From: Guo Ren <guoren@xxxxxxxxxxxxxxxxx>
The requirements of qspinlock have been documented by commit:
a8ad07e5240c ("asm-generic: qspinlock: Indicate the use of mixed-size
atomics").
Although RISC-V ISA gives out a weaker forward guarantee LR/SC, which
doesn't satisfy the requirements of qspinlock above, it won't prevent
some riscv vendors from implementing a strong fwd guarantee LR/SC in
microarchitecture to match xchg_tail requirement. T-HEAD C9xx processor
is the one.
We've tested the patch on SOPHGO sg2042 & th1520 and passed the stress
test on Fedora & Ubuntu & OpenEuler ... Here is the performance
comparison between qspinlock and ticket_lock on sg2042 (64 cores):
sysbench test=threads threads=32 yields=100 lock=8 (+13.8%):
queued_spinlock 0.5109/0.00
ticket_spinlock 0.5814/0.00
perf futex/hash (+6.7%):
queued_spinlock 1444393 operations/sec (+- 0.09%)
ticket_spinlock 1353215 operations/sec (+- 0.15%)
perf futex/wake-parallel (+8.6%):
queued_spinlock (waking 1/64 threads) in 0.0253 ms (+-2.90%)
ticket_spinlock (waking 1/64 threads) in 0.0275 ms (+-3.12%)
perf futex/requeue (+4.2%):
queued_spinlock Requeued 64 of 64 threads in 0.0785 ms (+-0.55%)
ticket_spinlock Requeued 64 of 64 threads in 0.0818 ms (+-4.12%)
System Benchmarks (+6.4%)
queued_spinlock:
System Benchmarks Index Values BASELINE RESULT INDEX
Dhrystone 2 using register variables 116700.0 628613745.4 53865.8
Double-Precision Whetstone 55.0 182422.8 33167.8
Execl Throughput 43.0 13116.6 3050.4
File Copy 1024 bufsize 2000 maxblocks 3960.0 7762306.2 19601.8
File Copy 256 bufsize 500 maxblocks 1655.0 3417556.8 20649.9
File Copy 4096 bufsize 8000 maxblocks 5800.0 7427995.7 12806.9
Pipe Throughput 12440.0 23058600.5 18535.9
Pipe-based Context Switching 4000.0 2835617.7 7089.0
Process Creation 126.0 12537.3 995.0
Shell Scripts (1 concurrent) 42.4 57057.4 13456.9
Shell Scripts (8 concurrent) 6.0 7367.1 12278.5
System Call Overhead 15000.0 33308301.3 22205.5
========
System Benchmarks Index Score 12426.1
ticket_spinlock:
System Benchmarks Index Values BASELINE RESULT INDEX
Dhrystone 2 using register variables 116700.0 626541701.9 53688.2
Double-Precision Whetstone 55.0 181921.0 33076.5
Execl Throughput 43.0 12625.1 2936.1
File Copy 1024 bufsize 2000 maxblocks 3960.0 6553792.9 16550.0
File Copy 256 bufsize 500 maxblocks 1655.0 3189231.6 19270.3
File Copy 4096 bufsize 8000 maxblocks 5800.0 7221277.0 12450.5
Pipe Throughput 12440.0 20594018.7 16554.7
Pipe-based Context Switching 4000.0 2571117.7 6427.8
Process Creation 126.0 10798.4 857.0
Shell Scripts (1 concurrent) 42.4 57227.5 13497.1
Shell Scripts (8 concurrent) 6.0 7329.2 12215.3
System Call Overhead 15000.0 30766778.4 20511.2
========
System Benchmarks Index Score 11670.7
The qspinlock has a significant improvement on SOPHGO SG2042 64
cores platform than the ticket_lock.
Signed-off-by: Guo Ren <guoren@xxxxxxxxxx>
Signed-off-by: Guo Ren <guoren@xxxxxxxxxxxxxxxxx>
---
arch/riscv/Kconfig | 16 ++++++++++++++++
arch/riscv/include/asm/Kbuild | 3 ++-
arch/riscv/include/asm/cmpxchg.h | 24 ++++++++++++++++++++++++
arch/riscv/include/asm/spinlock.h | 17 +++++++++++++++++
4 files changed, 59 insertions(+), 1 deletion(-)
create mode 100644 arch/riscv/include/asm/spinlock.h
diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
index 93ff677d2be5..e89a3bea3dc1 100644
--- a/arch/riscv/Kconfig
+++ b/arch/riscv/Kconfig
@@ -438,6 +438,22 @@ config NODES_SHIFT
Specify the maximum number of NUMA Nodes available on the target
system. Increases memory reserved to accommodate various tables.
