[RFC PATCH 8/9] pci: Add driver for Broadcom STB PCIe controller

[Sylwester Nawrocki <s.nawrocki@samsung.com>]

This patch adds basic driver for the Broadcom STB PCIe host controller.
The code is based on Linux upstream driver (pcie-brcmtsb.c) with MSI
handling removed. The inbound access memory region is not currently
parsed from dma-ranges DT property and is fixed as a 1:1 mapping of
whole RAM.
The patch has been tested on rpi4 board, i.e. on BCM2711 SoC with VL805
USB Host Controller.

Signed-off-by: Sylwester Nawrocki <s.nawrocki@samsung.com>
---
 drivers/pci/Kconfig        |   5 +
 drivers/pci/Makefile       |   1 +
 drivers/pci/pcie_brcmstb.c | 844 +++++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 850 insertions(+)
 create mode 100644 drivers/pci/pcie_brcmstb.c

diff --git a/drivers/pci/Kconfig b/drivers/pci/Kconfig
index 437cd9a..02dcc57 100644
--- a/drivers/pci/Kconfig
+++ b/drivers/pci/Kconfig
@@ -197,4 +197,9 @@ config PCIE_MEDIATEK
 	  Say Y here if you want to enable Gen2 PCIe controller,
 	  which could be found on MT7623 SoC family.
 
+config PCI_BRCMSTB
+	bool "Broadcom STB PCIe controller"
+	depends on DM_PCI
+	help
+	  Say Y here if you want to enable PCI controller support on BCM2711 SoC.
 endif
diff --git a/drivers/pci/Makefile b/drivers/pci/Makefile
index c051ecc..3e53b1f 100644
--- a/drivers/pci/Makefile
+++ b/drivers/pci/Makefile
@@ -43,3 +43,4 @@ obj-$(CONFIG_PCI_PHYTIUM) += pcie_phytium.o
 obj-$(CONFIG_PCIE_INTEL_FPGA) += pcie_intel_fpga.o
 obj-$(CONFIG_PCI_KEYSTONE) += pcie_dw_ti.o
 obj-$(CONFIG_PCIE_MEDIATEK) += pcie_mediatek.o
+obj-$(CONFIG_PCI_BRCMSTB) += pcie_brcmstb.o
diff --git a/drivers/pci/pcie_brcmstb.c b/drivers/pci/pcie_brcmstb.c
new file mode 100644
index 0000000..e96e163
--- /dev/null
+++ b/drivers/pci/pcie_brcmstb.c
@@ -0,0 +1,844 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Broadcom STB PCIe controller driver
+ *
+ * Copyright (C) 2020 Samsung Electronics Co., Ltd.
+ * Author: Sylwester Nawrocki <s.nawrocki@samsung.com>
+ *
+ * Based on upstream Linux kernel driver:
+ *
+ *  drivers/pci/controller/pcie-brcmstb.c
+ *  Copyright (C) 2009 - 2017 Broadcom
+ */
+
+#include <asm/io.h>
+#include <common.h>
+#include <dm.h>
+#include <dm/device-internal.h>
+#include <dm/lists.h>
+#include <dm/of_access.h>
+#include <dm/of.h>
+#include <linux/errno.h>
+#include <linux/ioport.h>
+#include <linux/log2.h>
+#include <linux/mbus.h>
+#include <pci.h>
+
+DECLARE_GLOBAL_DATA_PTR;
+
+/* BRCM_PCIE_CAP_REGS - Offset for the mandatory capability config regs */
+#define BRCM_PCIE_CAP_REGS				0x00ac
+
+/*
+ * Broadcom Settop Box PCIe Register Offsets. The names are from
+ * the chip's RDB and we use them here so that a script can correlate
+ * this code and the RDB to prevent discrepancies.
+ */
+#define PCIE_RC_CFG_VENDOR_VENDOR_SPECIFIC_REG1		0x0188
+#define PCIE_RC_CFG_PRIV1_ID_VAL3			0x043c
+#define PCIE_RC_DL_MDIO_ADDR				0x1100
+#define PCIE_RC_DL_MDIO_WR_DATA				0x1104
+#define PCIE_RC_DL_MDIO_RD_DATA				0x1108
+#define PCIE_MISC_MISC_CTRL				0x4008
+#define PCIE_MISC_CPU_2_PCIE_MEM_WIN0_LO		0x400c
+#define PCIE_MISC_CPU_2_PCIE_MEM_WIN0_HI		0x4010
+#define PCIE_MISC_RC_BAR1_CONFIG_LO			0x402c
+#define PCIE_MISC_RC_BAR2_CONFIG_LO			0x4034
+#define PCIE_MISC_RC_BAR2_CONFIG_HI			0x4038
+#define PCIE_MISC_RC_BAR3_CONFIG_LO			0x403c
+#define PCIE_MISC_MSI_BAR_CONFIG_LO			0x4044
+#define PCIE_MISC_MSI_BAR_CONFIG_HI			0x4048
+#define PCIE_MISC_MSI_DATA_CONFIG			0x404c
+#define PCIE_MISC_EOI_CTRL				0x4060
+#define PCIE_MISC_PCIE_CTRL				0x4064
+#define PCIE_MISC_PCIE_STATUS				0x4068
+#define PCIE_MISC_REVISION				0x406c
+#define PCIE_MISC_CPU_2_PCIE_MEM_WIN0_BASE_LIMIT	0x4070
+#define PCIE_MISC_CPU_2_PCIE_MEM_WIN0_BASE_HI		0x4080
+#define PCIE_MISC_CPU_2_PCIE_MEM_WIN0_LIMIT_HI		0x4084
+#define PCIE_MISC_HARD_PCIE_HARD_DEBUG			0x4204
+#define PCIE_INTR2_CPU_BASE				0x4300
+#define PCIE_MSI_INTR2_BASE				0x4500
+
+/*
+ * Broadcom Settop Box PCIe Register Field shift and mask info. The
+ * names are from the chip's RDB and we use them here so that a script
+ * can correlate this code and the RDB to prevent discrepancies.
