<feed xmlns='http://www.w3.org/2005/Atom'>
<title>kernel/linux.git/arch/arm64/lib/Makefile, branch v6.12.80</title>
<subtitle>Linux kernel stable tree (mirror)</subtitle>
<id>https://git.radix-linux.su/kernel/linux.git/atom?h=v6.12.80</id>
<link rel='self' href='https://git.radix-linux.su/kernel/linux.git/atom?h=v6.12.80'/>
<link rel='alternate' type='text/html' href='https://git.radix-linux.su/kernel/linux.git/'/>
<updated>2024-05-19T21:36:18+00:00</updated>
<entry>
<title>arm64: crypto: use CC_FLAGS_FPU for NEON CFLAGS</title>
<updated>2024-05-19T21:36:18+00:00</updated>
<author>
<name>Samuel Holland</name>
<email>samuel.holland@sifive.com</email>
</author>
<published>2024-03-29T07:18:20+00:00</published>
<link rel='alternate' type='text/html' href='https://git.radix-linux.su/kernel/linux.git/commit/?id=7177089525d97bd8d7fefd6a9406f45d818410e0'/>
<id>urn:sha1:7177089525d97bd8d7fefd6a9406f45d818410e0</id>
<content type='text'>
Now that CC_FLAGS_FPU is exported and can be used anywhere in the source
tree, use it instead of duplicating the flags here.

Link: https://lkml.kernel.org/r/20240329072441.591471-6-samuel.holland@sifive.com
Signed-off-by: Samuel Holland &lt;samuel.holland@sifive.com&gt;
Reviewed-by: Christoph Hellwig &lt;hch@lst.de&gt;
Acked-by: Christian König &lt;christian.koenig@amd.com&gt; 
Cc: Alex Deucher &lt;alexander.deucher@amd.com&gt;
Cc: Borislav Petkov (AMD) &lt;bp@alien8.de&gt;
Cc: Catalin Marinas &lt;catalin.marinas@arm.com&gt;
Cc: Dave Hansen &lt;dave.hansen@linux.intel.com&gt;
Cc: Huacai Chen &lt;chenhuacai@kernel.org&gt;
Cc: Ingo Molnar &lt;mingo@redhat.com&gt;
Cc: Jonathan Corbet &lt;corbet@lwn.net&gt;
Cc: Masahiro Yamada &lt;masahiroy@kernel.org&gt;
Cc: Michael Ellerman &lt;mpe@ellerman.id.au&gt;
Cc: Nathan Chancellor &lt;nathan@kernel.org&gt;
Cc: Nicolas Schier &lt;nicolas@fjasle.eu&gt;
Cc: Palmer Dabbelt &lt;palmer@rivosinc.com&gt;
Cc: Russell King &lt;linux@armlinux.org.uk&gt;
Cc: Thomas Gleixner &lt;tglx@linutronix.de&gt;
Cc: WANG Xuerui &lt;git@xen0n.name&gt;
Cc: Will Deacon &lt;will@kernel.org&gt;
Signed-off-by: Andrew Morton &lt;akpm@linux-foundation.org&gt;
</content>
</entry>
<entry>
<title>isystem: delete global -isystem compile option</title>
<updated>2021-09-22T00:26:24+00:00</updated>
<author>
<name>Alexey Dobriyan</name>
<email>adobriyan@gmail.com</email>
</author>
<published>2021-08-02T20:43:15+00:00</published>
<link rel='alternate' type='text/html' href='https://git.radix-linux.su/kernel/linux.git/commit/?id=04e85bbf71c9072dcf0ad9a7150495d72461105c'/>
<id>urn:sha1:04e85bbf71c9072dcf0ad9a7150495d72461105c</id>
<content type='text'>
Further isolate kernel from userspace, prevent accidental inclusion of
undesireable headers, mainly float.h and stdatomic.h.

nds32 keeps -isystem globally due to intrinsics used in entrenched header.

