Revision c9d398fa237882ea07167e23bcfc5e6847066518 authored by Naoya Horiguchi on 31 March 2017, 22:11:55 UTC, committed by Linus Torvalds on 01 April 2017, 00:13:30 UTC
I found the race condition which triggers the following bug when move_pages() and soft offline are called on a single hugetlb page concurrently. Soft offlining page 0x119400 at 0x700000000000 BUG: unable to handle kernel paging request at ffffea0011943820 IP: follow_huge_pmd+0x143/0x190 PGD 7ffd2067 PUD 7ffd1067 PMD 0 [61163.582052] Oops: 0000 [#1] SMP Modules linked in: binfmt_misc ppdev virtio_balloon parport_pc pcspkr i2c_piix4 parport i2c_core acpi_cpufreq ip_tables xfs libcrc32c ata_generic pata_acpi virtio_blk 8139too crc32c_intel ata_piix serio_raw libata virtio_pci 8139cp virtio_ring virtio mii floppy dm_mirror dm_region_hash dm_log dm_mod [last unloaded: cap_check] CPU: 0 PID: 22573 Comm: iterate_numa_mo Tainted: P OE 4.11.0-rc2-mm1+ #2 Hardware name: Red Hat KVM, BIOS 0.5.1 01/01/2011 RIP: 0010:follow_huge_pmd+0x143/0x190 RSP: 0018:ffffc90004bdbcd0 EFLAGS: 00010202 RAX: 0000000465003e80 RBX: ffffea0004e34d30 RCX: 00003ffffffff000 RDX: 0000000011943800 RSI: 0000000000080001 RDI: 0000000465003e80 RBP: ffffc90004bdbd18 R08: 0000000000000000 R09: ffff880138d34000 R10: ffffea0004650000 R11: 0000000000c363b0 R12: ffffea0011943800 R13: ffff8801b8d34000 R14: ffffea0000000000 R15: 000077ff80000000 FS: 00007fc977710740(0000) GS:ffff88007dc00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: ffffea0011943820 CR3: 000000007a746000 CR4: 00000000001406f0 Call Trace: follow_page_mask+0x270/0x550 SYSC_move_pages+0x4ea/0x8f0 SyS_move_pages+0xe/0x10 do_syscall_64+0x67/0x180 entry_SYSCALL64_slow_path+0x25/0x25 RIP: 0033:0x7fc976e03949 RSP: 002b:00007ffe72221d88 EFLAGS: 00000246 ORIG_RAX: 0000000000000117 RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007fc976e03949 RDX: 0000000000c22390 RSI: 0000000000001400 RDI: 0000000000005827 RBP: 00007ffe72221e00 R08: 0000000000c2c3a0 R09: 0000000000000004 R10: 0000000000c363b0 R11: 0000000000000246 R12: 0000000000400650 R13: 00007ffe72221ee0 R14: 0000000000000000 R15: 0000000000000000 Code: 81 e4 ff ff 1f 00 48 21 c2 49 c1 ec 0c 48 c1 ea 0c 4c 01 e2 49 bc 00 00 00 00 00 ea ff ff 48 c1 e2 06 49 01 d4 f6 45 bc 04 74 90 <49> 8b 7c 24 20 40 f6 c7 01 75 2b 4c 89 e7 8b 47 1c 85 c0 7e 2a RIP: follow_huge_pmd+0x143/0x190 RSP: ffffc90004bdbcd0 CR2: ffffea0011943820 ---[ end trace e4f81353a2d23232 ]--- Kernel panic - not syncing: Fatal exception Kernel Offset: disabled This bug is triggered when pmd_present() returns true for non-present hugetlb, so fixing the present check in follow_huge_pmd() prevents it. Using pmd_present() to determine present/non-present for hugetlb is not correct, because pmd_present() checks multiple bits (not only _PAGE_PRESENT) for historical reason and it can misjudge hugetlb state. Fixes: e66f17ff7177 ("mm/hugetlb: take page table lock in follow_huge_pmd()") Link: http://lkml.kernel.org/r/1490149898-20231-1-git-send-email-n-horiguchi@ah.jp.nec.com Signed-off-by: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com> Acked-by: Hillf Danton <hillf.zj@alibaba-inc.com> Cc: Hugh Dickins <hughd@google.com> Cc: Michal Hocko <mhocko@kernel.org> Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com> Cc: Mike Kravetz <mike.kravetz@oracle.com> Cc: Christian Borntraeger <borntraeger@de.ibm.com> Cc: Gerald Schaefer <gerald.schaefer@de.ibm.com> Cc: <stable@vger.kernel.org> [4.0+] Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
1 parent 0cefabd
locktorture.c
/*
* Module-based torture test facility for locking
*
* 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, 2014
*
* Authors: Paul E. McKenney <paulmck@us.ibm.com>
* Davidlohr Bueso <dave@stgolabs.net>
* Based on kernel/rcu/torture.c.
