megaraid_sas: Dual queue depth support

1. For iMR controllers, firmware will report two queue depths:

   - Controller-wide queue depth
   - LDIO queue depth (240)

Controller-wide queue depth will be greater among the two. Using this
new feature, iMR can provide larger Queue depth(QD) for JBOD and limited
QD for Virtual Disk(VD).

2. megaraid_sas driver will throttle read/write LDIOs based on "LDIO
Queue Depth".

3. Dual queue depth can be enabled/disabled via module parameter. It is
enabled by default if the firmware supports it. Only specific firmware
builds will enable the feature.

4. Added sysfs parameter "ldio_outstanding" which permits querying the
number of outstanding LDIO requests at runtime.

Signed-off-by: Sumit Saxena <sumit.saxena@avagotech.com>
Signed-off-by: Kashyap Desai <kashyap.desai@avagotech.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>

3 files changed, 107 insertions, 10 deletions

diff --git a/drivers/scsi/megaraid/megaraid_sas.h b/drivers/scsi/megaraid/megaraid_sas.h
index 3b1ed2d86efe..2a2f49134491 100644
--- a/drivers/scsi/megaraid/megaraid_sas.h
+++ b/drivers/scsi/megaraid/megaraid_sas.h
@@ -1353,6 +1353,12 @@ enum DCMD_TIMEOUT_ACTION {
 	KILL_ADAPTER = 1,
 	IGNORE_TIMEOUT = 2,
 };
+
+enum FW_BOOT_CONTEXT {
+	PROBE_CONTEXT = 0,
+	OCR_CONTEXT = 1,
+};
+
 /* Frame Type */
 #define IO_FRAME				0
 #define PTHRU_FRAME				1
@@ -2038,6 +2044,8 @@ struct megasas_instance {
 	u16 max_fw_cmds;
 	u16 max_mfi_cmds;
 	u16 max_scsi_cmds;
+	u16 ldio_threshold;
+	u16 cur_can_queue;
 	u32 max_sectors_per_req;
 	struct megasas_aen_event *ev;
 
@@ -2068,6 +2076,7 @@ struct megasas_instance {
 	u32 fw_support_ieee;
 
 	atomic_t fw_outstanding;
+	atomic_t ldio_outstanding;
 	atomic_t fw_reset_no_pci_access;
 
 	struct megasas_instance_template *instancet;
diff --git a/drivers/scsi/megaraid/megaraid_sas_base.c b/drivers/scsi/megaraid/megaraid_sas_base.c
index edf8911bdb12..961c024d11ca 100644
--- a/drivers/scsi/megaraid/megaraid_sas_base.c
+++ b/drivers/scsi/megaraid/megaraid_sas_base.c
@@ -96,6 +96,10 @@ int rdpq_enable = 1;
 module_param(rdpq_enable, int, S_IRUGO);
 MODULE_PARM_DESC(rdpq_enable, " Allocate reply queue in chunks for large queue depth enable/disable Default: disable(0)");
 
+unsigned int dual_qdepth_disable;
+module_param(dual_qdepth_disable, int, S_IRUGO);
+MODULE_PARM_DESC(dual_qdepth_disable, "Disable dual queue depth feature. Default: 0");
+
 MODULE_LICENSE("GPL");
 MODULE_VERSION(MEGASAS_VERSION);
 MODULE_AUTHOR("megaraidlinux.pdl@avagotech.com");
@@ -1976,7 +1980,7 @@ megasas_check_and_restore_queue_depth(struct megasas_instance *instance)
 		spin_lock_irqsave(instance->host->host_lock, flags);
 		instance->flag &= ~MEGASAS_FW_BUSY;
 
-		instance->host->can_queue = instance->max_scsi_cmds;
+		instance->host->can_queue = instance->cur_can_queue;
 		spin_unlock_irqrestore(instance->host->host_lock, flags);
 	}
 }
@@ -2941,6 +2945,16 @@ megasas_page_size_show(struct device *cdev,
 	return snprintf(buf, PAGE_SIZE, "%ld\n", (unsigned long)PAGE_SIZE - 1);
 }
 
