Update Linux to v5.10.109

Sourced from [1]

[1] https://cdn.kernel.org/pub/linux/kernel/v5.x/linux-5.10.109.tar.xz

Change-Id: I19bca9fc6762d4e63bcf3e4cba88bbe560d9c76c
Signed-off-by: Olivier Deprez <olivier.deprez@arm.com>
diff --git a/drivers/pci/controller/pci-aardvark.c b/drivers/pci/controller/pci-aardvark.c
index 0538348..f30144c 100644
--- a/drivers/pci/controller/pci-aardvark.c
+++ b/drivers/pci/controller/pci-aardvark.c
@@ -9,14 +9,19 @@
  */
 
 #include <linux/delay.h>
+#include <linux/gpio/consumer.h>
 #include <linux/interrupt.h>
 #include <linux/irq.h>
 #include <linux/irqdomain.h>
 #include <linux/kernel.h>
+#include <linux/module.h>
 #include <linux/pci.h>
 #include <linux/init.h>
+#include <linux/phy/phy.h>
 #include <linux/platform_device.h>
+#include <linux/msi.h>
 #include <linux/of_address.h>
+#include <linux/of_gpio.h>
 #include <linux/of_pci.h>
 
 #include "../pci.h"
@@ -25,21 +30,8 @@
 /* PCIe core registers */
 #define PCIE_CORE_DEV_ID_REG					0x0
 #define PCIE_CORE_CMD_STATUS_REG				0x4
-#define     PCIE_CORE_CMD_IO_ACCESS_EN				BIT(0)
-#define     PCIE_CORE_CMD_MEM_ACCESS_EN				BIT(1)
-#define     PCIE_CORE_CMD_MEM_IO_REQ_EN				BIT(2)
 #define PCIE_CORE_DEV_REV_REG					0x8
 #define PCIE_CORE_PCIEXP_CAP					0xc0
-#define PCIE_CORE_DEV_CTRL_STATS_REG				0xc8
-#define     PCIE_CORE_DEV_CTRL_STATS_RELAX_ORDER_DISABLE	(0 << 4)
-#define     PCIE_CORE_DEV_CTRL_STATS_MAX_PAYLOAD_SZ_SHIFT	5
-#define     PCIE_CORE_DEV_CTRL_STATS_SNOOP_DISABLE		(0 << 11)
-#define     PCIE_CORE_DEV_CTRL_STATS_MAX_RD_REQ_SIZE_SHIFT	12
-#define     PCIE_CORE_DEV_CTRL_STATS_MAX_RD_REQ_SZ		0x2
-#define PCIE_CORE_LINK_CTRL_STAT_REG				0xd0
-#define     PCIE_CORE_LINK_L0S_ENTRY				BIT(0)
-#define     PCIE_CORE_LINK_TRAINING				BIT(5)
-#define     PCIE_CORE_LINK_WIDTH_SHIFT				20
 #define PCIE_CORE_ERR_CAPCTL_REG				0x118
 #define     PCIE_CORE_ERR_CAPCTL_ECRC_CHK_TX			BIT(5)
 #define     PCIE_CORE_ERR_CAPCTL_ECRC_CHK_TX_EN			BIT(6)
@@ -101,6 +93,9 @@
 #define     PCIE_CORE_CTRL2_STRICT_ORDER_ENABLE	BIT(5)
 #define     PCIE_CORE_CTRL2_OB_WIN_ENABLE	BIT(6)
 #define     PCIE_CORE_CTRL2_MSI_ENABLE		BIT(10)
+#define PCIE_CORE_REF_CLK_REG			(CONTROL_BASE_ADDR + 0x14)
+#define     PCIE_CORE_REF_CLK_TX_ENABLE		BIT(1)
+#define     PCIE_CORE_REF_CLK_RX_ENABLE		BIT(2)
 #define PCIE_MSG_LOG_REG			(CONTROL_BASE_ADDR + 0x30)
 #define PCIE_ISR0_REG				(CONTROL_BASE_ADDR + 0x40)
 #define PCIE_MSG_PM_PME_MASK			BIT(7)
@@ -108,26 +103,109 @@
 #define     PCIE_ISR0_MSI_INT_PENDING		BIT(24)
 #define     PCIE_ISR0_INTX_ASSERT(val)		BIT(16 + (val))
