Merge tag 'rpi-next-2021.04' of https://gitlab.denx.de/u-boot/custodians/u-boot-raspberrypi

- add iProc RNG2000 driver for RPi4
- add support for CM4 and RPi400

15 files changed, 403 insertions, 40 deletions

diff --git a/drivers/core/Kconfig b/drivers/core/Kconfig
index dbfe51c6e8..00554af499 100644
--- a/drivers/core/Kconfig
+++ b/drivers/core/Kconfig
@@ -129,6 +129,16 @@ config TPL_DM_INLINE_OFNODE
 	  This applies to several ofnode functions (see ofnode.h) which are
 	  seldom used. Inlining them can help reduce code size.
 
+config DM_DMA
+	bool "Support per-device DMA constraints"
+	depends on DM
+	default n
+	help
+	  Enable this to extract per-device DMA constraints, only supported on
+	  device-tree systems for now. This is needed in order translate
+	  addresses on systems where different buses have different views of
+	  the physical address space.
+
 config REGMAP
 	bool "Support register maps"
 	depends on DM
diff --git a/drivers/core/device.c b/drivers/core/device.c
index 82a0098960..625134921d 100644
--- a/drivers/core/device.c
+++ b/drivers/core/device.c
@@ -422,6 +422,43 @@ fail:
 	return ret;
 }
 
+/**
+ * device_get_dma_constraints() - Populate device's DMA constraints
+ *
+ * Gets a device's DMA constraints from firmware. This information is later
+ * used by drivers to translate physcal addresses to the device's bus address
+ * space. For now only device-tree is supported.
+ *
+ * @dev: Pointer to target device
+ * Return: 0 if OK or if no DMA constraints were found, error otherwise
+ */
+static int device_get_dma_constraints(struct udevice *dev)
+{
+	struct udevice *parent = dev->parent;
+	phys_addr_t cpu = 0;
+	dma_addr_t bus = 0;
+	u64 size = 0;
+	int ret;
+
+	if (!CONFIG_IS_ENABLED(DM_DMA) || !parent || !dev_has_ofnode(parent))
+		return 0;
+
+	/*
+	 * We start parsing for dma-ranges from the device's bus node. This is
+	 * specially important on nested buses.
+	 */
+	ret = dev_get_dma_range(parent, &cpu, &bus, &size);
+	/* Don't return an error if no 'dma-ranges' were found */
+	if (ret && ret != -ENOENT) {
+		dm_warn("%s: failed to get DMA range, %d\n", dev->name, ret);
+		return ret;
+	}
+
+	dev_set_dma_offset(dev, cpu - bus);
+
+	return 0;
+}
+
 int device_probe(struct udevice *dev)
 {
 	const struct driver *drv;
@@ -484,6 +521,10 @@ int device_probe(struct udevice *dev)
 			goto fail;
 	}
 
+	ret = device_get_dma_constraints(dev);
+	if (ret)
+		goto fail;
+
 	ret = uclass_pre_probe_device(dev);
 	if (ret)
 		goto fail;
diff --git a/drivers/core/of_addr.c b/drivers/core/of_addr.c
index bbe80136ba..5bc6ca1de0 100644
--- a/drivers/core/of_addr.c
+++ b/drivers/core/of_addr.c
@@ -318,6 +318,84 @@ u64 of_translate_dma_address(const struct device_node *dev, const __be32 *in_add
 	return __of_translate_address(dev, in_addr, "dma-ranges");
 }
 