+static ssize_t
+megasas_ldio_outstanding_show(struct device *cdev, struct device_attribute *attr,
+	char *buf)
+{
+	struct Scsi_Host *shost = class_to_shost(cdev);
+	struct megasas_instance *instance = (struct megasas_instance *)shost->hostdata;
+
+	return snprintf(buf, PAGE_SIZE, "%d\n", atomic_read(&instance->ldio_outstanding));
+}
+
 static DEVICE_ATTR(fw_crash_buffer, S_IRUGO | S_IWUSR,
 	megasas_fw_crash_buffer_show, megasas_fw_crash_buffer_store);
 static DEVICE_ATTR(fw_crash_buffer_size, S_IRUGO,
@@ -2949,12 +2963,15 @@ static DEVICE_ATTR(fw_crash_state, S_IRUGO | S_IWUSR,
 	megasas_fw_crash_state_show, megasas_fw_crash_state_store);
 static DEVICE_ATTR(page_size, S_IRUGO,
 	megasas_page_size_show, NULL);
+static DEVICE_ATTR(ldio_outstanding, S_IRUGO,
+	megasas_ldio_outstanding_show, NULL);
 
 struct device_attribute *megaraid_host_attrs[] = {
 	&dev_attr_fw_crash_buffer_size,
 	&dev_attr_fw_crash_buffer,
 	&dev_attr_fw_crash_state,
 	&dev_attr_page_size,
+	&dev_attr_ldio_outstanding,
 	NULL,
 };
 
@@ -4749,6 +4766,7 @@ megasas_init_adapter_mfi(struct megasas_instance *instance)
 		sema_init(&instance->ioctl_sem, (MEGASAS_MFI_IOCTL_CMDS));
 	}
 
+	instance->cur_can_queue = instance->max_scsi_cmds;
 	/*
 	 * Create a pool of commands
 	 */
diff --git a/drivers/scsi/megaraid/megaraid_sas_fusion.c b/drivers/scsi/megaraid/megaraid_sas_fusion.c
index f5538303a9bc..6b8547cf9de4 100644
--- a/drivers/scsi/megaraid/megaraid_sas_fusion.c
+++ b/drivers/scsi/megaraid/megaraid_sas_fusion.c
@@ -92,6 +92,7 @@ void megasas_start_timer(struct megasas_instance *instance,
 			 void *fn, unsigned long interval);
 extern struct megasas_mgmt_info megasas_mgmt_info;
 extern int resetwaittime;
+extern unsigned int dual_qdepth_disable;
 static void megasas_free_rdpq_fusion(struct megasas_instance *instance);
 static void megasas_free_reply_fusion(struct megasas_instance *instance);
 
@@ -208,6 +209,67 @@ megasas_fire_cmd_fusion(struct megasas_instance *instance,
 }
 
 /**
+ * megasas_fusion_update_can_queue -	Do all Adapter Queue depth related calculations here
+ * @instance:							Adapter soft state
+ * fw_boot_context:						Whether this function called during probe or after OCR
+ *
+ * This function is only for fusion controllers.
+ * Update host can queue, if firmware downgrade max supported firmware commands.
+ * Firmware upgrade case will be skiped because underlying firmware has
+ * more resource than exposed to the OS.
+ *
+ */
+static void
+megasas_fusion_update_can_queue(struct megasas_instance *instance, int fw_boot_context)
+{
+	u16 cur_max_fw_cmds = 0;
+	u16 ldio_threshold = 0;
+	struct megasas_register_set __iomem *reg_set;
+
+	reg_set = instance->reg_set;
+
+	cur_max_fw_cmds = readl(&instance->reg_set->outbound_scratch_pad_3) & 0x00FFFF;
+
+	if (dual_qdepth_disable || !cur_max_fw_cmds)
+		cur_max_fw_cmds = instance->instancet->read_fw_status_reg(reg_set) & 0x00FFFF;
+	else
+		ldio_threshold =
+			(instance->instancet->read_fw_status_reg(reg_set) & 0x00FFFF) - MEGASAS_FUSION_IOCTL_CMDS;
+
+	dev_info(&instance->pdev->dev,
+			"Current firmware maximum commands: %d\t LDIO threshold: %d\n",
+			cur_max_fw_cmds, ldio_threshold);
+
+	if (fw_boot_context == OCR_CONTEXT) {
+		cur_max_fw_cmds = cur_max_fw_cmds - 1;
+		if (cur_max_fw_cmds <= instance->max_fw_cmds) {
+			instance->cur_can_queue =
+				cur_max_fw_cmds - (MEGASAS_FUSION_INTERNAL_CMDS +
+						MEGASAS_FUSION_IOCTL_CMDS);
+			instance->host->can_queue = instance->cur_can_queue;
+			instance->ldio_threshold = ldio_threshold;
+		}
+	} else {
+		instance->max_fw_cmds = cur_max_fw_cmds;
+		instance->ldio_threshold = ldio_threshold;
+
+		if (!instance->is_rdpq)
+			instance->max_fw_cmds = min_t(u16, instance->max_fw_cmds, 1024);
+
+		/*
+		* Reduce the max supported cmds by 1. This is to ensure that the
+		* reply_q_sz (1 more than the max cmd that driver may send)
+		* does not exceed max cmds that the FW can support
+		*/
+		instance->max_fw_cmds = instance->max_fw_cmds-1;
+
+		instance->max_scsi_cmds = instance->max_fw_cmds -
+				(MEGASAS_FUSION_INTERNAL_CMDS +
+				MEGASAS_FUSION_IOCTL_CMDS);
+		instance->cur_can_queue = instance->max_scsi_cmds;
+	}
+}
+/**
  * megasas_free_cmds_fusion -	Free all the cmds in the free cmd pool
  * @instance:		Adapter soft state
  */
@@ -738,6 +800,8 @@ megasas_ioc_init_fusion(struct megasas_instance *instance)
 		drv_ops->mfi_capabilities.support_ext_io_size = 1;
 
