qla2xxx misc. bug fixes
Subsystems (2)
Nilesh Javali
maintainerv2 cover qla2xxx misc. bug fixes
Martin,
Please apply the qla2xxx driver miscellaneous bug fixes to the scsi tree at your earliest convenience.
v2:
- Fix warning reported by kernel test robot
- Added Reviewed-by tag
Thanks,
Nilesh
Bikash Hazarika (1):
qla2xxx: Update manufacturer detail
Nilesh Javali (1):
qla2xxx: Update version to 10.02.09.200-k
Quinn Tran (6):
qla2xxx: Prevent command send on chip reset
qla2xxx: Fix N2N stuck connection
qla2xxx: Split FCE|EFT trace control
qla2xxx: NVME|FCP prefer flag not being honored
qla2xxx: Fix command flush on cable pull
qla2xxx: Delay IO Abort on PCI error
Saurav Kashyap (3):
qla2xxx: Fix double free of the ha->vp_map pointer.
qla2xxx: Fix double free of fcport
qla2xxx: change debug message during driver unload
drivers/scsi/qla2xxx/qla_attr.c | 14 +++- drivers/scsi/qla2xxx/qla_def.h | 2 +- drivers/scsi/qla2xxx/qla_gbl.h | 2 +- drivers/scsi/qla2xxx/qla_init.c | 128 +++++++++++++++-------------- drivers/scsi/qla2xxx/qla_iocb.c | 68 +++++++++------ drivers/scsi/qla2xxx/qla_mbx.c | 2 +- drivers/scsi/qla2xxx/qla_os.c | 3 +- drivers/scsi/qla2xxx/qla_target.c | 10 +++ drivers/scsi/qla2xxx/qla_version.h | 4 +- 9 files changed, 138 insertions(+), 95 deletions(-)
base-commit: f4469f3858352ad1197434557150b1f7086762a0
Signature · 1 line
2.23.1
Nilesh Javali
maintainerPATCH v2 1/11 qla2xxx: Prevent command send on chip reset
From: Quinn Tran <[email protected]>
Currently IOCBs are allowed to push through while chip reset could be in progress. During chip reset the outstanding_cmds array is cleared twice. Once when any command on this array is returned as failed and secondly when the array is initialize to zero. If a command is inserted on to the array between these intervals, then the command will be lost.
Check for chip reset before sending IOCB.
--- drivers/scsi/qla2xxx/qla_init.c | 8 ++++++-- drivers/scsi/qla2xxx/qla_iocb.c | 33 +++++++++++++++++++++++++++++++-- 2 files changed, 37 insertions(+), 4 deletions(-)
drivers/scsi/qla2xxx/qla_init.c +6 -2
@@ -1193,8 +1193,12 @@ int qla24xx_async_gnl(struct scsi_qla_host *vha, fc_port_t *fcport)return rval; done_free_sp: -/* ref: INIT */ -kref_put (&sp->cmd_kref, qla2x00_sp_release); +/* +* use qla24xx_async_gnl_sp_done to purge all pending gnl request. +* kref_put is call behind the scene. +*/ + sp->u.iocb_cmd.u.mbx.in_mb[0 ] =MBS_COMMAND_ERROR ; +qla24xx_async_gnl_sp_done (sp,QLA_COMMAND_ERROR ); fcport->flags &= ~(FCF_ASYNC_SENT ); done: fcport->flags &= ~(FCF_ASYNC_ACTIVE );
drivers/scsi/qla2xxx/qla_iocb.c +31 -2
@@ -2587,6 +2587,33 @@ void qla2x00_sp_release(struct kref *kref) { struct srb *sp = container_of(kref, struct srb, cmd_kref); +struct scsi_qla_host *vha = sp->vha; + +switch (sp->type) { +case SRB_CT_PTHRU_CMD : +/* GPSC & GFPNID use fcport->ct_desc.ct_sns for both req & rsp */ +if (sp->u.iocb_cmd.u.ctarg.req && + (!sp->fcport || + sp->u.iocb_cmd.u.ctarg.req != sp->fcport->ct_desc.ct_sns)) { +dma_free_coherent (&vha->hw->pdev->dev, + sp->u.iocb_cmd.u.ctarg.req_allocated_size, + sp->u.iocb_cmd.u.ctarg.req, + sp->u.iocb_cmd.u.ctarg.req_dma); + sp->u.iocb_cmd.u.ctarg.req =NULL ; + } +if (sp->u.iocb_cmd.u.ctarg.rsp && + (!sp->fcport || + sp->u.iocb_cmd.u.ctarg.rsp != sp->fcport->ct_desc.ct_sns)) { +dma_free_coherent (&vha->hw->pdev->dev, + sp->u.iocb_cmd.u.ctarg.rsp_allocated_size, + sp->u.iocb_cmd.u.ctarg.rsp, + sp->u.iocb_cmd.u.ctarg.rsp_dma); + sp->u.iocb_cmd.u.ctarg.rsp =NULL ; + } +break ; +default : +break ; + } sp->free (sp); }
