From 4c98586dafab4518a7eea8db9a19271e99ae3110 Mon Sep 17 00:00:00 2001 From: jdike <52420226+jdike@users.noreply.github.com> Date: Wed, 17 Jul 2019 12:18:24 -0400 Subject: [PATCH] Fix lockdep recursive locking false positive in dbuf_destroy 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 Reviewed-by: Brian Behlendorf Signed-off-by: Jeff Dike Closes #8984 --- include/spl/sys/mutex.h | 2 ++ include/sys/zfs_context.h | 2 ++ module/zfs/dbuf.c | 3 ++- 3 files changed, 6 insertions(+), 1 deletion(-) diff --git a/include/spl/sys/mutex.h b/include/spl/sys/mutex.h index ed0cd4932..a61f35c61 100644 --- a/include/spl/sys/mutex.h +++ b/include/spl/sys/mutex.h @@ -127,6 +127,8 @@ spl_mutex_lockdep_on_maybe(kmutex_t *mp) \ }) /* END CSTYLED */ +#define NESTED_SINGLE 1 + #ifdef CONFIG_DEBUG_LOCK_ALLOC #define mutex_enter_nested(mp, subclass) \ { \ diff --git a/include/sys/zfs_context.h b/include/sys/zfs_context.h index e3fa2e61b..598b86a7a 100644 --- a/include/sys/zfs_context.h +++ b/include/sys/zfs_context.h @@ -257,6 +257,8 @@ extern void mutex_enter(kmutex_t *mp); extern void mutex_exit(kmutex_t *mp); extern int mutex_tryenter(kmutex_t *mp); +#define NESTED_SINGLE 1 +#define mutex_enter_nested(mp, class) mutex_enter(mp) /* * RW locks */ diff --git a/module/zfs/dbuf.c b/module/zfs/dbuf.c index 07e616f6f..94c49b3ef 100644 --- a/module/zfs/dbuf.c +++ b/module/zfs/dbuf.c @@ -2591,7 +2591,8 @@ dbuf_destroy(dmu_buf_impl_t *db) if (db->db_blkid != DMU_BONUS_BLKID) { boolean_t needlock = !MUTEX_HELD(&dn->dn_dbufs_mtx); if (needlock) - mutex_enter(&dn->dn_dbufs_mtx); + mutex_enter_nested(&dn->dn_dbufs_mtx, + NESTED_SINGLE); avl_remove(&dn->dn_dbufs, db); atomic_dec_32(&dn->dn_dbufs_count); membar_producer();