From: Bart Van Assche <bvanassche@acm.org>
Date: Wed, 17 Apr 2019 14:44:41 -0700
Subject: scsi: qla2xxx: Fix hardirq-unsafe locking
Patch-mainline: v5.2-rc1
Git-commit: 300ec7415c1fed5c73660f50c8e14a67e236dc0a
References: bsc#1082635 bsc#1123034 bsc#1131304 bsc#1127988 bsc#1141340 bsc#1143706
Since fc_remote_port_delete() must be called with interrupts enabled, do
not disable interrupts when calling that function. Remove the lockin calls
from around the put_sess() call. This is safe because the function that is
called when the final reference is dropped, qlt_unreg_sess(), grabs the
proper locks. This patch avoids that lockdep reports the following:
WARNING: HARDIRQ-safe -> HARDIRQ-unsafe lock order detected
kworker/2:1/62 [HC0[0]:SC0[0]:HE0:SE1] is trying to acquire:
0000000009e679b3 (&(&k->k_lock)->rlock){+.+.}, at: klist_next+0x43/0x1d0
and this task is already holding:
00000000a033b71c (&(&ha->tgt.sess_lock)->rlock){-...}, at: qla24xx_delete_sess_fn+0x55/0xf0 [qla2xxx_scst]
which would create a new lock dependency:
(&(&ha->tgt.sess_lock)->rlock){-...} -> (&(&k->k_lock)->rlock){+.+.}
but this new dependency connects a HARDIRQ-irq-safe lock:
(&(&ha->tgt.sess_lock)->rlock){-...}
... which became HARDIRQ-irq-safe at:
lock_acquire+0xe3/0x200
_raw_spin_lock_irqsave+0x3d/0x60
qla24xx_report_id_acquisition+0xa69/0xe30 [qla2xxx_scst]
qla24xx_process_response_queue+0x69e/0x1270 [qla2xxx_scst]
qla24xx_msix_rsp_q+0x79/0xf0 [qla2xxx_scst]
__handle_irq_event_percpu+0x79/0x3c0
handle_irq_event_percpu+0x70/0xf0
handle_irq_event+0x5a/0x8b
handle_edge_irq+0x12c/0x310
handle_irq+0x192/0x20a
do_IRQ+0x73/0x160
ret_from_intr+0x0/0x1d
default_idle+0x23/0x1f0
arch_cpu_idle+0x15/0x20
default_idle_call+0x35/0x40
do_idle+0x2bb/0x2e0
cpu_startup_entry+0x1d/0x20
start_secondary+0x2a8/0x320
secondary_startup_64+0xa4/0xb0
to a HARDIRQ-irq-unsafe lock:
(&(&k->k_lock)->rlock){+.+.}
... which became HARDIRQ-irq-unsafe at:
...
lock_acquire+0xe3/0x200
_raw_spin_lock+0x32/0x50
klist_add_tail+0x33/0xb0
device_add+0x7e1/0xb50
device_create_groups_vargs+0x11c/0x150
device_create_with_groups+0x89/0xb0
vtconsole_class_init+0xb2/0x124
do_one_initcall+0xc5/0x3ce
kernel_init_freeable+0x295/0x32e
kernel_init+0x11/0x11b
ret_from_fork+0x3a/0x50
other info that might help us debug this:
Possible interrupt unsafe locking scenario:
CPU0 CPU1
---- ----
lock(&(&k->k_lock)->rlock);
local_irq_disable();
lock(&(&ha->tgt.sess_lock)->rlock);
lock(&(&k->k_lock)->rlock);
<Interrupt>
lock(&(&ha->tgt.sess_lock)->rlock);
*** DEADLOCK ***
3 locks held by kworker/2:1/62:
#0: 00000000a4319c16 ((wq_completion)"qla2xxx_wq"){+.+.}, at: process_one_work+0x437/0xa80
#1: 00000000ffa34c42 ((work_completion)(&sess->del_work)){+.+.}, at: process_one_work+0x437/0xa80
#2: 00000000a033b71c (&(&ha->tgt.sess_lock)->rlock){-...}, at: qla24xx_delete_sess_fn+0x55/0xf0 [qla2xxx_scst]
the dependencies between HARDIRQ-irq-safe lock and the holding lock:
-> (&(&ha->tgt.sess_lock)->rlock){-...} ops: 8 {
IN-HARDIRQ-W at:
lock_acquire+0xe3/0x200
_raw_spin_lock_irqsave+0x3d/0x60
qla24xx_report_id_acquisition+0xa69/0xe30 [qla2xxx_scst]
qla24xx_process_response_queue+0x69e/0x1270 [qla2xxx_scst]
qla24xx_msix_rsp_q+0x79/0xf0 [qla2xxx_scst]
__handle_irq_event_percpu+0x79/0x3c0
handle_irq_event_percpu+0x70/0xf0
handle_irq_event+0x5a/0x8b
handle_edge_irq+0x12c/0x310
handle_irq+0x192/0x20a
do_IRQ+0x73/0x160
ret_from_intr+0x0/0x1d
default_idle+0x23/0x1f0
arch_cpu_idle+0x15/0x20
default_idle_call+0x35/0x40
do_idle+0x2bb/0x2e0
cpu_startup_entry+0x1d/0x20
start_secondary+0x2a8/0x320
secondary_startup_64+0xa4/0xb0
INITIAL USE at:
lock_acquire+0xe3/0x200
_raw_spin_lock_irqsave+0x3d/0x60
qla24xx_report_id_acquisition+0xa69/0xe30 [qla2xxx_scst]
qla24xx_process_response_queue+0x69e/0x1270 [qla2xxx_scst]
qla24xx_msix_rsp_q+0x79/0xf0 [qla2xxx_scst]
__handle_irq_event_percpu+0x79/0x3c0
handle_irq_event_percpu+0x70/0xf0
handle_irq_event+0x5a/0x8b
handle_edge_irq+0x12c/0x310
handle_irq+0x192/0x20a
do_IRQ+0x73/0x160
ret_from_intr+0x0/0x1d
default_idle+0x23/0x1f0
arch_cpu_idle+0x15/0x20
default_idle_call+0x35/0x40
do_idle+0x2bb/0x2e0
cpu_startup_entry+0x1d/0x20
start_secondary+0x2a8/0x320
secondary_startup_64+0xa4/0xb0
}
... key at: [<ffffffffa0c0d080>] __key.85462+0x0/0xfffffffffff7df80 [qla2xxx_scst]
... acquired at:
lock_acquire+0xe3/0x200
_raw_spin_lock_irqsave+0x3d/0x60
klist_next+0x43/0x1d0
device_for_each_child+0x96/0x110
scsi_target_block+0x3c/0x40 [scsi_mod]
fc_remote_port_delete+0xe7/0x1c0 [scsi_transport_fc]
qla2x00_mark_device_lost+0xa0b/0xa30 [qla2xxx_scst]
qlt_unreg_sess+0x1c6/0x380 [qla2xxx_scst]
qla24xx_delete_sess_fn+0xe6/0xf0 [qla2xxx_scst]
process_one_work+0x511/0xa80
worker_thread+0x67/0x5b0
kthread+0x1d2/0x1f0
ret_from_fork+0x3a/0x50
the dependencies between the lock to be acquired
and HARDIRQ-irq-unsafe lock:
-> (&(&k->k_lock)->rlock){+.+.} ops: 13831 {
HARDIRQ-ON-W at:
lock_acquire+0xe3/0x200
_raw_spin_lock+0x32/0x50
klist_add_tail+0x33/0xb0
device_add+0x7e1/0xb50
device_create_groups_vargs+0x11c/0x150
device_create_with_groups+0x89/0xb0
vtconsole_class_init+0xb2/0x124
do_one_initcall+0xc5/0x3ce
kernel_init_freeable+0x295/0x32e
kernel_init+0x11/0x11b
ret_from_fork+0x3a/0x50
SOFTIRQ-ON-W at:
lock_acquire+0xe3/0x200
_raw_spin_lock+0x32/0x50
klist_add_tail+0x33/0xb0
device_add+0x7e1/0xb50
device_create_groups_vargs+0x11c/0x150
device_create_with_groups+0x89/0xb0
vtconsole_class_init+0xb2/0x124
do_one_initcall+0xc5/0x3ce
kernel_init_freeable+0x295/0x32e
kernel_init+0x11/0x11b
ret_from_fork+0x3a/0x50
INITIAL USE at:
lock_acquire+0xe3/0x200
_raw_spin_lock+0x32/0x50
klist_add_tail+0x33/0xb0
device_add+0x7e1/0xb50
device_create_groups_vargs+0x11c/0x150
device_create_with_groups+0x89/0xb0
vtconsole_class_init+0xb2/0x124
do_one_initcall+0xc5/0x3ce
kernel_init_freeable+0x295/0x32e
kernel_init+0x11/0x11b
ret_from_fork+0x3a/0x50
}
... key at: [<ffffffff83ed8780>] __key.15491+0x0/0x40
... acquired at:
lock_acquire+0xe3/0x200
_raw_spin_lock_irqsave+0x3d/0x60
klist_next+0x43/0x1d0
