Merge branch 'cpuidle-fix' into fixes

10 files changed, 780 insertions, 148 deletions

diff --git a/drivers/soc/ti/Kconfig b/drivers/soc/ti/Kconfig
index f5b82ffa637b..7e2fb1c16af1 100644
--- a/drivers/soc/ti/Kconfig
+++ b/drivers/soc/ti/Kconfig
@@ -1,22 +1,4 @@
 # SPDX-License-Identifier: GPL-2.0-only
-# 64-bit ARM SoCs from TI
-if ARM64
-
-if ARCH_K3
-
-config ARCH_K3_AM6_SOC
-	bool "K3 AM6 SoC"
-	help
-	  Enable support for TI's AM6 SoC Family support
-
-config ARCH_K3_J721E_SOC
-	bool "K3 J721E SoC"
-	help
-	  Enable support for TI's J721E SoC Family support
-
-endif
-
-endif
 
 #
 # TI SOC drivers
diff --git a/drivers/soc/ti/k3-ringacc.c b/drivers/soc/ti/k3-ringacc.c
index 1147dc4c1d59..b495b0d5d0fa 100644
--- a/drivers/soc/ti/k3-ringacc.c
+++ b/drivers/soc/ti/k3-ringacc.c
@@ -11,6 +11,7 @@
 #include <linux/of.h>
 #include <linux/platform_device.h>
 #include <linux/sys_soc.h>
+#include <linux/dma/ti-cppi5.h>
 #include <linux/soc/ti/k3-ringacc.h>
 #include <linux/soc/ti/ti_sci_protocol.h>
 #include <linux/soc/ti/ti_sci_inta_msi.h>
@@ -21,6 +22,7 @@ static LIST_HEAD(k3_ringacc_list);
 static DEFINE_MUTEX(k3_ringacc_list_lock);
 
 #define K3_RINGACC_CFG_RING_SIZE_ELCNT_MASK		GENMASK(19, 0)
+#define K3_DMARING_CFG_RING_SIZE_ELCNT_MASK		GENMASK(15, 0)
 
 /**
  * struct k3_ring_rt_regs - The RA realtime Control/Status Registers region
@@ -43,7 +45,13 @@ struct k3_ring_rt_regs {
 	u32	hwindx;
 };
 
-#define K3_RINGACC_RT_REGS_STEP	0x1000
+#define K3_RINGACC_RT_REGS_STEP			0x1000
+#define K3_DMARING_RT_REGS_STEP			0x2000
+#define K3_DMARING_RT_REGS_REVERSE_OFS		0x1000
+#define K3_RINGACC_RT_OCC_MASK			GENMASK(20, 0)
+#define K3_DMARING_RT_OCC_TDOWN_COMPLETE	BIT(31)
+#define K3_DMARING_RT_DB_ENTRY_MASK		GENMASK(7, 0)
+#define K3_DMARING_RT_DB_TDOWN_ACK		BIT(31)
 
 /**
  * struct k3_ring_fifo_regs - The Ring Accelerator Queues Registers region
@@ -122,6 +130,7 @@ struct k3_ring_state {
 	u32 occ;
 	u32 windex;
 	u32 rindex;
+	u32 tdown_complete:1;
 };
 
 /**
@@ -137,10 +146,13 @@ struct k3_ring_state {
  * @elm_size: Size of the ring element
  * @mode: Ring mode
  * @flags: flags
+ * @state: Ring state
  * @ring_id: Ring Id
  * @parent: Pointer on struct @k3_ringacc
  * @use_count: Use count for shared rings
  * @proxy_id: RA Ring Proxy Id (only if @K3_RINGACC_RING_USE_PROXY)
+ * @dma_dev: device to be used for DMA API (allocation, mapping)
+ * @asel: Address Space Select value for physical addresses
  */
 struct k3_ring {
 	struct k3_ring_rt_regs __iomem *rt;
@@ -155,11 +167,15 @@ struct k3_ring {
 	u32		flags;
 #define K3_RING_FLAG_BUSY	BIT(1)
 #define K3_RING_FLAG_SHARED	BIT(2)
+#define K3_RING_FLAG_REVERSE	BIT(3)
 	struct k3_ring_state state;
 	u32		ring_id;
 	struct k3_ringacc	*parent;
 	u32		use_count;
 	int		proxy_id;
+	struct device	*dma_dev;
+	u32		asel;
+#define K3_ADDRESS_ASEL_SHIFT	48
 };
 
 struct k3_ringacc_ops {
@@ -185,6 +201,7 @@ struct k3_ringacc_ops {
  * @tisci_ring_ops: ti-sci rings ops
  * @tisci_dev_id: ti-sci device id
  * @ops: SoC specific ringacc operation
+ * @dma_rings: indicate DMA ring (dual ring within BCDMA/PKTDMA)
  */
 struct k3_ringacc {
 	struct device *dev;
@@ -207,6 +224,7 @@ struct k3_ringacc {
 	u32 tisci_dev_id;
 
 	const struct k3_ringacc_ops *ops;
+	bool dma_rings;
 };
 
 /**
@@ -218,6 +236,21 @@ struct k3_ringacc_soc_data {
 	unsigned dma_ring_reset_quirk:1;
 };
 
+static int k3_ringacc_ring_read_occ(struct k3_ring *ring)
+{
+	return readl(&ring->rt->occ) & K3_RINGACC_RT_OCC_MASK;
+}
+
+static void k3_ringacc_ring_update_occ(struct k3_ring *ring)
+{
+	u32 val;
+
+	val = readl(&ring->rt->occ);
+
+	ring->state.occ = val & K3_RINGACC_RT_OCC_MASK;
+	ring->state.tdown_complete = !!(val & K3_DMARING_RT_OCC_TDOWN_COMPLETE);
+}
+
 static long k3_ringacc_ring_get_fifo_pos(struct k3_ring *ring)
 {
 	return K3_RINGACC_FIFO_WINDOW_SIZE_BYTES -
@@ -231,12 +264,24 @@ static void *k3_ringacc_get_elm_addr(struct k3_ring *ring, u32 idx)
 
 static int k3_ringacc_ring_push_mem(struct k3_ring *ring, void *elem);
 static int k3_ringacc_ring_pop_mem(struct k3_ring *ring, void *elem);
+static int k3_dmaring_fwd_pop(struct k3_ring *ring, void *elem);
+static int k3_dmaring_reverse_pop(struct k3_ring *ring, void *elem);
 
 static struct k3_ring_ops k3_ring_mode_ring_ops = {
 		.push_tail = k3_ringacc_ring_push_mem,
 		.pop_head = k3_ringacc_ring_pop_mem,
 };
 
+static struct k3_ring_ops k3_dmaring_fwd_ops = {
+		.push_tail = k3_ringacc_ring_push_mem,
+		.pop_head = k3_dmaring_fwd_pop,
+};
+
+static struct k3_ring_ops k3_dmaring_reverse_ops = {
+		/* Reverse side of the DMA ring can only be popped by SW */
+		.pop_head = k3_dmaring_reverse_pop,
+};
+
 static int k3_ringacc_ring_push_io(struct k3_ring *ring, void *elem);
 static int k3_ringacc_ring_pop_io(struct k3_ring *ring, void *elem);
 static int k3_ringacc_ring_push_head_io(struct k3_ring *ring, void *elem);
@@ -339,6 +384,40 @@ error:
 }
 EXPORT_SYMBOL_GPL(k3_ringacc_request_ring);
 
+static int k3_dmaring_request_dual_ring(struct k3_ringacc *ringacc, int fwd_id,
+					struct k3_ring **fwd_ring,
+					struct k3_ring **compl_ring)
+{
+	int ret = 0;
+
+	/*
+	 * DMA rings must be requested by ID, completion ring is the reverse
+	 * side of the forward ring
+	 */
+	if (fwd_id < 0)
+		return -EINVAL;
+
+	mutex_lock(&ringacc->req_lock);
+
+	if (test_bit(fwd_id, ringacc->rings_inuse)) {
+		ret = -EBUSY;
+		goto error;
+	}
+
+	*fwd_ring = &ringacc->rings[fwd_id];
+	*compl_ring = &ringacc->rings[fwd_id + ringacc->num_rings];
+	set_bit(fwd_id, ringacc->rings_inuse);
+	ringacc->rings[fwd_id].use_count++;
+	dev_dbg(ringacc->dev, "Giving ring#%d\n", fwd_id);
+
+	mutex_unlock(&ringacc->req_lock);
+	return 0;
+
+error:
+	mutex_unlock(&ringacc->req_lock);
+	return ret;
+}
+
 int k3_ringacc_request_rings_pair(struct k3_ringacc *ringacc,
 				  int fwd_id, int compl_id,
 				  struct k3_ring **fwd_ring,
@@ -349,6 +428,10 @@ int k3_ringacc_request_rings_pair(struct k3_ringacc *ringacc,
 	if (!fwd_ring || !compl_ring)
 		return -EINVAL;
 
+	if (ringacc->dma_rings)
+		return k3_dmaring_request_dual_ring(ringacc, fwd_id,
+						    fwd_ring, compl_ring);
+
 	*fwd_ring = k3_ringacc_request_ring(ringacc, fwd_id, 0);
 	if (!(*fwd_ring))
 		return -ENODEV;
@@ -365,20 +448,16 @@ EXPORT_SYMBOL_GPL(k3_ringacc_request_rings_pair);
 
 static void k3_ringacc_ring_reset_sci(struct k3_ring *ring)
 {
+	struct ti_sci_msg_rm_ring_cfg ring_cfg = { 0 };
 	struct k3_ringacc *ringacc = ring->parent;
 	int ret;
 
