From 6dfe4344c168c6ca20fe7640649aacfcefcccb26 Mon Sep 17 00:00:00 2001 From: Quinn Tran Date: Fri, 14 Jul 2023 12:30:55 +0530 Subject: scsi: qla2xxx: Fix deletion race condition System crash when using debug kernel due to link list corruption. The cause of the link list corruption is due to session deletion was allowed to queue up twice. Here's the internal trace that show the same port was allowed to double queue for deletion on different cpu. 20808683956 015 qla2xxx [0000:13:00.1]-e801:4: Scheduling sess ffff93ebf9306800 for deletion 50:06:0e:80:12:48:ff:50 fc4_type 1 20808683957 027 qla2xxx [0000:13:00.1]-e801:4: Scheduling sess ffff93ebf9306800 for deletion 50:06:0e:80:12:48:ff:50 fc4_type 1 Move the clearing/setting of deleted flag lock. Cc: stable@vger.kernel.org Fixes: 726b85487067 ("qla2xxx: Add framework for async fabric discovery") Signed-off-by: Quinn Tran Signed-off-by: Nilesh Javali Link: https://lore.kernel.org/r/20230714070104.40052-2-njavali@marvell.com Reviewed-by: Himanshu Madhani Signed-off-by: Martin K. Petersen --- drivers/scsi/qla2xxx/qla_init.c | 16 ++++++++++++++-- drivers/scsi/qla2xxx/qla_target.c | 14 +++++++------- 2 files changed, 21 insertions(+), 9 deletions(-) diff --git a/drivers/scsi/qla2xxx/qla_init.c b/drivers/scsi/qla2xxx/qla_init.c index c3dd8dd4f734..5c2a646265e4 100644 --- a/drivers/scsi/qla2xxx/qla_init.c +++ b/drivers/scsi/qla2xxx/qla_init.c @@ -508,6 +508,7 @@ static void qla24xx_handle_adisc_event(scsi_qla_host_t *vha, struct event_arg *ea) { struct fc_port *fcport = ea->fcport; + unsigned long flags; ql_dbg(ql_dbg_disc, vha, 0x20d2, "%s %8phC DS %d LS %d rc %d login %d|%d rscn %d|%d lid %d\n", @@ -522,9 +523,15 @@ void qla24xx_handle_adisc_event(scsi_qla_host_t *vha, struct event_arg *ea) ql_dbg(ql_dbg_disc, vha, 0x2066, "%s %8phC: adisc fail: post delete\n", __func__, ea->fcport->port_name); + + spin_lock_irqsave(&vha->work_lock, flags); /* deleted = 0 & logout_on_delete = force fw cleanup */ - fcport->deleted = 0; + if (fcport->deleted == QLA_SESS_DELETED) + fcport->deleted = 0; + fcport->logout_on_delete = 1; + spin_unlock_irqrestore(&vha->work_lock, flags); + qlt_schedule_sess_for_deletion(ea->fcport); return; } @@ -1446,7 +1453,6 @@ void __qla24xx_handle_gpdb_event(scsi_qla_host_t *vha, struct event_arg *ea) spin_lock_irqsave(&vha->hw->tgt.sess_lock, flags); ea->fcport->login_gen++; - ea->fcport->deleted = 0; ea->fcport->logout_on_delete = 1; if (!ea->fcport->login_succ && !IS_SW_RESV_ADDR(ea->fcport->d_id)) { @@ -6090,6 +6096,8 @@ qla2x00_reg_remote_port(scsi_qla_host_t *vha, fc_port_t *fcport) void qla2x00_update_fcport(scsi_qla_host_t *vha, fc_port_t *fcport) { + unsigned long flags; + if (IS_SW_RESV_ADDR(fcport->d_id)) return; @@ -6099,7 +6107,11 @@ qla2x00_update_fcport(scsi_qla_host_t *vha, fc_port_t *fcport) qla2x00_set_fcport_disc_state(fcport, DSC_UPD_FCPORT); fcport->login_retry = vha->hw->login_retry_count; fcport->flags &= ~(FCF_LOGIN_NEEDED | FCF_ASYNC_SENT); + + spin_lock_irqsave(&vha->work_lock, flags); fcport->deleted = 0; + spin_unlock_irqrestore(&vha->work_lock, flags); + if (vha->hw->current_topology == ISP_CFG_NL) fcport->logout_on_delete = 0; else diff --git a/drivers/scsi/qla2xxx/qla_target.c b/drivers/scsi/qla2xxx/qla_target.c index 5258b07687a9..2b815a9928ea 100644 --- a/drivers/scsi/qla2xxx/qla_target.c +++ b/drivers/scsi/qla2xxx/qla_target.c @@ -1068,10 +1068,6 @@ void qlt_free_session_done(struct work_struct *work) (struct imm_ntfy_from_isp *)sess->iocb, SRB_NACK_LOGO); } - spin_lock_irqsave(&vha->work_lock, flags); - sess->flags &= ~FCF_ASYNC_SENT; - spin_unlock_irqrestore(&vha->work_lock, flags); - spin_lock_irqsave(&ha->tgt.sess_lock, flags); if (sess->se_sess) { sess->se_sess = NULL; @@ -1081,7 +1077,6 @@ void qlt_free_session_done(struct work_struct *work) qla2x00_set_fcport_disc_state(sess, DSC_DELETED); sess->fw_login_state = DSC_LS_PORT_UNAVAIL; - sess->deleted = QLA_SESS_DELETED; if (sess->login_succ && !IS_SW_RESV_ADDR(sess->d_id)) { vha->fcport_count--; @@ -1133,10 +1128,15 @@ void