Limit overall SCSI EH runtime

index 19e1b42..106ff1a 100644
@@ -448,15 +448,7 @@ static int adpt_queue_lck(struct scsi_cmnd * cmd, void (*done) (struct scsi_cmnd
 	}
 
 	rmb();
-	/*
-	 * TODO: I need to block here if I am processing ioctl cmds
-	 * but if the outstanding cmds all finish before the ioctl,
-	 * the scsi-core will not know to start sending cmds to me again.
-	 * I need to a way to restart the scsi-cores queues or should I block
-	 * calling scsi_done on the outstanding cmds instead
-	 * for now we don't set the IOCTL state
-	 */
-	if(((pHba->state) & DPTI_STATE_IOCTL) || ((pHba->state) & DPTI_STATE_RESET)) {
+	if((pHba->state) & DPTI_STATE_RESET) {
 		pHba->host->last_reset = jiffies;
 		pHba->host->resetting = 1;
 		return 1;

@@ -1811,21 +1803,23 @@ static int adpt_i2o_passthru(adpt_hba* pHba, u32 __user *arg)
 	}
 
 	do {
-		if(pHba->host)
+		/*
+		 * Stop any new commands from enterring the
+		 * controller while processing the ioctl
+		 */
+		if(pHba->host) {
+			scsi_block_requests(pHba->host);
 			spin_lock_irqsave(pHba->host->host_lock, flags);
-		// This state stops any new commands from enterring the
-		// controller while processing the ioctl
-//		pHba->state |= DPTI_STATE_IOCTL;
-//		We can't set this now - The scsi subsystem sets host_blocked and
-//		the queue empties and stops.  We need a way to restart the queue
+		}
 		rcode = adpt_i2o_post_wait(pHba, msg, size, FOREVER);
 		if (rcode != 0)
 			printk("adpt_i2o_passthru: post wait failed %d %p\n",
 					rcode, reply);
-//		pHba->state &= ~DPTI_STATE_IOCTL;
-		if(pHba->host)
+		if(pHba->host) {
 			spin_unlock_irqrestore(pHba->host->host_lock, flags);
-	} while(rcode == -ETIMEDOUT);  
+			scsi_unblock_requests(pHba->host);
+		}
+	} while(rcode == -ETIMEDOUT);
 
 	if(rcode){
 		goto cleanup;

index beded71..aeb0461 100644
@@ -202,7 +202,6 @@ struct adpt_channel {
 
 // HBA state flags
 #define DPTI_STATE_RESET	(0x01)
-#define DPTI_STATE_IOCTL	(0x02)
 
 typedef struct _adpt_hba {
 	struct _adpt_hba *next;

index 106ff1a..0a2d801 100644
@@ -448,11 +448,8 @@ static int adpt_queue_lck(struct scsi_cmnd * cmd, void (*done) (struct scsi_cmnd
 	}
 
 	rmb();
-	if((pHba->state) & DPTI_STATE_RESET) {
-		pHba->host->last_reset = jiffies;
-		pHba->host->resetting = 1;
-		return 1;
-	}
+	if((pHba->state) & DPTI_STATE_RESET)
+		return SCSI_MLQUEUE_HOST_BUSY;
 
 	// TODO if the cmd->device if offline then I may need to issue a bus rescan
 	// followed by a get_lct to see if the device is there anymore

index c67e401..d814588 100644
@@ -2511,8 +2511,8 @@ static void asc_prt_scsi_host(struct Scsi_Host *s)
 	struct asc_board *boardp = shost_priv(s);
 
 	printk("Scsi_Host at addr 0x%p, device %s\n", s, dev_name(boardp->dev));
-	printk(" host_busy %u, host_no %d, last_reset %d,\n",
-	       s->host_busy, s->host_no, (unsigned)s->last_reset);
+	printk(" host_busy %u, host_no %d,\n",
+	       s->host_busy, s->host_no);
 
 	printk(" base 0x%lx, io_port 0x%lx, irq %d,\n",
 	       (ulong)s->base, (ulong)s->io_port, boardp->irq);