+int of_get_dma_range(const struct device_node *dev, phys_addr_t *cpu,
+		     dma_addr_t *bus, u64 *size)
+{
+	bool found_dma_ranges = false;
+	struct device_node *parent;
+	struct of_bus *bus_node;
+	int na, ns, pna, pns;
+	const __be32 *ranges;
+	int ret = 0;
+	int len;
+
+	/* Find the closest dma-ranges property */
+	dev = of_node_get(dev);
+	while (dev) {
+		ranges = of_get_property(dev, "dma-ranges", &len);
+
+		/* Ignore empty ranges, they imply no translation required */
+		if (ranges && len > 0)
+			break;
+
+		/* Once we find 'dma-ranges', then a missing one is an error */
+		if (found_dma_ranges && !ranges) {
+			ret = -EINVAL;
+			goto out;
+		}
+
+		if (ranges)
+			found_dma_ranges = true;
+
+		parent = of_get_parent(dev);
+		of_node_put(dev);
+		dev = parent;
+	}
+
+	if (!dev || !ranges) {
+		debug("no dma-ranges found for node %s\n",
+		      of_node_full_name(dev));
+		ret = -ENOENT;
+		goto out;
+	}
+
+	/* switch to that node */
+	parent = of_get_parent(dev);
+	if (!parent) {
+		printf("Found dma-ranges in root node, shoudln't happen\n");
+		ret = -EINVAL;
+		goto out;
+	}
+
+	/* Get the address sizes both for the bus and its parent */
+	bus_node = of_match_bus((struct device_node*)dev);
+	bus_node->count_cells(dev, &na, &ns);
+	if (!OF_CHECK_COUNTS(na, ns)) {
+		printf("Bad cell count for %s\n", of_node_full_name(dev));
+		return -EINVAL;
+		goto out_parent;
+	}
+
+	bus_node = of_match_bus(parent);
+	bus_node->count_cells(parent, &pna, &pns);
+	if (!OF_CHECK_COUNTS(pna, pns)) {
+		printf("Bad cell count for %s\n", of_node_full_name(parent));
+		return -EINVAL;
+		goto out_parent;
+	}
+
+	*bus = of_read_number(ranges, na);
+	*cpu = of_translate_dma_address(dev, ranges + na);
+	*size = of_read_number(ranges + na + pna, ns);
+
+out_parent:
+	of_node_put(parent);
+out:
+	of_node_put(dev);
+	return ret;
+}
+
+
 static int __of_address_to_resource(const struct device_node *dev,
 		const __be32 *addrp, u64 size, unsigned int flags,
 		const char *name, struct resource *r)
diff --git a/drivers/core/ofnode.c b/drivers/core/ofnode.c
index 26c9d04056..fa0bd2a9c4 100644
--- a/drivers/core/ofnode.c
+++ b/drivers/core/ofnode.c
@@ -927,6 +927,15 @@ u64 ofnode_translate_dma_address(ofnode node, const fdt32_t *in_addr)
 		return fdt_translate_dma_address(gd->fdt_blob, ofnode_to_offset(node), in_addr);
 }
 
+int ofnode_get_dma_range(ofnode node, phys_addr_t *cpu, dma_addr_t *bus, u64 *size)
+{
+	if (ofnode_is_np(node))
+		return of_get_dma_range(ofnode_to_np(node), cpu, bus, size);
+	else
+		return fdt_get_dma_range(gd->fdt_blob, ofnode_to_offset(node),
+					 cpu, bus, size);
+}
+
 int ofnode_device_is_compatible(ofnode node, const char *compat)
 {
 	if (ofnode_is_np(node))
diff --git a/drivers/core/read.c b/drivers/core/read.c
index 14fd1214d6..4307ca4579 100644
--- a/drivers/core/read.c
+++ b/drivers/core/read.c
@@ -341,6 +341,12 @@ u64 dev_translate_dma_address(const struct udevice *dev, const fdt32_t *in_addr)
 	return ofnode_translate_dma_address(dev_ofnode(dev), in_addr);
 }
 
+int dev_get_dma_range(const struct udevice *dev, phys_addr_t *cpu,
+		      dma_addr_t *bus, u64 *size)
+{
+	return ofnode_get_dma_range(dev_ofnode(dev), cpu, bus, size);
+}
+
 int dev_read_alias_highest_id(const char *stem)
 {
 	if (of_live_active())
diff --git a/drivers/mmc/sdhci.c b/drivers/mmc/sdhci.c
index ed0dc17325..5f18d472bd 100644
--- a/drivers/mmc/sdhci.c
+++ b/drivers/mmc/sdhci.c
@@ -74,6 +74,7 @@ static void sdhci_transfer_pio(struct sdhci_host *host, struct mmc_data *data)
 static void sdhci_prepare_dma(struct sdhci_host *host, struct mmc_data *data,
 			      int *is_aligned, int trans_bytes)
 {
+	dma_addr_t dma_addr;
 	unsigned char ctrl;
 	void *buf;
 
@@ -104,8 +105,8 @@ static void sdhci_prepare_dma(struct sdhci_host *host, struct mmc_data *data,
 					  mmc_get_dma_dir(data));
 