-	ret = ringacc->tisci_ring_ops->config(
-			ringacc->tisci,
-			TI_SCI_MSG_VALUE_RM_RING_COUNT_VALID,
-			ringacc->tisci_dev_id,
-			ring->ring_id,
-			0,
-			0,
-			ring->size,
-			0,
-			0,
-			0);
+	ring_cfg.nav_id = ringacc->tisci_dev_id;
+	ring_cfg.index = ring->ring_id;
+	ring_cfg.valid_params = TI_SCI_MSG_VALUE_RM_RING_COUNT_VALID;
+	ring_cfg.count = ring->size;
+
+	ret = ringacc->tisci_ring_ops->set_cfg(ringacc->tisci, &ring_cfg);
 	if (ret)
 		dev_err(ringacc->dev, "TISCI reset ring fail (%d) ring_idx %d\n",
 			ret, ring->ring_id);
@@ -398,20 +477,16 @@ EXPORT_SYMBOL_GPL(k3_ringacc_ring_reset);
 static void k3_ringacc_ring_reconfig_qmode_sci(struct k3_ring *ring,
 					       enum k3_ring_mode mode)
 {
+	struct ti_sci_msg_rm_ring_cfg ring_cfg = { 0 };
 	struct k3_ringacc *ringacc = ring->parent;
 	int ret;
 
-	ret = ringacc->tisci_ring_ops->config(
-			ringacc->tisci,
-			TI_SCI_MSG_VALUE_RM_RING_MODE_VALID,
-			ringacc->tisci_dev_id,
-			ring->ring_id,
-			0,
-			0,
-			0,
-			mode,
-			0,
-			0);
+	ring_cfg.nav_id = ringacc->tisci_dev_id;
+	ring_cfg.index = ring->ring_id;
+	ring_cfg.valid_params = TI_SCI_MSG_VALUE_RM_RING_MODE_VALID;
+	ring_cfg.mode = mode;
+
+	ret = ringacc->tisci_ring_ops->set_cfg(ringacc->tisci, &ring_cfg);
 	if (ret)
 		dev_err(ringacc->dev, "TISCI reconf qmode fail (%d) ring_idx %d\n",
 			ret, ring->ring_id);
@@ -426,7 +501,7 @@ void k3_ringacc_ring_reset_dma(struct k3_ring *ring, u32 occ)
 		goto reset;
 
 	if (!occ)
-		occ = readl(&ring->rt->occ);
+		occ = k3_ringacc_ring_read_occ(ring);
 
 	if (occ) {
 		u32 db_ring_cnt, db_ring_cnt_cur;
@@ -478,20 +553,15 @@ EXPORT_SYMBOL_GPL(k3_ringacc_ring_reset_dma);
 
 static void k3_ringacc_ring_free_sci(struct k3_ring *ring)
 {
+	struct ti_sci_msg_rm_ring_cfg ring_cfg = { 0 };
 	struct k3_ringacc *ringacc = ring->parent;
 	int ret;
 
-	ret = ringacc->tisci_ring_ops->config(
-			ringacc->tisci,
-			TI_SCI_MSG_VALUE_RM_ALL_NO_ORDER,
-			ringacc->tisci_dev_id,
-			ring->ring_id,
-			0,
-			0,
-			0,
-			0,
-			0,
-			0);
+	ring_cfg.nav_id = ringacc->tisci_dev_id;
+	ring_cfg.index = ring->ring_id;
+	ring_cfg.valid_params = TI_SCI_MSG_VALUE_RM_ALL_NO_ORDER;
+
+	ret = ringacc->tisci_ring_ops->set_cfg(ringacc->tisci, &ring_cfg);
 	if (ret)
 		dev_err(ringacc->dev, "TISCI ring free fail (%d) ring_idx %d\n",
 			ret, ring->ring_id);
@@ -506,6 +576,13 @@ int k3_ringacc_ring_free(struct k3_ring *ring)
 
 	ringacc = ring->parent;
 
+	/*
+	 * DMA rings: rings shared memory and configuration, only forward ring
+	 * is configured and reverse ring considered as slave.
+	 */
+	if (ringacc->dma_rings && (ring->flags & K3_RING_FLAG_REVERSE))
+		return 0;
+
 	dev_dbg(ring->parent->dev, "flags: 0x%08x\n", ring->flags);
 
 	if (!test_bit(ring->ring_id, ringacc->rings_inuse))
@@ -521,11 +598,14 @@ int k3_ringacc_ring_free(struct k3_ring *ring)
 
 	k3_ringacc_ring_free_sci(ring);
 
-	dma_free_coherent(ringacc->dev,
+	dma_free_coherent(ring->dma_dev,
 			  ring->size * (4 << ring->elm_size),
 			  ring->ring_mem_virt, ring->ring_mem_dma);
 	ring->flags = 0;
 	ring->ops = NULL;
+	ring->dma_dev = NULL;
+	ring->asel = 0;
+
 	if (ring->proxy_id != K3_RINGACC_PROXY_NOT_USED) {
 		clear_bit(ring->proxy_id, ringacc->proxy_inuse);
 		ring->proxy = NULL;
@@ -575,32 +655,115 @@ EXPORT_SYMBOL_GPL(k3_ringacc_get_ring_irq_num);
 
 static int k3_ringacc_ring_cfg_sci(struct k3_ring *ring)
 {
+	struct ti_sci_msg_rm_ring_cfg ring_cfg = { 0 };
 	struct k3_ringacc *ringacc = ring->parent;
-	u32 ring_idx;
 	int ret;
 
 	if (!ringacc->tisci)
 		return -EINVAL;
 
-	ring_idx = ring->ring_id;
-	ret = ringacc->tisci_ring_ops->config(
-			ringacc->tisci,
-			TI_SCI_MSG_VALUE_RM_ALL_NO_ORDER,
-			ringacc->tisci_dev_id,
-			ring_idx,
-			lower_32_bits(ring->ring_mem_dma),
-			upper_32_bits(ring->ring_mem_dma),
-			ring->size,
-			ring->mode,
-			ring->elm_size,
-			0);
+	ring_cfg.nav_id = ringacc->tisci_dev_id;
+	ring_cfg.index = ring->ring_id;
+	ring_cfg.valid_params = TI_SCI_MSG_VALUE_RM_ALL_NO_ORDER;
+	ring_cfg.addr_lo = lower_32_bits(ring->ring_mem_dma);
+	ring_cfg.addr_hi = upper_32_bits(ring->ring_mem_dma);
+	ring_cfg.count = ring->size;
+	ring_cfg.mode = ring->mode;
+	ring_cfg.size = ring->elm_size;
+	ring_cfg.asel = ring->asel;
+
+	ret = ringacc->tisci_ring_ops->set_cfg(ringacc->tisci, &ring_cfg);
 	if (ret)
 		dev_err(ringacc->dev, "TISCI config ring fail (%d) ring_idx %d\n",
-			ret, ring_idx);
+			ret, ring->ring_id);
 
 	return ret;
 }
 
+static int k3_dmaring_cfg(struct k3_ring *ring, struct k3_ring_cfg *cfg)
+{
+	struct k3_ringacc *ringacc;
+	struct k3_ring *reverse_ring;
+	int ret = 0;
+
+	if (cfg->elm_size != K3_RINGACC_RING_ELSIZE_8 ||
+	    cfg->mode != K3_RINGACC_RING_MODE_RING ||
+	    cfg->size & ~K3_DMARING_CFG_RING_SIZE_ELCNT_MASK)
+		return -EINVAL;
+
+	ringacc = ring->parent;
+
+	/*
+	 * DMA rings: rings shared memory and configuration, only forward ring
+	 * is configured and reverse ring considered as slave.
+	 */
+	if (ringacc->dma_rings && (ring->flags & K3_RING_FLAG_REVERSE))
+		return 0;
+
+	if (!test_bit(ring->ring_id, ringacc->rings_inuse))
+		return -EINVAL;
+
+	ring->size = cfg->size;
+	ring->elm_size = cfg->elm_size;
+	ring->mode = cfg->mode;
+	ring->asel = cfg->asel;
+	ring->dma_dev = cfg->dma_dev;
+	if (!ring->dma_dev) {
+		dev_warn(ringacc->dev, "dma_dev is not provided for ring%d\n",
+			 ring->ring_id);
+		ring->dma_dev = ringacc->dev;
+	}
+
+	memset(&ring->state, 0, sizeof(ring->state));
+
+	ring->ops = &k3_dmaring_fwd_ops;
+
+	ring->ring_mem_virt = dma_alloc_coherent(ring->dma_dev,
+						 ring->size * (4 << ring->elm_size),
+						 &ring->ring_mem_dma, GFP_KERNEL);
+	if (!ring->ring_mem_virt) {
+		dev_err(ringacc->dev, "Failed to alloc ring mem\n");
+		ret = -ENOMEM;
+		goto err_free_ops;
+	}
+
+	ret = k3_ringacc_ring_cfg_sci(ring);
+	if (ret)
+		goto err_free_mem;
+
+	ring->flags |= K3_RING_FLAG_BUSY;
+
+	k3_ringacc_ring_dump(ring);
+
+	/* DMA rings: configure reverse ring */
+	reverse_ring = &ringacc->rings[ring->ring_id + ringacc->num_rings];
+	reverse_ring->size = cfg->size;
+	reverse_ring->elm_size = cfg->elm_size;
+	reverse_ring->mode = cfg->mode;
+	reverse_ring->asel = cfg->asel;
+	memset(&reverse_ring->state, 0, sizeof(reverse_ring->state));
+	reverse_ring->ops = &k3_dmaring_reverse_ops;
+
+	reverse_ring->ring_mem_virt = ring->ring_mem_virt;
+	reverse_ring->ring_mem_dma = ring->ring_mem_dma;
+	reverse_ring->flags |= K3_RING_FLAG_BUSY;
+	k3_ringacc_ring_dump(reverse_ring);
+
+	return 0;
+
+err_free_mem:
+	dma_free_coherent(ring->dma_dev,
+			  ring->size * (4 << ring->elm_size),
+			  ring->ring_mem_virt,
+			  ring->ring_mem_dma);
+err_free_ops:
+	ring->ops = NULL;
+	ring->proxy = NULL;
+	ring->dma_dev = NULL;
+	ring->asel = 0;
+	return ret;
+}
+
 int k3_ringacc_ring_cfg(struct k3_ring *ring, struct k3_ring_cfg *cfg)
 {
 	struct k3_ringacc *ringacc;
@@ -608,8 +771,12 @@ int k3_ringacc_ring_cfg(struct k3_ring *ring, struct k3_ring_cfg *cfg)
 
