Jisheng Zhang <jszhang@kernel.org> says:
This series selects ARCH_USE_CMPXCHG_LOCKREF to enable the
cmpxchg-based lockless lockref implementation for riscv. Then,
implement arch_cmpxchg64_{relaxed|acquire|release}.
After patch1:
Using Linus' test case[1] on TH1520 platform, I see a 11.2% improvement.
On JH7110 platform, I see 12.0% improvement.
After patch2:
on both TH1520 and JH7110 platforms, I didn't see obvious
performance improvement with Linus' test case [1]. IMHO, this may
be related with the fence and lr.d/sc.d hw implementations. In theory,
lr/sc without fence could give performance improvement over lr/sc plus
fence, so add the code here to leave performance improvement room on
newer HW platforms.
* b4-shazam-merge:
riscv: cmpxchg: implement arch_cmpxchg64_{relaxed|acquire|release}
riscv: select ARCH_USE_CMPXCHG_LOCKREF
Link: http://marc.info/?l=linux-fsdevel&m=137782380714721&w=4 [1]
Link: https://lore.kernel.org/r/20240325111038.1700-1-jszhang@kernel.org
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
Leonardo Bras <leobras@redhat.com> says:
While studying riscv's cmpxchg.h file, I got really interested in
understanding how RISCV asm implemented the different versions of
{cmp,}xchg.
When I understood the pattern, it made sense for me to remove the
duplications and create macros to make it easier to understand what exactly
changes between the versions: Instruction sufixes & barriers.
Also, did the same kind of work on atomic.c.
After that, I noted both cmpxchg and xchg only accept variables of
size 4 and 8, compared to x86 and arm64 which do 1,2,4,8.
Now that deduplication is done, it is quite direct to implement them
for variable sizes 1 and 2, so I did it. Then Guo Ren already presented
me some possible users :)
I did compare the generated asm on a test.c that contained usage for every
changed function, and could not detect any change on patches 1 + 2 + 3
compared with upstream.
Pathes 4 & 5 were compiled-tested, merged with guoren/qspinlock_v11 and
booted just fine with qemu -machine virt -append "qspinlock".
(tree: https://gitlab.com/LeoBras/linux/-/commits/guo_qspinlock_v11)
Latest tests happened based on this tree:
https://github.com/guoren83/linux/tree/qspinlock_v12
* b4-shazam-lts:
riscv/cmpxchg: Implement xchg for variables of size 1 and 2
riscv/cmpxchg: Implement cmpxchg for variables of size 1 and 2
riscv/atomic.h : Deduplicate arch_atomic.*
riscv/cmpxchg: Deduplicate cmpxchg() asm and macros
riscv/cmpxchg: Deduplicate xchg() asm functions
Link: https://lore.kernel.org/r/20240103163203.72768-2-leobras@redhat.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
After selecting ARCH_USE_CMPXCHG_LOCKREF, one straight futher
optimization is implementing the arch_cmpxchg64_relaxed() because the
lockref code does not need the cmpxchg to have barrier semantics. At
the same time, implement arch_cmpxchg64_acquire and
arch_cmpxchg64_release as well.
However, on both TH1520 and JH7110 platforms, I didn't see obvious
performance improvement with Linus' test case [1]. IMHO, this may
be related with the fence and lr.d/sc.d hw implementations. In theory,
lr/sc without fence could give performance improvement over lr/sc plus
fence, so add the code here to leave performance improvement room on
newer HW platforms.
Link: http://marc.info/?l=linux-fsdevel&m=137782380714721&w=4 [1]
Signed-off-by: Jisheng Zhang <jszhang@kernel.org>
Reviewed-by: Andrea Parri <parri.andrea@gmail.com>
Link: https://lore.kernel.org/r/20240325111038.1700-3-jszhang@kernel.org
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
xchg for variables of size 1-byte and 2-bytes is not yet available for
riscv, even though its present in other architectures such as arm64 and
x86. This could lead to not being able to implement some locking mechanisms
or requiring some rework to make it work properly.
Implement 1-byte and 2-bytes xchg in order to achieve parity with other
architectures.
Signed-off-by: Leonardo Bras <leobras@redhat.com>
Tested-by: Guo Ren <guoren@kernel.org>
Link: https://lore.kernel.org/r/20240103163203.72768-7-leobras@redhat.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
cmpxchg for variables of size 1-byte and 2-bytes is not yet available for
riscv, even though its present in other architectures such as arm64 and
x86. This could lead to not being able to implement some locking mechanisms
or requiring some rework to make it work properly.
Implement 1-byte and 2-bytes cmpxchg in order to achieve parity with other
architectures.
