IB/iser: Fix connection teardown race condition

Under heavy iser target(scst) start/stop stress during login/logout
on iser intitiator side happened trace call provided below.

The function iscsi_iser_slave_alloc iser_conn pointer could be NULL,
due to the fact that function iscsi_iser_conn_stop can be called before
and free iser connection. Let's protect that flow by introducing global mutex.

BUG: unable to handle kernel paging request at 0000000000001018
IP: [<ffffffffc0426f7e>] iscsi_iser_slave_alloc+0x1e/0x50 [ib_iser]
Call Trace:
? scsi_alloc_sdev+0x242/0x300
scsi_probe_and_add_lun+0x9e1/0xea0
? kfree_const+0x21/0x30
? kobject_set_name_vargs+0x76/0x90
? __pm_runtime_resume+0x5b/0x70
__scsi_scan_target+0xf6/0x250
scsi_scan_target+0xea/0x100
iscsi_user_scan_session.part.13+0x101/0x130 [scsi_transport_iscsi]
? iscsi_user_scan_session.part.13+0x130/0x130 [scsi_transport_iscsi]
iscsi_user_scan_session+0x1e/0x30 [scsi_transport_iscsi]
device_for_each_child+0x50/0x90
iscsi_user_scan+0x44/0x60 [scsi_transport_iscsi]
store_scan+0xa8/0x100
? common_file_perm+0x5d/0x1c0
dev_attr_store+0x18/0x30
sysfs_kf_write+0x37/0x40
kernfs_fop_write+0x12c/0x1c0
__vfs_write+0x18/0x40
vfs_write+0xb5/0x1a0
SyS_write+0x55/0xc0

Fixes: 318d311e8f01 ("iser: Accept arbitrary sg lists mapping if the device supports it")
Cc: <stable@vger.kernel.org> # v4.5+
Signed-off-by: Vladimir Neyelov <vladimirn@mellanox.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
Reviewed-by: Sagi Grimberg <sagi@grimbeg.me>
Signed-off-by: Doug Ledford <dledford@redhat.com>

diff --git a/drivers/infiniband/ulp/iser/iscsi_iser.c b/drivers/infiniband/ulp/iser/iscsi_iser.c
index 5a887efb4bdf1b6405d3fc4342918084ae420b57..37b33d708c2dd5aecfa9bcc0328fb60876e9c310 100644 (file)
--- a/drivers/infiniband/ulp/iser/iscsi_iser.c
+++ b/drivers/infiniband/ulp/iser/iscsi_iser.c
@@ -83,6 +83,7 @@ static struct scsi_host_template iscsi_iser_sht;
 static struct iscsi_transport iscsi_iser_transport;
 static struct scsi_transport_template *iscsi_iser_scsi_transport;
 static struct workqueue_struct *release_wq;
+static DEFINE_MUTEX(unbind_iser_conn_mutex);
 struct iser_global ig;
 
 int iser_debug_level = 0;
@@ -550,12 +551,14 @@ iscsi_iser_conn_stop(struct iscsi_cls_conn *cls_conn, int flag)
         */
        if (iser_conn) {
                mutex_lock(&iser_conn->state_mutex);
+               mutex_lock(&unbind_iser_conn_mutex);
                iser_conn_terminate(iser_conn);
                iscsi_conn_stop(cls_conn, flag);
 
                /* unbind */
                iser_conn->iscsi_conn = NULL;
                conn->dd_data = NULL;
+               mutex_unlock(&unbind_iser_conn_mutex);
 
                complete(&iser_conn->stop_completion);
                mutex_unlock(&iser_conn->state_mutex);
@@ -977,13 +980,21 @@ static int iscsi_iser_slave_alloc(struct scsi_device *sdev)
        struct iser_conn *iser_conn;
        struct ib_device *ib_dev;
 
+       mutex_lock(&unbind_iser_conn_mutex);
+
        session = starget_to_session(scsi_target(sdev))->dd_data;
        iser_conn = session->leadconn->dd_data;
+       if (!iser_conn) {
+               mutex_unlock(&unbind_iser_conn_mutex);
+               return -ENOTCONN;
+       }
        ib_dev = iser_conn->ib_conn.device->ib_device;
 
        if (!(ib_dev->attrs.device_cap_flags & IB_DEVICE_SG_GAPS_REG))
                blk_queue_virt_boundary(sdev->request_queue, ~MASK_4K);
 
+       mutex_unlock(&unbind_iser_conn_mutex);
+
        return 0;
 }