From e9d338a0b1799c988b678e8ccb66a442272e6aa3 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Wed, 24 Jun 2020 15:59:59 -0700 Subject: [PATCH 01/19] scftorture: Add smp_call_function() torture test This commit adds an smp_call_function() torture test that repeatedly invokes this function and complains if things go badly awry. Signed-off-by: Paul E. McKenney --- .../admin-guide/kernel-parameters.txt | 92 +++++ kernel/Makefile | 2 + kernel/scftorture.c | 350 ++++++++++++++++++ lib/Kconfig.debug | 10 + 4 files changed, 454 insertions(+) create mode 100644 kernel/scftorture.c diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index bdc1f33fd3d1..91a56382ae56 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -4637,6 +4637,98 @@ Format: integer between 0 and 10 Default is 0. + scftorture.holdoff= [KNL] + Number of seconds to hold off before starting + test. Defaults to zero for module insertion and + to 10 seconds for built-in smp_call_function() + tests. + + scftorture.longwait= [KNL] + Request ridiculously long waits randomly selected + up to the chosen limit in seconds. Zero (the + default) disables this feature. Please note + that requesting even small non-zero numbers of + seconds can result in RCU CPU stall warnings, + softlockup complaints, and so on. + + scftorture.nthreads= [KNL] + Number of kthreads to spawn to invoke the + smp_call_function() family of functions. + The default of -1 specifies a number of kthreads + equal to the number of CPUs. + + scftorture.onoff_holdoff= [KNL] + Number seconds to wait after the start of the + test before initiating CPU-hotplug operations. + + scftorture.onoff_interval= [KNL] + Number seconds to wait between successive + CPU-hotplug operations. Specifying zero (which + is the default) disables CPU-hotplug operations. + + scftorture.shutdown_secs= [KNL] + The number of seconds following the start of the + test after which to shut down the system. The + default of zero avoids shutting down the system. + Non-zero values are useful for automated tests. + + scftorture.stat_interval= [KNL] + The number of seconds between outputting the + current test statistics to the console. A value + of zero disables statistics output. + + scftorture.stutter_cpus= [KNL] + The number of jiffies to wait between each change + to the set of CPUs under test. + + scftorture.use_cpus_read_lock= [KNL] + Use use_cpus_read_lock() instead of the default + preempt_disable() to disable CPU hotplug + while invoking one of the smp_call_function*() + functions. + + scftorture.verbose= [KNL] + Enable additional printk() statements. + + scftorture.weight_single= [KNL] + The probability weighting to use for the + smp_call_function_single() function with a zero + "wait" parameter. A value of -1 selects the + default if all other weights are -1. However, + if at least one weight has some other value, a + value of -1 will instead select a weight of zero. + + scftorture.weight_single_wait= [KNL] + The probability weighting to use for the + smp_call_function_single() function with a + non-zero "wait" parameter. See weight_single. + + scftorture.weight_many= [KNL] + The probability weighting to use for the + smp_call_function_many() function with a zero + "wait" parameter. See weight_single. + Note well that setting a high probability for + this weighting can place serious IPI load + on the system. + + scftorture.weight_many_wait= [KNL] + The probability weighting to use for the + smp_call_function_many() function with a + non-zero "wait" parameter. See weight_single + and weight_many. + + scftorture.weight_all= [KNL] + The probability weighting to use for the + smp_call_function_all() function with a zero + "wait" parameter. See weight_single and + weight_many. + + scftorture.weight_all_wait= [KNL] + The probability weighting to use for the + smp_call_function_all() function with a + non-zero "wait" parameter. See weight_single + and weight_many. + skew_tick= [KNL] Offset the periodic timer tick per cpu to mitigate xtime_lock contention on larger systems, and/or RCU lock contention on all systems with CONFIG_MAXSMP set. diff --git a/kernel/Makefile b/kernel/Makefile index 9a20016d4900..c45f551deaaa 100644 --- a/kernel/Makefile +++ b/kernel/Makefile @@ -133,6 +133,8 @@ KASAN_SANITIZE_stackleak.o := n KCSAN_SANITIZE_stackleak.o := n KCOV_INSTRUMENT_stackleak.o := n +obj-$(CONFIG_SCF_TORTURE_TEST) += scftorture.o + $(obj)/configs.o: $(obj)/config_data.gz targets += config_data.gz diff --git a/kernel/scftorture.c b/kernel/scftorture.c new file mode 100644 index 000000000000..44f1e49ba6e9 --- /dev/null +++ b/kernel/scftorture.c @@ -0,0 +1,350 @@ +// SPDX-License-Identifier: GPL-2.0+ +// +// Torture test for smp_call_function() and friends. +// +// Copyright (C) Facebook, 2020. +// +// Author: Paul E. McKenney + +#define pr_fmt(fmt) fmt + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#define SCFTORT_STRING "scftorture" +#define SCFTORT_FLAG SCFTORT_STRING ": " + +#define SCFTORTOUT(s, x...) \ + pr_alert(SCFTORT_FLAG s, ## x) + +#define VERBOSE_SCFTORTOUT(s, x...) \ + do { if (verbose) pr_alert(SCFTORT_FLAG s, ## x); } while (0) + +#define VERBOSE_SCFTORTOUT_ERRSTRING(s, x...) \ + do { if (verbose) pr_alert(SCFTORT_FLAG "!!! " s, ## x); } while (0) + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Paul E. McKenney "); + +// Wait until there are multiple CPUs before starting test. +torture_param(int, holdoff, IS_BUILTIN(CONFIG_SCF_TORTURE_TEST) ? 10 : 0, + "Holdoff time before test start (s)"); +torture_param(int, longwait, 0, "Include ridiculously long waits? (seconds)"); +torture_param(int, nthreads, -1, "# threads, defaults to -1 for all CPUs."); +torture_param(int, onoff_holdoff, 0, "Time after boot before CPU hotplugs (s)"); +torture_param(int, onoff_interval, 0, "Time between CPU hotplugs (s), 0=disable"); +torture_param(int, shutdown_secs, 0, "Shutdown time (ms), <= zero to disable."); +torture_param(int, stat_interval, 60, "Number of seconds between stats printk()s."); +torture_param(int, stutter_cpus, 5, "Number of jiffies to change CPUs under test, 0=disable"); +torture_param(bool, use_cpus_read_lock, 0, "Use cpus_read_lock() to exclude CPU hotplug."); +torture_param(int, verbose, 0, "Enable verbose debugging printk()s"); +torture_param(int, weight_single, -1, "Testing weight for single-CPU no-wait operations."); +torture_param(int, weight_single_wait, -1, "Testing weight for single-CPU operations."); +torture_param(int, weight_mult, -1, "Testing weight for multi-CPU no-wait operations."); +torture_param(int, weight_mult_wait, -1, "Testing weight for multi-CPU operations."); +torture_param(int, weight_all, -1, "Testing weight for all-CPU no-wait operations."); +torture_param(int, weight_all_wait, -1, "Testing weight for all-CPU operations."); + +char *torture_type = ""; + +#ifdef MODULE +# define SCFTORT_SHUTDOWN 0 +#else +# define SCFTORT_SHUTDOWN 1 +#endif + +torture_param(bool, shutdown, SCFTORT_SHUTDOWN, "Shutdown at end of torture test."); + +struct scf_statistics { + struct task_struct *task; + int cpu; + long long n_single; + long long n_single_wait; + long long n_multi; + long long n_multi_wait; + long long n_all; + long long n_all_wait; +}; + +static struct scf_statistics *scf_stats_p; +static struct task_struct *scf_torture_stats_task; +static DEFINE_PER_CPU(long long, scf_invoked_count); + +// Use to wait for all threads to start. +static atomic_t n_started; +static atomic_t n_errs; +static bool scfdone; + +DEFINE_TORTURE_RANDOM_PERCPU(scf_torture_rand); + +// Print torture statistics. Caller must ensure serialization. +static void scf_torture_stats_print(void) +{ + int cpu; + long long invoked_count = 0; + bool isdone = READ_ONCE(scfdone); + + for_each_possible_cpu(cpu) + invoked_count += data_race(per_cpu(scf_invoked_count, cpu)); + pr_alert("%s scf_invoked_count %s: %lld ", + SCFTORT_FLAG, isdone ? "VER" : "ver", invoked_count); + torture_onoff_stats(); + pr_cont("\n"); +} + +// Periodically prints torture statistics, if periodic statistics printing +// was specified via the stat_interval module parameter. +static int +scf_torture_stats(void *arg) +{ + VERBOSE_TOROUT_STRING("scf_torture_stats task started"); + do { + schedule_timeout_interruptible(stat_interval * HZ); + scf_torture_stats_print(); + torture_shutdown_absorb("scf_torture_stats"); + } while (!torture_must_stop()); + torture_kthread_stopping("scf_torture_stats"); + return 0; +} + +// Update statistics and occasionally burn up mass quantities of CPU time, +// if told to do so via scftorture.longwait. Otherwise, occasionally burn +// a little bit. +static void scf_handler(void *unused) +{ + int i; + int j; + unsigned long r = torture_random(this_cpu_ptr(&scf_torture_rand)); + + this_cpu_inc(scf_invoked_count); + if (longwait <= 0) { + if (!(r & 0xffc0)) + udelay(r & 0x3f); + return; + } + if (r & 0xfff) + return; + r = (r >> 12); + if (longwait <= 0) { + udelay((r & 0xff) + 1); + return; + } + r = r % longwait + 1; + for (i = 0; i < r; i++) { + for (j = 0; j < 1000; j++) { + udelay(1000); + cpu_relax(); + } + } +} + +// Randomly do an smp_call_function*() invocation. +static void scftorture_invoke_one(struct scf_statistics *scfp,struct torture_random_state *trsp) +{ + if (use_cpus_read_lock) + cpus_read_lock(); + else + preempt_disable(); + scfp->n_all++; + smp_call_function(scf_handler, NULL, 0); + if (use_cpus_read_lock) + cpus_read_unlock(); + else + preempt_enable(); + if (!(torture_random(trsp) & 0xfff)) + schedule_timeout_uninterruptible(1); +} + +// SCF test kthread. Repeatedly does calls to members of the +// smp_call_function() family of functions. +static int scftorture_invoker(void *arg) +{ + DEFINE_TORTURE_RANDOM(rand); + struct scf_statistics *scfp = (struct scf_statistics *)arg; + + VERBOSE_SCFTORTOUT("scftorture_invoker %d: task started", scfp->cpu); + set_cpus_allowed_ptr(current, cpumask_of(scfp->cpu % nr_cpu_ids)); + set_user_nice(current, MAX_NICE); + if (holdoff) + schedule_timeout_interruptible(holdoff * HZ); + + VERBOSE_SCFTORTOUT("scftorture_invoker %d: Waiting for all SCF torturers from cpu %d", scfp->cpu, smp_processor_id()); + + // Make sure that the CPU is affinitized appropriately during testing. + WARN_ON_ONCE(smp_processor_id() != scfp->cpu); + + if (!atomic_dec_return(&n_started)) + while (atomic_read_acquire(&n_started)) { + if (torture_must_stop()) { + VERBOSE_SCFTORTOUT("scftorture_invoker %d ended before starting", scfp->cpu); + goto end; + } + schedule_timeout_uninterruptible(1); + } + + VERBOSE_SCFTORTOUT("scftorture_invoker %d started", scfp->cpu); + + do { + scftorture_invoke_one(scfp, &rand); + } while (!torture_must_stop()); + + VERBOSE_SCFTORTOUT("scftorture_invoker %d ended", scfp->cpu); +end: + torture_kthread_stopping("scftorture_invoker"); + return 0; +} + +static void +scftorture_print_module_parms(const char *tag) +{ + pr_alert(SCFTORT_FLAG + "--- %s: verbose=%d holdoff=%d longwait=%d nthreads=%d onoff_holdoff=%d onoff_interval=%d shutdown_secs=%d stat_interval=%d stutter_cpus=%d use_cpus_read_lock=%d, weight_single=%d, weight_single_wait=%d, weight_mult=%d, weight_mult_wait=%d, weight_all=%d, weight_all_wait=%d\n", tag, + verbose, holdoff, longwait, nthreads, onoff_holdoff, onoff_interval, shutdown, stat_interval, stutter_cpus, use_cpus_read_lock, weight_single, weight_single_wait, weight_mult, weight_mult_wait, weight_all, weight_all_wait); +} + +static void scf_cleanup_handler(void *unused) +{ +} + +static void scf_torture_cleanup(void) +{ + int i; + + if (torture_cleanup_begin()) + return; + + WRITE_ONCE(scfdone, true); + if (nthreads) + for (i = 0; i < nthreads; i++) + torture_stop_kthread("scftorture_invoker", scf_stats_p[i].task); + else + goto end; + kfree(scf_stats_p); + scf_stats_p = NULL; + smp_call_function(scf_cleanup_handler, NULL, 0); + torture_stop_kthread(scf_torture_stats, scf_torture_stats_task); + scf_torture_stats_print(); // -After- the stats thread is stopped! + + if (atomic_read(&n_errs)) + scftorture_print_module_parms("End of test: FAILURE"); + else if (torture_onoff_failures()) + scftorture_print_module_parms("End of test: LOCK_HOTPLUG"); + else + scftorture_print_module_parms("End of test: SUCCESS"); + +end: + torture_cleanup_end(); +} + +static int __init scf_torture_init(void) +{ + long i; + int firsterr = 0; + + if (!torture_init_begin(SCFTORT_STRING, verbose)) + return -EBUSY; + + scftorture_print_module_parms("Start of test"); + + if (weight_single == -1 && weight_single_wait == -1 && + weight_mult == -1 && weight_mult_wait == -1 && + weight_all == -1 && weight_all_wait == -1) { + weight_single = 1; + weight_single_wait = 1; + weight_mult = 1; + weight_mult_wait = 1; + weight_all = 1; + weight_all_wait = 1; + } else { + if (weight_single == -1) + weight_single = 0; + if (weight_single_wait == -1) + weight_single_wait = 0; + if (weight_mult == -1) + weight_mult = 0; + if (weight_mult_wait == -1) + weight_mult_wait = 0; + if (weight_all == -1) + weight_all = 0; + if (weight_all_wait == -1) + weight_all_wait = 0; + } + if (weight_single == 0 && weight_single_wait == 0 && + weight_mult == 0 && weight_mult_wait == 0 && + weight_all == 0 && weight_all_wait == 0) { + firsterr = -EINVAL; + goto unwind; + } + + if (onoff_interval > 0) { + firsterr = torture_onoff_init(onoff_holdoff * HZ, onoff_interval, NULL); + if (firsterr) + goto unwind; + } + if (shutdown_secs > 0) { + firsterr = torture_shutdown_init(shutdown_secs, scf_torture_cleanup); + if (firsterr) + goto unwind; + } + + // Worker tasks invoking smp_call_function(). + if (nthreads < 0) + nthreads = num_online_cpus(); + scf_stats_p = kcalloc(nthreads, sizeof(scf_stats_p[0]), GFP_KERNEL); + if (!scf_stats_p) { + VERBOSE_SCFTORTOUT_ERRSTRING("out of memory"); + firsterr = -ENOMEM; + goto unwind; + } + + VERBOSE_SCFTORTOUT("Starting %d smp_call_function() threads\n", nthreads); + + atomic_set(&n_started, nthreads); + for (i = 0; i < nthreads; i++) { + scf_stats_p[i].cpu = i; + firsterr = torture_create_kthread(scftorture_invoker, (void *)&scf_stats_p[i], + scf_stats_p[i].task); + if (firsterr) + goto unwind; + } + if (stat_interval > 0) { + firsterr = torture_create_kthread(scf_torture_stats, NULL, scf_torture_stats_task); + if (firsterr) + goto unwind; + } + + torture_init_end(); + return 0; + +unwind: + torture_init_end(); + scf_torture_cleanup(); + return firsterr; +} + +module_init(scf_torture_init); +module_exit(scf_torture_cleanup); diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index e068c3c7189a..0c3a6c752ede 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -1367,6 +1367,16 @@ config WW_MUTEX_SELFTEST Say M if you want these self tests to build as a module. Say N if you are unsure. +config SCF_TORTURE_TEST + tristate "torture tests for smp_call_function*()" + depends on DEBUG_KERNEL + select TORTURE_TEST + help + This option provides a kernel module that runs torture tests + on the smp_call_function() family of primitives. The kernel + module may be built after the fact on the running kernel to + be tested, if desired. + endmenu # lock debugging config TRACE_IRQFLAGS From 687d4775db56d24c81b4704056186d6c506de30d Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Tue, 30 Jun 2020 13:37:22 -0700 Subject: [PATCH 02/19] torture: Declare parse-console.sh independence from rcutorture Currently, parse-torture.sh looks at the fifth field of torture-test console output for the version number. This works fine for rcutorture, but not for scftorture, which lacks the pointer field. This commit therefore adjusts matching lines so that the parse-console.sh awk script always sees the version number as the first field in the lines passed to it. Signed-off-by: Paul E. McKenney --- tools/testing/selftests/rcutorture/bin/parse-console.sh | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/tools/testing/selftests/rcutorture/bin/parse-console.sh b/tools/testing/selftests/rcutorture/bin/parse-console.sh index 71a9f43a3918..4e081a25761e 100755 --- a/tools/testing/selftests/rcutorture/bin/parse-console.sh +++ b/tools/testing/selftests/rcutorture/bin/parse-console.sh @@ -67,6 +67,7 @@ then grep --binary-files=text 'torture:.*ver:' $file | egrep --binary-files=text -v '\(null\)|rtc: 000000000* ' | sed -e 's/^(initramfs)[^]]*] //' -e 's/^\[[^]]*] //' | + sed -e 's/^.*ver: //' | awk ' BEGIN { ver = 0; @@ -74,13 +75,13 @@ then } { - if (!badseq && ($5 + 0 != $5 || $5 <= ver)) { + if (!badseq && ($1 + 0 != $1 || $1 <= ver)) { badseqno1 = ver; - badseqno2 = $5; + badseqno2 = $1; badseqnr = NR; badseq = 1; } - ver = $5 + ver = $1 } END { From 80c9476e683ec37ba45fd8e6a5c5081bea207e1a Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Wed, 24 Jun 2020 17:57:07 -0700 Subject: [PATCH 03/19] torture: Add scftorture to the rcutorture scripting This commit updates the rcutorture scripting to include the new scftorture torture-test module. Signed-off-by: Paul E. McKenney --- .../rcutorture/bin/kvm-recheck-scf.sh | 38 +++++++++++++++++++ tools/testing/selftests/rcutorture/bin/kvm.sh | 2 +- .../selftests/rcutorture/configs/scf/CFLIST | 2 + .../selftests/rcutorture/configs/scf/CFcommon | 2 + .../rcutorture/configs/scf/NOPREEMPT | 9 +++++ .../rcutorture/configs/scf/NOPREEMPT.boot | 1 + .../selftests/rcutorture/configs/scf/PREEMPT | 9 +++++ .../rcutorture/configs/scf/ver_functions.sh | 30 +++++++++++++++ 8 files changed, 92 insertions(+), 1 deletion(-) create mode 100755 tools/testing/selftests/rcutorture/bin/kvm-recheck-scf.sh create mode 100644 tools/testing/selftests/rcutorture/configs/scf/CFLIST create mode 100644 tools/testing/selftests/rcutorture/configs/scf/CFcommon create mode 100644 tools/testing/selftests/rcutorture/configs/scf/NOPREEMPT create mode 100644 tools/testing/selftests/rcutorture/configs/scf/NOPREEMPT.boot create mode 100644 tools/testing/selftests/rcutorture/configs/scf/PREEMPT create mode 100644 tools/testing/selftests/rcutorture/configs/scf/ver_functions.sh diff --git a/tools/testing/selftests/rcutorture/bin/kvm-recheck-scf.sh b/tools/testing/selftests/rcutorture/bin/kvm-recheck-scf.sh new file mode 100755 index 000000000000..671bfee4fcef --- /dev/null +++ b/tools/testing/selftests/rcutorture/bin/kvm-recheck-scf.sh @@ -0,0 +1,38 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0+ +# +# Analyze a given results directory for rcutorture progress. +# +# Usage: kvm-recheck-rcu.sh resdir +# +# Copyright (C) Facebook, 2020 +# +# Authors: Paul E. McKenney + +i="$1" +if test -d "$i" -a -r "$i" +then + : +else + echo Unreadable results directory: $i + exit 1 +fi +. functions.sh + +configfile=`echo $i | sed -e 's/^.*\///'` +nscfs="`grep 'scf_invoked_count ver:' $i/console.log 2> /dev/null | tail -1 | sed -e 's/^.* scf_invoked_count ver: //' -e 's/ .*$//' | tr -d '\015'`" +if test -z "$nscfs" +then + echo "$configfile ------- " +else + dur="`sed -e 's/^.* scftorture.shutdown_secs=//' -e 's/ .*$//' < $i/qemu-cmd 2> /dev/null`" + if test -z "$dur" + then + rate="" + else + nscfss=`awk -v nscfs=$nscfs -v dur=$dur ' + BEGIN { print nscfs / dur }' < /dev/null` + rate=" ($nscfss/s)" + fi + echo "${configfile} ------- ${nscfs} SCF handler invocations$rate" +fi diff --git a/tools/testing/selftests/rcutorture/bin/kvm.sh b/tools/testing/selftests/rcutorture/bin/kvm.sh index e655983b7429..44dfdd9be67e 100755 --- a/tools/testing/selftests/rcutorture/bin/kvm.sh +++ b/tools/testing/selftests/rcutorture/bin/kvm.sh @@ -184,7 +184,7 @@ do shift ;; --torture) - checkarg --torture "(suite name)" "$#" "$2" '^\(lock\|rcu\|rcuperf\|refscale\)$' '^--' + checkarg --torture "(suite name)" "$#" "$2" '^\(lock\|rcu\|rcuperf\|refscale\|scf\)$' '^--' TORTURE_SUITE=$2 shift if test "$TORTURE_SUITE" = rcuperf || test "$TORTURE_SUITE" = refscale diff --git a/tools/testing/selftests/rcutorture/configs/scf/CFLIST b/tools/testing/selftests/rcutorture/configs/scf/CFLIST new file mode 100644 index 000000000000..4d62eb4a39f9 --- /dev/null +++ b/tools/testing/selftests/rcutorture/configs/scf/CFLIST @@ -0,0 +1,2 @@ +NOPREEMPT +PREEMPT diff --git a/tools/testing/selftests/rcutorture/configs/scf/CFcommon b/tools/testing/selftests/rcutorture/configs/scf/CFcommon new file mode 100644 index 000000000000..c11ab91f49f5 --- /dev/null +++ b/tools/testing/selftests/rcutorture/configs/scf/CFcommon @@ -0,0 +1,2 @@ +CONFIG_SCF_TORTURE_TEST=y +CONFIG_PRINTK_TIME=y diff --git a/tools/testing/selftests/rcutorture/configs/scf/NOPREEMPT b/tools/testing/selftests/rcutorture/configs/scf/NOPREEMPT new file mode 100644 index 000000000000..b8429d6c6ebc --- /dev/null +++ b/tools/testing/selftests/rcutorture/configs/scf/NOPREEMPT @@ -0,0 +1,9 @@ +CONFIG_SMP=y +CONFIG_PREEMPT_NONE=y +CONFIG_PREEMPT_VOLUNTARY=n +CONFIG_PREEMPT=n +CONFIG_HZ_PERIODIC=n +CONFIG_NO_HZ_IDLE=n +CONFIG_NO_HZ_FULL=y +CONFIG_DEBUG_LOCK_ALLOC=n +CONFIG_PROVE_LOCKING=n diff --git a/tools/testing/selftests/rcutorture/configs/scf/NOPREEMPT.boot b/tools/testing/selftests/rcutorture/configs/scf/NOPREEMPT.boot new file mode 100644 index 000000000000..d6a7fa097c2e --- /dev/null +++ b/tools/testing/selftests/rcutorture/configs/scf/NOPREEMPT.boot @@ -0,0 +1 @@ +nohz_full=1 diff --git a/tools/testing/selftests/rcutorture/configs/scf/PREEMPT b/tools/testing/selftests/rcutorture/configs/scf/PREEMPT new file mode 100644 index 000000000000..ae4992b141b0 --- /dev/null +++ b/tools/testing/selftests/rcutorture/configs/scf/PREEMPT @@ -0,0 +1,9 @@ +CONFIG_SMP=y +CONFIG_PREEMPT_NONE=n +CONFIG_PREEMPT_VOLUNTARY=n +CONFIG_PREEMPT=y +CONFIG_HZ_PERIODIC=n +CONFIG_NO_HZ_IDLE=y +CONFIG_NO_HZ_FULL=n +CONFIG_DEBUG_LOCK_ALLOC=y +CONFIG_PROVE_LOCKING=y diff --git a/tools/testing/selftests/rcutorture/configs/scf/ver_functions.sh b/tools/testing/selftests/rcutorture/configs/scf/ver_functions.sh new file mode 100644 index 000000000000..d3d9e35d3d55 --- /dev/null +++ b/tools/testing/selftests/rcutorture/configs/scf/ver_functions.sh @@ -0,0 +1,30 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0+ +# +# Torture-suite-dependent shell functions for the rest of the scripts. +# +# Copyright (C) Facebook, 2020 +# +# Authors: Paul E. McKenney + +# scftorture_param_onoff bootparam-string config-file +# +# Adds onoff scftorture module parameters to kernels having it. +scftorture_param_onoff () { + if ! bootparam_hotplug_cpu "$1" && configfrag_hotplug_cpu "$2" + then + echo CPU-hotplug kernel, adding scftorture onoff. 1>&2 + echo scftorture.onoff_interval=1000 scftorture.onoff_holdoff=30 + fi +} + +# per_version_boot_params bootparam-string config-file seconds +# +# Adds per-version torture-module parameters to kernels supporting them. +per_version_boot_params () { + echo $1 `scftorture_param_onoff "$1" "$2"` \ + scftorture.stat_interval=15 \ + scftorture.shutdown_secs=$3 \ + scftorture.verbose=1 \ + scf +} From 5022b8ac608f8b80b042a8041fe2738c4b9ea8cf Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Thu, 25 Jun 2020 17:05:58 -0700 Subject: [PATCH 04/19] scftorture: Implement weighted primitive selection This commit uses the scftorture.weight* kernel parameters to randomly chooses between smp_call_function_single(), smp_call_function_many(), and smp_call_function(). For each variant, it also randomly chooses whether to invoke it synchronously (wait=1) or asynchronously (wait=0). The percentage weighting for each option are dumped to the console log (search for "scf_sel_dump"). This accumulates statistics, which a later commit will dump out at the end of the run. Signed-off-by: Paul E. McKenney --- kernel/scftorture.c | 184 +++++++++++++++++++++++++++++++++++++------- 1 file changed, 156 insertions(+), 28 deletions(-) diff --git a/kernel/scftorture.c b/kernel/scftorture.c index 44f1e49ba6e9..5f1984522ae4 100644 --- a/kernel/scftorture.c +++ b/kernel/scftorture.c @@ -64,8 +64,8 @@ torture_param(bool, use_cpus_read_lock, 0, "Use cpus_read_lock() to exclude CPU torture_param(int, verbose, 0, "Enable verbose debugging printk()s"); torture_param(int, weight_single, -1, "Testing weight for single-CPU no-wait operations."); torture_param(int, weight_single_wait, -1, "Testing weight for single-CPU operations."); -torture_param(int, weight_mult, -1, "Testing weight for multi-CPU no-wait operations."); -torture_param(int, weight_mult_wait, -1, "Testing weight for multi-CPU operations."); +torture_param(int, weight_many, -1, "Testing weight for multi-CPU no-wait operations."); +torture_param(int, weight_many_wait, -1, "Testing weight for multi-CPU operations."); torture_param(int, weight_all, -1, "Testing weight for all-CPU no-wait operations."); torture_param(int, weight_all_wait, -1, "Testing weight for all-CPU operations."); @@ -83,9 +83,11 @@ struct scf_statistics { struct task_struct *task; int cpu; long long n_single; + long long n_single_ofl; long long n_single_wait; - long long n_multi; - long long n_multi_wait; + long long n_single_wait_ofl; + long long n_many; + long long n_many_wait; long long n_all; long long n_all_wait; }; @@ -94,6 +96,27 @@ static struct scf_statistics *scf_stats_p; static struct task_struct *scf_torture_stats_task; static DEFINE_PER_CPU(long long, scf_invoked_count); +// Data for random primitive selection +#define SCF_PRIM_SINGLE 0 +#define SCF_PRIM_MANY 1 +#define SCF_PRIM_ALL 2 +#define SCF_NPRIMS (2 * 3) // Need wait and no-wait versions of each. + +static char *scf_prim_name[] = { + "smp_call_function_single", + "smp_call_function_many", + "smp_call_function", +}; + +struct scf_selector { + unsigned long scfs_weight; + int scfs_prim; + bool scfs_wait; +}; +static struct scf_selector scf_sel_array[SCF_NPRIMS]; +static int scf_sel_array_len; +static unsigned long scf_sel_totweight; + // Use to wait for all threads to start. static atomic_t n_started; static atomic_t n_errs; @@ -131,6 +154,57 @@ scf_torture_stats(void *arg) return 0; } +// Add a primitive to the scf_sel_array[]. +static void scf_sel_add(unsigned long weight, int prim, bool wait) +{ + struct scf_selector *scfsp = &scf_sel_array[scf_sel_array_len]; + + // If no weight, if array would overflow, if computing three-place + // percentages would overflow, or if the scf_prim_name[] array would + // overflow, don't bother. In the last three two cases, complain. + if (!weight || + WARN_ON_ONCE(scf_sel_array_len >= ARRAY_SIZE(scf_sel_array)) || + WARN_ON_ONCE(0 - 100000 * weight <= 100000 * scf_sel_totweight) || + WARN_ON_ONCE(prim >= ARRAY_SIZE(scf_prim_name))) + return; + scf_sel_totweight += weight; + scfsp->scfs_weight = scf_sel_totweight; + scfsp->scfs_prim = prim; + scfsp->scfs_wait = wait; + scf_sel_array_len++; +} + +// Dump out weighting percentages for scf_prim_name[] array. +static void scf_sel_dump(void) +{ + int i; + unsigned long oldw = 0; + struct scf_selector *scfsp; + unsigned long w; + + for (i = 0; i < scf_sel_array_len; i++) { + scfsp = &scf_sel_array[i]; + w = (scfsp->scfs_weight - oldw) * 100000 / scf_sel_totweight; + pr_info("%s: %3lu.