@@ -2692,7 +2719,7 @@ qla24xx_els_dcmd_iocb(scsi_qla_host_t *vha, int els_opcode,*/ sp =qla2x00_get_sp (vha, fcport,GFP_KERNEL );if (!sp) { -kfree (fcport); +qla2x00_free_fcport (fcport);ql_log (ql_log_info, vha,0x70e6 ,"SRB allocation failed\n" );return -ENOMEM ;
@@ -2747,6 +2774,7 @@ qla24xx_els_dcmd_iocb(scsi_qla_host_t *vha, int els_opcode,if (rval !=QLA_SUCCESS ) {/* ref: INIT */ kref_put (&sp->cmd_kref, qla2x00_sp_release); +qla2x00_free_fcport (fcport);return QLA_FUNCTION_FAILED ; }
@@ -2756,6 +2784,7 @@ qla24xx_els_dcmd_iocb(scsi_qla_host_t *vha, int els_opcode, fcport->d_id.b.area, fcport->d_id.b.al_pa);wait_for_completion (&elsio->u.els_logo.comp); +qla2x00_free_fcport (fcport);/* ref: INIT */ kref_put (&sp->cmd_kref, qla2x00_sp_release);
@@ -3918,7 +3947,7 @@ qla2x00_start_sp(srb_t *sp)return -EAGAIN ; } - pkt =__qla2x00_alloc_iocbs (sp->qpair, sp); + pkt =qla2x00_alloc_iocbs_ready (sp->qpair, sp);if (!pkt) { rval = -EAGAIN ; ql_log(ql_log_warn, vha, 0x700c,
Signature · 1 line
2.23.1
Nilesh Javali
maintainerPATCH v2 2/11 qla2xxx: Fix N2N stuck connection
In reply to Nilesh JavaliFrom: Quinn Tran <[email protected]>
Disk failed to rediscover after chip reset error injection. The chip reset happens at the time when a PLOGI is being sent. This cause a flag to be left on which blocks the retry. Clear the blocking flag.
--- drivers/scsi/qla2xxx/qla_gbl.h | 2 +- drivers/scsi/qla2xxx/qla_iocb.c | 32 +++++++++++--------------------- drivers/scsi/qla2xxx/qla_os.c | 2 +- 3 files changed, 13 insertions(+), 23 deletions(-)
drivers/scsi/qla2xxx/qla_gbl.h +1 -1
@@ -44,7 +44,7 @@ extern int qla2x00_fabric_login(scsi_qla_host_t *, fc_port_t *, uint16_t *);extern int qla2x00_local_device_login (scsi_qla_host_t *,fc_port_t *);extern int qla24xx_els_dcmd_iocb (scsi_qla_host_t *,int ,port_id_t ); -extern int qla24xx_els_dcmd2_iocb (scsi_qla_host_t *,int ,fc_port_t *,bool ); +extern int qla24xx_els_dcmd2_iocb (scsi_qla_host_t *,int ,fc_port_t *);extern void qla2x00_els_dcmd2_free (scsi_qla_host_t *vha,struct els_plogi *els_plogi);
drivers/scsi/qla2xxx/qla_iocb.c +11 -21
@@ -3041,7 +3041,7 @@ static void qla2x00_els_dcmd2_sp_done(srb_t *sp, int res)int qla24xx_els_dcmd2_iocb (scsi_qla_host_t *vha,int els_opcode, -fc_port_t *fcport,bool wait) +fc_port_t *fcport) {srb_t *sp;struct srb_iocb *elsio =NULL ;
@@ -3056,8 +3056,7 @@ qla24xx_els_dcmd2_iocb(scsi_qla_host_t *vha, int els_opcode,if (!sp) {ql_log (ql_log_info, vha,0x70e6 ,"SRB allocation failed\n" ); - fcport->flags &= ~FCF_ASYNC_ACTIVE ; -return -ENOMEM ; + goto done; } fcport->flags |=FCF_ASYNC_SENT ;
@@ -3066,9 +3065,6 @@ qla24xx_els_dcmd2_iocb(scsi_qla_host_t *vha, int els_opcode,ql_dbg (ql_dbg_io, vha,0x3073 ,"%s Enter: PLOGI portid=%06x\n" , __func__, fcport->d_id.b24); -if (wait) - sp->flags =SRB_WAKEUP_ON_COMP ; - sp->type =SRB_ELS_DCMD ; sp->name ="ELS_DCMD" ; sp->fcport = fcport;
@@ -3084,7 +3080,7 @@ qla24xx_els_dcmd2_iocb(scsi_qla_host_t *vha, int els_opcode,if (!elsio->u.els_plogi.els_plogi_pyld) { rval =QLA_FUNCTION_FAILED ; - goto out; + goto done_free_sp; } resp_ptr = elsio->u.els_plogi.els_resp_pyld =
