summaryrefslogtreecommitdiffstats
path: root/drivers/scsi/lpfc
AgeCommit message (Collapse)AuthorFilesLines
2019-10-24scsi: lpfc: lpfc_attr: Fix Use plain integer as NULL pointerSaurav Girepunje1-1/+1
Replace assignment of 0 to pointer with NULL assignment. Link: https://lore.kernel.org/r/20191024025726.GA31421@saurav Signed-off-by: Saurav Girepunje <saurav.girepunje@gmail.com> Acked-by: Dick Kennedy <dick.kennedy@broadcom.com> Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
2019-10-24scsi: lpfc: Update lpfc version to 12.6.0.0James Smart1-1/+1
Update lpfc version to 12.6.0.0 Link: https://lore.kernel.org/r/20191018211832.7917-17-jsmart2021@gmail.com Signed-off-by: Dick Kennedy <dick.kennedy@broadcom.com> Signed-off-by: James Smart <jsmart2021@gmail.com> Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
2019-10-24scsi: lpfc: Add additional discovery log messagesJames Smart3-9/+62
When debugging a recent discovery customer problem it was very hard to tell what was happening with the existing discovery log messages. To fully debug the issue additional log messages were necessary. Add or extend log messages so that sufficient information is present for debugging. Link: https://lore.kernel.org/r/20191018211832.7917-16-jsmart2021@gmail.com Signed-off-by: Dick Kennedy <dick.kennedy@broadcom.com> Signed-off-by: James Smart <jsmart2021@gmail.com> Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
2019-10-24scsi: lpfc: Add FC-AL support to lpe32000 modelsJames Smart6-1/+142
In the past, the lpe32000 models, based their main support being for 32G, and as FC-AL is not supported in the FC standards past 8G, did not support FC-AL operation. This patch adds private-loop FC-AL support for the LPE32000 adapters when a link is 8G or below. To avoid conditions where link rate may change, which would cause non-connectivity to the AL device, FC-AL mode must become a persistent setting and the link kept at a speed supporting FC-AL. The patch: - Adds a pls attribute indicating whether the adapter properly supports FC-AL. - Adds support for the adapter to indicate that topology should be fixed and the topology types to be configured. - Adds a pt attribute to report the persistent topology if present. Link: https://lore.kernel.org/r/20191018211832.7917-15-jsmart2021@gmail.com Signed-off-by: Dick Kennedy <dick.kennedy@broadcom.com> Signed-off-by: James Smart <jsmart2021@gmail.com> Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
2019-10-24scsi: lpfc: Add FA-WWN Async Event reportingJames Smart2-0/+11
Add decode support for adapter Async Events which report FA-WWN configuration errors. Link: https://lore.kernel.org/r/20191018211832.7917-14-jsmart2021@gmail.com Signed-off-by: Dick Kennedy <dick.kennedy@broadcom.com> Signed-off-by: James Smart <jsmart2021@gmail.com> Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
2019-10-24scsi: lpfc: Add log macros to allow print by serverity or verbosity settingJames Smart1-0/+17
Add two new macros to aid in message logging: Both macros print a message if the corresponding lpfc verbosity setting is set or the kernel log level is WARNING or more critical. One macro is for use with a phba structure, the other with a vport structure. [mkp: typo] Link: https://lore.kernel.org/r/20191018211832.7917-13-jsmart2021@gmail.com Signed-off-by: Dick Kennedy <dick.kennedy@broadcom.com> Signed-off-by: James Smart <jsmart2021@gmail.com> Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
2019-10-24scsi: lpfc: Make FW logging dynamically configurableJames Smart5-10/+204
Currently, the FW logging facility is a load/boot time parameter which requires the driver to be unloaded/reloaded or the system rebooted in order to change its configuration. Convert the logging facility to allow dynamic enablement and configuration. Specifically: - Convert the feature so that it can be enabled dynamically via an attribute. Additionally, the size of the buffer can be configured dynamically. - Add locks around states that now may be changing. - Tie the feature into debugfs so that the logs can be read at any time. Link: https://lore.kernel.org/r/20191018211832.7917-12-jsmart2021@gmail.com Signed-off-by: Dick Kennedy <dick.kennedy@broadcom.com> Signed-off-by: James Smart <jsmart2021@gmail.com> Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
2019-10-24scsi: lpfc: Revise interrupt coalescing for missing scenariosJames Smart4-32/+24
