scsi: megaraid_sas - intercepts cmd timeout and throttle io

eh_timed_out call back (megasas_reset_timer) is used to throttle io to the adapter when it is called the first time for a scmd.
The MEGASAS_FW_BUSY flag is set and can_queue reduced to 16. The can_queue is restored from completion routine in following two conditions : 5 seconds has elapsed and the # of outstanding cmds in FW is < 17.

Signed-off-by Sumant Patro <[email protected]>

---
 drivers/scsi/megaraid/megaraid_sas.c |   65 +++++++++++++++++++++++--
 drivers/scsi/megaraid/megaraid_sas.h |   13 +++--
 2 files changed, 70 insertions(+), 8 deletions(-)

This patch requires the patch submitted by James with subject line :

[PATCH] expose eh_timed_out to the host template

diff -uprN linux-2.6.orig/drivers/scsi/megaraid/megaraid_sas.c linux-2.6.new/drivers/scsi/megaraid/megaraid_sas.c

drivers/scsi/megaraid/megaraid_sas.c +8 -3

@@ -10,7 +10,7 @@
  *	   2 of the License, or (at your option) any later version.
  *
  * FILE		: megaraid_sas.c
- * Version	: v00.00.03.10-rc1
+ * Version	: v00.00.03.10-rc3
  *
  * Authors:
  *	(email-id : [email protected])

@@ -886,6 +886,7 @@ megasas_queue_command(struct scsi_cmnd *
 		goto out_return_cmd;
 
 	cmd->scmd = scmd;
+	scmd->SCp.ptr = (char *)cmd;
 
 	/*
 	 * Issue the command to the FW

@@ -981,8 +982,8 @@ static int megasas_generic_reset(struct 
 
 	instance = (struct megasas_instance *)scmd->device->host->hostdata;
 
-	scmd_printk(KERN_NOTICE, scmd, "megasas: RESET -%ld cmd=%x\n",
-	       scmd->serial_number, scmd->cmnd[0]);
+	scmd_printk(KERN_NOTICE, scmd, "megasas: RESET -%ld cmd=%x retries=%x\n",
+		 scmd->serial_number, scmd->cmnd[0], scmd->retries);
 
 	if (instance->hw_crit_error) {
 		printk(KERN_ERR "megasas: cannot recover from previous reset "

@@ -1000,6 +1001,40 @@ static int megasas_generic_reset(struct 
 }
 
 /**
+ * megasas_reset_timer - quiesce the adapter if required
+ * @scmd:		scsi cmnd
+ *
+ * Sets the FW busy flag and reduces the host->can_queue if the

drivers/scsi/megaraid/megaraid_sas.c +12 -0

+			instance->last_time = jiffies;
+			instance->flag |= MEGASAS_FW_BUSY;
+
+			spin_unlock_irqrestore(&instance->throttle_io_lock, flags);
+		}
+		return EH_RESET_TIMER;
+	}
+	return EH_HANDLED;
+}
+
+/**
  * megasas_reset_device -	Device reset handler entry point
  */
 static int megasas_reset_device(struct scsi_cmnd *scmd)

@@ -1112,6 +1147,7 @@ static struct scsi_host_template megasas
 	.eh_device_reset_handler = megasas_reset_device,
 	.eh_bus_reset_handler = megasas_reset_bus_host,
 	.eh_host_reset_handler = megasas_reset_bus_host,
+	.eh_timed_out = megasas_reset_timer,
 	.bios_param = megasas_bios_param,
 	.use_clustering = ENABLE_CLUSTERING,
 };

drivers/scsi/megaraid/megaraid_sas.c +20 -1

-	}
 
 	switch (hdr->cmd) {
 

@@ -1806,6 +1841,7 @@ static void megasas_complete_cmd_dpc(uns
 	u32 context;
 	struct megasas_cmd *cmd;
 	struct megasas_instance *instance = (struct megasas_instance *)instance_addr;
+	unsigned long flags;
 