@@ -3093,7 +3089,7 @@ qla24xx_els_dcmd2_iocb(scsi_qla_host_t *vha, int els_opcode,if (!elsio->u.els_plogi.els_resp_pyld) { rval =QLA_FUNCTION_FAILED ; - goto out; + goto done_free_sp; }ql_dbg (ql_dbg_io, vha,0x3073 ,"PLOGI %p %p\n" , ptr, resp_ptr);
@@ -3109,7 +3105,6 @@ qla24xx_els_dcmd2_iocb(scsi_qla_host_t *vha, int els_opcode,if (els_opcode ==ELS_DCMD_PLOGI &&DBELL_ACTIVE (vha)) {struct fc_els_flogi *p = ptr; - p->fl_csp.sp_features |=cpu_to_be16 (FC_SP_FT_SEC ); }
@@ -3118,10 +3113,11 @@ qla24xx_els_dcmd2_iocb(scsi_qla_host_t *vha, int els_opcode, (uint8_t *)elsio->u.els_plogi.els_plogi_pyld, sizeof(*elsio->u.els_plogi.els_plogi_pyld)); -init_completion (&elsio->u.els_plogi.comp); rval =qla2x00_start_sp (sp);if (rval !=QLA_SUCCESS ) { - rval =QLA_FUNCTION_FAILED ; + fcport->flags |=FCF_LOGIN_NEEDED ; +set_bit (RELOGIN_NEEDED , &vha->dpc_flags); + goto done_free_sp; }else { ql_dbg(ql_dbg_disc, vha, 0x3074, "%s PLOGI sent, hdl=%x, loopid=%x, to port_id %06x from port_id %06x\n",
@@ -3129,21 +3125,15 @@ qla24xx_els_dcmd2_iocb(scsi_qla_host_t *vha, int els_opcode, fcport->d_id.b24, vha->d_id.b24); } -if (wait) { -wait_for_completion (&elsio->u.els_plogi.comp); - -if (elsio->u.els_plogi.comp_status !=CS_COMPLETE ) - rval =QLA_FUNCTION_FAILED ; - }else { - goto done; - } +return rval; -out: - fcport->flags &= ~(FCF_ASYNC_SENT |FCF_ASYNC_ACTIVE ); +done_free_sp:qla2x00_els_dcmd2_free (vha, &elsio->u.els_plogi);/* ref: INIT */ kref_put (&sp->cmd_kref, qla2x00_sp_release); done: + fcport->flags &= ~(FCF_ASYNC_SENT |FCF_ASYNC_ACTIVE ); +qla2x00_set_fcport_disc_state (fcport,DSC_DELETED );return rval; }
drivers/scsi/qla2xxx/qla_os.c +1 -1
@@ -5583,7 +5583,7 @@ qla2x00_do_work(struct scsi_qla_host *vha)break ;case QLA_EVT_ELS_PLOGI :qla24xx_els_dcmd2_iocb (vha,ELS_DCMD_PLOGI , - e->u.fcport.fcport, false); + e->u.fcport.fcport);break ;case QLA_EVT_SA_REPLACE : rc =qla24xx_issue_sa_replace_iocb (vha, e);
Signature · 1 line
2.23.1
Nilesh Javali
maintainerPATCH v2 3/11 qla2xxx: Split FCE|EFT trace control
In reply to Nilesh JavaliFrom: Quinn Tran <[email protected]>
Current code combine the allocation of FCE|EFT trace buffers and enable the features all in 1 step.
Split this step into separate steps in preparation for follow on patch to allow user to have a choice to enable / disable FCE trace feature.
---
v2:
- Fix warning reported by kernel test robot
drivers/scsi/qla2xxx/qla_init.c | 102 +++++++++++++------------------- 1 file changed, 41 insertions(+), 61 deletions(-)
drivers/scsi/qla2xxx/qla_init.c +41 -61
@@ -2669,6 +2669,40 @@ qla83xx_nic_core_fw_load(scsi_qla_host_t *vha)return rval; } +static void qla_enable_fce_trace (scsi_qla_host_t *vha) +{ +int rval; +struct qla_hw_data *ha = vha->hw; + +if (ha->fce) { + ha->flags.fce_enabled =1 ; +memset (ha->fce,0 ,fce_calc_size (ha->fce_bufs)); + rval =qla2x00_enable_fce_trace (vha, + ha->fce_dma, ha->fce_bufs, ha->fce_mb, &ha->fce_bufs); + +if (rval) { +ql_log (ql_log_warn, vha,0x8033 , +"Unable to reinitialize FCE (%d).\n" , rval); + ha->flags.fce_enabled =0 ; + } + } +} + +static void qla_enable_eft_trace (scsi_qla_host_t *vha) +{ +int rval; +struct qla_hw_data *ha = vha->hw; + +if (ha->eft) { +memset (ha->eft,0 ,EFT_SIZE ); + rval =qla2x00_enable_eft_trace (vha, ha->eft_dma,EFT_NUM_BUFFERS ); + +if (rval) { +ql_log (ql_log_warn, vha,0x8034 , +"Unable to reinitialize EFT (%d).\n" , rval); + } + } +}/* * qla2x00_initialize_adapter * Initialize board.