qlt_free_session_done(struct work_struct *work) sess->explicit_logout = 0; spin_unlock_irqrestore(&ha->tgt.sess_lock, flags); - sess->free_pending = 0; qla2x00_dfs_remove_rport(vha, sess); + spin_lock_irqsave(&vha->work_lock, flags); + sess->flags &= ~FCF_ASYNC_SENT; + sess->deleted = QLA_SESS_DELETED; + sess->free_pending = 0; + spin_unlock_irqrestore(&vha->work_lock, flags); + ql_dbg(ql_dbg_disc, vha, 0xf001, "Unregistration of sess %p %8phC finished fcp_cnt %d\n", sess, sess->port_name, vha->fcport_count); @@ -1185,12 +1185,12 @@ void qlt_unreg_sess(struct fc_port *sess) * management from being sent. */ sess->flags |= FCF_ASYNC_SENT; + sess->deleted = QLA_SESS_DELETION_IN_PROGRESS; spin_unlock_irqrestore(&sess->vha->work_lock, flags); if (sess->se_sess) vha->hw->tgt.tgt_ops->clear_nacl_from_fcport_map(sess); - sess->deleted = QLA_SESS_DELETION_IN_PROGRESS; qla2x00_set_fcport_disc_state(sess, DSC_DELETE_PEND); sess->last_rscn_gen = sess->rscn_gen; sess->last_login_gen = sess->login_gen; -- cgit From efa74a62aaa2429c04fe6cb277b3bf6739747d86 Mon Sep 17 00:00:00 2001 From: Quinn Tran Date: Fri, 14 Jul 2023 12:30:56 +0530 Subject: scsi: qla2xxx: Adjust IOCB resource on qpair create During NVMe queue creation, a new qpair is created. FW resource limit needs to be re-adjusted to take into account the new qpair. Otherwise, NVMe command can not go through. This issue was discovered while testing/forcing FW execution to fail at load time. Add call to readjust IOCB and exchange limit. In addition, get FW state command and require FW to be running. Otherwise, error is generated. Cc: stable@vger.kernel.org Signed-off-by: Quinn Tran Signed-off-by: Nilesh Javali Link: https://lore.kernel.org/r/20230714070104.40052-3-njavali@marvell.com Reviewed-by: Himanshu Madhani Signed-off-by: Martin K. Petersen --- drivers/scsi/qla2xxx/qla_gbl.h | 1 + drivers/scsi/qla2xxx/qla_init.c | 52 ++++++++++++++++++++++++++--------------- drivers/scsi/qla2xxx/qla_mbx.c | 3 +++ drivers/scsi/qla2xxx/qla_nvme.c | 1 + 4 files changed, 38 insertions(+), 19 deletions(-) diff --git a/drivers/scsi/qla2xxx/qla_gbl.h b/drivers/scsi/qla2xxx/qla_gbl.h index ba7831f24734..33fba9d62969 100644 --- a/drivers/scsi/qla2xxx/qla_gbl.h +++ b/drivers/scsi/qla2xxx/qla_gbl.h @@ -143,6 +143,7 @@ void qla_edif_sess_down(struct scsi_qla_host *vha, struct fc_port *sess); void qla_edif_clear_appdata(struct scsi_qla_host *vha, struct fc_port *fcport); const char *sc_to_str(uint16_t cmd); +void qla_adjust_iocb_limit(scsi_qla_host_t *vha); /* * Global Data in qla_os.c source file. diff --git a/drivers/scsi/qla2xxx/qla_init.c b/drivers/scsi/qla2xxx/qla_init.c index 5c2a646265e4..eb25fc2451d3 100644 --- a/drivers/scsi/qla2xxx/qla_init.c +++ b/drivers/scsi/qla2xxx/qla_init.c @@ -4153,41 +4153,55 @@ out: return ha->flags.lr_detected; } -void qla_init_iocb_limit(scsi_qla_host_t *vha) +static void __qla_adjust_iocb_limit(struct qla_qpair *qpair) { - u16 i, num_qps; - u32 limit; - struct qla_hw_data *ha = vha->hw; + u8 num_qps; + u16 limit; + struct qla_hw_data *ha = qpair->vha->hw; num_qps = ha->num_qpairs + 1; limit = (ha->orig_fw_iocb_count * QLA_IOCB_PCT_LIMIT) / 100; - ha->base_qpair->fwres.iocbs_total = ha->orig_fw_iocb_count; - ha->base_qpair->fwres.iocbs_limit = limit; - ha->base_qpair->fwres.iocbs_qp_limit = limit / num_qps; - ha->base_qpair->fwres.iocbs_used = 0; + qpair->fwres.iocbs_total = ha->orig_fw_iocb_count; + qpair->fwres.iocbs_limit = limit; + qpair->fwres.iocbs_qp_limit = limit / num_qps; + + qpair->fwres.exch_total = ha->orig_fw_xcb_count; + qpair->fwres.exch_limit = (ha->orig_fw_xcb_count * + QLA_IOCB_PCT_LIMIT) / 100; +} + +void qla_init_iocb_limit(scsi_qla_host_t *vha) +{ + u8 i; + struct qla_hw_data *ha = vha->hw; - ha->base_qpair->fwres.exch_total = ha->orig_fw_xcb_count; - ha->base_qpair->fwres.exch_limit = (ha->orig_fw_xcb_count * - QLA_IOCB_PCT_LIMIT) / 100; + __qla_adjust_iocb_limit(ha->base_qpair); + ha->base_qpair->fwres.iocbs_used = 0; ha->base_qpair->fwres.exch_used = 0; for (i = 0; i < ha->max_qpairs; i++) { if (ha->queue_pair_map[i]) { - ha->queue_pair_map[i]->fwres.iocbs_total = - ha->orig_fw_iocb_count; - ha->queue_pair_map[i]->fwres.iocbs_limit = limit; - ha->queue_pair_map[i]->fwres.iocbs_qp_limit = - limit / num_qps; + __qla_adjust_iocb_limit(ha->queue_pair_map[i]); ha->queue_pair_map[i]->fwres.iocbs_used = 0; - ha->queue_pair_map[i]->fwres.exch_total = ha->orig_fw_xcb_count; - ha->queue_pair_map[i]->fwres.exch_limit = - (ha->orig_fw_xcb_count * QLA_IOCB_PCT_LIMIT) / 100; ha->queue_pair_map[i]->fwres.exch_used = 0; } } } +void qla_adjust_iocb_limit(scsi_qla_host_t *vha) +{ + u8 i; + struct qla_hw_data *ha = vha->hw; + + __qla_adjust_iocb_limit(ha->base_qpair); + + for (i = 0; i < ha->max_qpairs; i++) { + if (ha->queue_pair_map[i]) + __qla_adjust_iocb_limit(ha->queue_pair_map[i]); + } +} + /** * qla2x00_setup_chip() - Load and start RISC firmware. * @vha: HA context diff --git a/drivers/scsi/qla2xxx/qla_mbx.c b/drivers/scsi/qla2xxx/qla_mbx.c index 254fd4c64262..b05f93037875 100644 --- a/drivers/scsi/qla2xxx/qla_mbx.c +++ b/drivers/scsi/qla2xxx/qla_mbx.c @@ -2213,6 +2213,9 @@ qla2x00_get_firmware_state(scsi_qla_host_t *vha, uint16_t *states) ql_dbg(ql_dbg_mbx + ql_dbg_verbose, vha, 0x1054, "Entered %s.\n", __func__); + if (!ha->flags.fw_started) + return QLA_FUNCTION_FAILED; + mcp->mb[0] = MBC_GET_FIRMWARE_STATE; mcp->out_mb = MBX_0; if (IS_FWI2_CAPABLE(vha->hw)) diff --git a/drivers/scsi/qla2xxx/qla_nvme.c b/drivers/scsi/qla2xxx/qla_nvme.c index 86e85f2f4782..6769c40287b9 100644 --- a/drivers/scsi/qla2xxx/qla_nvme.c +++ b/drivers/scsi/qla2xxx/qla_nvme.c @@ -132,6 +132,7 @@ static int qla_nvme_alloc_queue(struct nvme_fc_local_port *lport, "Failed to allocate qpair\n"); return -EINVAL; } + qla_adjust_iocb_limit(vha); } *handle = qpair; -- cgit From a8ec192427e0516436e61f9ca9eb49c54eadfe0a Mon Sep 17 00:00:00 2001 From: Quinn Tran Date: Fri, 14 Jul 2023 12:30:57 +0530 Subject: scsi: qla2xxx: Limit TMF to 8 per function Per FW recommendation, 8 TMF's can be outstanding for each function. Previously, it allowed 8 per target. Limit TMF to 8 per function. Cc: stable@vger.kernel.org Fixes: 6a87679626b5 ("scsi: qla2xxx: Fix task management cmd fail due to unavailable resource") Signed-off-by: Quinn Tran Signed-off-by: Nilesh Javali Link: https://lore.kernel.org/r/20230714070104.40052-4-njavali@marvell.com Reviewed-by: Himanshu Madhani Signed-off-by: Martin K. Petersen --- drivers/scsi/qla2xxx/qla_def.h | 9 ++++--- drivers/scsi/qla2xxx/qla_init.c | 55 +++++++++++++++++++++++++---------------- drivers/scsi/qla2xxx/qla_os.c | 2 ++ 3 files changed, 41 insertions(+), 25 deletions(-) diff --git a/drivers/scsi/qla2xxx/qla_def.h b/drivers/scsi/qla2xxx/qla_def.h index d44c4d37b50b..b3b1df34afd3 100644 --- a/drivers/scsi/qla2xxx/qla_def.h +++ b/drivers/scsi/qla2xxx/qla_def.h @@ -466,6 +466,7 @@ static inline be_id_t port_id_to_be_id(port_id_t port_id) } struct tmf_arg { + struct list_head tmf_elem; struct qla_qpair *qpair; struct fc_port *fcport; struct scsi_qla_host *vha; @@ -2541,7 +2542,6 @@ enum rscn_addr_format { typedef struct fc_port { struct list_head list; struct scsi_qla_host *vha; - struct list_head tmf_pending; unsigned int conf_compl_supported:1; unsigned int deleted:2; @@ -2562,9 +2562,6 @@ typedef struct fc_port { unsigned int do_prli_nvme:1; uint8_t nvme_flag; - uint8_t active_tmf; -#define MAX_ACTIVE_TMF 8 - uint8_t node_name[WWN_SIZE]; uint8_t port_name[WWN_SIZE]; port_id_t d_id; @@ -4657,6 +4654,8 @@ struct qla_hw_data { uint32_t flt_region_aux_img_status_sec; }; uint8_t active_image; + uint8_t active_tmf; +#define MAX_ACTIVE_TMF 8 /* Needed for BEACON */ uint16_t beacon_blink_led; @@ -4671,6 +4670,8 @@ struct qla_hw_data { struct qla_msix_entry *msix_entries; + struct list_head tmf_pending; + struct list_head tmf_active; struct list_head vp_list; /* list of VP */ unsigned long vp_idx_map[(MAX_MULTI_ID_FABRIC / 8) / sizeof(unsigned long)]; diff --git a/drivers/scsi/qla2xxx/qla_init.c b/drivers/scsi/qla2xxx/qla_init.c index eb25fc2451d3..404b32ceeaa2 100644 --- a/drivers/scsi/qla2xxx/qla_init.c +++ b/drivers/scsi/qla2xxx/qla_init.c @@ -2192,30 +2192,42 @@ done: return rval; } -static void qla_put_tmf(fc_port_t *fcport) +static void qla_put_tmf(struct tmf_arg *arg) { - struct scsi_qla_host *vha = fcport->vha; + struct scsi_qla_host *vha = arg->vha; struct qla_hw_data *ha = vha->hw; unsigned long flags; spin_lock_irqsave(&ha->tgt.sess_lock, flags); - fcport->active_tmf--; + ha->active_tmf--; + list_del(&arg->tmf_elem); spin_unlock_irqrestore(&ha->tgt.sess_lock, flags); } static -int qla_get_tmf(fc_port_t *fcport) +int qla_get_tmf(struct tmf_arg *arg) { - struct scsi_qla_host *vha = fcport->vha; + struct scsi_qla_host *vha = arg->vha; struct qla_hw_data *ha = vha->hw; unsigned long flags; + fc_port_t *fcport = arg->fcport; int rc = 0; - LIST_HEAD(tmf_elem); + struct tmf_arg *t; spin_lock_irqsave(&ha->tgt.sess_lock, flags); - list_add_tail(&tmf_elem, &fcport->tmf_pending); + list_for_each_entry(t, &ha->tmf_active, tmf_elem) { + if (t->fcport == arg->fcport && t->lun == arg->lun) { + /* reject duplicate TMF */ + ql_log(ql_log_warn, vha, 0x802c, + "found duplicate TMF. Nexus=%ld:%06x:%llu.\n", + vha->host_no, fcport->d_id.b24, arg->lun); + spin_unlock_irqrestore(&ha->tgt.sess_lock, flags); + return -EINVAL; + } + } - while (fcport->active_tmf >= MAX_ACTIVE_TMF) { + list_add_tail(&arg->tmf_elem, &ha->tmf_pending); + while (ha->active_tmf >= MAX_ACTIVE_TMF) { spin_unlock_irqrestore(&ha->tgt.sess_lock, flags); msleep(1); @@ -2227,15 +2239,17 @@ int qla_get_tmf(fc_port_t *fcport) rc = EIO; break; } - if (fcport->active_tmf < MAX_ACTIVE_TMF && - list_is_first(&tmf_elem, &fcport->tmf_pending)) + if (ha->active_tmf < MAX_ACTIVE_TMF && + list_is_first(&arg->tmf_elem, &ha->tmf_pending)) break; } - list_del(&tmf_elem); + list_del(&arg->tmf_elem); - if (!rc) - fcport->active_tmf++; + if (!rc) { + ha->active_tmf++; + list_add_tail(&arg->tmf_elem, &ha->tmf_active); + } spin_unlock_irqrestore(&ha->tgt.sess_lock, flags); @@ -2257,15 +2271,18 @@ qla2x00_async_tm_cmd(fc_port_t *fcport, uint32_t flags, uint64_t lun, a.vha = fcport->vha; a.fcport = fcport; a.lun = lun; + a.flags = flags; + INIT_LIST_HEAD(&a.tmf_elem); + if (flags & (TCF_LUN_RESET|TCF_ABORT_TASK_SET|TCF_CLEAR_TASK_SET|TCF_CLEAR_ACA)) { a.modifier = MK_SYNC_ID_LUN; - - if (qla_get_tmf(fcport)) - return QLA_FUNCTION_FAILED; } else { a.modifier = MK_SYNC_ID; } + if (qla_get_tmf(&a)) + return QLA_FUNCTION_FAILED; + if (vha->hw->mqenable) { for (i = 0; i < vha->hw->num_qpairs; i++) { qpair = vha->hw->queue_pair_map[i]; @@ -2291,13 +2308,10 @@ qla2x00_async_tm_cmd(fc_port_t *fcport, uint32_t flags, uint64_t lun, goto bailout; a.qpair = vha->hw->base_qpair; - a.flags = flags; rval = __qla2x00_async_tm_cmd(&a); bailout: - if (a.modifier == MK_SYNC_ID_LUN) - qla_put_tmf(fcport); - + qla_put_tmf(&a); return rval; } @@ -5526,7 +5540,6 @@ qla2x00_alloc_fcport(scsi_qla_host_t *vha, gfp_t flags) INIT_WORK(&fcport->reg_work, qla_register_fcport_fn); INIT_LIST_HEAD(&fcport->gnl_entry); INIT_LIST_HEAD(&fcport->list); - INIT_LIST_HEAD(&fcport->tmf_pending); INIT_LIST_HEAD(&fcport->sess_cmd_list); spin_lock_init(&fcport->sess_cmd_lock); diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c index 877e4f446709..47bbc8b321f8 100644 --- a/drivers/scsi/qla2xxx/qla_os.c +++ b/drivers/scsi/qla2xxx/qla_os.c @@ -3009,6 +3009,8 @@ qla2x00_probe_one(struct pci_dev *pdev, const struct pci_device_id *id) atomic_set(&ha->num_pend_mbx_stage3, 0); atomic_set(&ha->zio_threshold, DEFAULT_ZIO_THRESHOLD); ha->last_zio_threshold = DEFAULT_ZIO_THRESHOLD; + INIT_LIST_HEAD(&ha->tmf_pending); + INIT_LIST_HEAD(&ha->tmf_active); /* Assign ISP specific operations. */ if (IS_QLA2100(ha)) { -- cgit From da7c21b72aa86e990af5f73bce6590b8d8d148d0 Mon Sep 17 00:00:00 2001 From: Quinn Tran Date: Fri, 14 Jul 2023 12:30:58 +0530 Subject: scsi: qla2xxx: Fix command flush during TMF For each TMF request, driver iterates through each qpair and flushes commands associated to the TMF. At the end of the qpair flush, a Marker is used to complete