The existing "auto eq delay" mechanism was sometimes skipping over an EQ, not ramping the coalescing down under light load fast enough, and in other cases never kicked in as cpu sharing by multiple vectors didn't quite add up right. Tweak the interrupt mechanism such that: - Add a flag to the EQ to force checking for colaescing values when being serviced in the interrupt handler. The flag will be set by any CQ bound to the EQ whenever the number of CQ elements process in a single scan meets or exceeds the hardware queue notify level. E.g. there's a significant number of completions happening. - In the heartbeat work item that checks coalescing: - Replace the structure that was counting the number of EQs that interrupted on a single cpu with a new structure that looks at the EQ to see whether EQ currently has a coalescing value (thus it should be re-evaluate) or was marked by the new flag indicating heavy completions. - When a cpu, which may be servicing multiple vectors, had at least 1 EQ that should be checked, a new coalescing delay is calculated based on the number of interrupts that occurred on the cpu. - The new coalescing value is then applied to the EQs that had interrupted on the cpu. Link: https://lore.kernel.org/r/20191018211832.7917-11-jsmart2021@gmail.com Signed-off-by: Dick Kennedy <dick.kennedy@broadcom.com> Signed-off-by: James Smart <jsmart2021@gmail.com> Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
2019-10-24scsi: lpfc: Remove lock contention target write pathJames Smart5-54/+14
Lower IOps performance with write operations. Perf tool shows lock contention in dma_pool_alloc and dma_pool_free related to the txrdy_payload_pool. The allocations are for dma buffers for XFER_RDY's, which actually are not needed for the FCP_TRECEIVE command as the command contents are used by the adapter to generate the IU. Remove the allocations and the associated buffer pool. Rather than leaving NULLs in buffer pointer locations, set command and sgl to indicate skipped SGLE indexes. Link: https://lore.kernel.org/r/20191018211832.7917-10-jsmart2021@gmail.com Signed-off-by: Dick Kennedy <dick.kennedy@broadcom.com> Signed-off-by: James Smart <jsmart2021@gmail.com> Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
2019-10-24scsi: lpfc: Slight fast-path performance optimizationsJames Smart2-9/+10
Slightly rework some error check code paths for better streamlining. Added compiler unlikely hints to allow slightly better optimization of the fast-path. Removed a few pointer checks that were obviously already valid. Link: https://lore.kernel.org/r/20191018211832.7917-9-jsmart2021@gmail.com Signed-off-by: Dick Kennedy <dick.kennedy@broadcom.com> Signed-off-by: James Smart <jsmart2021@gmail.com> Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
2019-10-24scsi: lpfc: fix coverity error of dereference after null checkJames Smart1-2/+2
Log message conditional upon vport being NULL dereferences vport to determine log verbose setting. Changed to use lpfc_print_log which uses phba to determine the active log verbose setting. Fixes: 43bfea1bffb6 ("scsi: lpfc: Fix coverity errors on NULL pointer checks") Link: https://lore.kernel.org/r/20191018211832.7917-8-jsmart2021@gmail.com Signed-off-by: Dick Kennedy <dick.kennedy@broadcom.com> Signed-off-by: James Smart <jsmart2021@gmail.com> Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
2019-10-24scsi: lpfc: Fix hardlockup in lpfc_abort_handlerJames Smart1-2/+3
In lpfc_abort_handler, the lock acquire order is hbalock (irqsave), buf_lock (irq) and ring_lock (irq). The issue is that in two places the locks are released out of order - the buf_lock and the hbalock - resulting in the cpu preemption/lock flags getting restored out of order and deadlocking the cpu. Fix the unlock order by fully releasing the hbalocks as well. CC: Zhangguanghui <zhang.guanghui@h3c.com> Link: https://lore.kernel.org/r/20191018211832.7917-7-jsmart2021@gmail.com Signed-off-by: Dick Kennedy <dick.kennedy@broadcom.com> Signed-off-by: James Smart <jsmart2021@gmail.com> Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
2019-10-24scsi: lpfc: Fix bad ndlp ptr in xri aborted handlingJames Smart3-7/+12
In cases where I/O may be aborted, such as driver unload or link bounces, the system will crash based on a bad ndlp pointer. Example: RIP: 0010:lpfc_sli4_abts_err_handler+0x15/0x140 [lpfc] ... lpfc_sli4_io_xri_aborted+0x20d/0x270 [lpfc] lpfc_sli4_sp_handle_abort_xri_wcqe.isra.54+0x84/0x170 [lpfc] lpfc_sli4_fp_handle_cqe+0xc2/0x480 [lpfc] __lpfc_sli4_process_cq+0xc6/0x230 [lpfc] __lpfc_sli4_hba_process_cq+0x29/0xc0 [lpfc] process_one_work+0x14c/0x390 Crash was caused by a bad ndlp address passed to I/O indicated by the XRI aborted CQE. The address was not NULL so the routine deferenced the ndlp ptr. The bad ndlp also caused the lpfc_sli4_io_xri_aborted to call an erroneous io handler. Root cause for the bad ndlp was an lpfc_ncmd that was aborted, put on the abort_io list, completed, taken off the abort_io list, sent to lpfc_release_nvme_buf where it was put back on the abort_io list because the lpfc_ncmd->flags setting LPFC_SBUF_XBUSY was not cleared on the final completion. Rework the exchange busy handling to ensure the flags are properly set for both scsi and nvme. Fixes: c490850a0947 ("scsi: lpfc: Adapt partitioned XRI lists to efficient sharing") Cc: <stable@vger.kernel.org> # v5.1+ Link: https://lore.kernel.org/r/20191018211832.7917-6-jsmart2021@gmail.com Signed-off-by: Dick Kennedy <dick.kennedy@broadcom.com> Signed-off-by: James Smart <jsmart2021@gmail.com> Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
2019-10-24scsi: lpfc: Fix SLI3 hba in loop mode not discovering devicesJames Smart1-1/+3