 	if (!ring || !cfg)
 		return -EINVAL;
+
 	ringacc = ring->parent;
 
+	if (ringacc->dma_rings)
+		return k3_dmaring_cfg(ring, cfg);
+
 	if (cfg->elm_size > K3_RINGACC_RING_ELSIZE_256 ||
 	    cfg->mode >= K3_RINGACC_RING_MODE_INVALID ||
 	    cfg->size & ~K3_RINGACC_CFG_RING_SIZE_ELCNT_MASK ||
@@ -648,8 +815,12 @@ int k3_ringacc_ring_cfg(struct k3_ring *ring, struct k3_ring_cfg *cfg)
 	switch (ring->mode) {
 	case K3_RINGACC_RING_MODE_RING:
 		ring->ops = &k3_ring_mode_ring_ops;
+		ring->dma_dev = cfg->dma_dev;
+		if (!ring->dma_dev)
+			ring->dma_dev = ringacc->dev;
 		break;
 	case K3_RINGACC_RING_MODE_MESSAGE:
+		ring->dma_dev = ringacc->dev;
 		if (ring->proxy)
 			ring->ops = &k3_ring_mode_proxy_ops;
 		else
@@ -661,9 +832,9 @@ int k3_ringacc_ring_cfg(struct k3_ring *ring, struct k3_ring_cfg *cfg)
 		goto err_free_proxy;
 	}
 
-	ring->ring_mem_virt = dma_alloc_coherent(ringacc->dev,
-					ring->size * (4 << ring->elm_size),
-					&ring->ring_mem_dma, GFP_KERNEL);
+	ring->ring_mem_virt = dma_alloc_coherent(ring->dma_dev,
+						 ring->size * (4 << ring->elm_size),
+						 &ring->ring_mem_dma, GFP_KERNEL);
 	if (!ring->ring_mem_virt) {
 		dev_err(ringacc->dev, "Failed to alloc ring mem\n");
 		ret = -ENOMEM;
@@ -684,12 +855,13 @@ int k3_ringacc_ring_cfg(struct k3_ring *ring, struct k3_ring_cfg *cfg)
 	return 0;
 
 err_free_mem:
-	dma_free_coherent(ringacc->dev,
+	dma_free_coherent(ring->dma_dev,
 			  ring->size * (4 << ring->elm_size),
 			  ring->ring_mem_virt,
 			  ring->ring_mem_dma);
 err_free_ops:
 	ring->ops = NULL;
+	ring->dma_dev = NULL;
 err_free_proxy:
 	ring->proxy = NULL;
 	return ret;
@@ -711,7 +883,7 @@ u32 k3_ringacc_ring_get_free(struct k3_ring *ring)
 		return -EINVAL;
 
 	if (!ring->state.free)
-		ring->state.free = ring->size - readl(&ring->rt->occ);
+		ring->state.free = ring->size - k3_ringacc_ring_read_occ(ring);
 
 	return ring->state.free;
 }
@@ -722,7 +894,7 @@ u32 k3_ringacc_ring_get_occ(struct k3_ring *ring)
 	if (!ring || !(ring->flags & K3_RING_FLAG_BUSY))
 		return -EINVAL;
 
-	return readl(&ring->rt->occ);
+	return k3_ringacc_ring_read_occ(ring);
 }
 EXPORT_SYMBOL_GPL(k3_ringacc_ring_get_occ);
 
@@ -898,6 +1070,72 @@ static int k3_ringacc_ring_pop_tail_io(struct k3_ring *ring, void *elem)
 					 K3_RINGACC_ACCESS_MODE_POP_HEAD);
 }
 
+/*
+ * The element is 48 bits of address + ASEL bits in the ring.
+ * ASEL is used by the DMAs and should be removed for the kernel as it is not
+ * part of the physical memory address.
+ */
+static void k3_dmaring_remove_asel_from_elem(u64 *elem)
+{
+	*elem &= GENMASK_ULL(K3_ADDRESS_ASEL_SHIFT - 1, 0);
+}
+
+static int k3_dmaring_fwd_pop(struct k3_ring *ring, void *elem)
+{
+	void *elem_ptr;
+	u32 elem_idx;
+
+	/*
+	 * DMA rings: forward ring is always tied DMA channel and HW does not
+	 * maintain any state data required for POP operation and its unknown
+	 * how much elements were consumed by HW. So, to actually
+	 * do POP, the read pointer has to be recalculated every time.
+	 */
+	ring->state.occ = k3_ringacc_ring_read_occ(ring);
+	if (ring->state.windex >= ring->state.occ)
+		elem_idx = ring->state.windex - ring->state.occ;
+	else
+		elem_idx = ring->size - (ring->state.occ - ring->state.windex);
+
+	elem_ptr = k3_ringacc_get_elm_addr(ring, elem_idx);
+	memcpy(elem, elem_ptr, (4 << ring->elm_size));
+	k3_dmaring_remove_asel_from_elem(elem);
+
+	ring->state.occ--;
+	writel(-1, &ring->rt->db);
+
+	dev_dbg(ring->parent->dev, "%s: occ%d Windex%d Rindex%d pos_ptr%px\n",
+		__func__, ring->state.occ, ring->state.windex, elem_idx,
+		elem_ptr);
+	return 0;
+}
+
+static int k3_dmaring_reverse_pop(struct k3_ring *ring, void *elem)
+{
+	void *elem_ptr;
+
+	elem_ptr = k3_ringacc_get_elm_addr(ring, ring->state.rindex);
+
+	if (ring->state.occ) {
+		memcpy(elem, elem_ptr, (4 << ring->elm_size));
+		k3_dmaring_remove_asel_from_elem(elem);
+
+		ring->state.rindex = (ring->state.rindex + 1) % ring->size;
+		ring->state.occ--;
+		writel(-1 & K3_DMARING_RT_DB_ENTRY_MASK, &ring->rt->db);
+	} else if (ring->state.tdown_complete) {
+		dma_addr_t *value = elem;
+
+		*value = CPPI5_TDCM_MARKER;
+		writel(K3_DMARING_RT_DB_TDOWN_ACK, &ring->rt->db);
+		ring->state.tdown_complete = false;
+	}
+
+	dev_dbg(ring->parent->dev, "%s: occ%d index%d pos_ptr%px\n",
+		__func__, ring->state.occ, ring->state.rindex, elem_ptr);
+	return 0;
+}
+
 static int k3_ringacc_ring_push_mem(struct k3_ring *ring, void *elem)
 {
 	void *elem_ptr;
@@ -905,6 +1143,11 @@ static int k3_ringacc_ring_push_mem(struct k3_ring *ring, void *elem)
 	elem_ptr = k3_ringacc_get_elm_addr(ring, ring->state.windex);
 
 	memcpy(elem_ptr, elem, (4 << ring->elm_size));
+	if (ring->parent->dma_rings) {
+		u64 *addr = elem_ptr;
+
+		*addr |= ((u64)ring->asel << K3_ADDRESS_ASEL_SHIFT);
+	}
 
 	ring->state.windex = (ring->state.windex + 1) % ring->size;
 	ring->state.free--;
@@ -981,12 +1224,12 @@ int k3_ringacc_ring_pop(struct k3_ring *ring, void *elem)
 		return -EINVAL;
 
 	if (!ring->state.occ)
-		ring->state.occ = k3_ringacc_ring_get_occ(ring);
+		k3_ringacc_ring_update_occ(ring);
 
 	dev_dbg(ring->parent->dev, "ring_pop: occ%d index%d\n", ring->state.occ,
 		ring->state.rindex);
 