*/
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/kthread.h>
#include <linux/sched/rt.h>
#include <linux/spinlock.h>
#include <linux/rwlock.h>
#include <linux/mutex.h>
#include <linux/rwsem.h>
#include <linux/smp.h>
#include <linux/interrupt.h>
#include <linux/sched.h>
#include <uapi/linux/sched/types.h>
#include <linux/rtmutex.h>
#include <linux/atomic.h>
#include <linux/moduleparam.h>
#include <linux/delay.h>
#include <linux/slab.h>
#include <linux/percpu-rwsem.h>
#include <linux/torture.h>
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Paul E. McKenney <paulmck@us.ibm.com>");
torture_param(int, nwriters_stress, -1,
"Number of write-locking stress-test threads");
torture_param(int, nreaders_stress, -1,
"Number of read-locking stress-test threads");
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, shuffle_interval, 3,
"Number of jiffies between shuffles, 0=disable");
torture_param(int, shutdown_secs, 0, "Shutdown time (j), <= zero to disable.");
torture_param(int, stat_interval, 60,
"Number of seconds between stats printk()s");
torture_param(int, stutter, 5, "Number of jiffies to run/halt test, 0=disable");
torture_param(bool, verbose, true,
"Enable verbose debugging printk()s");
static char *torture_type = "spin_lock";
module_param(torture_type, charp, 0444);
MODULE_PARM_DESC(torture_type,
"Type of lock to torture (spin_lock, spin_lock_irq, mutex_lock, ...)");
static struct task_struct *stats_task;
static struct task_struct **writer_tasks;
static struct task_struct **reader_tasks;
static bool lock_is_write_held;
static bool lock_is_read_held;
struct lock_stress_stats {
long n_lock_fail;
long n_lock_acquired;
};
int torture_runnable = IS_ENABLED(MODULE);
module_param(torture_runnable, int, 0444);
MODULE_PARM_DESC(torture_runnable, "Start locktorture at module init");
/* Forward reference. */
static void lock_torture_cleanup(void);
/*
* Operations vector for selecting different types of tests.
*/
struct lock_torture_ops {
void (*init)(void);
int (*writelock)(void);
void (*write_delay)(struct torture_random_state *trsp);
void (*task_boost)(struct torture_random_state *trsp);
void (*writeunlock)(void);
int (*readlock)(void);
void (*read_delay)(struct torture_random_state *trsp);
void (*readunlock)(void);
unsigned long flags; /* for irq spinlocks */
const char *name;
};
struct lock_torture_cxt {
int nrealwriters_stress;
int nrealreaders_stress;
bool debug_lock;
atomic_t n_lock_torture_errors;
struct lock_torture_ops *cur_ops;
struct lock_stress_stats *lwsa; /* writer statistics */
struct lock_stress_stats *lrsa; /* reader statistics */
};
static struct lock_torture_cxt cxt = { 0, 0, false,
ATOMIC_INIT(0),
NULL, NULL};
/*
* Definitions for lock torture testing.
*/
static int torture_lock_busted_write_lock(void)
{
return 0; /* BUGGY, do not use in real life!!! */
}
static void torture_lock_busted_write_delay(struct torture_random_state *trsp)
{
const unsigned long longdelay_ms = 100;
/* We want a long delay occasionally to force massive contention. */
if (!(torture_random(trsp) %
(cxt.nrealwriters_stress * 2000 * longdelay_ms)))
mdelay(longdelay_ms);
#ifdef CONFIG_PREEMPT
if (!(torture_random(trsp) % (cxt.nrealwriters_stress * 20000)))
preempt_schedule(); /* Allow test to be preempted. */
#endif
}
static void torture_lock_busted_write_unlock(void)
{
/* BUGGY, do not use in real life!!! */
}
static void torture_boost_dummy(struct torture_random_state *trsp)
{
/* Only rtmutexes care about priority */
}
static struct lock_torture_ops lock_busted_ops = {
.writelock = torture_lock_busted_write_lock,
.write_delay = torture_lock_busted_write_delay,
.task_boost = torture_boost_dummy,
.writeunlock = torture_lock_busted_write_unlock,
.readlock = NULL,
.read_delay = NULL,
.readunlock = NULL,
.name = "lock_busted"
};
static DEFINE_SPINLOCK(torture_spinlock);
static int torture_spin_lock_write_lock(void) __acquires(torture_spinlock)
{
spin_lock(&torture_spinlock);
return 0;
}
static void torture_spin_lock_write_delay(struct torture_random_state *trsp)
{
const unsigned long shortdelay_us = 2;
const unsigned long longdelay_ms = 100;
/* We want a short delay mostly to emulate likely code, and
* we want a long delay occasionally to force massive contention.