 	/* If we have already declared adapter dead, donot complete cmds */
 	if (instance->hw_crit_error)

@@ -1828,6 +1864,22 @@ static void megasas_complete_cmd_dpc(uns
 	}
 
 	*instance->consumer = producer;
+
+	/*
+	 * Check if we can restore can_queue
+	 */
+	if (instance->flag & MEGASAS_FW_BUSY
+		&& time_after(jiffies, instance->last_time + 5 * HZ)
+		&& atomic_read(&instance->fw_outstanding) < 17) {
+
+		spin_lock_irqsave(&instance->throttle_io_lock, flags);
+
+		instance->flag &= ~MEGASAS_FW_BUSY;
+		instance->host->can_queue =
+				instance->max_fw_cmds - MEGASAS_INT_CMDS;
+
+		spin_unlock_irqrestore(&instance->throttle_io_lock, flags);
+	}
 }
 
 /**

@@ -2384,6 +2436,7 @@ megasas_probe_one(struct pci_dev *pdev, 
 	init_waitqueue_head(&instance->int_cmd_wait_q);
 	init_waitqueue_head(&instance->abort_cmd_wait_q);
 
+	spin_lock_init(&instance->throttle_io_lock);
 	spin_lock_init(&instance->cmd_pool_lock);
 
 	sema_init(&instance->aen_mutex, 1);

@@ -2398,6 +2451,8 @@ megasas_probe_one(struct pci_dev *pdev, 
 	instance->init_id = MEGASAS_DEFAULT_INIT_ID;
 
 	megasas_dbg_lvl = 0;
+	instance->flag = 0;
+	instance->last_time = 0;
 
 	/*
 	 * Initialize MFI Firmware

diff -uprN linux-2.6.orig/drivers/scsi/megaraid/megaraid_sas.h linux-2.6.new/drivers/scsi/megaraid/megaraid_sas.h

drivers/scsi/megaraid/megaraid_sas.h +5 -3

@@ -18,9 +18,9 @@
 /*
  * MegaRAID SAS Driver meta data
  */
-#define MEGASAS_VERSION				"00.00.03.10-rc1"
-#define MEGASAS_RELDATE				"Feb 14, 2007"
-#define MEGASAS_EXT_VERSION			"Wed Feb 14 10:14:25 PST 2007"
+#define MEGASAS_VERSION				"00.00.03.10-rc3"
+#define MEGASAS_RELDATE				"Mar 28, 2007"
+#define MEGASAS_EXT_VERSION			"Wed Mar 28 10:25:52 PST 2007"
 
 /*
  * Device IDs

@@ -539,6 +539,8 @@ struct megasas_ctrl_info {
 
 #define MEGASAS_DBG_LVL				1
 
+#define MEGASAS_FW_BUSY				1
+
 /*
  * When SCSI mid-layer calls driver's reset routine, driver waits for
  * MEGASAS_RESET_WAIT_TIME seconds for all outstanding IO to complete. Note

eh_timed_out call back (megasas_reset_timer) is used to throttle io to

the adapter when it is called the first time for a scmd. The MEGASAS_FW_BUSY flag is set and can_queue reduced to 16. The can_queue is restored from completion routine in following two conditions : 5 seconds has elapsed and the # of outstanding cmds in FW

Signed-off-by Sumant Patro <[email protected]>

---
 drivers/scsi/megaraid/megaraid_sas.c |   65 +++++++++++++++++++++++--
 drivers/scsi/megaraid/megaraid_sas.h |   13 +++--
 2 files changed, 70 insertions(+), 8 deletions(-)

This patch requires the patch submitted by James with subject line :

