> -----Original Message----- > From: i...@itu.dk [mailto:i...@itu.dk] > Sent: Monday, October 17, 2016 1:00 PM > To: Jiri Kosina > Cc: Kashyap Desai; Sumit Saxena; Uday Lingala; James E.J. Bottomley; Martin K. > Petersen; megaraidlinux....@avagotech.com; linux-scsi@vger.kernel.org; Iago > Abal > Subject: [PATCH] Fix: scsi: megaraid: reduce the scope of pending-list lock to > avoid double lock > > From: Iago Abal <m...@iagoabal.eu> > > The EBA code analyzer (https://github.com/models-team/eba) reported the > following double lock: > > 1. In function `megaraid_reset_handler' at 2571; > 2. take `&adapter->pend_list_lock' for the first time at 2602: > > // FIRST > spin_lock_irqsave(PENDING_LIST_LOCK(adapter), flags); > > 3. enter the `list_for_each_entry_safe' loop at 2603; > 4. call `megaraid_mbox_mm_done' at 2616; > 5. call `megaraid_mbox_runpendq' at 3782; > 6. take `&adapter->pend_list_lock' for the second time at 1892: > > // SECOND: DOUBLE LOCK !!! > spin_lock_irqsave(PENDING_LIST_LOCK(adapter), flags); > > From my shallow understanding of the code (so please review carefully), I think > that it is not necessary to hold `PENDING_LIST_LOCK(adapter)' while executing > the body of the `list_for_each_entry_safe' loop. I assume this because both > `megaraid_mbox_mm_done' and `megaraid_dealloc_scb' are called from > several places where, as far as I can tell, this lock is not hold. In fact, as reported > by EBA, at some point `megaraid_mbox_mm_done' will acquire this lock again. > > Fixes: c005fb4fb2d2 ("[SCSI] megaraid_{mm,mbox}: fix a bug in reset handler") > Signed-off-by: Iago Abal <m...@iagoabal.eu> > --- > drivers/scsi/megaraid/megaraid_mbox.c | 2 ++ > 1 file changed, 2 insertions(+) > > diff --git a/drivers/scsi/megaraid/megaraid_mbox.c > b/drivers/scsi/megaraid/megaraid_mbox.c > index f0987f2..7f11898 100644 > --- a/drivers/scsi/megaraid/megaraid_mbox.c > +++ b/drivers/scsi/megaraid/megaraid_mbox.c > @@ -2603,6 +2603,7 @@ static DEF_SCSI_QCMD(megaraid_queue_command) > list_for_each_entry_safe(scb, tmp, &adapter->pend_list, list) { > list_del_init(&scb->list); // from pending list > > + spin_unlock_irqrestore(PENDING_LIST_LOCK(adapter), flags); > if (scb->sno >= MBOX_MAX_SCSI_CMDS) { > con_log(CL_ANN, (KERN_WARNING > "megaraid: IOCTL packet with %d[%d:%d] being > reset\n", @@ -2630,6 +2631,7 @@ static > DEF_SCSI_QCMD(megaraid_queue_command) > > megaraid_dealloc_scb(adapter, scb); > } > + spin_lock_irqsave(PENDING_LIST_LOCK(adapter), flags); > } > spin_unlock_irqrestore(PENDING_LIST_LOCK(adapter), flags);
Looks correct, but please note that MEGARAID_MAILBOX and MEGARAID_MM is not supported by LSI/ Broadcom. We will revert back to you shortly if we can safely remove those two modules. . > > -- > 1.9.1 -- To unsubscribe from this list: send the line "unsubscribe linux-scsi" in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html