+ */
+#define PCIE_RC_CFG_VENDOR_VENDOR_SPECIFIC_REG1_ENDIAN_MODE_BAR2_MASK	0xc
+#define PCIE_RC_CFG_VENDOR_VENDOR_SPECIFIC_REG1_ENDIAN_MODE_BAR2_SHIFT	0x2
+#define PCIE_RC_CFG_PRIV1_ID_VAL3_CLASS_CODE_MASK		0xffffff
+#define PCIE_RC_CFG_PRIV1_ID_VAL3_CLASS_CODE_SHIFT		0x0
+#define PCIE_MISC_MISC_CTRL_SCB_ACCESS_EN_MASK			0x1000
+#define PCIE_MISC_MISC_CTRL_SCB_ACCESS_EN_SHIFT			0xc
+#define PCIE_MISC_MISC_CTRL_CFG_READ_UR_MODE_MASK		0x2000
+#define PCIE_MISC_MISC_CTRL_CFG_READ_UR_MODE_SHIFT		0xd
+#define PCIE_MISC_MISC_CTRL_MAX_BURST_SIZE_MASK			0x300000
+#define PCIE_MISC_MISC_CTRL_MAX_BURST_SIZE_SHIFT		0x14
+#define PCIE_MISC_MISC_CTRL_SCB0_SIZE_MASK			0xf8000000
+#define PCIE_MISC_MISC_CTRL_SCB0_SIZE_SHIFT			0x1b
+#define PCIE_MISC_MISC_CTRL_SCB1_SIZE_MASK			0x7c00000
+#define PCIE_MISC_MISC_CTRL_SCB1_SIZE_SHIFT			0x16
+#define PCIE_MISC_MISC_CTRL_SCB2_SIZE_MASK			0x1f
+#define PCIE_MISC_MISC_CTRL_SCB2_SIZE_SHIFT			0x0
+#define PCIE_MISC_RC_BAR1_CONFIG_LO_SIZE_MASK			0x1f
+#define PCIE_MISC_RC_BAR1_CONFIG_LO_SIZE_SHIFT			0x0
+#define PCIE_MISC_RC_BAR2_CONFIG_LO_SIZE_MASK			0x1f
+#define PCIE_MISC_RC_BAR2_CONFIG_LO_SIZE_SHIFT			0x0
+#define PCIE_MISC_RC_BAR3_CONFIG_LO_SIZE_MASK			0x1f
+#define PCIE_MISC_RC_BAR3_CONFIG_LO_SIZE_SHIFT			0x0
+#define PCIE_MISC_PCIE_CTRL_PCIE_PERSTB_MASK			0x4
+#define PCIE_MISC_PCIE_CTRL_PCIE_PERSTB_SHIFT			0x2
+#define PCIE_MISC_PCIE_CTRL_PCIE_L23_REQUEST_MASK		0x1
+#define PCIE_MISC_PCIE_CTRL_PCIE_L23_REQUEST_SHIFT		0x0
+#define PCIE_MISC_PCIE_STATUS_PCIE_PORT_MASK			0x80
+#define PCIE_MISC_PCIE_STATUS_PCIE_PORT_SHIFT			0x7
+#define PCIE_MISC_PCIE_STATUS_PCIE_DL_ACTIVE_MASK		0x20
+#define PCIE_MISC_PCIE_STATUS_PCIE_DL_ACTIVE_SHIFT		0x5
+#define PCIE_MISC_PCIE_STATUS_PCIE_PHYLINKUP_MASK		0x10
+#define PCIE_MISC_PCIE_STATUS_PCIE_PHYLINKUP_SHIFT		0x4
+#define PCIE_MISC_PCIE_STATUS_PCIE_LINK_IN_L23_MASK		0x40
+#define PCIE_MISC_PCIE_STATUS_PCIE_LINK_IN_L23_SHIFT		0x6
+#define PCIE_MISC_REVISION_MAJMIN_MASK				0xffff
+#define PCIE_MISC_REVISION_MAJMIN_SHIFT				0
+#define PCIE_MISC_CPU_2_PCIE_MEM_WIN0_BASE_LIMIT_LIMIT_MASK	0xfff00000
+#define PCIE_MISC_CPU_2_PCIE_MEM_WIN0_BASE_LIMIT_LIMIT_SHIFT	0x14
+#define PCIE_MISC_CPU_2_PCIE_MEM_WIN0_BASE_LIMIT_BASE_MASK	0xfff0
+#define PCIE_MISC_CPU_2_PCIE_MEM_WIN0_BASE_LIMIT_BASE_SHIFT	0x4
+#define PCIE_MISC_CPU_2_PCIE_MEM_WIN0_BASE_LIMIT_NUM_MASK_BITS	0xc
+#define PCIE_MISC_CPU_2_PCIE_MEM_WIN0_BASE_HI_BASE_MASK		0xff
+#define PCIE_MISC_CPU_2_PCIE_MEM_WIN0_BASE_HI_BASE_SHIFT	0x0
+#define PCIE_MISC_CPU_2_PCIE_MEM_WIN0_LIMIT_HI_LIMIT_MASK	0xff
+#define PCIE_MISC_CPU_2_PCIE_MEM_WIN0_LIMIT_HI_LIMIT_SHIFT	0x0
+#define PCIE_MISC_HARD_PCIE_HARD_DEBUG_CLKREQ_DEBUG_ENABLE_MASK	0x2
+#define PCIE_MISC_HARD_PCIE_HARD_DEBUG_CLKREQ_DEBUG_ENABLE_SHIFT 0x1
+#define PCIE_MISC_HARD_PCIE_HARD_DEBUG_SERDES_IDDQ_MASK		0x08000000
+#define PCIE_MISC_HARD_PCIE_HARD_DEBUG_SERDES_IDDQ_SHIFT	0x1b
+#define PCIE_RGR1_SW_INIT_1_PERST_MASK				0x1
+#define PCIE_RGR1_SW_INIT_1_PERST_SHIFT				0x0
+
+/* Offsets from PCIE_INTR2_CPU_BASE */
+#define STATUS				0x0
+#define SET				0x4
+#define CLR				0x8
+#define MASK_STATUS			0xc
+#define MASK_SET			0x10
+#define MASK_CLR			0x14
+
+#define BRCM_NUM_PCIE_OUT_WINS		0x4
