IF YOU WOULD LIKE TO GET AN ACCOUNT, please write an
email to Administrator. User accounts are meant only to access repo
and report issues and/or generate pull requests.
This is a purpose-specific Git hosting for
BaseALT
projects. Thank you for your understanding!
Только зарегистрированные пользователи имеют доступ к сервису!
Для получения аккаунта, обратитесь к администратору.
Evan Green <evan@rivosinc.com> says:
The current setting for the hwprobe bit indicating misaligned access
speed is controlled by a vendor-specific feature probe function. This is
essentially a per-SoC table we have to maintain on behalf of each vendor
going forward. Let's convert that instead to something we detect at
runtime.
We have two assembly routines at the heart of our probe: one that
does a bunch of word-sized accesses (without aligning its input buffer),
and the other that does byte accesses. If we can move a larger number of
bytes using misaligned word accesses than we can with the same amount of
time doing byte accesses, then we can declare misaligned accesses as
"fast".
The tradeoff of reducing this maintenance burden is boot time. We spend
4-6 jiffies per core doing this measurement (0-2 on jiffie edge
alignment, and 4 on measurement). The timing loop was based on
raid6_choose_gen(), which uses (16+1)*N jiffies (where N is the number
of algorithms). By taking only the fastest iteration out of all
attempts for use in the comparison, variance between runs is very low.
On my THead C906, it looks like this:
[ 0.047563] cpu0: Ratio of byte access time to unaligned word access is 4.34, unaligned accesses are fast
Several others have chimed in with results on slow machines with the
older algorithm, which took all runs into account, including noise like
interrupts. Even with this variation, results indicate that in all cases
(fast, slow, and emulated) the measured numbers are nowhere near each
other (always multiple factors away).
* b4-shazam-merge:
RISC-V: alternative: Remove feature_probe_func
RISC-V: Probe for unaligned access speed
Link: https://lore.kernel.org/r/20230818194136.4084400-1-evan@rivosinc.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
Rather than deferring unaligned access speed determinations to a vendor
function, let's probe them and find out how fast they are. If we
determine that an unaligned word access is faster than N byte accesses,
mark the hardware's unaligned access as "fast". Otherwise, we mark
accesses as slow.
The algorithm itself runs for a fixed amount of jiffies. Within each
iteration it attempts to time a single loop, and then keeps only the best
(fastest) loop it saw. This algorithm was found to have lower variance from
run to run than my first attempt, which counted the total number of
iterations that could be done in that fixed amount of jiffies. By taking
only the best iteration in the loop, assuming at least one loop wasn't
perturbed by an interrupt, we eliminate the effects of interrupts and
other "warm up" factors like branch prediction. The only downside is it
depends on having an rdtime granular and accurate enough to measure a
single copy. If we ever manage to complete a loop in 0 rdtime ticks, we
leave the unaligned setting at UNKNOWN.
There is a slight change in user-visible behavior here. Previously, all
boards except the THead C906 reported misaligned access speed of
UNKNOWN. C906 reported FAST. With this change, since we're now measuring
misaligned access speed on each hart, all RISC-V systems will have this
key set as either FAST or SLOW.
Currently, we don't have a way to confidently measure the difference between
SLOW and EMULATED, so we label anything not fast as SLOW. This will
mislabel some systems that are actually EMULATED as SLOW. When we get
support for delegating misaligned access traps to the kernel (as opposed
to the firmware quietly handling it), we can explicitly test in Linux to
see if unaligned accesses trap. Those systems will start to report
EMULATED, though older (today's) systems without that new SBI mechanism
will continue to report SLOW.
I've updated the documentation for those hwprobe values to reflect
this, specifically: SLOW may or may not be emulated by software, and FAST
represents means being faster than equivalent byte accesses. The change
in documentation is accurate with respect to both the former and current
behavior.
Signed-off-by: Evan Green <evan@rivosinc.com>
Acked-by: Conor Dooley <conor.dooley@microchip.com>
Link: https://lore.kernel.org/r/20230818194136.4084400-2-evan@rivosinc.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
- Work from Carlos Bilbao to integrate rustdoc output into the generated
HTML documentation. This took some work to figure out how to do it
without slowing the docs build and without creating people who don't have
Rust installed, but Carlos got there.
