Change-Id: I00388d639f7b62355550197c9033dab7a996b916
Signed-off-by: Dark-Matter7232 <me@const.eu.org>
Signed-off-by: Richard Raya <rdxzv.dev@gmail.com>
This reverts commit d7fd8e47786a2781d2100f9fec3f38b5718914f6.
Change-Id: I05439cb3b974123b47d6cbad58a2252adaa3dc0b
Signed-off-by: Richard Raya <rdxzv.dev@gmail.com>
This reverts commit a252be0a7170bef864e281851d6a885e4ebfb193.
Change-Id: I52e6256688a154cc94beb6f52a8fd509861745ae
Signed-off-by: Richard Raya <rdxzv.dev@gmail.com>
This reverts commit 84e325d9cfea60ebb192d0f2307021ac818f8df7.
Change-Id: I59da5bae06fff3ea775cdcc938ee0dc327feb45d
Signed-off-by: Richard Raya <rdxzv.dev@gmail.com>
crc32_le and __crc32c_le can be overridden - extend this to crc32_be.
Change-Id: Ia51b0f97201903ba27bd22a345b781af13ef4a53
Signed-off-by: Kevin Bracey <kevin@bracey.fi>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: Jebaitedneko <Jebaitedneko@gmail.com>
Signed-off-by: Richard Raya <rdxzv.dev@gmail.com>
Casts were added in commit 8f243af42ade ("sections: fix const sections
for crc32 table") to cope with the tables not being const. They are no
longer required since commit f5e38b9284e1 ("lib: crc32: constify crc32
lookup table").
Change-Id: If601e66d4f0a753fba9c72698ba83c645409b634
Signed-off-by: Kevin Bracey <kevin@bracey.fi>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: Jebaitedneko <Jebaitedneko@gmail.com>
Signed-off-by: Richard Raya <rdxzv.dev@gmail.com>
Header was defining CRCPOLY_LE/BE and CRC32C_POLY_LE but in fact all of
them are CRC-32 polynomials so use consistent naming.
Change-Id: I21da6af43ebc69dcae24f2b97652728f739a2876
Signed-off-by: Krzysztof Kozlowski <krzk@kernel.org>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: Jebaitedneko <Jebaitedneko@gmail.com>
Signed-off-by: Richard Raya <rdxzv.dev@gmail.com>
Allow other drivers and parts of kernel to use the same define for
CRC32 polynomial, instead of duplicating it in many places. This code
does not bring any functional changes, except moving existing code.
Change-Id: Ibe919da197be32e1298d7b64c1602810bd3c0bb3
Signed-off-by: Krzysztof Kozlowski <krzk@kernel.org>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: Jebaitedneko <Jebaitedneko@gmail.com>
Signed-off-by: Richard Raya <rdxzv.dev@gmail.com>
Change-Id: Ia61397e4e71c3251e34def8d25d06f4f0f59a2f0
Signed-off-by: Jebaitedneko <Jebaitedneko@gmail.com>
Signed-off-by: Richard Raya <rdxzv.dev@gmail.com>
It makes no sense to leave crc32_be using the generic code while we
only accelerate the little-endian ops.
Even though the big-endian form doesn't fit as smoothly into the arm64,
we can speed it up and avoid hitting the D cache.
Tested on Cortex-A53. Without acceleration:
crc32: CRC_LE_BITS = 64, CRC_BE BITS = 64
crc32: self tests passed, processed 225944 bytes in 192240 nsec
crc32c: CRC_LE_BITS = 64
crc32c: self tests passed, processed 112972 bytes in 21360 nsec
With acceleration:
crc32: CRC_LE_BITS = 64, CRC_BE BITS = 64
crc32: self tests passed, processed 225944 bytes in 53480 nsec
crc32c: CRC_LE_BITS = 64
crc32c: self tests passed, processed 112972 bytes in 21480 nsec
Change-Id: I42ec0b2416ff44de4b6537dc8275c8777ebbbc3a
Acked-by: Catalin Marinas <catalin.marinas@arm.com>
Tested-by: Ard Biesheuvel <ardb@kernel.org>
Reviewed-by: Ard Biesheuvel <ardb@kernel.org>
Signed-off-by: Kevin Bracey <kevin@bracey.fi>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: Jebaitedneko <Jebaitedneko@gmail.com>
Signed-off-by: Richard Raya <rdxzv.dev@gmail.com>
* Currently most of the assembly files that use architecture
extensions enable them using the .arch directive but crc32.S
uses .cpu instead. Move that over to .arch for consistency.
