Revision 7318413077a5141a50a753b1fab687b7907eef16 authored by Linus Torvalds on 16 September 2017, 03:43:33 UTC, committed by Linus Torvalds on 16 September 2017, 03:43:33 UTC
Pull MIPS updates from Ralf Baechle: "This is the main pull request for 4.14 for MIPS; below a summary of the non-merge commits: CM: - Rename mips_cm_base to mips_gcr_base - Specify register size when generating accessors - Use BIT/GENMASK for register fields, order & drop shifts - Add cluster & block args to mips_cm_lock_other() CPC: - Use common CPS accessor generation macros - Use BIT/GENMASK for register fields, order & drop shifts - Introduce register modify (set/clear/change) accessors - Use change_*, set_* & clear_* where appropriate - Add CM/CPC 3.5 register definitions - Use GlobalNumber macros rather than magic numbers - Have asm/mips-cps.h include CM & CPC headers - Cluster support for topology functions - Detect CPUs in secondary clusters CPS: - Read GIC_VL_IDENT directly, not via irqchip driver DMA: - Consolidate coherent and non-coherent dma_alloc code - Don't use dma_cache_sync to implement fd_cacheflush FPU emulation / FP assist code: - Another series of 14 commits fixing corner cases such as NaN propgagation and other special input values. - Zero bits 32-63 of the result for a CLASS.D instruction. - Enhanced statics via debugfs - Do not use bools for arithmetic. GCC 7.1 moans about this. - Correct user fault_addr type Generic MIPS: - Enhancement of stack backtraces - Cleanup from non-existing options - Handle non word sized instructions when examining frame - Fix detection and decoding of ADDIUSP instruction - Fix decoding of SWSP16 instruction - Refactor handling of stack pointer in get_frame_info - Remove unreachable code from force_fcr31_sig() - Convert to using %pOF instead of full_name - Remove the R6000 support. - Move FP code from *_switch.S to *_fpu.S - Remove unused ST_OFF from r2300_switch.S - Allow platform to specify multiple its.S files - Add #includes to various files to ensure code builds reliable and without warning.. - Remove __invalidate_kernel_vmap_range - Remove plat_timer_setup - Declare various variables & functions static - Abstract CPU core & VP(E) ID access through accessor functions - Store core & VP IDs in GlobalNumber-style variable - Unify checks for sibling CPUs - Add CPU cluster number accessors - Prevent direct use of generic_defconfig - Make CONFIG_MIPS_MT_SMP default y - Add __ioread64_copy - Remove unnecessary inclusions of linux/irqchip/mips-gic.h GIC: - Introduce asm/mips-gic.h with accessor functions - Use new GIC accessor functions in mips-gic-timer - Remove counter access functions from irq-mips-gic.c - Remove gic_read_local_vp_id() from irq-mips-gic.c - Simplify shared interrupt pending/mask reads in irq-mips-gic.c - Simplify gic_local_irq_domain_map() in irq-mips-gic.c - Drop gic_(re)set_mask() functions in irq-mips-gic.c - Remove gic_set_polarity(), gic_set_trigger(), gic_set_dual_edge(), gic_map_to_pin() and gic_map_to_vpe() from irq-mips-gic.c. - Convert remaining shared reg access, local int mask access and remaining local reg access to new accessors - Move GIC_LOCAL_INT_* to asm/mips-gic.h - Remove GIC_CPU_INT* macros from irq-mips-gic.c - Move various definitions to the driver - Remove gic_get_usm_range() - Remove __gic_irq_dispatch() forward declaration - Remove gic_init() - Use mips_gic_present() in place of gic_present and remove gic_present - Move gic_get_c0_*_int() to asm/mips-gic.h - Remove linux/irqchip/mips-gic.h - Inline __gic_init() - Inline gic_basic_init() - Make pcpu_masks a per-cpu variable - Use pcpu_masks to avoid reading GIC_SH_MASK* - Clean up mti, reserved-cpu-vectors handling - Use cpumask_first_and() in gic_set_affinity() - Let the core set struct irq_common_data affinity microMIPS: - Fix microMIPS stack unwinding on big endian systems MIPS-GIC: - SYNC after enabling GIC region NUMA: - Remove the unused parent_node() macro R6: - Constify r2_decoder_tables - Add accessor & bit definitions for GlobalNumber SMP: - Constify smp ops - Allow boot_secondary SMP op to return errors VDSO: - Drop gic_get_usm_range() usage - Avoid use of linux/irqchip/mips-gic.h Platform changes: Alchemy: - Add devboard machine type to cpuinfo - update cpu feature overrides - Threaded carddetect irqs for devboards AR7: - allow NULL clock for clk_get_rate BCM63xx: - Fix ENETDMA_6345_MAXBURST_REG offset - Allow NULL clock for clk_get_rate CI20: - Enable GPIO and RTC drivers in defconfig - Add ethernet and fixed-regulator nodes to DTS Generic platform: - Move Boston and NI 169445 FIT image source to their own files - Include asm/bootinfo.h for plat_fdt_relocated() - Include asm/time.h for get_c0_*_int() - Include asm/bootinfo.h for plat_fdt_relocated() - Include asm/time.h for get_c0_*_int() - Allow filtering enabled boards by requirements - Don't explicitly disable CONFIG_USB_SUPPORT - Bump default NR_CPUS to 16 JZ4700: - Probe the jz4740-rtc driver from devicetree Lantiq: - Drop check of boot select from the spi-falcon driver. - Drop check of boot select from the lantiq-flash MTD driver. - Access boot cause register in the watchdog driver through regmap - Add device tree binding documentation for the watchdog driver - Add docs for the RCU DT bindings. - Convert the fpi bus driver to a platform_driver - Remove ltq_reset_cause() and ltq_boot_select( - Switch to a proper reset driver - Switch to a new drivers/soc GPHY driver - Add an USB PHY driver for the Lantiq SoCs using the RCU module - Use of_platform_default_populate instead of __dt_register_buses - Enable MFD_SYSCON to be able to use it for the RCU MFD - Replace ltq_boot_select() with dummy implementation. Loongson 2F: - Allow NULL clock for clk_get_rate Malta: - Use new GIC accessor functions NI 169445: - Add support for NI 169445 board. - Only include in 32r2el kernels Octeon: - Add support for watchdog of 78XX SOCs. - Add support for watchdog of CN68XX SOCs. - Expose support for mips32r1, mips32r2 and mips64r1 - Enable more drivers in config file - Add support for accessing the boot vector. - Remove old boot vector code from watchdog driver - Define watchdog registers for 70xx, 73xx, 78xx, F75xx. - Make CSR functions node aware. - Allow access to CIU3 IRQ domains. - Misc cleanups in the watchdog driver Omega2+: - New board, add support and defconfig Pistachio: - Enable Root FS on NFS in defconfig Ralink: - Add Mediatek MT7628A SoC - Allow NULL clock for clk_get_rate - Explicitly request exclusive reset control in the pci-mt7620 PCI driver. SEAD3: - Only include in 32 bit kernels by default VoCore: - Add VoCore as a vendor t0 dt-bindings - Add defconfig file" * '4.14-features' of git://git.linux-mips.org/pub/scm/ralf/upstream-linus: (167 commits) MIPS: Refactor handling of stack pointer in get_frame_info MIPS: Stacktrace: Fix microMIPS stack unwinding on big endian systems MIPS: microMIPS: Fix decoding of swsp16 instruction MIPS: microMIPS: Fix decoding of addiusp instruction MIPS: microMIPS: Fix detection of addiusp instruction MIPS: Handle non word sized instructions when examining frame MIPS: ralink: allow NULL clock for clk_get_rate MIPS: Loongson 2F: allow NULL clock for clk_get_rate MIPS: BCM63XX: allow NULL clock for clk_get_rate MIPS: AR7: allow NULL clock for clk_get_rate MIPS: BCM63XX: fix ENETDMA_6345_MAXBURST_REG offset mips: Save all registers when saving the frame MIPS: Add DWARF unwinding to assembly MIPS: Make SAVE_SOME more standard MIPS: Fix issues in backtraces MIPS: jz4780: DTS: Probe the jz4740-rtc driver from devicetree MIPS: Ci20: Enable RTC driver watchdog: octeon-wdt: Add support for 78XX SOCs. watchdog: octeon-wdt: Add support for cn68XX SOCs. watchdog: octeon-wdt: File cleaning. ...