Signed-off-by: Leonardo Bras <leobras@redhat.com>
Tested-by: Guo Ren <guoren@kernel.org>
Link: https://lore.kernel.org/r/20240103163203.72768-6-leobras@redhat.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
In this header every cmpxchg define (_relaxed, _acquire, _release,
vanilla) contain it's own asm file, both for 4-byte variables an 8-byte
variables, on a total of 8 versions of mostly the same asm.
This is usually bad, as it means any change may be done in up to 8
different places.
Unify those versions by creating a new define with enough parameters to
generate any version of the previous 8.
Then unify the result under a more general define, and simplify
arch_cmpxchg* generation
(This did not cause any change in generated asm)
Signed-off-by: Leonardo Bras <leobras@redhat.com>
Reviewed-by: Guo Ren <guoren@kernel.org>
Reviewed-by: Andrea Parri <parri.andrea@gmail.com>
Tested-by: Guo Ren <guoren@kernel.org>
Link: https://lore.kernel.org/r/20240103163203.72768-4-leobras@redhat.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
In this header every xchg define (_relaxed, _acquire, _release, vanilla)
contain it's own asm file, both for 4-byte variables an 8-byte variables,
on a total of 8 versions of mostly the same asm.
This is usually bad, as it means any change may be done in up to 8
different places.
Unify those versions by creating a new define with enough parameters to
generate any version of the previous 8.
Then unify the result under a more general define, and simplify
arch_xchg* generation.
(This did not cause any change in generated asm)
Signed-off-by: Leonardo Bras <leobras@redhat.com>
Reviewed-by: Guo Ren <guoren@kernel.org>
Reviewed-by: Andrea Parri <parri.andrea@gmail.com>
Tested-by: Guo Ren <guoren@kernel.org>
Link: https://lore.kernel.org/r/20240103163203.72768-3-leobras@redhat.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
Disparate fence implementations are consolidated into fence.h.
Also introduce RISCV_FENCE_ASM to make fence macro more reusable.
Signed-off-by: Eric Chan <ericchancf@google.com>
Reviewed-by: Andrea Parri <parri.andrea@gmail.com>
Reviewed-by: Samuel Holland <samuel.holland@sifive.com>
Tested-by: Samuel Holland <samuel.holland@sifive.com>
Link: https://lore.kernel.org/r/20240217131316.3668927-1-ericchancf@google.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
Introduce RISCV_FULL_BARRIER and use in arch_atomic* function.
like RISCV_ACQUIRE_BARRIER and RISCV_RELEASE_BARRIER, the fence
instruction can be eliminated When SMP is not enabled.
Signed-off-by: Eric Chan <ericchancf@google.com>
Reviewed-by: Andrea Parri <parri.andrea@gmail.com>
Reviewed-by: Samuel Holland <samuel.holland@sifive.com>
Tested-by: Samuel Holland <samuel.holland@sifive.com>
Link: https://lore.kernel.org/r/20240217131302.3668481-1-ericchancf@google.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
Decrease the probability of this internal facility to be used by
driver code.
Signed-off-by: Andrzej Hajda <andrzej.hajda@intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Arnd Bergmann <arnd@arndb.de>
Reviewed-by: Andi Shyti <andi.shyti@linux.intel.com>
Acked-by: Geert Uytterhoeven <geert@linux-m68k.org> [m68k]
Acked-by: Palmer Dabbelt <palmer@rivosinc.com> [riscv]
Link: https://lore.kernel.org/r/20230118154450.73842-1-andrzej.hajda@intel.com
Cc: Linus Torvalds <torvalds@linux-foundation.org>
The cmpxchg32 & cmpxchg32_local are not used in Linux anymore. So
clean up asm/cmpxchg.h.
Signed-off-by: Guo Ren <guoren@linux.alibaba.com>
Signed-off-by: Guo Ren <guoren@kernel.org>
Link: https://lore.kernel.org/r/20220505035526.2974382-2-guoren@kernel.org
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
We'd like all architectures to convert to ARCH_ATOMIC, as once all
architectures are converted it will be possible to make significant
cleanups to the atomics headers, and this will make it much easier to
generically enable atomic functionality (e.g. debug logic in the
instrumented wrappers).
As a step towards that, this patch migrates riscv to ARCH_ATOMIC. The
arch code provides arch_{atomic,atomic64,xchg,cmpxchg}*(), and common
code wraps these with optional instrumentation to provide the regular
functions.
Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Reviewed-by: Palmer Dabbelt <palmerdabbelt@google.com>
Acked-by: Palmer Dabbelt <palmerdabbelt@google.com>
Cc: Albert Ou <aou@eecs.berkeley.edu>
Cc: Boqun Feng <boqun.feng@gmail.com>
Cc: Paul Walmsley <paul.walmsley@sifive.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Will Deacon <will@kernel.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/r/20210525140232.53872-29-mark.rutland@arm.com
The argument passed to cmpxchg is not guaranteed to be sign
extended, but lr.w sign extends on RV64I. This makes cmpxchg
fail on clang built kernels when __old is negative.
To fix this, we just cast __old to long which sign extends on
RV64I. With this fix, clang built RISC-V kernels now boot.
Link: https://github.com/ClangBuiltLinux/linux/issues/867
Signed-off-by: Nathan Huckleberry <nhuck@google.com>
Signed-off-by: Palmer Dabbelt <palmerdabbelt@google.com>
Based on 1 normalized pattern(s):
this program is free software you can redistribute it and or modify
it under the terms of the gnu general public license as published by
the free software foundation version 2 this program is distributed
in the hope that it will be useful but without any warranty without
even the implied warranty of merchantability or fitness for a
particular purpose see the gnu general public license for more
details
extracted by the scancode license scanner the SPDX license identifier
GPL-2.0-only
has been chosen to replace the boilerplate/reference in 97 file(s).
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Allison Randal <allison@lohutok.net>
Reviewed-by: Alexios Zavras <alexios.zavras@intel.com>
Cc: linux-spdx@vger.kernel.org
Link: https://lkml.kernel.org/r/20190529141901.025053186@linutronix.de
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Atomics present the same issue with locking: release and acquire
variants need to be strengthened to meet the constraints defined
by the Linux-kernel memory consistency model [1].
Atomics present a further issue: implementations of atomics such
as atomic_cmpxchg() and atomic_add_unless() rely on LR/SC pairs,
which do not give full-ordering with .aqrl; for example, current
implementations allow the "lr-sc-aqrl-pair-vs-full-barrier" test
below to end up with the state indicated in the "exists" clause.
In order to "synchronize" LKMM and RISC-V's implementation, this
commit strengthens the implementations of the atomics operations
by replacing .rl and .aq with the use of ("lightweigth") fences,
and by replacing .aqrl LR/SC pairs in sequences such as:
0: lr.w.aqrl %0, %addr
bne %0, %old, 1f
...
sc.w.aqrl %1, %new, %addr
bnez %1, 0b
1:
with sequences of the form:
0: lr.w %0, %addr
bne %0, %old, 1f
...
sc.w.rl %1, %new, %addr /* SC-release */
bnez %1, 0b
fence rw, rw /* "full" fence */
1:
following Daniel's suggestion.
These modifications were validated with simulation of the RISC-V
memory consistency model.
C lr-sc-aqrl-pair-vs-full-barrier
{}
P0(int *x, int *y, atomic_t *u)
{
int r0;
int r1;
WRITE_ONCE(*x, 1);
r0 = atomic_cmpxchg(u, 0, 1);
r1 = READ_ONCE(*y);
}
P1(int *x, int *y, atomic_t *v)
{
int r0;
int r1;
WRITE_ONCE(*y, 1);
r0 = atomic_cmpxchg(v, 0, 1);
r1 = READ_ONCE(*x);
}
exists (u=1 /\ v=1 /\ 0:r1=0 /\ 1:r1=0)
[1] https://marc.info/?l=linux-kernel&m=151930201102853&w=2https://groups.google.com/a/groups.riscv.org/forum/#!topic/isa-dev/hKywNHBkAXMhttps://marc.info/?l=linux-kernel&m=151633436614259&w=2
Suggested-by: Daniel Lustig <dlustig@nvidia.com>
Signed-off-by: Andrea Parri <parri.andrea@gmail.com>
Cc: Palmer Dabbelt <palmer@sifive.com>
Cc: Albert Ou <albert@sifive.com>
Cc: Daniel Lustig <dlustig@nvidia.com>
Cc: Alan Stern <stern@rowland.harvard.edu>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Boqun Feng <boqun.feng@gmail.com>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: David Howells <dhowells@redhat.com>
Cc: Jade Alglave <j.alglave@ucl.ac.uk>
Cc: Luc Maranget <luc.maranget@inria.fr>
Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Cc: Akira Yokosawa <akiyks@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: linux-riscv@lists.infradead.org
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Palmer Dabbelt <palmer@sifive.com>
This contains all the code that directly interfaces with the RISC-V
memory model. While this code corforms to the current RISC-V ISA
specifications (user 2.2 and priv 1.10), the memory model is somewhat
underspecified in those documents. There is a working group that hopes
to produce a formal memory model by the end of the year, but my
understanding is that the basic definitions we're relying on here won't
change significantly.
Reviewed-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Palmer Dabbelt <palmer@dabbelt.com>