@@ -3345,8 +3345,8 @@ static void asc_prt_driver_conf(struct seq_file *m, struct Scsi_Host *shost)
 		shost->host_no);
 
 	seq_printf(m,
-		   " host_busy %u, last_reset %lu, max_id %u, max_lun %u, max_channel %u\n",
-		   shost->host_busy, shost->last_reset, shost->max_id,
+		   " host_busy %u, max_id %u, max_lun %u, max_channel %u\n",
+		   shost->host_busy, shost->max_id,
 		   shost->max_lun, shost->max_channel);
 
 	seq_printf(m,

index 9327f5f..1142361 100644
@@ -521,7 +521,7 @@ dc390_StartSCSI( struct dc390_acb* pACB, struct dc390_dcb* pDCB, struct dc390_sr
 	pACB->SelConn++;
 	return 1;
     }
-    if (time_before (jiffies, pACB->pScsiHost->last_reset))
+    if (time_before (jiffies, pACB->last_reset))
     {
 	DEBUG0(printk ("DC390: We were just reset and don't accept commands yet!\n"));
 	return 1;

@@ -1863,7 +1863,7 @@ dc390_ScsiRstDetect( struct dc390_acb* pACB )
     /* delay half a second */
     udelay (1000);
     DC390_write8 (ScsiCmd, CLEAR_FIFO_CMD);
-    pACB->pScsiHost->last_reset = jiffies + 5*HZ/2
+    pACB->last_reset = jiffies + 5*HZ/2
 		    + HZ * dc390_eepromBuf[pACB->AdapterIndex][EE_DELAY];
     pACB->Connected = 0;
 

@@ -2048,9 +2048,9 @@ static int DC390_bus_reset (struct scsi_cmnd *cmd)
 
 	dc390_ResetDevParam(pACB);
 	mdelay(1);
-	pACB->pScsiHost->last_reset = jiffies + 3*HZ/2 
+	pACB->last_reset = jiffies + 3*HZ/2
 		+ HZ * dc390_eepromBuf[pACB->AdapterIndex][EE_DELAY];
-    
+
 	DC390_write8(ScsiCmd, CLEAR_FIFO_CMD);
 	DC390_read8(INT_Status);		/* Reset Pending INT */
 

@@ -2383,7 +2383,7 @@ static void dc390_init_hw(struct dc390_acb *pACB, u8 index)
 	if (pACB->Gmode2 & RST_SCSI_BUS) {
 		dc390_ResetSCSIBus(pACB);
 		udelay(1000);
-		shost->last_reset = jiffies + HZ/2 +
+		pACB->last_reset = jiffies + HZ/2 +
 			HZ * dc390_eepromBuf[pACB->AdapterIndex][EE_DELAY];
 	}
 

@@ -2455,8 +2455,8 @@ static int dc390_probe_one(struct pci_dev *pdev, const struct pci_device_id *id)
 	shost->irq = pdev->irq;
 	shost->base = io_port;
 	shost->unique_id = io_port;
-	shost->last_reset = jiffies;
-	
+
+	pACB->last_reset = jiffies;
 	pACB->pScsiHost = shost;
 	pACB->IOPortBase = (u16) io_port;
 	pACB->IRQLevel = pdev->irq;

index 77adc54..3d1bb4a 100644
@@ -143,6 +143,7 @@ u8		Ignore_IRQ;	/* Not used */
 
 struct pci_dev	*pdev;
 
+unsigned long   last_reset;
 unsigned long	Cmds;
 u32		SelLost;
 u32		SelConn;

index 694e13c..42e8624 100644
@@ -308,6 +308,8 @@ struct AdapterCtlBlk {
 	struct timer_list waiting_timer;
 	struct timer_list selto_timer;
 
+	unsigned long last_reset;
+
 	u16 srb_count;
 
 	u8 sel_timeout;