%03lu %s(%s)\n", __func__, w / 1000, w % 1000, + scf_prim_name[scfsp->scfs_prim], + scfsp->scfs_wait ? "wait" : "nowait"); + oldw = scfsp->scfs_weight; + } +} + +// Randomly pick a primitive and wait/nowait, based on weightings. +static struct scf_selector *scf_sel_rand(struct torture_random_state *trsp) +{ + int i; + unsigned long w = torture_random(trsp) % (scf_sel_totweight + 1); + + for (i = 0; i < scf_sel_array_len; i++) + if (scf_sel_array[i].scfs_weight >= w) + return &scf_sel_array[i]; + WARN_ON_ONCE(1); + return &scf_sel_array[0]; +} + // Update statistics and occasionally burn up mass quantities of CPU time, // if told to do so via scftorture.longwait. Otherwise, occasionally burn // a little bit. @@ -162,15 +236,55 @@ static void scf_handler(void *unused) } } -// Randomly do an smp_call_function*() invocation. -static void scftorture_invoke_one(struct scf_statistics *scfp,struct torture_random_state *trsp) +// As above, but check for correct CPU. +static void scf_handler_1(void *me) { + if (WARN_ON_ONCE(smp_processor_id() != (uintptr_t)me)) + atomic_inc(&n_errs); + scf_handler(NULL); +} + +// Randomly do an smp_call_function*() invocation. +static void scftorture_invoke_one(struct scf_statistics *scfp, struct torture_random_state *trsp) +{ + uintptr_t cpu; + int ret; + struct scf_selector *scfsp = scf_sel_rand(trsp); + if (use_cpus_read_lock) cpus_read_lock(); else preempt_disable(); - scfp->n_all++; - smp_call_function(scf_handler, NULL, 0); + switch (scfsp->scfs_prim) { + case SCF_PRIM_SINGLE: + cpu = torture_random(trsp) % nr_cpu_ids; + if (scfsp->scfs_wait) + scfp->n_single_wait++; + else + scfp->n_single++; + ret = smp_call_function_single(cpu, scf_handler_1, (void *)cpu, scfsp->scfs_wait); + if (ret) { + if (scfsp->scfs_wait) + scfp->n_single_wait_ofl++; + else + scfp->n_single_ofl++; + } + break; + case SCF_PRIM_MANY: + if (scfsp->scfs_wait) + scfp->n_many_wait++; + else + scfp->n_many++; + smp_call_function_many(cpu_online_mask, scf_handler, NULL, scfsp->scfs_wait); + break; + case SCF_PRIM_ALL: + if (scfsp->scfs_wait) + scfp->n_all_wait++; + else + scfp->n_all++; + smp_call_function(scf_handler, NULL, scfsp->scfs_wait); + break; + } if (use_cpus_read_lock) cpus_read_unlock(); else @@ -222,8 +336,8 @@ static void scftorture_print_module_parms(const char *tag) { pr_alert(SCFTORT_FLAG - "--- %s: verbose=%d holdoff=%d longwait=%d nthreads=%d onoff_holdoff=%d onoff_interval=%d shutdown_secs=%d stat_interval=%d stutter_cpus=%d use_cpus_read_lock=%d, weight_single=%d, weight_single_wait=%d, weight_mult=%d, weight_mult_wait=%d, weight_all=%d, weight_all_wait=%d\n", tag, - verbose, holdoff, longwait, nthreads, onoff_holdoff, onoff_interval, shutdown, stat_interval, stutter_cpus, use_cpus_read_lock, weight_single, weight_single_wait, weight_mult, weight_mult_wait, weight_all, weight_all_wait); + "--- %s: verbose=%d holdoff=%d longwait=%d nthreads=%d onoff_holdoff=%d onoff_interval=%d shutdown_secs=%d stat_interval=%d stutter_cpus=%d use_cpus_read_lock=%d, weight_single=%d, weight_single_wait=%d, weight_many=%d, weight_many_wait=%d, weight_all=%d, weight_all_wait=%d\n", tag, + verbose, holdoff, longwait, nthreads, onoff_holdoff, onoff_interval, shutdown, stat_interval, stutter_cpus, use_cpus_read_lock, weight_single, weight_single_wait, weight_many, weight_many_wait, weight_all, weight_all_wait); } static void scf_cleanup_handler(void *unused) @@ -264,6 +378,12 @@ static int __init scf_torture_init(void) { long i; int firsterr = 0; + unsigned long weight_single1 = weight_single; + unsigned long weight_single_wait1 = weight_single_wait; + unsigned long weight_many1 = weight_many; + unsigned long weight_many_wait1 = weight_many_wait; + unsigned long weight_all1 = weight_all; + unsigned long weight_all_wait1 = weight_all_wait; if (!torture_init_begin(SCFTORT_STRING, verbose)) return -EBUSY; @@ -271,34 +391,42 @@ static int __init scf_torture_init(void) scftorture_print_module_parms("Start of test"); if (weight_single == -1 && weight_single_wait == -1 && - weight_mult == -1 && weight_mult_wait == -1 && + weight_many == -1 && weight_many_wait == -1 && weight_all == -1 && weight_all_wait == -1) { - weight_single = 1; - weight_single_wait = 1; - weight_mult = 1; - weight_mult_wait = 1; - weight_all = 1; - weight_all_wait = 1; + weight_single1 = 2 * nr_cpu_ids; + weight_single_wait1 = 2 * nr_cpu_ids; + weight_many1 = 2; + weight_many_wait1 = 2; + weight_all1 = 1; + weight_all_wait1 = 1; } else { if (weight_single == -1) - weight_single = 0; + weight_single1 = 0; if (weight_single_wait == -1) - weight_single_wait = 0; - if (weight_mult == -1) - weight_mult = 0; - if (weight_mult_wait == -1) - weight_mult_wait = 0; + weight_single_wait1 = 0; + if (weight_many == -1) + weight_many1 = 0; + if (weight_many_wait == -1) + weight_many_wait1 = 0; if (weight_all == -1) - weight_all = 0; + weight_all1 = 0; if (weight_all_wait == -1) - weight_all_wait = 0; + weight_all_wait1 = 0; } - if (weight_single == 0 && weight_single_wait == 0 && - weight_mult == 0 && weight_mult_wait == 0 && - weight_all == 0 && weight_all_wait == 0) { + if (weight_single1 == 0 && weight_single_wait1 == 0 && + weight_many1 == 0 && weight_many_wait1 == 0 && + weight_all1 == 0 && weight_all_wait1 == 0) { + VERBOSE_SCFTORTOUT_ERRSTRING("all zero weights makes no sense"); firsterr = -EINVAL; goto unwind; } + scf_sel_add(weight_single1, SCF_PRIM_SINGLE, false); + scf_sel_add(weight_single_wait1, SCF_PRIM_SINGLE, true); + scf_sel_add(weight_many1, SCF_PRIM_MANY, false); + scf_sel_add(weight_many_wait1, SCF_PRIM_MANY, true); + scf_sel_add(weight_all1, SCF_PRIM_ALL, false); + scf_sel_add(weight_all_wait1, SCF_PRIM_ALL, true); + scf_sel_dump(); if (onoff_interval > 0) { firsterr = torture_onoff_init(onoff_holdoff * HZ, onoff_interval, NULL); From bca37119c57bdc2c68c84b313a5118005e8693cf Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Fri, 26 Jun 2020 13:39:41 -0700 Subject: [PATCH 05/19] tick-sched: Clarify "NOHZ: local_softirq_pending" warning Currently, can_stop_idle_tick() prints "NOHZ: local_softirq_pending HH" (where "HH" is the hexadecimal softirq vector number) when one or more non-RCU softirq handlers are still enabled when checking to stop the scheduler-tick interrupt. This message is not as enlightening as one might hope, so this commit changes it to "NOHZ tick-stop error: Non-RCU local softirq work is pending, handler #HH". Reported-by: Andy Lutomirski Cc: Frederic Weisbecker Cc: Thomas Gleixner Cc: Ingo Molnar Signed-off-by: Paul E. McKenney --- kernel/time/tick-sched.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index f0199a4ba1ad..81632cd5e3b7 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -927,7 +927,7 @@ static bool can_stop_idle_tick(int cpu, struct tick_sched *ts) if (ratelimit < 10 && (local_softirq_pending() & SOFTIRQ_STOP_IDLE_MASK)) { - pr_warn("NOHZ: local_softirq_pending %02x\n", + pr_warn("NOHZ tick-stop error: Non-RCU local softirq work is pending, handler #%02x!!!\n", (unsigned int) local_softirq_pending()); ratelimit++; } From dba3142b37f343734bf61dbce2914acb76e69fb6 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Tue, 30 Jun 2020 16:13:37 -0700 Subject: [PATCH 06/19] scftorture: Summarize per-thread statistics This commit summarizes the per-thread statistics, providing counts of the number of single, many, and all calls, both no-wait and wait, and, for the single case, the number where the target CPU was offline. Signed-off-by: Paul E. McKenney --- kernel/scftorture.c | 22 ++++++++++++++++++---- 1 file changed, 18 insertions(+), 4 deletions(-) diff --git a/kernel/scftorture.c b/kernel/scftorture.c index 5f1984522ae4..09a62424bb8c 100644 --- a/kernel/scftorture.c +++ b/kernel/scftorture.c @@ -128,13 +128,27 @@ DEFINE_TORTURE_RANDOM_PERCPU(scf_torture_rand); static void scf_torture_stats_print(void) { int cpu; + int i; long long invoked_count = 0; bool isdone = READ_ONCE(scfdone); + struct scf_statistics scfs = {}; for_each_possible_cpu(cpu) invoked_count += data_race(per_cpu(scf_invoked_count, cpu)); - pr_alert("%s scf_invoked_count %s: %lld ", - SCFTORT_FLAG, isdone ? "VER" : "ver", invoked_count); + for (i = 0; i < nthreads; i++) { + scfs.n_single += scf_stats_p[i].n_single; + scfs.n_single_ofl += scf_stats_p[i].n_single_ofl; + scfs.n_single_wait += scf_stats_p[i].n_single_wait; + scfs.n_single_wait_ofl += scf_stats_p[i].n_single_wait_ofl; + scfs.n_many += scf_stats_p[i].n_many; + scfs.n_many_wait += scf_stats_p[i].n_many_wait; + scfs.n_all += scf_stats_p[i].n_all; + scfs.n_all_wait += scf_stats_p[i].n_all_wait; + } + pr_alert("%s scf_invoked_count %s: %lld single: %lld/%lld single_ofl: %lld/%lld many: %lld/%lld all: %lld/%lld ", + SCFTORT_FLAG, isdone ? "VER" : "ver", invoked_count, + scfs.n_single, scfs.n_single_wait, scfs.n_single_ofl, scfs.n_single_wait_ofl, + scfs.n_many, scfs.n_many_wait, scfs.n_all, scfs.n_all_wait); torture_onoff_stats(); pr_cont("\n"); } @@ -357,11 +371,11 @@ static void scf_torture_cleanup(void) torture_stop_kthread("scftorture_invoker", scf_stats_p[i].task); else goto end; - kfree(scf_stats_p); - scf_stats_p = NULL; smp_call_function(scf_cleanup_handler, NULL, 0); torture_stop_kthread(scf_torture_stats, scf_torture_stats_task); scf_torture_stats_print(); // -After- the stats thread is stopped! + kfree(scf_stats_p); // -After- the last stats print has completed! + scf_stats_p = NULL; if (atomic_read(&n_errs)) scftorture_print_module_parms("End of test: FAILURE"); From b93e21a51e1c8ed3816da888d34f88193ad1b917 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Tue, 30 Jun 2020 20:49:50 -0700 Subject: [PATCH 07/19] scftorture: Add smp_call_function_single() memory-ordering checks This commit adds checks for memory misordering across calls to smp_call_function_single() and also across returns in the case where the caller waits. Misordering results in a splat. [ paulmck: s/GFP_KERNEL/GFP_ATOMIC/ per kernel test robot feedback. ] Signed-off-by: Paul E. McKenney --- kernel/scftorture.c | 56 ++++++++++++++++++++++++++++++++++++++------- 1 file changed, 48 insertions(+), 8 deletions(-) diff --git a/kernel/scftorture.c b/kernel/scftorture.c index 09a62424bb8c..9b42271d64f1 100644 --- a/kernel/scftorture.c +++ b/kernel/scftorture.c @@ -117,9 +117,20 @@ static struct scf_selector scf_sel_array[SCF_NPRIMS]; static int scf_sel_array_len; static unsigned long scf_sel_totweight; +// Communicate between caller and handler. +struct scf_check { + bool scfc_in; + bool scfc_out; + int scfc_cpu; // -1 for not _single(). + bool scfc_wait; +}; + // Use to wait for all threads to start. static atomic_t n_started; static atomic_t n_errs; +static atomic_t n_mb_in_errs; +static atomic_t n_mb_out_errs; +static atomic_t n_alloc_errs; static bool scfdone; DEFINE_TORTURE_RANDOM_PERCPU(scf_torture_rand); @@ -222,24 +233,27 @@ static struct scf_selector *scf_sel_rand(struct torture_random_state *trsp) // Update statistics and occasionally burn up mass quantities of CPU time, // if told to do so via scftorture.longwait. Otherwise, occasionally burn // a little bit. -static void scf_handler(void *unused) +static void scf_handler(void *scfc_in) { int i; int j; unsigned long r = torture_random(this_cpu_ptr(&scf_torture_rand)); + struct scf_check *scfcp = scfc_in; + if (likely(scfcp) && WARN_ON_ONCE(unlikely(!READ_ONCE(scfcp->scfc_in)))) + atomic_inc(&n_mb_in_errs); this_cpu_inc(scf_invoked_count); if (longwait <= 0) { if (!