When operating in private loop mode, PLOGI exchanges are racing and the driver tries to abort it's PLOGI. But the PLOGI abort ends up terminating the login with the other end causing the other end to abort its PLOGI as well. Discovery never fully completes. Fix by disabling the PLOGI abort when private loop and letting the state machine play out. Link: https://lore.kernel.org/r/20191018211832.7917-5-jsmart2021@gmail.com Signed-off-by: Dick Kennedy <dick.kennedy@broadcom.com> Signed-off-by: James Smart <jsmart2021@gmail.com> Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
2019-10-24scsi: lpfc: Fix lockdep errors in sli_ringtx_putJames Smart1-3/+7
Fix lockdep error in __lpfc_sli_ringtx_put(): The hbalock is valid for sli3, but not for sli4. Change lockdep to look at ring lock if sli4. Also update comment in __lpfc_sli_issue_iocb_s4() to reflect proper lock. Note: lockdep check is already correct. Link: https://lore.kernel.org/r/20191018211832.7917-4-jsmart2021@gmail.com Signed-off-by: Dick Kennedy <dick.kennedy@broadcom.com> Signed-off-by: James Smart <jsmart2021@gmail.com> Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
2019-10-24scsi: lpfc: Fix reporting of read-only fw error errorsJames Smart2-20/+50
When the adapter FW is administratively set to RO mode, a FW update triggered by the driver's sysfs attribute will fail. Currently, the driver's logging mechanism does not properly parse the adapter return codes and print a meaningful message. This oversight prevents quick diagnosis in the field. Parse the adapter return codes for Write_Object and write an appropriate message to the system console. [mkp: typo] Link: https://lore.kernel.org/r/20191018211832.7917-3-jsmart2021@gmail.com Signed-off-by: Dick Kennedy <dick.kennedy@broadcom.com> Signed-off-by: James Smart <jsmart2021@gmail.com> Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
2019-10-24scsi: lpfc: fix lpfc_nvmet_mrq to be bound by hdw queue countJames Smart2-7/+5
Currently, lpfc_nvmet_mrq is always scaled back to the min(lpfc_nvmet_mrq, lpfc_irq_chann). There's no reason to reduce it to the number of interrupt vectors. Rather, it should be scaled down based on the number of hardware queues for the system (if lower than max of 16). Change scaling to use hardware queue count rather than interrupt vector count. Link: https://lore.kernel.org/r/20191018211832.7917-2-jsmart2021@gmail.com Signed-off-by: Dick Kennedy <dick.kennedy@broadcom.com> Signed-off-by: James Smart <jsmart2021@gmail.com> Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
2019-10-22scsi: lpfc: Honor module parameter lpfc_use_adiscDaniel Wagner1-2/+2
The initial lpfc_desc_set_adisc implementation in commit dea3101e0a5c ("lpfc: add Emulex FC driver version 8.0.28") enabled ADISC if cfg_use_adisc && RSCN_MODE && FCP_2_DEVICE In commit 92d7f7b0cde3 ("[SCSI] lpfc: NPIV: add NPIV support on top of SLI-3") this changed to (cfg_use_adisc && RSC_MODE) || FCP_2_DEVICE and later in commit ffc954936b13 ("[SCSI] lpfc 8.3.13: FC Discovery Fixes and enhancements.") to (cfg_use_adisc && RSC_MODE) || (FCP_2_DEVICE && FCP_TARGET) A customer reports that after a devloss, an ADISC failure is logged. It turns out the ADISC flag is set even the user explicitly set lpfc_use_adisc = 0. [Sat Dec 22 22:55:58 2018] lpfc 0000:82:00.0: 2:(0):0203 Devloss timeout on WWPN 50:01:43:80:12:8e:40:20 NPort x05df00 Data: x82000000 x8 xa [Sat Dec 22 23:08:20 2018] lpfc 0000:82:00.0: 2:(0):2755 ADISC failure DID:05DF00 Status:x9/x70000 [mkp: fixed Hannes' email] Fixes: 92d7f7b0cde3 ("[SCSI] lpfc: NPIV: add NPIV support on top of SLI-3") Cc: Dick Kennedy <dick.kennedy@broadcom.com> Cc: James Smart <james.smart@broadcom.com> Link: https://lore.kernel.org/r/20191022072112.132268-1-dwagner@suse.de Reviewed-by: Hannes Reinecke <hare@suse.de> Reviewed-by: James Smart <james.smart@broadcom.com> Signed-off-by: Daniel Wagner <dwagner@suse.de> Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
2019-10-18scsi: lpfc: Check queue pointer before useDaniel Wagner1-1/+1
The queue pointer might not be valid. The rest of the code checks the pointer before accessing it. lpfc_sli4_process_missed_mbox_completions is the only place where the check is missing. Fixes: 657add4e5e15 ("scsi: lpfc: Fix poor use of hardware queues if fewer irq vectors") Cc: James Smart <jsmart2021@gmail.com> Link: https://lore.kernel.org/r/20191018162111.8798-1-dwagner@suse.de Signed-off-by: Daniel Wagner <dwagner@suse.de> Reviewed-by: James Smart <james.smart@broadcom.com> Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
2019-10-17scsi: lpfc: remove left-over BUILD_NVME definesHannes Reinecke2-4/+0
The BUILD_NVME define never got defined anywhere, causing NVMe commands to be treated as SCSI commands when freeing the buffers. This was causing a stuck discovery and a horrible crash in lpfc_set_rrq_active() later on. Link: https://lore.kernel.org/r/20191017150019.75769-1-hare@suse.de Fixes: c00f62e6c546 ("scsi: lpfc: Merge per-protocol WQ/CQ pairs into single per-cpu pair") Signed-off-by: Hannes Reinecke <hare@suse.com> Reviewed-by: James Smart <james.smart@broadcom.com> Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