device_for_each_child+0x96/0x110
scsi_target_block+0x3c/0x40 [scsi_mod]
fc_remote_port_delete+0xe7/0x1c0 [scsi_transport_fc]
qla2x00_mark_device_lost+0xa0b/0xa30 [qla2xxx_scst]
qlt_unreg_sess+0x1c6/0x380 [qla2xxx_scst]
qla24xx_delete_sess_fn+0xe6/0xf0 [qla2xxx_scst]
process_one_work+0x511/0xa80
worker_thread+0x67/0x5b0
kthread+0x1d2/0x1f0
ret_from_fork+0x3a/0x50
stack backtrace:
CPU: 2 PID: 62 Comm: kworker/2:1 Tainted: G O 5.0.7-dbg+ #8
Hardware name: Bochs Bochs, BIOS Bochs 01/01/2011
Workqueue: qla2xxx_wq qla24xx_delete_sess_fn [qla2xxx_scst]
Call Trace:
dump_stack+0x86/0xca
check_usage.cold.52+0x473/0x563
__lock_acquire+0x11c0/0x23e0
lock_acquire+0xe3/0x200
_raw_spin_lock_irqsave+0x3d/0x60
klist_next+0x43/0x1d0
device_for_each_child+0x96/0x110
scsi_target_block+0x3c/0x40 [scsi_mod]
fc_remote_port_delete+0xe7/0x1c0 [scsi_transport_fc]
qla2x00_mark_device_lost+0xa0b/0xa30 [qla2xxx_scst]
qlt_unreg_sess+0x1c6/0x380 [qla2xxx_scst]
qla24xx_delete_sess_fn+0xe6/0xf0 [qla2xxx_scst]
process_one_work+0x511/0xa80
worker_thread+0x67/0x5b0
kthread+0x1d2/0x1f0
ret_from_fork+0x3a/0x50
Cc: Himanshu Madhani <hmadhani@marvell.com>
Cc: Giridhar Malavali <gmalavali@marvell.com>
Signed-off-by: Bart Van Assche <bvanassche@acm.org>
Acked-by: Himanshu Madhani <hmadhani@marvell.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Acked-by: Daniel Wagner <dwagner@suse.de>
---
drivers/scsi/qla2xxx/qla_target.c | 25 ++++++++-----------------
drivers/scsi/qla2xxx/tcm_qla2xxx.c | 2 --
2 files changed, 8 insertions(+), 19 deletions(-)
--- a/drivers/scsi/qla2xxx/qla_target.c
+++ b/drivers/scsi/qla2xxx/qla_target.c
@@ -682,7 +682,6 @@ done:
void qla24xx_do_nack_work(struct scsi_qla_host *vha, struct qla_work_evt *e)
{
fc_port_t *t;
- unsigned long flags;
switch (e->u.nack.type) {
case SRB_NACK_PRLI:
@@ -695,10 +694,8 @@ void qla24xx_do_nack_work(struct scsi_ql
if (t) {
ql_log(ql_log_info, vha, 0xd034,
"%s create sess success %p", __func__, t);
- spin_lock_irqsave(&vha->hw->tgt.sess_lock, flags);
/* create sess has an extra kref */
vha->hw->tgt.tgt_ops->put_sess(e->u.nack.fcport);
- spin_unlock_irqrestore(&vha->hw->tgt.sess_lock, flags);
}
break;
}
@@ -710,9 +707,6 @@ void qla24xx_delete_sess_fn(struct work_
{
fc_port_t *fcport = container_of(work, struct fc_port, del_work);
struct qla_hw_data *ha = fcport->vha->hw;
- unsigned long flags;
-
- spin_lock_irqsave(&ha->tgt.sess_lock, flags);
if (fcport->se_sess) {
ha->tgt.tgt_ops->shutdown_sess(fcport);
@@ -720,7 +714,6 @@ void qla24xx_delete_sess_fn(struct work_
} else {
qlt_unreg_sess(fcport);
}
- spin_unlock_irqrestore(&ha->tgt.sess_lock, flags);
}
/*
@@ -789,8 +782,9 @@ void qlt_fc_port_added(struct scsi_qla_h
fcport->port_name, sess->loop_id);
sess->local = 0;
}
- ha->tgt.tgt_ops->put_sess(sess);
spin_unlock_irqrestore(&ha->tgt.sess_lock, flags);
+
+ ha->tgt.tgt_ops->put_sess(sess);
}
/*
@@ -4180,9 +4174,7 @@ static void __qlt_do_work(struct qla_tgt
/*
* Drop extra session reference from qlt_handle_cmd_for_atio().
