From 4dc2757a2e9a9d1f2faee4fc6119276fc0061c16 Mon Sep 17 00:00:00 2001 From: "Kashyap, Desai" Date: Tue, 4 Jan 2011 11:32:13 +0530 Subject: [PATCH 1/9] [SCSI] mpt2sas: Fix device removal handshake for zoned devices When zoning end devices, the driver is not sending device removal handshake alogrithm to firmware. This results in controller firmware not sending sas topology add events the next time the device is added. The fix is the driver should be doing the device removal handshake even though the PHYSTATUS_VACANT bit is set in the PhyStatus of the event data. The current design is avoiding the handshake when the VACANT bit is set in the phy status. Signed-off-by: Kashyap Desai Cc: stable@kernel.org Signed-off-by: James Bottomley --- drivers/scsi/mpt2sas/mpt2sas_scsih.c | 3 --- 1 file changed, 3 deletions(-) diff --git a/drivers/scsi/mpt2sas/mpt2sas_scsih.c b/drivers/scsi/mpt2sas/mpt2sas_scsih.c index eda347c57979..95d82743d7b1 100644 --- a/drivers/scsi/mpt2sas/mpt2sas_scsih.c +++ b/drivers/scsi/mpt2sas/mpt2sas_scsih.c @@ -2981,9 +2981,6 @@ _scsih_check_topo_delete_events(struct MPT2SAS_ADAPTER *ioc, u16 handle; for (i = 0 ; i < event_data->NumEntries; i++) { - if (event_data->PHY[i].PhyStatus & - MPI2_EVENT_SAS_TOPO_PHYSTATUS_VACANT) - continue; handle = le16_to_cpu(event_data->PHY[i].AttachedDevHandle); if (!handle) continue; From efe82a16bc0f9f9e1fc8fa706eb0309fcd57770a Mon Sep 17 00:00:00 2001 From: "Kashyap, Desai" Date: Tue, 4 Jan 2011 11:34:17 +0530 Subject: [PATCH 2/9] [SCSI] mpt2sas: fix internal device reset for older firmware prior to MPI Rev K The "internal device reset complete" event is not supported for older firmware prior to MPI Rev K We added a check in the driver so the "internal device reset" event is ignored for older firmware. When ignored, the tm_busy flag doesn't get set nor cleared. Without this fix, IO queues would be froozen indefinetly after the "internal device reset" event, as the "complete" event never sent to clear the flag. Signed-off-by: Kashyap Desai Cc: stable@kernel.org Signed-off-by: James Bottomley --- drivers/scsi/mpt2sas/mpt2sas_scsih.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/drivers/scsi/mpt2sas/mpt2sas_scsih.c b/drivers/scsi/mpt2sas/mpt2sas_scsih.c index 95d82743d7b1..a16f2a05736f 100644 --- a/drivers/scsi/mpt2sas/mpt2sas_scsih.c +++ b/drivers/scsi/mpt2sas/mpt2sas_scsih.c @@ -5002,6 +5002,12 @@ _scsih_sas_device_status_change_event(struct MPT2SAS_ADAPTER *ioc, event_data); #endif + /* In MPI Revision K (0xC), the internal device reset complete was + * implemented, so avoid setting tm_busy flag for older firmware. + */ + if ((ioc->facts.HeaderVersion >> 8) < 0xC) + return; + if (event_data->ReasonCode != MPI2_EVENT_SAS_DEV_STAT_RC_INTERNAL_DEVICE_RESET && event_data->ReasonCode != From 11e1b961ab067ee3acaf723531da4d3f23e1d6f7 Mon Sep 17 00:00:00 2001 From: "Kashyap, Desai" Date: Tue, 4 Jan 2011 11:34:57 +0530 Subject: [PATCH 3/9] [SCSI] mpt2sas: Correct resizing calculation for max_queue_depth The ioc->hba_queue_depth is not properly resized when the controller firmware reports that it supports more outstanding IO than what can be fit inside the reply descriptor pool depth. This is reproduced by setting the controller global credits larger than 30,000. The bug results in an incorrect sizing of the queues. The fix is to resize the queue_size by dividing queue_diff by two. Signed-off-by: Kashyap Desai Cc: stable@kernel.org Signed-off-by: James Bottomley --- drivers/scsi/mpt2sas/mpt2sas_base.