mirror of
https://git.proxmox.com/git/mirror_zfs.git
synced 2024-11-18 18:31:00 +03:00
4c98586daf
lockdep reports a possible recursive lock in dbuf_destroy. It is true that dbuf_destroy is acquiring the dn_dbufs_mtx on one dnode while holding it on another dnode. However, it is impossible for these to be the same dnode because, among other things,dbuf_destroy checks MUTEX_HELD before acquiring the mutex. This fix defines a class NESTED_SINGLE == 1 and changes that lock to call mutex_enter_nested with a subclass of NESTED_SINGLE. In order to make the userspace code compile, include/sys/zfs_context.h now defines mutex_enter_nested and NESTED_SINGLE. This is the lockdep report: [ 122.950921] ============================================ [ 122.950921] WARNING: possible recursive locking detected [ 122.950921] 4.19.29-4.19.0-debug-d69edad5368c1166 #1 Tainted: G O [ 122.950921] -------------------------------------------- [ 122.950921] dbu_evict/1457 is trying to acquire lock: [ 122.950921] 0000000083e9cbcf (&dn->dn_dbufs_mtx){+.+.}, at: dbuf_destroy+0x3c0/0xdb0 [zfs] [ 122.950921] but task is already holding lock: [ 122.950921] 0000000055523987 (&dn->dn_dbufs_mtx){+.+.}, at: dnode_evict_dbufs+0x90/0x740 [zfs] [ 122.950921] other info that might help us debug this: [ 122.950921] Possible unsafe locking scenario: [ 122.950921] CPU0 [ 122.950921] ---- [ 122.950921] lock(&dn->dn_dbufs_mtx); [ 122.950921] lock(&dn->dn_dbufs_mtx); [ 122.950921] *** DEADLOCK *** [ 122.950921] May be due to missing lock nesting notation [ 122.950921] 1 lock held by dbu_evict/1457: [ 122.950921] #0: 0000000055523987 (&dn->dn_dbufs_mtx){+.+.}, at: dnode_evict_dbufs+0x90/0x740 [zfs] [ 122.950921] stack backtrace: [ 122.950921] CPU: 0 PID: 1457 Comm: dbu_evict Tainted: G O 4.19.29-4.19.0-debug-d69edad5368c1166 #1 [ 122.950921] Hardware name: Supermicro H8SSL-I2/H8SSL-I2, BIOS 080011 03/13/2009 [ 122.950921] Call Trace: [ 122.950921] dump_stack+0x91/0xeb [ 122.950921] __lock_acquire+0x2ca7/0x4f10 [ 122.950921] lock_acquire+0x153/0x330 [ 122.950921] dbuf_destroy+0x3c0/0xdb0 [zfs] [ 122.950921] dbuf_evict_one+0x1cc/0x3d0 [zfs] [ 122.950921] dbuf_rele_and_unlock+0xb84/0xd60 [zfs] [ 122.950921] dnode_evict_dbufs+0x3a6/0x740 [zfs] [ 122.950921] dmu_objset_evict+0x7a/0x500 [zfs] [ 122.950921] dsl_dataset_evict_async+0x70/0x480 [zfs] [ 122.950921] taskq_thread+0x979/0x1480 [spl] [ 122.950921] kthread+0x2e7/0x3e0 [ 122.950921] ret_from_fork+0x27/0x50 Reviewed-by: Tony Hutter <hutter2@llnl.gov> Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov> Signed-off-by: Jeff Dike <jdike@akamai.com> Closes #8984
188 lines
5.3 KiB
C
188 lines
5.3 KiB
C
/*
|
|
* Copyright (C) 2007-2010 Lawrence Livermore National Security, LLC.
|
|
* Copyright (C) 2007 The Regents of the University of California.
|
|
* Produced at Lawrence Livermore National Laboratory (cf, DISCLAIMER).
|
|
* Written by Brian Behlendorf <behlendorf1@llnl.gov>.
|
|
* UCRL-CODE-235197
|
|
*
|
|
* This file is part of the SPL, Solaris Porting Layer.
|
|
* For details, see <http://zfsonlinux.org/>.
|
|
*
|
|
* The SPL 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.
|
|
*
|
|
* The SPL 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 the SPL. If not, see <http://www.gnu.org/licenses/>.
|
|
*/
|
|
|
|
#ifndef _SPL_MUTEX_H
|
|
#define _SPL_MUTEX_H
|
|
|
|
#include <sys/types.h>
|
|
#include <linux/mutex.h>
|
|
#include <linux/lockdep.h>
|
|
#include <linux/compiler_compat.h>
|
|
|
|
typedef enum {
|
|
MUTEX_DEFAULT = 0,
|
|
MUTEX_SPIN = 1,
|
|
MUTEX_ADAPTIVE = 2,
|
|
MUTEX_NOLOCKDEP = 3
|
|
} kmutex_type_t;
|
|
|
|
typedef struct {
|
|
struct mutex m_mutex;
|
|
spinlock_t m_lock; /* used for serializing mutex_exit */
|
|
kthread_t *m_owner;
|
|
#ifdef CONFIG_LOCKDEP
|
|
kmutex_type_t m_type;
|
|
#endif /* CONFIG_LOCKDEP */
|
|
} kmutex_t;
|
|
|
|
#define MUTEX(mp) (&((mp)->m_mutex))
|
|
|
|
static inline void
|
|
spl_mutex_set_owner(kmutex_t *mp)
|
|
{
|
|
mp->m_owner = current;
|
|
}
|
|
|
|
static inline void
|
|
spl_mutex_clear_owner(kmutex_t *mp)
|
|
{
|
|
mp->m_owner = NULL;
|
|
}
|
|
|
|
#define mutex_owner(mp) (READ_ONCE((mp)->m_owner))
|
|
#define mutex_owned(mp) (mutex_owner(mp) == current)
|
|
#define MUTEX_HELD(mp) mutex_owned(mp)
|
|
#define MUTEX_NOT_HELD(mp) (!MUTEX_HELD(mp))
|
|
|
|
#ifdef CONFIG_LOCKDEP
|
|
static inline void
|
|
spl_mutex_set_type(kmutex_t *mp, kmutex_type_t type)
|
|
{
|
|
mp->m_type = type;
|
|
}
|
|
static inline void
|
|
spl_mutex_lockdep_off_maybe(kmutex_t *mp) \
|
|
{ \
|
|
if (mp && mp->m_type == MUTEX_NOLOCKDEP) \
|
|
lockdep_off(); \
|
|
}
|
|
static inline void
|
|
spl_mutex_lockdep_on_maybe(kmutex_t *mp) \
|
|
{ \
|
|
if (mp && mp->m_type == MUTEX_NOLOCKDEP) \
|
|
lockdep_on(); \
|
|
}
|
|
#else /* CONFIG_LOCKDEP */
|
|
#define spl_mutex_set_type(mp, type)
|
|
#define spl_mutex_lockdep_off_maybe(mp)
|
|
#define spl_mutex_lockdep_on_maybe(mp)
|
|
#endif /* CONFIG_LOCKDEP */
|
|
|
|
/*
|
|
* The following functions must be a #define and not static inline.