 	if (host->flags & USE_SDMA) {
-		sdhci_writel(host, phys_to_bus((ulong)host->start_addr),
-				SDHCI_DMA_ADDRESS);
+		dma_addr = dev_phys_to_bus(mmc_to_dev(host->mmc), host->start_addr);
+		sdhci_writel(host, dma_addr, SDHCI_DMA_ADDRESS);
 	}
 #if CONFIG_IS_ENABLED(MMC_SDHCI_ADMA)
 	else if (host->flags & (USE_ADMA | USE_ADMA64)) {
@@ -163,8 +164,9 @@ static int sdhci_transfer_data(struct sdhci_host *host, struct mmc_data *data)
 				start_addr &=
 				~(SDHCI_DEFAULT_BOUNDARY_SIZE - 1);
 				start_addr += SDHCI_DEFAULT_BOUNDARY_SIZE;
-				sdhci_writel(host, phys_to_bus((ulong)start_addr),
-					     SDHCI_DMA_ADDRESS);
+				start_addr = dev_phys_to_bus(mmc_to_dev(host->mmc),
+							     start_addr);
+				sdhci_writel(host, start_addr, SDHCI_DMA_ADDRESS);
 			}
 		}
 		if (timeout-- > 0)
diff --git a/drivers/pci/pcie_brcmstb.c b/drivers/pci/pcie_brcmstb.c
index dd2a4ef629..90225f6779 100644
--- a/drivers/pci/pcie_brcmstb.c
+++ b/drivers/pci/pcie_brcmstb.c
@@ -432,6 +432,7 @@ static int brcm_pcie_probe(struct udevice *dev)
 	struct pci_controller *hose = dev_get_uclass_priv(ctlr);
 	struct brcm_pcie *pcie = dev_get_priv(dev);
 	void __iomem *base = pcie->base;
+	struct pci_region region;
 	bool ssc_good = false;
 	int num_out_wins = 0;
 	u64 rc_bar2_offset, rc_bar2_size;
@@ -468,13 +469,10 @@ static int brcm_pcie_probe(struct udevice *dev)
 			MISC_CTRL_SCB_ACCESS_EN_MASK |
 			MISC_CTRL_CFG_READ_UR_MODE_MASK |
 			MISC_CTRL_MAX_BURST_SIZE_128);
-	/*
-	 * TODO: When support for other SoCs than BCM2711 is added we may
-	 * need to use the base address and size(s) provided in the dma-ranges
-	 * property.
-	 */
-	rc_bar2_offset = 0;
-	rc_bar2_size = 0xc0000000;
+
+	pci_get_dma_regions(dev, &region, 0);
+	rc_bar2_offset = region.bus_start - region.phys_start;
+	rc_bar2_size = 1ULL << fls64(region.size - 1);
 
 	tmp = lower_32_bits(rc_bar2_offset);
 	u32p_replace_bits(&tmp, brcm_pcie_encode_ibar_size(rc_bar2_size),
@@ -579,6 +577,24 @@ static int brcm_pcie_probe(struct udevice *dev)
 	return 0;
 }
 
+static int brcm_pcie_remove(struct udevice *dev)
+{
+	struct brcm_pcie *pcie = dev_get_priv(dev);
+	void __iomem *base = pcie->base;
+
+	/* Assert fundamental reset */
+	setbits_le32(base + PCIE_RGR1_SW_INIT_1, RGR1_SW_INIT_1_PERST_MASK);
+
+	/* Turn off SerDes */
+	setbits_le32(base + PCIE_MISC_HARD_PCIE_HARD_DEBUG,
+		     PCIE_HARD_DEBUG_SERDES_IDDQ_MASK);
+
+	/* Shutdown bridge */
+	setbits_le32(base + PCIE_RGR1_SW_INIT_1, RGR1_SW_INIT_1_INIT_MASK);
+
+	return 0;
+}
+
 static int brcm_pcie_of_to_plat(struct udevice *dev)
 {
 	struct brcm_pcie *pcie = dev_get_priv(dev);
@@ -618,6 +634,8 @@ U_BOOT_DRIVER(pcie_brcm_base) = {
 	.ops			= &brcm_pcie_ops,
 	.of_match		= brcm_pcie_ids,
 	.probe			= brcm_pcie_probe,
+	.remove			= brcm_pcie_remove,
 	.of_to_plat	= brcm_pcie_of_to_plat,
 	.priv_auto	= sizeof(struct brcm_pcie),
+	.flags		= DM_FLAG_OS_PREPARE,
 };
diff --git a/drivers/rng/Kconfig b/drivers/rng/Kconfig
index 11001c8ae7..94915d45b3 100644
--- a/drivers/rng/Kconfig
+++ b/drivers/rng/Kconfig
@@ -46,4 +46,10 @@ config RNG_ROCKCHIP
 	  Enable random number generator for rockchip.This driver is
 	  support rng module of crypto v1 and crypto v2.
 