rcuperf.c
/*
* Read-Copy Update module-based performance-test facility
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, you can access it online at
* http://www.gnu.org/licenses/gpl-2.0.html.
*
* Copyright (C) IBM Corporation, 2015
*
* Authors: Paul E. McKenney <paulmck@us.ibm.com>
*/
#include <linux/types.h>
#include <linux/kernel.h>
#include <linux/init.h>
#include <linux/module.h>
#include <linux/kthread.h>
#include <linux/err.h>
#include <linux/spinlock.h>
#include <linux/smp.h>
#include <linux/rcupdate.h>
#include <linux/interrupt.h>
#include <linux/sched.h>
#include <uapi/linux/sched/types.h>
#include <linux/atomic.h>
#include <linux/bitops.h>
#include <linux/completion.h>
#include <linux/moduleparam.h>
#include <linux/percpu.h>
#include <linux/notifier.h>
#include <linux/reboot.h>
#include <linux/freezer.h>
#include <linux/cpu.h>
#include <linux/delay.h>
#include <linux/stat.h>
#include <linux/srcu.h>
#include <linux/slab.h>
#include <asm/byteorder.h>
#include <linux/torture.h>
#include <linux/vmalloc.h>
#include "rcu.h"
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Paul E. McKenney <paulmck@linux.vnet.ibm.com>");
#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)
torture_param(bool, gp_async, false, "Use asynchronous GP wait primitives");
torture_param(int, gp_async_max, 1000, "Max # outstanding waits per reader");
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, 0, "Number of RCU reader threads");
torture_param(int, nwriters, -1, "Number of RCU updater threads");
torture_param(bool, shutdown, !IS_ENABLED(MODULE),
"Shutdown at end of performance tests.");
torture_param(bool, verbose, true, "Enable verbose debugging printk()s");
torture_param(int, writer_holdoff, 0, "Holdoff (us) between GPs, zero to disable");
static char *perf_type = "rcu";
module_param(perf_type, charp, 0444);
MODULE_PARM_DESC(perf_type, "Type of RCU to performance-test (rcu, rcu_bh, ...)");
static int nrealreaders;
static int nrealwriters;
static struct task_struct **writer_tasks;
static struct task_struct **reader_tasks;
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 wait_queue_head_t shutdown_wq;
static u64 t_rcu_perf_writer_started;
static u64 t_rcu_perf_writer_finished;
static unsigned long b_rcu_perf_writer_started;
static unsigned long b_rcu_perf_writer_finished;
static DEFINE_PER_CPU(atomic_t, n_async_inflight);
static int rcu_perf_writer_state;
#define RTWS_INIT 0
#define RTWS_ASYNC 1
#define RTWS_BARRIER 2
#define RTWS_EXP_SYNC 3
#define RTWS_SYNC 4
#define RTWS_IDLE 5
#define RTWS_STOPPING 6
#define MAX_MEAS 10000
#define MIN_MEAS 100
static int perf_runnable = IS_ENABLED(MODULE);
module_param(perf_runnable, int, 0444);
MODULE_PARM_DESC(perf_runnable, "Start rcuperf at boot");
/*
* Operations vector for selecting different types of tests.