*/
- spin_lock_irqsave(&ha->tgt.sess_lock, flags);
ha->tgt.tgt_ops->put_sess(sess);
- spin_unlock_irqrestore(&ha->tgt.sess_lock, flags);
return;
out_term:
@@ -4199,9 +4191,7 @@ out_term:
percpu_ida_free(&sess->se_sess->sess_tag_pool, cmd->se_cmd.map_tag);
spin_unlock_irqrestore(qpair->qp_lock_ptr, flags);
- spin_lock_irqsave(&ha->tgt.sess_lock, flags);
ha->tgt.tgt_ops->put_sess(sess);
- spin_unlock_irqrestore(&ha->tgt.sess_lock, flags);
}
static void qlt_do_work(struct work_struct *work)
@@ -4409,9 +4399,7 @@ static int qlt_handle_cmd_for_atio(struc
if (!cmd) {
ql_dbg(ql_dbg_io, vha, 0x3062,
"qla_target(%d): Allocation of cmd failed\n", vha->vp_idx);
- spin_lock_irqsave(&ha->tgt.sess_lock, flags);
ha->tgt.tgt_ops->put_sess(sess);
- spin_unlock_irqrestore(&ha->tgt.sess_lock, flags);
return -EBUSY;
}
@@ -6261,17 +6249,19 @@ static void qlt_abort_work(struct qla_tg
}
rc = __qlt_24xx_handle_abts(vha, &prm->abts, sess);
- ha->tgt.tgt_ops->put_sess(sess);
spin_unlock_irqrestore(&ha->tgt.sess_lock, flags2);
+ ha->tgt.tgt_ops->put_sess(sess);
+
if (rc != 0)
goto out_term;
return;
out_term2:
+ spin_unlock_irqrestore(&ha->tgt.sess_lock, flags2);
+
if (sess)
ha->tgt.tgt_ops->put_sess(sess);
- spin_unlock_irqrestore(&ha->tgt.sess_lock, flags2);
out_term:
spin_lock_irqsave(&ha->hardware_lock, flags);
@@ -6329,9 +6319,10 @@ static void qlt_tmr_work(struct qla_tgt
scsilun_to_int((struct scsi_lun *)&a->u.isp24.fcp_cmnd.lun);
rc = qlt_issue_task_mgmt(sess, unpacked_lun, fn, iocb, 0);
- ha->tgt.tgt_ops->put_sess(sess);
spin_unlock_irqrestore(&ha->tgt.sess_lock, flags);
+ ha->tgt.tgt_ops->put_sess(sess);
+
if (rc != 0)
goto out_term;
return;
--- a/drivers/scsi/qla2xxx/tcm_qla2xxx.c
+++ b/drivers/scsi/qla2xxx/tcm_qla2xxx.c
@@ -350,7 +350,6 @@ static void tcm_qla2xxx_put_sess(struct
if (!sess)
return;
- assert_spin_locked(&sess->vha->hw->tgt.sess_lock);
kref_put(&sess->sess_kref, tcm_qla2xxx_release_session);
}
@@ -837,7 +836,6 @@ static void tcm_qla2xxx_clear_nacl_from_
static void tcm_qla2xxx_shutdown_sess(struct fc_port *sess)
{
- assert_spin_locked(&sess->vha->hw->tgt.sess_lock);
target_sess_cmd_list_set_waiting(sess->se_sess);
}