+config RNG_IPROC200
+	bool "Broadcom iProc RNG200 random number generator"
+	depends on DM_RNG
+	default n
+	help
+	  Enable random number generator for RPI4.
 endif
diff --git a/drivers/rng/Makefile b/drivers/rng/Makefile
index 8953406882..39f7ee3f03 100644
--- a/drivers/rng/Makefile
+++ b/drivers/rng/Makefile
@@ -9,3 +9,4 @@ obj-$(CONFIG_RNG_SANDBOX) += sandbox_rng.o
 obj-$(CONFIG_RNG_MSM) += msm_rng.o
 obj-$(CONFIG_RNG_STM32MP1) += stm32mp1_rng.o
 obj-$(CONFIG_RNG_ROCKCHIP) += rockchip_rng.o
+obj-$(CONFIG_RNG_IPROC200) += iproc_rng200.o
diff --git a/drivers/rng/iproc_rng200.c b/drivers/rng/iproc_rng200.c
new file mode 100644
index 0000000000..f71f285f53
--- /dev/null
+++ b/drivers/rng/iproc_rng200.c
@@ -0,0 +1,185 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright 2020, Matthias Brugger <mbrugger@suse.com>
+ *
+ * Driver for Raspberry Pi hardware random number generator
+ */
+
+#include <common.h>
+#include <dm.h>
+#include <linux/delay.h>
+#include <rng.h>
+#include <asm/io.h>
+
+#define usleep_range(a, b) udelay((b))
+
+#define RNG_CTRL_OFFSET					0x00
+#define RNG_CTRL_RNG_RBGEN_MASK				0x00001FFF
+#define RNG_CTRL_RNG_RBGEN_ENABLE			0x00000001
+#define RNG_CTRL_RNG_RBGEN_DISABLE			0x00000000
+
+#define RNG_SOFT_RESET_OFFSET				0x04
+#define RNG_SOFT_RESET					0x00000001
+
+#define RBG_SOFT_RESET_OFFSET				0x08
+#define RBG_SOFT_RESET					0x00000001
+
+#define RNG_INT_STATUS_OFFSET				0x18
+#define RNG_INT_STATUS_MASTER_FAIL_LOCKOUT_IRQ_MASK	0x80000000
+#define RNG_INT_STATUS_NIST_FAIL_IRQ_MASK		0x00000020
+
+#define RNG_FIFO_DATA_OFFSET				0x20
+
+#define RNG_FIFO_COUNT_OFFSET				0x24
+#define RNG_FIFO_COUNT_RNG_FIFO_COUNT_MASK		0x000000FF
+
+struct iproc_rng200_platdata {
+	fdt_addr_t base;
+};
+
+static void iproc_rng200_enable(struct iproc_rng200_platdata *pdata, bool enable)
+{
+	fdt_addr_t rng_base = pdata->base;
+	u32 val;
+
+	val = readl(rng_base + RNG_CTRL_OFFSET);
+	val &= ~RNG_CTRL_RNG_RBGEN_MASK;
+	if (enable)
+		val |= RNG_CTRL_RNG_RBGEN_ENABLE;
+	else
+		val &= ~RNG_CTRL_RNG_RBGEN_ENABLE;
+
+	writel(val, rng_base + RNG_CTRL_OFFSET);
+}
+
+static void iproc_rng200_restart(struct iproc_rng200_platdata *pdata)
+{
+	fdt_addr_t rng_base = pdata->base;
+	u32 val;
+
+	iproc_rng200_enable(pdata, false);
+
+	/* Clear all interrupt status */
+	writel(0xFFFFFFFFUL, rng_base + RNG_INT_STATUS_OFFSET);
+
+	/* Reset RNG and RBG */
+	val = readl(rng_base + RBG_SOFT_RESET_OFFSET);
+	val |= RBG_SOFT_RESET;
+	writel(val, rng_base + RBG_SOFT_RESET_OFFSET);
+
+	val = readl(rng_base + RNG_SOFT_RESET_OFFSET);
+	val |= RNG_SOFT_RESET;
+	writel(val, rng_base + RNG_SOFT_RESET_OFFSET);
+
+	val = readl(rng_base + RNG_SOFT_RESET_OFFSET);
+	val &= ~RNG_SOFT_RESET;
+	writel(val, rng_base + RNG_SOFT_RESET_OFFSET);
+
+	val = readl(rng_base + RBG_SOFT_RESET_OFFSET);
+	val &= ~RBG_SOFT_RESET;
+	writel(val, rng_base + RBG_SOFT_RESET_OFFSET);
+
+	iproc_rng200_enable(pdata, true);
+}
+
+static int iproc_rng200_read(struct udevice *dev, void *data, size_t len)
+{
+	struct iproc_rng200_platdata *priv = dev_get_plat(dev);
+	char *buf = (char *)data;
+	u32 num_remaining = len;
+	u32 status;
+
+	#define MAX_RESETS_PER_READ	1
+	u32 num_resets = 0;
+
+	while (num_remaining > 0) {
+
+		/* Is RNG sane? If not, reset it. */
+		status = readl(priv->base + RNG_INT_STATUS_OFFSET);
+		if ((status & (RNG_INT_STATUS_MASTER_FAIL_LOCKOUT_IRQ_MASK |
+			RNG_INT_STATUS_NIST_FAIL_IRQ_MASK)) != 0) {
+
+			if (num_resets >= MAX_RESETS_PER_READ)
+				return len - num_remaining;
+
+			iproc_rng200_restart(priv);
+			num_resets++;
+		}
+
+		/* Are there any random numbers available? */
+		if ((readl(priv->base + RNG_FIFO_COUNT_OFFSET) &
+				RNG_FIFO_COUNT_RNG_FIFO_COUNT_MASK) > 0) {
+
+			if (num_remaining >= sizeof(u32)) {
+				/* Buffer has room to store entire word */
+				*(u32 *)buf = readl(priv->base +
+							RNG_FIFO_DATA_OFFSET);
+				buf += sizeof(u32);
+				num_remaining -= sizeof(u32);
+			} else {
+				/* Buffer can only store partial word */
+				u32 rnd_number = readl(priv->base +
+							RNG_FIFO_DATA_OFFSET);
+				memcpy(buf, &rnd_number, num_remaining);
+				buf += num_remaining;
+				num_remaining = 0;
+			}
+
+		} else {
+			/* Can wait, give others chance to run */
+			usleep_range(min(num_remaining * 10, 500U), 500);
+		}
+	}
+
+	return 0;
+}
+
+static int iproc_rng200_probe(struct udevice *dev)
+{
+	struct iproc_rng200_platdata *priv = dev_get_plat(dev);
+
+	iproc_rng200_enable(priv, true);
+
+	return 0;
+}
+
+static int iproc_rng200_remove(struct udevice *dev)
+{
+	struct iproc_rng200_platdata *priv = dev_get_plat(dev);
+
+	iproc_rng200_enable(priv, false);
+
+	return 0;
+}
+
+static int iproc_rng200_ofdata_to_platdata(struct udevice *dev)
+{
+	struct iproc_rng200_platdata *pdata = dev_get_plat(dev);
+
+	pdata->base = dev_read_addr(dev);
+	if (!pdata->base)
+		return -ENODEV;
+
+	return 0;
+}
+
+static const struct dm_rng_ops iproc_rng200_ops = {
+	.read = iproc_rng200_read,
+};
+
+static const struct udevice_id iproc_rng200_rng_match[] = {
+	{ .compatible = "brcm,bcm2711-rng200", },
+	{ .compatible = "brcm,iproc-rng200", },
+	{},
+};
+
+U_BOOT_DRIVER(iproc_rng200_rng) = {
+	.name = "iproc_rng200-rng",
+	.id = UCLASS_RNG,
+	.of_match = iproc_rng200_rng_match,
+	.ops = &iproc_rng200_ops,
+	.probe = iproc_rng200_probe,
+	.remove = iproc_rng200_remove,
+	.plat_auto = sizeof(struct iproc_rng200_platdata),
+	.of_to_plat = iproc_rng200_ofdata_to_platdata,
+};
diff --git a/drivers/usb/host/xhci-mem.c b/drivers/usb/host/xhci-mem.c
index b002d6f166..83147d51b5 100644
--- a/drivers/usb/host/xhci-mem.c
+++ b/drivers/usb/host/xhci-mem.c
@@ -110,7 +110,7 @@ static void xhci_scratchpad_free(struct xhci_ctrl *ctrl)
 