2019-10-09scsi: lpfc: Make function lpfc_defer_pt2pt_acc staticzhengbin1-1/+1
Fix sparse warnings: drivers/scsi/lpfc/lpfc_nportdisc.c:290:1: warning: symbol 'lpfc_defer_pt2pt_acc' was not declared. Should it be static? Link: https://lore.kernel.org/r/1570183477-137273-1-git-send-email-zhengbin13@huawei.com Reported-by: Hulk Robot <hulkci@huawei.com> Signed-off-by: zhengbin <zhengbin13@huawei.com> Reviewed-by: Dick Kennedy <dick.kennedy@broadcom.com> Reviewed-by: James Smart <james.smart@broadcom.com> Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
2019-09-30scsi: lpfc: Update lpfc version to 12.4.0.1James Smart1-1/+1
Update lpfc version to 12.4.0.1 Link: https://lore.kernel.org/r/20190922035906.10977-21-jsmart2021@gmail.com Signed-off-by: Dick Kennedy <dick.kennedy@broadcom.com> Signed-off-by: James Smart <jsmart2021@gmail.com> Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
2019-09-30scsi: lpfc: cleanup: remove unused fcp_txcmlpq_cntJames Smart1-3/+1
Local variable fcp_txcmplq_cnt is initialized to 0 and then displayed in lpfc driver message 0387. Presumed residual (or unused) code from previous commit. Removed fcp_txcmplq_cnt. Link: https://lore.kernel.org/r/20190922035906.10977-20-jsmart2021@gmail.com Signed-off-by: Dick Kennedy <dick.kennedy@broadcom.com> Signed-off-by: James Smart <jsmart2021@gmail.com> Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
2019-09-30scsi: lpfc: Complete removal of FCoE T10 PI support on SLI-4 adaptersJames Smart1-3/+14
T10 PI support on SLI-4-based FCoE adapters is not supported. A prior commit in the 12.4.0.0 stream added device recognition that would prevent T10 PI enablement. However, it didn't contain a complete device list. Thus some SLI-4 FCoE adapters still had T10 PI enabled. Fix by expanding the device list that identifies FCoE devices. Link: https://lore.kernel.org/r/20190922035906.10977-19-jsmart2021@gmail.com Signed-off-by: Dick Kennedy <dick.kennedy@broadcom.com> Signed-off-by: James Smart <jsmart2021@gmail.com> Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
2019-09-30scsi: lpfc: Update async event loggingJames Smart2-6/+12
This patch updates ACQE handling for: - an EEPROM failure error reported by the adapter. - ensures that all data for any ACQE, recognized or not, is logged. - Given that all data is now logged unconditionally, the default case (unrecognized) data can be reduced. Link: https://lore.kernel.org/r/20190922035906.10977-18-jsmart2021@gmail.com Signed-off-by: Dick Kennedy <dick.kennedy@broadcom.com> Signed-off-by: James Smart <jsmart2021@gmail.com> Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
2019-09-30scsi: lpfc: Fix list corruption detected in lpfc_put_sgl_per_hdwqJames Smart1-7/+7
In lpfc_release_io_buf, an lpfc_io_buf is returned to the 'available' pool before any associated sgl or cmd and rsp buffers are returned via their respective 'put' routines. If xri rebalancing occurs and an lpfc_io_buf structure is reused quickly, there may be a race condition between release of old and association of new resources. Re-ordered lpfc_release_io_buf to release sgl and cmd/rsp buffer lists before releasing the lpfc_io_buf structure for re-use. Fixes: d79c9e9d4b3d ("scsi: lpfc: Support dynamic unbounded SGL lists on G7 hardware.") Link: https://lore.kernel.org/r/20190922035906.10977-17-jsmart2021@gmail.com Signed-off-by: Dick Kennedy <dick.kennedy@broadcom.com> Signed-off-by: James Smart <jsmart2021@gmail.com> Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
2019-09-30scsi: lpfc: Fix hdwq sgl locks and irq handlingJames Smart1-16/+22
Many of the sgl-per-hdwq paths are locking with spin_lock_irq() and spin_unlock_irq() and may unwittingly raising irq when it shouldn't. Hard deadlocks were seen around lpfc_scsi_prep_cmnd(). Fix by converting the locks to irqsave/irqrestore. Fixes: d79c9e9d4b3d ("scsi: lpfc: Support dynamic unbounded SGL lists on G7 hardware.") Link: https://lore.kernel.org/r/20190922035906.10977-16-jsmart2021@gmail.com Signed-off-by: Dick Kennedy <dick.kennedy@broadcom.com> Signed-off-by: James Smart <jsmart2021@gmail.com> Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
2019-09-30scsi: lpfc: Fix spinlock_irq issues in lpfc_els_flush_cmd()James Smart1-7/+9
While reviewing the CT behavior, issues with spinlock_irq were seen. The driver should be using spinlock_irqsave/irqrestore in the els flush routine. Changed to spinlock_irqsave/irqrestore. Link: https://lore.kernel.org/r/20190922035906.10977-15-jsmart2021@gmail.com Signed-off-by: Dick Kennedy <dick.kennedy@broadcom.com> Signed-off-by: James Smart <jsmart2021@gmail.com> Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
2019-09-30scsi: lpfc: Fix list corruption in lpfc_sli_get_iocbqJames Smart4-4/+13
