@@ -33,6 +33,7 @@
 #include <linux/list.h>
 #include <linux/netdevice.h>
 #include <linux/pci.h>
+#include <linux/pm_runtime.h>
 #include <linux/sched.h>
 #include <linux/skbuff.h>
 #include <linux/slab.h>

@@ -262,6 +263,8 @@ static void t7xx_cldma_rx_done(struct work_struct *work)
 	t7xx_cldma_clear_ip_busy(&md_ctrl->hw_info);
 	t7xx_cldma_hw_irq_en_txrx(&md_ctrl->hw_info, queue->index, MTK_RX);
 	t7xx_cldma_hw_irq_en_eq(&md_ctrl->hw_info, queue->index, MTK_RX);
+	pm_runtime_mark_last_busy(md_ctrl->dev);
+	pm_runtime_put_autosuspend(md_ctrl->dev);
 }
 
 static int t7xx_cldma_gpd_tx_collect(struct cldma_queue *queue)

@@ -373,6 +376,9 @@ static void t7xx_cldma_tx_done(struct work_struct *work)
 		t7xx_cldma_hw_irq_en_txrx(hw_info, queue->index, MTK_TX);
 	}
 	spin_unlock_irqrestore(&md_ctrl->cldma_lock, flags);
+
+	pm_runtime_mark_last_busy(md_ctrl->dev);
+	pm_runtime_put_autosuspend(md_ctrl->dev);
 }
 
 static void t7xx_cldma_ring_free(struct cldma_ctrl *md_ctrl,

@@ -579,6 +585,7 @@ static void t7xx_cldma_irq_work_cb(struct cldma_ctrl *md_ctrl)
 		if (l2_tx_int & (TXRX_STATUS_BITMASK | EMPTY_STATUS_BITMASK)) {
 			for_each_set_bit(i, (unsigned long *)&l2_tx_int, L2_INT_BIT_COUNT) {
 				if (i < CLDMA_TXQ_NUM) {
+					pm_runtime_get(md_ctrl->dev);
 					t7xx_cldma_hw_irq_dis_eq(hw_info, i, MTK_TX);
 					t7xx_cldma_hw_irq_dis_txrx(hw_info, i, MTK_TX);
 					queue_work(md_ctrl->txq[i].worker,

@@ -603,6 +610,7 @@ static void t7xx_cldma_irq_work_cb(struct cldma_ctrl *md_ctrl)
 		if (l2_rx_int & (TXRX_STATUS_BITMASK | EMPTY_STATUS_BITMASK)) {
 			l2_rx_int |= l2_rx_int >> CLDMA_RXQ_NUM;
 			for_each_set_bit(i, (unsigned long *)&l2_rx_int, CLDMA_RXQ_NUM) {
+				pm_runtime_get(md_ctrl->dev);
 				t7xx_cldma_hw_irq_dis_eq(hw_info, i, MTK_RX);
 				t7xx_cldma_hw_irq_dis_txrx(hw_info, i, MTK_RX);
 				queue_work(md_ctrl->rxq[i].worker, &md_ctrl->rxq[i].cldma_work);

@@ -933,6 +941,10 @@ int t7xx_cldma_send_skb(struct cldma_ctrl *md_ctrl, int qno, struct sk_buff *skb
 	if (qno >= CLDMA_TXQ_NUM)
 		return -EINVAL;
 
+	ret = pm_runtime_resume_and_get(md_ctrl->dev);
+	if (ret < 0 && ret != -EACCES)
+		return ret;
+
 	queue = &md_ctrl->txq[qno];
 
 	spin_lock_irqsave(&md_ctrl->cldma_lock, flags);

@@ -976,6 +988,8 @@ int t7xx_cldma_send_skb(struct cldma_ctrl *md_ctrl, int qno, struct sk_buff *skb
 	} while (!ret);
 
 allow_sleep:
+	pm_runtime_mark_last_busy(md_ctrl->dev);
+	pm_runtime_put_autosuspend(md_ctrl->dev);
 	return ret;
 }
 

@@ -32,6 +32,7 @@
 #include <linux/minmax.h>
 #include <linux/mm.h>
 #include <linux/netdevice.h>
+#include <linux/pm_runtime.h>
 #include <linux/sched.h>
 #include <linux/skbuff.h>
 #include <linux/slab.h>

