From: Nicholas Bellinger nab@linux-iscsi.org
This patch fixes a bug associated with iscsit_reset_np_thread() that can occur during parallel configfs rmdir of a single iscsi_np used across multiple iscsi-target instances, that would result in hung task(s) similar to below where configfs rmdir process context was blocked indefinately waiting for iscsi_np->np_restart_comp to finish:
[ 6726.112076] INFO: task dcp_proxy_node_:15550 blocked for more than 120 seconds. [ 6726.119440] Tainted: G W O 4.1.26-3321 #2 [ 6726.125045] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. [ 6726.132927] dcp_proxy_node_ D ffff8803f202bc88 0 15550 1 0x00000000 [ 6726.140058] ffff8803f202bc88 ffff88085c64d960 ffff88083b3b1ad0 ffff88087fffeb08 [ 6726.147593] ffff8803f202c000 7fffffffffffffff ffff88083f459c28 ffff88083b3b1ad0 [ 6726.155132] ffff88035373c100 ffff8803f202bca8 ffffffff8168ced2 ffff8803f202bcb8 [ 6726.162667] Call Trace: [ 6726.165150] [<ffffffff8168ced2>] schedule+0x32/0x80 [ 6726.170156] [<ffffffff8168f5b4>] schedule_timeout+0x214/0x290 [ 6726.176030] [<ffffffff810caef2>] ? __send_signal+0x52/0x4a0 [ 6726.181728] [<ffffffff8168d7d6>] wait_for_completion+0x96/0x100 [ 6726.187774] [<ffffffff810e7c80>] ? wake_up_state+0x10/0x10 [ 6726.193395] [<ffffffffa035d6e2>] iscsit_reset_np_thread+0x62/0xe0 [iscsi_target_mod] [ 6726.201278] [<ffffffffa0355d86>] iscsit_tpg_disable_portal_group+0x96/0x190 [iscsi_target_mod] [ 6726.210033] [<ffffffffa0363f7f>] lio_target_tpg_store_enable+0x4f/0xc0 [iscsi_target_mod] [ 6726.218351] [<ffffffff81260c5a>] configfs_write_file+0xaa/0x110 [ 6726.224392] [<ffffffff811ea364>] vfs_write+0xa4/0x1b0 [ 6726.229576] [<ffffffff811eb111>] SyS_write+0x41/0xb0 [ 6726.234659] [<ffffffff8169042e>] system_call_fastpath+0x12/0x71
It would happen because each iscsit_reset_np_thread() sets state to ISCSI_NP_THREAD_RESET, sends SIGINT, and then blocks waiting for completion on iscsi_np->np_restart_comp.
However, if iscsi_np was active processing a login request and more than a single iscsit_reset_np_thread() caller to the same iscsi_np was blocked on iscsi_np->np_restart_comp, iscsi_np kthread process context in __iscsi_target_login_thread() would flush pending signals and only perform a single completion of np->np_restart_comp before going back to sleep within transport specific iscsit_transport->iscsi_accept_np code.
To address this bug, add a iscsi_np->np_reset_count and update __iscsi_target_login_thread() to keep completing np->np_restart_comp until ->np_reset_count has reached zero.
Reported-by: Gary Guo ghg@datera.io Tested-by: Gary Guo ghg@datera.io Cc: Mike Christie mchristi@redhat.com Cc: Hannes Reinecke hare@suse.de Cc: stable@vger.kernel.org # 3.10+ Signed-off-by: Nicholas Bellinger nab@linux-iscsi.org --- drivers/target/iscsi/iscsi_target.c | 1 + drivers/target/iscsi/iscsi_target_core.h | 1 + drivers/target/iscsi/iscsi_target_login.c | 7 +++++-- include/target/iscsi/iscsi_target_core.h | 1 + 4 files changed, 8 insertions(+), 2 deletions(-)
diff --git a/drivers/target/iscsi/iscsi_target.c b/drivers/target/iscsi/iscsi_target.c index 801369f..2fc6b49 100644 --- a/drivers/target/iscsi/iscsi_target.c +++ b/drivers/target/iscsi/iscsi_target.c @@ -428,6 +428,7 @@ int iscsit_reset_np_thread( return 0; } np->np_thread_state = ISCSI_NP_THREAD_RESET; + atomic_inc(&np->np_reset_count);
if (np->np_thread) { spin_unlock_bh(&np->np_thread_lock); diff --git a/drivers/target/iscsi/iscsi_target_core.h b/drivers/target/iscsi/iscsi_target_core.h index 1863de2..bf3da8e 100644 --- a/drivers/target/iscsi/iscsi_target_core.h +++ b/drivers/target/iscsi/iscsi_target_core.h @@ -783,6 +783,7 @@ struct iscsi_np { int np_sock_type; enum np_thread_state_table np_thread_state; bool enabled; + atomic_t np_reset_count; enum iscsi_timer_flags_table np_login_timer_flags; u32 np_exports; enum np_flags_table np_flags; diff --git a/drivers/target/iscsi/iscsi_target_login.c b/drivers/target/iscsi/iscsi_target_login.c index 4608d8d..540af1b 100644 --- a/drivers/target/iscsi/iscsi_target_login.c +++ b/drivers/target/iscsi/iscsi_target_login.c @@ -1275,9 +1275,11 @@ static int __iscsi_target_login_thread(struct iscsi_np *np) flush_signals(current);
spin_lock_bh(&np->np_thread_lock); - if (np->np_thread_state == ISCSI_NP_THREAD_RESET) { + if (atomic_dec_if_positive(&np->np_reset_count) >= 0) { np->np_thread_state = ISCSI_NP_THREAD_ACTIVE; + spin_unlock_bh(&np->np_thread_lock); complete(&np->np_restart_comp); + return 1; } else if (np->np_thread_state == ISCSI_NP_THREAD_SHUTDOWN) { spin_unlock_bh(&np->np_thread_lock); goto exit; @@ -1310,7 +1312,8 @@ static int __iscsi_target_login_thread(struct iscsi_np *np) goto exit; } else if (rc < 0) { spin_lock_bh(&np->np_thread_lock); - if (np->np_thread_state == ISCSI_NP_THREAD_RESET) { + if (atomic_dec_if_positive(&np->np_reset_count) >= 0) { + np->np_thread_state = ISCSI_NP_THREAD_ACTIVE; spin_unlock_bh(&np->np_thread_lock); complete(&np->np_restart_comp); iscsit_put_transport(conn->conn_transport); diff --git a/include/target/iscsi/iscsi_target_core.h b/include/target/iscsi/iscsi_target_core.h index 7bd03f8..e365ed9 100644 --- a/include/target/iscsi/iscsi_target_core.h +++ b/include/target/iscsi/iscsi_target_core.h @@ -784,6 +784,7 @@ struct iscsi_np { int np_sock_type; enum np_thread_state_table np_thread_state; bool enabled; + atomic_t np_reset_count; enum iscsi_timer_flags_table np_login_timer_flags; u32 np_exports; enum np_flags_table np_flags;