- Move the loongarch and mips architecture documentation under
Documentation/arch/.
- Some more maintainer documentation from Jakub
...plus the usual assortment of updates, translations, and fixes.
-----BEGIN PGP SIGNATURE-----
iQFDBAABCAAtFiEEIw+MvkEiF49krdp9F0NaE2wMflgFAmTvqNkPHGNvcmJldEBs
d24ubmV0AAoJEBdDWhNsDH5YgIgH/3drfLtlFtzLqDOzrzDXS8yGnE3pPdxw796b
/ZFzAK16wYKaKevYoIz8bVGGKaE1sEUW0mhlq4KGdfZuxLG8YnWS8URyCW4FDU2E
6qNL+8oJ8LZfID46f9Q8ZgfEz7yF/mhCqPk7MEswYtwbscs2ZTGCTGYB/5BHlBuT
LR+M89uLmHgr8S1o24v30OgiX+VvQFyu0xoxIhbiqUZvBd/XdfX2pgYd9BGzMj5q
C2ZP+V14g36c5pV0EO9TwhCXOF/WVrp7DbjbfWAsqBSLxvpXPydH2q1DUzGeQtP1
exujrBD1O8q3pPdaNA5R+h6cWlHmUZug9mE4BRLp9ErGrozwJsQ=
=C3Uv
-----END PGP SIGNATURE-----
Merge tag 'docs-6.6' of git://git.lwn.net/linux
Pull documentation updates from Jonathan Corbet:
"Documentation work keeps chugging along; this includes:
- Work from Carlos Bilbao to integrate rustdoc output into the
generated HTML documentation. This took some work to figure out how
to do it without slowing the docs build and without creating people
who don't have Rust installed, but Carlos got there
- Move the loongarch and mips architecture documentation under
Documentation/arch/
- Some more maintainer documentation from Jakub
... plus the usual assortment of updates, translations, and fixes"
* tag 'docs-6.6' of git://git.lwn.net/linux: (56 commits)
Docu: genericirq.rst: fix irq-example
input: docs: pxrc: remove reference to phoenix-sim
Documentation: serial-console: Fix literal block marker
docs/mm: remove references to hmm_mirror ops and clean typos
docs/zh_CN: correct regi_chg(),regi_add() to region_chg(),region_add()
Documentation: Fix typos
Documentation/ABI: Fix typos
scripts: kernel-doc: fix macro handling in enums
scripts: kernel-doc: parse DEFINE_DMA_UNMAP_[ADDR|LEN]
Documentation: riscv: Update boot image header since EFI stub is supported
Documentation: riscv: Add early boot document
Documentation: arm: Add bootargs to the table of added DT parameters
docs: kernel-parameters: Refer to the correct bitmap function
doc: update params of memhp_default_state=
docs: Add book to process/kernel-docs.rst
docs: sparse: fix invalid link addresses
docs: vfs: clean up after the iterate() removal
docs: Add a section on surveys to the researcher guidelines
docs: move mips under arch
docs: move loongarch under arch
...
I'm not sure what I was trying to do with the ':'s, but they're just
rendered to HTML which looks odd. This makes "fence.i" look like
"mvendorid" and such, which is seems reasonable to me.
Reviewed-by: Evan Green <evan@rivosinc.com>
Link: https://lore.kernel.org/r/20230710193329.2742-1-palmer@rivosinc.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
Evan Green <evan@rivosinc.com> says:
This change detects the presence of Zba, Zbb, and Zbs extensions and exports
them per-hart to userspace via the hwprobe mechanism. Glibc can then use
these in setting up hwcaps-based library search paths.
There's a little bit of extra housekeeping here: the first change adds
Zba and Zbs to the set of extensions the kernel recognizes, and the second
change starts tracking ISA features per-hart (in addition to the ANDed
mask of features across all harts which the kernel uses to make
decisions). Now that we track the ISA information per-hart, we could
even fix up /proc/cpuinfo to accurately report extension per-hart,
though I've left that out of this series for now.
* b4-shazam-merge:
RISC-V: hwprobe: Expose Zba, Zbb, and Zbs
RISC-V: Track ISA extensions per hart
RISC-V: Add Zba, Zbs extension probing
Link: https://lore.kernel.org/r/20230509182504.2997252-1-evan@rivosinc.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
Add two new bits to the IMA_EXT_0 key for ZBA, ZBB, and ZBS extensions.