@@ -3672,9 +3706,8 @@ qla24xx_chip_diag(scsi_qla_host_t *vha) }static void -qla2x00_init_fce_trace (scsi_qla_host_t *vha) +qla2x00_alloc_fce_trace (scsi_qla_host_t *vha) { -int rval;dma_addr_t tc_dma;void *tc;struct qla_hw_data *ha = vha->hw;
@@ -3703,27 +3736,17 @@ qla2x00_init_fce_trace(scsi_qla_host_t *vha)return ; } - rval =qla2x00_enable_fce_trace (vha, tc_dma,FCE_NUM_BUFFERS , - ha->fce_mb, &ha->fce_bufs); -if (rval) { -ql_log (ql_log_warn, vha,0x00bf , -"Unable to initialize FCE (%d).\n" , rval); -dma_free_coherent (&ha->pdev->dev,FCE_SIZE , tc, tc_dma); -return ; - } -ql_dbg (ql_dbg_init, vha,0x00c0 ,"Allocated (%d KB) for FCE...\n" ,FCE_SIZE /1024 ); - ha->flags.fce_enabled =1 ; ha->fce_dma = tc_dma; ha->fce = tc; + ha->fce_bufs =FCE_NUM_BUFFERS ; }static void -qla2x00_init_eft_trace (scsi_qla_host_t *vha) +qla2x00_alloc_eft_trace (scsi_qla_host_t *vha) { -int rval;dma_addr_t tc_dma;void *tc;struct qla_hw_data *ha = vha->hw;
@@ -3748,14 +3771,6 @@ qla2x00_init_eft_trace(scsi_qla_host_t *vha)return ; } - rval =qla2x00_enable_eft_trace (vha, tc_dma,EFT_NUM_BUFFERS ); -if (rval) { -ql_log (ql_log_warn, vha,0x00c2 , -"Unable to initialize EFT (%d).\n" , rval); -dma_free_coherent (&ha->pdev->dev,EFT_SIZE , tc, tc_dma); -return ; - } -ql_dbg (ql_dbg_init, vha,0x00c3 ,"Allocated (%d KB) EFT ...\n" ,EFT_SIZE /1024 );
@@ -3763,13 +3778,6 @@ qla2x00_init_eft_trace(scsi_qla_host_t *vha) ha->eft = tc; } -static void -qla2x00_alloc_offload_mem (scsi_qla_host_t *vha) -{ -qla2x00_init_fce_trace (vha); -qla2x00_init_eft_trace (vha); -} -void qla2x00_alloc_fw_dump (scsi_qla_host_t *vha) {
@@ -3824,10 +3832,10 @@ qla2x00_alloc_fw_dump(scsi_qla_host_t *vha)if (ha->tgt.atio_ring) mq_size += ha->tgt.atio_q_length *sizeof (request_t); -qla2x00_init_fce_trace (vha); +qla2x00_alloc_fce_trace (vha);if (ha->fce) fce_size =sizeof (struct qla2xxx_fce_chain ) +FCE_SIZE ; -qla2x00_init_eft_trace (vha); +qla2x00_alloc_eft_trace (vha);if (ha->eft) eft_size =EFT_SIZE ; }
@@ -4257,7 +4265,6 @@ qla2x00_setup_chip(scsi_qla_host_t *vha)struct qla_hw_data *ha = vha->hw;struct device_reg_2xxx __iomem *reg = &ha->iobase->isp;unsigned long flags; -uint16_t fw_major_version;int done_once =0 ;if (IS_P3P_TYPE (ha)) {
@@ -4324,7 +4331,6 @@ qla2x00_setup_chip(scsi_qla_host_t *vha) goto failed; enable_82xx_npiv: - fw_major_version = ha->fw_major_version;if (IS_P3P_TYPE (ha))qla82xx_check_md_needed (vha);else
@@ -4353,12 +4359,11 @@ qla2x00_setup_chip(scsi_qla_host_t *vha)if (rval !=QLA_SUCCESS ) goto failed; -if (!fw_major_version && !(IS_P3P_TYPE (ha))) -qla2x00_alloc_offload_mem (vha); -if (ql2xallocfwdump && !(IS_P3P_TYPE (ha)))qla2x00_alloc_fw_dump (vha); +qla_enable_fce_trace (vha); +qla_enable_eft_trace (vha); }else { goto failed; }
@@ -7491,7 +7496,6 @@ qla2x00_abort_isp_cleanup(scsi_qla_host_t *vha)int qla2x00_abort_isp (scsi_qla_host_t *vha) { -int rval;uint8_t status =0 ;struct qla_hw_data *ha = vha->hw;struct scsi_qla_host *vp, *tvp;