-	if (!ring->state.occ)
+	if (!ring->state.occ && !ring->state.tdown_complete)
 		return -ENODATA;
 
 	if (ring->ops && ring->ops->pop_head)
@@ -1004,7 +1247,7 @@ int k3_ringacc_ring_pop_tail(struct k3_ring *ring, void *elem)
 		return -EINVAL;
 
 	if (!ring->state.occ)
-		ring->state.occ = k3_ringacc_ring_get_occ(ring);
+		k3_ringacc_ring_update_occ(ring);
 
 	dev_dbg(ring->parent->dev, "ring_pop_tail: occ%d index%d\n",
 		ring->state.occ, ring->state.rindex);
@@ -1209,6 +1452,68 @@ static const struct of_device_id k3_ringacc_of_match[] = {
 	{},
 };
 
+struct k3_ringacc *k3_ringacc_dmarings_init(struct platform_device *pdev,
+					    struct k3_ringacc_init_data *data)
+{
+	struct device *dev = &pdev->dev;
+	struct k3_ringacc *ringacc;
+	void __iomem *base_rt;
+	struct resource *res;
+	int i;
+
+	ringacc = devm_kzalloc(dev, sizeof(*ringacc), GFP_KERNEL);
+	if (!ringacc)
+		return ERR_PTR(-ENOMEM);
+
+	ringacc->dev = dev;
+	ringacc->dma_rings = true;
+	ringacc->num_rings = data->num_rings;
+	ringacc->tisci = data->tisci;
+	ringacc->tisci_dev_id = data->tisci_dev_id;
+
+	mutex_init(&ringacc->req_lock);
+
+	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "ringrt");
+	base_rt = devm_ioremap_resource(dev, res);
+	if (IS_ERR(base_rt))
+		return ERR_CAST(base_rt);
+
+	ringacc->rings = devm_kzalloc(dev,
+				      sizeof(*ringacc->rings) *
+				      ringacc->num_rings * 2,
+				      GFP_KERNEL);
+	ringacc->rings_inuse = devm_kcalloc(dev,
+					    BITS_TO_LONGS(ringacc->num_rings),
+					    sizeof(unsigned long), GFP_KERNEL);
+
+	if (!ringacc->rings || !ringacc->rings_inuse)
+		return ERR_PTR(-ENOMEM);
+
+	for (i = 0; i < ringacc->num_rings; i++) {
+		struct k3_ring *ring = &ringacc->rings[i];
+
+		ring->rt = base_rt + K3_DMARING_RT_REGS_STEP * i;
+		ring->parent = ringacc;
+		ring->ring_id = i;
+		ring->proxy_id = K3_RINGACC_PROXY_NOT_USED;
+
+		ring = &ringacc->rings[ringacc->num_rings + i];
+		ring->rt = base_rt + K3_DMARING_RT_REGS_STEP * i +
+			   K3_DMARING_RT_REGS_REVERSE_OFS;
+		ring->parent = ringacc;
+		ring->ring_id = i;
+		ring->proxy_id = K3_RINGACC_PROXY_NOT_USED;
+		ring->flags = K3_RING_FLAG_REVERSE;
+	}
+
+	ringacc->tisci_ring_ops = &ringacc->tisci->ops.rm_ring_ops;
+
+	dev_info(dev, "Number of rings: %u\n", ringacc->num_rings);
+
+	return ringacc;
+}
+EXPORT_SYMBOL_GPL(k3_ringacc_dmarings_init);
+
 static int k3_ringacc_probe(struct platform_device *pdev)
 {
 	const struct ringacc_match_data *match_data;
diff --git a/drivers/soc/ti/k3-socinfo.c b/drivers/soc/ti/k3-socinfo.c
index bbbc2d2b7091..fd91129de6e5 100644
--- a/drivers/soc/ti/k3-socinfo.c
+++ b/drivers/soc/ti/k3-socinfo.c
@@ -40,6 +40,7 @@ static const struct k3_soc_id {
 	{ 0xBB5A, "AM65X" },
 	{ 0xBB64, "J721E" },
 	{ 0xBB6D, "J7200" },
+	{ 0xBB38, "AM64X" }
 };
 
 static int
diff --git a/drivers/soc/ti/knav_dma.c b/drivers/soc/ti/knav_dma.c
index 8c863ecb1c60..7b5cb5d48f7d 100644
--- a/drivers/soc/ti/knav_dma.c
+++ b/drivers/soc/ti/knav_dma.c
@@ -500,7 +500,7 @@ EXPORT_SYMBOL_GPL(knav_dma_open_channel);
 /**
  * knav_dma_close_channel()	- Destroy a dma channel
  *
- * channel:	dma channel handle
+ * @channel:	dma channel handle
  *
  */
 void knav_dma_close_channel(void *channel)
@@ -749,8 +749,9 @@ static int knav_dma_probe(struct platform_device *pdev)
 	pm_runtime_enable(kdev->dev);
 	ret = pm_runtime_get_sync(kdev->dev);
 	if (ret < 0) {
+		pm_runtime_put_noidle(kdev->dev);
 		dev_err(kdev->dev, "unable to enable pktdma, err %d\n", ret);
-		return ret;
+		goto err_pm_disable;
 	}
 
 	/* Initialise all packet dmas */
@@ -764,7 +765,8 @@ static int knav_dma_probe(struct platform_device *pdev)
 
 	if (list_empty(&kdev->list)) {
 		dev_err(dev, "no valid dma instance\n");
-		return -ENODEV;
+		ret = -ENODEV;
+		goto err_put_sync;
 	}
 
 	debugfs_create_file("knav_dma", S_IFREG | S_IRUGO, NULL, NULL,
@@ -772,6 +774,13 @@ static int knav_dma_probe(struct platform_device *pdev)
 
 	device_ready = true;
 	return ret;
+
+err_put_sync:
+	pm_runtime_put_sync(kdev->dev);
+err_pm_disable:
+	pm_runtime_disable(kdev->dev);
+
+	return ret;
 }
 
 static int knav_dma_remove(struct platform_device *pdev)
diff --git a/drivers/soc/ti/knav_qmss_queue.c b/drivers/soc/ti/knav_qmss_queue.c
index a460f201bf8e..2e521f1eda96 100644
--- a/drivers/soc/ti/knav_qmss_queue.c
+++ b/drivers/soc/ti/knav_qmss_queue.c
@@ -79,7 +79,7 @@ EXPORT_SYMBOL_GPL(knav_qmss_device_ready);
 /**
  * knav_queue_notify: qmss queue notfier call
  *
- * @inst:		qmss queue instance like accumulator
+ * @inst:		- qmss queue instance like accumulator
  */
 void knav_queue_notify(struct knav_queue_inst *inst)
 {
@@ -511,10 +511,10 @@ static int knav_queue_flush(struct knav_queue *qh)
 
 /**
  * knav_queue_open()	- open a hardware queue
- * @name		- name to give the queue handle
- * @id			- desired queue number if any or specifes the type
+ * @name:		- name to give the queue handle
+ * @id:			- desired queue number if any or specifes the type
  *			  of queue
- * @flags		- the following flags are applicable to queues:
+ * @flags:		- the following flags are applicable to queues:
  *	KNAV_QUEUE_SHARED - allow the queue to be shared. Queues are
  *			     exclusive by default.
  *			     Subsequent attempts to open a shared queue should
@@ -545,7 +545,7 @@ EXPORT_SYMBOL_GPL(knav_queue_open);
 
 /**
  * knav_queue_close()	- close a hardware queue handle
- * @qh			- handle to close
+ * @qhandle:		- handle to close
  */
 void knav_queue_close(void *qhandle)
 {
@@ -572,9 +572,9 @@ EXPORT_SYMBOL_GPL(knav_queue_close);
 
 /**
  * knav_queue_device_control()	- Perform control operations on a queue
- * @qh				- queue handle
- * @cmd				- control commands
- * @arg				- command argument
+ * @qhandle:			- queue handle
+ * @cmd:			- control commands
+ * @arg:			- command argument
  *
  * Returns 0 on success, errno otherwise.
  */
@@ -623,10 +623,10 @@ EXPORT_SYMBOL_GPL(knav_queue_device_control);
 
 /**
  * knav_queue_push()	- push data (or descriptor) to the tail of a queue
- * @qh			- hardware queue handle
- * @data		- data to push
- * @size		- size of data to push
- * @flags		- can be used to pass additional information
+ * @qhandle:		- hardware queue handle
+ * @dma:		- DMA data to push
+ * @size:		- size of data to push
+ * @flags:		- can be used to pass additional information
  *
  * Returns 0 on success, errno otherwise.
  */
@@ -646,8 +646,8 @@ EXPORT_SYMBOL_GPL(knav_queue_push);
 
 /**
  * knav_queue_pop()	- pop data (or descriptor) from the head of a queue
- * @qh			- hardware queue handle
- * @size		- (optional) size of the data pop'ed.
+ * @qhandle:		- hardware queue handle
+ * @size:		- (optional) size of the data pop'ed.
  *
  * Returns a DMA address on success, 0 on failure.
  */
@@ -746,9 +746,9 @@ EXPORT_SYMBOL_GPL(knav_pool_desc_dma_to_virt);
 
 /**
  * knav_pool_create()	- Create a pool of descriptors
- * @name		- name to give the pool handle
- * @num_desc		- numbers of descriptors in the pool
- * @region_id		- QMSS region id from which the descriptors are to be
+ * @name:		- name to give the pool handle
+ * @num_desc:		- numbers of descriptors in the pool
+ * @region_id:		- QMSS region id from which the descriptors are to be
  *			  allocated.
  *
  * Returns a pool handle on success.
@@ -856,7 +856,7 @@ EXPORT_SYMBOL_GPL(knav_pool_create);
 