*/
if (!(torture_random(trsp) %
(cxt.nrealwriters_stress * 2000 * longdelay_ms)))
mdelay(longdelay_ms);
if (!(torture_random(trsp) %
(cxt.nrealwriters_stress * 2 * shortdelay_us)))
udelay(shortdelay_us);
#ifdef CONFIG_PREEMPT
if (!(torture_random(trsp) % (cxt.nrealwriters_stress * 20000)))
preempt_schedule(); /* Allow test to be preempted. */
#endif
}
static void torture_spin_lock_write_unlock(void) __releases(torture_spinlock)
{
spin_unlock(&torture_spinlock);
}
static struct lock_torture_ops spin_lock_ops = {
.writelock = torture_spin_lock_write_lock,
.write_delay = torture_spin_lock_write_delay,
.task_boost = torture_boost_dummy,
.writeunlock = torture_spin_lock_write_unlock,
.readlock = NULL,
.read_delay = NULL,
.readunlock = NULL,
.name = "spin_lock"
};
static int torture_spin_lock_write_lock_irq(void)
__acquires(torture_spinlock)
{
unsigned long flags;
spin_lock_irqsave(&torture_spinlock, flags);
cxt.cur_ops->flags = flags;
return 0;
}
static void torture_lock_spin_write_unlock_irq(void)
__releases(torture_spinlock)
{
spin_unlock_irqrestore(&torture_spinlock, cxt.cur_ops->flags);
}
static struct lock_torture_ops spin_lock_irq_ops = {
.writelock = torture_spin_lock_write_lock_irq,
.write_delay = torture_spin_lock_write_delay,
.task_boost = torture_boost_dummy,
.writeunlock = torture_lock_spin_write_unlock_irq,
.readlock = NULL,
.read_delay = NULL,
.readunlock = NULL,
.name = "spin_lock_irq"
};
static DEFINE_RWLOCK(torture_rwlock);
static int torture_rwlock_write_lock(void) __acquires(torture_rwlock)
{
write_lock(&torture_rwlock);
return 0;
}
static void torture_rwlock_write_delay(struct torture_random_state *trsp)
{
const unsigned long shortdelay_us = 2;
const unsigned long longdelay_ms = 100;
/* We want a short delay mostly to emulate likely code, and
* we want a long delay occasionally to force massive contention.
*/
if (!(torture_random(trsp) %
(cxt.nrealwriters_stress * 2000 * longdelay_ms)))
mdelay(longdelay_ms);
else
udelay(shortdelay_us);
}
static void torture_rwlock_write_unlock(void) __releases(torture_rwlock)
{
write_unlock(&torture_rwlock);
}
static int torture_rwlock_read_lock(void) __acquires(torture_rwlock)
{
read_lock(&torture_rwlock);
return 0;
}
static void torture_rwlock_read_delay(struct torture_random_state *trsp)
{
const unsigned long shortdelay_us = 10;
const unsigned long longdelay_ms = 100;
/* We want a short delay mostly to emulate likely code, and
* we want a long delay occasionally to force massive contention.
*/
if (!(torture_random(trsp) %
(cxt.nrealreaders_stress * 2000 * longdelay_ms)))
mdelay(longdelay_ms);
else
udelay(shortdelay_us);
}
static void torture_rwlock_read_unlock(void) __releases(torture_rwlock)
{
read_unlock(&torture_rwlock);
}
static struct lock_torture_ops rw_lock_ops = {
.writelock = torture_rwlock_write_lock,
.write_delay = torture_rwlock_write_delay,
.task_boost = torture_boost_dummy,
.writeunlock = torture_rwlock_write_unlock,
.readlock = torture_rwlock_read_lock,
.read_delay = torture_rwlock_read_delay,
.readunlock = torture_rwlock_read_unlock,
.name = "rw_lock"
};
static int torture_rwlock_write_lock_irq(void) __acquires(torture_rwlock)
{
unsigned long flags;
write_lock_irqsave(&torture_rwlock, flags);
cxt.cur_ops->flags = flags;
return 0;
}
static void torture_rwlock_write_unlock_irq(void)
__releases(torture_rwlock)
{
write_unlock_irqrestore(&torture_rwlock, cxt.cur_ops->flags);
}
static int torture_rwlock_read_lock_irq(void) __acquires(torture_rwlock)
{
unsigned long flags;
read_lock_irqsave(&torture_rwlock, flags);
cxt.cur_ops->flags = flags;
return 0;
}
static void torture_rwlock_read_unlock_irq(void)
__releases(torture_rwlock)
{
read_unlock_irqrestore(&torture_rwlock, cxt.cur_ops->flags);
}
static struct lock_torture_ops rw_lock_irq_ops = {