the flush transaction. This process was repeated for each qpair. The multiple flush and marker for this TMF request seems to cause confusion for FW. Instead, 1 flush is sent to FW. Driver would wait for FW to go through all the I/Os on each qpair to be read then return. Driver then closes out the transaction with a Marker. Cc: stable@vger.kernel.org Fixes: d90171dd0da5 ("scsi: qla2xxx: Multi-que support for TMF") Signed-off-by: Quinn Tran Signed-off-by: Nilesh Javali Link: https://lore.kernel.org/r/20230714070104.40052-5-njavali@marvell.com Reviewed-by: Himanshu Madhani Signed-off-by: Martin K. Petersen --- drivers/scsi/qla2xxx/qla_init.c | 74 ++++++++++++++++++++++------------------- drivers/scsi/qla2xxx/qla_iocb.c | 1 + drivers/scsi/qla2xxx/qla_os.c | 9 ++--- 3 files changed, 45 insertions(+), 39 deletions(-) diff --git a/drivers/scsi/qla2xxx/qla_init.c b/drivers/scsi/qla2xxx/qla_init.c index 404b32ceeaa2..f6f172fa1e18 100644 --- a/drivers/scsi/qla2xxx/qla_init.c +++ b/drivers/scsi/qla2xxx/qla_init.c @@ -2002,12 +2002,11 @@ qla2x00_tmf_iocb_timeout(void *data) int rc, h; unsigned long flags; - if (sp->type == SRB_MARKER) { - complete(&tmf->u.tmf.comp); - return; - } + if (sp->type == SRB_MARKER) + rc = QLA_FUNCTION_FAILED; + else + rc = qla24xx_async_abort_cmd(sp, false); - rc = qla24xx_async_abort_cmd(sp, false); if (rc) { spin_lock_irqsave(sp->qpair->qp_lock_ptr, flags); for (h = 1; h < sp->qpair->req->num_outstanding_cmds; h++) { @@ -2129,6 +2128,17 @@ static void qla2x00_tmf_sp_done(srb_t *sp, int res) complete(&tmf->u.tmf.comp); } +static int qla_tmf_wait(struct tmf_arg *arg) +{ + /* there are only 2 types of error handling that reaches here, lun or target reset */ + if (arg->flags & (TCF_LUN_RESET | TCF_ABORT_TASK_SET | TCF_CLEAR_TASK_SET)) + return qla2x00_eh_wait_for_pending_commands(arg->vha, + arg->fcport->d_id.b24, arg->lun, WAIT_LUN); + else + return qla2x00_eh_wait_for_pending_commands(arg->vha, + arg->fcport->d_id.b24, arg->lun, WAIT_TARGET); +} + static int __qla2x00_async_tm_cmd(struct tmf_arg *arg) { @@ -2136,8 +2146,9 @@ __qla2x00_async_tm_cmd(struct tmf_arg *arg) struct srb_iocb *tm_iocb; srb_t *sp; int rval = QLA_FUNCTION_FAILED; - fc_port_t *fcport = arg->fcport; + u32 chip_gen, login_gen; + u64 jif; if (TMF_NOT_READY(arg->fcport)) { ql_dbg(ql_dbg_taskm, vha, 0x8032, @@ -2182,8 +2193,27 @@ __qla2x00_async_tm_cmd(struct tmf_arg *arg) "TM IOCB failed (%x).\n", rval); } - if (!test_bit(UNLOADING, &vha->dpc_flags) && !IS_QLAFX00(vha->hw)) - rval = qla26xx_marker(arg); + if (!test_bit(UNLOADING, &vha->dpc_flags) && !IS_QLAFX00(vha->hw)) { + chip_gen = vha->hw->chip_reset; + login_gen = fcport->login_gen; + + jif = jiffies; + if (qla_tmf_wait(arg)) { + ql_log(ql_log_info, vha, 0x803e, + "Waited %u ms Nexus=%ld:%06x:%llu.\n", + jiffies_to_msecs(jiffies - jif), vha->host_no, + fcport->d_id.b24, arg->lun); + } + + if (chip_gen == vha->hw->chip_reset && login_gen == fcport->login_gen) { + rval = qla26xx_marker(arg); + } else { + ql_log(ql_log_info, vha, 0x803e, + "Skip Marker due to disruption. Nexus=%ld:%06x:%llu.\n", + vha->host_no, fcport->d_id.b24, arg->lun); + rval = QLA_FUNCTION_FAILED; + } + } done_free_sp: /* ref: INIT */ @@ -2261,9 +2291,8 @@ qla2x00_async_tm_cmd(fc_port_t *fcport, uint32_t flags, uint64_t lun, uint32_t tag) { struct scsi_qla_host *vha = fcport->vha; - struct qla_qpair *qpair; struct tmf_arg a; - int i, rval = QLA_SUCCESS; + int rval = QLA_SUCCESS; if (TMF_NOT_READY(fcport)) return QLA_SUSPENDED; @@ -2283,34 +2312,9 @@ qla2x00_async_tm_cmd(fc_port_t *fcport, uint32_t flags, uint64_t lun, if (qla_get_tmf(&a)) return QLA_FUNCTION_FAILED; - if (vha->hw->mqenable) { - for (i = 0; i < vha->hw->num_qpairs; i++) { - qpair = vha->hw->queue_pair_map[i]; - if (!qpair) - continue; - - if (TMF_NOT_READY(fcport)) { - ql_log(ql_log_warn, vha, 0x8026, - "Unable to send TM due to disruption.