 #define     PCIE_ISR0_INTX_DEASSERT(val)	BIT(20 + (val))
-#define	    PCIE_ISR0_ALL_MASK			GENMASK(26, 0)
+#define     PCIE_ISR0_ALL_MASK			GENMASK(31, 0)
 #define PCIE_ISR1_REG				(CONTROL_BASE_ADDR + 0x48)
 #define PCIE_ISR1_MASK_REG			(CONTROL_BASE_ADDR + 0x4C)
 #define     PCIE_ISR1_POWER_STATE_CHANGE	BIT(4)
 #define     PCIE_ISR1_FLUSH			BIT(5)
 #define     PCIE_ISR1_INTX_ASSERT(val)		BIT(8 + (val))
-#define     PCIE_ISR1_ALL_MASK			GENMASK(11, 4)
+#define     PCIE_ISR1_ALL_MASK			GENMASK(31, 0)
 #define PCIE_MSI_ADDR_LOW_REG			(CONTROL_BASE_ADDR + 0x50)
 #define PCIE_MSI_ADDR_HIGH_REG			(CONTROL_BASE_ADDR + 0x54)
 #define PCIE_MSI_STATUS_REG			(CONTROL_BASE_ADDR + 0x58)
 #define PCIE_MSI_MASK_REG			(CONTROL_BASE_ADDR + 0x5C)
 #define PCIE_MSI_PAYLOAD_REG			(CONTROL_BASE_ADDR + 0x9C)
+#define     PCIE_MSI_DATA_MASK			GENMASK(15, 0)
+
+/* PCIe window configuration */
+#define OB_WIN_BASE_ADDR			0x4c00
+#define OB_WIN_BLOCK_SIZE			0x20
+#define OB_WIN_COUNT				8
+#define OB_WIN_REG_ADDR(win, offset)		(OB_WIN_BASE_ADDR + \
+						 OB_WIN_BLOCK_SIZE * (win) + \
+						 (offset))
+#define OB_WIN_MATCH_LS(win)			OB_WIN_REG_ADDR(win, 0x00)
+#define     OB_WIN_ENABLE			BIT(0)
+#define OB_WIN_MATCH_MS(win)			OB_WIN_REG_ADDR(win, 0x04)
+#define OB_WIN_REMAP_LS(win)			OB_WIN_REG_ADDR(win, 0x08)
+#define OB_WIN_REMAP_MS(win)			OB_WIN_REG_ADDR(win, 0x0c)
+#define OB_WIN_MASK_LS(win)			OB_WIN_REG_ADDR(win, 0x10)
+#define OB_WIN_MASK_MS(win)			OB_WIN_REG_ADDR(win, 0x14)
+#define OB_WIN_ACTIONS(win)			OB_WIN_REG_ADDR(win, 0x18)
+#define OB_WIN_DEFAULT_ACTIONS			(OB_WIN_ACTIONS(OB_WIN_COUNT-1) + 0x4)
+#define     OB_WIN_FUNC_NUM_MASK		GENMASK(31, 24)
+#define     OB_WIN_FUNC_NUM_SHIFT		24
+#define     OB_WIN_FUNC_NUM_ENABLE		BIT(23)
+#define     OB_WIN_BUS_NUM_BITS_MASK		GENMASK(22, 20)
+#define     OB_WIN_BUS_NUM_BITS_SHIFT		20
+#define     OB_WIN_MSG_CODE_ENABLE		BIT(22)
+#define     OB_WIN_MSG_CODE_MASK		GENMASK(21, 14)
+#define     OB_WIN_MSG_CODE_SHIFT		14
+#define     OB_WIN_MSG_PAYLOAD_LEN		BIT(12)
+#define     OB_WIN_ATTR_ENABLE			BIT(11)
+#define     OB_WIN_ATTR_TC_MASK			GENMASK(10, 8)
+#define     OB_WIN_ATTR_TC_SHIFT		8
+#define     OB_WIN_ATTR_RELAXED			BIT(7)
+#define     OB_WIN_ATTR_NOSNOOP			BIT(6)
+#define     OB_WIN_ATTR_POISON			BIT(5)
+#define     OB_WIN_ATTR_IDO			BIT(4)
+#define     OB_WIN_TYPE_MASK			GENMASK(3, 0)
+#define     OB_WIN_TYPE_SHIFT			0
+#define     OB_WIN_TYPE_MEM			0x0
+#define     OB_WIN_TYPE_IO			0x4
+#define     OB_WIN_TYPE_CONFIG_TYPE0		0x8
+#define     OB_WIN_TYPE_CONFIG_TYPE1		0x9
+#define     OB_WIN_TYPE_MSG			0xc
 