|
|
* This ensures that the native linux mutex functions (lock/unlock)
|
|
* will be correctly located in the users code which is important
|
|
* for the built in kernel lock analysis tools
|
|
*/
|
|
#undef mutex_init
|
|
#define mutex_init(mp, name, type, ibc) \
|
|
{ \
|
|
static struct lock_class_key __key; \
|
|
ASSERT(type == MUTEX_DEFAULT || type == MUTEX_NOLOCKDEP); \
|
|
\
|
|
__mutex_init(MUTEX(mp), (name) ? (#name) : (#mp), &__key); \
|
|
spin_lock_init(&(mp)->m_lock); \
|
|
spl_mutex_clear_owner(mp); \
|
|
spl_mutex_set_type(mp, type); \
|
|
}
|
|
|
|
#undef mutex_destroy
|
|
#define mutex_destroy(mp) \
|
|
{ \
|
|
VERIFY3P(mutex_owner(mp), ==, NULL); \
|
|
}
|
|
|
|
/* BEGIN CSTYLED */
|
|
#define mutex_tryenter(mp) \
|
|
({ \
|
|
int _rc_; \
|
|
\
|
|
spl_mutex_lockdep_off_maybe(mp); \
|
|
if ((_rc_ = mutex_trylock(MUTEX(mp))) == 1) \
|
|
spl_mutex_set_owner(mp); \
|
|
spl_mutex_lockdep_on_maybe(mp); \
|
|
\
|
|
_rc_; \
|
|
})
|
|
/* END CSTYLED */
|
|
|
|
#define NESTED_SINGLE 1
|
|
|
|
#ifdef CONFIG_DEBUG_LOCK_ALLOC
|
|
#define mutex_enter_nested(mp, subclass) \
|
|
{ \
|
|
ASSERT3P(mutex_owner(mp), !=, current); \
|
|
spl_mutex_lockdep_off_maybe(mp); \
|
|
mutex_lock_nested(MUTEX(mp), (subclass)); \
|
|
spl_mutex_lockdep_on_maybe(mp); \
|
|
spl_mutex_set_owner(mp); \
|
|
}
|
|
#else /* CONFIG_DEBUG_LOCK_ALLOC */
|
|
#define mutex_enter_nested(mp, subclass) \
|
|
{ \
|
|
ASSERT3P(mutex_owner(mp), !=, current); \
|
|
spl_mutex_lockdep_off_maybe(mp); \
|
|
mutex_lock(MUTEX(mp)); \
|
|
spl_mutex_lockdep_on_maybe(mp); \
|
|
spl_mutex_set_owner(mp); \
|
|
}
|
|
#endif /* CONFIG_DEBUG_LOCK_ALLOC */
|
|
|
|
#define mutex_enter(mp) mutex_enter_nested((mp), 0)
|
|
|
|
/*
|
|
* The reason for the spinlock:
|
|
*
|
|
* The Linux mutex is designed with a fast-path/slow-path design such that it
|
|
* does not guarantee serialization upon itself, allowing a race where latter
|
|
* acquirers finish mutex_unlock before former ones.
|
|
*
|
|
* The race renders it unsafe to be used for serializing the freeing of an
|
|
* object in which the mutex is embedded, where the latter acquirer could go
|
|
* on to free the object while the former one is still doing mutex_unlock and
|
|
* causing memory corruption.
|
|
*
|
|
* However, there are many places in ZFS where the mutex is used for
|
|
* serializing object freeing, and the code is shared among other OSes without
|
|
* this issue. Thus, we need the spinlock to force the serialization on
|
|
* mutex_exit().
|
|
*
|
|
* See http://lwn.net/Articles/575477/ for the information about the race.
|
|
*/
|
|
#define mutex_exit(mp) \
|
|
{ \
|
|
spl_mutex_clear_owner(mp); \
|
|
spin_lock(&(mp)->m_lock); \
|
|
spl_mutex_lockdep_off_maybe(mp); \
|
|
mutex_unlock(MUTEX(mp)); \
|
|
spl_mutex_lockdep_on_maybe(mp); \
|
|
spin_unlock(&(mp)->m_lock); \
|
|
/* NOTE: do not dereference mp after this point */ \
|
|
}
|
|
|
|
int spl_mutex_init(void);
|
|
void spl_mutex_fini(void);
|
|
|
|
#endif /* _SPL_MUTEX_H */
|