\n"); - rval = QLA_SUSPENDED; - break; - } - - a.qpair = qpair; - a.flags = flags|TCF_NOTMCMD_TO_TARGET; - rval = __qla2x00_async_tm_cmd(&a); - if (rval) - break; - } - } - - if (rval) - goto bailout; - a.qpair = vha->hw->base_qpair; rval = __qla2x00_async_tm_cmd(&a); -bailout: qla_put_tmf(&a); return rval; } diff --git a/drivers/scsi/qla2xxx/qla_iocb.c b/drivers/scsi/qla2xxx/qla_iocb.c index a1675f056a5c..1c6e300ed3ab 100644 --- a/drivers/scsi/qla2xxx/qla_iocb.c +++ b/drivers/scsi/qla2xxx/qla_iocb.c @@ -3881,6 +3881,7 @@ qla_marker_iocb(srb_t *sp, struct mrk_entry_24xx *mrk) { mrk->entry_type = MARKER_TYPE; mrk->modifier = sp->u.iocb_cmd.u.tmf.modifier; + mrk->handle = make_handle(sp->qpair->req->id, sp->handle); if (sp->u.iocb_cmd.u.tmf.modifier != MK_SYNC_ALL) { mrk->nport_handle = cpu_to_le16(sp->u.iocb_cmd.u.tmf.loop_id); int_to_scsilun(sp->u.iocb_cmd.u.tmf.lun, (struct scsi_lun *)&mrk->lun); diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c index 47bbc8b321f8..03bc3a0b45b6 100644 --- a/drivers/scsi/qla2xxx/qla_os.c +++ b/drivers/scsi/qla2xxx/qla_os.c @@ -1488,8 +1488,9 @@ qla2xxx_eh_device_reset(struct scsi_cmnd *cmd) goto eh_reset_failed; } err = 3; - if (qla2x00_eh_wait_for_pending_commands(vha, sdev->id, - sdev->lun, WAIT_LUN) != QLA_SUCCESS) { + if (qla2x00_eh_wait_for_pending_commands(vha, fcport->d_id.b24, + cmd->device->lun, + WAIT_LUN) != QLA_SUCCESS) { ql_log(ql_log_warn, vha, 0x800d, "wait for pending cmds failed for cmd=%p.\n", cmd); goto eh_reset_failed; @@ -1555,8 +1556,8 @@ qla2xxx_eh_target_reset(struct scsi_cmnd *cmd) goto eh_reset_failed; } err = 3; - if (qla2x00_eh_wait_for_pending_commands(vha, sdev->id, - 0, WAIT_TARGET) != QLA_SUCCESS) { + if (qla2x00_eh_wait_for_pending_commands(vha, fcport->d_id.b24, 0, + WAIT_TARGET) != QLA_SUCCESS) { ql_log(ql_log_warn, vha, 0x800d, "wait for pending cmds failed for cmd=%p.\n", cmd); goto eh_reset_failed; -- cgit From 5b51f35d127e7bef55fa869d2465e2bca4636454 Mon Sep 17 00:00:00 2001 From: Quinn Tran Date: Fri, 14 Jul 2023 12:30:59 +0530 Subject: scsi: qla2xxx: Fix erroneous link up failure Link up failure occurred where driver failed to see certain events from FW indicating link up (AEN 8011) and fabric login completion (AEN 8014). Without these 2 events, driver would not proceed forward to scan the fabric. The cause of this is due to delay in the receive of interrupt for Mailbox 60 that causes qla to set the fw_started flag late. The late setting of this flag causes other interrupts to be dropped. These dropped interrupts happen to be the link up (AEN 8011) and fabric login completion (AEN 8014). Set fw_started flag early to prevent interrupts being dropped. Cc: stable@vger.kernel.org Signed-off-by: Quinn Tran Signed-off-by: Nilesh Javali Link: https://lore.kernel.org/r/20230714070104.40052-6-njavali@marvell.com Reviewed-by: Himanshu Madhani Signed-off-by: Martin K. Petersen --- drivers/scsi/qla2xxx/qla_init.c | 3 ++- drivers/scsi/qla2xxx/qla_isr.c | 6 +++++- 2 files changed, 7 insertions(+), 2 deletions(-) diff --git a/drivers/scsi/qla2xxx/qla_init.c b/drivers/scsi/qla2xxx/qla_init.c index f6f172fa1e18..1236acb1fd83 100644 --- a/drivers/scsi/qla2xxx/qla_init.c +++ b/drivers/scsi/qla2xxx/qla_init.c @@ -4815,15 +4815,16 @@ qla2x00_init_rings(scsi_qla_host_t *vha) if (ha->flags.edif_enabled) mid_init_cb->init_cb.frame_payload_size = cpu_to_le16(ELS_MAX_PAYLOAD); + QLA_FW_STARTED(ha); rval = qla2x00_init_firmware(vha, ha->init_cb_size); next_check: if (rval) { + QLA_FW_STOPPED(ha); ql_log(ql_log_fatal, vha, 0x00d2, "Init Firmware **** FAILED ****.\n"); } else { ql_dbg(ql_dbg_init, vha, 0x00d3, "Init Firmware -- success.\n"); - QLA_FW_STARTED(ha); vha->u_ql2xexchoffld = vha->u_ql2xiniexchg = 0; } diff --git a/drivers/scsi/qla2xxx/qla_isr.c b/drivers/scsi/qla2xxx/qla_isr.c index 656700f79325..c1b6fce9c415 100644 --- a/drivers/scsi/qla2xxx/qla_isr.c +++ b/drivers/scsi/qla2xxx/qla_isr.c @@ -1121,8 +1121,12 @@ qla2x00_async_event(scsi_qla_host_t *vha, struct rsp_que *rsp, uint16_t *mb) unsigned long flags; fc_port_t *fcport = NULL; - if (!vha->hw->flags.fw_started) + if (!vha->hw->flags.fw_started) { + ql_log(ql_log_warn, vha, 0x50ff, + "Dropping AEN - %04x %04x %04x %04x.