After study, it was determined there was a double free of a CT iocb during execution of lpfc_offline_prep and lpfc_offline. The prep routine issued an abort for some CT iocbs, but the aborts did not complete fast enough for a subsequent routine that waits for completion. Thus the driver proceeded to lpfc_offline, which releases any pending iocbs. Unfortunately, the completions for the aborts were then received which re-released the ct iocbs. Turns out the issue for why the aborts didn't complete fast enough was not their time on the wire/in the adapter. It was the lpfc_work_done routine, which requires the adapter state to be UP before it calls lpfc_sli_handle_slow_ring_event() to process the completions. The issue is the prep routine takes the link down as part of it's processing. To fix, the following was performed: - Prevent the offline routine from releasing iocbs that have had aborts issued on them. Defer to the abort completions. Also means the driver fully waits for the completions. Given this change, the recognition of "driver-generated" status which then releases the iocb is no longer valid. As such, the change made in the commit 296012285c90 is reverted. As recognition of "driver-generated" status is no longer valid, this patch reverts the changes made in commit 296012285c90 ("scsi: lpfc: Fix leak of ELS completions on adapter reset") - Modify lpfc_work_done to allow slow path completions so that the abort completions aren't ignored. - Updated the fdmi path to recognize a CT request that fails due to the port being unusable. This stops FDMI retries. FDMI will be restarted on next link up. Link: https://lore.kernel.org/r/20190922035906.10977-14-jsmart2021@gmail.com Signed-off-by: Dick Kennedy <dick.kennedy@broadcom.com> Signed-off-by: James Smart <jsmart2021@gmail.com> Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
2019-09-30scsi: lpfc: Fix host hang at boot or slow bootJames Smart1-6/+36
Scenarios were seen where a host hung when the system booted or the host was very slow in booting. The link would not come up and no luns were visible to the host. After investigation, this was found to be due to the introduction of a new ACQE that adapter may generate to report a adapter hw warning. The ACQE was delivered to the driver very early in adapter initialization, when the driver did not expect command completion. As part of handling this unexpected interrupt the an EQEs are consumed and discarded and the EQ rearmed. The issue is the CQ that cause the EQE and thus the interrupt was not processed and the CQ was left unarmed. Meaning it would no longer generate a new interrupt condition. Subsequent mailbox commands used to initialize the adapter use the same CQ, and as there was no completion interrupt generated, the driver never saw the mailbox commands complete and it would wait long command timeouts. Fix by having the early flush routine also process the related CQ and rearm the CQ. Link: https://lore.kernel.org/r/20190922035906.10977-13-jsmart2021@gmail.com Signed-off-by: Dick Kennedy <dick.kennedy@broadcom.com> Signed-off-by: James Smart <jsmart2021@gmail.com> Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
2019-09-30scsi: lpfc: Fix coverity errors on NULL pointer checksJames Smart4-8/+27
Coverity flagged several scenarios where checking of null pointer values wasn't consistent. Fix the code to that be consistent on checking. Link: https://lore.kernel.org/r/20190922035906.10977-12-jsmart2021@gmail.com Signed-off-by: Dick Kennedy <dick.kennedy@broadcom.com> Signed-off-by: James Smart <jsmart2021@gmail.com> Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
2019-09-30scsi: lpfc: Fix NVMe ABTS in response to receiving an ABTSJames Smart4-63/+46
When the port, running as a nvme target, receives an ABTS, it submits commands to the adapter to Abort i/o outstanding in the adapter. The Abort command formatting routine left a command field set to zero, which instructs the adapter to generate an ABTS on the wire as part of cleaning up the I/O. This is common operation for an initiator, but not for a target. Fix the driver to check whether an ABTS had been received for the I/O, and if so, change the Abort command formatting so that the ABTS generation is disabled (IA=1). No need to ABTS it when the other side already has. Also refactored the code such that there is a single routine being used for nvme or nvmet ABORT requests, and IA is an argument. Link: https://lore.kernel.org/r/20190922035906.10977-11-jsmart2021@gmail.com Signed-off-by: Dick Kennedy <dick.kennedy@broadcom.com> Signed-off-by: James Smart <jsmart2021@gmail.com> Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
2019-09-30scsi: lpfc: Fix discovery failures when target device connectivity bouncesJames Smart1-1/+6