-isystem is selectively reenabled for some files, again, for intrinsics.

Compile tested on:

hexagon-defconfig hexagon-allmodconfig
alpha-allmodconfig alpha-allnoconfig alpha-defconfig arm64-allmodconfig
arm64-allnoconfig arm64-defconfig arm-am200epdkit arm-aspeed_g4
arm-aspeed_g5 arm-assabet arm-at91_dt arm-axm55xx arm-badge4 arm-bcm2835
arm-cerfcube arm-clps711x arm-cm_x300 arm-cns3420vb arm-colibri_pxa270
arm-colibri_pxa300 arm-collie arm-corgi arm-davinci_all arm-dove
arm-ep93xx arm-eseries_pxa arm-exynos arm-ezx arm-footbridge arm-gemini
arm-h3600 arm-h5000 arm-hackkit arm-hisi arm-imote2 arm-imx_v4_v5
arm-imx_v6_v7 arm-integrator arm-iop32x arm-ixp4xx arm-jornada720
arm-keystone arm-lart arm-lpc18xx arm-lpc32xx arm-lpd270 arm-lubbock
arm-magician arm-mainstone arm-milbeaut_m10v arm-mini2440 arm-mmp2
arm-moxart arm-mps2 arm-multi_v4t arm-multi_v5 arm-multi_v7 arm-mv78xx0
arm-mvebu_v5 arm-mvebu_v7 arm-mxs arm-neponset arm-netwinder arm-nhk8815
arm-omap1 arm-omap2plus arm-orion5x arm-oxnas_v6 arm-palmz72 arm-pcm027
arm-pleb arm-pxa arm-pxa168 arm-pxa255-idp arm-pxa3xx arm-pxa910
arm-qcom arm-realview arm-rpc arm-s3c2410 arm-s3c6400 arm-s5pv210
arm-sama5 arm-shannon arm-shmobile arm-simpad arm-socfpga arm-spear13xx
arm-spear3xx arm-spear6xx arm-spitz arm-stm32 arm-sunxi arm-tct_hammer
arm-tegra arm-trizeps4 arm-u8500 arm-versatile arm-vexpress arm-vf610m4
arm-viper arm-vt8500_v6_v7 arm-xcep arm-zeus csky-allmodconfig
csky-allnoconfig csky-defconfig h8300-edosk2674 h8300-h8300h-sim
h8300-h8s-sim i386-allmodconfig i386-allnoconfig i386-defconfig
ia64-allmodconfig ia64-allnoconfig ia64-bigsur ia64-generic ia64-gensparse
ia64-tiger ia64-zx1 m68k-amcore m68k-amiga m68k-apollo m68k-atari
m68k-bvme6000 m68k-hp300 m68k-m5208evb m68k-m5249evb m68k-m5272c3
m68k-m5275evb m68k-m5307c3 m68k-m5407c3 m68k-m5475evb m68k-mac
m68k-multi m68k-mvme147 m68k-mvme16x m68k-q40 m68k-stmark2 m68k-sun3
m68k-sun3x microblaze-allmodconfig microblaze-allnoconfig microblaze-mmu
mips-ar7 mips-ath25 mips-ath79 mips-bcm47xx mips-bcm63xx mips-bigsur
mips-bmips_be mips-bmips_stb mips-capcella mips-cavium_octeon mips-ci20
mips-cobalt mips-cu1000-neo mips-cu1830-neo mips-db1xxx mips-decstation
mips-decstation_64 mips-decstation_r4k mips-e55 mips-fuloong2e
mips-gcw0 mips-generic mips-gpr mips-ip22 mips-ip27 mips-ip28 mips-ip32
mips-jazz mips-jmr3927 mips-lemote2f mips-loongson1b mips-loongson1c
mips-loongson2k mips-loongson3 mips-malta mips-maltaaprp mips-malta_kvm
mips-malta_qemu_32r6 mips-maltasmvp mips-maltasmvp_eva mips-maltaup
mips-maltaup_xpa mips-mpc30x mips-mtx1 mips-nlm_xlp mips-nlm_xlr
mips-omega2p mips-pic32mzda mips-pistachio mips-qi_lb60 mips-rb532
mips-rbtx49xx mips-rm200 mips-rs90 mips-rt305x mips-sb1250_swarm
mips-tb0219 mips-tb0226 mips-tb0287 mips-vocore2 mips-workpad mips-xway
nds32-allmodconfig nds32-allnoconfig nds32-defconfig nios2-10m50
nios2-3c120 nios2-allmodconfig nios2-allnoconfig openrisc-allmodconfig