*/
struct rcu_perf_ops {
int ptype;
void (*init)(void);
void (*cleanup)(void);
int (*readlock)(void);
void (*readunlock)(int idx);
unsigned long (*started)(void);
unsigned long (*completed)(void);
unsigned long (*exp_completed)(void);
void (*async)(struct rcu_head *head, rcu_callback_t func);
void (*gp_barrier)(void);
void (*sync)(void);
void (*exp_sync)(void);
const char *name;
};
static struct rcu_perf_ops *cur_ops;
/*
* Definitions for rcu perf testing.
*/
static int rcu_perf_read_lock(void) __acquires(RCU)
{
rcu_read_lock();
return 0;
}
static void rcu_perf_read_unlock(int idx) __releases(RCU)
{
rcu_read_unlock();
}
static unsigned long __maybe_unused rcu_no_completed(void)
{
return 0;
}
static void rcu_sync_perf_init(void)
{
}
static struct rcu_perf_ops rcu_ops = {
.ptype = RCU_FLAVOR,
.init = rcu_sync_perf_init,
.readlock = rcu_perf_read_lock,
.readunlock = rcu_perf_read_unlock,
.started = rcu_batches_started,
.completed = rcu_batches_completed,
.exp_completed = rcu_exp_batches_completed,
.async = call_rcu,
.gp_barrier = rcu_barrier,
.sync = synchronize_rcu,
.exp_sync = synchronize_rcu_expedited,
.name = "rcu"
};
/*
* Definitions for rcu_bh perf testing.
*/
static int rcu_bh_perf_read_lock(void) __acquires(RCU_BH)
{
rcu_read_lock_bh();
return 0;
}
static void rcu_bh_perf_read_unlock(int idx) __releases(RCU_BH)
{
rcu_read_unlock_bh();
}
static struct rcu_perf_ops rcu_bh_ops = {
.ptype = RCU_BH_FLAVOR,
.init = rcu_sync_perf_init,
.readlock = rcu_bh_perf_read_lock,
.readunlock = rcu_bh_perf_read_unlock,
.started = rcu_batches_started_bh,
.completed = rcu_batches_completed_bh,
.exp_completed = rcu_exp_batches_completed_sched,
.async = call_rcu_bh,
.gp_barrier = rcu_barrier_bh,
.sync = synchronize_rcu_bh,
.exp_sync = synchronize_rcu_bh_expedited,
.name = "rcu_bh"
};
/*
* Definitions for srcu perf testing.
*/
DEFINE_STATIC_SRCU(srcu_ctl_perf);
static struct srcu_struct *srcu_ctlp = &srcu_ctl_perf;
static int srcu_perf_read_lock(void) __acquires(srcu_ctlp)
{
return srcu_read_lock(srcu_ctlp);
}
static void srcu_perf_read_unlock(int idx) __releases(srcu_ctlp)
{
srcu_read_unlock(srcu_ctlp, idx);
}
static unsigned long srcu_perf_completed(void)
{
return srcu_batches_completed(srcu_ctlp);
}
static void srcu_call_rcu(struct rcu_head *head, rcu_callback_t func)
{
call_srcu(srcu_ctlp, head, func);
}
static void srcu_rcu_barrier(void)
{
srcu_barrier(srcu_ctlp);
}
static void srcu_perf_synchronize(void)
{
synchronize_srcu(srcu_ctlp);
}
static void srcu_perf_synchronize_expedited(void)
{
synchronize_srcu_expedited(srcu_ctlp);
}
static struct rcu_perf_ops srcu_ops = {
.ptype = SRCU_FLAVOR,
.init = rcu_sync_perf_init,
.readlock = srcu_perf_read_lock,
.readunlock = srcu_perf_read_unlock,
.started = NULL,
.completed = srcu_perf_completed,
.exp_completed = srcu_perf_completed,
.async = srcu_call_rcu,
.gp_barrier = srcu_rcu_barrier,
.sync = srcu_perf_synchronize,
.exp_sync = srcu_perf_synchronize_expedited,
.name = "srcu"
};
static struct srcu_struct srcud;
static void srcu_sync_perf_init(void)
{
srcu_ctlp = &srcud;
init_srcu_struct(srcu_ctlp);
}
static void srcu_sync_perf_cleanup(void)
{
cleanup_srcu_struct(srcu_ctlp);
}
static struct rcu_perf_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,
.started = NULL,
.completed = srcu_perf_completed,
.exp_completed = srcu_perf_completed,
.async = srcu_call_rcu,
.gp_barrier = srcu_rcu_barrier,
.sync = srcu_perf_synchronize,
.exp_sync = srcu_perf_synchronize_expedited,
.name = "srcud"
};
/*
* Definitions for sched perf testing.