An issue was seen discovering all SCSI Luns when a target device undergoes link bounce. The driver currently does not qualify the FC4 support on the target. Therefore it will send a SCSI PRLI and an NVMe PRLI. The expectation is that the target will reject the PRLI if it is not supported. If a PRLI times out, the driver will retry. The driver will not proceed with the device until both SCSI and NVMe PRLIs are resolved. In the failure case, the device is FCP only and does not respond to the NVMe PRLI, thus initiating the wait/retry loop in the driver. During that time, a RSCN is received (device bounced) causing the driver to issue a GID_FT. The GID_FT response comes back before the PRLI mess is resolved and it prematurely cancels the PRLI retry logic and leaves the device in a STE_PRLI_ISSUE state. Discovery with the target never completes or resets. Fix by resetting the node state back to STE_NPR_NODE when GID_FT completes, thereby restarting the discovery process for the node. Link: https://lore.kernel.org/r/20190922035906.10977-10-jsmart2021@gmail.com Signed-off-by: Dick Kennedy <dick.kennedy@broadcom.com> Signed-off-by: James Smart <jsmart2021@gmail.com> Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
2019-09-30scsi: lpfc: Fix GPF on scsi command completionJames Smart1-5/+5
Faults are seen with RIP of lpfc_scsi_cmd_iocb_cmpl(). The failure is when lpfc_update_status is being called as part of the completion. After debugging, it was seen the issue was the shost pointer that the driver derived from the scsi cmd. The crash showed the cmd->device pointer being bogus, which is likely as the scsi devices were offlined prior. The bogus device pointer caused subsequent pointers derived from the location, specifically the vport, to be bogus. Fix by adjusting the calling sequence to pass in the vport rather than having to derive it from the cmd structure. Link: https://lore.kernel.org/r/20190922035906.10977-9-jsmart2021@gmail.com Signed-off-by: Dick Kennedy <dick.kennedy@broadcom.com> Signed-off-by: James Smart <jsmart2021@gmail.com> Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
2019-09-30scsi: lpfc: Fix locking on mailbox command completionJames Smart1-1/+7
Symptoms were seen of the driver not having valid data for mailbox commands. After debugging, the following sequence was found: The driver maintains a port-wide pointer of the mailbox command that is currently in execution. Once finished, the port-wide pointer is cleared (done in lpfc_sli4_mq_release()). The next mailbox command issued will set the next pointer and so on. The mailbox response data is only copied if there is a valid port-wide pointer. In the failing case, it was seen that a new mailbox command was being attempted in parallel with the completion. The parallel path was seeing the mailbox no long in use (flag check under lock) and thus set the port pointer. The completion path had cleared the active flag under lock, but had not touched the port pointer. The port pointer is cleared after the lock is released. In this case, the completion path cleared the just-set value by the parallel path. Fix by making the calls that clear mbox state/port pointer while under lock. Also slightly cleaned up the error path. Link: https://lore.kernel.org/r/20190922035906.10977-8-jsmart2021@gmail.com Signed-off-by: Dick Kennedy <dick.kennedy@broadcom.com> Signed-off-by: James Smart <jsmart2021@gmail.com> Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
2019-09-30scsi: lpfc: Fix device recovery errors after PLOGI failuresJames Smart3-37/+55
When target-side fault injections are made, the driver isn't reconnecting to the remote port. The driver is logging "2753" error messages which state: "PLOGI failure DID:1B2400 Status:x3/xf0240008" The failures status is indicating a Illegal field error, which points to the Temporary RPI field being used for the ELS. This error typically means the driver used an RPI that was already registered (shouldn't be registered if using it in this context). Study has found that if the driver were in discovery attempts and encountered an error, it wouldn't flag the temporary rpi in error. Yet the rpi was released for reallocation in these error paths and another ELS could allocate the rpi. In the failure situation a retry was done on an ELS that had encountered an error, and as the rpi wasn't marked in error, the ELS reused the rpi it originally allocated. But that rpi had been allocated by a different ELS issued after the original error and before the retry attempt. The different ELS had succeeded and the RPI was registered. Fix by marking the rpi state for the node to be in error, aka as needing reallocation, upon an error in the els processing. Error state marking is always done prior to release back to the internal rpi free list, which the driver wasn't doing in cases prior. Also enhanced some of the logging to help in the next case of problem troubleshooting. Link: https://lore.kernel.org/r/20190922035906.10977-7-jsmart2021@gmail.com Signed-off-by: Dick Kennedy <dick.kennedy@broadcom.com> Signed-off-by: James Smart <jsmart2021@gmail.com> Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
2019-09-30scsi: lpfc: Fix rpi release when deleting vportJames Smart2-29/+61