 	ctrl->dcbaa->dev_context_ptrs[0] = 0;
 
-	free((void *)(uintptr_t)le64_to_cpu(ctrl->scratchpad->sp_array[0]));
+	free(xhci_bus_to_virt(ctrl, le64_to_cpu(ctrl->scratchpad->sp_array[0])));
 	free(ctrl->scratchpad->sp_array);
 	free(ctrl->scratchpad);
 	ctrl->scratchpad = NULL;
@@ -216,8 +216,8 @@ static void *xhci_malloc(unsigned int size)
  * @param link_trbs	flag to indicate whether to link the trbs or NOT
  * @return none
  */
-static void xhci_link_segments(struct xhci_segment *prev,
-				struct xhci_segment *next, bool link_trbs)
+static void xhci_link_segments(struct xhci_ctrl *ctrl, struct xhci_segment *prev,
+			       struct xhci_segment *next, bool link_trbs)
 {
 	u32 val;
 	u64 val_64 = 0;
@@ -226,7 +226,7 @@ static void xhci_link_segments(struct xhci_segment *prev,
 		return;
 	prev->next = next;
 	if (link_trbs) {
-		val_64 = virt_to_phys(next->trbs);
+		val_64 = xhci_virt_to_bus(ctrl, next->trbs);
 		prev->trbs[TRBS_PER_SEGMENT-1].link.segment_ptr =
 			cpu_to_le64(val_64);
 