 /**
  * knav_pool_destroy()	- Free a pool of descriptors
- * @pool		- pool handle
+ * @ph:		- pool handle
  */
 void knav_pool_destroy(void *ph)
 {
@@ -884,7 +884,7 @@ EXPORT_SYMBOL_GPL(knav_pool_destroy);
 
 /**
  * knav_pool_desc_get()	- Get a descriptor from the pool
- * @pool			- pool handle
+ * @ph:		- pool handle
  *
  * Returns descriptor from the pool.
  */
@@ -905,7 +905,8 @@ EXPORT_SYMBOL_GPL(knav_pool_desc_get);
 
 /**
  * knav_pool_desc_put()	- return a descriptor to the pool
- * @pool			- pool handle
+ * @ph:		- pool handle
+ * @desc:	- virtual address
  */
 void knav_pool_desc_put(void *ph, void *desc)
 {
@@ -918,11 +919,11 @@ EXPORT_SYMBOL_GPL(knav_pool_desc_put);
 
 /**
  * knav_pool_desc_map()	- Map descriptor for DMA transfer
- * @pool			- pool handle
- * @desc			- address of descriptor to map
- * @size			- size of descriptor to map
- * @dma				- DMA address return pointer
- * @dma_sz			- adjusted return pointer
+ * @ph:				- pool handle
+ * @desc:			- address of descriptor to map
+ * @size:			- size of descriptor to map
+ * @dma:			- DMA address return pointer
+ * @dma_sz:			- adjusted return pointer
  *
  * Returns 0 on success, errno otherwise.
  */
@@ -945,9 +946,9 @@ EXPORT_SYMBOL_GPL(knav_pool_desc_map);
 
 /**
  * knav_pool_desc_unmap()	- Unmap descriptor after DMA transfer
- * @pool			- pool handle
- * @dma				- DMA address of descriptor to unmap
- * @dma_sz			- size of descriptor to unmap
+ * @ph:				- pool handle
+ * @dma:			- DMA address of descriptor to unmap
+ * @dma_sz:			- size of descriptor to unmap
  *
  * Returns descriptor address on success, Use IS_ERR_OR_NULL() to identify
  * error values on return.
@@ -968,7 +969,7 @@ EXPORT_SYMBOL_GPL(knav_pool_desc_unmap);
 
 /**
  * knav_pool_count()	- Get the number of descriptors in pool.
- * @pool		- pool handle
+ * @ph:			- pool handle
  * Returns number of elements in the pool.
  */
 int knav_pool_count(void *ph)
@@ -1307,12 +1308,11 @@ static int knav_setup_queue_pools(struct knav_device *kdev,
 				   struct device_node *queue_pools)
 {
 	struct device_node *type, *range;
-	int ret;
 
 	for_each_child_of_node(queue_pools, type) {
 		for_each_child_of_node(type, range) {
-			ret = knav_setup_queue_range(kdev, range);
 			/* return value ignored, we init the rest... */
+			knav_setup_queue_range(kdev, range);
 		}
 	}
 
@@ -1784,6 +1784,7 @@ static int knav_queue_probe(struct platform_device *pdev)
 	pm_runtime_enable(&pdev->dev);
 	ret = pm_runtime_get_sync(&pdev->dev);
 	if (ret < 0) {
+		pm_runtime_put_noidle(&pdev->dev);
 		dev_err(dev, "Failed to enable QMSS\n");
 		return ret;
 	}
@@ -1851,9 +1852,10 @@ static int knav_queue_probe(struct platform_device *pdev)
 	if (ret)
 		goto err;
 
-	regions =  of_get_child_by_name(node, "descriptor-regions");
+	regions = of_get_child_by_name(node, "descriptor-regions");
 	if (!regions) {
 		dev_err(dev, "descriptor-regions not specified\n");
+		ret = -ENODEV;
 		goto err;
 	}
 	ret = knav_queue_setup_regions(kdev, regions);
diff --git a/drivers/soc/ti/omap_prm.c b/drivers/soc/ti/omap_prm.c
index 3dc3f34afbab..bf1468e5bccb 100644
--- a/drivers/soc/ti/omap_prm.c
+++ b/drivers/soc/ti/omap_prm.c
@@ -7,6 +7,7 @@
  */
 
 #include <linux/kernel.h>
+#include <linux/clk.h>
 #include <linux/device.h>
 #include <linux/io.h>
 #include <linux/iopoll.h>
@@ -14,6 +15,7 @@
 #include <linux/of.h>
 #include <linux/of_device.h>
 #include <linux/platform_device.h>
+#include <linux/pm_clock.h>
 #include <linux/pm_domain.h>
 #include <linux/reset-controller.h>
 #include <linux/delay.h>
@@ -41,6 +43,7 @@ struct omap_prm_domain {
 	u16 pwrstst;
 	const struct omap_prm_domain_map *cap;
 	u32 pwrstctrl_saved;
+	unsigned int uses_pm_clk:1;
 };
 
 struct omap_rst_map {
@@ -121,6 +124,16 @@ static const struct omap_prm_domain_map omap_prm_onoff_noauto = {
 	.statechange = 1,
 };
 
+static const struct omap_prm_domain_map omap_prm_alwon = {
+	.usable_modes = BIT(OMAP_PRMD_ON_ACTIVE),
+};
+
+static const struct omap_prm_domain_map omap_prm_reton = {
+	.usable_modes = BIT(OMAP_PRMD_ON_ACTIVE) | BIT(OMAP_PRMD_RETENTION),
+	.statechange = 1,
+	.logicretstate = 1,
+};
+
 static const struct omap_rst_map rst_map_0[] = {
 	{ .rst = 0, .st = 0 },
 	{ .rst = -1 },
@@ -140,39 +153,237 @@ static const struct omap_rst_map rst_map_012[] = {
 };
 
 static const struct omap_prm_data omap4_prm_data[] = {
-	{ .name = "tesla", .base = 0x4a306400, .rstctrl = 0x10, .rstst = 0x14, .rstmap = rst_map_01 },
+	{
+		.name = "mpu", .base = 0x4a306300,
+		.pwrstctrl = 0x0, .pwrstst = 0x4, .dmap = &omap_prm_reton,
+	},
+	{
+		.name = "tesla", .base = 0x4a306400,
+		.pwrstctrl = 0x0, .pwrstst = 0x4, .dmap = &omap_prm_noinact,
+		.rstctrl = 0x10, .rstst = 0x14, .rstmap = rst_map_01
+	},
 	{
 		.name = "abe", .base = 0x4a306500,
 		.pwrstctrl = 0, .pwrstst = 0x4, .dmap = &omap_prm_all,
 	},
-	{ .name = "core", .base = 0x4a306700, .rstctrl = 0x210, .rstst = 0x214, .clkdm_name = "ducati", .rstmap = rst_map_012 },
-	{ .name = "ivahd", .base = 0x4a306f00, .rstctrl = 0x10, .rstst = 0x14, .rstmap = rst_map_012 },
-	{ .name = "device", .base = 0x4a307b00, .rstctrl = 0x0, .rstst = 0x4, .rstmap = rst_map_01, .flags = OMAP_PRM_HAS_RSTCTRL | OMAP_PRM_HAS_NO_CLKDM },
+	{
+		.name = "always_on_core", .base = 0x4a306600,
+		.pwrstctrl = 0x0, .pwrstst = 0x4, .dmap = &omap_prm_alwon,
+	},
+	{
+		.name = "core", .base = 0x4a306700,
+		.pwrstctrl = 0x0, .pwrstst = 0x4, .dmap = &omap_prm_reton,
+		.rstctrl = 0x210, .rstst = 0x214, .clkdm_name = "ducati",
+		.rstmap = rst_map_012
+	},
+	{
+		.name = "ivahd", .base = 0x4a306f00,
+		.pwrstctrl = 0x0, .pwrstst = 0x4, .dmap = &omap_prm_noinact,
+		.rstctrl = 0x10, .rstst = 0x14, .rstmap = rst_map_012
+	},
+	{
+		.name = "cam", .base = 0x4a307000,
+		.pwrstctrl = 0x0, .pwrstst = 0x4, .dmap = &omap_prm_onoff_noauto,
+	},
+	{
+		.name = "dss", .base = 0x4a307100,
+		.pwrstctrl = 0x0, .pwrstst = 0x4, .dmap = &omap_prm_noinact
+	},
+	{
+		.name = "gfx", .base = 0x4a307200,
+		.pwrstctrl = 0x0, .pwrstst = 0x4, .dmap = &omap_prm_onoff_noauto
+	},
+	{
+		.name = "l3init", .base = 0x4a307300,
+		.pwrstctrl = 0x0, .pwrstst = 0x4, .dmap = &omap_prm_reton
+	},
+	{
+		.name = "l4per", .base = 0x4a307400,
+		.pwrstctrl = 0x0, .pwrstst = 0x4, .dmap = &omap_prm_reton
+	},
+	{
+		.name = "cefuse", .base = 0x4a307600,
+		.pwrstctrl = 0x0, .pwrstst = 0x4, .dmap = &omap_prm_onoff_noauto
+	},
+	{
+		.name = "wkup", .base = 0x4a307700,
+		.pwrstctrl = 0x0, .pwrstst = 0x4, .dmap = &omap_prm_alwon
+	},
+	{
+		.name = "emu", .base = 0x4a307900,
+		.pwrstctrl = 0x0, .pwrstst = 0x4, .dmap = &omap_prm_onoff_noauto
+	},
+	{
+		.name = "device", .base = 0x4a307b00,
+		.rstctrl = 0x0, .rstst = 0x4, .rstmap = rst_map_01,
+		.flags = OMAP_PRM_HAS_RSTCTRL | OMAP_PRM_HAS_NO_CLKDM
+	},
 	{ },
 };
 