(r & 0xffc0)) udelay(r & 0x3f); - return; + goto out; } if (r & 0xfff) - return; + goto out; r = (r >> 12); if (longwait <= 0) { udelay((r & 0xff) + 1); - return; + goto out; } r = r % longwait + 1; for (i = 0; i < r; i++) { @@ -248,14 +262,24 @@ static void scf_handler(void *unused) cpu_relax(); } } +out: + if (unlikely(!scfcp)) + return; + if (scfcp->scfc_wait) + WRITE_ONCE(scfcp->scfc_out, true); + else + kfree(scfcp); } // As above, but check for correct CPU. -static void scf_handler_1(void *me) +static void scf_handler_1(void *scfc_in) { - if (WARN_ON_ONCE(smp_processor_id() != (uintptr_t)me)) + struct scf_check *scfcp = scfc_in; + + if (likely(scfcp) && WARN_ONCE(smp_processor_id() != scfcp->scfc_cpu, "%s: Wanted CPU %d got CPU %d\n", __func__, scfcp->scfc_cpu, smp_processor_id())) { atomic_inc(&n_errs); - scf_handler(NULL); + } + scf_handler(scfcp); } // Randomly do an smp_call_function*() invocation. @@ -263,6 +287,7 @@ static void scftorture_invoke_one(struct scf_statistics *scfp, struct torture_ra { uintptr_t cpu; int ret; + struct scf_check *scfcp = NULL; struct scf_selector *scfsp = scf_sel_rand(trsp); if (use_cpus_read_lock) @@ -271,17 +296,32 @@ static void scftorture_invoke_one(struct scf_statistics *scfp, struct torture_ra preempt_disable(); switch (scfsp->scfs_prim) { case SCF_PRIM_SINGLE: + scfcp = kmalloc(sizeof(*scfcp), GFP_ATOMIC); + if (WARN_ON_ONCE(!scfcp)) + atomic_inc(&n_alloc_errs); cpu = torture_random(trsp) % nr_cpu_ids; if (scfsp->scfs_wait) scfp->n_single_wait++; else scfp->n_single++; - ret = smp_call_function_single(cpu, scf_handler_1, (void *)cpu, scfsp->scfs_wait); + if (scfcp) { + scfcp->scfc_cpu = cpu; + scfcp->scfc_wait = scfsp->scfs_wait; + scfcp->scfc_out = false; + scfcp->scfc_in = true; + } + ret = smp_call_function_single(cpu, scf_handler_1, (void *)scfcp, scfsp->scfs_wait); if (ret) { if (scfsp->scfs_wait) scfp->n_single_wait_ofl++; else scfp->n_single_ofl++; + kfree(scfcp); + } else if (scfcp && scfsp->scfs_wait) { + if (WARN_ON_ONCE(!scfcp->scfc_out)) + atomic_inc(&n_mb_out_errs); // Leak rather than trash! + else + kfree(scfcp); } break; case SCF_PRIM_MANY: From 980205ee8489d53c4380f7762debac87312b0fb3 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Wed, 1 Jul 2020 12:30:02 -0700 Subject: [PATCH 08/19] scftorture: Add smp_call_function_many() memory-ordering checks This commit adds checks for memory misordering across calls to and returns from smp_call_function_many() in the case where the caller waits. Misordering results in a splat. Note that in contrast to smp_call_function_single(), this code does not test memory ordering into the handler in the no-wait case because none of the handlers would be able to free the scf_check structure without introducing heavy synchronization to work out which was last. [ paulmck: s/GFP_KERNEL/GFP_ATOMIC/ per kernel test robot feedback. ] Signed-off-by: Paul E. McKenney --- kernel/scftorture.c | 26 +++++++++++++++++++++++--- 1 file changed, 23 insertions(+), 3 deletions(-) diff --git a/kernel/scftorture.c b/kernel/scftorture.c index 9b42271d64f1..3519ad1b3278 100644 --- a/kernel/scftorture.c +++ b/kernel/scftorture.c @@ -240,8 +240,11 @@ static void scf_handler(void *scfc_in) unsigned long r = torture_random(this_cpu_ptr(&scf_torture_rand)); struct scf_check *scfcp = scfc_in; - if (likely(scfcp) && WARN_ON_ONCE(unlikely(!READ_ONCE(scfcp->scfc_in)))) - atomic_inc(&n_mb_in_errs); + if (likely(scfcp)) { + WRITE_ONCE(scfcp->scfc_out, false); // For multiple receivers. + if (WARN_ON_ONCE(unlikely(!READ_ONCE(scfcp->scfc_in)))) + atomic_inc(&n_mb_in_errs); + } this_cpu_inc(scf_invoked_count); if (longwait <= 0) { if (!(r & 0xffc0)) @@ -325,11 +328,28 @@ static void scftorture_invoke_one(struct scf_statistics *scfp, struct torture_ra } break; case SCF_PRIM_MANY: + if (scfsp->scfs_wait) { + scfcp = kmalloc(sizeof(*scfcp), GFP_ATOMIC); + if (WARN_ON_ONCE(!scfcp)) + atomic_inc(&n_alloc_errs); + } if (scfsp->scfs_wait) scfp->n_many_wait++; else scfp->n_many++; - smp_call_function_many(cpu_online_mask, scf_handler, NULL, scfsp->scfs_wait); + if (scfcp) { + scfcp->scfc_cpu = -1; + scfcp->scfc_wait = true; + scfcp->scfc_out = false; + scfcp->scfc_in = true; + } + smp_call_function_many(cpu_online_mask, scf_handler, scfcp, scfsp->scfs_wait); + if (scfcp) { + if (WARN_ON_ONCE(!scfcp->scfc_out)) + atomic_inc(&n_mb_out_errs); // Leak rather than trash! + else + kfree(scfcp); + } break; case SCF_PRIM_ALL: if (scfsp->scfs_wait) From 34e8c4837adb579962e528a4f7dd1f75cb120be4 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Wed, 1 Jul 2020 13:49:06 -0700 Subject: [PATCH 09/19] scftorture: Add smp_call_function() memory-ordering checks This commit adds checks for memory misordering across calls to and returns from smp_call_function() in the case where the caller waits. Misordering results in a splat. Note that in contrast to smp_call_function_single(), this code does not test memory ordering into the handler in the no-wait case because none of the handlers would be able to free the scf_check structure without introducing heavy synchronization to work out which was last. [ paulmck: s/GFP_KERNEL/GFP_ATOMIC/ per kernel test robot feedback. ] Signed-off-by: Paul E. McKenney --- kernel/scftorture.c | 25 +++++++++++++++++-------- 1 file changed, 17 insertions(+), 8 deletions(-) diff --git a/kernel/scftorture.c b/kernel/scftorture.c index 3519ad1b3278..0d7299d32dd0 100644 --- a/kernel/scftorture.c +++ b/kernel/scftorture.c @@ -297,11 +297,13 @@ static void scftorture_invoke_one(struct scf_statistics *scfp, struct torture_ra cpus_read_lock(); else preempt_disable(); - switch (scfsp->scfs_prim) { - case SCF_PRIM_SINGLE: + if (scfsp->scfs_prim == SCF_PRIM_SINGLE || scfsp->scfs_wait) { scfcp = kmalloc(sizeof(*scfcp), GFP_ATOMIC); if (WARN_ON_ONCE(!scfcp)) atomic_inc(&n_alloc_errs); + } + switch (scfsp->scfs_prim) { + case SCF_PRIM_SINGLE: cpu = torture_random(trsp) % nr_cpu_ids; if (scfsp->scfs_wait) scfp->n_single_wait++; @@ -328,11 +330,6 @@ static void scftorture_invoke_one(struct scf_statistics *scfp, struct torture_ra } break; case SCF_PRIM_MANY: - if (scfsp->scfs_wait) { - scfcp = kmalloc(sizeof(*scfcp), GFP_ATOMIC); - if (WARN_ON_ONCE(!scfcp)) - atomic_inc(&n_alloc_errs); - } if (scfsp->scfs_wait) scfp->n_many_wait++; else @@ -356,7 +353,19 @@ static void scftorture_invoke_one(struct scf_statistics *scfp, struct torture_ra scfp->n_all_wait++; else scfp->n_all++; - smp_call_function(scf_handler, NULL, scfsp->scfs_wait); + if (scfcp) { + scfcp->scfc_cpu = -1; + scfcp->scfc_wait = true; + scfcp->scfc_out = false; + scfcp->scfc_in = true; + } + smp_call_function(scf_handler, scfcp, scfsp->scfs_wait); + if (scfcp) { + if (WARN_ON_ONCE(!scfcp->scfc_out)) + atomic_inc(&n_mb_out_errs); // Leak rather than trash! + else + kfree(scfcp); + } break; } if (use_cpus_read_lock) From 676e5469643e716df7f39ef77ba8f09c85b0c4f8 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Wed, 1 Jul 2020 14:13:02 -0700 Subject: [PATCH 10/19] scftorture: Consolidate scftorture_invoke_one() check and kfree() This commit moves checking of the ->scfc_out field and the freeing of the scf_check structure down below the end of switch statement, thus saving a few lines of code. Signed-off-by: Paul E. McKenney --- kernel/scftorture.c | 26 ++++++++------------------ 1 file changed, 8 insertions(+), 18 deletions(-) diff --git a/kernel/scftorture.c b/kernel/scftorture.c index 0d7299d32dd0..f220cd364e23 100644 --- a/kernel/scftorture.c +++ b/kernel/scftorture.c @@ -289,7 +289,7 @@ static void scf_handler_1(void *scfc_in) static void scftorture_invoke_one(struct scf_statistics *scfp, struct torture_random_state *trsp) { uintptr_t cpu; - int ret; + int ret = 0; struct scf_check *scfcp = NULL; struct scf_selector *scfsp = scf_sel_rand(trsp); @@ -322,11 +322,7 @@ static void scftorture_invoke_one(struct scf_statistics *scfp, struct torture_ra else scfp->n_single_ofl++; kfree(scfcp); - } else if (scfcp && scfsp->scfs_wait) { - if (WARN_ON_ONCE(!scfcp->scfc_out)) - atomic_inc(&n_mb_out_errs); // Leak rather than trash! - else - kfree(scfcp); + scfcp = NULL; } break; case SCF_PRIM_MANY: @@ -341,12 +337,6 @@ static void scftorture_invoke_one(struct scf_statistics *scfp, struct torture_ra scfcp->scfc_in = true; } smp_call_function_many(cpu_online_mask, scf_handler, scfcp, scfsp->scfs_wait); - if (scfcp) { - if (WARN_ON_ONCE(!scfcp->scfc_out)) - atomic_inc(&n_mb_out_errs); // Leak rather than trash! - else - kfree(scfcp); - } break; case SCF_PRIM_ALL: if (scfsp->scfs_wait) @@ -360,14 +350,14 @@ static void scftorture_invoke_one(struct scf_statistics *scfp, struct torture_ra scfcp->scfc_in = true; } smp_call_function(scf_handler, scfcp, scfsp->scfs_wait); - if (scfcp) { - if (WARN_ON_ONCE(!scfcp->scfc_out)) - atomic_inc(&n_mb_out_errs); // Leak rather than trash! - else - kfree(scfcp); - } break; } + if (scfcp && scfsp->scfs_wait) { + if (WARN_ON_ONCE(!scfcp->scfc_out)) + atomic_inc(&n_mb_out_errs); // Leak rather than trash! + else + kfree(scfcp); + } if (use_cpus_read_lock) cpus_read_unlock(); else From 4df55bddc1a360e94c86e227fe417ac9422cb615 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Thu, 9 Jul 2020 13:58:32 -0700 Subject: [PATCH 11/19] scftorture: Consolidate scftorture_invoke_one() scf_check initialization This commit hoists much of the initialization of the scf_check structure out of the switch statement, thus saving a few lines of code. The initialization of the ->scfc_in field remains in each leg of the switch statement in order to more heavily stress memory ordering. Signed-off-by: Paul E. McKenney --- kernel/scftorture.c | 21 ++++++++------------- 1 file changed, 8 insertions(+), 13 deletions(-) diff --git a/kernel/scftorture.c b/kernel/scftorture.c index f220cd364e23..8ab72e545a61 100644 --- a/kernel/scftorture.c +++ b/kernel/scftorture.c @@ -299,8 +299,13 @@ static void scftorture_invoke_one(struct scf_statistics *scfp, struct torture_ra preempt_disable(); if (scfsp->scfs_prim == SCF_PRIM_SINGLE || scfsp->scfs_wait) { scfcp = kmalloc(sizeof(*scfcp), GFP_ATOMIC); - if (WARN_ON_ONCE(!scfcp)) + if (WARN_ON_ONCE(!scfcp)) { atomic_inc(&n_alloc_errs); + } else { + scfcp->scfc_cpu = -1; + scfcp->scfc_wait = scfsp->scfs_wait; + scfcp->scfc_out = false; + } } switch (scfsp->scfs_prim) { case SCF_PRIM_SINGLE: @@ -311,8 +316,6 @@ static void scftorture_invoke_one(struct scf_statistics *scfp, struct torture_ra scfp->n_single++; if (scfcp) { scfcp->scfc_cpu = cpu; - scfcp->scfc_wait = scfsp->scfs_wait; - scfcp->scfc_out = false; scfcp->scfc_in = true; } ret = smp_call_function_single(cpu, scf_handler_1, (void *)scfcp, scfsp->scfs_wait); @@ -330,12 +333,8 @@ static void scftorture_invoke_one(struct scf_statistics *scfp, struct torture_ra scfp->n_many_wait++; else scfp->n_many++; - if (scfcp) { - scfcp->scfc_cpu = -1; - scfcp->scfc_wait = true; - scfcp->scfc_out = false; + if (scfcp) scfcp->scfc_in = true; - } smp_call_function_many(cpu_online_mask, scf_handler, scfcp, scfsp->scfs_wait); break; case SCF_PRIM_ALL: @@ -343,12 +342,8 @@ static void scftorture_invoke_one(struct scf_statistics *scfp, struct torture_ra scfp->n_all_wait++; else scfp->n_all++; - if (scfcp) { - scfcp->scfc_cpu = -1; - scfcp->scfc_wait = true; - scfcp->scfc_out = false; + if (scfcp) scfcp->scfc_in = true; - } smp_call_function(scf_handler, scfcp, scfsp->scfs_wait); break; } From dbf83b655a7853bc430af10e9a3e7eb1f4c90f86 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Wed, 1 Jul 2020 16:06:22 -0700 Subject: [PATCH 12/19] scftorture: Flag errors in torture-compatible manner This commit prints error counts on the statistics line and also adds a "!!!" if any of the counters are non-zero. Allocation