.writelock = torture_rwlock_write_lock_irq,
.write_delay = torture_rwlock_write_delay,
.task_boost = torture_boost_dummy,
.writeunlock = torture_rwlock_write_unlock_irq,
.readlock = torture_rwlock_read_lock_irq,
.read_delay = torture_rwlock_read_delay,
.readunlock = torture_rwlock_read_unlock_irq,
.name = "rw_lock_irq"
};
static DEFINE_MUTEX(torture_mutex);
static int torture_mutex_lock(void) __acquires(torture_mutex)
{
mutex_lock(&torture_mutex);
return 0;
}
static void torture_mutex_delay(struct torture_random_state *trsp)
{
const unsigned long longdelay_ms = 100;
/* We want a long delay occasionally to force massive contention. */
if (!(torture_random(trsp) %
(cxt.nrealwriters_stress * 2000 * longdelay_ms)))
mdelay(longdelay_ms * 5);
else
mdelay(longdelay_ms / 5);
#ifdef CONFIG_PREEMPT
if (!(torture_random(trsp) % (cxt.nrealwriters_stress * 20000)))
preempt_schedule(); /* Allow test to be preempted. */
#endif
}
static void torture_mutex_unlock(void) __releases(torture_mutex)
{
mutex_unlock(&torture_mutex);
}
static struct lock_torture_ops mutex_lock_ops = {
.writelock = torture_mutex_lock,
.write_delay = torture_mutex_delay,
.task_boost = torture_boost_dummy,
.writeunlock = torture_mutex_unlock,
.readlock = NULL,
.read_delay = NULL,
.readunlock = NULL,
.name = "mutex_lock"
};
#include <linux/ww_mutex.h>
static DEFINE_WW_CLASS(torture_ww_class);
static DEFINE_WW_MUTEX(torture_ww_mutex_0, &torture_ww_class);
static DEFINE_WW_MUTEX(torture_ww_mutex_1, &torture_ww_class);
static DEFINE_WW_MUTEX(torture_ww_mutex_2, &torture_ww_class);
static int torture_ww_mutex_lock(void)
__acquires(torture_ww_mutex_0)
__acquires(torture_ww_mutex_1)
__acquires(torture_ww_mutex_2)
{
LIST_HEAD(list);
struct reorder_lock {
struct list_head link;
struct ww_mutex *lock;
} locks[3], *ll, *ln;
struct ww_acquire_ctx ctx;
locks[0].lock = &torture_ww_mutex_0;
list_add(&locks[0].link, &list);
locks[1].lock = &torture_ww_mutex_1;
list_add(&locks[1].link, &list);
locks[2].lock = &torture_ww_mutex_2;
list_add(&locks[2].link, &list);
ww_acquire_init(&ctx, &torture_ww_class);
list_for_each_entry(ll, &list, link) {
int err;
err = ww_mutex_lock(ll->lock, &ctx);
if (!err)
continue;
ln = ll;
list_for_each_entry_continue_reverse(ln, &list, link)
ww_mutex_unlock(ln->lock);
if (err != -EDEADLK)
return err;
ww_mutex_lock_slow(ll->lock, &ctx);
list_move(&ll->link, &list);
}
ww_acquire_fini(&ctx);
return 0;
}
static void torture_ww_mutex_unlock(void)
__releases(torture_ww_mutex_0)
__releases(torture_ww_mutex_1)
__releases(torture_ww_mutex_2)
{
ww_mutex_unlock(&torture_ww_mutex_0);
ww_mutex_unlock(&torture_ww_mutex_1);
ww_mutex_unlock(&torture_ww_mutex_2);
}
static struct lock_torture_ops ww_mutex_lock_ops = {
.writelock = torture_ww_mutex_lock,
.write_delay = torture_mutex_delay,
.task_boost = torture_boost_dummy,
.writeunlock = torture_ww_mutex_unlock,
.readlock = NULL,
.read_delay = NULL,
.readunlock = NULL,
.name = "ww_mutex_lock"
};
#ifdef CONFIG_RT_MUTEXES
static DEFINE_RT_MUTEX(torture_rtmutex);
static int torture_rtmutex_lock(void) __acquires(torture_rtmutex)
{
rt_mutex_lock(&torture_rtmutex);
return 0;
}
static void torture_rtmutex_boost(struct torture_random_state *trsp)
{
int policy;
struct sched_param param;
const unsigned int factor = 50000; /* yes, quite arbitrary */
if (!rt_task(current)) {
/*
* Boost priority once every ~50k operations. When the
* task tries to take the lock, the rtmutex it will account
* for the new priority, and do any corresponding pi-dance.
*/
if (trsp && !(torture_random(trsp) %
(cxt.nrealwriters_stress * factor))) {
policy = SCHED_FIFO;
param.sched_priority = MAX_RT_PRIO - 1;
} else /* common case, do nothing */
return;
} else {
/*
* The task will remain boosted for another ~500k operations,
* then restored back to its original prio, and so forth.