 static const struct omap_prm_data omap5_prm_data[] = {
-	{ .name = "dsp", .base = 0x4ae06400, .rstctrl = 0x10, .rstst = 0x14, .rstmap = rst_map_01 },
+	{
+		.name = "mpu", .base = 0x4ae06300,
+		.pwrstctrl = 0x0, .pwrstst = 0x4, .dmap = &omap_prm_reton,
+	},
+	{
+		.name = "dsp", .base = 0x4ae06400,
+		.pwrstctrl = 0x0, .pwrstst = 0x4, .dmap = &omap_prm_noinact,
+		.rstctrl = 0x10, .rstst = 0x14, .rstmap = rst_map_01
+	},
 	{
 		.name = "abe", .base = 0x4ae06500,
 		.pwrstctrl = 0, .pwrstst = 0x4, .dmap = &omap_prm_nooff,
 	},
-	{ .name = "core", .base = 0x4ae06700, .rstctrl = 0x210, .rstst = 0x214, .clkdm_name = "ipu", .rstmap = rst_map_012 },
-	{ .name = "iva", .base = 0x4ae07200, .rstctrl = 0x10, .rstst = 0x14, .rstmap = rst_map_012 },
-	{ .name = "device", .base = 0x4ae07c00, .rstctrl = 0x0, .rstst = 0x4, .rstmap = rst_map_01, .flags = OMAP_PRM_HAS_RSTCTRL | OMAP_PRM_HAS_NO_CLKDM },
+	{
+		.name = "coreaon", .base = 0x4ae06600,
+		.pwrstctrl = 0x0, .pwrstst = 0x4, .dmap = &omap_prm_alwon
+	},
+	{
+		.name = "core", .base = 0x4ae06700,
+		.pwrstctrl = 0x0, .pwrstst = 0x4, .dmap = &omap_prm_reton,
+		.rstctrl = 0x210, .rstst = 0x214, .clkdm_name = "ipu",
+		.rstmap = rst_map_012
+	},
+	{
+		.name = "iva", .base = 0x4ae07200,
+		.pwrstctrl = 0x0, .pwrstst = 0x4, .dmap = &omap_prm_noinact,
+		.rstctrl = 0x10, .rstst = 0x14, .rstmap = rst_map_012
+	},
+	{
+		.name = "cam", .base = 0x4ae07300,
+		.pwrstctrl = 0x0, .pwrstst = 0x4, .dmap = &omap_prm_onoff_noauto
+	},
+	{
+		.name = "dss", .base = 0x4ae07400,
+		.pwrstctrl = 0x0, .pwrstst = 0x4, .dmap = &omap_prm_noinact
+	},
+	{
+		.name = "gpu", .base = 0x4ae07500,
+		.pwrstctrl = 0x0, .pwrstst = 0x4, .dmap = &omap_prm_onoff_noauto
+	},
+	{
+		.name = "l3init", .base = 0x4ae07600,
+		.pwrstctrl = 0x0, .pwrstst = 0x4, .dmap = &omap_prm_reton
+	},
+	{
+		.name = "custefuse", .base = 0x4ae07700,
+		.pwrstctrl = 0x0, .pwrstst = 0x4, .dmap = &omap_prm_onoff_noauto
+	},
+	{
+		.name = "wkupaon", .base = 0x4ae07800,
+		.pwrstctrl = 0x0, .pwrstst = 0x4, .dmap = &omap_prm_alwon
+	},
+	{
+		.name = "emu", .base = 0x4ae07a00,
+		.pwrstctrl = 0x0, .pwrstst = 0x4, .dmap = &omap_prm_onoff_noauto
+	},
+	{
+		.name = "device", .base = 0x4ae07c00,
+		.rstctrl = 0x0, .rstst = 0x4, .rstmap = rst_map_01,
+		.flags = OMAP_PRM_HAS_RSTCTRL | OMAP_PRM_HAS_NO_CLKDM
+	},
 	{ },
 };
 
 static const struct omap_prm_data dra7_prm_data[] = {
-	{ .name = "dsp1", .base = 0x4ae06400, .rstctrl = 0x10, .rstst = 0x14, .rstmap = rst_map_01 },
-	{ .name = "ipu", .base = 0x4ae06500, .rstctrl = 0x10, .rstst = 0x14, .clkdm_name = "ipu1", .rstmap = rst_map_012 },
-	{ .name = "core", .base = 0x4ae06700, .rstctrl = 0x210, .rstst = 0x214, .clkdm_name = "ipu2", .rstmap = rst_map_012 },
-	{ .name = "iva", .base = 0x4ae06f00, .rstctrl = 0x10, .rstst = 0x14, .rstmap = rst_map_012 },
-	{ .name = "dsp2", .base = 0x4ae07b00, .rstctrl = 0x10, .rstst = 0x14, .rstmap = rst_map_01 },
-	{ .name = "eve1", .base = 0x4ae07b40, .rstctrl = 0x10, .rstst = 0x14, .rstmap = rst_map_01 },
-	{ .name = "eve2", .base = 0x4ae07b80, .rstctrl = 0x10, .rstst = 0x14, .rstmap = rst_map_01 },
-	{ .name = "eve3", .base = 0x4ae07bc0, .rstctrl = 0x10, .rstst = 0x14, .rstmap = rst_map_01 },
-	{ .name = "eve4", .base = 0x4ae07c00, .rstctrl = 0x10, .rstst = 0x14, .rstmap = rst_map_01 },
+	{
+		.name = "mpu", .base = 0x4ae06300,
+		.pwrstctrl = 0x0, .pwrstst = 0x4, .dmap = &omap_prm_reton,
+	},
+	{
+		.name = "dsp1", .base = 0x4ae06400,
+		.pwrstctrl = 0x0, .pwrstst = 0x4, .dmap = &omap_prm_onoff_noauto,
+		.rstctrl = 0x10, .rstst = 0x14, .rstmap = rst_map_01,
+	},
+	{
+		.name = "ipu", .base = 0x4ae06500,
+		.pwrstctrl = 0x0, .pwrstst = 0x4, .dmap = &omap_prm_onoff_noauto,
+		.rstctrl = 0x10, .rstst = 0x14, .rstmap = rst_map_012,
+		.clkdm_name = "ipu1"
+	},
+	{
+		.name = "coreaon", .base = 0x4ae06628,
+		.pwrstctrl = 0x0, .pwrstst = 0x4, .dmap = &omap_prm_alwon,
+	},
+	{
+		.name = "core", .base = 0x4ae06700,
+		.pwrstctrl = 0x0, .pwrstst = 0x4, .dmap = &omap_prm_alwon,
+		.rstctrl = 0x210, .rstst = 0x214, .rstmap = rst_map_012,
+		.clkdm_name = "ipu2"
+	},
+	{
+		.name = "iva", .base = 0x4ae06f00,
+		.pwrstctrl = 0x0, .pwrstst = 0x4, .dmap = &omap_prm_onoff_noauto,
+		.rstctrl = 0x10, .rstst = 0x14, .rstmap = rst_map_012,
+	},
+	{
+		.name = "cam", .base = 0x4ae07000,
+		.pwrstctrl = 0x0, .pwrstst = 0x4, .dmap = &omap_prm_onoff_noauto,
+	},
+	{
+		.name = "dss", .base = 0x4ae07100,
+		.pwrstctrl = 0x0, .pwrstst = 0x4, .dmap = &omap_prm_onoff_noauto,
+	},
+	{
+		.name = "gpu", .base = 0x4ae07200,
+		.pwrstctrl = 0x0, .pwrstst = 0x4, .dmap = &omap_prm_onoff_noauto,
+	},
+	{
+		.name = "l3init", .base = 0x4ae07300,
+		.pwrstctrl = 0x0, .pwrstst = 0x4, .dmap = &omap_prm_alwon,
+		.rstctrl = 0x10, .rstst = 0x14, .rstmap = rst_map_012,
+		.clkdm_name = "pcie"
+	},
+	{
+		.name = "l4per", .base = 0x4ae07400,
+		.pwrstctrl = 0x0, .pwrstst = 0x4, .dmap = &omap_prm_alwon,
+	},
+	{
+		.name = "custefuse", .base = 0x4ae07600,
+		.pwrstctrl = 0x0, .pwrstst = 0x4, .dmap = &omap_prm_onoff_noauto,
+	},
+	{
+		.name = "wkupaon", .base = 0x4ae07724,
+		.pwrstctrl = 0x0, .pwrstst = 0x4, .dmap = &omap_prm_alwon,
+	},
+	{
+		.name = "emu", .base = 0x4ae07900,
+		.pwrstctrl = 0x0, .pwrstst = 0x4, .dmap = &omap_prm_onoff_noauto,
+	},
+	{
+		.name = "dsp2", .base = 0x4ae07b00,
+		.pwrstctrl = 0x0, .pwrstst = 0x4, .dmap = &omap_prm_onoff_noauto,
+		.rstctrl = 0x10, .rstst = 0x14, .rstmap = rst_map_01
+	},
+	{
+		.name = "eve1", .base = 0x4ae07b40,
+		.pwrstctrl = 0x0, .pwrstst = 0x4, .dmap = &omap_prm_onoff_noauto,
+		.rstctrl = 0x10, .rstst = 0x14, .rstmap = rst_map_01
+	},
+	{
+		.name = "eve2", .base = 0x4ae07b80,
+		.pwrstctrl = 0x0, .pwrstst = 0x4, .dmap = &omap_prm_onoff_noauto,
+		.rstctrl = 0x10, .rstst = 0x14, .rstmap = rst_map_01
+	},
+	{
+		.name = "eve3", .base = 0x4ae07bc0,
+		.pwrstctrl = 0x0, .pwrstst = 0x4, .dmap = &omap_prm_onoff_noauto,
+		.rstctrl = 0x10, .rstst = 0x14, .rstmap = rst_map_01
+	},
+	{
+		.name = "eve4", .base = 0x4ae07c00,
+		.pwrstctrl = 0x0, .pwrstst = 0x4, .dmap = &omap_prm_onoff_noauto,
+		.rstctrl = 0x10, .rstst = 0x14, .rstmap = rst_map_01
+	},
+	{
+		.name = "rtc", .base = 0x4ae07c60,
+		.pwrstctrl = 0x0, .pwrstst = 0x4, .dmap = &omap_prm_alwon,
+	},
+	{
+		.name = "vpe", .base = 0x4ae07c80,
+		.pwrstctrl = 0x0, .pwrstst = 0x4, .dmap = &omap_prm_onoff_noauto,
+	},
 	{ },
 };
 