@@ -912,6 +913,7 @@ static void t7xx_dpmaif_rxq_work(struct work_struct *work)
 {
 	struct dpmaif_rx_queue *rxq = container_of(work, struct dpmaif_rx_queue, dpmaif_rxq_work);
 	struct dpmaif_ctrl *dpmaif_ctrl = rxq->dpmaif_ctrl;
+	int ret;
 
 	atomic_set(&rxq->rx_processing, 1);
 	/* Ensure rx_processing is changed to 1 before actually begin RX flow */

@@ -923,7 +925,14 @@ static void t7xx_dpmaif_rxq_work(struct work_struct *work)
 		return;
 	}
 
+	ret = pm_runtime_resume_and_get(dpmaif_ctrl->dev);
+	if (ret < 0 && ret != -EACCES)
+		return;
+
 	t7xx_dpmaif_do_rx(dpmaif_ctrl, rxq);
+
+	pm_runtime_mark_last_busy(dpmaif_ctrl->dev);
+	pm_runtime_put_autosuspend(dpmaif_ctrl->dev);
 	atomic_set(&rxq->rx_processing, 0);
 }
 

@@ -1126,11 +1135,19 @@ static void t7xx_dpmaif_bat_release_work(struct work_struct *work)
 {
 	struct dpmaif_ctrl *dpmaif_ctrl = container_of(work, struct dpmaif_ctrl, bat_release_work);
 	struct dpmaif_rx_queue *rxq;
+	int ret;
+
+	ret = pm_runtime_resume_and_get(dpmaif_ctrl->dev);
+	if (ret < 0 && ret != -EACCES)
+		return;
 
 	/* ALL RXQ use one BAT table, so choose DPF_RX_QNO_DFT */
 	rxq = &dpmaif_ctrl->rxq[DPF_RX_QNO_DFT];
 	t7xx_dpmaif_bat_release_and_add(rxq);
 	t7xx_dpmaif_frag_bat_release_and_add(rxq);
+
+	pm_runtime_mark_last_busy(dpmaif_ctrl->dev);
+	pm_runtime_put_autosuspend(dpmaif_ctrl->dev);
 }
 
 int t7xx_dpmaif_bat_rel_wq_alloc(struct dpmaif_ctrl *dpmaif_ctrl)

@@ -28,6 +28,7 @@
 #include <linux/list.h>
 #include <linux/minmax.h>
 #include <linux/netdevice.h>
+#include <linux/pm_runtime.h>
 #include <linux/sched.h>
 #include <linux/spinlock.h>
 #include <linux/skbuff.h>

@@ -164,6 +165,10 @@ static void t7xx_dpmaif_tx_done(struct work_struct *work)
 	struct dpmaif_hw_info *hw_info;
 	int ret;
 
+	ret = pm_runtime_resume_and_get(dpmaif_ctrl->dev);
+	if (ret < 0 && ret != -EACCES)
+		return;
+
 	hw_info = &dpmaif_ctrl->hw_info;
 	ret = t7xx_dpmaif_tx_release(dpmaif_ctrl, txq->index, txq->drb_size_cnt);
 	if (ret == -EAGAIN ||

@@ -177,6 +182,9 @@ static void t7xx_dpmaif_tx_done(struct work_struct *work)
 		t7xx_dpmaif_clr_ip_busy_sts(hw_info);
 		t7xx_dpmaif_unmask_ulq_intr(hw_info, txq->index);
 	}
+
+	pm_runtime_mark_last_busy(dpmaif_ctrl->dev);
+	pm_runtime_put_autosuspend(dpmaif_ctrl->dev);
 }
 
 static void t7xx_setup_msg_drb(struct dpmaif_ctrl *dpmaif_ctrl, unsigned char q_num,

@@ -438,6 +446,7 @@ static void t7xx_do_tx_hw_push(struct dpmaif_ctrl *dpmaif_ctrl)
 static int t7xx_dpmaif_tx_hw_push_thread(void *arg)
 {
 	struct dpmaif_ctrl *dpmaif_ctrl = arg;
+	int ret;
 
 	while (!kthread_should_stop()) {
 		if (t7xx_tx_lists_are_all_empty(dpmaif_ctrl) ||

@@ -452,7 +461,13 @@ static int t7xx_dpmaif_tx_hw_push_thread(void *arg)
 				break;
 		}
 
+		ret = pm_runtime_resume_and_get(dpmaif_ctrl->dev);
+		if (ret < 0 && ret != -EACCES)
+			return ret;
+
 		t7xx_do_tx_hw_push(dpmaif_ctrl);
+		pm_runtime_mark_last_busy(dpmaif_ctrl->dev);
+		pm_runtime_put_autosuspend(dpmaif_ctrl->dev);
 	}
 
 	return 0;