+#define BRCM_MAX_SCB			0x4
+
+#define BURST_SIZE_128			0
+
+#define PCIE_BUSNUM_SHIFT		20
+#define PCIE_SLOT_SHIFT			15
+#define PCIE_FUNC_SHIFT			12
+
+#if defined(__BIG_ENDIAN)
+#define	DATA_ENDIAN			2	/* PCIe->DDR inbound traffic */
+#define MMIO_ENDIAN			2	/* CPU->PCIe outbound traffic */
+#else
+#define	DATA_ENDIAN			0
+#define MMIO_ENDIAN			0
+#endif
+
+#define MDIO_PORT0			0x0
+#define MDIO_DATA_MASK			0x7fffffff
+#define MDIO_DATA_SHIFT			0x0
+#define MDIO_PORT_MASK			0xf0000
+#define MDIO_PORT_SHIFT			0x16
+#define MDIO_REGAD_MASK			0xffff
+#define MDIO_REGAD_SHIFT		0x0
+#define MDIO_CMD_MASK			0xfff00000
+#define MDIO_CMD_SHIFT			0x14
+#define MDIO_CMD_READ			0x1
+#define MDIO_CMD_WRITE			0x0
+#define MDIO_DATA_DONE_MASK		0x80000000
+#define MDIO_RD_DONE(x)			(((x) & MDIO_DATA_DONE_MASK) ? 1 : 0)
+#define MDIO_WT_DONE(x)			(((x) & MDIO_DATA_DONE_MASK) ? 0 : 1)
+#define SSC_REGS_ADDR			0x1100
+#define SET_ADDR_OFFSET			0x1f
+#define SSC_CNTL_OFFSET			0x2
+#define SSC_CNTL_OVRD_EN_MASK		0x8000
+#define SSC_CNTL_OVRD_EN_SHIFT		0xf
+#define SSC_CNTL_OVRD_VAL_MASK		0x4000
+#define SSC_CNTL_OVRD_VAL_SHIFT		0xe
+#define SSC_STATUS_OFFSET		0x1
+#define SSC_STATUS_SSC_MASK		0x400
+#define SSC_STATUS_SSC_SHIFT		0xa
+#define SSC_STATUS_PLL_LOCK_MASK	0x800
+#define SSC_STATUS_PLL_LOCK_SHIFT	0xb
+
+#define IDX_ADDR(pcie)	((pcie)->reg_offsets[EXT_CFG_INDEX])
+#define DATA_ADDR(pcie)	((pcie)->reg_offsets[EXT_CFG_DATA])
+#define PCIE_RGR1_SW_INIT_1(pcie) ((pcie)->reg_offsets[RGR1_SW_INIT_1])
+
+enum {
+	RGR1_SW_INIT_1,
+	EXT_CFG_INDEX,
+	EXT_CFG_DATA,
+};
+
+enum {
+	RGR1_SW_INIT_1_INIT_MASK,
+	RGR1_SW_INIT_1_INIT_SHIFT,
+	RGR1_SW_INIT_1_PERST_MASK,
+	RGR1_SW_INIT_1_PERST_SHIFT,
+};
+
+enum pcie_type {
+	BCM7425,
+	BCM7435,
+	GENERIC,
+	BCM7278,
+	BCM2711,
+};
+
+struct brcm_window {
+	dma_addr_t pci_addr;
+	phys_addr_t phys_addr;
+	dma_addr_t size;
+};
+
+struct brcm_pcie {
+	struct resource		mem;
+	bool			ssc;
+
+	struct device_node	*dn;
+	void __iomem		*base;
+
+	int			num_out_wins;
+	struct brcm_window	out_wins[BRCM_NUM_PCIE_OUT_WINS];
+
+	int			gen;
+	unsigned int		rev;
+
+	const int		*reg_offsets;
+	const int		*reg_field_info;
+	u32			max_burst_size;
+	enum pcie_type		type;
+};
+
+struct pcie_cfg_data {
+	const int		*reg_field_info;
+	const int		*offsets;
+	const u32		max_burst_size;
+	const enum pcie_type	type;
+};
+
+static struct brcm_window dma_ranges[1];
+static int num_dma_ranges;
+
+static const int pcie_reg_field_info[] = {
+	[RGR1_SW_INIT_1_INIT_MASK] = 0x2,
+	[RGR1_SW_INIT_1_INIT_SHIFT] = 0x1,
+};
+
+static const int pcie_offsets[] = {
+	[RGR1_SW_INIT_1] = 0x9210,
+	[EXT_CFG_INDEX]  = 0x9000,
+	[EXT_CFG_DATA]   = 0x8000,
+};
+
+static const struct pcie_cfg_data generic_cfg = {
+	.reg_field_info	= pcie_reg_field_info,
+	.offsets	= pcie_offsets,
+	.max_burst_size	= BURST_SIZE_128,
+	.type		= GENERIC,
+};
+
+static const struct pcie_cfg_data bcm2711_cfg = {
+	.reg_field_info	= pcie_reg_field_info,
+	.offsets	= pcie_offsets,
+	.max_burst_size	= BURST_SIZE_128,
+	.type		= BCM2711,
+};
+
+/* These macros extract/insert fields to host controller's register set */
+#define WR_FLD(base, reg, field, val) \