*
* When @trsp is nil, we want to force-reset the task for
* stopping the kthread.
*/
if (!trsp || !(torture_random(trsp) %
(cxt.nrealwriters_stress * factor * 2))) {
policy = SCHED_NORMAL;
param.sched_priority = 0;
} else /* common case, do nothing */
return;
}
sched_setscheduler_nocheck(current, policy, ¶m);
}
static void torture_rtmutex_delay(struct torture_random_state *trsp)
{
const unsigned long shortdelay_us = 2;
const unsigned long longdelay_ms = 100;
/*
* We want a short delay mostly to emulate likely code, and
* we want a long delay occasionally to force massive contention.
*/
if (!(torture_random(trsp) %
(cxt.nrealwriters_stress * 2000 * longdelay_ms)))
mdelay(longdelay_ms);
if (!(torture_random(trsp) %
(cxt.nrealwriters_stress * 2 * shortdelay_us)))
udelay(shortdelay_us);
#ifdef CONFIG_PREEMPT
if (!(torture_random(trsp) % (cxt.nrealwriters_stress * 20000)))
preempt_schedule(); /* Allow test to be preempted. */
#endif
}
static void torture_rtmutex_unlock(void) __releases(torture_rtmutex)
{
rt_mutex_unlock(&torture_rtmutex);
}
static struct lock_torture_ops rtmutex_lock_ops = {
.writelock = torture_rtmutex_lock,
.write_delay = torture_rtmutex_delay,
.task_boost = torture_rtmutex_boost,
.writeunlock = torture_rtmutex_unlock,
.readlock = NULL,
.read_delay = NULL,
.readunlock = NULL,
.name = "rtmutex_lock"
};
#endif
static DECLARE_RWSEM(torture_rwsem);
static int torture_rwsem_down_write(void) __acquires(torture_rwsem)
{
down_write(&torture_rwsem);
return 0;
}
static void torture_rwsem_write_delay(struct torture_random_state *trsp)
{
const unsigned long longdelay_ms = 100;
/* We want a long delay occasionally to force massive contention. */
if (!(torture_random(trsp) %
(cxt.nrealwriters_stress * 2000 * longdelay_ms)))
mdelay(longdelay_ms * 10);
else
mdelay(longdelay_ms / 10);
#ifdef CONFIG_PREEMPT
if (!(torture_random(trsp) % (cxt.nrealwriters_stress * 20000)))
preempt_schedule(); /* Allow test to be preempted. */
#endif
}
static void torture_rwsem_up_write(void) __releases(torture_rwsem)
{
up_write(&torture_rwsem);
}
static int torture_rwsem_down_read(void) __acquires(torture_rwsem)
{
down_read(&torture_rwsem);
return 0;
}
static void torture_rwsem_read_delay(struct torture_random_state *trsp)
{
const unsigned long longdelay_ms = 100;
/* We want a long delay occasionally to force massive contention. */
if (!(torture_random(trsp) %
(cxt.nrealwriters_stress * 2000 * longdelay_ms)))
mdelay(longdelay_ms * 2);
else
mdelay(longdelay_ms / 2);
#ifdef CONFIG_PREEMPT
if (!(torture_random(trsp) % (cxt.nrealreaders_stress * 20000)))
preempt_schedule(); /* Allow test to be preempted. */
#endif
}
static void torture_rwsem_up_read(void) __releases(torture_rwsem)
{
up_read(&torture_rwsem);
}
static struct lock_torture_ops rwsem_lock_ops = {
.writelock = torture_rwsem_down_write,
.write_delay = torture_rwsem_write_delay,
.task_boost = torture_boost_dummy,
.writeunlock = torture_rwsem_up_write,
.readlock = torture_rwsem_down_read,
.read_delay = torture_rwsem_read_delay,
.readunlock = torture_rwsem_up_read,
.name = "rwsem_lock"
};
#include <linux/percpu-rwsem.h>
static struct percpu_rw_semaphore pcpu_rwsem;
void torture_percpu_rwsem_init(void)
{
BUG_ON(percpu_init_rwsem(&pcpu_rwsem));
}
static int torture_percpu_rwsem_down_write(void) __acquires(pcpu_rwsem)
{
percpu_down_write(&pcpu_rwsem);
return 0;
}
static void torture_percpu_rwsem_up_write(void) __releases(pcpu_rwsem)
{
percpu_up_write(&pcpu_rwsem);
}
static int torture_percpu_rwsem_down_read(void) __acquires(pcpu_rwsem)
{
percpu_down_read(&pcpu_rwsem);
return 0;
}
static void torture_percpu_rwsem_up_read(void) __releases(pcpu_rwsem)
{
percpu_up_read(&pcpu_rwsem);
}
static struct lock_torture_ops percpu_rwsem_lock_ops = {
.init = torture_percpu_rwsem_init,
.writelock = torture_percpu_rwsem_down_write,
.write_delay = torture_rwsem_write_delay,
.task_boost = torture_boost_dummy,
.writeunlock = torture_percpu_rwsem_up_write,
.readlock = torture_percpu_rwsem_down_read,
.read_delay = torture_rwsem_read_delay,
.readunlock = torture_percpu_rwsem_up_read,
.name = "percpu_rwsem_lock"
};
/*
* Lock torture writer kthread. Repeatedly acquires and releases
* the lock, checking for duplicate acquisitions.