These are accurately reported per CPU.
Signed-off-by: Evan Green <evan@rivosinc.com>
Reviewed-by: Andrew Jones <ajones@ventanamicro.com>
Reviewed-by: Conor Dooley <conor.dooley@microchip.com>
Reviewed-by: Heiko Stuebner <heiko.stuebner@vrull.eu>
Link: https://lore.kernel.org/r/20230509182504.2997252-4-evan@rivosinc.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
Probing kernel support for Vector extension is available now. This only
add detection for V only. Extenions like Zvfh, Zk are not in this scope.
Signed-off-by: Andy Chiu <andy.chiu@sifive.com>
Reviewed-by: Conor Dooley <conor.dooley@microchip.com>
Reviewed-by: Evan Green <evan@rivosinc.com>
Reviewed-by: Palmer Dabbelt <palmer@rivosinc.com>
Link: https://lore.kernel.org/r/20230605110724.21391-4-andy.chiu@sifive.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
This allows userspace to select various routines to use based on the
performance of misaligned access on the target hardware.
Rather than adding DT bindings, this change taps into the alternatives
mechanism used to probe CPU errata. Add a new function pointer alongside
the vendor-specific errata_patch_func() that probes for desirable errata
(otherwise known as "features"). Unlike the errata_patch_func(), this
function is called on each CPU as it comes up, so it can save
feature information per-CPU.
The T-head C906 has fast unaligned access, both as defined by GCC [1],
and in performing a basic benchmark, which determined that byte copies
are >50% slower than a misaligned word copy of the same data size (source
for this test at [2]):
bytecopy size f000 count 50000 offset 0 took 31664899 us
wordcopy size f000 count 50000 offset 0 took 5180919 us
wordcopy size f000 count 50000 offset 1 took 13416949 us
[1] https://github.com/gcc-mirror/gcc/blob/master/gcc/config/riscv/riscv.cc#L353
[2] https://pastebin.com/EPXvDHSW
Co-developed-by: Palmer Dabbelt <palmer@rivosinc.com>
Signed-off-by: Evan Green <evan@rivosinc.com>
Reviewed-by: Heiko Stuebner <heiko.stuebner@vrull.eu>
Tested-by: Heiko Stuebner <heiko.stuebner@vrull.eu>
Reviewed-by: Conor Dooley <conor.dooley@microchip.com>
Reviewed-by: Paul Walmsley <paul.walmsley@sifive.com>
Link: https://lore.kernel.org/r/20230407231103.2622178-5-evan@rivosinc.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
We have an implicit set of base behaviors that userspace depends on,
which are mostly defined in various ISA specifications.
Co-developed-by: Palmer Dabbelt <palmer@rivosinc.com>
Signed-off-by: Evan Green <evan@rivosinc.com>
Reviewed-by: Conor Dooley <conor.dooley@microchip.com>
Reviewed-by: Heiko Stuebner <heiko.stuebner@vrull.eu>
Tested-by: Heiko Stuebner <heiko.stuebner@vrull.eu>
Reviewed-by: Paul Walmsley <paul.walmsley@sifive.com>
Link: https://lore.kernel.org/r/20230407231103.2622178-4-evan@rivosinc.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
We don't have enough space for these all in ELF_HWCAP{,2} and there's no
system call that quite does this, so let's just provide an arch-specific
one to probe for hardware capabilities. This currently just provides
m{arch,imp,vendor}id, but with the key-value pairs we can pass more in
the future.
Co-developed-by: Palmer Dabbelt <palmer@rivosinc.com>
Signed-off-by: Evan Green <evan@rivosinc.com>
Reviewed-by: Conor Dooley <conor.dooley@microchip.com>
Reviewed-by: Heiko Stuebner <heiko.stuebner@vrull.eu>
Tested-by: Heiko Stuebner <heiko.stuebner@vrull.eu>
Reviewed-by: Paul Walmsley <paul.walmsley@sifive.com>
Link: https://lore.kernel.org/r/20230407231103.2622178-3-evan@rivosinc.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