+	wr_fld(base + reg, reg##_##field##_MASK, reg##_##field##_SHIFT, val)
+#define WR_FLD_RB(base, reg, field, val) \
+	wr_fld_rb(base + reg, reg##_##field##_MASK, reg##_##field##_SHIFT, val)
+#define WR_FLD_WITH_OFFSET(base, off, reg, field, val) \
+	wr_fld(base + reg + off, reg##_##field##_MASK, \
+	       reg##_##field##_SHIFT, val)
+#define EXTRACT_FIELD(val, reg, field) \
+	((val & reg##_##field##_MASK) >> reg##_##field##_SHIFT)
+#define INSERT_FIELD(val, reg, field, field_val) \
+	((val & ~reg##_##field##_MASK) | \
+	 (reg##_##field##_MASK & (field_val << reg##_##field##_SHIFT)))
+
+#define msleep(a) udelay((a) * 1000)
+
+/*
+ * The roundup_pow_of_two() from log2.h invokes
+ * __roundup_pow_of_two(unsigned long), but we really need
+ * such a function to take a native u64 since unsigned long
+ * is 32 bits on some configurations.  So we provide this helper
+ * function below.
+ */
+static u64 roundup_pow_of_two_64(u64 n)
+{
+	return 1ULL << fls64(n - 1);
+}
+
+/*
+ * This is to convert the size of the inbound "BAR" region to the
+ * non-linear values of PCIE_X_MISC_RC_BAR[123]_CONFIG_LO.SIZE
+ */
+int encode_ibar_size(u64 size)
+{
+	int log2_in = ilog2(size);
+
+	if (log2_in >= 12 && log2_in <= 15)
+		/* Covers 4KB to 32KB (inclusive) */
+		return (log2_in - 12) + 0x1c;
+	else if (log2_in >= 16 && log2_in <= 37)
+		/* Covers 64KB to 32GB, (inclusive) */
+		return log2_in - 15;
+	/* Something is awry so disable */
+	return 0;
+}
+
+/* Configuration space read/write support */
+static int cfg_index(int busnr, int devfn, int reg)
+{
+	return (PCI_DEV(devfn) << PCIE_SLOT_SHIFT)
+		| (PCI_FUNC(devfn) << PCIE_FUNC_SHIFT)
+		| (busnr << PCIE_BUSNUM_SHIFT)
+		| (reg & ~3);
+}
+
+/* The controller is capable of serving in both RC and EP roles */
+static bool brcm_pcie_rc_mode(struct brcm_pcie *pcie)
+{
+	void __iomem *base = pcie->base;
+	u32 val = readl(base + PCIE_MISC_PCIE_STATUS);
+
+	return !!EXTRACT_FIELD(val, PCIE_MISC_PCIE_STATUS, PCIE_PORT);
+}
+
+static bool brcm_pcie_link_up(struct brcm_pcie *pcie)
+{
+	void __iomem *base = pcie->base;
+	u32 val = readl(base + PCIE_MISC_PCIE_STATUS);
+	u32 dla = EXTRACT_FIELD(val, PCIE_MISC_PCIE_STATUS, PCIE_DL_ACTIVE);
+	u32 plu = EXTRACT_FIELD(val, PCIE_MISC_PCIE_STATUS, PCIE_PHYLINKUP);
+
+	return  (dla && plu) ? true : false;
+}
+
+static int brcm_pcie_config_address(const struct udevice *udev, pci_dev_t bdf,
+				    uint offset, void **paddress)
+{
+	struct brcm_pcie *pcie = dev_get_priv(udev);
+	unsigned int bus = PCI_BUS(bdf);
+	unsigned int dev = PCI_DEV(bdf);
+	int idx;
+
+	if (bus > 0 && !brcm_pcie_link_up(pcie))
+		return -ENODEV;
+
+	/*
+	 * Busses 0 (host PCIe bridge) and 1 (its immediate child)
+	 * are limited to a single device each
+	 */
+	if ((bus == (udev->seq + 1)) && dev > 0)
+		return -ENODEV;
+
+	/* Accesses to the RC go right to the RC registers if PCI device == 0 */
+	if (bus == udev->seq) {
+		if (PCI_DEV(bdf))
+			return -ENODEV;
+
+		*paddress = pcie->base + offset;
+		return 0;
+	}
+
+	/* For devices, write to the config space index register */
+	idx = cfg_index(bus, bdf, 0);
+
+	writel(idx, pcie->base + IDX_ADDR(pcie));
+	*paddress = pcie->base + DATA_ADDR(pcie) + offset;
+