failures are (somewhat) forgiven, but all other errors result in a "FAILURE" print at the end of the test. Signed-off-by: Paul E. McKenney --- kernel/scftorture.c | 14 ++++++++++---- 1 file changed, 10 insertions(+), 4 deletions(-) diff --git a/kernel/scftorture.c b/kernel/scftorture.c index 8ab72e545a61..880c2cef13e7 100644 --- a/kernel/scftorture.c +++ b/kernel/scftorture.c @@ -132,6 +132,7 @@ static atomic_t n_mb_in_errs; static atomic_t n_mb_out_errs; static atomic_t n_alloc_errs; static bool scfdone; +static char *bangstr = ""; DEFINE_TORTURE_RANDOM_PERCPU(scf_torture_rand); @@ -156,12 +157,17 @@ static void scf_torture_stats_print(void) scfs.n_all += scf_stats_p[i].n_all; scfs.n_all_wait += scf_stats_p[i].n_all_wait; } - pr_alert("%s scf_invoked_count %s: %lld single: %lld/%lld single_ofl: %lld/%lld many: %lld/%lld all: %lld/%lld ", - SCFTORT_FLAG, isdone ? "VER" : "ver", invoked_count, + if (atomic_read(&n_errs) || atomic_read(&n_mb_in_errs) || + atomic_read(&n_mb_out_errs) || atomic_read(&n_alloc_errs)) + bangstr = "!!! "; + pr_alert("%s %sscf_invoked_count %s: %lld single: %lld/%lld single_ofl: %lld/%lld many: %lld/%lld all: %lld/%lld ", + SCFTORT_FLAG, bangstr, isdone ? "VER" : "ver", invoked_count, scfs.n_single, scfs.n_single_wait, scfs.n_single_ofl, scfs.n_single_wait_ofl, scfs.n_many, scfs.n_many_wait, scfs.n_all, scfs.n_all_wait); torture_onoff_stats(); - pr_cont("\n"); + pr_cont("ste: %d stnmie: %d stnmoe: %d staf: %d\n", atomic_read(&n_errs), + atomic_read(&n_mb_in_errs), atomic_read(&n_mb_out_errs), + atomic_read(&n_alloc_errs)); } // Periodically prints torture statistics, if periodic statistics printing @@ -431,7 +437,7 @@ static void scf_torture_cleanup(void) kfree(scf_stats_p); // -After- the last stats print has completed! scf_stats_p = NULL; - if (atomic_read(&n_errs)) + if (atomic_read(&n_errs) || atomic_read(&n_mb_in_errs) || atomic_read(&n_mb_out_errs)) scftorture_print_module_parms("End of test: FAILURE"); else if (torture_onoff_failures()) scftorture_print_module_parms("End of test: LOCK_HOTPLUG"); From ee7035d29576dcb59b1191e5f609517cacab1e56 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Wed, 1 Jul 2020 16:38:16 -0700 Subject: [PATCH 13/19] scftorture: Prevent compiler from reducing race probabilities Detecting smp_call_function() memory misordering requires close timing, so it is necessary to have the checks immediately before and after the call to the smp_call_function*() function under test. This commit therefore inserts barrier() calls to prevent the compiler from optimizing memory-misordering detection down into the zone of extreme improbability. Signed-off-by: Paul E. McKenney --- kernel/scftorture.c | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) diff --git a/kernel/scftorture.c b/kernel/scftorture.c index 880c2cef13e7..83496810fc48 100644 --- a/kernel/scftorture.c +++ b/kernel/scftorture.c @@ -322,6 +322,7 @@ static void scftorture_invoke_one(struct scf_statistics *scfp, struct torture_ra scfp->n_single++; if (scfcp) { scfcp->scfc_cpu = cpu; + barrier(); // Prevent race-reduction compiler optimizations. scfcp->scfc_in = true; } ret = smp_call_function_single(cpu, scf_handler_1, (void *)scfcp, scfsp->scfs_wait); @@ -339,8 +340,10 @@ static void scftorture_invoke_one(struct scf_statistics *scfp, struct torture_ra scfp->n_many_wait++; else scfp->n_many++; - if (scfcp) + if (scfcp) { + barrier(); // Prevent race-reduction compiler optimizations. scfcp->scfc_in = true; + } smp_call_function_many(cpu_online_mask, scf_handler, scfcp, scfsp->scfs_wait); break; case SCF_PRIM_ALL: @@ -348,8 +351,10 @@ static void scftorture_invoke_one(struct scf_statistics *scfp, struct torture_ra scfp->n_all_wait++; else scfp->n_all++; - if (scfcp) + if (scfcp) { + barrier(); // Prevent race-reduction compiler optimizations. scfcp->scfc_in = true; + } smp_call_function(scf_handler, scfcp, scfsp->scfs_wait); break; } @@ -358,6 +363,7 @@ static void scftorture_invoke_one(struct scf_statistics *scfp, struct torture_ra atomic_inc(&n_mb_out_errs); // Leak rather than trash! else kfree(scfcp); + barrier(); // Prevent race-reduction compiler optimizations. } if (use_cpus_read_lock) cpus_read_unlock(); From 9a52a574676f8d4aa55f69319231ce6c343b00bb Mon Sep 17 00:00:00 2001 From: Wei Yongjun Date: Thu, 2 Jul 2020 09:56:50 -0700 Subject: [PATCH 14/19] scftorture: Make symbol 'scf_torture_rand' static The sparse tool complains as follows kernel/scftorture.c:124:1: warning: symbol '__pcpu_scope_scf_torture_rand' was not declared. Should it be static? And this per-CPU variable is not used outside of scftorture.c, so this commit marks it static. Reported-by: Hulk Robot Signed-off-by: Wei Yongjun Signed-off-by: Paul E. McKenney --- kernel/scftorture.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/scftorture.c b/kernel/scftorture.c index 83496810fc48..9180de73e4e8 100644 --- a/kernel/scftorture.c +++ b/kernel/scftorture.c @@ -134,7 +134,7 @@ static atomic_t n_alloc_errs; static bool scfdone; static char *bangstr = ""; -DEFINE_TORTURE_RANDOM_PERCPU(scf_torture_rand); +static DEFINE_TORTURE_RANDOM_PERCPU(scf_torture_rand); // Print torture statistics. Caller must ensure serialization. static void scf_torture_stats_print(void) From de77d4da54d10df97d265e7e99112bfc2fef7d4a Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Thu, 2 Jul 2020 12:15:37 -0700 Subject: [PATCH 15/19] scftorture: Check unexpected "switch" statement value This commit adds a "default" case to the switch statement in scftorture_invoke_one() which contains a WARN_ON_ONCE() and an assignment to ->scfc_out to suppress knock-on warnings. These knock-on warnings could otherwise cause the user to think that there was a memory-ordering problem in smp_call_function() instead of a bug in scftorture.c itself. Signed-off-by: Paul E. McKenney --- kernel/scftorture.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/kernel/scftorture.c b/kernel/scftorture.c index 9180de73e4e8..d9c01c722e2a 100644 --- a/kernel/scftorture.c +++ b/kernel/scftorture.c @@ -357,6 +357,10 @@ static void scftorture_invoke_one(struct scf_statistics *scfp, struct torture_ra } smp_call_function(scf_handler, scfcp, scfsp->scfs_wait); break; + default: + WARN_ON_ONCE(1); + if (scfcp) + scfcp->scfc_out = true; } if (scfcp && scfsp->scfs_wait) { if (WARN_ON_ONCE(!scfcp->scfc_out)) From a7c072ef26644b632241d549869f10f8d2dd3b5c Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Thu, 2 Jul 2020 14:15:33 -0700 Subject: [PATCH 16/19] scftorture: Block scftorture_invoker() kthreads for offline CPUs Currently, CPU-hotplug operations might result in all but two of (say) 100 CPUs being offline, which in turn might result in false-positive diagnostics due to overload. This commit therefore causes scftorture_invoker() kthreads for offline CPUs to loop blocking for 200 milliseconds at a time, thus continuously adjusting the number of threads to match the number of online CPUs. Signed-off-by: Paul E. McKenney --- kernel/scftorture.c | 13 ++++++++++++- 1 file changed, 12 insertions(+), 1 deletion(-) diff --git a/kernel/scftorture.c b/kernel/scftorture.c index d9c01c722e2a..04d3a4279413 100644 --- a/kernel/scftorture.c +++ b/kernel/scftorture.c @@ -381,11 +381,14 @@ static void scftorture_invoke_one(struct scf_statistics *scfp, struct torture_ra // smp_call_function() family of functions. static int scftorture_invoker(void *arg) { + int cpu; DEFINE_TORTURE_RANDOM(rand); struct scf_statistics *scfp = (struct scf_statistics *)arg; + bool was_offline = false; VERBOSE_SCFTORTOUT("scftorture_invoker %d: task started", scfp->cpu); - set_cpus_allowed_ptr(current, cpumask_of(scfp->cpu % nr_cpu_ids)); + cpu = scfp->cpu % nr_cpu_ids; + set_cpus_allowed_ptr(current, cpumask_of(cpu)); set_user_nice(current, MAX_NICE); if (holdoff) schedule_timeout_interruptible(holdoff * HZ); @@ -408,6 +411,14 @@ static int scftorture_invoker(void *arg) do { scftorture_invoke_one(scfp, &rand); + while (cpu_is_offline(cpu) && !torture_must_stop()) { + schedule_timeout_interruptible(HZ / 5); + was_offline = true; + } + if (was_offline) { + set_cpus_allowed_ptr(current, cpumask_of(cpu)); + was_offline = false; + } } while (!torture_must_stop()); VERBOSE_SCFTORTOUT("scftorture_invoker %d ended", scfp->cpu); From 9e66bf03f9c538863e614a72c5799bcd9579630e Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Fri, 3 Jul 2020 15:23:19 -0700 Subject: [PATCH 17/19] scftorture: Adapt memory-ordering test to UP operation On uniprocessor systems, smp_call_function() does nothing. This commit therefore avoids complaining about the lack of handler accesses in the single-CPU case where there is no handler. Signed-off-by: Paul E. McKenney --- kernel/scftorture.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/kernel/scftorture.c b/kernel/scftorture.c index 04d3a4279413..fc22bcc9a589 100644 --- a/kernel/scftorture.c +++ b/kernel/scftorture.c @@ -363,7 +363,8 @@ static void scftorture_invoke_one(struct scf_statistics *scfp, struct torture_ra scfcp->scfc_out = true; } if (scfcp && scfsp->scfs_wait) { - if (WARN_ON_ONCE(!scfcp->scfc_out)) + if (WARN_ON_ONCE((num_online_cpus() > 1 || scfsp->scfs_prim == SCF_PRIM_SINGLE) && + !scfcp->scfc_out)) atomic_inc(&n_mb_out_errs); // Leak rather than trash! else kfree(scfcp); From 65bd77f554336407f5fd7ced7a6df686767fba21 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Thu, 23 Jul 2020 15:53:02 -0700 Subject: [PATCH 18/19] scftorture: Add cond_resched() to test loop Although the test loop does randomly delay, which would provide quiescent states and so forth, it is possible for there to be a series of long smp_call_function*() handler runtimes with no delays, which results in softlockup and RCU CPU stall warning messages. This commit therefore inserts a cond_resched() into the main test loop. Signed-off-by: Paul E. McKenney --- kernel/scftorture.c | 1 + 1 file changed, 1 insertion(+) diff --git a/kernel/scftorture.c b/kernel/scftorture.c index fc22bcc9a589..554a521ee235 100644 --- a/kernel/scftorture.c +++ b/kernel/scftorture.c @@ -420,6 +420,7 @@ static int scftorture_invoker(void *arg) set_cpus_allowed_ptr(current, cpumask_of(cpu)); was_offline = false; } + cond_resched(); } while (!torture_must_stop()); VERBOSE_SCFTORTOUT("scftorture_invoker %d ended", scfp->cpu); From 4e88ec4a9eb17527e640b063f79e5b875733eb53 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Tue, 11 Aug 2020 21:18:12 -0700 Subject: [PATCH 19/19] rcuperf: Change rcuperf to rcuscale This commit further avoids conflation of rcuperf with the kernel's perf feature by renaming kernel/rcu/rcuperf.c to kernel/rcu/rcuscale.c, and also by similarly renaming the functions and variables inside this file. This has the side effect of changing the names of the kernel boot parameters, so kernel-parameters.txt and ver_functions.sh are also updated. The rcutorture --torture type was also updated from rcuperf to rcuscale. [ paulmck: Fix bugs located by Stephen Rothwell. ] Reported-by: Ingo Molnar Signed-off-by: Paul E. McKenney --- .../admin-guide/kernel-parameters.txt | 36 +- MAINTAINERS | 3 +- kernel/rcu/Kconfig.debug | 2 +- kernel/rcu/Makefile | 2 +- kernel/rcu/{rcuperf.c => rcuscale.c} | 330 +++++++++--------- ...race.sh => kvm-recheck-rcuscale-ftrace.sh} | 6 +- ...eck-rcuperf.sh => kvm-recheck-rcuscale.sh} | 14 +- tools/testing/selftests/rcutorture/bin/kvm.sh | 8 +- .../selftests/rcutorture/bin/parse-console.sh | 4 +- .../rcutorture/configs/rcuperf/CFcommon | 2 - .../configs/{rcuperf => rcuscale}/CFLIST | 0 .../rcutorture/configs/rcuscale/CFcommon | 2 + .../configs/{rcuperf => rcuscale}/TINY | 0 .../configs/{rcuperf => rcuscale}/TREE | 0 .../configs/{rcuperf => rcuscale}/TREE54 | 0 .../{rcuperf => rcuscale}/ver_functions.sh | 4 +- 16 files changed, 207 insertions(+), 206 deletions(-) rename kernel/rcu/{rcuperf.c => rcuscale.c} (64%) rename tools/testing/selftests/rcutorture/bin/{kvm-recheck-rcuperf-ftrace.sh => kvm-recheck-rcuscale-ftrace.sh} (92%) rename tools/testing/selftests/rcutorture/bin/{kvm-recheck-rcuperf.sh => kvm-recheck-rcuscale.sh} (84%) delete mode 100644 tools/testing/selftests/rcutorture/configs/rcuperf/CFcommon rename tools/testing/selftests/rcutorture/configs/{rcuperf => rcuscale}/CFLIST (100%) create mode 100644 tools/testing/selftests/rcutorture/configs/rcuscale/CFcommon rename tools/testing/selftests/rcutorture/configs/{rcuperf => rcuscale}/TINY (100%) rename tools/testing/selftests/rcutorture/configs/{rcuperf => rcuscale}/TREE (100%) rename