@@ -187,14 +398,40 @@ static const struct omap_rst_map am3_wkup_rst_map[] = {
 };
 
 static const struct omap_prm_data am3_prm_data[] = {
-	{ .name = "per", .base = 0x44e00c00, .rstctrl = 0x0, .rstmap = am3_per_rst_map, .flags = OMAP_PRM_HAS_RSTCTRL, .clkdm_name = "pruss_ocp" },
-	{ .name = "wkup", .base = 0x44e00d00, .rstctrl = 0x0, .rstst = 0xc, .rstmap = am3_wkup_rst_map, .flags = OMAP_PRM_HAS_RSTCTRL | OMAP_PRM_HAS_NO_CLKDM },
-	{ .name = "device", .base = 0x44e00f00, .rstctrl = 0x0, .rstst = 0x8, .rstmap = rst_map_01, .flags = OMAP_PRM_HAS_RSTCTRL | OMAP_PRM_HAS_NO_CLKDM },
+	{
+		.name = "per", .base = 0x44e00c00,
+		.pwrstctrl = 0xc, .pwrstst = 0x8, .dmap = &omap_prm_noinact,
+		.rstctrl = 0x0, .rstmap = am3_per_rst_map,
+		.flags = OMAP_PRM_HAS_RSTCTRL, .clkdm_name = "pruss_ocp"
+	},
+	{
+		.name = "wkup", .base = 0x44e00d00,
+		.pwrstctrl = 0x4, .pwrstst = 0x4, .dmap = &omap_prm_alwon,
+		.rstctrl = 0x0, .rstst = 0xc, .rstmap = am3_wkup_rst_map,
+		.flags = OMAP_PRM_HAS_RSTCTRL | OMAP_PRM_HAS_NO_CLKDM
+	},
+	{
+		.name = "mpu", .base = 0x44e00e00,
+		.pwrstctrl = 0x0, .pwrstst = 0x4, .dmap = &omap_prm_noinact,
+	},
+	{
+		.name = "device", .base = 0x44e00f00,
+		.rstctrl = 0x0, .rstst = 0x8, .rstmap = rst_map_01,
+		.flags = OMAP_PRM_HAS_RSTCTRL | OMAP_PRM_HAS_NO_CLKDM
+	},
+	{
+		.name = "rtc", .base = 0x44e01000,
+		.pwrstctrl = 0x0, .pwrstst = 0x4, .dmap = &omap_prm_alwon,
+	},
 	{
 		.name = "gfx", .base = 0x44e01100,
 		.pwrstctrl = 0, .pwrstst = 0x10, .dmap = &omap_prm_noinact,
 		.rstctrl = 0x4, .rstst = 0x14, .rstmap = rst_map_0, .clkdm_name = "gfx_l3",
 	},
+	{
+		.name = "cefuse", .base = 0x44e01200,
+		.pwrstctrl = 0x0, .pwrstst = 0x4, .dmap = &omap_prm_onoff_noauto,
+	},
 	{ },
 };
 
@@ -211,13 +448,43 @@ static const struct omap_rst_map am4_device_rst_map[] = {
 
 static const struct omap_prm_data am4_prm_data[] = {
 	{
+		.name = "mpu", .base = 0x44df0300,
+		.pwrstctrl = 0x0, .pwrstst = 0x4, .dmap = &omap_prm_noinact,
+	},
+	{
 		.name = "gfx", .base = 0x44df0400,
 		.pwrstctrl = 0, .pwrstst = 0x4, .dmap = &omap_prm_onoff_noauto,
 		.rstctrl = 0x10, .rstst = 0x14, .rstmap = rst_map_0, .clkdm_name = "gfx_l3",
 	},
-	{ .name = "per", .base = 0x44df0800, .rstctrl = 0x10, .rstst = 0x14, .rstmap = am4_per_rst_map, .clkdm_name = "pruss_ocp" },
-	{ .name = "wkup", .base = 0x44df2000, .rstctrl = 0x10, .rstst = 0x14, .rstmap = am3_wkup_rst_map, .flags = OMAP_PRM_HAS_NO_CLKDM },
-	{ .name = "device", .base = 0x44df4000, .rstctrl = 0x0, .rstst = 0x4, .rstmap = am4_device_rst_map, .flags = OMAP_PRM_HAS_RSTCTRL | OMAP_PRM_HAS_NO_CLKDM },
+	{
+		.name = "rtc", .base = 0x44df0500,
+		.pwrstctrl = 0x0, .pwrstst = 0x4, .dmap = &omap_prm_alwon,
+	},
+	{
+		.name = "tamper", .base = 0x44df0600,
+		.pwrstctrl = 0x0, .pwrstst = 0x4, .dmap = &omap_prm_alwon,
+	},
+	{
+		.name = "cefuse", .base = 0x44df0700,
+		.pwrstctrl = 0x0, .pwrstst = 0x4, .dmap = &omap_prm_onoff_noauto,
+	},
+	{
+		.name = "per", .base = 0x44df0800,
+		.pwrstctrl = 0x0, .pwrstst = 0x4, .dmap = &omap_prm_noinact,
+		.rstctrl = 0x10, .rstst = 0x14, .rstmap = am4_per_rst_map,
+		.clkdm_name = "pruss_ocp"
+	},
+	{
+		.name = "wkup", .base = 0x44df2000,
+		.pwrstctrl = 0x0, .pwrstst = 0x4, .dmap = &omap_prm_alwon,
+		.rstctrl = 0x10, .rstst = 0x14, .rstmap = am3_wkup_rst_map,
+		.flags = OMAP_PRM_HAS_NO_CLKDM
+	},
+	{
+		.name = "device", .base = 0x44df4000,
+		.rstctrl = 0x0, .rstst = 0x4, .rstmap = am4_device_rst_map,
+		.flags = OMAP_PRM_HAS_RSTCTRL | OMAP_PRM_HAS_NO_CLKDM
+	},
 	{ },
 };
 
@@ -325,6 +592,38 @@ static int omap_prm_domain_power_off(struct generic_pm_domain *domain)
 	return 0;
 }
 
+/*
+ * Note that ti-sysc already manages the module clocks separately so
+ * no need to manage those. Interconnect instances need clocks managed
+ * for simple-pm-bus.
+ */
+static int omap_prm_domain_attach_clock(struct device *dev,
+					struct omap_prm_domain *prmd)
+{
+	struct device_node *np = dev->of_node;
+	int error;
+
+	if (!of_device_is_compatible(np, "simple-pm-bus"))
+		return 0;
+
+	if (!of_property_read_bool(np, "clocks"))
+		return 0;
+
+	error = pm_clk_create(dev);
+	if (error)
+		return error;
+
+	error = of_pm_clk_add_clks(dev);
+	if (error < 0) {
+		pm_clk_destroy(dev);
+		return error;
+	}
+
+	prmd->uses_pm_clk = 1;
+
+	return 0;
+}
+
 static int omap_prm_domain_attach_dev(struct generic_pm_domain *domain,
 				      struct device *dev)
 {
@@ -349,6 +648,10 @@ static int omap_prm_domain_attach_dev(struct generic_pm_domain *domain,
 	genpd_data = dev_gpd_data(dev);
 	genpd_data->data = NULL;
 
+	ret = omap_prm_domain_attach_clock(dev, prmd);
+	if (ret)
+		return ret;
+
 	return 0;
 }
 