*/
static int lock_torture_writer(void *arg)
{
struct lock_stress_stats *lwsp = arg;
static DEFINE_TORTURE_RANDOM(rand);
VERBOSE_TOROUT_STRING("lock_torture_writer task started");
set_user_nice(current, MAX_NICE);
do {
if ((torture_random(&rand) & 0xfffff) == 0)
schedule_timeout_uninterruptible(1);
cxt.cur_ops->task_boost(&rand);
cxt.cur_ops->writelock();
if (WARN_ON_ONCE(lock_is_write_held))
lwsp->n_lock_fail++;
lock_is_write_held = 1;
if (WARN_ON_ONCE(lock_is_read_held))
lwsp->n_lock_fail++; /* rare, but... */
lwsp->n_lock_acquired++;
cxt.cur_ops->write_delay(&rand);
lock_is_write_held = 0;
cxt.cur_ops->writeunlock();
stutter_wait("lock_torture_writer");
} while (!torture_must_stop());
cxt.cur_ops->task_boost(NULL); /* reset prio */
torture_kthread_stopping("lock_torture_writer");
return 0;
}
/*
* Lock torture reader kthread. Repeatedly acquires and releases
* the reader lock.
*/
static int lock_torture_reader(void *arg)
{
struct lock_stress_stats *lrsp = arg;
static DEFINE_TORTURE_RANDOM(rand);
VERBOSE_TOROUT_STRING("lock_torture_reader task started");
set_user_nice(current, MAX_NICE);
do {
if ((torture_random(&rand) & 0xfffff) == 0)
schedule_timeout_uninterruptible(1);
cxt.cur_ops->readlock();
lock_is_read_held = 1;
if (WARN_ON_ONCE(lock_is_write_held))
lrsp->n_lock_fail++; /* rare, but... */
lrsp->n_lock_acquired++;
cxt.cur_ops->read_delay(&rand);
lock_is_read_held = 0;
cxt.cur_ops->readunlock();
stutter_wait("lock_torture_reader");
} while (!torture_must_stop());
torture_kthread_stopping("lock_torture_reader");
return 0;
}
/*
* Create an lock-torture-statistics message in the specified buffer.
*/
static void __torture_print_stats(char *page,
struct lock_stress_stats *statp, bool write)
{
bool fail = 0;
int i, n_stress;
long max = 0;
long min = statp[0].n_lock_acquired;
long long sum = 0;
n_stress = write ? cxt.nrealwriters_stress : cxt.nrealreaders_stress;
for (i = 0; i < n_stress; i++) {
if (statp[i].n_lock_fail)
fail = true;
sum += statp[i].n_lock_acquired;
if (max < statp[i].n_lock_fail)
max = statp[i].n_lock_fail;
if (min > statp[i].n_lock_fail)
min = statp[i].n_lock_fail;
}
page += sprintf(page,
"%s: Total: %lld Max/Min: %ld/%ld %s Fail: %d %s\n",
write ? "Writes" : "Reads ",
sum, max, min, max / 2 > min ? "???" : "",
fail, fail ? "!!!" : "");
if (fail)
atomic_inc(&cxt.n_lock_torture_errors);
}
/*
* Print torture statistics. Caller must ensure that there is only one
* call to this function at a given time!!! This is normally accomplished
* by relying on the module system to only have one copy of the module
* loaded, and then by giving the lock_torture_stats kthread full control
* (or the init/cleanup functions when lock_torture_stats thread is not
* running).
*/
static void lock_torture_stats_print(void)
{
int size = cxt.nrealwriters_stress * 200 + 8192;
char *buf;
if (cxt.cur_ops->readlock)
size += cxt.nrealreaders_stress * 200 + 8192;
buf = kmalloc(size, GFP_KERNEL);
if (!buf) {
pr_err("lock_torture_stats_print: Out of memory, need: %d",
size);
return;
}
__torture_print_stats(buf, cxt.lwsa, true);
pr_alert("%s", buf);
kfree(buf);
if (cxt.cur_ops->readlock) {
buf = kmalloc(size, GFP_KERNEL);
if (!buf) {
pr_err("lock_torture_stats_print: Out of memory, need: %d",
size);
return;
}
__torture_print_stats(buf, cxt.lrsa, false);
pr_alert("%s", buf);
kfree(buf);
}
}
/*
* Periodically prints torture statistics, if periodic statistics printing
* was specified via the stat_interval module parameter.