openrisc-allnoconfig openrisc-or1klitex openrisc-or1ksim
openrisc-simple_smp parisc-allnoconfig parisc-generic-32bit
parisc-generic-64bit powerpc-acadia powerpc-adder875 powerpc-akebono
powerpc-amigaone powerpc-arches powerpc-asp8347 powerpc-bamboo
powerpc-bluestone powerpc-canyonlands powerpc-cell powerpc-chrp32
powerpc-cm5200 powerpc-currituck powerpc-ebony powerpc-eiger
powerpc-ep8248e powerpc-ep88xc powerpc-fsp2 powerpc-g5 powerpc-gamecube
powerpc-ge_imp3a powerpc-holly powerpc-icon powerpc-iss476-smp
powerpc-katmai powerpc-kilauea powerpc-klondike powerpc-kmeter1
powerpc-ksi8560 powerpc-linkstation powerpc-lite5200b powerpc-makalu
powerpc-maple powerpc-mgcoge powerpc-microwatt powerpc-motionpro
powerpc-mpc512x powerpc-mpc5200 powerpc-mpc7448_hpc2 powerpc-mpc8272_ads
powerpc-mpc8313_rdb powerpc-mpc8315_rdb powerpc-mpc832x_mds
powerpc-mpc832x_rdb powerpc-mpc834x_itx powerpc-mpc834x_itxgp
powerpc-mpc834x_mds powerpc-mpc836x_mds powerpc-mpc836x_rdk
powerpc-mpc837x_mds powerpc-mpc837x_rdb powerpc-mpc83xx
powerpc-mpc8540_ads powerpc-mpc8560_ads powerpc-mpc85xx_cds
powerpc-mpc866_ads powerpc-mpc885_ads powerpc-mvme5100 powerpc-obs600
powerpc-pasemi powerpc-pcm030 powerpc-pmac32 powerpc-powernv
powerpc-ppa8548 powerpc-ppc40x powerpc-ppc44x powerpc-ppc64
powerpc-ppc64e powerpc-ppc6xx powerpc-pq2fads powerpc-ps3
powerpc-pseries powerpc-rainier powerpc-redwood powerpc-sam440ep
powerpc-sbc8548 powerpc-sequoia powerpc-skiroot powerpc-socrates
powerpc-storcenter powerpc-stx_gp3 powerpc-taishan powerpc-tqm5200
powerpc-tqm8540 powerpc-tqm8541 powerpc-tqm8548 powerpc-tqm8555
powerpc-tqm8560 powerpc-tqm8xx powerpc-walnut powerpc-warp powerpc-wii
powerpc-xes_mpc85xx riscv-allmodconfig riscv-allnoconfig riscv-nommu_k210
riscv-nommu_k210_sdcard riscv-nommu_virt riscv-rv32 s390-allmodconfig
s390-allnoconfig s390-debug s390-zfcpdump sh-ap325rxa sh-apsh4a3a
sh-apsh4ad0a sh-dreamcast sh-ecovec24 sh-ecovec24-romimage sh-edosk7705
sh-edosk7760 sh-espt sh-hp6xx sh-j2 sh-kfr2r09 sh-kfr2r09-romimage
sh-landisk sh-lboxre2 sh-magicpanelr2 sh-microdev sh-migor sh-polaris
sh-r7780mp sh-r7785rp sh-rsk7201 sh-rsk7203 sh-rsk7264 sh-rsk7269
sh-rts7751r2d1 sh-rts7751r2dplus sh-sdk7780 sh-sdk7786 sh-se7206 sh-se7343
sh-se7619 sh-se7705 sh-se7712 sh-se7721 sh-se7722 sh-se7724 sh-se7750
sh-se7751 sh-se7780 sh-secureedge5410 sh-sh03 sh-sh2007 sh-sh7710voipgw
sh-sh7724_generic sh-sh7757lcr sh-sh7763rdp sh-sh7770_generic sh-sh7785lcr
sh-sh7785lcr_32bit sh-shmin sh-shx3 sh-titan sh-ul2 sh-urquell
sparc-allmodconfig sparc-allnoconfig sparc-sparc32 sparc-sparc64
um-i386-allmodconfig um-i386-allnoconfig um-i386-defconfig
um-x86_64-allmodconfig um-x86_64-allnoconfig x86_64-allmodconfig
x86_64-allnoconfig x86_64-defconfig xtensa-allmodconfig xtensa-allnoconfig
xtensa-audio_kc705 xtensa-cadence_csp xtensa-common xtensa-generic_kc705
xtensa-iss xtensa-nommu_kc705 xtensa-smp_lx200 xtensa-virt
xtensa-xip_kc705

