arndb.de> # kconfig fixups
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>

show more ...

virtio-blk: avoid preallocating big SGL for data

[ Upstream commit 02746e26c39ee473b975e0f68d1295abc92672ed ]

No need to pre-allocate a big buffer for the IO SGL anymore. If a device
has lots of de

virtio-blk: avoid preallocating big SGL for data

[ Upstream commit 02746e26c39ee473b975e0f68d1295abc92672ed ]

No need to pre-allocate a big buffer for the IO SGL anymore. If a device
has lots of deep queues, preallocation for the sg list can consume
substantial amounts of memory. For HW virtio-blk device, nr_hw_queues
can be 64 or 128 and each queue's depth might be 128. This means the
resulting preallocation for the data SGLs is big.

Switch to runtime allocation for SGL for lists longer than 2 entries.
This is the approach used by NVMe drivers so it should be reasonable for
virtio block as well. Runtime SGL allocation has always been the case
for the legacy I/O path so this is nothing new.

The preallocated small SGL depends on SG_CHAIN so if the ARCH doesn't
support SG_CHAIN, use only runtime allocation for the SGL.

Re-organize the setup of the IO request to fit the new sg chain
mechanism.

No performance degradation was seen (fio libaio engine with 16 jobs and
128 iodepth):

IO size IOPs Rand Read (before/after) IOPs Rand Write (before/after)
-------- --------------------------------- ----------------------------------
512B 318K/316K 329K/325K

4KB 323K/321K 353K/349K

16KB 199K/208K 250K/275K

128KB 36K/36.1K 39.2K/41.7K

Signed-off-by: Max Gurtovoy <mgurtovoy@nvidia.com>
Reviewed-by: Israel Rukshin <israelr@nvidia.com>
Link: https://lore.kernel.org/r/20210901131434.31158-1-mgurtovoy@nvidia.com
Reviewed-by: Feng Li <lifeng1519@gmail.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Tested-by: Stefan Hajnoczi <stefanha@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Arnd Bergmann <arnd@arndb.de> # kconfig fixups
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>

show more ...

virtio-blk: avoid preallocating big SGL for data

[ Upstream commit 02746e26c39ee473b975e0f68d1295abc92672ed ]

No need to pre-allocate a big buffer for the IO SGL anymore. If a device
has lots of de

virtio-blk: avoid preallocating big SGL for data

[ Upstream commit 02746e26c39ee473b975e0f68d1295abc92672ed ]

No need to pre-allocate a big buffer for the IO SGL anymore. If a device
has lots of deep queues, preallocation for the sg list can consume
substantial amounts of memory. For HW virtio-blk device, nr_hw_queues
can be 64 or 128 and each queue's depth might be 128. This means the
resulting preallocation for the data SGLs is big.

Switch to runtime allocation for SGL for lists longer than 2 entries.
This is the approach used by NVMe drivers so it should be reasonable for
virtio block as well. Runtime SGL allocation has always been the case
for the legacy I/O path so this is nothing new.

The preallocated small SGL depends on SG_CHAIN so if the ARCH doesn't
support SG_CHAIN, use only runtime allocation for the SGL.

Re-organize the setup of the IO request to fit the new sg chain
mechanism.

No performance degradation was seen (fio libaio engine with 16 jobs and
128 iodepth):

IO size IOPs Rand Read (before/after) IOPs Rand Write (before/after)
-------- --------------------------------- ----------------------------------
512B 318K/316K 329K/325K

4KB 323K/321K 353K/349K

16KB 199K/208K 250K/275K

128KB 36K/36.1K 39.2K/41.7K

Signed-off-by: Max Gurtovoy <mgurtovoy@nvidia.com>
Reviewed-by: Israel Rukshin <israelr@nvidia.com>
Link: https://lore.kernel.org/r/20210901131434.31158-1-mgurtovoy@nvidia.com
Reviewed-by: Feng Li <lifeng1519@gmail.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Tested-by: Stefan Hajnoczi <stefanha@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Arnd Bergmann <arnd@arndb.de> # kconfig fixups
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>

show more ...

virtio-blk: avoid preallocating big SGL for data

[ Upstream commit 02746e26c39ee473b975e0f68d1295abc92672ed ]

No need to pre-allocate a big buffer for the IO SGL anymore. If a device
has lots of de

virtio-blk: avoid preallocating big SGL for data

[ Upstream commit 02746e26c39ee473b975e0f68d1295abc92672ed ]

No need to pre-allocate a big buffer for the IO SGL anymore. If a device
has lots of deep queues, preallocation for the sg list can consume
substantial amounts of memory. For HW virtio-blk device, nr_hw_queues
can be 64 or 128 and each queue's depth might be 128. This means the
resulting preallocation for the data SGLs is big.

Switch to runtime allocation for SGL for lists longer than 2 entries.
This is the approach used by NVMe drivers so it should be reasonable for
virtio block as well. Runtime SGL allocation has always been the case
for the legacy I/O path so this is nothing new.

The preallocated small SGL depends on SG_CHAIN so if the ARCH doesn't
support SG_CHAIN, use only runtime allocation for the SGL.

Re-organize the setup of the IO request to fit the new sg chain
mechanism.

No performance degradation was seen (fio libaio engine with 16 jobs and
128 iodepth):

IO size IOPs Rand Read (before/after) IOPs Rand Write (before/after)
-------- --------------------------------- ----------------------------------
512B 318K/316K 329K/325K

4KB 323K/321K 353K/349K

16KB 199K/208K 250K/275K

128KB 36K/36.1K 39.2K/41.7K

Signed-off-by: Max Gurtovoy <mgurtovoy@nvidia.com>
Reviewed-by: Israel Rukshin <israelr@nvidia.com>
Link: https://lore.kernel.org/r/20210901131434.31158-1-mgurtovoy@nvidia.com
Reviewed-by: Feng Li <lifeng1519@gmail.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Tested-by: Stefan Hajnoczi <stefanha@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Arnd Bergmann <arnd@arndb.de> # kconfig fixups
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>

show more ...