+	return 0;
+}
+
+static int brcm_pcie_read_config(const struct udevice *bus, pci_dev_t bdf,
+				 uint offset, ulong *valuep,
+				 enum pci_size_t size)
+{
+	return pci_generic_mmap_read_config(bus, brcm_pcie_config_address,
+					    bdf, offset, valuep, size);
+}
+
+static int brcm_pcie_write_config(struct udevice *bus, pci_dev_t bdf,
+				  uint offset, ulong value,
+				  enum pci_size_t size)
+{
+	return pci_generic_mmap_write_config(bus, brcm_pcie_config_address,
+					     bdf, offset, value, size);
+}
+
+static void wr_fld(void __iomem *p, u32 mask, int shift, u32 val)
+{
+	u32 reg = readl(p);
+
+	reg = (reg & ~mask) | ((val << shift) & mask);
+	writel(reg, p);
+}
+
+static void wr_fld_rb(void __iomem *p, u32 mask, int shift, u32 val)
+{
+	wr_fld(p, mask, shift, val);
+	(void)readl(p);
+}
+
+static const char *link_speed_to_str(int s)
+{
+	switch (s) {
+	case 1:
+		return "2.5";
+	case 2:
+		return "5.0";
+	case 3:
+		return "8.0";
+	default:
+		break;
+	}
+	return "???";
+}
+
+static inline void brcm_pcie_bridge_sw_init_set(struct brcm_pcie *pcie,
+						unsigned int val)
+{
+	unsigned int shift = pcie->reg_field_info[RGR1_SW_INIT_1_INIT_SHIFT];
+	u32 mask =  pcie->reg_field_info[RGR1_SW_INIT_1_INIT_MASK];
+
+	wr_fld_rb(pcie->base + PCIE_RGR1_SW_INIT_1(pcie), mask, shift, val);
+}
+
+static inline void brcm_pcie_perst_set(struct brcm_pcie *pcie,
+				       unsigned int val)
+{
+	if (pcie->type != BCM7278)
+		wr_fld_rb(pcie->base + PCIE_RGR1_SW_INIT_1(pcie),
+			  PCIE_RGR1_SW_INIT_1_PERST_MASK,
+			  PCIE_RGR1_SW_INIT_1_PERST_SHIFT, val);
+	else
+		/* Assert = 0, de-assert = 1 on 7278 */
+		WR_FLD_RB(pcie->base, PCIE_MISC_PCIE_CTRL, PCIE_PERSTB, !val);
+}
+
+static u32 mdio_form_pkt(int port, int regad, int cmd)
+{
+	u32 pkt = 0;
+
+	pkt |= (port << MDIO_PORT_SHIFT) & MDIO_PORT_MASK;
+	pkt |= (regad << MDIO_REGAD_SHIFT) & MDIO_REGAD_MASK;
+	pkt |= (cmd << MDIO_CMD_SHIFT) & MDIO_CMD_MASK;
+
+	return pkt;
+}
+
+/* Negative return value indicates error */
+static int mdio_read(void __iomem *base, u8 port, u8 regad)
+{
+	int tries;
+	u32 data;
+
+	writel(mdio_form_pkt(port, regad, MDIO_CMD_READ),
+	       base + PCIE_RC_DL_MDIO_ADDR);
+	readl(base + PCIE_RC_DL_MDIO_ADDR);
+
+	data = readl(base + PCIE_RC_DL_MDIO_RD_DATA);
+	for (tries = 0; !MDIO_RD_DONE(data) && tries < 10; tries++) {
+		udelay(10);
+		data = readl(base + PCIE_RC_DL_MDIO_RD_DATA);
+	}
+
+	return MDIO_RD_DONE(data)
+		? (data & MDIO_DATA_MASK) >> MDIO_DATA_SHIFT
+		: -EIO;
+}
+
+/* Negative return value indicates error */
+static int mdio_write(void __iomem *base, u8 port, u8 regad, u16 wrdata)
+{
+	int tries;
+	u32 data;
+
+	writel(mdio_form_pkt(port, regad, MDIO_CMD_WRITE),
+	       base + PCIE_RC_DL_MDIO_ADDR);
+	readl(base + PCIE_RC_DL_MDIO_ADDR);
+	writel(MDIO_DATA_DONE_MASK | wrdata,
+	       base + PCIE_RC_DL_MDIO_WR_DATA);
+
+	data = readl(base + PCIE_RC_DL_MDIO_WR_DATA);
+	for (tries = 0; !MDIO_WT_DONE(data) && tries < 10; tries++) {
+		udelay(10);
+		data = readl(base + PCIE_RC_DL_MDIO_WR_DATA);
+	}
+
+	return MDIO_WT_DONE(data) ? 0 : -EIO;
+}
+
+/*
+ * Configures device for Spread Spectrum Clocking (SSC) mode; negative
+ * return value indicates error.