Tested-by: Nathan Chancellor &lt;nathan@kernel.org&gt; # build (hexagon)
Signed-off-by: Alexey Dobriyan &lt;adobriyan@gmail.com&gt;
Acked-by: Ard Biesheuvel &lt;ardb@kernel.org&gt;
Signed-off-by: Masahiro Yamada &lt;masahiroy@kernel.org&gt;
</content>
</entry>
<entry>
<title>arch: remove compat_alloc_user_space</title>
<updated>2021-09-08T22:32:35+00:00</updated>
<author>
<name>Arnd Bergmann</name>
<email>arnd@arndb.de</email>
</author>
<published>2021-09-08T22:18:29+00:00</published>
<link rel='alternate' type='text/html' href='https://git.radix-linux.su/kernel/linux.git/commit/?id=a7a08b275a8bbade798c4bdaad07ade68fe7003c'/>
<id>urn:sha1:a7a08b275a8bbade798c4bdaad07ade68fe7003c</id>
<content type='text'>
All users of compat_alloc_user_space() and copy_in_user() have been
removed from the kernel, only a few functions in sparc remain that can be
changed to calling arch_copy_in_user() instead.

Link: https://lkml.kernel.org/r/20210727144859.4150043-7-arnd@kernel.org
Signed-off-by: Arnd Bergmann &lt;arnd@arndb.de&gt;
Reviewed-by: Christoph Hellwig &lt;hch@lst.de&gt;
Cc: Al Viro &lt;viro@zeniv.linux.org.uk&gt;
Cc: Benjamin Herrenschmidt &lt;benh@kernel.crashing.org&gt;
Cc: Borislav Petkov &lt;bp@alien8.de&gt;
Cc: Catalin Marinas &lt;catalin.marinas@arm.com&gt;
Cc: Christian Borntraeger &lt;borntraeger@de.ibm.com&gt;
Cc: Christoph Hellwig &lt;hch@infradead.org&gt;
Cc: "David S. Miller" &lt;davem@davemloft.net&gt;
Cc: Eric Biederman &lt;ebiederm@xmission.com&gt;
Cc: Feng Tang &lt;feng.tang@intel.com&gt;
Cc: Heiko Carstens &lt;hca@linux.ibm.com&gt;
Cc: Helge Deller &lt;deller@gmx.de&gt;
Cc: "H. Peter Anvin" &lt;hpa@zytor.com&gt;
Cc: Ingo Molnar &lt;mingo@redhat.com&gt;
Cc: "James E.J. Bottomley" &lt;James.Bottomley@HansenPartnership.com&gt;
Cc: Michael Ellerman &lt;mpe@ellerman.id.au&gt;
Cc: Paul Mackerras &lt;paulus@samba.org&gt;
Cc: Thomas Bogendoerfer &lt;tsbogend@alpha.franken.de&gt;
Cc: Thomas Gleixner &lt;tglx@linutronix.de&gt;
Cc: Vasily Gorbik &lt;gor@linux.ibm.com&gt;
Cc: Will Deacon &lt;will@kernel.org&gt;
Signed-off-by: Andrew Morton &lt;akpm@linux-foundation.org&gt;
Signed-off-by: Linus Torvalds &lt;torvalds@linux-foundation.org&gt;
</content>
</entry>
<entry>
<title>Merge branch 'for-next/kasan' into for-next/core</title>
<updated>2021-06-24T13:04:00+00:00</updated>
<author>
<name>Will Deacon</name>
<email>will@kernel.org</email>
</author>
<published>2021-06-24T13:04:00+00:00</published>