tools/testing/selftests/rcutorture/configs/{rcuperf => rcuscale}/TREE54 (100%) rename tools/testing/selftests/rcutorture/configs/{rcuperf => rcuscale}/ver_functions.sh (88%) diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index 91a56382ae56..c27bbe95e7cb 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -4157,41 +4157,41 @@ rcu_node tree with an eye towards determining why a new grace period has not yet started. - rcuperf.gp_async= [KNL] + rcuscale.gp_async= [KNL] Measure performance of asynchronous grace-period primitives such as call_rcu(). - rcuperf.gp_async_max= [KNL] + rcuscale.gp_async_max= [KNL] Specify the maximum number of outstanding callbacks per writer thread. When a writer thread exceeds this limit, it invokes the corresponding flavor of rcu_barrier() to allow previously posted callbacks to drain. - rcuperf.gp_exp= [KNL] + rcuscale.gp_exp= [KNL] Measure performance of expedited synchronous grace-period primitives. - rcuperf.holdoff= [KNL] + rcuscale.holdoff= [KNL] Set test-start holdoff period. The purpose of this parameter is to delay the start of the test until boot completes in order to avoid interference. - rcuperf.kfree_rcu_test= [KNL] + rcuscale.kfree_rcu_test= [KNL] Set to measure performance of kfree_rcu() flooding. - rcuperf.kfree_nthreads= [KNL] + rcuscale.kfree_nthreads= [KNL] The number of threads running loops of kfree_rcu(). - rcuperf.kfree_alloc_num= [KNL] + rcuscale.kfree_alloc_num= [KNL] Number of allocations and frees done in an iteration. - rcuperf.kfree_loops= [KNL] - Number of loops doing rcuperf.kfree_alloc_num number + rcuscale.kfree_loops= [KNL] + Number of loops doing rcuscale.kfree_alloc_num number of allocations and frees. - rcuperf.nreaders= [KNL] + rcuscale.nreaders= [KNL] Set number of RCU readers. The value -1 selects N, where N is the number of CPUs. A value "n" less than -1 selects N-n+1, where N is again @@ -4200,23 +4200,23 @@ A value of "n" less than or equal to -N selects a single reader. - rcuperf.nwriters= [KNL] + rcuscale.nwriters= [KNL] Set number of RCU writers. The values operate - the same as for rcuperf.nreaders. + the same as for rcuscale.nreaders. N, where N is the number of CPUs - rcuperf.perf_type= [KNL] + rcuscale.perf_type= [KNL] Specify the RCU implementation to test. - rcuperf.shutdown= [KNL] + rcuscale.shutdown= [KNL] Shut the system down after performance tests complete. This is useful for hands-off automated testing. - rcuperf.verbose= [KNL] + rcuscale.verbose= [KNL] Enable additional printk() statements. - rcuperf.writer_holdoff= [KNL] + rcuscale.writer_holdoff= [KNL] Write-side holdoff between grace periods, in microseconds. The default of zero says no holdoff. @@ -4490,8 +4490,8 @@ refscale.shutdown= [KNL] Shut down the system at the end of the performance test. This defaults to 1 (shut it down) when - rcuperf is built into the kernel and to 0 (leave - it running) when rcuperf is built as a module. + refscale is built into the kernel and to 0 (leave + it running) when refscale is built as a module. refscale.verbose= [KNL] Enable additional printk() statements. diff --git a/MAINTAINERS b/MAINTAINERS index deaafb617361..d299e3bb10ad 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -17510,8 +17510,9 @@ S: Supported T: git git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-rcu.git dev F: Documentation/RCU/torture.rst F: kernel/locking/locktorture.c -F: kernel/rcu/rcuperf.c +F: kernel/rcu/rcuscale.c F: kernel/rcu/rcutorture.c +F: kernel/rcu/refscale.c F: kernel/torture.c TOSHIBA ACPI EXTRAS DRIVER diff --git a/kernel/rcu/Kconfig.debug b/kernel/rcu/Kconfig.debug index 3cf6132a4bb9..5cb175df6ece 100644 --- a/kernel/rcu/Kconfig.debug +++ b/kernel/rcu/Kconfig.debug @@ -23,7 +23,7 @@ config TORTURE_TEST tristate default n -config RCU_PERF_TEST +config RCU_SCALE_TEST tristate "performance tests for RCU" depends on DEBUG_KERNEL select TORTURE_TEST diff --git a/kernel/rcu/Makefile b/kernel/rcu/Makefile index 95f5117ef8da..0cfb009a99b9 100644 --- a/kernel/rcu/Makefile +++ b/kernel/rcu/Makefile @@ -11,7 +11,7 @@ obj-y += update.o sync.o obj-$(CONFIG_TREE_SRCU) += srcutree.o obj-$(CONFIG_TINY_SRCU) += srcutiny.o obj-$(CONFIG_RCU_TORTURE_TEST) += rcutorture.o -obj-$(CONFIG_RCU_PERF_TEST) += rcuperf.o +obj-$(CONFIG_RCU_SCALE_TEST) += rcuscale.o obj-$(CONFIG_RCU_REF_SCALE_TEST) += refscale.o obj-$(CONFIG_TREE_RCU) += tree.o obj-$(CONFIG_TINY_RCU) += tiny.o diff --git a/kernel/rcu/rcuperf.c b/kernel/rcu/rcuscale.c similarity index 64% rename from kernel/rcu/rcuperf.c rename to kernel/rcu/rcuscale.c index 21448d3374e2..2819b95479af 100644 --- a/kernel/rcu/rcuperf.c +++ b/kernel/rcu/rcuscale.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0+ /* - * Read-Copy Update module-based performance-test facility + * Read-Copy Update module-based scalability-test facility * * Copyright (C) IBM Corporation, 2015 * @@ -44,13 +44,13 @@ MODULE_LICENSE("GPL"); MODULE_AUTHOR("Paul E. McKenney "); -#define PERF_FLAG "-perf:" -#define PERFOUT_STRING(s) \ - pr_alert("%s" PERF_FLAG " %s\n", perf_type, s) -#define VERBOSE_PERFOUT_STRING(s) \ - do { if (verbose) pr_alert("%s" PERF_FLAG " %s\n", perf_type, s); } while (0) -#define VERBOSE_PERFOUT_ERRSTRING(s) \ - do { if (verbose) pr_alert("%s" PERF_FLAG "!!! %s\n", perf_type, s); } while (0) +#define SCALE_FLAG "-scale:" +#define SCALEOUT_STRING(s) \ + pr_alert("%s" SCALE_FLAG " %s\n", scale_type, s) +#define VERBOSE_SCALEOUT_STRING(s) \ + do { if (verbose) pr_alert("%s" SCALE_FLAG " %s\n", scale_type, s); } while (0) +#define VERBOSE_SCALEOUT_ERRSTRING(s) \ + do { if (verbose) pr_alert("%s" SCALE_FLAG "!!! %s\n", scale_type, s); } while (0) /* * The intended use cases for the nreaders and nwriters module parameters @@ -61,25 +61,25 @@ MODULE_AUTHOR("Paul E. McKenney "); * nr_cpus for a mixed reader/writer test. * * 2. Specify the nr_cpus kernel boot parameter, but set - * rcuperf.nreaders to zero. This will set nwriters to the + * rcuscale.nreaders to zero. This will set nwriters to the * value specified by nr_cpus for an update-only test. * * 3. Specify the nr_cpus kernel boot parameter, but set - * rcuperf.nwriters to zero. This will set nreaders to the + * rcuscale.nwriters to zero. This will set nreaders to the * value specified by nr_cpus for a read-only test. * * Various other use cases may of course be specified. * * Note that this test's readers are intended only as a test load for - * the writers. The reader performance statistics will be overly + * the writers. The reader scalability statistics will be overly * pessimistic due to the per-critical-section interrupt disabling, * test-end checks, and the pair of calls through pointers. */ #ifdef MODULE -# define RCUPERF_SHUTDOWN 0 +# define RCUSCALE_SHUTDOWN 0 #else -# define RCUPERF_SHUTDOWN 1 +# define RCUSCALE_SHUTDOWN 1 #endif torture_param(bool, gp_async, false, "Use asynchronous GP wait primitives"); @@ -88,16 +88,16 @@ torture_param(bool, gp_exp, false, "Use expedited GP wait primitives"); torture_param(int, holdoff, 10, "Holdoff time before test start (s)"); torture_param(int, nreaders, -1, "Number of RCU reader threads"); torture_param(int, nwriters, -1, "Number of RCU updater threads"); -torture_param(bool, shutdown, RCUPERF_SHUTDOWN, - "Shutdown at end of performance tests."); +torture_param(bool, shutdown, RCUSCALE_SHUTDOWN, + "Shutdown at end of scalability tests."); torture_param(int, verbose, 1, "Enable verbose debugging printk()s"); torture_param(int, writer_holdoff, 0, "Holdoff (us) between GPs, zero to disable"); -torture_param(int, kfree_rcu_test, 0, "Do we run a kfree_rcu() perf test?"); +torture_param(int, kfree_rcu_test, 0, "Do we run a kfree_rcu() scale test?"); torture_param(int, kfree_mult, 1, "Multiple of kfree_obj size to allocate."); -static char *perf_type = "rcu"; -module_param(perf_type, charp, 0444); -MODULE_PARM_DESC(perf_type, "Type of RCU to performance-test (rcu, srcu, ...)"); +static char *scale_type = "rcu"; +module_param(scale_type, charp, 0444); +MODULE_PARM_DESC(scale_type, "Type of RCU to scalability-test (rcu, srcu, ...)"); static int nrealreaders; static int nrealwriters; @@ -107,12 +107,12 @@ static struct task_struct *shutdown_task; static u64 **writer_durations; static int *writer_n_durations; -static atomic_t n_rcu_perf_reader_started; -static atomic_t n_rcu_perf_writer_started; -static atomic_t n_rcu_perf_writer_finished; +static atomic_t n_rcu_scale_reader_started; +static atomic_t n_rcu_scale_writer_started; +static atomic_t n_rcu_scale_writer_finished; static wait_queue_head_t shutdown_wq; -static u64 t_rcu_perf_writer_started; -static u64 t_rcu_perf_writer_finished; +static u64 t_rcu_scale_writer_started; +static u64 t_rcu_scale_writer_finished; static unsigned long b_rcu_gp_test_started; static unsigned long b_rcu_gp_test_finished; static DEFINE_PER_CPU(atomic_t, n_async_inflight); @@ -124,7 +124,7 @@ static DEFINE_PER_CPU(atomic_t, n_async_inflight); * Operations vector for selecting different types of tests. */ -struct rcu_perf_ops { +struct rcu_scale_ops { int ptype; void (*init)(void); void (*cleanup)(void); @@ -140,19 +140,19 @@ struct rcu_perf_ops { const char *name; }; -static struct rcu_perf_ops *cur_ops; +static struct rcu_scale_ops *cur_ops; /* - * Definitions for rcu perf testing. + * Definitions for rcu scalability testing. */ -static int rcu_perf_read_lock(void) __acquires(RCU) +static int rcu_scale_read_lock(void) __acquires(RCU) { rcu_read_lock(); return 0; } -static void rcu_perf_read_unlock(int idx) __releases(RCU) +static void rcu_scale_read_unlock(int idx) __releases(RCU) { rcu_read_unlock(); } @@ -162,15 +162,15 @@ static unsigned long __maybe_unused rcu_no_completed(void) return 0; } -static void rcu_sync_perf_init(void) +static void rcu_sync_scale_init(void) { } -static struct rcu_perf_ops rcu_ops = { +static struct rcu_scale_ops rcu_ops = { .ptype = RCU_FLAVOR, - .init = rcu_sync_perf_init, - .readlock = rcu_perf_read_lock, - .readunlock = rcu_perf_read_unlock, + .init = rcu_sync_scale_init, + .readlock = rcu_scale_read_lock, + .readunlock = rcu_scale_read_unlock, .get_gp_seq = rcu_get_gp_seq, .gp_diff = rcu_seq_diff, .exp_completed = rcu_exp_batches_completed, @@ -182,23 +182,23 @@ static struct rcu_perf_ops rcu_ops = { }; /* - * Definitions for srcu perf testing. + * Definitions for srcu scalability testing. */ -DEFINE_STATIC_SRCU(srcu_ctl_perf); -static struct srcu_struct *srcu_ctlp = &srcu_ctl_perf; +DEFINE_STATIC_SRCU(srcu_ctl_scale); +static struct srcu_struct *srcu_ctlp = &srcu_ctl_scale; -static int srcu_perf_read_lock(void) __acquires(srcu_ctlp) +static int srcu_scale_read_lock(void) __acquires(srcu_ctlp) { return srcu_read_lock(srcu_ctlp); } -static void srcu_perf_read_unlock(int idx) __releases(srcu_ctlp) +static void srcu_scale_read_unlock(int idx) __releases(srcu_ctlp) { srcu_read_unlock(srcu_ctlp, idx); } -static unsigned long srcu_perf_completed(void) +static unsigned long srcu_scale_completed(void) { return srcu_batches_completed(srcu_ctlp); } @@ -213,78 +213,78 @@ static void srcu_rcu_barrier(void) srcu_barrier(srcu_ctlp); } -static void srcu_perf_synchronize(void) +static void srcu_scale_synchronize(void) { synchronize_srcu(srcu_ctlp); } -static void srcu_perf_synchronize_expedited(void) +static void srcu_scale_synchronize_expedited(void) { synchronize_srcu_expedited(srcu_ctlp); } -static struct rcu_perf_ops srcu_ops = { +static struct rcu_scale_ops srcu_ops = { .ptype = SRCU_FLAVOR, - .init = rcu_sync_perf_init, - .readlock = srcu_perf_read_lock, - .readunlock = srcu_perf_read_unlock, - .get_gp_seq = srcu_perf_completed, + .init = rcu_sync_scale_init, + .readlock = srcu_scale_read_lock, + .readunlock = srcu_scale_read_unlock, + .get_gp_seq = srcu_scale_completed, .gp_diff = rcu_seq_diff, - .exp_completed = srcu_perf_completed, + .exp_completed = srcu_scale_completed, .async = srcu_call_rcu, .gp_barrier = srcu_rcu_barrier, - .sync = srcu_perf_synchronize, - .exp_sync = srcu_perf_synchronize_expedited, + .sync = srcu_scale_synchronize, + .exp_sync = srcu_scale_synchronize_expedited, .name = "srcu" }; static struct srcu_struct srcud; -static void srcu_sync_perf_init(void) +static void srcu_sync_scale_init(void) { srcu_ctlp = &srcud; init_srcu_struct(srcu_ctlp); } -static void srcu_sync_perf_cleanup(void) +static void srcu_sync_scale_cleanup(void) { cleanup_srcu_struct(srcu_ctlp); } -static struct rcu_perf_ops srcud_ops = { +static struct rcu_scale_ops srcud_ops = { .ptype = SRCU_FLAVOR, - .init = srcu_sync_perf_init, - .cleanup = srcu_sync_perf_cleanup, - .readlock = srcu_perf_read_lock, - .readunlock = srcu_perf_read_unlock, - .get_gp_seq = srcu_perf_completed, + .init = srcu_sync_scale_init, + .cleanup = srcu_sync_scale_cleanup, + .readlock = srcu_scale_read_lock, + .readunlock = srcu_scale_read_unlock, + .get_gp_seq = srcu_scale_completed, .gp_diff = rcu_seq_diff, - .exp_completed = srcu_perf_completed, + .exp_completed = srcu_scale_completed, .async = srcu_call_rcu, .gp_barrier = srcu_rcu_barrier, - .sync = srcu_perf_synchronize, - .exp_sync = srcu_perf_synchronize_expedited, + .sync = srcu_scale_synchronize, + .exp_sync = srcu_scale_synchronize_expedited, .name = "srcud" }; /* - * Definitions for RCU-tasks perf testing. + * Definitions for RCU-tasks scalability testing. */ -static int tasks_perf_read_lock(void) +static int tasks_scale_read_lock(void) { return 0; } -static void tasks_perf_read_unlock(int idx) +static void tasks_scale_read_unlock(int idx) { } -static struct rcu_perf_ops tasks_ops = { +static struct rcu_scale_ops tasks_ops = { .ptype = RCU_TASKS_FLAVOR, - .init = rcu_sync_perf_init, - .readlock = tasks_perf_read_lock, - .readunlock = tasks_perf_read_unlock, + .init = rcu_sync_scale_init, + .readlock = tasks_scale_read_lock, + .readunlock = tasks_scale_read_unlock, .get_gp_seq = rcu_no_completed, .gp_diff = rcu_seq_diff, .async = call_rcu_tasks, @@ -294,7 +294,7 @@ static struct rcu_perf_ops tasks_ops = { .name = "tasks" }; -static unsigned long rcuperf_seq_diff(unsigned long new, unsigned long old) +static unsigned long rcuscale_seq_diff(unsigned long new, unsigned long old) { if (!cur_ops->gp_diff) return new - old; @@ -302,60 +302,60 @@ static unsigned long rcuperf_seq_diff(unsigned long new, unsigned long old) } /* - * If performance tests complete, wait for shutdown to commence. + * If scalability tests complete, wait for shutdown to commence. */ -static void rcu_perf_wait_shutdown(void) +static void rcu_scale_wait_shutdown(void) { cond_resched_tasks_rcu_qs(); - if (atomic_read(&n_rcu_perf_writer_finished) < nrealwriters) + if (atomic_read(&n_rcu_scale_writer_finished) < nrealwriters) return; while (!torture_must_stop()) schedule_timeout_uninterruptible(1); } /* - * RCU perf reader kthread. Repeatedly does empty RCU read-side critical - * section, minimizing update-side interference. However, the point of - * this test is not to evaluate reader performance, but instead to serve - * as a test load for update-side performance testing. + * RCU scalability reader kthread. Repeatedly does empty RCU read-side + * critical section, minimizing update-side interference. However, the + * point of this test is not to evaluate reader scalability, but instead + * to serve as a test load for update-side scalability testing. */ static int -rcu_perf_reader(void *arg) +rcu_scale_reader(void *arg) { unsigned long flags; int idx; long me = (long)arg; - VERBOSE_PERFOUT_STRING("rcu_perf_reader task started"); + VERBOSE_SCALEOUT_STRING("rcu_scale_reader task started"); set_cpus_allowed_ptr(current, cpumask_of(me % nr_cpu_ids)); set_user_nice(current, MAX_NICE); - atomic_inc(&n_rcu_perf_reader_started); + atomic_inc(&n_rcu_scale_reader_started); do { local_irq_save(flags); idx = cur_ops->readlock(); cur_ops->readunlock(idx); local_irq_restore(flags); - rcu_perf_wait_shutdown(); + rcu_scale_wait_shutdown(); } while (!torture_must_stop()); - torture_kthread_stopping("rcu_perf_reader"); + torture_kthread_stopping("rcu_scale_reader"); return 0; } /* - * Callback function for asynchronous grace periods from rcu_perf_writer(). + * Callback function for asynchronous grace periods from rcu_scale_writer(). */ -static void rcu_perf_async_cb(struct rcu_head *rhp) +static void rcu_scale_async_cb(struct rcu_head *rhp) { atomic_dec(this_cpu_ptr(&n_async_inflight)); kfree(rhp); } /* - * RCU perf writer kthread. Repeatedly does a grace period. + * RCU scale writer kthread. Repeatedly does a grace period. */ static int -rcu_perf_writer(void *arg) +rcu_scale_writer(void *arg) { int i = 0; int i_max; @@ -366,7 +366,7 @@ rcu_perf_writer(void *arg) u64 *wdp; u64 *wdpp = writer_durations[me]; - VERBOSE_PERFOUT_STRING("rcu_perf_writer task started"); + VERBOSE_SCALEOUT_STRING("rcu_scale_writer task started"); WARN_ON(!wdpp); set_cpus_allowed_ptr(current, cpumask_of(me % nr_cpu_ids)); sched_set_fifo_low(current); @@ -383,8 +383,8 @@ rcu_perf_writer(void *arg) schedule_timeout_uninterruptible(1); t = ktime_get_mono_fast_ns(); - if (atomic_inc_return(&n_rcu_perf_writer_started) >= nrealwriters) { - t_rcu_perf_writer_started = t; + if (atomic_inc_return(&n_rcu_scale_writer_started) >= nrealwriters) { + t_rcu_scale_writer_started = t; if (gp_exp) { b_rcu_gp_test_started = cur_ops->exp_completed() / 2; @@ -404,7 +404,7 @@ rcu_perf_writer(void *arg) rhp = kmalloc(sizeof(*rhp), GFP_KERNEL); if (rhp && atomic_read(this_cpu_ptr(&n_async_inflight)) < gp_async_max) { atomic_inc(this_cpu_ptr(&n_async_inflight)); - cur_ops->async(rhp, rcu_perf_async_cb); + cur_ops->async(rhp, rcu_scale_async_cb); rhp = NULL; } else if (!kthread_should_stop()) { cur_ops->gp_barrier(); @@ -421,19 +421,19 @@ rcu_perf_writer(void *arg) *wdp = t - *wdp; i_max = i; if (!started && - atomic_read(&n_rcu_perf_writer_started) >= nrealwriters) + atomic_read(&n_rcu_scale_writer_started) >= nrealwriters) started = true; if (!done && i >= MIN_MEAS) { done = true; sched_set_normal(current, 0); - pr_alert("%s%s rcu_perf_writer %ld has %d measurements\n", - perf_type, PERF_FLAG, me, MIN_MEAS); - if (atomic_inc_return(&n_rcu_perf_writer_finished) >= + pr_alert("%s%s rcu_scale_writer %ld has %d measurements\n", + scale_type, SCALE_FLAG, me, MIN_MEAS); + if (atomic_inc_return(&n_rcu_scale_writer_finished) >= nrealwriters) { schedule_timeout_interruptible(10); rcu_ftrace_dump(DUMP_ALL); - PERFOUT_STRING("Test complete"); - t_rcu_perf_writer_finished = t; + SCALEOUT_STRING("Test complete"); + t_rcu_scale_writer_finished = t; if (gp_exp) { b_rcu_gp_test_finished = cur_ops->exp_completed() / 2; @@ -448,30 +448,30 @@ rcu_perf_writer(void *arg) } } if (done && !alldone && - atomic_read(&n_rcu_perf_writer_finished) >= nrealwriters) + atomic_read(&n_rcu_scale_writer_finished) >= nrealwriters) alldone = true; if (started && !alldone && i < MAX_MEAS - 1) i++; - rcu_perf_wait_shutdown(); + rcu_scale_wait_shutdown(); } while (!torture_must_stop()); if (gp_async) { cur_ops->gp_barrier(); } writer_n_durations[me] = i_max; - torture_kthread_stopping("rcu_perf_writer"); + torture_kthread_stopping("rcu_scale_writer"); return 0; } static void -rcu_perf_print_module_parms(struct rcu_perf_ops *cur_ops, const char *tag) +rcu_scale_print_module_parms(struct rcu_scale_ops *cur_ops, const char *tag) { - pr_alert("%s" PERF_FLAG + pr_alert("%s" SCALE_FLAG "--- %s: nreaders=%d nwriters=%d verbose=%d shutdown=%d\n", - perf_type, tag, nrealreaders, nrealwriters, verbose, shutdown); + scale_type, tag, nrealreaders, nrealwriters, verbose, shutdown); } static void -rcu_perf_cleanup(void) +rcu_scale_cleanup(void) { int i; int j; @@ -484,11 +484,11 @@ rcu_perf_cleanup(void) * during the mid-boot phase, so have to wait till the end. */ if (rcu_gp_is_expedited() && !rcu_gp_is_normal() && !gp_exp) - VERBOSE_PERFOUT_ERRSTRING("All grace periods expedited, no normal ones to measure!"); + VERBOSE_SCALEOUT_ERRSTRING("All grace periods expedited, no normal ones to measure!"); if (rcu_gp_is_normal() && gp_exp) - VERBOSE_PERFOUT_ERRSTRING("All grace periods normal, no expedited ones to measure!"); + VERBOSE_SCALEOUT_ERRSTRING("All grace periods normal, no expedited ones to measure!"); if (gp_exp && gp_async) - VERBOSE_PERFOUT_ERRSTRING("No expedited async GPs, so went with async!"); + VERBOSE_SCALEOUT_ERRSTRING("No expedited async GPs, so went with async!"); if (torture_cleanup_begin()) return; @@ -499,30 +499,30 @@ rcu_perf_cleanup(void) if (reader_tasks) { for (i = 0; i < nrealreaders; i++) - torture_stop_kthread(rcu_perf_reader, + torture_stop_kthread(rcu_scale_reader, reader_tasks[i]); kfree(reader_tasks); } if (writer_tasks) { for (i = 0; i < nrealwriters; i++) { - torture_stop_kthread(rcu_perf_writer, + torture_stop_kthread(rcu_scale_writer, writer_tasks[i]); if (!writer_n_durations) continue; j = writer_n_durations[i]; pr_alert("%s%s writer %d gps: %d\n", - perf_type, PERF_FLAG, i, j); + scale_type, SCALE_FLAG, i, j); ngps += j; } pr_alert("%s%s start: %llu end: %llu duration: %llu gps: %d batches: %ld\n", - perf_type, PERF_FLAG, - t_rcu_perf_writer_started, t_rcu_perf_writer_finished, - t_rcu_perf_writer_finished - - t_rcu_perf_writer_started, + scale_type, SCALE_FLAG, + t_rcu_scale_writer_started, t_rcu_scale_writer_finished, + t_rcu_scale_writer_finished - + t_rcu_scale_writer_started, ngps, - rcuperf_seq_diff(b_rcu_gp_test_finished, - b_rcu_gp_test_started)); + rcuscale_seq_diff(b_rcu_gp_test_finished, + b_rcu_gp_test_started)); for (i = 0; i < nrealwriters; i++) { if (!writer_durations) break; @@ -534,7 +534,7 @@ rcu_perf_cleanup(void) for (j = 0; j <= writer_n_durations[i]; j++) { wdp = &wdpp[j]; pr_alert("%s%s %4d writer-duration: %5d %llu\n", - perf_type, PERF_FLAG, + scale_type, SCALE_FLAG, i, j, *wdp); if (j % 100 == 0) schedule_timeout_uninterruptible(1); @@ -573,22 +573,22 @@ static int compute_real(int n) } /* - * RCU perf shutdown kthread. Just waits to be awakened, then shuts + * RCU scalability shutdown kthread. Just waits to be awakened, then shuts * down system. */ static int -rcu_perf_shutdown(void *arg) +rcu_scale_shutdown(void *arg) { wait_event(shutdown_wq, - atomic_read(&n_rcu_perf_writer_finished) >= nrealwriters); + atomic_read(&n_rcu_scale_writer_finished) >= nrealwriters); smp_mb(); /* Wake before output. */ - rcu_perf_cleanup(); + rcu_scale_cleanup(); kernel_power_off(); return -EINVAL; } /* - * kfree_rcu() performance tests: Start a kfree_rcu() loop on all CPUs for number + * kfree_rcu() scalability tests: Start a kfree_rcu() loop on all CPUs for number * of iterations and measure total time and number of GP for all iterations to complete. */ @@ -598,8 +598,8 @@ torture_param(int, kfree_loops, 10, "Number of loops doing kfree_alloc_num alloc static struct task_struct **kfree_reader_tasks; static int kfree_nrealthreads; -static atomic_t n_kfree_perf_thread_started; -static atomic_t n_kfree_perf_thread_ended; +static atomic_t n_kfree_scale_thread_started; +static atomic_t n_kfree_scale_thread_ended; struct kfree_obj { char kfree_obj[8]; @@ -607,7 +607,7 @@ struct kfree_obj { }; static int -kfree_perf_thread(void *arg) +kfree_scale_thread(void *arg) { int i, loop = 0; long me = (long)arg; @@ -615,13 +615,13 @@ kfree_perf_thread(void *arg) u64 start_time, end_time; long long mem_begin, mem_during = 0; - VERBOSE_PERFOUT_STRING("kfree_perf_thread task started"); + VERBOSE_SCALEOUT_STRING("kfree_scale_thread task started"); set_cpus_allowed_ptr(current, cpumask_of(me % nr_cpu_ids)); set_user_nice(current, MAX_NICE); start_time = ktime_get_mono_fast_ns(); - if (atomic_inc_return(&n_kfree_perf_thread_started) >= kfree_nrealthreads) { + if (atomic_inc_return(&n_kfree_scale_thread_started) >= kfree_nrealthreads) { if (gp_exp) b_rcu_gp_test_started = cur_ops->exp_completed() / 2; else @@ -646,7 +646,7 @@ kfree_perf_thread(void *arg) cond_resched(); } while (!torture_must_stop() && ++loop < kfree_loops); - if (atomic_inc_return(&n_kfree_perf_thread_ended) >= kfree_nrealthreads) { + if (atomic_inc_return(&n_kfree_scale_thread_ended) >= kfree_nrealthreads) { end_time = ktime_get_mono_fast_ns(); if (gp_exp) @@ -656,7 +656,7 @@ kfree_perf_thread(void *arg) pr_alert("Total time taken by all kfree'ers: %llu ns, loops: %d, batches: %ld, memory footprint: %lldMB\n", (unsigned long long)(end_time - start_time), kfree_loops, - rcuperf_seq_diff(b_rcu_gp_test_finished, b_rcu_gp_test_started), + rcuscale_seq_diff(b_rcu_gp_test_finished, b_rcu_gp_test_started), (mem_begin - mem_during) >> (20 - PAGE_SHIFT)); if (shutdown) { @@ -665,12 +665,12 @@ kfree_perf_thread(void *arg) } } - torture_kthread_stopping("kfree_perf_thread"); + torture_kthread_stopping("kfree_scale_thread"); return 0; } static void -kfree_perf_cleanup(void) +kfree_scale_cleanup(void) { int i; @@ -679,7 +679,7 @@ kfree_perf_cleanup(void) if (kfree_reader_tasks) { for (i = 0; i < kfree_nrealthreads; i++) - torture_stop_kthread(kfree_perf_thread, + torture_stop_kthread(kfree_scale_thread, kfree_reader_tasks[i]); kfree(kfree_reader_tasks); } @@ -691,20 +691,20 @@ kfree_perf_cleanup(void) * shutdown