@@ -304,7 +304,8 @@ static struct xhci_segment *xhci_segment_alloc(void)
  * @param link_trbs	flag to indicate whether to link the trbs or NOT
  * @return pointer to the newly created RING
  */
-struct xhci_ring *xhci_ring_alloc(unsigned int num_segs, bool link_trbs)
+struct xhci_ring *xhci_ring_alloc(struct xhci_ctrl *ctrl, unsigned int num_segs,
+				  bool link_trbs)
 {
 	struct xhci_ring *ring;
 	struct xhci_segment *prev;
@@ -327,12 +328,12 @@ struct xhci_ring *xhci_ring_alloc(unsigned int num_segs, bool link_trbs)
 		next = xhci_segment_alloc();
 		BUG_ON(!next);
 
-		xhci_link_segments(prev, next, link_trbs);
+		xhci_link_segments(ctrl, prev, next, link_trbs);
 
 		prev = next;
 		num_segs--;
 	}
-	xhci_link_segments(prev, ring->first_seg, link_trbs);
+	xhci_link_segments(ctrl, prev, ring->first_seg, link_trbs);
 	if (link_trbs) {
 		/* See section 4.9.2.1 and 6.4.4.1 */
 		prev->trbs[TRBS_PER_SEGMENT-1].link.control |=
@@ -354,6 +355,7 @@ static int xhci_scratchpad_alloc(struct xhci_ctrl *ctrl)
 	struct xhci_hccr *hccr = ctrl->hccr;
 	struct xhci_hcor *hcor = ctrl->hcor;
 	struct xhci_scratchpad *scratchpad;
+	uint64_t val_64;
 	int num_sp;
 	uint32_t page_size;
 	void *buf;
@@ -371,8 +373,9 @@ static int xhci_scratchpad_alloc(struct xhci_ctrl *ctrl)
 	scratchpad->sp_array = xhci_malloc(num_sp * sizeof(u64));
 	if (!scratchpad->sp_array)
 		goto fail_sp2;
-	ctrl->dcbaa->dev_context_ptrs[0] =
-		cpu_to_le64((uintptr_t)scratchpad->sp_array);
+
+	val_64 = xhci_virt_to_bus(ctrl, scratchpad->sp_array);
+	ctrl->dcbaa->dev_context_ptrs[0] = cpu_to_le64(val_64);
 
 	xhci_flush_cache((uintptr_t)&ctrl->dcbaa->dev_context_ptrs[0],
 		sizeof(ctrl->dcbaa->dev_context_ptrs[0]));
@@ -393,8 +396,8 @@ static int xhci_scratchpad_alloc(struct xhci_ctrl *ctrl)
 	xhci_flush_cache((uintptr_t)buf, num_sp * page_size);
 
 	for (i = 0; i < num_sp; i++) {
-		uintptr_t ptr = (uintptr_t)buf + i * page_size;
-		scratchpad->sp_array[i] = cpu_to_le64(ptr);
+		val_64 = xhci_virt_to_bus(ctrl, buf + i * page_size);
+		scratchpad->sp_array[i] = cpu_to_le64(val_64);
 	}
 
 	xhci_flush_cache((uintptr_t)scratchpad->sp_array,
@@ -484,9 +487,9 @@ int xhci_alloc_virt_device(struct xhci_ctrl *ctrl, unsigned int slot_id)
 	}
 
 	/* Allocate endpoint 0 ring */
-	virt_dev->eps[0].ring = xhci_ring_alloc(1, true);
+	virt_dev->eps[0].ring = xhci_ring_alloc(ctrl, 1, true);
 
-	byte_64 = virt_to_phys(virt_dev->out_ctx->bytes);
+	byte_64 = xhci_virt_to_bus(ctrl, virt_dev->out_ctx->bytes);
 
 	/* Point to output device context in dcbaa. */
 	ctrl->dcbaa->dev_context_ptrs[slot_id] = cpu_to_le64(byte_64);
@@ -522,15 +525,15 @@ int xhci_mem_init(struct xhci_ctrl *ctrl, struct xhci_hccr *hccr,
 		return -ENOMEM;
 	}
 
-	val_64 = virt_to_phys(ctrl->dcbaa);
+	val_64 = xhci_virt_to_bus(ctrl, ctrl->dcbaa);
 	/* Set the pointer in DCBAA register */
 	xhci_writeq(&hcor->or_dcbaap, val_64);
 
 	/* Command ring control pointer register initialization */
-	ctrl->cmd_ring = xhci_ring_alloc(1, true);
+	ctrl->cmd_ring = xhci_ring_alloc(ctrl, 1, true);
 
