target: Fix NULL dereference during LUN lookup + active I/O shutdown
When transport_clear_lun_ref() is shutting down a se_lun via
configfs with new I/O in-flight, it's possible to trigger a
NULL pointer dereference in transport_lookup_cmd_lun() due
to the fact percpu_ref_get() doesn't do any __PERCPU_REF_DEAD
checking before incrementing lun->lun_ref.count after
lun->lun_ref has switched to atomic_t mode.
This results in a NULL pointer dereference as LUN shutdown
code in core_tpg_remove_lun() continues running after the
existing ->release() -> core_tpg_lun_ref_release() callback
completes, and clears the RCU protected se_lun->lun_se_dev
pointer.
During the OOPs, the state of lun->lun_ref in the process
which triggered the NULL pointer dereference looks like
the following on v4.1.y stable code:
struct se_lun {
lun_link_magic = 4294932337,
lun_status = TRANSPORT_LUN_STATUS_FREE,
.....
lun_se_dev = 0x0,
lun_sep = 0x0,
.....
lun_ref = {
count = {
counter = 1
},
percpu_count_ptr = 3,
release = 0xffffffffa02fa1e0 <core_tpg_lun_ref_release>,
confirm_switch = 0x0,
force_atomic = false,
rcu = {
next = 0xffff88154fa1a5d0,
func = 0xffffffff8137c4c0 <percpu_ref_switch_to_atomic_rcu>
}
}
}
To address this bug, use percpu_ref_tryget_live() to ensure
once __PERCPU_REF_DEAD is visable on all CPUs and ->lun_ref
has switched to atomic_t, all new I/Os will fail to obtain
a new lun->lun_ref reference.
Also use an explicit percpu_ref_kill_and_confirm() callback
to block on ->lun_ref_comp to allow the first stage and
associated RCU grace period to complete, and then block on
->lun_ref_shutdown waiting for the final percpu_ref_put()
to drop the last reference via transport_lun_remove_cmd()
before continuing with core_tpg_remove_lun() shutdown.
Reported-by: Rob Millner <rlm@daterainc.com>
Tested-by: Rob Millner <rlm@daterainc.com>
Cc: Rob Millner <rlm@daterainc.com>
Tested-by: Vaibhav Tandon <vst@datera.io>
Cc: Vaibhav Tandon <vst@datera.io>
Tested-by: Bryant G. Ly <bryantly@linux.vnet.ibm.com>
Cc: <stable@vger.kernel.org> # v3.14+
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
diff --git a/drivers/target/target_core_device.c b/drivers/target/target_core_device.c
index cb7047d..c754ae3 100644
--- a/drivers/target/target_core_device.c
+++ b/drivers/target/target_core_device.c
@@ -78,12 +78,16 @@ transport_lookup_cmd_lun(struct se_cmd *se_cmd, u64 unpacked_lun)
&deve->read_bytes);
se_lun = rcu_dereference(deve->se_lun);
+
+ if (!percpu_ref_tryget_live(&se_lun->lun_ref)) {
+ se_lun = NULL;
+ goto out_unlock;
+ }
+
se_cmd->se_lun = rcu_dereference(deve->se_lun);
se_cmd->pr_res_key = deve->pr_res_key;
se_cmd->orig_fe_lun = unpacked_lun;
se_cmd->se_cmd_flags |= SCF_SE_LUN_CMD;
-
- percpu_ref_get(&se_lun->lun_ref);
se_cmd->lun_ref_active = true;
if ((se_cmd->data_direction == DMA_TO_DEVICE) &&
@@ -97,6 +101,7 @@ transport_lookup_cmd_lun(struct se_cmd *se_cmd, u64 unpacked_lun)
goto ref_dev;
}
}
+out_unlock:
rcu_read_unlock();
if (!se_lun) {
@@ -815,6 +820,7 @@ struct se_device *target_alloc_device(struct se_hba *hba, const char *name)
xcopy_lun = &dev->xcopy_lun;
rcu_assign_pointer(xcopy_lun->lun_se_dev, dev);
init_completion(&xcopy_lun->lun_ref_comp);
+ init_completion(&xcopy_lun->lun_shutdown_comp);
INIT_LIST_HEAD(&xcopy_lun->lun_deve_list);
INIT_LIST_HEAD(&xcopy_lun->lun_dev_link);
mutex_init(&xcopy_lun->lun_tg_pt_md_mutex);
