From eddb98ad9364b4e778768785d46cfab04ce52100 Mon Sep 17 00:00:00 2001 From: Damien Le Moal Date: Fri, 20 Feb 2026 13:43:00 +0900 Subject: ata: libata-eh: correctly handle deferred qc timeouts A deferred qc may timeout while waiting for the device queue to drain to be submitted. In such case, since the qc is not active, ata_scsi_cmd_error_handler() ends up calling scsi_eh_finish_cmd(), which frees the qc. But as the port deferred_qc field still references this finished/freed qc, the deferred qc work may eventually attempt to call ata_qc_issue() against this invalid qc, leading to errors such as reported by UBSAN (syzbot run): UBSAN: shift-out-of-bounds in drivers/ata/libata-core.c:5166:24 shift exponent 4210818301 is too large for 64-bit type 'long long unsigned int' ... Call Trace: __dump_stack lib/dump_stack.c:94 [inline] dump_stack_lvl+0x100/0x190 lib/dump_stack.c:120 ubsan_epilogue+0xa/0x30 lib/ubsan.c:233 __ubsan_handle_shift_out_of_bounds+0x279/0x2a0 lib/ubsan.c:494 ata_qc_issue.cold+0x38/0x9f drivers/ata/libata-core.c:5166 ata_scsi_deferred_qc_work+0x154/0x1f0 drivers/ata/libata-scsi.c:1679 process_one_work+0x9d7/0x1920 kernel/workqueue.c:3275 process_scheduled_works kernel/workqueue.c:3358 [inline] worker_thread+0x5da/0xe40 kernel/workqueue.c:3439 kthread+0x370/0x450 kernel/kthread.c:467 ret_from_fork+0x754/0xd80 arch/x86/kernel/process.c:158 ret_from_fork_asm+0x1a/0x30 arch/x86/entry/entry_64.S:245 Fix this by checking if the qc of a timed out SCSI command is a deferred one, and in such case, clear the port deferred_qc field and finish the SCSI command with DID_TIME_OUT. Reported-by: syzbot+1f77b8ca15336fff21ff@syzkaller.appspotmail.com Fixes: 0ea84089dbf6 ("ata: libata-scsi: avoid Non-NCQ command starvation") Signed-off-by: Damien Le Moal Reviewed-by: Hannes Reinecke Reviewed-by: Igor Pylypiv --- drivers/ata/libata-eh.c | 22 +++++++++++++++++++--- 1 file changed, 19 insertions(+), 3 deletions(-) diff --git a/drivers/ata/libata-eh.c b/drivers/ata/libata-eh.c index 72a22b6c9682..b373cceb95d2 100644 --- a/drivers/ata/libata-eh.c +++ b/drivers/ata/libata-eh.c @@ -640,12 +640,28 @@ void ata_scsi_cmd_error_handler(struct Scsi_Host *host, struct ata_port *ap, set_host_byte(scmd, DID_OK); ata_qc_for_each_raw(ap, qc, i) { - if (qc->flags & ATA_QCFLAG_ACTIVE && - qc->scsicmd == scmd) + if (qc->scsicmd != scmd) + continue; + if ((qc->flags & ATA_QCFLAG_ACTIVE) || + qc == ap->deferred_qc) break; } - if (i < ATA_MAX_QUEUE) { + if (qc == ap->deferred_qc) { + /* + * This is a deferred command that timed out while + * waiting for the command queue to drain. Since the qc + * is not active yet (deferred_qc is still set, so the + * deferred qc work has not issued the command yet), + * simply signal the timeout by finishing the SCSI + * command and clear the deferred qc to prevent the + * deferred qc work from issuing this qc. + */ + WARN_ON_ONCE(qc->flags & ATA_QCFLAG_ACTIVE); + ap->deferred_qc = NULL; + set_host_byte(scmd, DID_TIME_OUT); + scsi_eh_finish_cmd(scmd, &ap->eh_done_q); + } else if (i < ATA_MAX_QUEUE) { /* the scmd has an associated qc */ if (!(qc->flags & ATA_QCFLAG_EH)) { /* which hasn't failed yet, timeout */ -- cgit v1.2.3 From 55db009926634b20955bd8abbee921adbc8d2cb4 Mon Sep 17 00:00:00 2001 From: Damien Le Moal Date: Fri, 20 Feb 2026 12:09:12 +0900 Subject: ata: libata-core: fix cancellation of a port deferred qc work cancel_work_sync() is a sleeping function so it cannot be called with the spin lock of a port being held. Move the call to this function in ata_port_detach() after EH completes, with the port lock released, together with other work cancellation calls. Fixes: 0ea84089dbf6 ("ata: libata-scsi: avoid Non-NCQ command starvation") Signed-off-by: Damien Le Moal Reviewed-by: Hannes Reinecke Reviewed-by: Igor Pylypiv --- drivers/ata/libata-core.c | 8 +++----- 1 file changed, 3 insertions(+), 5 deletions(-) diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c index 11909417f017..ccbf320524da 100644 --- a/drivers/ata/libata-core.c +++ b/drivers/ata/libata-core.c @@ -6269,10 +6269,6 @@ static void ata_port_detach(struct ata_port *ap) } } - /* Make sure the deferred qc work finished. */ - cancel_work_sync(&ap->deferred_qc_work); - WARN_ON(ap->deferred_qc); - /* Tell EH to disable all devices */ ap->pflags |= ATA_PFLAG_UNLOADING; ata_port_schedule_eh(ap); @@ -6283,9 +6279,11 @@ static void ata_port_detach(struct ata_port *ap) /* wait till EH commits suicide */ ata_port_wait_eh(ap); - /* it better be dead now */ + /* It better be dead now and not have any remaining deferred qc. */ WARN_ON(!(ap->pflags & ATA_PFLAG_UNLOADED)); + WARN_ON(ap->deferred_qc); + cancel_work_sync(&ap->deferred_qc_work); cancel_delayed_work_sync(&ap->hotplug_task); cancel_delayed_work_sync(&ap->scsi_rescan_task); -- cgit v1.2.3