 	/* Set the address in the Command Ring Control register */
-	trb_64 = virt_to_phys(ctrl->cmd_ring->first_seg->trbs);
+	trb_64 = xhci_virt_to_bus(ctrl, ctrl->cmd_ring->first_seg->trbs);
 	val_64 = xhci_readq(&hcor->or_crcr);
 	val_64 = (val_64 & (u64) CMD_RING_RSVD_BITS) |
 		(trb_64 & (u64) ~CMD_RING_RSVD_BITS) |
@@ -551,7 +554,7 @@ int xhci_mem_init(struct xhci_ctrl *ctrl, struct xhci_hccr *hccr,
 	ctrl->ir_set = &ctrl->run_regs->ir_set[0];
 
 	/* Event ring does not maintain link TRB */
-	ctrl->event_ring = xhci_ring_alloc(ERST_NUM_SEGS, false);
+	ctrl->event_ring = xhci_ring_alloc(ctrl, ERST_NUM_SEGS, false);
 	ctrl->erst.entries = xhci_malloc(sizeof(struct xhci_erst_entry) *
 					 ERST_NUM_SEGS);
 
@@ -560,8 +563,8 @@ int xhci_mem_init(struct xhci_ctrl *ctrl, struct xhci_hccr *hccr,
 	for (val = 0, seg = ctrl->event_ring->first_seg;
 			val < ERST_NUM_SEGS;
 			val++) {
-		trb_64 = virt_to_phys(seg->trbs);
 		struct xhci_erst_entry *entry = &ctrl->erst.entries[val];
+		trb_64 = xhci_virt_to_bus(ctrl, seg->trbs);
 		entry->seg_addr = cpu_to_le64(trb_64);
 		entry->seg_size = cpu_to_le32(TRBS_PER_SEGMENT);
 		entry->rsvd = 0;
@@ -570,7 +573,7 @@ int xhci_mem_init(struct xhci_ctrl *ctrl, struct xhci_hccr *hccr,
 	xhci_flush_cache((uintptr_t)ctrl->erst.entries,
 			 ERST_NUM_SEGS * sizeof(struct xhci_erst_entry));
 
-	deq = virt_to_phys(ctrl->event_ring->dequeue);
+	deq = xhci_virt_to_bus(ctrl, ctrl->event_ring->dequeue);
 
 	/* Update HC event ring dequeue pointer */
 	xhci_writeq(&ctrl->ir_set->erst_dequeue,
@@ -585,7 +588,7 @@ int xhci_mem_init(struct xhci_ctrl *ctrl, struct xhci_hccr *hccr,
 	/* this is the event ring segment table pointer */
 	val_64 = xhci_readq(&ctrl->ir_set->erst_base);
 	val_64 &= ERST_PTR_MASK;
-	val_64 |= virt_to_phys(ctrl->erst.entries) & ~ERST_PTR_MASK;
+	val_64 |= xhci_virt_to_bus(ctrl, ctrl->erst.entries) & ~ERST_PTR_MASK;
 
 	xhci_writeq(&ctrl->ir_set->erst_base, val_64);
 
@@ -848,7 +851,7 @@ void xhci_setup_addressable_virt_dev(struct xhci_ctrl *ctrl,
 	/* EP 0 can handle "burst" sizes of 1, so Max Burst Size field is 0 */
 	ep0_ctx->ep_info2 |= cpu_to_le32(MAX_BURST(0) | ERROR_COUNT(3));
 
-	trb_64 = virt_to_phys(virt_dev->eps[0].ring->first_seg->trbs);
+	trb_64 = xhci_virt_to_bus(ctrl, virt_dev->eps[0].ring->first_seg->trbs);
 	ep0_ctx->deq = cpu_to_le64(trb_64 | virt_dev->eps[0].ring->cycle_state);
 
 	/*
diff --git a/drivers/usb/host/xhci-pci.c b/drivers/usb/host/xhci-pci.c
index 6c5024d3f1..aaa243f291 100644
--- a/drivers/usb/host/xhci-pci.c
+++ b/drivers/usb/host/xhci-pci.c
@@ -70,7 +70,7 @@ U_BOOT_DRIVER(xhci_pci) = {
 	.ops	= &xhci_usb_ops,
 	.plat_auto	= sizeof(struct usb_plat),
 	.priv_auto	= sizeof(struct xhci_ctrl),
-	.flags	= DM_FLAG_ALLOC_PRIV_DMA,
+	.flags	= DM_FLAG_OS_PREPARE | DM_FLAG_ALLOC_PRIV_DMA,
 };
 
 static struct pci_device_id xhci_pci_supported[] = {
diff --git a/drivers/usb/host/xhci-ring.c b/drivers/usb/host/xhci-ring.c
index d6c47d579b..46c137f857 100644
--- a/drivers/usb/host/xhci-ring.c
+++ b/drivers/usb/host/xhci-ring.c
@@ -275,10 +275,13 @@ void xhci_queue_command(struct xhci_ctrl *ctrl, u8 *ptr, u32 slot_id,
 			u32 ep_index, trb_type cmd)
 {
 	u32 fields[4];
-	u64 val_64 = virt_to_phys(ptr);
+	u64 val_64 = 0;
 