@@ -860,9 +862,9 @@ static void waiting_set_timer(struct AdapterCtlBlk *acb, unsigned long to)
 	init_timer(&acb->waiting_timer);
 	acb->waiting_timer.function = waiting_timeout;
 	acb->waiting_timer.data = (unsigned long) acb;
-	if (time_before(jiffies + to, acb->scsi_host->last_reset - HZ / 2))
+	if (time_before(jiffies + to, acb->last_reset - HZ / 2))
 		acb->waiting_timer.expires =
-		    acb->scsi_host->last_reset - HZ / 2 + 1;
+		    acb->last_reset - HZ / 2 + 1;
 	else
 		acb->waiting_timer.expires = jiffies + to + 1;
 	add_timer(&acb->waiting_timer);

@@ -1319,7 +1321,7 @@ static int __dc395x_eh_bus_reset(struct scsi_cmnd *cmd)
 	udelay(500);
 
 	/* We may be in serious trouble. Wait some seconds */
-	acb->scsi_host->last_reset =
+	acb->last_reset =
 	    jiffies + 3 * HZ / 2 +
 	    HZ * acb->eeprom.delay_time;
 

@@ -1462,9 +1464,9 @@ static void selto_timer(struct AdapterCtlBlk *acb)
 	acb->selto_timer.function = selection_timeout_missed;
 	acb->selto_timer.data = (unsigned long) acb;
 	if (time_before
-	    (jiffies + HZ, acb->scsi_host->last_reset + HZ / 2))
+	    (jiffies + HZ, acb->last_reset + HZ / 2))
 		acb->selto_timer.expires =
-		    acb->scsi_host->last_reset + HZ / 2 + 1;
+		    acb->last_reset + HZ / 2 + 1;
 	else
 		acb->selto_timer.expires = jiffies + HZ + 1;
 	add_timer(&acb->selto_timer);

@@ -1535,7 +1537,7 @@ static u8 start_scsi(struct AdapterCtlBlk* acb, struct DeviceCtlBlk* dcb,
 	}
 	/* Allow starting of SCSI commands half a second before we allow the mid-level
 	 * to queue them again after a reset */
-	if (time_before(jiffies, acb->scsi_host->last_reset - HZ / 2)) {
+	if (time_before(jiffies, acb->last_reset - HZ / 2)) {
 		dprintkdbg(DBG_KG, "start_scsi: Refuse cmds (reset wait)\n");
 		return 1;
 	}

@@ -3031,7 +3033,7 @@ static void disconnect(struct AdapterCtlBlk *acb)
 		dprintkl(KERN_ERR, "disconnect: No such device\n");
 		udelay(500);
 		/* Suspend queue for a while */
-		acb->scsi_host->last_reset =
+		acb->last_reset =
 		    jiffies + HZ / 2 +
 		    HZ * acb->eeprom.delay_time;
 		clear_fifo(acb, "disconnectEx");

@@ -3053,7 +3055,7 @@ static void disconnect(struct AdapterCtlBlk *acb)
 		waiting_process_next(acb);
 	} else if (srb->state & SRB_ABORT_SENT) {
 		dcb->flag &= ~ABORT_DEV_;
-		acb->scsi_host->last_reset = jiffies + HZ / 2 + 1;
+		acb->last_reset = jiffies + HZ / 2 + 1;
 		dprintkl(KERN_ERR, "disconnect: SRB_ABORT_SENT\n");
 		doing_srb_done(acb, DID_ABORT, srb->cmd, 1);
 		waiting_process_next(acb);

@@ -3649,7 +3651,7 @@ static void scsi_reset_detect(struct AdapterCtlBlk *acb)
 	/*DC395x_write8(acb, TRM_S1040_DMA_CONTROL,STOPDMAXFER); */
 	udelay(500);
 	/* Maybe we locked up the bus? Then lets wait even longer ... */
-	acb->scsi_host->last_reset =
+	acb->last_reset =
 	    jiffies + 5 * HZ / 2 +
 	    HZ * acb->eeprom.delay_time;
 