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/scsi/mpt2sas/mpt2sas_base.c b/drivers/scsi/mpt2sas/mpt2sas_base.c index b2a817055b8b..a11ac6701043 100644 --- a/drivers/scsi/mpt2sas/mpt2sas_base.c +++ b/drivers/scsi/mpt2sas/mpt2sas_base.c @@ -2176,9 +2176,9 @@ _base_allocate_memory_pools(struct MPT2SAS_ADAPTER *ioc, int sleep_flag) /* adjust hba_queue_depth, reply_free_queue_depth, * and queue_size */ - ioc->hba_queue_depth -= queue_diff; - ioc->reply_free_queue_depth -= queue_diff; - queue_size -= queue_diff; + ioc->hba_queue_depth -= (queue_diff / 2); + ioc->reply_free_queue_depth -= (queue_diff / 2); + queue_size = facts->MaxReplyDescriptorPostQueueDepth; } ioc->reply_post_queue_depth = queue_size; From ec07a053597bdab51cbd23619f9f9f392712508a Mon Sep 17 00:00:00 2001 From: "Kashyap, Desai" Date: Wed, 5 Jan 2011 17:54:32 +0530 Subject: [PATCH 4/9] [SCSI] mpt2sas: Fix the race between broadcast asyn event and scsi command completion False timeout after hard resets, there were two issues which leads to timeout. (1) Panic because of invalid memory access in the broadcast asyn event processing routine due to a race between accessing the scsi command pointer from broadcast asyn event processing thread and completing the same scsi command from the interrupt context. (2) Broadcast asyn event notifcations are not handled due to events ignored while the broadcast asyn event is activity being processed from the event process kernel thread. In addition, changed the ABRT_TASK_SET to ABORT_TASK in the broadcast async event processing routine. This is less disruptive to other request that generate Broadcast Asyn Primitives besides target reset. e.g clear reservations, microcode download,and mode select. Signed-off-by: Kashyap Desai Cc: stable@kernel.org Signed-off-by: James Bottomley --- drivers/scsi/mpt2sas/mpt2sas_scsih.c | 54 +++++++++++++++++++++++----- 1 file changed, 45 insertions(+), 9 deletions(-) diff --git a/drivers/scsi/mpt2sas/mpt2sas_scsih.c b/drivers/scsi/mpt2sas/mpt2sas_scsih.c index a16f2a05736f..db287d79bdcf 100644 --- a/drivers/scsi/mpt2sas/mpt2sas_scsih.c +++ b/drivers/scsi/mpt2sas/mpt2sas_scsih.c @@ -819,7 +819,7 @@ _scsih_is_end_device(u32 device_info) } /** - * mptscsih_get_scsi_lookup - returns scmd entry + * _scsih_scsi_lookup_get - returns scmd entry * @ioc: per adapter object * @smid: system request message index * @@ -831,6 +831,28 @@ _scsih_scsi_lookup_get(struct MPT2SAS_ADAPTER *ioc, u16 smid) return ioc->scsi_lookup[smid - 1].scmd; } +/** + * _scsih_scsi_lookup_get_clear - returns scmd entry + * @ioc: per adapter object + * @smid: system request message index + * + * Returns the smid stored scmd pointer. + * Then will derefrence the stored scmd pointer. + */ +static inline struct scsi_cmnd * +_scsih_scsi_lookup_get_clear(struct MPT2SAS_ADAPTER *ioc, u16 smid) +{ + unsigned long flags; + struct scsi_cmnd *scmd; + + spin_lock_irqsave(&ioc->scsi_lookup_lock, flags); + scmd = ioc->scsi_lookup[smid - 1].scmd; + ioc->scsi_lookup[smid - 1].scmd = NULL; + spin_unlock_irqrestore(&ioc->scsi_lookup_lock, flags); + + return scmd; +} + /** * _scsih_scsi_lookup_find_by_scmd - scmd lookup * @ioc: per adapter object @@ -3207,7 +3229,7 @@ _scsih_flush_running_cmds(struct MPT2SAS_ADAPTER *ioc) u16 count = 0; for (smid = 1; smid <= ioc->scsiio_depth; smid++) { - scmd = _scsih_scsi_lookup_get(ioc, smid); + scmd = _scsih_scsi_lookup_get_clear(ioc, smid); if (!scmd) continue; count++; @@ -3801,7 +3823,7 @@ _scsih_io_done(struct MPT2SAS_ADAPTER *ioc, u16 smid, u8 msix_index, u32 reply) u32 response_code = 0; mpi_reply = mpt2sas_base_get_reply_virt_addr(ioc, reply); - scmd = _scsih_scsi_lookup_get(ioc, smid); + scmd = _scsih_scsi_lookup_get_clear(ioc, smid); if (scmd == NULL) return 1; @@ -5102,6 +5124,7 @@ _scsih_sas_broadcast_primative_event(struct MPT2SAS_ADAPTER *ioc, struct fw_event_work *fw_event) { struct scsi_cmnd *scmd; + struct scsi_device *sdev; u16 smid, handle; u32 lun; struct MPT2SAS_DEVICE *sas_device_priv_data; @@ -5112,12 +5135,17 @@ _scsih_sas_broadcast_primative_event(struct MPT2SAS_ADAPTER *ioc, Mpi2EventDataSasBroadcastPrimitive_t *event_data = fw_event->event_data; #endif u16 ioc_status; + unsigned long flags; + int r; + dewtprintk(ioc, printk(MPT2SAS_INFO_FMT "broadcast primative: " "phy number(%d), width(%d)\n", ioc->name, event_data->PhyNum, event_data->PortWidth)); dtmprintk(ioc, printk(MPT2SAS_INFO_FMT "%s: enter\n", ioc->name, __func__)); + spin_lock_irqsave(&ioc->scsi_lookup_lock, flags); + ioc->broadcast_aen_busy = 0; termination_count = 0; query_count = 0; mpi_reply = ioc->tm_cmds.reply; @@ -5125,7 +5153,8 @@ _scsih_sas_broadcast_primative_event(struct MPT2SAS_ADAPTER *ioc, scmd = _scsih_scsi_lookup_get(ioc, smid); if (!scmd) continue; - sas_device_priv_data = scmd->device->hostdata; + sdev = scmd->device; + sas_device_priv_data = sdev->hostdata; if (!sas_device_priv_data || !sas_device_priv_data->sas_target) continue; /* skip hidden raid components */ @@ -5141,6 +5170,7 @@ _scsih_sas_broadcast_primative_event(struct MPT2SAS_ADAPTER *ioc, lun = sas_device_priv_data->lun; query_count++; + spin_unlock_irqrestore(&ioc->scsi_lookup_lock, flags); mpt2sas_scsih_issue_tm(ioc, handle, 0, 0, lun, MPI2_SCSITASKMGMT_TASKTYPE_QUERY_TASK, smid, 30, NULL); ioc->tm_cmds.status = MPT2_CMD_NOT_USED; @@ -5150,14 +5180,20 @@ _scsih_sas_broadcast_primative_event(struct MPT2SAS_ADAPTER *ioc, (mpi_reply->ResponseCode == MPI2_SCSITASKMGMT_RSP_TM_SUCCEEDED || mpi_reply->ResponseCode == - MPI2_SCSITASKMGMT_RSP_IO_QUEUED_ON_IOC)) + MPI2_SCSITASKMGMT_RSP_IO_QUEUED_ON_IOC)) { + spin_lock_irqsave(&ioc->scsi_lookup_lock, flags); continue; - - mpt2sas_scsih_issue_tm(ioc, handle, 0, 0, lun, - MPI2_SCSITASKMGMT_TASKTYPE_ABRT_TASK_SET, 0, 30, NULL); + } + r = mpt2sas_scsih_issue_tm(ioc, handle, sdev->channel, sdev->id, + sdev->lun, MPI2_SCSITASKMGMT_TASKTYPE_ABORT_TASK, smid, 30, + scmd); + if (r == FAILED) + sdev_printk(KERN_WARNING, sdev, "task abort: FAILED " + "scmd(%p)\n", scmd); termination_count += le32_to_cpu(mpi_reply->TerminationCount); + spin_lock_irqsave(&ioc->scsi_lookup_lock, flags); } - ioc->broadcast_aen_busy = 0; + spin_unlock_irqrestore(&ioc->scsi_lookup_lock, flags); dtmprintk(ioc, printk(MPT2SAS_INFO_FMT "%s - exit, query_count = %d termination_count = %d\n", From 4224489f45b503f0a1f1cf310f76dc108f45689a Mon Sep 17 00:00:00 2001 From: "Kashyap, Desai" Date: Tue, 4 Jan 2011 11:38:39 +0530 Subject: [PATCH 5/9] [SCSI] mpt2sas: Kernel Panic during Large Topology discovery There was a configuration page timing out during the initial port enable at driver load time. The port enable would fail, and this would result in the driver unloading itself, meanwhile the driver was accessing freed memory in another context resulting in the panic. The fix is to prevent access to freed memory once the driver had issued the diag reset which woke up the sleeping port enable process. The routine _base_reset_handler was reorganized so the last sleeping process woken up was the port_enable. Signed-off-by: Kashyap Desai Cc: stable@kernel.org Signed-off-by: James Bottomley --- drivers/scsi/mpt2sas/mpt2sas_base.c | 13 +++++++++++-- 1 file changed, 11 insertions(+), 2 deletions(-) diff --git a/drivers/scsi/mpt2sas/mpt2sas_base.c b/drivers/scsi/mpt2sas/mpt2sas_base.c index a11ac6701043..9ead0399808a 