*/
static int sched_perf_read_lock(void)
{
preempt_disable();
return 0;
}
static void sched_perf_read_unlock(int idx)
{
preempt_enable();
}
static struct rcu_perf_ops sched_ops = {
.ptype = RCU_SCHED_FLAVOR,
.init = rcu_sync_perf_init,
.readlock = sched_perf_read_lock,
.readunlock = sched_perf_read_unlock,
.started = rcu_batches_started_sched,
.completed = rcu_batches_completed_sched,
.exp_completed = rcu_exp_batches_completed_sched,
.async = call_rcu_sched,
.gp_barrier = rcu_barrier_sched,
.sync = synchronize_sched,
.exp_sync = synchronize_sched_expedited,
.name = "sched"
};
/*
* Definitions for RCU-tasks perf testing.
*/
static int tasks_perf_read_lock(void)
{
return 0;
}
static void tasks_perf_read_unlock(int idx)
{
}
static struct rcu_perf_ops tasks_ops = {
.ptype = RCU_TASKS_FLAVOR,
.init = rcu_sync_perf_init,
.readlock = tasks_perf_read_lock,
.readunlock = tasks_perf_read_unlock,
.started = rcu_no_completed,
.completed = rcu_no_completed,
.async = call_rcu_tasks,
.gp_barrier = rcu_barrier_tasks,
.sync = synchronize_rcu_tasks,
.exp_sync = synchronize_rcu_tasks,
.name = "tasks"
};
static bool __maybe_unused torturing_tasks(void)
{
return cur_ops == &tasks_ops;
}
/*
* If performance tests complete, wait for shutdown to commence.
*/
static void rcu_perf_wait_shutdown(void)
{
cond_resched_rcu_qs();
if (atomic_read(&n_rcu_perf_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.
*/
static int
rcu_perf_reader(void *arg)
{
unsigned long flags;
int idx;
long me = (long)arg;
VERBOSE_PERFOUT_STRING("rcu_perf_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);
do {
local_irq_save(flags);
idx = cur_ops->readlock();
cur_ops->readunlock(idx);
local_irq_restore(flags);
rcu_perf_wait_shutdown();
} while (!torture_must_stop());
torture_kthread_stopping("rcu_perf_reader");
return 0;
}
/*
* Callback function for asynchronous grace periods from rcu_perf_writer().
*/
static void rcu_perf_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.