 	BUG_ON(prepare_ring(ctrl, ctrl->cmd_ring, EP_STATE_RUNNING));
 
+	if (ptr)
+		val_64 = xhci_virt_to_bus(ctrl, ptr);
+
 	fields[0] = lower_32_bits(val_64);
 	fields[1] = upper_32_bits(val_64);
 	fields[2] = 0;
@@ -401,7 +404,7 @@ void xhci_acknowledge_event(struct xhci_ctrl *ctrl)
 
 	/* Inform the hardware */
 	xhci_writeq(&ctrl->ir_set->erst_dequeue,
-		    virt_to_phys(ctrl->event_ring->dequeue) | ERST_EHB);
+		    xhci_virt_to_bus(ctrl, ctrl->event_ring->dequeue) | ERST_EHB);
 }
 
 /**
@@ -579,7 +582,7 @@ int xhci_bulk_tx(struct usb_device *udev, unsigned long pipe,
 	u64 addr;
 	int ret;
 	u32 trb_fields[4];
-	u64 val_64 = virt_to_phys(buffer);
+	u64 val_64 = xhci_virt_to_bus(ctrl, buffer);
 	void *last_transfer_trb_addr;
 	int available_length;
 
@@ -724,7 +727,7 @@ again:
 	}
 
 	if ((uintptr_t)(le64_to_cpu(event->trans_event.buffer)) !=
-	    (uintptr_t)virt_to_phys(last_transfer_trb_addr)) {
+	    (uintptr_t)xhci_virt_to_bus(ctrl, last_transfer_trb_addr)) {
 		available_length -=
 			(int)EVENT_TRB_LEN(le32_to_cpu(event->trans_event.transfer_len));
 		xhci_acknowledge_event(ctrl);
@@ -884,7 +887,7 @@ int xhci_ctrl_tx(struct usb_device *udev, unsigned long pipe,
 	if (length > 0) {
 		if (req->requesttype & USB_DIR_IN)
 			field |= TRB_DIR_IN;
-		buf_64 = virt_to_phys(buffer);
+		buf_64 = xhci_virt_to_bus(ctrl, buffer);
 
 		trb_fields[0] = lower_32_bits(buf_64);
 		trb_fields[1] = upper_32_bits(buf_64);
diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c
index 7080f8fabe..d27ac01c83 100644
--- a/drivers/usb/host/xhci.c
+++ b/drivers/usb/host/xhci.c
@@ -604,7 +604,7 @@ static int xhci_set_configuration(struct usb_device *udev)
 		ep_ctx[ep_index] = xhci_get_ep_ctx(ctrl, in_ctx, ep_index);
 
 		/* Allocate the ep rings */
-		virt_dev->eps[ep_index].ring = xhci_ring_alloc(1, true);
+		virt_dev->eps[ep_index].ring = xhci_ring_alloc(ctrl, 1, true);
 		if (!virt_dev->eps[ep_index].ring)
 			return -ENOMEM;
 
@@ -628,7 +628,7 @@ static int xhci_set_configuration(struct usb_device *udev)
 			cpu_to_le32(MAX_BURST(max_burst) |
 			ERROR_COUNT(err_count));
 
-		trb_64 = virt_to_phys(virt_dev->eps[ep_index].ring->enqueue);
+		trb_64 = xhci_virt_to_bus(ctrl, virt_dev->eps[ep_index].ring->enqueue);
 		ep_ctx[ep_index]->deq = cpu_to_le64(trb_64 |
 				virt_dev->eps[ep_index].ring->cycle_state);
 
diff --git a/drivers/video/bcm2835.c b/drivers/video/bcm2835.c
index 9326999cd3..c2962932c9 100644
--- a/drivers/video/bcm2835.c
+++ b/drivers/video/bcm2835.c
@@ -52,6 +52,7 @@ static int bcm2835_video_probe(struct udevice *dev)
 
 static const struct udevice_id bcm2835_video_ids[] = {
 	{ .compatible = "brcm,bcm2835-hdmi" },
+	{ .compatible = "brcm,bcm2711-hdmi0" },
 	{ .compatible = "brcm,bcm2708-fb" },
 	{ }
 };