@@ -7585,31 +7589,7 @@ qla2x00_abort_isp(scsi_qla_host_t *vha)if (IS_QLA81XX (ha) ||IS_QLA8031 (ha))qla2x00_get_fw_version (vha); -if (ha->fce) { - ha->flags.fce_enabled =1 ; -memset (ha->fce,0 , -fce_calc_size (ha->fce_bufs)); - rval =qla2x00_enable_fce_trace (vha, - ha->fce_dma, ha->fce_bufs, ha->fce_mb, - &ha->fce_bufs); -if (rval) { -ql_log (ql_log_warn, vha,0x8033 , -"Unable to reinitialize FCE " -"(%d).\n" , rval); - ha->flags.fce_enabled =0 ; - } - } -if (ha->eft) { -memset (ha->eft,0 ,EFT_SIZE ); - rval =qla2x00_enable_eft_trace (vha, - ha->eft_dma,EFT_NUM_BUFFERS ); -if (rval) { -ql_log (ql_log_warn, vha,0x8034 , -"Unable to reinitialize EFT " -"(%d).\n" , rval); - } - } }else {/* failed the ISP abort */ vha->flags.online =1 ;if (test_bit (ISP_ABORT_RETRY , &vha->dpc_flags)) {
Signature · 1 line
2.23.1
Nilesh Javali
maintainerPATCH v2 4/11 qla2xxx: Update manufacturer detail
In reply to Nilesh JavaliFrom: Bikash Hazarika <[email protected]>
Update manufacturer detail from "Marvell Semiconductor, Inc." to "Marvell".
--- drivers/scsi/qla2xxx/qla_def.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/scsi/qla2xxx/qla_def.h +1 -1
@@ -82,7 +82,7 @@ typedef union {#include "qla_nvme.h" #define QLA2XXX_DRIVER_NAME "qla2xxx"#define QLA2XXX_APIDEV "ql2xapidev" -#define QLA2XXX_MANUFACTURER "Marvell Semiconductor, Inc." +#define QLA2XXX_MANUFACTURER "Marvell"/* * We have MAILBOX_REGISTER_COUNT sized arrays in a few places,
Signature · 1 line
2.23.1
Nilesh Javali
maintainerPATCH v2 5/11 qla2xxx: NVME|FCP prefer flag not being honored
In reply to Nilesh JavaliFrom: Quinn Tran <[email protected]>
Changing of [FCP|NVME] prefer flag in flash has
no effect on driver. For device that support both FCP + NVME over the same connection, driver continue to connect to this device using the previous successful login mode.
On completion of flash update, adapter will be reset. Driver will reset the prefer flag based on setting from flash.
--- drivers/scsi/qla2xxx/qla_init.c | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+)
drivers/scsi/qla2xxx/qla_init.c +18 -0
@@ -7501,6 +7501,7 @@ qla2x00_abort_isp(scsi_qla_host_t *vha)struct scsi_qla_host *vp, *tvp;struct req_que *req = ha->req_q_map[0 ];unsigned long flags; +fc_port_t *fcport;if (vha->flags.online) {qla2x00_abort_isp_cleanup (vha);
@@ -7569,6 +7570,15 @@ qla2x00_abort_isp(scsi_qla_host_t *vha) "ISP Abort - ISP reg disconnect post nvmram config, exiting.\n");return status; } + +/* User may have updated [fcp|nvme] prefer in flash */ +list_for_each_entry (fcport, &vha->vp_fcports, list) { +if (NVME_PRIORITY (ha, fcport)) + fcport->do_prli_nvme =1 ; +else + fcport->do_prli_nvme =0 ; + } +if (!qla2x00_restart_isp (vha)) {clear_bit (RESET_MARKER_NEEDED , &vha->dpc_flags);
@@ -7639,6 +7649,14 @@ qla2x00_abort_isp(scsi_qla_host_t *vha)atomic_inc (&vp->vref_count);spin_unlock_irqrestore (&ha->vport_slock, flags); +/* User may have updated [fcp|nvme] prefer in flash */ +list_for_each_entry (fcport, &vp->vp_fcports, list) { +if (NVME_PRIORITY (ha, fcport)) + fcport->do_prli_nvme =1 ; +else + fcport->do_prli_nvme =0 ; + } +qla2x00_vp_abort_isp (vp);spin_lock_irqsave (&ha->vport_slock, flags);
Signature · 1 line
2.23.1
Nilesh Javali
maintainerPATCH v2 6/11 qla2xxx: Fix command flush on cable pull
In reply to Nilesh JavaliFrom: Quinn Tran <[email protected]>
System crash due to command failed to flush back
to scsi layer.