\n", + mb[0], mb[1], mb[2], mb[3]); return; + } /* Setup to process RIO completion. */ handle_cnt = 0; -- cgit From 39d22740712c7563a2e18c08f033deeacdaf66e7 Mon Sep 17 00:00:00 2001 From: Quinn Tran Date: Fri, 14 Jul 2023 12:31:00 +0530 Subject: scsi: qla2xxx: Fix session hang in gnl Connection does not resume after a host reset / chip reset. The cause of the blockage is due to the FCF_ASYNC_ACTIVE left on. The gnl command was interrupted by the chip reset. On exiting the command, this flag should be turn off to allow relogin to reoccur. Clear this flag to prevent blockage. Cc: stable@vger.kernel.org Fixes: 17e64648aa47 ("scsi: qla2xxx: Correct fcport flags handling") Signed-off-by: Quinn Tran Signed-off-by: Nilesh Javali Link: https://lore.kernel.org/r/20230714070104.40052-7-njavali@marvell.com Reviewed-by: Himanshu Madhani Signed-off-by: Martin K. Petersen --- drivers/scsi/qla2xxx/qla_init.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/scsi/qla2xxx/qla_init.c b/drivers/scsi/qla2xxx/qla_init.c index 1236acb1fd83..7ac4738fda25 100644 --- a/drivers/scsi/qla2xxx/qla_init.c +++ b/drivers/scsi/qla2xxx/qla_init.c @@ -1141,7 +1141,7 @@ int qla24xx_async_gnl(struct scsi_qla_host *vha, fc_port_t *fcport) u16 *mb; if (!vha->flags.online || (fcport->flags & FCF_ASYNC_SENT)) - return rval; + goto done; ql_dbg(ql_dbg_disc, vha, 0x20d9, "Async-gnlist WWPN %8phC \n", fcport->port_name); @@ -1195,8 +1195,9 @@ int qla24xx_async_gnl(struct scsi_qla_host *vha, fc_port_t *fcport) done_free_sp: /* ref: INIT */ kref_put(&sp->cmd_kref, qla2x00_sp_release); + fcport->flags &= ~(FCF_ASYNC_SENT); done: - fcport->flags &= ~(FCF_ASYNC_ACTIVE | FCF_ASYNC_SENT); + fcport->flags &= ~(FCF_ASYNC_ACTIVE); return rval; } -- cgit From 8ebaa45163a3fedc885c1dc7d43ea987a2f00a06 Mon Sep 17 00:00:00 2001 From: Quinn Tran Date: Fri, 14 Jul 2023 12:31:01 +0530 Subject: scsi: qla2xxx: Turn off noisy message log Some consider noisy log as test failure. Turn off noisy message log. Cc: stable@vger.kernel.org Signed-off-by: Quinn Tran Signed-off-by: Nilesh Javali Link: https://lore.kernel.org/r/20230714070104.40052-8-njavali@marvell.com Reviewed-by: Himanshu Madhani Signed-off-by: Martin K. Petersen --- drivers/scsi/qla2xxx/qla_nvme.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/scsi/qla2xxx/qla_nvme.c b/drivers/scsi/qla2xxx/qla_nvme.c index 6769c40287b9..9941b38eac93 100644 --- a/drivers/scsi/qla2xxx/qla_nvme.c +++ b/drivers/scsi/qla2xxx/qla_nvme.c @@ -668,7 +668,7 @@ static int qla_nvme_post_cmd(struct nvme_fc_local_port *lport, rval = qla2x00_start_nvme_mq(sp); if (rval != QLA_SUCCESS) { - ql_log(ql_log_warn, vha, 0x212d, + ql_dbg(ql_dbg_io + ql_dbg_verbose, vha, 0x212d, "qla2x00_start_nvme_mq failed = %d\n", rval); sp->priv = NULL; priv->sp = NULL; -- cgit From 5d3148d8e8b05f084e607ac3bd55a4c317a9f934 Mon Sep 17 00:00:00 2001 From: Quinn Tran Date: Fri, 14 Jul 2023 12:31:02 +0530 Subject: scsi: qla2xxx: Fix TMF leak through Task management can retry up to 5 times when FW resource becomes bottle neck. Between the retries, there is a short sleep. Current code assumes the chip has not reset or session has not changed. Check for chip reset or session change before sending Task management. Cc: stable@vger.kernel.org Fixes: 9803fb5d2759 ("scsi: qla2xxx: Fix task management cmd failure") Signed-off-by: Quinn Tran Signed-off-by: Nilesh Javali Link: https://lore.kernel.org/r/20230714070104.40052-9-njavali@marvell.com Reviewed-by: Himanshu Madhani Signed-off-by: Martin K. Petersen --- drivers/scsi/qla2xxx/qla_init.c | 20 ++++++++++++++------ 1 file changed, 14 insertions(+), 6 deletions(-) diff --git a/drivers/scsi/qla2xxx/qla_init.c b/drivers/scsi/qla2xxx/qla_init.c index 7ac4738fda25..059175f2c8f5 100644 --- a/drivers/scsi/qla2xxx/qla_init.c +++ b/drivers/scsi/qla2xxx/qla_init.c @@ -2038,10 +2038,14 @@ static void qla_marker_sp_done(srb_t *sp, int res) complete(&tmf->u.tmf.comp); } -#define START_SP_W_RETRIES(_sp, _rval) \ +#define START_SP_W_RETRIES(_sp, _rval, _chip_gen, _login_gen) \ {\ int cnt = 5; \ do { \ + if (_chip_gen != sp->vha->hw->chip_reset || _login_gen != sp->fcport->login_gen) {\ + _rval = EINVAL; \ + break; \ + } \ _rval = qla2x00_start_sp(_sp); \ if (_rval == EAGAIN) \ msleep(1); \ @@ -2064,6 +2068,7 @@ qla26xx_marker(struct tmf_arg *arg) srb_t *sp; int rval = QLA_FUNCTION_FAILED; fc_port_t *fcport = arg->fcport; + u32 chip_gen, login_gen; if (TMF_NOT_READY(arg->fcport)) { ql_dbg(ql_dbg_taskm, vha, 0x8039, @@ -2073,6 +2078,9 @@ qla26xx_marker(struct tmf_arg *arg) return QLA_SUSPENDED; } + chip_gen = vha->hw->chip_reset; + login_gen = fcport->login_gen; + /* ref: INIT */ sp = qla2xxx_get_qpair_sp(vha, arg->qpair, fcport, GFP_KERNEL); if (!sp) @@ -2090,7 +2098,7 @@ qla26xx_marker(struct tmf_arg *arg) tm_iocb->u.tmf.loop_id = fcport->loop_id; tm_iocb->u.tmf.vp_index = vha->vp_idx; - START_SP_W_RETRIES(sp, rval); + START_SP_W_RETRIES(sp, rval, chip_gen, login_gen); ql_dbg(ql_dbg_taskm, vha, 0x8006, "Async-marker hdl=%x loop-id=%x portid=%06x modifier=%x lun=%lld qp=%d rval %d.\n", @@ -2159,6 +2167,9 @@ __qla2x00_async_tm_cmd(struct tmf_arg *arg) return QLA_SUSPENDED; } + chip_gen = vha->hw->chip_reset; + login_gen = fcport->login_gen; + /* ref: INIT */ sp = qla2xxx_get_qpair_sp(vha, arg->qpair, fcport, GFP_KERNEL); if (!sp) @@ -2176,7 +2187,7 @@ __qla2x00_async_tm_cmd(struct tmf_arg *arg) tm_iocb->u.tmf.flags = arg->flags; tm_iocb->u.tmf.lun = arg->lun; - START_SP_W_RETRIES(sp, rval); + START_SP_W_RETRIES(sp, rval, chip_gen, login_gen); ql_dbg(ql_dbg_taskm, vha, 0x802f, "Async-tmf hdl=%x loop-id=%x portid=%06x ctrl=%x lun=%lld qp=%d rval=%x.\n", @@ -2195,9 +2206,6 @@ __qla2x00_async_tm_cmd(struct tmf_arg *arg) } if (!test_bit(UNLOADING, &vha->dpc_flags) && !IS_QLAFX00(vha->hw)) { - chip_gen = vha->hw->chip_reset; - login_gen = fcport->login_gen; - jif = jiffies; if (qla_tmf_wait(arg)) { ql_log(ql_log_info, vha, 0x803e, -- cgit From 009e7fe4a1ed52276b332842a6b6e23b07200f2d Mon Sep 17 00:00:00 2001 From: Quinn Tran Date: Fri, 14 Jul 2023 12:31:03 +0530 Subject: scsi: qla2xxx: fix inconsistent TMF timeout Different behavior were experienced of session being torn down vs not when TMF is timed out. When FW detects the time out, the session is torn down. When driver detects the time out, the session is not torn down. Allow TMF error to return to upper layer without session tear down. Cc: stable@vger.kernel.org Signed-off-by: Quinn Tran Signed-off-by: Nilesh Javali Link: https://lore.kernel.org/r/20230714070104.40052-10-njavali@marvell.com Reviewed-by: Himanshu Madhani Signed-off-by: Martin K. Petersen --- drivers/scsi/qla2xxx/qla_isr.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/scsi/qla2xxx/qla_isr.c b/drivers/scsi/qla2xxx/qla_isr.c index c1b6fce9c415..1f42a413b598 100644 --- a/drivers/scsi/qla2xxx/qla_isr.c +++ b/drivers/scsi/qla2xxx/qla_isr.c @@ -2543,7 +2543,6 @@ qla24xx_tm_iocb_entry(scsi_qla_host_t *vha, struct req_que *req, void *tsk) case CS_PORT_BUSY: case CS_INCOMPLETE: case CS_PORT_UNAVAILABLE: - case CS_TIMEOUT: case CS_RESET: if (atomic_read(&fcport->state) == FCS_ONLINE) { ql_dbg(ql_dbg_disc, fcport->vha, 0x3021, -- cgit From a31a596a426555ff603599e115466d596a1abd85 Mon Sep 17 00:00:00 2001 From: Nilesh Javali Date: Fri, 14 Jul 2023 12:31:04 +0530 Subject: scsi: qla2xxx: Update version to 10.02.08.500-k Signed-off-by: Nilesh Javali Link: https://lore.kernel.org/r/20230714070104.40052-11-njavali@marvell.com Reviewed-by: Himanshu Madhani Signed-off-by: Martin K. Petersen --- drivers/scsi/qla2xxx/qla_version.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/scsi/qla2xxx/qla_version.h b/drivers/scsi/qla2xxx/qla_version.h index e3771923b0d7..81bdf6b03241 100644 --- a/drivers/scsi/qla2xxx/qla_version.h +++ b/drivers/scsi/qla2xxx/qla_version.h @@ -6,9 +6,9 @@ /* * Driver version */ -#define QLA2XXX_VERSION "10.02.08.400-k" +#define QLA2XXX_VERSION "10.02.08.500-k" #define QLA_DRIVER_MAJOR_VER 10 #define QLA_DRIVER_MINOR_VER 2 #define QLA_DRIVER_PATCH_VER 8 -#define QLA_DRIVER_BETA_VER 400 +#define QLA_DRIVER_BETA_VER 500 -- cgit