From: Xiang Chen <chenxiang66@hisilicon.com> virt inclusion category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/IBPH85 ------------------------------------------------------------------------ This benchmark sends many IPIs in different modes and measures time for IPI delivery (first column), and total time, ie including time to acknowledge the receive by sender (second column). The scenarios are: Dry-run: do everything except actually sending IPI. Useful to estimate system overhead. Self-IPI: Send IPI to self CPU. Normal IPI: Send IPI to some other CPU. Broadcast IPI: Send broadcast IPI to all online CPUs. Broadcast lock: Send broadcast IPI to all online CPUs and force them acquire/release spinlock. The raw output looks like this: [ 155.363374] Dry-run: 0, 2999696 ns [ 155.429162] Self-IPI: 30385328, 65589392 ns [ 156.060821] Normal IPI: 566914128, 631453008 ns [ 158.384427] Broadcast IPI: 0, 2323368720 ns [ 160.831850] Broadcast lock: 0, 2447000544 ns For virtualized guests, sending and reveiving IPIs causes guest exit. I used this test to measure performance impact on KVM subsystem of Christoffer Dall's series "Optimize KVM/ARM for VHE systems" [1]. Test machine is ThunderX2, 112 online CPUs. Below the results normalized to host dry-run time, broadcast lock results omitted. Smaller - better. Host, v4.14: Dry-run: 0 1 Self-IPI: 9 18 Normal IPI: 81 110 Broadcast IPI: 0 2106 Guest, v4.14: Dry-run: 0 1 Self-IPI: 10 18 Normal IPI: 305 525 Broadcast IPI: 0 9729 Guest, v4.14 + [1]: Dry-run: 0 1 Self-IPI: 9 18 Normal IPI: 176 343 Broadcast IPI: 0 9885 [1] https://www.spinics.net/lists/kvm/msg156755.html v2: added broadcast lock test; added example raw output in patch description; CC: Andrew Morton <akpm@linux-foundation.org> CC: Ashish Kalra <Ashish.Kalra@cavium.com> CC: Christoffer Dall <christoffer.dall@linaro.org> CC: Geert Uytterhoeven <geert@linux-m68k.org> CC: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> CC: Linu Cherian <Linu.Cherian@cavium.com> CC: Shih-Wei Li <shihwei@cs.columbia.edu> CC: Sunil Goutham <Sunil.Goutham@cavium.com> Signed-off-by: Yury Norov <ynorov@caviumnetworks.com> Signed-off-by: Xiang Chen <chenxiang66@hisilicon.com> Signed-off-by: Jinqian Yang <yangjinqian1@huawei.com> --- arch/Kconfig | 10 +++ kernel/Makefile | 1 + kernel/ipi_benchmark.c | 155 +++++++++++++++++++++++++++++++++++++++++ 3 files changed, 166 insertions(+) create mode 100644 kernel/ipi_benchmark.c diff --git a/arch/Kconfig b/arch/Kconfig index a4ed5d338dad..43958c65e76f 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -97,6 +97,16 @@ config JUMP_LABEL ( On 32-bit x86, the necessary options added to the compiler flags may increase the size of the kernel slightly. ) +config IPI_BENCHMARK + tristate "Test IPI performance on SMP systems" + depends on SMP + help + Test IPI performance on SMP systems. If system has only one online + CPU, sending IPI to other CPU is obviously not possible, and ENOENT + is returned for corresponding test. + + If unsure, say N. + config STATIC_KEYS_SELFTEST bool "Static key selftest" depends on JUMP_LABEL diff --git a/kernel/Makefile b/kernel/Makefile index 1fe46db40806..f48134b8e29d 100644 --- a/kernel/Makefile +++ b/kernel/Makefile @@ -115,6 +115,7 @@ obj-$(CONFIG_HAVE_STATIC_CALL) += static_call.o obj-$(CONFIG_HAVE_STATIC_CALL_INLINE) += static_call_inline.o obj-$(CONFIG_CFI_CLANG) += cfi.o obj-$(CONFIG_PGO_CLANG) += pgo/ +obj-$(CONFIG_IPI_BENCHMARK) += ipi_benchmark.o obj-$(CONFIG_PERF_EVENTS) += events/ diff --git a/kernel/ipi_benchmark.c b/kernel/ipi_benchmark.c new file mode 100644 index 000000000000..8853ccb264ca --- /dev/null +++ b/kernel/ipi_benchmark.c @@ -0,0 +1,155 @@ +/* + * Performance test for IPI on SMP machines. + * + * Copyright (c) 2017 Cavium Networks. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of version 2 of the GNU General Public + * License as published by the Free Software Foundation. + * + * 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. + */ + +#include <linux/module.h> +#include <linux/kernel.h> +#include <linux/init.h> +#include <linux/ktime.h> + +#define NTIMES 100000 + +#define POKE_ANY 0 +#define DRY_RUN 1 +#define POKE_SELF 2 +#define POKE_ALL 3 +#define POKE_ALL_LOCK 4 + +static void __init handle_ipi_spinlock(void *t) +{ + spinlock_t *lock = (spinlock_t *) t; + + spin_lock(lock); + spin_unlock(lock); +} + +static void __init handle_ipi(void *t) +{ + ktime_t *time = (ktime_t *) t; + + if (time) + *time = ktime_get() - *time; +} + +static ktime_t __init send_ipi(int flags) +{ + ktime_t time = 0; + DEFINE_SPINLOCK(lock); + unsigned int cpu = get_cpu(); + + switch (flags) { + case DRY_RUN: + /* Do everything except actually sending IPI. */ + break; + case POKE_ALL: + /* If broadcasting, don't force all CPUs to update time. */ + smp_call_function_many(cpu_online_mask, handle_ipi, NULL, 1); + break; + case POKE_ALL_LOCK: + smp_call_function_many(cpu_online_mask, + handle_ipi_spinlock, &lock, 1); + break; + case POKE_ANY: + cpu = cpumask_any_but(cpu_online_mask, cpu); + if (cpu >= nr_cpu_ids) { + time = -ENOENT; + break; + } + time = ktime_get(); + smp_call_function_single(cpu, handle_ipi, &time, 1); + break; + case POKE_SELF: + time = ktime_get(); + smp_call_function_single(cpu, handle_ipi, &time, 1); + break; + default: + time = -EINVAL; + } + + put_cpu(); + return time; +} + +static int __init __bench_ipi(unsigned long i, ktime_t *time, int flags) +{ + ktime_t t; + + *time = 0; + while (i--) { + t = send_ipi(flags); + if ((int) t < 0) + return (int) t; + + *time += t; + } + + return 0; +} + +static int __init bench_ipi(unsigned long times, int flags, + ktime_t *ipi, ktime_t *total) +{ + int ret; + + *total = ktime_get(); + ret = __bench_ipi(times, ipi, flags); + if (unlikely(ret)) + return ret; + + *total = ktime_get() - *total; + + return 0; +} + +static int __init init_bench_ipi(void) +{ + ktime_t ipi, total; + int ret; + + ret = bench_ipi(NTIMES, DRY_RUN, &ipi, &total); + if (ret) + pr_err("Dry-run FAILED: %d\n", ret); + else + pr_err("Dry-run: %18llu, %18llu ns\n", ipi, total); + + ret = bench_ipi(NTIMES, POKE_SELF, &ipi, &total); + if (ret) + pr_err("Self-IPI FAILED: %d\n", ret); + else + pr_err("Self-IPI: %18llu, %18llu ns\n", ipi, total); + + ret = bench_ipi(NTIMES, POKE_ANY, &ipi, &total); + if (ret) + pr_err("Normal IPI FAILED: %d\n", ret); + else + pr_err("Normal IPI: %18llu, %18llu ns\n", ipi, total); + + ret = bench_ipi(NTIMES, POKE_ALL, &ipi, &total); + if (ret) + pr_err("Broadcast IPI FAILED: %d\n", ret); + else + pr_err("Broadcast IPI: %18llu, %18llu ns\n", ipi, total); + + ret = bench_ipi(NTIMES, POKE_ALL_LOCK, &ipi, &total); + if (ret) + pr_err("Broadcast lock FAILED: %d\n", ret); + else + pr_err("Broadcast lock: %18llu, %18llu ns\n", ipi, total); + + /* Return error to avoid annoying rmmod. */ + return -EINVAL; +} +module_init(init_bench_ipi); + +MODULE_LICENSE("GPL"); -- 2.33.0