A prior use-after-free mailbox fix solved it's problem by null'ing a ndlp pointer. However, further testing has shown that this change causes a later state change to occasionally be skipped, which results in a reference count never being decremented thus the rpi is never released, which causes a vport delete to never succeed. Revise the fix in the prior patch to no longer null the ndlp. Instead the RELEASE_RPI flag is set which will drive the release of the rpi. Given the new code was added at a deep indentation level, refactor the code block using a new routine that avoids the indentation issues. Fixes: 9b1640686470 ("scsi: lpfc: Fix use-after-free mailbox cmd completion") Link: https://lore.kernel.org/r/20190922035906.10977-6-jsmart2021@gmail.com Signed-off-by: Dick Kennedy <dick.kennedy@broadcom.com> Signed-off-by: James Smart <jsmart2021@gmail.com> Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
2019-09-30scsi: lpfc: Fix NVME io abort failures causing hangsJames Smart4-18/+14
The nvme-fc transport may call to abort an io on controller reset. If the driver is out of resources to issue an abort command, it just gives up and does nothing. The transport expects the lldd to always be able to terminate an io it has issued. At that point, the controller hangs waiting for aborted ios to be returned. Note: flaged by "6136" and "6176" error messages. Root issue was the adapter mis-allocated the number resources it allocated for command entries for the adapter. Convert the driver to allocate command resources based on the number of xris supported by the FC port - 1 resource for the original command and 1 resource for the abort request. Link: https://lore.kernel.org/r/20190922035906.10977-5-jsmart2021@gmail.com Signed-off-by: Dick Kennedy <dick.kennedy@broadcom.com> Signed-off-by: James Smart <jsmart2021@gmail.com> Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
2019-09-30scsi: lpfc: Fix miss of register read failure checkJames Smart1-4/+6
Coverity flagged missing status check on register read that flags a poisoned data return value. Add checking of register read status. Link: https://lore.kernel.org/r/20190922035906.10977-4-jsmart2021@gmail.com Signed-off-by: Dick Kennedy <dick.kennedy@broadcom.com> Signed-off-by: James Smart <jsmart2021@gmail.com> Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
2019-09-30scsi: lpfc: Fix premature re-enabling of interrupts in lpfc_sli_host_downJames Smart1-2/+2
Use of spin_lock_irq may re-enable interrupts prematurely. Convert to spin_lock. Note: code is under the phba->hba_lock which has been locked with irqsave. Link: https://lore.kernel.org/r/20190922035906.10977-3-jsmart2021@gmail.com Signed-off-by: Dick Kennedy <dick.kennedy@broadcom.com> Signed-off-by: James Smart <jsmart2021@gmail.com> Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
2019-09-30scsi: lpfc: Fix pt2pt discovery on SLI3 HBAsJames Smart1-26/+115
After exchanging PLOGI on an SLI-3 adapter, the PRLI exchange failed. Link trace showed the port was assigned a non-zero n_port_id, but didn't use the address on the PRLI. The assigned address is set on the port by the CONFIG_LINK mailbox command. The driver responded to the PRLI before the mailbox command completed. Thus the PRLI response used the old n_port_id. Defer the PRLI response until CONFIG_LINK completes. Link: https://lore.kernel.org/r/20190922035906.10977-2-jsmart2021@gmail.com Signed-off-by: Dick Kennedy <dick.kennedy@broadcom.com> Signed-off-by: James Smart <jsmart2021@gmail.com> Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
2019-09-21Merge tag 'scsi-misc' of git://git.kernel.org/pub/scm/linux/kernel/git/jejb/scsiLinus Torvalds23-1498/+1974
Pull SCSI updates from James Bottomley: "This is mostly update of the usual drivers: qla2xxx, ufs, smartpqi, lpfc, hisi_sas, qedf, mpt3sas; plus a whole load of minor updates. The only core change this time around is the addition of request batching for virtio. Since batching requires an additional flag to use, it should be invisible to the rest of the drivers" * tag 'scsi-misc' of git://git.kernel.org/pub/scm/linux/kernel/git/jejb/scsi: (264 commits) scsi: hisi_sas: Fix the conflict between device gone and host reset scsi: hisi_sas: Add BIST support for phy loopback scsi: hisi_sas: Add hisi_sas_debugfs_alloc() to centralise allocation scsi: hisi_sas: Remove some unused function arguments scsi: hisi_sas: Remove redundant work declaration scsi: hisi_sas: Remove hisi_sas_hw.slot_complete scsi: hisi_sas: Assign NCQ tag for all NCQ commands scsi: hisi_sas: Update all the registers after suspend and resume scsi: hisi_sas: Retry 3 times TMF IO for SAS disks when init device scsi: hisi_sas: Remove sleep after issue phy reset if sas_smp_phy_control() fails scsi: hisi_sas: Directly return when running I_T_nexus reset if phy disabled scsi: hisi_sas: Use true/false as input parameter of sas_phy_reset() scsi: hisi_sas: add debugfs auto-trigger for internal abort time out scsi: virtio_scsi: unplug LUNs when events missed scsi: scsi_dh_rdac: zero cdb in send_mode_select() scsi: fcoe: fix null-ptr-deref Read in fc_release_transport scsi: ufs-hisi: use devm_platform_ioremap_resource() to simplify code scsi: ufshcd: use devm_platform_ioremap_resource() to simplify code scsi: hisi_sas: use devm_platform_ioremap_resource() to simplify code scsi: ufs: Use kmemdup in ufshcd_read_string_desc() ...