Link: https://lore.kernel.org/r/20200414182843.31664-1-broonie@kernel.org
Change-Id: I675cbbe78927b1465d12e550d6ae688d5bce601e
Signed-off-by: Richard Raya <rdxzv.dev@gmail.com>
* Add a CRC32 feature bit and wire it up to the CPU id register so we
will be able to use alternatives patching for CRC32 operations.
Change-Id: Iae808f77016c242c74475f75a85190465088c6f8
Signed-off-by: Richard Raya <rdxzv.dev@gmail.com>
Remove the code for fair tag sharing because it significantly hurts
performance for UFS devices. Removing this code is safe because the
legacy block layer worked fine without any equivalent fairness
algorithm.
This algorithm hurts performance for UFS devices because UFS devices
have multiple logical units. One of these logical units (WLUN) is used
to submit control commands, e.g. START STOP UNIT. If any request is
submitted to the WLUN, the queue depth is reduced from 31 to 15 or
lower for data LUNs.
See also https://lore.kernel.org/linux-scsi/20221229030645.11558-1-ed.tsai@mediatek.com/
Bug: 281845090
Change-Id: Ia6d75917d533f32fffc68348b52fd3d972c9074c
Link: https://lore.kernel.org/linux-block/20230103195337.158625-1-bvanassche@acm.org/
Cc: Christoph Hellwig <hch@lst.de>
Cc: Martin K. Petersen <martin.petersen@oracle.com>
Cc: Ming Lei <ming.lei@redhat.com>
Cc: Keith Busch <kbusch@kernel.org>
Cc: Damien Le Moal <damien.lemoal@opensource.wdc.com>
Cc: Ed Tsai <ed.tsai@mediatek.com>
Signed-off-by: Bart Van Assche <bvanassche@acm.org>
Signed-off-by: Richard Raya <rdxzv.dev@gmail.com>
Switch an accidental use of DEFINE_PER_CPU when
the developer clearly wanted to use DECLARE_PER_CPU.
CONFIG_DEBUG_FORCE_WEAK_CPU enforces that each per-cpu object
in the kernel have a unique name so if one accidently uses
DEFINE_PER_CPU_READ_MOSTLY in a header it would define the same
symbol in each file that used the header.
Fixes: 0aaf4cf7415a ("drivers: soc: qcom: snapshot of idle/sleep driver as of msm-4.14")
Change-Id: Ic0dedbadbce4e85f2130ea59c84d1e10767d50d7
Signed-off-by: Jordan Crouse <jcrouse@codeaurora.org>
Signed-off-by: Richard Raya <rdxzv.dev@gmail.com>
Change-Id: I59f83fb9f2f13f246a57b771a410aeaf7392e6df
Signed-off-by: Samuel Pascua <pascua.samuel.14@gmail.com>
Signed-off-by: Richard Raya <rdxzv.dev@gmail.com>
A minor optimization to reduce IPIs.
Change-Id: Ifd6c94ad5cac9dc3646547818506ce47f2b0ff6a
Signed-off-by: Alexander Winkowski <dereference23@outlook.com>
Signed-off-by: Richard Raya <rdxzv.dev@gmail.com>
It may lead to pstore being lost which is not a desirable behavior.
Change-Id: I483db403c4abe9fc03119d3d31a049f9a6ec5754
Signed-off-by: Alexander Winkowski <dereference23@outlook.com>
Signed-off-by: Richard Raya <rdxzv.dev@gmail.com>
ShadowCallStack protects against stack buffer overflows; there is little
point in keeping both SCS and Stack Protector enabled. Runtime testing
showed that SCS is faster than Stack Protector.
Change-Id: Ibea0ea09055f2d1bf3d65b8f34fdfce4a5ca470b
Signed-off-by: Alexander Winkowski <dereference23@outlook.com>
Signed-off-by: Richard Raya <rdxzv.dev@gmail.com>
Disabling CT NETLINK won't hurt anything
in Android. Reduces NETLINK wakeups a bit.
Change-Id: I16670140779a2fe4f13f1e7849f7a77053396047
Signed-off-by: Richard Raya <rdxzv.dev@gmail.com>
Change-Id: Iaeeeb1491e8940bf870aac0e36a75591a286776d
Signed-off-by: Samuel Pascua <pascua.samuel.14@gmail.com>
Signed-off-by: Richard Raya <rdxzv.dev@gmail.com>
It does seem like functions that use those values suffer __A LOT__
after moving to 300 HZ, that causes terrible connectivity issues
on Mata and maybe other devices with bad antennas.