<link rel='alternate' type='text/html' href='https://git.radix-linux.su/kernel/linux.git/commit/?id=2c9bd9d806757bc84e9d744044d6937a85df5f60'/>
<id>urn:sha1:2c9bd9d806757bc84e9d744044d6937a85df5f60</id>
<content type='text'>
Optimise out-of-line KASAN checking when using software tagging.

* for-next/kasan:
  kasan: arm64: support specialized outlined tag mismatch checks
</content>
</entry>
<entry>
<title>Merge branch 'for-next/insn' into for-next/core</title>
<updated>2021-06-24T13:03:24+00:00</updated>
<author>
<name>Will Deacon</name>
<email>will@kernel.org</email>
</author>
<published>2021-06-24T13:03:24+00:00</published>
<link rel='alternate' type='text/html' href='https://git.radix-linux.su/kernel/linux.git/commit/?id=181a126979307a0192f41a4a1fac235d6f4ac9f0'/>
<id>urn:sha1:181a126979307a0192f41a4a1fac235d6f4ac9f0</id>
<content type='text'>
Refactoring of our instruction decoding routines and addition of some
missing encodings.

* for-next/insn:
  arm64: insn: avoid circular include dependency
  arm64: insn: move AARCH64_INSN_SIZE into &lt;asm/insn.h&gt;
  arm64: insn: decouple patching from insn code
  arm64: insn: Add load/store decoding helpers
  arm64: insn: Add some opcodes to instruction decoder
  arm64: insn: Add barrier encodings
  arm64: insn: Add SVE instruction class
  arm64: Move instruction encoder/decoder under lib/
  arm64: Move aarch32 condition check functions
  arm64: Move patching utilities out of instruction encoding/decoding
</content>
</entry>
<entry>
<title>arm64: Import latest memcpy()/memmove() implementation</title>
<updated>2021-06-01T17:34:38+00:00</updated>
<author>
<name>Robin Murphy</name>
<email>robin.murphy@arm.com</email>
</author>
<published>2021-05-27T15:34:46+00:00</published>
<link rel='alternate' type='text/html' href='https://git.radix-linux.su/kernel/linux.git/commit/?id=285133040e6ce0e6f37db962f2b4dad10ea46da0'/>
<id>urn:sha1:285133040e6ce0e6f37db962f2b4dad10ea46da0</id>
<content type='text'>
Import the latest implementation of memcpy(), based on the
upstream code of string/aarch64/memcpy.S at commit afd6244 from
https://github.com/ARM-software/optimized-routines, and subsuming
memmove() in the process.

Note that for simplicity Arm have chosen to contribute this code
to Linux under GPLv2 rather than the original MIT license.

Note also that the needs of the usercopy routines vs. regular memcpy()
have now diverged so far that we abandon the shared template idea
and the damage which that incurred to the tuning of LDP/STP loops.
We'll be back to tackle those routines separately in future.