*/
static int
rcu_perf_writer(void *arg)
{
int i = 0;
int i_max;
long me = (long)arg;
struct rcu_head *rhp = NULL;
struct sched_param sp;
bool started = false, done = false, alldone = false;
u64 t;
u64 *wdp;
u64 *wdpp = writer_durations[me];
VERBOSE_PERFOUT_STRING("rcu_perf_writer task started");
WARN_ON(!wdpp);
set_cpus_allowed_ptr(current, cpumask_of(me % nr_cpu_ids));
sp.sched_priority = 1;
sched_setscheduler_nocheck(current, SCHED_FIFO, &sp);
if (holdoff)
schedule_timeout_uninterruptible(holdoff * HZ);
t = ktime_get_mono_fast_ns();
if (atomic_inc_return(&n_rcu_perf_writer_started) >= nrealwriters) {
t_rcu_perf_writer_started = t;
if (gp_exp) {
b_rcu_perf_writer_started =
cur_ops->exp_completed() / 2;
} else {
b_rcu_perf_writer_started =
cur_ops->completed();
}
}
do {
if (writer_holdoff)
udelay(writer_holdoff);
wdp = &wdpp[i];
*wdp = ktime_get_mono_fast_ns();
if (gp_async) {
retry:
if (!rhp)
rhp = kmalloc(sizeof(*rhp), GFP_KERNEL);
if (rhp && atomic_read(this_cpu_ptr(&n_async_inflight)) < gp_async_max) {
rcu_perf_writer_state = RTWS_ASYNC;
atomic_inc(this_cpu_ptr(&n_async_inflight));
cur_ops->async(rhp, rcu_perf_async_cb);
rhp = NULL;
} else if (!kthread_should_stop()) {
rcu_perf_writer_state = RTWS_BARRIER;
cur_ops->gp_barrier();
goto retry;
} else {
kfree(rhp); /* Because we are stopping. */
}
} else if (gp_exp) {
rcu_perf_writer_state = RTWS_EXP_SYNC;
cur_ops->exp_sync();
} else {
rcu_perf_writer_state = RTWS_SYNC;
cur_ops->sync();
}
rcu_perf_writer_state = RTWS_IDLE;
t = ktime_get_mono_fast_ns();
*wdp = t - *wdp;
i_max = i;
if (!started &&
atomic_read(&n_rcu_perf_writer_started) >= nrealwriters)
started = true;
if (!done && i >= MIN_MEAS) {
done = true;
sp.sched_priority = 0;
sched_setscheduler_nocheck(current,
SCHED_NORMAL, &sp);
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) >=
nrealwriters) {
schedule_timeout_interruptible(10);
rcu_ftrace_dump(DUMP_ALL);
PERFOUT_STRING("Test complete");
t_rcu_perf_writer_finished = t;
if (gp_exp) {
b_rcu_perf_writer_finished =
cur_ops->exp_completed() / 2;
} else {
b_rcu_perf_writer_finished =
cur_ops->completed();
}
if (shutdown) {
smp_mb(); /* Assign before wake. */
wake_up(&shutdown_wq);
}
}
}
if (done && !alldone &&
atomic_read(&n_rcu_perf_writer_finished) >= nrealwriters)
alldone = true;
if (started && !alldone && i < MAX_MEAS - 1)
i++;
rcu_perf_wait_shutdown();
} while (!torture_must_stop());
if (gp_async) {
rcu_perf_writer_state = RTWS_BARRIER;
cur_ops->gp_barrier();
}
rcu_perf_writer_state = RTWS_STOPPING;
writer_n_durations[me] = i_max;
torture_kthread_stopping("rcu_perf_writer");
return 0;
}
static inline void
rcu_perf_print_module_parms(struct rcu_perf_ops *cur_ops, const char *tag)
{
pr_alert("%s" PERF_FLAG
"--- %s: nreaders=%d nwriters=%d verbose=%d shutdown=%d\n",
perf_type, tag, nrealreaders, nrealwriters, verbose, shutdown);
}
static void
rcu_perf_cleanup(void)
{
int i;
int j;
int ngps = 0;
u64 *wdp;
u64 *wdpp;
/*
* Would like warning at start, but everything is expedited
* 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!");
if (rcu_gp_is_normal() && gp_exp)
VERBOSE_PERFOUT_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!");
if (torture_cleanup_begin())
return;
if (reader_tasks) {
for (i = 0; i < nrealreaders; i++)
torture_stop_kthread(rcu_perf_reader,
reader_tasks[i]);
kfree(reader_tasks);
}
if (writer_tasks) {
for (i = 0; i < nrealwriters; i++) {
torture_stop_kthread(rcu_perf_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);
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,
ngps,
b_rcu_perf_writer_finished -
b_rcu_perf_writer_started);
for (i = 0; i < nrealwriters; i++) {
if (!writer_durations)
break;
if (!writer_n_durations)
continue;
wdpp = writer_durations[i];
if (!wdpp)
continue;
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,
i, j, *wdp);
if (j % 100 == 0)
schedule_timeout_uninterruptible(1);
}
kfree(writer_durations[i]);
}
kfree(writer_tasks);
kfree(writer_durations);
kfree(writer_n_durations);
}
/* Do flavor-specific cleanup operations. */
if (cur_ops->cleanup != NULL)
cur_ops->cleanup();
torture_cleanup_end();
}
/*
* Return the number if non-negative. If -1, the number of CPUs.