+choice
+ prompt "RISC-V spinlock type"
+ default RISCV_TICKET_SPINLOCKS
+
+config RISCV_TICKET_SPINLOCKS
+ bool "Using ticket spinlock"
+
+config RISCV_QUEUED_SPINLOCKS
+ bool "Using queued spinlock"
+ depends on SMP && MMU
+ select ARCH_USE_QUEUED_SPINLOCKS
+ help
+ Make sure your micro arch LL/SC has a strong forward progress guarantee.
+ Otherwise, stay at ticket-lock.
+endchoice
+
config RISCV_ALTERNATIVE
bool
depends on !XIP_KERNEL
diff --git a/arch/riscv/include/asm/Kbuild b/arch/riscv/include/asm/Kbuild
index 504f8b7e72d4..a0dc85e4a754 100644
--- a/arch/riscv/include/asm/Kbuild
+++ b/arch/riscv/include/asm/Kbuild
@@ -2,10 +2,11 @@
generic-y += early_ioremap.h
generic-y += flat.h
generic-y += kvm_para.h
+generic-y += mcs_spinlock.h
generic-y += parport.h
-generic-y += spinlock.h
generic-y += spinlock_types.h
generic-y += qrwlock.h
generic-y += qrwlock_types.h
+generic-y += qspinlock.h
generic-y += user.h
generic-y += vmlinux.lds.h
diff --git a/arch/riscv/include/asm/cmpxchg.h b/arch/riscv/include/asm/cmpxchg.h
index 2f4726d3cfcc..d12231d752a4 100644
--- a/arch/riscv/include/asm/cmpxchg.h
+++ b/arch/riscv/include/asm/cmpxchg.h
@@ -11,12 +11,36 @@
#include <asm/barrier.h>
#include <asm/fence.h>
+static inline ulong __xchg16_relaxed(ulong new, void *ptr)
+{
+ ulong ret, tmp;
+ ulong shif = ((ulong)ptr & 2) ? 16 : 0;
+ ulong mask = 0xffff << shif;
+ ulong *__ptr = (ulong *)((ulong)ptr & ~2);
+
+ __asm__ __volatile__ (
+ "0: lr.w %0, %2\n"
+ " and %1, %0, %z3\n"
+ " or %1, %1, %z4\n"
+ " sc.w %1, %1, %2\n"
+ " bnez %1, 0b\n"
+ : "=&r" (ret), "=&r" (tmp), "+A" (*__ptr)
+ : "rJ" (~mask), "rJ" (new << shif)
+ : "memory");
+
+ return (ulong)((ret & mask) >> shif);
+}
+
#define __xchg_relaxed(ptr, new, size) \
({ \
__typeof__(ptr) __ptr = (ptr); \
__typeof__(new) __new = (new); \
__typeof__(*(ptr)) __ret; \
switch (size) { \
+ case 2: \
+ __ret = (__typeof__(*(ptr))) \
+ __xchg16_relaxed((ulong)__new, __ptr); \
+ break; \
case 4: \
__asm__ __volatile__ ( \
" amoswap.w %0, %2, %1\n" \
diff --git a/arch/riscv/include/asm/spinlock.h b/arch/riscv/include/asm/spinlock.h
new file mode 100644
index 000000000000..c644a92d4548
--- /dev/null
+++ b/arch/riscv/include/asm/spinlock.h
@@ -0,0 +1,17 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef __ASM_RISCV_SPINLOCK_H
+#define __ASM_RISCV_SPINLOCK_H
+
+#ifdef CONFIG_QUEUED_SPINLOCKS
+#define _Q_PENDING_LOOPS (1 << 9)
+#endif
+
+#ifdef CONFIG_QUEUED_SPINLOCKS
+#include <asm/qspinlock.h>
+#include <asm/qrwlock.h>
+#else
+#include <asm-generic/spinlock.h>
+#endif
+
+#endif /* __ASM_RISCV_SPINLOCK_H */
--
2.36.1