 	drv_ops->mfi_capabilities.support_fp_rlbypass = 1;
+	if (!dual_qdepth_disable)
+		drv_ops->mfi_capabilities.support_ext_queue_depth = 1;
 
 	/* Convert capability to LE32 */
 	cpu_to_le32s((u32 *)&init_frame->driver_operations.mfi_capabilities);
@@ -1153,15 +1217,7 @@ megasas_init_adapter_fusion(struct megasas_instance *instance)
 
 	reg_set = instance->reg_set;
 
-	/*
-	 * Get various operational parameters from status register
-	 */
-	instance->max_fw_cmds =
-		instance->instancet->read_fw_status_reg(reg_set) & 0x00FFFF;
-	dev_info(&instance->pdev->dev,
-		"firmware support max fw cmd\t: (%d)\n", instance->max_fw_cmds);
-	if (!instance->is_rdpq)
-		instance->max_fw_cmds = min_t(u16, instance->max_fw_cmds, 1024);
+	megasas_fusion_update_can_queue(instance, PROBE_CONTEXT);
 
 	/*
 	 * Reduce the max supported cmds by 1. This is to ensure that the
@@ -2119,6 +2175,14 @@ megasas_build_and_issue_cmd_fusion(struct megasas_instance *instance,
 
 	fusion = instance->ctrl_context;
 
+	if ((megasas_cmd_type(scmd) == READ_WRITE_LDIO) &&
+		instance->ldio_threshold &&
+		(atomic_inc_return(&instance->ldio_outstanding) >
+		instance->ldio_threshold)) {
+		atomic_dec(&instance->ldio_outstanding);
+		return SCSI_MLQUEUE_DEVICE_BUSY;
+	}
+
 	cmd = megasas_get_cmd_fusion(instance, scmd->request->tag);
 
 	index = cmd->index;
@@ -2249,6 +2313,8 @@ complete_cmd_fusion(struct megasas_instance *instance, u32 MSIxIndex)
 			map_cmd_status(cmd_fusion, status, extStatus);
 			scsi_io_req->RaidContext.status = 0;
 			scsi_io_req->RaidContext.exStatus = 0;
+			if (megasas_cmd_type(scmd_local) == READ_WRITE_LDIO)
+				atomic_dec(&instance->ldio_outstanding);
 			megasas_return_cmd_fusion(instance, cmd_fusion);
 			scsi_dma_unmap(scmd_local);
 			scmd_local->scsi_done(scmd_local);
@@ -3367,6 +3433,8 @@ int megasas_reset_fusion(struct Scsi_Host *shost, int reason)
 				scmd_local->result =
 					megasas_check_mpio_paths(instance,
 							scmd_local);
+				if (megasas_cmd_type(scmd_local) == READ_WRITE_LDIO)
+					atomic_dec(&instance->ldio_outstanding);
 				megasas_return_cmd_fusion(instance, cmd_fusion);
 				scsi_dma_unmap(scmd_local);
 				scmd_local->scsi_done(scmd_local);
@@ -3459,6 +3527,8 @@ int megasas_reset_fusion(struct Scsi_Host *shost, int reason)
 			}
 
 			megasas_reset_reply_desc(instance);
+			megasas_fusion_update_can_queue(instance, OCR_CONTEXT);
+
 			if (megasas_ioc_init_fusion(instance)) {
 				dev_warn(&instance->pdev->dev,
 				       "megasas_ioc_init_fusion() failed!"