100644 --- a/drivers/scsi/mpt2sas/mpt2sas_base.c +++ b/drivers/scsi/mpt2sas/mpt2sas_base.c @@ -3941,6 +3941,8 @@ mpt2sas_base_detach(struct MPT2SAS_ADAPTER *ioc) static void _base_reset_handler(struct MPT2SAS_ADAPTER *ioc, int reset_phase) { + mpt2sas_scsih_reset_handler(ioc, reset_phase); + mpt2sas_ctl_reset_handler(ioc, reset_phase); switch (reset_phase) { case MPT2_IOC_PRE_RESET: dtmprintk(ioc, printk(MPT2SAS_INFO_FMT "%s: " @@ -3971,8 +3973,6 @@ _base_reset_handler(struct MPT2SAS_ADAPTER *ioc, int reset_phase) "MPT2_IOC_DONE_RESET\n", ioc->name, __func__)); break; } - mpt2sas_scsih_reset_handler(ioc, reset_phase); - mpt2sas_ctl_reset_handler(ioc, reset_phase); } /** @@ -4026,6 +4026,7 @@ mpt2sas_base_hard_reset_handler(struct MPT2SAS_ADAPTER *ioc, int sleep_flag, { int r; unsigned long flags; + u8 pe_complete = ioc->wait_for_port_enable_to_complete; dtmprintk(ioc, printk(MPT2SAS_INFO_FMT "%s: enter\n", ioc->name, __func__)); @@ -4068,6 +4069,14 @@ mpt2sas_base_hard_reset_handler(struct MPT2SAS_ADAPTER *ioc, int sleep_flag, if (r) goto out; _base_reset_handler(ioc, MPT2_IOC_AFTER_RESET); + + /* If this hard reset is called while port enable is active, then + * there is no reason to call make_ioc_operational + */ + if (pe_complete) { + r = -EFAULT; + goto out; + } r = _base_make_ioc_operational(ioc, sleep_flag); if (!r) _base_reset_handler(ioc, MPT2_IOC_DONE_RESET); From 3a9c913a3e57b170887d39456e04c18f2305ec67 Mon Sep 17 00:00:00 2001 From: "Kashyap, Desai" Date: Tue, 4 Jan 2011 11:40:23 +0530 Subject: [PATCH 6/9] [SCSI] mpt2sas: fix Integrated Raid unsynced on shutdown problem Issue: IR shutdown(sending) and IR shutdown(complete) messages not listed in /var/log/messages when driver is removed. The driver needs to issue a MPI2_RAID_ACTION_SYSTEM_SHUTDOWN_INITIATED request when the driver is unloaded so the IR metadata journal is updated. If this request is not sent, then the volume would need a "check consistency" issued on the next bootup if the volume was roamed from one initiator to another. The current driver supports this feature only when the system is rebooted, however this also need to be supported if the driver is unloaded Fix: To fix this issue, the driver is going to need to call the _scsih_ir_shutdown prior to reporting the volumes missing from the OS, hence the device handles are still present. Signed-off-by: Kashyap Desai Cc: stable@kernel.org Signed-off-by: James Bottomley --- drivers/scsi/mpt2sas/mpt2sas_scsih.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/scsi/mpt2sas/mpt2sas_scsih.c b/drivers/scsi/mpt2sas/mpt2sas_scsih.c index db287d79bdcf..5ded3db6e316 100644 --- a/drivers/scsi/mpt2sas/mpt2sas_scsih.c +++ b/drivers/scsi/mpt2sas/mpt2sas_scsih.c @@ -6665,6 +6665,7 @@ _scsih_remove(struct pci_dev *pdev) destroy_workqueue(wq); /* release all the volumes */ + _scsih_ir_shutdown(ioc); list_for_each_entry_safe(raid_device, next, &ioc->raid_device_list, list) { if (raid_device->starget) { From 97b991277a9966333b3bcea0d972822278780694 Mon Sep 17 00:00:00 2001 From: NickCheng Date: Thu, 6 Jan 2011 17:32:41 +0800 Subject: [PATCH 7/9] [SCSI] arcmsr: Fix the issue of system hangup after commands timeout on ARC-1200 [jejb: fix up patch problems and checkpatch.pl issues] Signed-off-by: Nick Cheng Signed-off-by: James Bottomley --- drivers/scsi/arcmsr/arcmsr.h | 11 +-- drivers/scsi/arcmsr/arcmsr_attr.c | 2 +- drivers/scsi/arcmsr/arcmsr_hba.c | 114 +++++++++++------------------- 3 files changed, 49 insertions(+), 78 deletions(-) diff --git a/drivers/scsi/arcmsr/arcmsr.h b/drivers/scsi/arcmsr/arcmsr.h index 475c31ae985c..77b26f5b9c33 