@@ -4426,7 +4428,7 @@ static void adapter_init_scsi_host(struct Scsi_Host *host)
 	host->dma_channel = -1;
 	host->unique_id = acb->io_port_base;
 	host->irq = acb->irq_level;
-	host->last_reset = jiffies;
+	acb->last_reset = jiffies;
 
 	host->max_id = 16;
 	if (host->max_id - 1 == eeprom->scsi_id)

@@ -4484,7 +4486,7 @@ static void adapter_init_chip(struct AdapterCtlBlk *acb)
 		/*spin_unlock_irq (&io_request_lock); */
 		udelay(500);
 
-		acb->scsi_host->last_reset =
+		acb->last_reset =
 		    jiffies + HZ / 2 +
 		    HZ * acb->eeprom.delay_time;
 

index eaa808e..fe0bcb1 100644
@@ -78,11 +78,6 @@ static void scsi_done(struct scsi_cmnd *cmd);
  * Definitions and constants.
  */
 
-#define MIN_RESET_DELAY (2*HZ)
-
-/* Do not call reset on error if we just did a reset within 15 sec. */
-#define MIN_RESET_PERIOD (15*HZ)
-
 /*
  * Note - the initial logging level can be set here to log events at boot time.
  * After the system is up, you may enable logging via the /proc interface.

@@ -658,7 +653,6 @@ EXPORT_SYMBOL(scsi_cmd_get_serial);
 int scsi_dispatch_cmd(struct scsi_cmnd *cmd)
 {
 	struct Scsi_Host *host = cmd->device->host;
-	unsigned long timeout;
 	int rtn = 0;
 
 	atomic_inc(&cmd->device->iorequest_cnt);

@@ -704,28 +698,6 @@ int scsi_dispatch_cmd(struct scsi_cmnd *cmd)
 			       (cmd->device->lun << 5 & 0xe0);
 	}
 
-	/*
-	 * We will wait MIN_RESET_DELAY clock ticks after the last reset so
-	 * we can avoid the drive not being ready.
-	 */
-	timeout = host->last_reset + MIN_RESET_DELAY;
-
-	if (host->resetting && time_before(jiffies, timeout)) {
-		int ticks_remaining = timeout - jiffies;
-		/*
-		 * NOTE: This may be executed from within an interrupt
-		 * handler!  This is bad, but for now, it'll do.  The irq
-		 * level of the interrupt handler has been masked out by the
-		 * platform dependent interrupt handling code already, so the
-		 * sti() here will not cause another call to the SCSI host's
-		 * interrupt handler (assuming there is one irq-level per
-		 * host).
-		 */
-		while (--ticks_remaining >= 0)
-			mdelay(1 + 999 / HZ);
-		host->resetting = 0;
-	}
-
 	scsi_log_send(cmd);
 
 	/*

index df0c3c7..f334859 100644
@@ -316,6 +316,12 @@ static void scsi_host_dev_release(struct device *dev)
 	kfree(shost);
 }
 
+static unsigned int shost_eh_deadline;
+
+module_param_named(eh_deadline, shost_eh_deadline, uint, S_IRUGO|S_IWUSR);
+MODULE_PARM_DESC(eh_deadline,
+		 "SCSI EH timeout in seconds (should be between 1 and 2^32-1)");
+
 static struct device_type scsi_host_type = {
 	.name =		"scsi_host",
 	.release =	scsi_host_dev_release,

@@ -388,6 +394,7 @@ struct Scsi_Host *scsi_host_alloc(struct scsi_host_template *sht, int privsize)
 	shost->unchecked_isa_dma = sht->unchecked_isa_dma;
 	shost->use_clustering = sht->use_clustering;
 	shost->ordered_tag = sht->ordered_tag;
+	shost->eh_deadline = shost_eh_deadline * HZ;
 
 	if (sht->supported_mode == MODE_UNKNOWN)
 		/* means we didn't set it ... default to INITIATOR */

