forked from Minki/linux
scsi: fcoe: clear FC_RP_STARTED flags when receiving a LOGO
When receiving a LOGO request we forget to clear the FC_RP_STARTED flag before starting the rport delete routine. As the started flag was not cleared, we're not deleting the rport but waiting for a restart and thus are keeping the reference count of the rdata object at 1. This leads to the following kmemleak report: unreferenced object 0xffff88006542aa00 (size 512): comm "kworker/0:2", pid 24, jiffies 4294899222 (age 226.880s) hex dump (first 32 bytes): 68 96 fe 65 00 88 ff ff 00 00 00 00 00 00 00 00 h..e............ 01 00 00 00 08 00 00 00 02 c5 45 24 ac b8 00 10 ..........E$.... backtrace: [<(____ptrval____)>] fcoe_ctlr_vn_add.isra.5+0x7f/0x770 [libfcoe] [<(____ptrval____)>] fcoe_ctlr_vn_recv+0x12af/0x27f0 [libfcoe] [<(____ptrval____)>] fcoe_ctlr_recv_work+0xd01/0x32f0 [libfcoe] [<(____ptrval____)>] process_one_work+0x7ff/0x1420 [<(____ptrval____)>] worker_thread+0x87/0xef0 [<(____ptrval____)>] kthread+0x2db/0x390 [<(____ptrval____)>] ret_from_fork+0x35/0x40 [<(____ptrval____)>] 0xffffffffffffffff Signed-off-by: Johannes Thumshirn <jthumshirn@suse.de> Reported-by: ard <ard@kwaak.net> Reviewed-by: Hannes Reinecke <hare@suse.com> Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
This commit is contained in:
parent
63d0e3dffd
commit
1550ec458e
@ -2164,6 +2164,7 @@ static void fc_rport_recv_logo_req(struct fc_lport *lport, struct fc_frame *fp)
|
||||
FC_RPORT_DBG(rdata, "Received LOGO request while in state %s\n",
|
||||
fc_rport_state(rdata));
|
||||
|
||||
rdata->flags &= ~FC_RP_STARTED;
|
||||
fc_rport_enter_delete(rdata, RPORT_EV_STOP);
|
||||
mutex_unlock(&rdata->rp_mutex);
|
||||
kref_put(&rdata->kref, fc_rport_destroy);
|
||||
|
Loading…
Reference in New Issue
Block a user