BUG: unable to handle kernel NULL pointer dereference at 0000000000000000 PGD 0 P4D 0 Oops: 0000 [#1] SMP NOPTI CPU: 27 PID: 793455 Comm: kworker/u130:6 Kdump: loaded Tainted: G OE --------- - - 4.18.0-372.9.1.el8.x86_64 #1 Hardware name: HPE ProLiant DL360 Gen10/ProLiant DL360 Gen10, BIOS U32 09/03/2021 Workqueue: nvme-wq nvme_fc_connect_ctrl_work [nvme_fc] RIP: 0010:__wake_up_common+0x4c/0x190 Code: 24 10 4d 85 c9 74 0a 41 f6 01 04 0f 85 9d 00 00 00 48 8b 43 08 48 83 c3 08 4c 8d 48 e8 49 8d 41 18 48 39 c3 0f 84 f0 00 00 00 <49> 8b 41 18 89 54 24 08 31 ed 4c 8d 70 e8 45 8b 29 41 f6 c5 04 75 RSP: 0018:ffff95f3e0cb7cd0 EFLAGS: 00010086 RAX: 0000000000000000 RBX: ffff8b08d3b26328 RCX: 0000000000000000 RDX: 0000000000000001 RSI: 0000000000000003 RDI: ffff8b08d3b26320 RBP: 0000000000000001 R08: 0000000000000000 R09: ffffffffffffffe8 R10: 0000000000000000 R11: ffff95f3e0cb7a60 R12: ffff95f3e0cb7d20 R13: 0000000000000003 R14: 0000000000000000 R15: 0000000000000000 FS: 0000000000000000(0000) GS:ffff8b2fdf6c0000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000000 CR3: 0000002f1e410002 CR4: 00000000007706e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 PKRU: 55555554 Call Trace: __wake_up_common_lock+0x7c/0xc0 qla_nvme_ls_req+0x355/0x4c0 [qla2xxx] qla2xxx [0000:12:00.1]-f084:3: qlt_free_session_done: se_sess 0000000000000000 / sess ffff8ae1407ca000 from port 21:32:00:02:ac:07:ee:b8 loop_id 0x02 s_id 01:02:00 logout 1 keep 0 els_logo 0 ? __nvme_fc_send_ls_req+0x260/0x380 [nvme_fc] qla2xxx [0000:12:00.1]-207d:3: FCPort 21:32:00:02:ac:07:ee:b8 state transitioned from ONLINE to LOST - portid=010200. ? nvme_fc_send_ls_req.constprop.42+0x1a/0x45 [nvme_fc] qla2xxx [0000:12:00.1]-2109:3: qla2x00_schedule_rport_del 21320002ac07eeb8. rport ffff8ae598122000 roles 1 ? nvme_fc_connect_ctrl_work.cold.63+0x1e3/0xa7d [nvme_fc] qla2xxx [0000:12:00.1]-f084:3: qlt_free_session_done: se_sess 0000000000000000 / sess ffff8ae14801e000 from port 21:32:01:02:ad:f7:ee:b8 loop_id 0x04 s_id 01:02:01 logout 1 keep 0 els_logo 0 ? __switch_to+0x10c/0x450 ? process_one_work+0x1a7/0x360 qla2xxx [0000:12:00.1]-207d:3: FCPort 21:32:01:02:ad:f7:ee:b8 state transitioned from ONLINE to LOST - portid=010201. ? worker_thread+0x1ce/0x390 ? create_worker+0x1a0/0x1a0 qla2xxx [0000:12:00.1]-2109:3: qla2x00_schedule_rport_del 21320102adf7eeb8. rport ffff8ae3b2312800 roles 70 ? kthread+0x10a/0x120 qla2xxx [0000:12:00.1]-2112:3: qla_nvme_unregister_remote_port: unregister remoteport on ffff8ae14801e000 21320102adf7eeb8 ? set_kthread_struct+0x40/0x40 qla2xxx [0000:12:00.1]-2110:3: remoteport_delete of ffff8ae14801e000 21320102adf7eeb8 completed. ? ret_from_fork+0x1f/0x40 qla2xxx [0000:12:00.1]-f086:3: qlt_free_session_done: waiting for sess ffff8ae14801e000 logout
The system was under memory stress where driver was not able to allocate a srb to carry out error recovery of cable pull. The failure to flush cause upper layer to start modifying scsi_cmnd. When the system free up some memory, the subsequent cable pull trigger another command flush. At this point the driver access a null pointer when attempting to dma unmap the SGL.
Add a check to make sure commands are flush back on session tear down to prevent the null pointer access.