+ */
+static int set_ssc(void __iomem *base)
+{
+	int tmp;
+	u16 wrdata;
+	int pll, ssc;
+
+	tmp = mdio_write(base, MDIO_PORT0, SET_ADDR_OFFSET, SSC_REGS_ADDR);
+	if (tmp < 0)
+		return tmp;
+
+	tmp = mdio_read(base, MDIO_PORT0, SSC_CNTL_OFFSET);
+	if (tmp < 0)
+		return tmp;
+
+	wrdata = INSERT_FIELD(tmp, SSC_CNTL_OVRD, EN, 1);
+	wrdata = INSERT_FIELD(wrdata, SSC_CNTL_OVRD, VAL, 1);
+	tmp = mdio_write(base, MDIO_PORT0, SSC_CNTL_OFFSET, wrdata);
+	if (tmp < 0)
+		return tmp;
+
+	udelay(1500);
+	tmp = mdio_read(base, MDIO_PORT0, SSC_STATUS_OFFSET);
+	if (tmp < 0)
+		return tmp;
+
+	ssc = EXTRACT_FIELD(tmp, SSC_STATUS, SSC);
+	pll = EXTRACT_FIELD(tmp, SSC_STATUS, PLL_LOCK);
+
+	return (ssc && pll) ? 0 : -EIO;
+}
+
+/* Limits operation to a specific generation (1, 2, or 3) */
+static void set_gen(void __iomem *base, int gen)
+{
+	u32 lnkcap = readl(base + BRCM_PCIE_CAP_REGS + PCI_EXP_LNKCAP);
+	u16 lnkctl2 = readw(base + BRCM_PCIE_CAP_REGS + PCI_EXP_LNKCTL2);
+
+	lnkcap = (lnkcap & ~PCI_EXP_LNKCAP_SLS) | gen;
+	writel(lnkcap, base + BRCM_PCIE_CAP_REGS + PCI_EXP_LNKCAP);
+
+	lnkctl2 = (lnkctl2 & ~0xf) | gen;
+	writew(lnkctl2, base + BRCM_PCIE_CAP_REGS + PCI_EXP_LNKCTL2);
+}
+
+static void brcm_pcie_set_outbound_win(struct brcm_pcie *pcie,
+				       unsigned int win, phys_addr_t phys_addr,
+				       dma_addr_t pcie_addr, dma_addr_t size)
+{
+	void __iomem *base = pcie->base;
+	phys_addr_t phys_addr_mb, limit_addr_mb;
+	u32 tmp;
+
+	/* Set the base of the pcie_addr window */
+	writel(lower_32_bits(pcie_addr) + MMIO_ENDIAN,
+	       base + PCIE_MISC_CPU_2_PCIE_MEM_WIN0_LO + (win * 8));
+	writel(upper_32_bits(pcie_addr),
+	       base + PCIE_MISC_CPU_2_PCIE_MEM_WIN0_HI + (win * 8));
+
+	phys_addr_mb = phys_addr >> 20;
+	limit_addr_mb = (phys_addr + size - 1) >> 20;
+
+	/* Write the addr base low register */
+	WR_FLD_WITH_OFFSET(base, (win * 4),
+			   PCIE_MISC_CPU_2_PCIE_MEM_WIN0_BASE_LIMIT,
+			   BASE, phys_addr_mb);
+	/* Write the addr limit low register */
+	WR_FLD_WITH_OFFSET(base, (win * 4),
+			   PCIE_MISC_CPU_2_PCIE_MEM_WIN0_BASE_LIMIT,
+			   LIMIT, limit_addr_mb);
+
+	if (pcie->type != BCM7435 && pcie->type != BCM7425) {
+		/* Write the cpu addr high register */
+		tmp = (u32)(phys_addr_mb >>
+			PCIE_MISC_CPU_2_PCIE_MEM_WIN0_BASE_LIMIT_NUM_MASK_BITS);
+		WR_FLD_WITH_OFFSET(base, (win * 8),
+				   PCIE_MISC_CPU_2_PCIE_MEM_WIN0_BASE_HI,
+				   BASE, tmp);
+		/* Write the cpu limit high register */
+		tmp = (u32)(limit_addr_mb >>
+			PCIE_MISC_CPU_2_PCIE_MEM_WIN0_BASE_LIMIT_NUM_MASK_BITS);
+		WR_FLD_WITH_OFFSET(base, (win * 8),
+				   PCIE_MISC_CPU_2_PCIE_MEM_WIN0_LIMIT_HI,
+				   LIMIT, tmp);
+	}
+}
+
+static int brcm_pcie_setup(struct brcm_pcie *pcie)
+{
+	phys_addr_t scb_size[BRCM_MAX_SCB] = {0};
+	void __iomem *base = pcie->base;
+	unsigned int scb_size_val;
+	u64 rc_bar2_offset, rc_bar2_size;
+	u64 total_mem_size = 0;
+	int i, j, ret, limit, num_memc;
+	u16 nlw, cls, lnksta;
+	bool ssc_good = false;
+	u32 tmp;
+
+	/* Reset the bridge */
+	brcm_pcie_bridge_sw_init_set(pcie, 1);
+
+	/*
+	 * Ensure that the fundamental reset is asserted, except for 7278,
+	 * which fails if we do this.
+	 */
+	if (pcie->type != BCM7278)
+		brcm_pcie_perst_set(pcie, 1);
+
+	udelay(150);
+
+	/* Take the bridge out of reset */
+	brcm_pcie_bridge_sw_init_set(pcie, 0);
+
+	WR_FLD_RB(base, PCIE_MISC_HARD_PCIE_HARD_DEBUG, SERDES_IDDQ, 0);
+	/* Wait for SerDes to be stable */
+	udelay(150);
+
+	/* Grab the PCIe hw revision number */
+	tmp = readl(base + PCIE_MISC_REVISION);
+	pcie->rev = EXTRACT_FIELD(tmp, PCIE_MISC_REVISION, MAJMIN);
+
+	/* Set SCB_MAX_BURST_SIZE, CFG_READ_UR_MODE, SCB_ACCESS_EN */
+	tmp = INSERT_FIELD(0, PCIE_MISC_MISC_CTRL, SCB_ACCESS_EN, 1);
+	tmp = INSERT_FIELD(tmp, PCIE_MISC_MISC_CTRL, CFG_READ_UR_MODE, 1);
+	tmp = INSERT_FIELD(tmp, PCIE_MISC_MISC_CTRL, MAX_BURST_SIZE,
+			   pcie->max_burst_size);
+	writel(tmp, base + PCIE_MISC_MISC_CTRL);
+
+	/*
+	 * Set up inbound memory view for the EP (called RC_BAR2, not to be
+	 * confused with the BARs that are advertised by the EP).