@@ -356,7 +659,11 @@ static void omap_prm_domain_detach_dev(struct generic_pm_domain *domain,
 				       struct device *dev)
 {
 	struct generic_pm_domain_data *genpd_data;
+	struct omap_prm_domain *prmd;
 
+	prmd = genpd_to_prm_domain(domain);
+	if (prmd->uses_pm_clk)
+		pm_clk_destroy(dev);
 	genpd_data = dev_gpd_data(dev);
 	genpd_data->data = NULL;
 }
@@ -393,6 +700,7 @@ static int omap_prm_domain_init(struct device *dev, struct omap_prm *prm)
 	prmd->pd.power_off = omap_prm_domain_power_off;
 	prmd->pd.attach_dev = omap_prm_domain_attach_dev;
 	prmd->pd.detach_dev = omap_prm_domain_detach_dev;
+	prmd->pd.flags = GENPD_FLAG_PM_CLK;
 
 	pm_genpd_init(&prmd->pd, NULL, true);
 	error = of_genpd_add_provider_simple(np, &prmd->pd);
@@ -484,6 +792,10 @@ static int omap_reset_deassert(struct reset_controller_dev *rcdev,
 	struct ti_prm_platform_data *pdata = dev_get_platdata(reset->dev);
 	int ret = 0;
 
+	/* Nothing to do if the reset is already deasserted */
+	if (!omap_reset_status(rcdev, id))
+		return 0;
+
 	has_rstst = reset->prm->data->rstst ||
 		(reset->prm->data->flags & OMAP_PRM_HAS_RSTST);
 
diff --git a/drivers/soc/ti/pm33xx.c b/drivers/soc/ti/pm33xx.c
index d2f5e7001a93..64f3e3105540 100644
--- a/drivers/soc/ti/pm33xx.c
+++ b/drivers/soc/ti/pm33xx.c
@@ -19,6 +19,7 @@
 #include <linux/of_address.h>
 #include <linux/platform_data/pm33xx.h>
 #include <linux/platform_device.h>
+#include <linux/pm_runtime.h>
 #include <linux/rtc.h>
 #include <linux/rtc/rtc-omap.h>
 #include <linux/sizes.h>
@@ -135,13 +136,11 @@ static int am33xx_push_sram_idle(void)
 
 static int am33xx_do_sram_idle(u32 wfi_flags)
 {
-	int ret = 0;
-
 	if (!m3_ipc || !pm_ops)
 		return 0;
 
 	if (wfi_flags & WFI_FLAG_WAKE_M3)
-		ret = m3_ipc->ops->prepare_low_power(m3_ipc, WKUP_M3_IDLE);
+		m3_ipc->ops->prepare_low_power(m3_ipc, WKUP_M3_IDLE);
 
 	return pm_ops->cpu_suspend(am33xx_do_wfi_sram, wfi_flags);
 }
@@ -555,16 +554,26 @@ static int am33xx_pm_probe(struct platform_device *pdev)
 	suspend_wfi_flags |= WFI_FLAG_WAKE_M3;
 #endif /* CONFIG_SUSPEND */
 
+	pm_runtime_enable(dev);
+	ret = pm_runtime_get_sync(dev);
+	if (ret < 0) {
+		pm_runtime_put_noidle(dev);
+		goto err_pm_runtime_disable;
+	}
+
 	ret = pm_ops->init(am33xx_do_sram_idle);
 	if (ret) {
 		dev_err(dev, "Unable to call core pm init!\n");
 		ret = -ENODEV;
-		goto err_put_wkup_m3_ipc;
+		goto err_pm_runtime_put;
 	}
 
 	return 0;
 
-err_put_wkup_m3_ipc:
+err_pm_runtime_put:
+	pm_runtime_put_sync(dev);
+err_pm_runtime_disable:
+	pm_runtime_disable(dev);
 	wkup_m3_ipc_put(m3_ipc);
 err_free_sram:
 	am33xx_pm_free_sram();
@@ -574,6 +583,8 @@ err_free_sram:
 
 static int am33xx_pm_remove(struct platform_device *pdev)
 {
+	pm_runtime_put_sync(&pdev->dev);
+	pm_runtime_disable(&pdev->dev);
 	if (pm_ops->deinit)
 		pm_ops->deinit();
 	suspend_set_ops(NULL);
diff --git a/drivers/soc/ti/pruss.c b/drivers/soc/ti/pruss.c
index cc0b4ad7a3d3..5d6e7132a5c4 100644
--- a/drivers/soc/ti/pruss.c
+++ b/drivers/soc/ti/pruss.c
@@ -126,8 +126,6 @@ static int pruss_clk_init(struct pruss *pruss, struct device_node *cfg_node)
 	int ret = 0;
 
 	data = of_device_get_match_data(dev);
-	if (IS_ERR(data))
-		return -ENODEV;
 
 	clks_np = of_get_child_by_name(cfg_node, "clocks");
 	if (!clks_np) {
@@ -175,10 +173,6 @@ static int pruss_probe(struct platform_device *pdev)
 	const char *mem_names[PRUSS_MEM_MAX] = { "dram0", "dram1", "shrdram2" };
 
 	data = of_device_get_match_data(&pdev->dev);
-	if (IS_ERR(data)) {
-		dev_err(dev, "missing private data\n");
-		return -ENODEV;
-	}
 
 	ret = dma_set_coherent_mask(dev, DMA_BIT_MASK(32));
 	if (ret) {
diff --git a/drivers/soc/ti/ti_sci_inta_msi.c b/drivers/soc/ti/ti_sci_inta_msi.c
index 0eb9462f609e..a1d9c027022a 100644
--- a/drivers/soc/ti/ti_sci_inta_msi.c
+++ b/drivers/soc/ti/ti_sci_inta_msi.c
@@ -89,6 +89,18 @@ static int ti_sci_inta_msi_alloc_descs(struct device *dev,
 			list_add_tail(&msi_desc->list, dev_to_msi_list(dev));
 			count++;
 		}
+		for (i = 0; i < res->desc[set].num_sec; i++) {
+			msi_desc = alloc_msi_entry(dev, 1, NULL);
+			if (!msi_desc) {
+				ti_sci_inta_msi_free_descs(dev);
+				return -ENOMEM;
+			}
+
+			msi_desc->inta.dev_index = res->desc[set].start_sec + i;
+			INIT_LIST_HEAD(&msi_desc->list);
+			list_add_tail(&msi_desc->list, dev_to_msi_list(dev));
+			count++;
+		}
 	}
 
 	return count;
diff --git a/drivers/soc/ti/wkup_m3_ipc.c b/drivers/soc/ti/wkup_m3_ipc.c
index e9ece45d7a33..c3e2161df732 100644
--- a/drivers/soc/ti/wkup_m3_ipc.c
+++ b/drivers/soc/ti/wkup_m3_ipc.c
@@ -218,6 +218,7 @@ static int wkup_m3_is_available(struct wkup_m3_ipc *m3_ipc)
 /* Public functions */
 /**
  * wkup_m3_set_mem_type - Pass wkup_m3 which type of memory is in use
+ * @m3_ipc: Pointer to wkup_m3_ipc context
  * @mem_type: memory type value read directly from emif
  *
  * wkup_m3 must know what memory type is in use to properly suspend
@@ -230,6 +231,7 @@ static void wkup_m3_set_mem_type(struct wkup_m3_ipc *m3_ipc, int mem_type)
 
 /**
  * wkup_m3_set_resume_address - Pass wkup_m3 resume address
+ * @m3_ipc: Pointer to wkup_m3_ipc context
  * @addr: Physical address from which resume code should execute
  */
 static void wkup_m3_set_resume_address(struct wkup_m3_ipc *m3_ipc, void *addr)
@@ -239,6 +241,7 @@ static void wkup_m3_set_resume_address(struct wkup_m3_ipc *m3_ipc, void *addr)
 
 /**
  * wkup_m3_request_pm_status - Retrieve wkup_m3 status code after suspend
+ * @m3_ipc: Pointer to wkup_m3_ipc context
  *
  * Returns code representing the status of a low power mode transition.
  *	0 - Successful transition
@@ -260,6 +263,7 @@ static int wkup_m3_request_pm_status(struct wkup_m3_ipc *m3_ipc)
 /**
  * wkup_m3_prepare_low_power - Request preparation for transition to
  *			       low power state
+ * @m3_ipc: Pointer to wkup_m3_ipc context
  * @state: A kernel suspend state to enter, either MEM or STANDBY
  *
  * Returns 0 if preparation was successful, otherwise returns error code
@@ -315,6 +319,7 @@ static int wkup_m3_prepare_low_power(struct wkup_m3_ipc *m3_ipc, int state)
 
 /**
  * wkup_m3_finish_low_power - Return m3 to reset state
+ * @m3_ipc: Pointer to wkup_m3_ipc context
  *
  * Returns 0 if reset was successful, otherwise returns error code
  */
@@ -362,8 +367,7 @@ static const char *wkup_m3_request_wake_src(struct wkup_m3_ipc *m3_ipc)
 
 /**
  * wkup_m3_set_rtc_only - Set the rtc_only flag
- * @wkup_m3_wakeup: struct wkup_m3_wakeup_src * gets assigned the
- *                  wakeup src value
+ * @m3_ipc: Pointer to wkup_m3_ipc context
  */
 static void wkup_m3_set_rtc_only(struct wkup_m3_ipc *m3_ipc)
 {