Signed-off-by: Robin Murphy &lt;robin.murphy@arm.com&gt;
Link: https://lore.kernel.org/r/3c953af43506581b2422f61952261e76949ba711.1622128527.git.robin.murphy@arm.com
Signed-off-by: Will Deacon &lt;will@kernel.org&gt;
</content>
</entry>
<entry>
<title>arm64: Move instruction encoder/decoder under lib/</title>
<updated>2021-05-27T16:38:30+00:00</updated>
<author>
<name>Julien Thierry</name>
<email>jthierry@redhat.com</email>
</author>
<published>2021-03-03T17:05:32+00:00</published>
<link rel='alternate' type='text/html' href='https://git.radix-linux.su/kernel/linux.git/commit/?id=72fd723694b6f4f1d1f19f673fb93801d7d1a0e8'/>
<id>urn:sha1:72fd723694b6f4f1d1f19f673fb93801d7d1a0e8</id>
<content type='text'>
Aarch64 instruction set encoding and decoding logic can prove useful
for some features/tools both part of the kernel and outside the kernel.

Isolate the function dealing only with encoding/decoding instructions,
with minimal dependency on kernel utilities in order to be able to reuse
that code.

Code was only moved, no code should have been added, removed nor
modifier.

Signed-off-by: Julien Thierry &lt;jthierry@redhat.com&gt;
Link: https://lore.kernel.org/r/20210303170536.1838032-5-jthierry@redhat.com
Signed-off-by: Will Deacon &lt;will@kernel.org&gt;
</content>
</entry>
<entry>
<title>kasan: arm64: support specialized outlined tag mismatch checks</title>
<updated>2021-05-26T22:31:26+00:00</updated>
<author>
<name>Peter Collingbourne</name>
<email>pcc@google.com</email>
</author>
<published>2021-05-26T17:49:27+00:00</published>
<link rel='alternate' type='text/html' href='https://git.radix-linux.su/kernel/linux.git/commit/?id=1cbdf60bd1b74e397d48aa877367cfc621f45ffe'/>
<id>urn:sha1:1cbdf60bd1b74e397d48aa877367cfc621f45ffe</id>
<content type='text'>
By using outlined checks we can achieve a significant code size
improvement by moving the tag-based ASAN checks into separate
functions. Unlike the existing CONFIG_KASAN_OUTLINE mode these
functions have a custom calling convention that preserves most
registers and is specialized to the register containing the address
and the type of access, and as a result we can eliminate the code
size and performance overhead of a standard calling convention such
as AAPCS for these functions.

This change depends on a separate series of changes to Clang [1] to
support outlined checks in the kernel, although the change works fine
without them (we just don't get outlined checks). This is because the
flag -mllvm -hwasan-inline-all-checks=0 has no effect until the Clang
changes land. The flag was introduced in the Clang 9.0 timeframe as
part of the support for outlined checks in userspace and because our
minimum Clang version is 10.0 we can pass it unconditionally.

Outlined checks require a new runtime function with a custom calling
convention. Add this function to arch/arm64/lib.

I measured the code size of defconfig + tag-based KASAN, as well
as boot time (i.e. time to init launch) on a DragonBoard 845c with
an Android arm64 GKI kernel. The results are below:

                               code size    boot time
CONFIG_KASAN_INLINE=y before    92824064      6.18s
CONFIG_KASAN_INLINE=y after     38822400      6.65s
CONFIG_KASAN_OUTLINE=y          39215616     11.48s

We can see straight away that specialized outlined checks beat the
existing CONFIG_KASAN_OUTLINE=y on both code size and boot time
for tag-based ASAN.

As for the comparison between CONFIG_KASAN_INLINE=y before and after
we saw similar performance numbers in userspace [2] and decided
that since the performance overhead is minimal compared to the
overhead of tag-based ASAN itself as well as compared to the code
size improvements we would just replace the inlined checks with the
specialized outlined checks without the option to select between them,
and that is what I have implemented in this patch.