+	 *
+	 * The PCIe host controller by design must set the inbound viewport
+	 * to be a contiguous arrangement of all of the system's memory.
+	 * In addition, its size must be a power of two.  Further, the MSI
+	 * target address must NOT be placed inside this region, as the
+	 * decoding logic will consider its address to be inbound memory
+	 * traffic.  To further complicate matters, the viewport must start
+	 * on a pcie-address that is aligned on a multiple of its size.
+	 * If a portion of the viewport does not represent system memory
+	 * -- e.g. 3GB of memory requires a 4GB viewport -- we can map
+	 * the outbound memory in or after 3GB and even though the viewport
+	 * will overlap the outbound memory the controller will know to send
+	 * outbound memory downstream and everything else upstream.
+	 */
+
+	if (num_dma_ranges) {
+		/*
+		 * Use the base address and size(s) provided in the dma-ranges
+		 * property.
+		 */
+		for (i = 0; i < num_dma_ranges; i++)
+			scb_size[i] = roundup_pow_of_two_64(dma_ranges[i].size);
+
+		num_memc = num_dma_ranges;
+		rc_bar2_offset = dma_ranges[0].pci_addr;
+	} else {
+		return -EINVAL;
+	}
+
+	for (i = 0; i < num_memc; i++)
+		total_mem_size += scb_size[i];
+
+	rc_bar2_size = roundup_pow_of_two_64(total_mem_size);
+
+	/* Verify the alignment is correct */
+	if (rc_bar2_offset & (rc_bar2_size - 1)) {
+		printf("PCIe BRCM: inbound window is misaligned\n");
+		return -EINVAL;
+	}
+
+	tmp = lower_32_bits(rc_bar2_offset);
+	tmp = INSERT_FIELD(tmp, PCIE_MISC_RC_BAR2_CONFIG_LO, SIZE,
+			   encode_ibar_size(rc_bar2_size));
+	writel(tmp, base + PCIE_MISC_RC_BAR2_CONFIG_LO);
+	writel(upper_32_bits(rc_bar2_offset),
+	       base + PCIE_MISC_RC_BAR2_CONFIG_HI);
+
+	scb_size_val = scb_size[0]
+		? ilog2(scb_size[0]) - 15 : 0xf; /* 0xf is 1GB */
+	WR_FLD(base, PCIE_MISC_MISC_CTRL, SCB0_SIZE, scb_size_val);
+
+	if (num_memc > 1) {
+		scb_size_val = scb_size[1]
+			? ilog2(scb_size[1]) - 15 : 0xf; /* 0xf is 1GB */
+		WR_FLD(base, PCIE_MISC_MISC_CTRL, SCB1_SIZE, scb_size_val);
+	}
+
+	if (num_memc > 2) {
+		scb_size_val = scb_size[2]
+			? ilog2(scb_size[2]) - 15 : 0xf; /* 0xf is 1GB */
+		WR_FLD(base, PCIE_MISC_MISC_CTRL, SCB2_SIZE, scb_size_val);
+	}
+
+	/* Disable the PCIe->GISB memory window (RC_BAR1) */
+	WR_FLD(base, PCIE_MISC_RC_BAR1_CONFIG_LO, SIZE, 0);
+
+	/* Disable the PCIe->SCB memory window (RC_BAR3) */
+	WR_FLD(base, PCIE_MISC_RC_BAR3_CONFIG_LO, SIZE, 0);
+
+	/* Clear any interrupts we find on boot */
+	writel(0xffffffff, base + PCIE_INTR2_CPU_BASE + CLR);
+	(void)readl(base + PCIE_INTR2_CPU_BASE + CLR);
+
+	/* Mask all interrupts since we are not handling any yet */
+	writel(0xffffffff, base + PCIE_INTR2_CPU_BASE + MASK_SET);
+	(void)readl(base + PCIE_INTR2_CPU_BASE + MASK_SET);
+
+	if (pcie->gen)
+		set_gen(base, pcie->gen);
+
+	/* Unassert the fundamental reset */
+	brcm_pcie_perst_set(pcie, 0);
+
+	/* Give the RC/EP time to wake up, before trying to configure RC. */
+	limit = 100;
+	for (i = 1, j = 0; j < limit && !brcm_pcie_link_up(pcie);
+	     j += i, i = i * 2)
+		msleep(i + j > limit ? limit - j : i);
+
+	if (!brcm_pcie_link_up(pcie)) {
+		printf("PCIe BRCM: link down\n");
+		return -ENODEV;
+	}
+
+	if (!brcm_pcie_rc_mode(pcie)) {
+		printf("PCIe misconfigured; is in EP mode\n");
+		return -EINVAL;
+	}
+
+	for (i = 0; i < pcie->num_out_wins; i++)
+		brcm_pcie_set_outbound_win(pcie, i, pcie->out_wins[i].phys_addr,
+					   pcie->out_wins[i].pci_addr,
+					   pcie->out_wins[i].size);
+
+	/*
+	 * For config space accesses on the RC, show the right class for
+	 * a PCIe-PCIe bridge (the default setting is to be EP mode).