*
* No need to worry about fullstop here, since this one doesn't reference
* volatile state or register callbacks.
*/
static int lock_torture_stats(void *arg)
{
VERBOSE_TOROUT_STRING("lock_torture_stats task started");
do {
schedule_timeout_interruptible(stat_interval * HZ);
lock_torture_stats_print();
torture_shutdown_absorb("lock_torture_stats");
} while (!torture_must_stop());
torture_kthread_stopping("lock_torture_stats");
return 0;
}
static inline void
lock_torture_print_module_parms(struct lock_torture_ops *cur_ops,
const char *tag)
{
pr_alert("%s" TORTURE_FLAG
"--- %s%s: nwriters_stress=%d nreaders_stress=%d stat_interval=%d verbose=%d shuffle_interval=%d stutter=%d shutdown_secs=%d onoff_interval=%d onoff_holdoff=%d\n",
torture_type, tag, cxt.debug_lock ? " [debug]": "",
cxt.nrealwriters_stress, cxt.nrealreaders_stress, stat_interval,
verbose, shuffle_interval, stutter, shutdown_secs,
onoff_interval, onoff_holdoff);
}
static void lock_torture_cleanup(void)
{
int i;
if (torture_cleanup_begin())
return;
/*
* Indicates early cleanup, meaning that the test has not run,
* such as when passing bogus args when loading the module. As
* such, only perform the underlying torture-specific cleanups,
* and avoid anything related to locktorture.
*/
if (!cxt.lwsa)
goto end;
if (writer_tasks) {
for (i = 0; i < cxt.nrealwriters_stress; i++)
torture_stop_kthread(lock_torture_writer,
writer_tasks[i]);
kfree(writer_tasks);
writer_tasks = NULL;
}
if (reader_tasks) {
for (i = 0; i < cxt.nrealreaders_stress; i++)
torture_stop_kthread(lock_torture_reader,
reader_tasks[i]);
kfree(reader_tasks);
reader_tasks = NULL;
}
torture_stop_kthread(lock_torture_stats, stats_task);
lock_torture_stats_print(); /* -After- the stats thread is stopped! */
if (atomic_read(&cxt.n_lock_torture_errors))
lock_torture_print_module_parms(cxt.cur_ops,
"End of test: FAILURE");
else if (torture_onoff_failures())
lock_torture_print_module_parms(cxt.cur_ops,
"End of test: LOCK_HOTPLUG");
else
lock_torture_print_module_parms(cxt.cur_ops,
"End of test: SUCCESS");
kfree(cxt.lwsa);
kfree(cxt.lrsa);
end:
torture_cleanup_end();
}
static int __init lock_torture_init(void)
{
int i, j;
int firsterr = 0;
static struct lock_torture_ops *torture_ops[] = {
&lock_busted_ops,
&spin_lock_ops, &spin_lock_irq_ops,
&rw_lock_ops, &rw_lock_irq_ops,
&mutex_lock_ops,
&ww_mutex_lock_ops,
#ifdef CONFIG_RT_MUTEXES
&rtmutex_lock_ops,
#endif
&rwsem_lock_ops,
&percpu_rwsem_lock_ops,
};
if (!torture_init_begin(torture_type, verbose, &torture_runnable))
return -EBUSY;
/* Process args and tell the world that the torturer is on the job. */
for (i = 0; i < ARRAY_SIZE(torture_ops); i++) {
cxt.cur_ops = torture_ops[i];
if (strcmp(torture_type, cxt.cur_ops->name) == 0)
break;
}
if (i == ARRAY_SIZE(torture_ops)) {
pr_alert("lock-torture: invalid torture type: \"%s\"\n",
torture_type);
pr_alert("lock-torture types:");
for (i = 0; i < ARRAY_SIZE(torture_ops); i++)
pr_alert(" %s", torture_ops[i]->name);
pr_alert("\n");
firsterr = -EINVAL;
goto unwind;
}
if (cxt.cur_ops->init)
cxt.cur_ops->init();
if (nwriters_stress >= 0)
cxt.nrealwriters_stress = nwriters_stress;
else
cxt.nrealwriters_stress = 2 * num_online_cpus();
#ifdef CONFIG_DEBUG_MUTEXES
if (strncmp(torture_type, "mutex", 5) == 0)
cxt.debug_lock = true;
#endif
#ifdef CONFIG_DEBUG_RT_MUTEXES
if (strncmp(torture_type, "rtmutex", 7) == 0)
cxt.debug_lock = true;
#endif
#ifdef CONFIG_DEBUG_SPINLOCK
if ((strncmp(torture_type, "spin", 4) == 0) ||
(strncmp(torture_type, "rw_lock", 7) == 0))
cxt.debug_lock = true;
#endif
/* Initialize the statistics so that each run gets its own numbers. */
lock_is_write_held = 0;
cxt.lwsa = kmalloc(sizeof(*cxt.lwsa) * cxt.nrealwriters_stress, GFP_KERNEL);
if (cxt.lwsa == NULL) {
VERBOSE_TOROUT_STRING("cxt.lwsa: Out of memory");
firsterr = -ENOMEM;
goto unwind;
}
for (i = 0; i < cxt.nrealwriters_stress; i++) {
cxt.lwsa[i].n_lock_fail = 0;
cxt.lwsa[i].n_lock_acquired = 0;
}
if (cxt.cur_ops->readlock) {
if (nreaders_stress >= 0)
cxt.nrealreaders_stress = nreaders_stress;
else {
/*
* By default distribute evenly the number of
* readers and writers. We still run the same number
* of threads as the writer-only locks default.