100644 --- a/drivers/scsi/arcmsr/arcmsr.h +++ b/drivers/scsi/arcmsr/arcmsr.h @@ -2,7 +2,7 @@ ******************************************************************************* ** O.S : Linux ** FILE NAME : arcmsr.h -** BY : Erich Chen +** BY : Nick Cheng ** Description: SCSI RAID Device Driver for ** ARECA RAID Host adapter ******************************************************************************* @@ -46,8 +46,12 @@ struct device_attribute; /*The limit of outstanding scsi command that firmware can handle*/ #define ARCMSR_MAX_OUTSTANDING_CMD 256 -#define ARCMSR_MAX_FREECCB_NUM 320 -#define ARCMSR_DRIVER_VERSION "Driver Version 1.20.00.15 2010/02/02" +#ifdef CONFIG_XEN + #define ARCMSR_MAX_FREECCB_NUM 160 +#else + #define ARCMSR_MAX_FREECCB_NUM 320 +#endif +#define ARCMSR_DRIVER_VERSION "Driver Version 1.20.00.15 2010/08/05" #define ARCMSR_SCSI_INITIATOR_ID 255 #define ARCMSR_MAX_XFER_SECTORS 512 #define ARCMSR_MAX_XFER_SECTORS_B 4096 @@ -60,7 +64,6 @@ struct device_attribute; #define ARCMSR_MAX_HBB_POSTQUEUE 264 #define ARCMSR_MAX_XFER_LEN 0x26000 /* 152K */ #define ARCMSR_CDB_SG_PAGE_LENGTH 256 -#define SCSI_CMD_ARECA_SPECIFIC 0xE1 #ifndef PCI_DEVICE_ID_ARECA_1880 #define PCI_DEVICE_ID_ARECA_1880 0x1880 #endif diff --git a/drivers/scsi/arcmsr/arcmsr_attr.c b/drivers/scsi/arcmsr/arcmsr_attr.c index a4e04c50c436..acdae33de521 100644 --- a/drivers/scsi/arcmsr/arcmsr_attr.c +++ b/drivers/scsi/arcmsr/arcmsr_attr.c @@ -2,7 +2,7 @@ ******************************************************************************* ** O.S : Linux ** FILE NAME : arcmsr_attr.c -** BY : Erich Chen +** BY : Nick Cheng ** Description: attributes exported to sysfs and device host ******************************************************************************* ** Copyright (C) 2002 - 2005, Areca Technology Corporation All rights reserved diff --git a/drivers/scsi/arcmsr/arcmsr_hba.c b/drivers/scsi/arcmsr/arcmsr_hba.c index 1cadcd6b7da6..984bd527c6c9 100644 --- a/drivers/scsi/arcmsr/arcmsr_hba.c +++ b/drivers/scsi/arcmsr/arcmsr_hba.c @@ -2,7 +2,7 @@ ******************************************************************************* ** O.S : Linux ** FILE NAME : arcmsr_hba.c -** BY : Erich Chen +** BY : Nick Cheng ** Description: SCSI RAID Device Driver for ** ARECA RAID Host adapter ******************************************************************************* @@ -76,7 +76,7 @@ MODULE_DESCRIPTION("ARECA (ARC11xx/12xx/16xx/1880) SATA/SAS RAID Host Bus Adapte MODULE_LICENSE("Dual BSD/GPL"); MODULE_VERSION(ARCMSR_DRIVER_VERSION); static int sleeptime = 10; -static int retrycount = 30; +static int retrycount = 12; wait_queue_head_t wait_q; static int arcmsr_iop_message_xfer(struct AdapterControlBlock *acb, struct scsi_cmnd *cmd); @@ -187,7 +187,6 @@ int arcmsr_sleep_for_bus_reset(struct scsi_cmnd *cmd) if (isleep > 0) { msleep(isleep*1000); } - printk(KERN_NOTICE "wake-up\n"); return 0; } @@ -921,7 +920,6 @@ static void arcmsr_report_ccb_state(struct AdapterControlBlock *acb, } static void arcmsr_drain_donequeue(struct AdapterControlBlock *acb, struct CommandControlBlock *pCCB, bool error) - { int id, lun; if ((pCCB->acb != acb) || (pCCB->startdone != ARCMSR_CCB_START)) { @@ -948,7 +946,7 @@ static void arcmsr_drain_donequeue(struct AdapterControlBlock *acb, struct Comma , pCCB->startdone , atomic_read(&acb->ccboutstandingcount)); return; - } + } arcmsr_report_ccb_state(acb, pCCB, error); } @@ -981,7 +979,7 @@ static void arcmsr_done4abort_postqueue(struct AdapterControlBlock *acb) case ACB_ADAPTER_TYPE_B: { struct MessageUnit_B *reg = acb->pmuB; /*clear all outbound posted Q*/ - writel(ARCMSR_DOORBELL_INT_CLEAR_PATTERN, ®->iop2drv_doorbell); /* clear doorbell interrupt */ + writel(ARCMSR_DOORBELL_INT_CLEAR_PATTERN, reg->iop2drv_doorbell); /* clear doorbell interrupt */ for (i = 0; i < ARCMSR_MAX_HBB_POSTQUEUE; i++) { if ((flag_ccb = readl(®->done_qbuffer[i])) != 0) { writel(0, ®->done_qbuffer[i]); @@ -1511,7 +1509,6 @@ static void arcmsr_hba_postqueue_isr(struct AdapterControlBlock *acb) arcmsr_drain_donequeue(acb, pCCB, error); } } - static void arcmsr_hbb_postqueue_isr(struct AdapterControlBlock *acb) { uint32_t index; @@ -2106,10 +2103,6 @@ static int arcmsr_queue_command_lck(struct scsi_cmnd *cmd, if (atomic_read(&acb->ccboutstandingcount) >= ARCMSR_MAX_OUTSTANDING_CMD) return SCSI_MLQUEUE_HOST_BUSY; - if ((scsicmd == SCSI_CMD_ARECA_SPECIFIC)) { - printk(KERN_NOTICE "Receiveing SCSI_CMD_ARECA_SPECIFIC command..\n"); - return 0; - } ccb = arcmsr_get_freeccb(acb); if (!ccb) return SCSI_MLQUEUE_HOST_BUSY; @@ -2393,6 +2386,7 @@ static int arcmsr_polling_hbb_ccbdone(struct AdapterControlBlock *acb, int index, rtn; bool error; polling_hbb_ccb_retry: + poll_count++; /* clear doorbell interrupt */ writel(ARCMSR_DOORBELL_INT_CLEAR_PATTERN, reg->iop2drv_doorbell); @@ -2663,6 +2657,7 @@ static void arcmsr_request_hba_device_map(struct AdapterControlBlock *acb) { struct MessageUnit_A __iomem *reg = acb->pmuA; if (unlikely(atomic_read(&acb->rq_map_token) == 0) || ((acb->acb_flags & ACB_F_BUS_RESET) != 0 ) || ((acb->acb_flags & ACB_F_ABORT) != 0 )){ + mod_timer(&acb->eternal_timer, jiffies + msecs_to_jiffies(6 * HZ)); return; } else { acb->fw_flag = FW_NORMAL; @@ -2670,8 +2665,10 @@ static void arcmsr_request_hba_device_map(struct AdapterControlBlock *acb) atomic_set(&acb->rq_map_token, 16); } atomic_set(&acb->ante_token_value, atomic_read(&acb->rq_map_token)); - if (atomic_dec_and_test(&acb->rq_map_token)) + if (atomic_dec_and_test(&acb->rq_map_token)) { + mod_timer(&acb->eternal_timer, jiffies + msecs_to_jiffies(6 * HZ)); return; + } writel(ARCMSR_INBOUND_MESG0_GET_CONFIG, ®->inbound_msgaddr0); mod_timer(&acb->eternal_timer, jiffies + msecs_to_jiffies(6 * HZ)); } @@ -2682,15 +2679,18 @@ static void arcmsr_request_hbb_device_map(struct AdapterControlBlock *acb) { struct MessageUnit_B __iomem *reg = acb->pmuB; if (unlikely(atomic_read(&acb->rq_map_token) == 0) || ((acb->acb_flags & ACB_F_BUS_RESET) != 0 ) || ((acb->acb_flags & ACB_F_ABORT) != 0 )){ + mod_timer(&acb->eternal_timer, jiffies + msecs_to_jiffies(6 * HZ)); return; } else { acb->fw_flag = FW_NORMAL; if (atomic_read(&acb->ante_token_value) == atomic_read(&acb->rq_map_token)) { - atomic_set(&acb->rq_map_token,16); + atomic_set(&acb->rq_map_token, 16); } atomic_set(&acb->ante_token_value, atomic_read(&acb->rq_map_token)); - if(atomic_dec_and_test(&acb->rq_map_token)) + if (atomic_dec_and_test(&acb->rq_map_token)) { + mod_timer(&acb->eternal_timer, jiffies + msecs_to_jiffies(6 * HZ)); return; + } writel(ARCMSR_MESSAGE_GET_CONFIG, reg->drv2iop_doorbell); mod_timer(&acb->eternal_timer, jiffies + msecs_to_jiffies(6 * HZ)); } @@ -2701,6 +2701,7 @@ static void arcmsr_request_hbc_device_map(struct AdapterControlBlock *acb) { struct MessageUnit_C __iomem *reg = acb->pmuC; if (unlikely(atomic_read(&acb->rq_map_token) == 0) || ((acb->acb_flags & ACB_F_BUS_RESET) != 0) || ((acb->acb_flags & ACB_F_ABORT) != 0)) { + mod_timer(&acb->eternal_timer, jiffies + msecs_to_jiffies(6 * HZ)); return; } else { acb->fw_flag = FW_NORMAL; @@ -2708,8 +2709,10 @@ static void arcmsr_request_hbc_device_map(struct AdapterControlBlock *acb) atomic_set(&acb->rq_map_token, 