--- drivers/scsi/qla2xxx/qla_target.c | 10 ++++++++++ 1 file changed, 10 insertions(+)
drivers/scsi/qla2xxx/qla_target.c +10 -0
@@ -1062,6 +1062,16 @@ void qlt_free_session_done(struct work_struct *work) "%s: sess %p logout completed\n", __func__, sess); } +/* check for any straggling io left behind */ +if (!(sess->flags &FCF_FCP2_DEVICE ) && +qla2x00_eh_wait_for_pending_commands (sess->vha, sess->d_id.b24,0 ,WAIT_TARGET )) { +ql_log (ql_log_warn, vha,0x3027 , +"IO not return. Resetting.\n" ); +set_bit (ISP_ABORT_NEEDED , &vha->dpc_flags); +qla2xxx_wake_dpc (vha); +qla2x00_wait_for_chip_reset (vha); + } +if (sess->logo_ack_needed) { sess->logo_ack_needed =0 ; qla24xx_async_notify_ack(vha, sess,
Signature · 1 line
2.23.1
Nilesh Javali
maintainerPATCH v2 7/11 qla2xxx: Fix double free of the ha->vp_map pointer.
In reply to Nilesh JavaliFrom: Saurav Kashyap <[email protected]>
Coverity scan reported potential risk of double free of the pointer ha->vp_map.
ha→vp_map was freed in qla2x00_mem_alloc(), and again freed in function qla2x00_mem_free(ha).
Assign NULL to vp_map and kfree take care of NULL.
--- drivers/scsi/qla2xxx/qla_os.c | 1 + 1 file changed, 1 insertion(+)
drivers/scsi/qla2xxx/qla_os.c +1 -0
@@ -4602,6 +4602,7 @@ qla2x00_mem_alloc(struct qla_hw_data *ha, uint16_t req_len, uint16_t rsp_len, ha->init_cb_dma =0 ; fail_free_vp_map:kfree (ha->vp_map); + ha->vp_map =NULL ; fail:ql_log (ql_log_fatal,NULL ,0x0030 ,"Memory allocation failure.\n" );
Signature · 1 line
2.23.1
Nilesh Javali
maintainerPATCH v2 8/11 qla2xxx: Fix double free of fcport
In reply to Nilesh JavaliFrom: Saurav Kashyap <[email protected]>
The server was crashing after LOGO because fcport was getting freed twice.
-----------[ cut here ]-----------
kernel BUG at mm/slub.c:371!
invalid opcode: 0000 1 SMP PTI
CPU: 35 PID: 4610 Comm: bash Kdump: loaded Tainted: G OE --------- - - 4.18.0-425.3.1.el8.x86_64 #1 Hardware name: HPE ProLiant DL360 Gen10/ProLiant DL360 Gen10, BIOS U32 09/03/2021 RIP: 0010:set_freepointer.part.57+0x0/0x10 RSP: 0018:ffffb07107027d90 EFLAGS: 00010246 RAX: ffff9cb7e3150000 RBX: ffff9cb7e332b9c0 RCX: ffff9cb7e3150400 RDX: 0000000000001f37 RSI: 0000000000000000 RDI: ffff9cb7c0005500 RBP: fffff693448c5400 R08: 0000000080000000 R09: 0000000000000009 R10: 0000000000000000 R11: 0000000000132af0 R12: ffff9cb7c0005500 R13: ffff9cb7e3150000 R14: ffffffffc06990e0 R15: ffff9cb7ea85ea58 FS: 00007ff6b79c2740(0000) GS:ffff9cb8f7ec0000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 000055b426b7d700 CR3: 0000000169c18002 CR4: 00000000007706e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 PKRU: 55555554 Call Trace: kfree+0x238/0x250 qla2x00_els_dcmd_sp_free+0x20/0x230 [qla2xxx] ? qla24xx_els_dcmd_iocb+0x607/0x690 [qla2xxx] qla2x00_issue_logo+0x28c/0x2a0 [qla2xxx] ? qla2x00_issue_logo+0x28c/0x2a0 [qla2xxx] ? kernfs_fop_write+0x11e/0x1a0
Remove one of the free call and add check for valid fcport. Also use function qla2x00_free_fcport instead of kfree.
--- drivers/scsi/qla2xxx/qla_iocb.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-)
drivers/scsi/qla2xxx/qla_iocb.c +3 -2
@@ -2637,7 +2637,8 @@ static void qla2x00_els_dcmd_sp_free(srb_t *sp) {struct srb_iocb *elsio = &sp->u.iocb_cmd; -kfree (sp->fcport); +if (sp->fcport) +qla2x00_free_fcport (sp->fcport);if (elsio->u.els_logo.els_logo_pyld) dma_free_coherent(&sp->vha->hw->pdev->dev, DMA_POOL_SIZE,
@@ -2750,6 +2751,7 @@ qla24xx_els_dcmd_iocb(scsi_qla_host_t *vha, int els_opcode,if (!elsio->u.els_logo.els_logo_pyld) {/* ref: INIT */ kref_put (&sp->cmd_kref, qla2x00_sp_release); +qla2x00_free_fcport (fcport);return QLA_FUNCTION_FAILED ; }
@@ -2784,7 +2786,6 @@ qla24xx_els_dcmd_iocb(scsi_qla_host_t *vha, int els_opcode, fcport->d_id.b.area, fcport->d_id.b.al_pa);wait_for_completion (&elsio->u.els_logo.comp); -qla2x00_free_fcport (fcport);/* ref: INIT */ kref_put (&sp->cmd_kref, qla2x00_sp_release);
Signature · 1 line
2.23.1
Nilesh Javali
maintainerPATCH v2 9/11 qla2xxx: change debug message during driver unload
In reply to Nilesh JavaliFrom: Saurav Kashyap <[email protected]>
Upon driver unload, purge_mbox flag is set and the heartbeat monitor thread detects this flag and does not send the mailbox command down to FW with a debug message "Error detected: purge[1] eeh[0] cmd=0x0, Exiting". This being not a real error, change the debug message.