*/
if (nwriters_stress < 0) /* user doesn't care */
cxt.nrealwriters_stress = num_online_cpus();
cxt.nrealreaders_stress = cxt.nrealwriters_stress;
}
lock_is_read_held = 0;
cxt.lrsa = kmalloc(sizeof(*cxt.lrsa) * cxt.nrealreaders_stress, GFP_KERNEL);
if (cxt.lrsa == NULL) {
VERBOSE_TOROUT_STRING("cxt.lrsa: Out of memory");
firsterr = -ENOMEM;
kfree(cxt.lwsa);
cxt.lwsa = NULL;
goto unwind;
}
for (i = 0; i < cxt.nrealreaders_stress; i++) {
cxt.lrsa[i].n_lock_fail = 0;
cxt.lrsa[i].n_lock_acquired = 0;
}
}
lock_torture_print_module_parms(cxt.cur_ops, "Start of test");
/* Prepare torture context. */
if (onoff_interval > 0) {
firsterr = torture_onoff_init(onoff_holdoff * HZ,
onoff_interval * HZ);
if (firsterr)
goto unwind;
}
if (shuffle_interval > 0) {
firsterr = torture_shuffle_init(shuffle_interval);
if (firsterr)
goto unwind;
}
if (shutdown_secs > 0) {
firsterr = torture_shutdown_init(shutdown_secs,
lock_torture_cleanup);
if (firsterr)
goto unwind;
}
if (stutter > 0) {
firsterr = torture_stutter_init(stutter);
if (firsterr)
goto unwind;
}
writer_tasks = kzalloc(cxt.nrealwriters_stress * sizeof(writer_tasks[0]),
GFP_KERNEL);
if (writer_tasks == NULL) {
VERBOSE_TOROUT_ERRSTRING("writer_tasks: Out of memory");
firsterr = -ENOMEM;
goto unwind;
}
if (cxt.cur_ops->readlock) {
reader_tasks = kzalloc(cxt.nrealreaders_stress * sizeof(reader_tasks[0]),
GFP_KERNEL);
if (reader_tasks == NULL) {
VERBOSE_TOROUT_ERRSTRING("reader_tasks: Out of memory");
kfree(writer_tasks);
writer_tasks = NULL;
firsterr = -ENOMEM;
goto unwind;
}
}
/*
* Create the kthreads and start torturing (oh, those poor little locks).
*
* TODO: Note that we interleave writers with readers, giving writers a
* slight advantage, by creating its kthread first. This can be modified
* for very specific needs, or even let the user choose the policy, if
* ever wanted.
*/
for (i = 0, j = 0; i < cxt.nrealwriters_stress ||
j < cxt.nrealreaders_stress; i++, j++) {
if (i >= cxt.nrealwriters_stress)
goto create_reader;
/* Create writer. */
firsterr = torture_create_kthread(lock_torture_writer, &cxt.lwsa[i],
writer_tasks[i]);
if (firsterr)
goto unwind;
create_reader:
if (cxt.cur_ops->readlock == NULL || (j >= cxt.nrealreaders_stress))
continue;
/* Create reader. */
firsterr = torture_create_kthread(lock_torture_reader, &cxt.lrsa[j],
reader_tasks[j]);
if (firsterr)
goto unwind;
}
if (stat_interval > 0) {
firsterr = torture_create_kthread(lock_torture_stats, NULL,
stats_task);
if (firsterr)
goto unwind;
}
torture_init_end();
return 0;
unwind:
torture_init_end();
lock_torture_cleanup();
return firsterr;
}
module_init(lock_torture_init);
module_exit(lock_torture_cleanup);
![swh spinner](/static/img/swh-spinner.gif)
Computing file changes ...