2019-09-07scsi: lpfc: Fix reset recovery paths that are not recoveringJames Smart1-4/+5
A recent patch unconditionally marks the hba as in error as part of resetting the adapter. The driver flow that called the adapter reset was a recovery path, which expects the adapter to not be in an error state in order to finish the recovery. Given the new error state being set, the recovery fails and the adapter is left in limbo. Revise the adapter reset routine so that it will only mark the adapter in error if it was unable to reset the adapter. Fixes: 8c24a4f643ed ("scsi: lpfc: Fix crash due to port reset racing vs adapter error handling") Link: https://lore.kernel.org/r/20190903215441.10490-1-jsmart2021@gmail.com Signed-off-by: Dick Kennedy <dick.kennedy@broadcom.com> Signed-off-by: James Smart <jsmart2021@gmail.com> Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
2019-09-07scsi: lpfc: Convert existing %pf users to %psSakari Ailus2-3/+3
Convert the remaining %pf users to %ps to prepare for the removal of the old %pf conversion specifier support. Fixes: 323506644972 ("scsi: lpfc: Migrate to %px and %pf in kernel print calls") Link: https://lore.kernel.org/r/20190904160423.3865-1-sakari.ailus@linux.intel.com Signed-off-by: Sakari Ailus <sakari.ailus@linux.intel.com> Reviewed-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com> Reviewed-by: James Smart <james.smart@broadcom.com> Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
2019-08-29scsi: lpfc: fix 12.4.0.0 GPF at bootJames Smart1-1/+1
The 12.4.0.0 patch that merged WQ/CQ pairs into single per-cpu pair contained a bug: a local variable was set to the queue pair by index. This should have allowed the local variable to be natively used. Instead, the code reused the index relative to the local variable, obtaining a random pointer value that when used eventually faulted the system Convert offending code to use local variable. Fixes: c00f62e6c546 ("scsi: lpfc: Merge per-protocol WQ/CQ pairs into single per-cpu pair") Signed-off-by: Dick Kennedy <dick.kennedy@broadcom.com> Signed-off-by: James Smart <jsmart2021@gmail.com> Tested-by: Abdul Haleem <abdhalee@linux.vnet.ibm.com> Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
2019-08-29scsi: lpfc: Raise config max for lpfc_fcp_mq_threshold variableJames Smart2-2/+2
Raise the config max for lpfc_fcp_mq_threshold variable to 256. Signed-off-by: Dick Kennedy <dick.kennedy@broadcom.com> Signed-off-by: James Smart <jsmart2021@gmail.com> CC: Hannes Reinecke <hare@suse.de> Reviewed-by: Hannes Reinecke <hare@suse.com> Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
2019-08-29scsi: lpfc: Remove bg debugfs buffersJames Smart5-295/+0
Capturing and downloading dif command data and dif data was done a dozen years ago and no longer being used. Also creates a potential security hole. Remove the debugfs buffer for dif debugging. Signed-off-by: Dick Kennedy <dick.kennedy@broadcom.com> Signed-off-by: James Smart <jsmart2021@gmail.com> CC: KyleMahlkuch <kmahlkuc@linux.vnet.ibm.com> CC: Hannes Reinecke <hare@suse.de> Reviewed-by: Hannes Reinecke <hare@suse.com> Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
2019-08-29scsi: lpfc: Resolve checker warning for lpfc_new_io_buf()James Smart2-13/+1
Per Dan Carpenter: The patch d79c9e9d4b3d: "scsi: lpfc: Support dynamic unbounded SGL lists on G7 hardware." from Aug 14, 2019, leads to the following static checker warning: drivers/scsi/lpfc/lpfc_init.c:4107 lpfc_new_io_buf() error: not allocating enough data 784 vs 768 There was no need to compare sizes nor to allocate size based on a define. Change allocation to use actual structure length Signed-off-by: Dick Kennedy <dick.kennedy@broadcom.com> Signed-off-by: James Smart <jsmart2021@gmail.com> CC: Dan Carpenter <dan.carpenter@oracle.com> Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
2019-08-19scsi: lpfc: Update lpfc version to 12.4.0.0James Smart1-1/+1
Update lpfc version to 12.4.0.0 Signed-off-by: Dick Kennedy <dick.kennedy@broadcom.com> Signed-off-by: James Smart <jsmart2021@gmail.com> Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
2019-08-19scsi: lpfc: Merge per-protocol WQ/CQ pairs into single per-cpu pairJames Smart10-557/+218
Currently, each hardware queue, typically allocated per-cpu, consists of a WQ/CQ pair per protocol. Meaning if both SCSI and NVMe are supported 2 WQ/CQ pairs will exist for the hardware queue. Separate queues are unnecessary. The current implementation wastes memory backing the 2nd set of queues, and the use of double the SLI-4 WQ/CQ's means less hardware queues can be supported which means there may not always be enough to have a pair per cpu. If there is only 1 pair per cpu, more cpu's may get their own WQ/CQ. Rework the implementation to use a single WQ/CQ pair by both protocols. Signed-off-by: Dick Kennedy <dick.kennedy@broadcom.com> Signed-off-by: James Smart <jsmart2021@gmail.com> Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
generated by cgit v1.2.3 (git 2.39.1) at 2024-10-20 21:21:45 +0000