* If less than -1, that much less than the number of CPUs, but
* at least one.
*/
static int compute_real(int n)
{
int nr;
if (n >= 0) {
nr = n;
} else {
nr = num_online_cpus() + 1 + n;
if (nr <= 0)
nr = 1;
}
return nr;
}
/*
* RCU perf shutdown kthread. Just waits to be awakened, then shuts
* down system.
*/
static int
rcu_perf_shutdown(void *arg)
{
do {
wait_event(shutdown_wq,
atomic_read(&n_rcu_perf_writer_finished) >=
nrealwriters);
} while (atomic_read(&n_rcu_perf_writer_finished) < nrealwriters);
smp_mb(); /* Wake before output. */
rcu_perf_cleanup();
kernel_power_off();
return -EINVAL;
}
static int __init
rcu_perf_init(void)
{
long i;
int firsterr = 0;
static struct rcu_perf_ops *perf_ops[] = {
&rcu_ops, &rcu_bh_ops, &srcu_ops, &srcud_ops, &sched_ops,
&tasks_ops,
};
if (!torture_init_begin(perf_type, verbose, &perf_runnable))
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)
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_alert(" %s", perf_ops[i]->name);
pr_alert("\n");
firsterr = -EINVAL;
goto unwind;
}
if (cur_ops->init)
cur_ops->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");
/* Start up the kthreads. */
if (shutdown) {
init_waitqueue_head(&shutdown_wq);
firsterr = torture_create_kthread(rcu_perf_shutdown, NULL,
shutdown_task);
if (firsterr)
goto unwind;
schedule_timeout_uninterruptible(1);
}
reader_tasks = kcalloc(nrealreaders, sizeof(reader_tasks[0]),
GFP_KERNEL);
if (reader_tasks == NULL) {
VERBOSE_PERFOUT_ERRSTRING("out of memory");
firsterr = -ENOMEM;
goto unwind;
}
for (i = 0; i < nrealreaders; i++) {
firsterr = torture_create_kthread(rcu_perf_reader, (void *)i,
reader_tasks[i]);
if (firsterr)
goto unwind;
}
while (atomic_read(&n_rcu_perf_reader_started) < nrealreaders)
schedule_timeout_uninterruptible(1);
writer_tasks = kcalloc(nrealwriters, sizeof(reader_tasks[0]),
GFP_KERNEL);
writer_durations = kcalloc(nrealwriters, sizeof(*writer_durations),
GFP_KERNEL);
writer_n_durations =
kcalloc(nrealwriters, sizeof(*writer_n_durations),
GFP_KERNEL);
if (!writer_tasks || !writer_durations || !writer_n_durations) {
VERBOSE_PERFOUT_ERRSTRING("out of memory");
firsterr = -ENOMEM;
goto unwind;
}
for (i = 0; i < nrealwriters; i++) {
writer_durations[i] =
kcalloc(MAX_MEAS, sizeof(*writer_durations[i]),
GFP_KERNEL);
if (!writer_durations[i]) {
firsterr = -ENOMEM;
goto unwind;
}
firsterr = torture_create_kthread(rcu_perf_writer, (void *)i,
writer_tasks[i]);
if (firsterr)
goto unwind;
}
torture_init_end();
return 0;
unwind:
torture_init_end();
rcu_perf_cleanup();
return firsterr;
}
module_init(rcu_perf_init);
module_exit(rcu_perf_cleanup);
![swh spinner](/static/img/swh-spinner.gif)
Computing file changes ...