@@ -31,6 +31,7 @@
 #include <linux/mutex.h>
 #include <linux/pci.h>
 #include <linux/pm.h>
+#include <linux/pm_runtime.h>
 #include <linux/pm_wakeup.h>
 
 #include "t7xx_mhccif.h"

@@ -44,6 +45,7 @@
 #define T7XX_PCI_EREG_BASE		2
 
 #define PM_ACK_TIMEOUT_MS		1500
+#define PM_AUTOSUSPEND_MS		20000
 #define PM_RESOURCE_POLL_TIMEOUT_US	10000
 #define PM_RESOURCE_POLL_STEP_US	100
 

@@ -86,6 +88,8 @@ static int t7xx_pci_pm_init(struct t7xx_pci_dev *t7xx_dev)
 	atomic_set(&t7xx_dev->md_pm_state, MTK_PM_INIT);
 
 	iowrite32(L1_DISABLE_BIT(0), IREG_BASE(t7xx_dev) + DIS_ASPM_LOWPWR_SET_0);
+	pm_runtime_set_autosuspend_delay(&pdev->dev, PM_AUTOSUSPEND_MS);
+	pm_runtime_use_autosuspend(&pdev->dev);
 
 	return t7xx_wait_pm_config(t7xx_dev);
 }

@@ -100,6 +104,8 @@ void t7xx_pci_pm_init_late(struct t7xx_pci_dev *t7xx_dev)
 			     D2H_INT_RESUME_ACK_AP);
 	iowrite32(L1_DISABLE_BIT(0), IREG_BASE(t7xx_dev) + DIS_ASPM_LOWPWR_CLR_0);
 	atomic_set(&t7xx_dev->md_pm_state, MTK_PM_RESUMED);
+
+	pm_runtime_put_noidle(&t7xx_dev->pdev->dev);
 }
 
 static int t7xx_pci_pm_reinit(struct t7xx_pci_dev *t7xx_dev)

@@ -108,6 +114,9 @@ static int t7xx_pci_pm_reinit(struct t7xx_pci_dev *t7xx_dev)
 	 * so just roll back PM setting to the init setting.
 	 */
 	atomic_set(&t7xx_dev->md_pm_state, MTK_PM_INIT);
+
+	pm_runtime_get_noresume(&t7xx_dev->pdev->dev);
+
 	iowrite32(L1_DISABLE_BIT(0), IREG_BASE(t7xx_dev) + DIS_ASPM_LOWPWR_SET_0);
 	return t7xx_wait_pm_config(t7xx_dev);
 }

@@ -407,6 +416,7 @@ static int __t7xx_pci_pm_resume(struct pci_dev *pdev, bool state_check)
 	t7xx_dev->rgu_pci_irq_en = true;
 	t7xx_pcie_mac_set_int(t7xx_dev, SAP_RGU_INT);
 	iowrite32(L1_DISABLE_BIT(0), IREG_BASE(t7xx_dev) + DIS_ASPM_LOWPWR_CLR_0);
+	pm_runtime_mark_last_busy(&pdev->dev);
 	atomic_set(&t7xx_dev->md_pm_state, MTK_PM_RESUMED);
 
 	return ret;

@@ -443,6 +453,16 @@ static int t7xx_pci_pm_thaw(struct device *dev)
 	return __t7xx_pci_pm_resume(to_pci_dev(dev), false);
 }
 
+static int t7xx_pci_pm_runtime_suspend(struct device *dev)
+{
+	return __t7xx_pci_pm_suspend(to_pci_dev(dev));
+}
+
+static int t7xx_pci_pm_runtime_resume(struct device *dev)
+{
+	return __t7xx_pci_pm_resume(to_pci_dev(dev), true);
+}
+
 static const struct dev_pm_ops t7xx_pci_pm_ops = {
 	.suspend = t7xx_pci_pm_suspend,
 	.resume = t7xx_pci_pm_resume,

@@ -452,6 +472,8 @@ static const struct dev_pm_ops t7xx_pci_pm_ops = {
 	.poweroff = t7xx_pci_pm_suspend,
 	.restore = t7xx_pci_pm_resume,
 	.restore_noirq = t7xx_pci_pm_resume_noirq,
+	.runtime_suspend = t7xx_pci_pm_runtime_suspend,
+	.runtime_resume = t7xx_pci_pm_runtime_resume
 };
 
 static int t7xx_request_irq(struct pci_dev *pdev)