--- drivers/scsi/qla2xxx/qla_mbx.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/scsi/qla2xxx/qla_mbx.c +1 -1
@@ -194,7 +194,7 @@ qla2x00_mailbox_command(scsi_qla_host_t *vha, mbx_cmd_t *mcp)if (ha->flags.purge_mbox || chip_reset != ha->chip_reset || ha->flags.eeh_busy) {ql_log (ql_log_warn, vha,0xd035 , -"Error detected: purge[%d] eeh[%d] cmd=0x%x, Exiting.\n" , +"Purge mbox: purge[%d] eeh[%d] cmd=0x%x, Exiting.\n" , ha->flags.purge_mbox, ha->flags.eeh_busy, mcp->mb[0 ]); rval =QLA_ABORTED ; goto premature_exit;
Signature · 1 line
2.23.1
Nilesh Javali
maintainerPATCH v2 10/11 qla2xxx: Delay IO Abort on PCI error
In reply to Nilesh JavaliFrom: Quinn Tran <[email protected]>
Currently when PCI error is detected, IO is aborted manually through the ABORT IOCB mechanism which is not guaranteed to succeed.
Instead, wait for the OS or system to notify driver to wind down IO through the pci_error_handlers api. Set eeh_busy flag to pause all traffic and wait for IO to drain.
--- drivers/scsi/qla2xxx/qla_attr.c | 14 ++++++++++++-- 1 file changed, 12 insertions(+), 2 deletions(-)
drivers/scsi/qla2xxx/qla_attr.c +12 -2
@@ -2741,7 +2741,13 @@ qla2x00_dev_loss_tmo_callbk(struct fc_rport *rport)return ;if (unlikely (pci_channel_offline (fcport->vha->hw->pdev))) { -qla2x00_abort_all_cmds (fcport->vha,DID_NO_CONNECT <<16 ); +/* Will wait for wind down of adapter */ +ql_dbg (ql_dbg_aer, fcport->vha,0x900c , +"%s pci offline detected (id %06x)\n" , __func__, + fcport->d_id.b24); +qla_pci_set_eeh_busy (fcport->vha); +qla2x00_eh_wait_for_pending_commands (fcport->vha, fcport->d_id.b24, +0 ,WAIT_TARGET );return ; } }
@@ -2763,7 +2769,11 @@ qla2x00_terminate_rport_io(struct fc_rport *rport) vha = fcport->vha;if (unlikely (pci_channel_offline (fcport->vha->hw->pdev))) { -qla2x00_abort_all_cmds (fcport->vha,DID_NO_CONNECT <<16 ); +/* Will wait for wind down of adapter */ +ql_dbg (ql_dbg_aer, fcport->vha,0x900b , +"%s pci offline detected (id %06x)\n" , __func__, + fcport->d_id.b24); +qla_pci_set_eeh_busy (vha);qla2x00_eh_wait_for_pending_commands (fcport->vha, fcport->d_id.b24,0 ,WAIT_TARGET );return ;
Signature · 1 line
2.23.1
Nilesh Javali
maintainerPATCH v2 11/11 qla2xxx: Update version to 10.02.09.200-k
In reply to Nilesh Javali--- drivers/scsi/qla2xxx/qla_version.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)
drivers/scsi/qla2xxx/qla_version.h +2 -2
@@ -6,9 +6,9 @@/* * Driver version */ -#define QLA2XXX_VERSION "10.02.09.100-k" +#define QLA2XXX_VERSION "10.02.09.200-k"#define QLA_DRIVER_MAJOR_VER 10#define QLA_DRIVER_MINOR_VER 2#define QLA_DRIVER_PATCH_VER 9 -#define QLA_DRIVER_BETA_VER 100 +#define QLA_DRIVER_BETA_VER 200
Signature · 1 line
2.23.1
Martin K. Petersen
AppliedNilesh,
Quoted 2 lines
Please apply the qla2xxx driver miscellaneous bug fixes to the scsi tree at your earliest convenience.
Applied to 6.9/scsi-staging, thanks!
Signature · 1 line
Martin K. Petersen Oracle Linux Engineering