Signed-off-by: Peter Collingbourne &lt;pcc@google.com&gt;
Acked-by: Andrey Konovalov &lt;andreyknvl@gmail.com&gt;
Reviewed-by: Mark Rutland &lt;mark.rutland@arm.com&gt;
Tested-by: Mark Rutland &lt;mark.rutland@arm.com&gt;
Link: https://linux-review.googlesource.com/id/I1a30036c70ab3c3ee78d75ed9b87ef7cdc3fdb76
Link: [1] https://reviews.llvm.org/D90426
Link: [2] https://reviews.llvm.org/D56954
Link: https://lore.kernel.org/r/20210526174927.2477847-3-pcc@google.com
Signed-off-by: Will Deacon &lt;will@kernel.org&gt;
</content>
</entry>
<entry>
<title>arm64: mte: Clear the tags when a page is mapped in user-space with PROT_MTE</title>
<updated>2020-09-04T11:46:06+00:00</updated>
<author>
<name>Catalin Marinas</name>
<email>catalin.marinas@arm.com</email>
</author>
<published>2020-05-04T13:42:36+00:00</published>
<link rel='alternate' type='text/html' href='https://git.radix-linux.su/kernel/linux.git/commit/?id=34bfeea4a9e9cdae713637541f240c3adfdfede3'/>
<id>urn:sha1:34bfeea4a9e9cdae713637541f240c3adfdfede3</id>
<content type='text'>
Pages allocated by the kernel are not guaranteed to have the tags
zeroed, especially as the kernel does not (yet) use MTE itself. To
ensure the user can still access such pages when mapped into its address
space, clear the tags via set_pte_at(). A new page flag - PG_mte_tagged
(PG_arch_2) - is used to track pages with valid allocation tags.

Since the zero page is mapped as pte_special(), it won't be covered by
the above set_pte_at() mechanism. Clear its tags during early MTE
initialisation.

Co-developed-by: Steven Price &lt;steven.price@arm.com&gt;
Signed-off-by: Steven Price &lt;steven.price@arm.com&gt;
Signed-off-by: Catalin Marinas &lt;catalin.marinas@arm.com&gt;
Cc: Will Deacon &lt;will@kernel.org&gt;
</content>
</entry>
<entry>
<title>arm64: Implement optimised checksum routine</title>
<updated>2020-01-16T15:23:29+00:00</updated>
<author>
<name>Robin Murphy</name>
<email>robin.murphy@arm.com</email>
</author>
<published>2020-01-15T16:42:39+00:00</published>
<link rel='alternate' type='text/html' href='https://git.radix-linux.su/kernel/linux.git/commit/?id=5777eaed566a1d63e344d3dd8f2b5e33be20643e'/>
<id>urn:sha1:5777eaed566a1d63e344d3dd8f2b5e33be20643e</id>
<content type='text'>
Apparently there exist certain workloads which rely heavily on software
checksumming, for which the generic do_csum() implementation becomes a
significant bottleneck. Therefore let's give arm64 its own optimised
version - for ease of maintenance this foregoes assembly or intrisics,
and is thus not actually arm64-specific, but does rely heavily on C
idioms that translate well to the A64 ISA and the typical load/store
capabilities of most ARMv8 CPU cores.

The resulting increase in checksum throughput scales nicely with buffer
size, tending towards 4x for a small in-order core (Cortex-A53), and up
to 6x or more for an aggressive big core (Ampere eMAG).

Reported-by: Lingyan Huang &lt;huanglingyan2@huawei.com&gt;
Tested-by: Lingyan Huang &lt;huanglingyan2@huawei.com&gt;
Signed-off-by: Robin Murphy &lt;robin.murphy@arm.com&gt;
Signed-off-by: Will Deacon &lt;will@kernel.org&gt;
</content>
</entry>
</feed>