244 lines not on this page · raw message

index a734710..8ff62c2 100644
@@ -281,6 +281,42 @@ exit_store_host_reset:
 
 static DEVICE_ATTR(host_reset, S_IWUSR, NULL, store_host_reset);
 
+static ssize_t
+show_shost_eh_deadline(struct device *dev,
+		      struct device_attribute *attr, char *buf)
+{
+	struct Scsi_Host *shost = class_to_shost(dev);
+
+	return sprintf(buf, "%d\n", shost->eh_deadline / HZ);
+}
+
+static ssize_t
+store_shost_eh_deadline(struct device *dev, struct device_attribute *attr,
+		const char *buf, size_t count)
+{
+	struct Scsi_Host *shost = class_to_shost(dev);
+	int ret = -EINVAL;
+	int deadline;
+	unsigned long flags;
+
+	if (shost->transportt && shost->transportt->eh_strategy_handler)
+		return ret;
+
+	if (sscanf(buf, "%d\n", &deadline) == 1) {
+		spin_lock_irqsave(shost->host_lock, flags);
+		if (scsi_host_in_recovery(shost))
+			ret = -EBUSY;
+		else {
+			shost->eh_deadline = deadline * HZ;
+			ret = count;
+		}
+		spin_unlock_irqrestore(shost->host_lock, flags);
+	}
+	return ret;
+}
+
+static DEVICE_ATTR(eh_deadline, S_IRUGO | S_IWUSR, show_shost_eh_deadline, store_shost_eh_deadline);
+
 shost_rd_attr(unique_id, "%u\n");
 shost_rd_attr(host_busy, "%hu\n");
 shost_rd_attr(cmd_per_lun, "%hd\n");

@@ -308,6 +344,7 @@ static struct attribute *scsi_sysfs_shost_attrs[] = {
 	&dev_attr_prot_capabilities.attr,
 	&dev_attr_prot_guard_type.attr,
 	&dev_attr_host_reset.attr,
+	&dev_attr_eh_deadline.attr,
 	NULL
 };
 

index 7552435..896bb05 100644
@@ -596,9 +596,9 @@ struct Scsi_Host {
 	unsigned int host_busy;		   /* commands actually active on low-level */
 	unsigned int host_failed;	   /* commands that failed. */
 	unsigned int host_eh_scheduled;    /* EH scheduled without command */
-    
+
 	unsigned int host_no;  /* Used for IOCTL_GET_IDLUN, /proc/scsi et al. */
-	int resetting; /* if set, it means that last_reset is a valid value */
+	int eh_deadline;
 	unsigned long last_reset;
 
 	/*

index edae9e2..e8bee9f 100644
@@ -1192,18 +1192,20 @@ static int scsi_eh_abort_cmds(struct list_head *work_q,
 						  "0x%p\n", current->comm,
 						  scmd));
 		rtn = scsi_try_to_abort_cmd(shost->hostt, scmd);
-		if (rtn == SUCCESS || rtn == FAST_IO_FAIL) {
-			scmd->eh_eflags &= ~SCSI_EH_CANCEL_CMD;
-			if (rtn == FAST_IO_FAIL)
-				scsi_eh_finish_cmd(scmd, done_q);
-			else
-				list_move_tail(&scmd->eh_entry, &check_list);
-		} else
+		if (rtn == FAILED) {
 			SCSI_LOG_ERROR_RECOVERY(3, printk("%s: aborting"
 							  " cmd failed:"
 							  "0x%p\n",
 							  current->comm,
 							  scmd));
+			list_splice_init(&check_list, work_q);
+			return list_empty(work_q);
+		}
+		scmd->eh_eflags &= ~SCSI_EH_CANCEL_CMD;
+		if (rtn == FAST_IO_FAIL)
+			scsi_eh_finish_cmd(scmd, done_q);
+		else
+			list_move_tail(&scmd->eh_entry, &check_list);
 	}
 
 	return scsi_eh_test_devices(&check_list, work_q, done_q, 0);