16); } atomic_set(&acb->ante_token_value, atomic_read(&acb->rq_map_token)); - if (atomic_dec_and_test(&acb->rq_map_token)) + if (atomic_dec_and_test(&acb->rq_map_token)) { + mod_timer(&acb->eternal_timer, jiffies + msecs_to_jiffies(6 * HZ)); return; + } writel(ARCMSR_INBOUND_MESG0_GET_CONFIG, ®->inbound_msgaddr0); writel(ARCMSR_HBCMU_DRV2IOP_MESSAGE_CMD_DONE, ®->inbound_doorbell); mod_timer(&acb->eternal_timer, jiffies + msecs_to_jiffies(6 * HZ)); @@ -2897,6 +2900,8 @@ static uint8_t arcmsr_iop_reset(struct AdapterControlBlock *acb) uint32_t intmask_org; uint8_t rtnval = 0x00; int i = 0; + unsigned long flags; + if (atomic_read(&acb->ccboutstandingcount) != 0) { /* disable all outbound interrupt */ intmask_org = arcmsr_disable_outbound_ints(acb); @@ -2907,7 +2912,12 @@ static uint8_t arcmsr_iop_reset(struct AdapterControlBlock *acb) for (i = 0; i < ARCMSR_MAX_FREECCB_NUM; i++) { ccb = acb->pccb_pool[i]; if (ccb->startdone == ARCMSR_CCB_START) { - arcmsr_ccb_complete(ccb); + scsi_dma_unmap(ccb->pcmd); + ccb->startdone = ARCMSR_CCB_DONE; + ccb->ccb_flags = 0; + spin_lock_irqsave(&acb->ccblist_lock, flags); + list_add_tail(&ccb->list, &acb->ccb_free_list); + spin_unlock_irqrestore(&acb->ccblist_lock, flags); } } atomic_set(&acb->ccboutstandingcount, 0); @@ -2920,8 +2930,7 @@ static uint8_t arcmsr_iop_reset(struct AdapterControlBlock *acb) static int arcmsr_bus_reset(struct scsi_cmnd *cmd) { - struct AdapterControlBlock *acb = - (struct AdapterControlBlock *)cmd->device->host->hostdata; + struct AdapterControlBlock *acb; uint32_t intmask_org, outbound_doorbell; int retry_count = 0; int rtn = FAILED; @@ -2971,31 +2980,16 @@ sleep_again: atomic_set(&acb->rq_map_token, 16); atomic_set(&acb->ante_token_value, 16); acb->fw_flag = FW_NORMAL; - init_timer(&acb->eternal_timer); - acb->eternal_timer.expires = jiffies + msecs_to_jiffies(6*HZ); - acb->eternal_timer.data = (unsigned long) acb; - acb->eternal_timer.function = &arcmsr_request_device_map; - add_timer(&acb->eternal_timer); + mod_timer(&acb->eternal_timer, jiffies + msecs_to_jiffies(6 * HZ)); acb->acb_flags &= ~ACB_F_BUS_RESET; rtn = SUCCESS; printk(KERN_ERR "arcmsr: scsi bus reset eh returns with success\n"); } else { acb->acb_flags &= ~ACB_F_BUS_RESET; - if (atomic_read(&acb->rq_map_token) == 0) { - atomic_set(&acb->rq_map_token, 16); - atomic_set(&acb->ante_token_value, 16); - acb->fw_flag = FW_NORMAL; - init_timer(&acb->eternal_timer); - acb->eternal_timer.expires = jiffies + msecs_to_jiffies(6*HZ); - acb->eternal_timer.data = (unsigned long) acb; - acb->eternal_timer.function = &arcmsr_request_device_map; - add_timer(&acb->eternal_timer); - } else { - atomic_set(&acb->rq_map_token, 16); - atomic_set(&acb->ante_token_value, 16); - acb->fw_flag = FW_NORMAL; - mod_timer(&acb->eternal_timer, jiffies + msecs_to_jiffies(6*HZ)); - } + atomic_set(&acb->rq_map_token, 16); + atomic_set(&acb->ante_token_value, 16); + acb->fw_flag = FW_NORMAL; + mod_timer(&acb->eternal_timer, jiffies + msecs_to_jiffies(6*HZ)); rtn = SUCCESS; } break; @@ -3007,21 +3001,10 @@ sleep_again: rtn = FAILED; } else { acb->acb_flags &= ~ACB_F_BUS_RESET; - if (atomic_read(&acb->rq_map_token) == 0) { - atomic_set(&acb->rq_map_token, 16); - atomic_set(&acb->ante_token_value, 16); - acb->fw_flag = FW_NORMAL; - init_timer(&acb->eternal_timer); - acb->eternal_timer.expires = jiffies + msecs_to_jiffies(6*HZ); - acb->eternal_timer.data = (unsigned long) acb; - acb->eternal_timer.function = &arcmsr_request_device_map; - add_timer(&acb->eternal_timer); - } else { - atomic_set(&acb->rq_map_token, 16); - atomic_set(&acb->ante_token_value, 16); - acb->fw_flag = FW_NORMAL; - mod_timer(&acb->eternal_timer, jiffies + msecs_to_jiffies(6*HZ)); - } + atomic_set(&acb->rq_map_token, 16); + atomic_set(&acb->ante_token_value, 16); + acb->fw_flag = FW_NORMAL; + mod_timer(&acb->eternal_timer, jiffies + msecs_to_jiffies(6 * HZ)); rtn = SUCCESS; } break; @@ -3067,31 +3050,16 @@ sleep: atomic_set(&acb->rq_map_token, 16); atomic_set(&acb->ante_token_value, 16); acb->fw_flag = FW_NORMAL; - init_timer(&acb->eternal_timer); - acb->eternal_timer.expires = jiffies + msecs_to_jiffies(6 * HZ); - acb->eternal_timer.data = (unsigned long) acb; - acb->eternal_timer.function = &arcmsr_request_device_map; - add_timer(&acb->eternal_timer); + mod_timer(&acb->eternal_timer, jiffies + msecs_to_jiffies(6 * HZ)); acb->acb_flags &= ~ACB_F_BUS_RESET; rtn = SUCCESS; printk(KERN_ERR "arcmsr: scsi bus reset eh returns with success\n"); } else { acb->acb_flags &= ~ACB_F_BUS_RESET; - if (atomic_read(&acb->rq_map_token) == 0) { - atomic_set(&acb->rq_map_token, 16); - atomic_set(&acb->ante_token_value, 16); - acb->fw_flag = FW_NORMAL; - init_timer(&acb->eternal_timer); - acb->eternal_timer.expires = jiffies + msecs_to_jiffies(6*HZ); - acb->eternal_timer.data = (unsigned long) acb; - acb->eternal_timer.function = &arcmsr_request_device_map; - add_timer(&acb->eternal_timer); - } else { - atomic_set(&acb->rq_map_token, 16); - atomic_set(&acb->ante_token_value, 16); - acb->fw_flag = FW_NORMAL; - mod_timer(&acb->eternal_timer, jiffies + msecs_to_jiffies(6*HZ)); - } + atomic_set(&acb->rq_map_token, 16); + atomic_set(&acb->ante_token_value, 16); + acb->fw_flag = FW_NORMAL; + mod_timer(&acb->eternal_timer, jiffies + msecs_to_jiffies(6*HZ)); rtn = SUCCESS; } break; From ac61c46f4f7665ab4548e90430c37b2529e16cff Mon Sep 17 00:00:00 2001 From: David Dillow Date: Sun, 16 Jan 2011 15:12:39 -0500 Subject: [PATCH 8/9] [SCSI] fix incorrect value of SCSI_MAX_SG_CHAIN_SEGMENTS due to include file ordering If the compiled object doesn't include linux/scatterlist.h before scsi/scsi.h, it will get an incorrect definition of SCSI_MAX_SG_CHAIN_SEGMENTS. Signed-off-by: David Dillow Cc: stable@kernel.org Signed-off-by: James Bottomley --- include/scsi/scsi.h | 1 + 1 file changed, 1 insertion(+) diff --git a/include/scsi/scsi.h b/include/scsi/scsi.h index 648d23358038..b76d4006e36d 100644 --- a/include/scsi/scsi.h +++ b/include/scsi/scsi.h @@ -9,6 +9,7 @@ #define _SCSI_SCSI_H #include +#include struct scsi_cmnd; From 9ee91f7fb550a4c82f82d9818e42493484c754af Mon Sep 17 00:00:00 2001 From: James Bottomley Date: Thu, 20 Jan 2011 17:26:44 -0600 Subject: [PATCH 9/9] [SCSI] libsas: fix runaway error handler problem libsas makes use of scsi_schedule_eh() but forgets to clear the host_eh_scheduled flag in its error handling routine. Because of this, the error handler thread never gets to sleep; it's constantly awake and trying to run the error routine leading to console spew and inability to run anything else (at least on a UP system). The fix is to clear the flag as we splice the work queue. Cc: stable@kernel.org Signed-off-by: James Bottomley --- drivers/scsi/libsas/sas_scsi_host.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/scsi/libsas/sas_scsi_host.c b/drivers/scsi/libsas/sas_scsi_host.c index 5815cbeb27a6..9a7aaf5f1311 100644 --- a/drivers/scsi/libsas/sas_scsi_host.c +++ b/drivers/scsi/libsas/sas_scsi_host.c @@ -646,6 +646,7 @@ void sas_scsi_recover_host(struct Scsi_Host *shost) spin_lock_irqsave(shost->host_lock, flags); list_splice_init(&shost->eh_cmd_q, &eh_work_q); + shost->host_eh_scheduled = 0; spin_unlock_irqrestore(shost->host_lock, flags); SAS_DPRINTK("Enter %s\n", __func__);