Change-Id: Ie2f4e4d3ce4beaedad733d58747cab592e2fb4e8
Signed-off-by: Yaroslav Furman <yaro330@gmail.com>
Signed-off-by: Richard Raya <rdxzv.dev@gmail.com>
There is no need to "select BUG" when CONFIG_HARDENED_USERCOPY is enabled.
The kernel thread will always die, regardless of the CONFIG_BUG.
Change-Id: I1e297a1c1d5fdf8ad48bed4088537e13066565a7
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
Signed-off-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Richard Raya <rdxzv.dev@gmail.com>
This caused so much performance regressions in hackbench.
Change-Id: Ib72d4f4aca54ee00799809d4eb2fcb6cdb1f4971
Signed-off-by: Tashfin Shakeer Rhythm <tashfinshakeerrhythm@gmail.com>
Signed-off-by: Richard Raya <rdxzv.dev@gmail.com>
Change-Id: I512afa97c7cc07a9200f0ba3265fc9b3fbca44cf
Signed-off-by: Alexander Winkowski <dereference23@outlook.com>
Signed-off-by: Richard Raya <rdxzv.dev@gmail.com>
Since this will be part of the scheduler's hotpath in some cases, use
unlikely() for few of the obvious conditionals.
Change-Id: I751f3189304326caeab7ccccc5df327f9be3c897
Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Signed-off-by: Richard Raya <rdxzv.dev@gmail.com>
That's a LONG wait. Don't busy wait there to save power.
Change-Id: I14069b2aaf1872d276932f9904d2c1a20ee0845c
Signed-off-by: Kazuki Hashimoto <kazukih@tuta.io>
Signed-off-by: Richard Raya <rdxzv.dev@gmail.com>
Change-Id: Iee0c13a5f0773c31b8a896d650fe9b61ab50828e
Signed-off-by: Cyber Knight <cyberknight755@gmail.com>
Signed-off-by: Richard Raya <rdxzv.dev@gmail.com>
For lower runtime overheads
Change-Id: Ic4e59db7be8f90d92660c3462c566b4568929655
Signed-off-by: Park Ju Hyung <qkrwngud825@gmail.com>
Signed-off-by: Richard Raya <rdxzv.dev@gmail.com>
Change-Id: I9e78135ea3c5644f3328da7b7424ea80a15c2f85
Signed-off-by: Samuel Pascua <pascua.samuel.14@gmail.com>
Signed-off-by: Richard Raya <rdxzv.dev@gmail.com>
Other stuff don't do anything or only there for debugging.
Change-Id: I2f2311dbafef0edcc89b9174605cb22b2169cf69
Signed-off-by: Kazuki Hashimoto <kazukih0205@gmail.com>
Signed-off-by: Richard Raya <rdxzv.dev@gmail.com>
Change-Id: I27814ed92ac864c92393ee674058b2ab07708905
Signed-off-by: Kazuki Hashimoto <kazukih0205@gmail.com>
Signed-off-by: Richard Raya <rdxzv.dev@gmail.com>
Change-Id: Ib7a07ea499910cc32e41a05d65d2e2b6f9d15bbc
Signed-off-by: Samuel Pascua <pascua.samuel.14@gmail.com>
Signed-off-by: Richard Raya <rdxzv.dev@gmail.com>
Page pool additions and removals are very hot during GPU workloads, so
they should be optimized accordingly. We can use a lock-less list for
storing the free pages in order to speed things up. The lock-less list
allows for one llist_del_first() user and unlimited llist_add() users to
run concurrently, so only a spin lock around the llist_del_first() is
needed; everything else is lock-free. The per-pool page count is now an
atomic to make it lock-free as well.
Change-Id: I5a1b6cef1eba2172728037ff5b38a2729c9e1d3e
Signed-off-by: Sultan Alsawaf <sultan@kerneltoast.com>
Signed-off-by: Richard Raya <rdxzv.dev@gmail.com>
This reverts commit ea9ce4d947b9e7177cb32046f497405947622030.
Change-Id: I37f4fda9b19ee4d102a451cd031ebfabadc90228
Signed-off-by: Richard Raya <rdxzv.dev@gmail.com>
This reverts commit 91be8a168642a6431da272c5400b21b297281d29.
Change-Id: I7b5f89e3c79a26b5614c2fe25b983e268993651f
Signed-off-by: Richard Raya <rdxzv.dev@gmail.com>
This reverts commit 032448d80056adeb00075e2883fc042fc334d1e8.
Change-Id: I142e5cf4220a4c093f6eb9537f9fcf948a5ad0e7
Signed-off-by: Richard Raya <rdxzv.dev@gmail.com>