[PATCH] expose eh_timed_out to the host template

diff -uprN linux-2.6.orig/drivers/scsi/megaraid/megaraid_sas.c

--- linux-2.6.orig/drivers/scsi/megaraid/megaraid_sas.c

+++ linux-2.6.new/drivers/scsi/megaraid/megaraid_sas.c

drivers/scsi/megaraid/megaraid_sas.c +2 -1

@@ -10,7 +10,7 @@
  *	   2 of the License, or (at your option) any later version.
  *
  * FILE		: megaraid_sas.c
- * Version	: v00.00.03.10-rc1
+ * Version	: v00.00.03.10-rc3
  *
  * Authors:
  *	(email-id : [email protected])

@@ -886,6 +886,7 @@ megasas_queue_command(struct scsi_cmnd *
 		goto out_return_cmd;
 
 	cmd->scmd = scmd;
+	scmd->SCp.ptr = (char *)cmd;
 
 	/*
 	 * Issue the command to the FW

drivers/scsi/megaraid/megaraid_sas.c +3 -0

@@ -1000,6 +1001,40 @@ static int megasas_generic_reset(struct  }
 
 /**
+ * megasas_reset_timer - quiesce the adapter if required
+ * @scmd:		scsi cmnd
+ *

drivers/scsi/megaraid/megaraid_sas.c +9 -0

+		}
+		return EH_RESET_TIMER;
+	}
+	return EH_HANDLED;
+}
+
+/**
  * megasas_reset_device -	Device reset handler entry point
  */
 static int megasas_reset_device(struct scsi_cmnd *scmd) @@ -1112,6 
+1147,7 @@ static struct scsi_host_template megasas
 	.eh_device_reset_handler = megasas_reset_device,
 	.eh_bus_reset_handler = megasas_reset_bus_host,
 	.eh_host_reset_handler = megasas_reset_bus_host,
+	.eh_timed_out = megasas_reset_timer,
 	.bios_param = megasas_bios_param,
 	.use_clustering = ENABLE_CLUSTERING,  }; @@ -1215,9 +1251,8 @@ 

megasas_complete_cmd(struct megasas_inst

drivers/scsi/megaraid/megaraid_sas.c +3 -0

 	if (instance->hw_crit_error)

@@ -1828,6 +1864,22 @@ static void megasas_complete_cmd_dpc(uns
 	}
 
 	*instance->consumer = producer;
+
+	/*
+	 * Check if we can restore can_queue

drivers/scsi/megaraid/megaraid_sas.c +4 -0

+	}
 }
 
 /**

@@ -2384,6 +2436,7 @@ megasas_probe_one(struct pci_dev *pdev, 
 	init_waitqueue_head(&instance->int_cmd_wait_q);
 	init_waitqueue_head(&instance->abort_cmd_wait_q);
 
+	spin_lock_init(&instance->throttle_io_lock);
 	spin_lock_init(&instance->cmd_pool_lock);
 
 	sema_init(&instance->aen_mutex, 1);

@@ -2398,6 +2451,8 @@ megasas_probe_one(struct pci_dev *pdev, 
 	instance->init_id = MEGASAS_DEFAULT_INIT_ID;
 
 	megasas_dbg_lvl = 0;
+	instance->flag = 0;
+	instance->last_time = 0;
 
 	/*
 	 * Initialize MFI Firmware

diff -uprN linux-2.6.orig/drivers/scsi/megaraid/megaraid_sas.h

--- linux-2.6.orig/drivers/scsi/megaraid/megaraid_sas.h

+++ linux-2.6.new/drivers/scsi/megaraid/megaraid_sas.h

drivers/scsi/megaraid/megaraid_sas.h +2 -0

 /*
  * Device IDs

@@ -539,6 +539,8 @@ struct megasas_ctrl_info {
 
 #define MEGASAS_DBG_LVL				1
 
+#define MEGASAS_FW_BUSY				1
+
 /*
  * When SCSI mid-layer calls driver's reset routine, driver waits for
  * MEGASAS_RESET_WAIT_TIME seconds for all outstanding IO to 

complete. Note @@ -1104,6 +1106,11 @@ struct megasas_instance {

The rsvd[3] is reserved for future use. If you have objection to
the definition I will take it out in a future patch submission.