From: Nicholas Bellinger nab@linux-iscsi.org
commit 49cb77e297dc611a1b795cfeb79452b3002bd331 upstream.
This patch closes a race between se_lun deletion during configfs unlink in target_fabric_port_unlink() -> core_dev_del_lun() -> core_tpg_remove_lun(), when transport_clear_lun_ref() blocks waiting for percpu_ref RCU grace period to finish, but a new NodeACL mappedlun is added before the RCU grace period has completed.
This can happen in target_fabric_mappedlun_link() because it only checks for se_lun->lun_se_dev, which is not cleared until after transport_clear_lun_ref() percpu_ref RCU grace period finishes.
This bug originally manifested as NULL pointer dereference OOPsen in target_stat_scsi_att_intr_port_show_attr_dev() on v4.1.y code, because it dereferences lun->lun_se_dev without a explicit NULL pointer check.
In post v4.1 code with target-core RCU conversion, the code in target_stat_scsi_att_intr_port_show_attr_dev() no longer uses se_lun->lun_se_dev, but the same race still exists.
To address the bug, go ahead and set se_lun>lun_shutdown as early as possible in core_tpg_remove_lun(), and ensure new NodeACL mappedlun creation in target_fabric_mappedlun_link() fails during se_lun shutdown.
Reported-by: James Shen jcs@datera.io Cc: James Shen jcs@datera.io Tested-by: James Shen jcs@datera.io Signed-off-by: Nicholas Bellinger nab@linux-iscsi.org --- drivers/target/target_core_fabric_configfs.c | 5 +++++ drivers/target/target_core_tpg.c | 3 +++ include/target/target_core_base.h | 1 + 3 files changed, 9 insertions(+)
diff --git a/drivers/target/target_core_fabric_configfs.c b/drivers/target/target_core_fabric_configfs.c index 1f7886b..65e0a06 100644 --- a/drivers/target/target_core_fabric_configfs.c +++ b/drivers/target/target_core_fabric_configfs.c @@ -98,6 +98,11 @@ static int target_fabric_mappedlun_link( "_tpg does not exist\n"); return -EINVAL; } + if (lun->lun_shutdown) { + pr_err("Unable to create mappedlun symlink because" + " lun->lun_shutdown=true\n"); + return -EINVAL; + } se_tpg = lun->lun_sep->sep_tpg;
nacl_ci = &lun_acl_ci->ci_parent->ci_group->cg_item; diff --git a/drivers/target/target_core_tpg.c b/drivers/target/target_core_tpg.c index 6c350f0..03f43ce 100644 --- a/drivers/target/target_core_tpg.c +++ b/drivers/target/target_core_tpg.c @@ -883,6 +883,8 @@ void core_tpg_remove_lun( struct se_portal_group *tpg, struct se_lun *lun) { + lun->lun_shutdown = true; + core_clear_lun_from_tpg(lun, tpg); transport_clear_lun_ref(lun);
@@ -890,6 +892,7 @@ void core_tpg_remove_lun(
spin_lock(&tpg->tpg_lun_lock); lun->lun_status = TRANSPORT_LUN_STATUS_FREE; + lun->lun_shutdown = false; spin_unlock(&tpg->tpg_lun_lock);
percpu_ref_exit(&lun->lun_ref); diff --git a/include/target/target_core_base.h b/include/target/target_core_base.h index c978ad2..ad3c146 100644 --- a/include/target/target_core_base.h +++ b/include/target/target_core_base.h @@ -725,6 +725,7 @@ struct se_lun { u32 lun_access; u32 lun_flags; u32 unpacked_lun; + bool lun_shutdown; atomic_t lun_acl_count; spinlock_t lun_acl_lock; spinlock_t lun_sep_lock;