+	 */
+	WR_FLD_RB(base, PCIE_RC_CFG_PRIV1_ID_VAL3, CLASS_CODE, 0x060400);
+
+	if (pcie->ssc) {
+		ret = set_ssc(base);
+		if (ret == 0)
+			ssc_good = true;
+		else
+			printf("PCIe BRCM: failed attempt to enter ssc mode\n");
+	}
+
+	lnksta = readw(base + BRCM_PCIE_CAP_REGS + PCI_EXP_LNKSTA);
+	cls = lnksta & PCI_EXP_LNKSTA_CLS;
+	nlw = (lnksta & PCI_EXP_LNKSTA_NLW) >> PCI_EXP_LNKSTA_NLW_SHIFT;
+
+	printf("PCIe BRCM: link up, %s Gbps x%u %s\n", link_speed_to_str(cls),
+	       nlw, ssc_good ? "(SSC)" : "(!SSC)");
+
+	/* PCIe->SCB endian mode for BAR */
+	/* field ENDIAN_MODE_BAR2 = DATA_ENDIAN */
+	WR_FLD_RB(base, PCIE_RC_CFG_VENDOR_VENDOR_SPECIFIC_REG1,
+		  ENDIAN_MODE_BAR2, DATA_ENDIAN);
+
+	/*
+	 * Refclk from RC should be gated with CLKREQ# input when ASPM L0s,L1
+	 * is enabled =>  setting the CLKREQ_DEBUG_ENABLE field to 1.
+	 */
+	WR_FLD_RB(base, PCIE_MISC_HARD_PCIE_HARD_DEBUG, CLKREQ_DEBUG_ENABLE, 1);
+
+	return 0;
+}
+
+static const struct udevice_id brcm_pcie_ids[] = {
+	{ .compatible = "brcm,bcm7445-pcie", .data = (ulong)&generic_cfg },
+	{ .compatible = "brcm,bcm2711-pcie", .data = (ulong)&bcm2711_cfg },
+	{ }
+};
+
+static int brcm_pcie_probe(struct udevice *dev)
+{
+	struct udevice *ctlr = pci_get_controller(dev);
+	struct pci_controller *hose = dev_get_uclass_priv(ctlr);
+	struct brcm_pcie *pcie = dev_get_priv(dev);
+	struct pcie_cfg_data *data = (struct pcie_cfg_data *)dev_get_driver_data(dev);
+	ofnode dn = dev_ofnode(dev);
+	u32 max_link_speed;
+	int i;
+
+	if (hose->region_count < 2) {
+		pr_err("PCIe BRCM: Missing PCI regions definition");
+		return -EINVAL;
+	}
+
+	for (i = 0; i < hose->region_count; i++) {
+		if (hose->regions[i].flags == PCI_REGION_SYS_MEMORY)
+			continue;
+
+		pcie->out_wins[i].phys_addr = hose->regions[i].phys_start;
+		pcie->out_wins[i].pci_addr = hose->regions[i].bus_start;
+		pcie->out_wins[i].size = hose->regions[i].size;
+		pcie->num_out_wins++;
+	}
+
+	/* TODO: Parse inbound access mapping from dma-ranges DT property */
+	num_dma_ranges = 1;
+	for (i = 0; i < hose->region_count; i++) {
+		if (hose->regions[i].flags != PCI_REGION_SYS_MEMORY)
+			continue;
+
+		dma_ranges[0].pci_addr = hose->regions[i].bus_start;
+		dma_ranges[0].phys_addr = hose->regions[i].phys_start;
+		dma_ranges[0].size = hose->regions[i].size;
+		break;
+	}
+
+	pcie->reg_offsets = data->offsets;
+	pcie->reg_field_info = data->reg_field_info;
+	pcie->max_burst_size = data->max_burst_size;
+	pcie->type = data->type;
+
+	if (ofnode_read_u32(dn, "max-link-speed", &max_link_speed) ||
+	    max_link_speed > 4)
+		pcie->gen = 0;
+	else
+		pcie->gen = max_link_speed;
+
+	pcie->ssc = ofnode_read_bool(dn, "brcm,enable-ssc");
+
+	return brcm_pcie_setup(pcie);
+}
+
+static int brcm_pcie_ofdata_to_platdata(struct udevice *dev)
+{
+	struct brcm_pcie *pcie = dev_get_priv(dev);
+
+	/* Get the controller base address */
+	pcie->base = dev_read_addr_ptr(dev);
+	if (!pcie->base)
+		return -EINVAL;
+
+	return 0;
+}
+
+static const struct dm_pci_ops brcm_pcie_ops = {
+	.read_config	= brcm_pcie_read_config,
+	.write_config	= brcm_pcie_write_config,
+};
+
+U_BOOT_DRIVER(pcie_brcm_base) = {
+	.name			= "pcie_brcm",
+	.id			= UCLASS_PCI,
+	.ops			= &brcm_pcie_ops,
+	.of_match		= brcm_pcie_ids,
+	.probe			= brcm_pcie_probe,
+	.ofdata_to_platdata	= brcm_pcie_ofdata_to_platdata,
+	.priv_auto_alloc_size	= sizeof(struct brcm_pcie),
+};
-- 
2.7.4