kthread. Just waits to be awakened, then shuts down system. */ static int -kfree_perf_shutdown(void *arg) +kfree_scale_shutdown(void *arg) { wait_event(shutdown_wq, - atomic_read(&n_kfree_perf_thread_ended) >= kfree_nrealthreads); + atomic_read(&n_kfree_scale_thread_ended) >= kfree_nrealthreads); smp_mb(); /* Wake before output. */ - kfree_perf_cleanup(); + kfree_scale_cleanup(); kernel_power_off(); return -EINVAL; } static int __init -kfree_perf_init(void) +kfree_scale_init(void) { long i; int firsterr = 0; @@ -713,7 +713,7 @@ kfree_perf_init(void) /* Start up the kthreads. */ if (shutdown) { init_waitqueue_head(&shutdown_wq); - firsterr = torture_create_kthread(kfree_perf_shutdown, NULL, + firsterr = torture_create_kthread(kfree_scale_shutdown, NULL, shutdown_task); if (firsterr) goto unwind; @@ -730,13 +730,13 @@ kfree_perf_init(void) } for (i = 0; i < kfree_nrealthreads; i++) { - firsterr = torture_create_kthread(kfree_perf_thread, (void *)i, + firsterr = torture_create_kthread(kfree_scale_thread, (void *)i, kfree_reader_tasks[i]); if (firsterr) goto unwind; } - while (atomic_read(&n_kfree_perf_thread_started) < kfree_nrealthreads) + while (atomic_read(&n_kfree_scale_thread_started) < kfree_nrealthreads) schedule_timeout_uninterruptible(1); torture_init_end(); @@ -744,35 +744,35 @@ kfree_perf_init(void) unwind: torture_init_end(); - kfree_perf_cleanup(); + kfree_scale_cleanup(); return firsterr; } static int __init -rcu_perf_init(void) +rcu_scale_init(void) { long i; int firsterr = 0; - static struct rcu_perf_ops *perf_ops[] = { + static struct rcu_scale_ops *scale_ops[] = { &rcu_ops, &srcu_ops, &srcud_ops, &tasks_ops, }; - if (!torture_init_begin(perf_type, verbose)) + if (!torture_init_begin(scale_type, verbose)) return -EBUSY; - /* Process args and tell the world that the perf'er is on the job. */ - for (i = 0; i < ARRAY_SIZE(perf_ops); i++) { - cur_ops = perf_ops[i]; - if (strcmp(perf_type, cur_ops->name) == 0) + /* Process args and announce that the scalability'er is on the job. */ + for (i = 0; i < ARRAY_SIZE(scale_ops); i++) { + cur_ops = scale_ops[i]; + if (strcmp(scale_type, cur_ops->name) == 0) break; } - if (i == ARRAY_SIZE(perf_ops)) { - pr_alert("rcu-perf: invalid perf type: \"%s\"\n", perf_type); - pr_alert("rcu-perf types:"); - for (i = 0; i < ARRAY_SIZE(perf_ops); i++) - pr_cont(" %s", perf_ops[i]->name); + if (i == ARRAY_SIZE(scale_ops)) { + pr_alert("rcu-scale: invalid scale type: \"%s\"\n", scale_type); + pr_alert("rcu-scale types:"); + for (i = 0; i < ARRAY_SIZE(scale_ops); i++) + pr_cont(" %s", scale_ops[i]->name); pr_cont("\n"); - WARN_ON(!IS_MODULE(CONFIG_RCU_PERF_TEST)); + WARN_ON(!IS_MODULE(CONFIG_RCU_SCALE_TEST)); firsterr = -EINVAL; cur_ops = NULL; goto unwind; @@ -781,20 +781,20 @@ rcu_perf_init(void) cur_ops->init(); if (kfree_rcu_test) - return kfree_perf_init(); + return kfree_scale_init(); nrealwriters = compute_real(nwriters); nrealreaders = compute_real(nreaders); - atomic_set(&n_rcu_perf_reader_started, 0); - atomic_set(&n_rcu_perf_writer_started, 0); - atomic_set(&n_rcu_perf_writer_finished, 0); - rcu_perf_print_module_parms(cur_ops, "Start of test"); + atomic_set(&n_rcu_scale_reader_started, 0); + atomic_set(&n_rcu_scale_writer_started, 0); + atomic_set(&n_rcu_scale_writer_finished, 0); + rcu_scale_print_module_parms(cur_ops, "Start of test"); /* Start up the kthreads. */ if (shutdown) { init_waitqueue_head(&shutdown_wq); - firsterr = torture_create_kthread(rcu_perf_shutdown, NULL, + firsterr = torture_create_kthread(rcu_scale_shutdown, NULL, shutdown_task); if (firsterr) goto unwind; @@ -803,17 +803,17 @@ rcu_perf_init(void) reader_tasks = kcalloc(nrealreaders, sizeof(reader_tasks[0]), GFP_KERNEL); if (reader_tasks == NULL) { - VERBOSE_PERFOUT_ERRSTRING("out of memory"); + VERBOSE_SCALEOUT_ERRSTRING("out of memory"); firsterr = -ENOMEM; goto unwind; } for (i = 0; i < nrealreaders; i++) { - firsterr = torture_create_kthread(rcu_perf_reader, (void *)i, + firsterr = torture_create_kthread(rcu_scale_reader, (void *)i, reader_tasks[i]); if (firsterr) goto unwind; } - while (atomic_read(&n_rcu_perf_reader_started) < nrealreaders) + while (atomic_read(&n_rcu_scale_reader_started) < nrealreaders) schedule_timeout_uninterruptible(1); writer_tasks = kcalloc(nrealwriters, sizeof(reader_tasks[0]), GFP_KERNEL); @@ -823,7 +823,7 @@ rcu_perf_init(void) kcalloc(nrealwriters, sizeof(*writer_n_durations), GFP_KERNEL); if (!writer_tasks || !writer_durations || !writer_n_durations) { - VERBOSE_PERFOUT_ERRSTRING("out of memory"); + VERBOSE_SCALEOUT_ERRSTRING("out of memory"); firsterr = -ENOMEM; goto unwind; } @@ -835,7 +835,7 @@ rcu_perf_init(void) firsterr = -ENOMEM; goto unwind; } - firsterr = torture_create_kthread(rcu_perf_writer, (void *)i, + firsterr = torture_create_kthread(rcu_scale_writer, (void *)i, writer_tasks[i]); if (firsterr) goto unwind; @@ -845,9 +845,9 @@ rcu_perf_init(void) unwind: torture_init_end(); - rcu_perf_cleanup(); + rcu_scale_cleanup(); return firsterr; } -module_init(rcu_perf_init); -module_exit(rcu_perf_cleanup); +module_init(rcu_scale_init); +module_exit(rcu_scale_cleanup); diff --git a/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcuperf-ftrace.sh b/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcuscale-ftrace.sh similarity index 92% rename from tools/testing/selftests/rcutorture/bin/kvm-recheck-rcuperf-ftrace.sh rename to tools/testing/selftests/rcutorture/bin/kvm-recheck-rcuscale-ftrace.sh index 7d3c2be66c64..d4bec538086d 100755 --- a/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcuperf-ftrace.sh +++ b/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcuscale-ftrace.sh @@ -1,12 +1,12 @@ #!/bin/bash # SPDX-License-Identifier: GPL-2.0+ # -# Analyze a given results directory for rcuperf performance measurements, +# Analyze a given results directory for rcuscale performance measurements, # looking for ftrace data. Exits with 0 if data was found, analyzed, and -# printed. Intended to be invoked from kvm-recheck-rcuperf.sh after +# printed. Intended to be invoked from kvm-recheck-rcuscale.sh after # argument checking. # -# Usage: kvm-recheck-rcuperf-ftrace.sh resdir +# Usage: kvm-recheck-rcuscale-ftrace.sh resdir # # Copyright (C) IBM Corporation, 2016 # diff --git a/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcuperf.sh b/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcuscale.sh similarity index 84% rename from tools/testing/selftests/rcutorture/bin/kvm-recheck-rcuperf.sh rename to tools/testing/selftests/rcutorture/bin/kvm-recheck-rcuscale.sh index db0375a57f28..aa745152a525 100755 --- a/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcuperf.sh +++ b/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcuscale.sh @@ -1,9 +1,9 @@ #!/bin/bash # SPDX-License-Identifier: GPL-2.0+ # -# Analyze a given results directory for rcuperf performance measurements. +# Analyze a given results directory for rcuscale scalability measurements. # -# Usage: kvm-recheck-rcuperf.sh resdir +# Usage: kvm-recheck-rcuscale.sh resdir # # Copyright (C) IBM Corporation, 2016 # @@ -20,7 +20,7 @@ fi PATH=`pwd`/tools/testing/selftests/rcutorture/bin:$PATH; export PATH . functions.sh -if kvm-recheck-rcuperf-ftrace.sh $i +if kvm-recheck-rcuscale-ftrace.sh $i then # ftrace data was successfully analyzed, call it good! exit 0 @@ -30,12 +30,12 @@ configfile=`echo $i | sed -e 's/^.*\///'` sed -e 's/^\[[^]]*]//' < $i/console.log | awk ' -/-perf: .* gps: .* batches:/ { +/-scale: .* gps: .* batches:/ { ngps = $9; nbatches = $11; } -/-perf: .*writer-duration/ { +/-scale: .*writer-duration/ { gptimes[++n] = $5 / 1000.; sum += $5 / 1000.; } @@ -43,7 +43,7 @@ awk ' END { newNR = asort(gptimes); if (newNR <= 0) { - print "No rcuperf records found???" + print "No rcuscale records found???" exit; } pct50 = int(newNR * 50 / 100); @@ -79,5 +79,5 @@ END { print "99th percentile grace-period duration: " gptimes[pct99]; print "Maximum grace-period duration: " gptimes[newNR]; print "Grace periods: " ngps + 0 " Batches: " nbatches + 0 " Ratio: " ngps / nbatches; - print "Computed from rcuperf printk output."; + print "Computed from rcuscale printk output."; }' diff --git a/tools/testing/selftests/rcutorture/bin/kvm.sh b/tools/testing/selftests/rcutorture/bin/kvm.sh index 44dfdd9be67e..0489c198a72a 100755 --- a/tools/testing/selftests/rcutorture/bin/kvm.sh +++ b/tools/testing/selftests/rcutorture/bin/kvm.sh @@ -65,7 +65,7 @@ usage () { echo " --qemu-args qemu-arguments" echo " --qemu-cmd qemu-system-..." echo " --results absolute-pathname" - echo " --torture rcu" + echo " --torture lock|rcu|rcuscale|refscale|scf" echo " --trust-make" exit 1 } @@ -184,13 +184,13 @@ do shift ;; --torture) - checkarg --torture "(suite name)" "$#" "$2" '^\(lock\|rcu\|rcuperf\|refscale\|scf\)$' '^--' + checkarg --torture "(suite name)" "$#" "$2" '^\(lock\|rcu\|rcuscale\|refscale\|scf\)$' '^--' TORTURE_SUITE=$2 shift - if test "$TORTURE_SUITE" = rcuperf || test "$TORTURE_SUITE" = refscale + if test "$TORTURE_SUITE" = rcuscale || test "$TORTURE_SUITE" = refscale then # If you really want jitter for refscale or - # rcuperf, specify it after specifying the rcuperf + # rcuscale, specify it after specifying the rcuscale # or the refscale. (But why jitter in these cases?) jitter=0 fi diff --git a/tools/testing/selftests/rcutorture/bin/parse-console.sh b/tools/testing/selftests/rcutorture/bin/parse-console.sh index 4e081a25761e..e03338091a06 100755 --- a/tools/testing/selftests/rcutorture/bin/parse-console.sh +++ b/tools/testing/selftests/rcutorture/bin/parse-console.sh @@ -33,8 +33,8 @@ then fi cat /dev/null > $file.diags -# Check for proper termination, except for rcuperf and refscale. -if test "$TORTURE_SUITE" != rcuperf && test "$TORTURE_SUITE" != refscale +# Check for proper termination, except for rcuscale and refscale. +if test "$TORTURE_SUITE" != rcuscale && test "$TORTURE_SUITE" != refscale then # check for abject failure diff --git a/tools/testing/selftests/rcutorture/configs/rcuperf/CFcommon b/tools/testing/selftests/rcutorture/configs/rcuperf/CFcommon deleted file mode 100644 index a09816b8c0f3..000000000000 --- a/tools/testing/selftests/rcutorture/configs/rcuperf/CFcommon +++ /dev/null @@ -1,2 +0,0 @@ -CONFIG_RCU_PERF_TEST=y -CONFIG_PRINTK_TIME=y diff --git a/tools/testing/selftests/rcutorture/configs/rcuperf/CFLIST b/tools/testing/selftests/rcutorture/configs/rcuscale/CFLIST similarity index 100% rename from tools/testing/selftests/rcutorture/configs/rcuperf/CFLIST rename to tools/testing/selftests/rcutorture/configs/rcuscale/CFLIST diff --git a/tools/testing/selftests/rcutorture/configs/rcuscale/CFcommon b/tools/testing/selftests/rcutorture/configs/rcuscale/CFcommon new file mode 100644 index 000000000000..87caa0e932c7 --- /dev/null +++ b/tools/testing/selftests/rcutorture/configs/rcuscale/CFcommon @@ -0,0 +1,2 @@ +CONFIG_RCU_SCALE_TEST=y +CONFIG_PRINTK_TIME=y diff --git a/tools/testing/selftests/rcutorture/configs/rcuperf/TINY b/tools/testing/selftests/rcutorture/configs/rcuscale/TINY similarity index 100% rename from tools/testing/selftests/rcutorture/configs/rcuperf/TINY rename to tools/testing/selftests/rcutorture/configs/rcuscale/TINY diff --git a/tools/testing/selftests/rcutorture/configs/rcuperf/TREE b/tools/testing/selftests/rcutorture/configs/rcuscale/TREE similarity index 100% rename from tools/testing/selftests/rcutorture/configs/rcuperf/TREE rename to tools/testing/selftests/rcutorture/configs/rcuscale/TREE diff --git a/tools/testing/selftests/rcutorture/configs/rcuperf/TREE54 b/tools/testing/selftests/rcutorture/configs/rcuscale/TREE54 similarity index 100% rename from tools/testing/selftests/rcutorture/configs/rcuperf/TREE54 rename to tools/testing/selftests/rcutorture/configs/rcuscale/TREE54 diff --git a/tools/testing/selftests/rcutorture/configs/rcuperf/ver_functions.sh b/tools/testing/selftests/rcutorture/configs/rcuscale/ver_functions.sh similarity index 88% rename from tools/testing/selftests/rcutorture/configs/rcuperf/ver_functions.sh rename to tools/testing/selftests/rcutorture/configs/rcuscale/ver_functions.sh index 777d5b0c190f..0333e9b18522 100644 --- a/tools/testing/selftests/rcutorture/configs/rcuperf/ver_functions.sh +++ b/tools/testing/selftests/rcutorture/configs/rcuscale/ver_functions.sh @@ -11,6 +11,6 @@ # # Adds per-version torture-module parameters to kernels supporting them. per_version_boot_params () { - echo $1 rcuperf.shutdown=1 \ - rcuperf.verbose=1 + echo $1 rcuscale.shutdown=1 \ + rcuscale.verbose=1 }