 /* LMI registers base address and register offsets */
 #define LMI_BASE_ADDR				0x6000
 #define CFG_REG					(LMI_BASE_ADDR + 0x0)
 #define     LTSSM_SHIFT				24
 #define     LTSSM_MASK				0x3f
-#define     LTSSM_L0				0x10
 #define     RC_BAR_CONFIG			0x300
+
+/* LTSSM values in CFG_REG */
+enum {
+	LTSSM_DETECT_QUIET			= 0x0,
+	LTSSM_DETECT_ACTIVE			= 0x1,
+	LTSSM_POLLING_ACTIVE			= 0x2,
+	LTSSM_POLLING_COMPLIANCE		= 0x3,
+	LTSSM_POLLING_CONFIGURATION		= 0x4,
+	LTSSM_CONFIG_LINKWIDTH_START		= 0x5,
+	LTSSM_CONFIG_LINKWIDTH_ACCEPT		= 0x6,
+	LTSSM_CONFIG_LANENUM_ACCEPT		= 0x7,
+	LTSSM_CONFIG_LANENUM_WAIT		= 0x8,
+	LTSSM_CONFIG_COMPLETE			= 0x9,
+	LTSSM_CONFIG_IDLE			= 0xa,
+	LTSSM_RECOVERY_RCVR_LOCK		= 0xb,
+	LTSSM_RECOVERY_SPEED			= 0xc,
+	LTSSM_RECOVERY_RCVR_CFG			= 0xd,
+	LTSSM_RECOVERY_IDLE			= 0xe,
+	LTSSM_L0				= 0x10,
+	LTSSM_RX_L0S_ENTRY			= 0x11,
+	LTSSM_RX_L0S_IDLE			= 0x12,
+	LTSSM_RX_L0S_FTS			= 0x13,
+	LTSSM_TX_L0S_ENTRY			= 0x14,
+	LTSSM_TX_L0S_IDLE			= 0x15,
+	LTSSM_TX_L0S_FTS			= 0x16,
+	LTSSM_L1_ENTRY				= 0x17,
+	LTSSM_L1_IDLE				= 0x18,
+	LTSSM_L2_IDLE				= 0x19,
+	LTSSM_L2_TRANSMIT_WAKE			= 0x1a,
+	LTSSM_DISABLED				= 0x20,
+	LTSSM_LOOPBACK_ENTRY_MASTER		= 0x21,
+	LTSSM_LOOPBACK_ACTIVE_MASTER		= 0x22,
+	LTSSM_LOOPBACK_EXIT_MASTER		= 0x23,
+	LTSSM_LOOPBACK_ENTRY_SLAVE		= 0x24,
+	LTSSM_LOOPBACK_ACTIVE_SLAVE		= 0x25,
+	LTSSM_LOOPBACK_EXIT_SLAVE		= 0x26,
+	LTSSM_HOT_RESET				= 0x27,
+	LTSSM_RECOVERY_EQUALIZATION_PHASE0	= 0x28,
+	LTSSM_RECOVERY_EQUALIZATION_PHASE1	= 0x29,
+	LTSSM_RECOVERY_EQUALIZATION_PHASE2	= 0x2a,
+	LTSSM_RECOVERY_EQUALIZATION_PHASE3	= 0x2b,
+};
+
 #define VENDOR_ID_REG				(LMI_BASE_ADDR + 0x44)
 
 /* PCIe core controller registers */
@@ -160,7 +238,7 @@
 #define     PCIE_IRQ_MSI_INT2_DET		BIT(21)
 #define     PCIE_IRQ_RC_DBELL_DET		BIT(22)
 #define     PCIE_IRQ_EP_STATUS			BIT(23)
-#define     PCIE_IRQ_ALL_MASK			0xfff0fb
+#define     PCIE_IRQ_ALL_MASK			GENMASK(31, 0)
 #define     PCIE_IRQ_ENABLE_INTS_MASK		PCIE_IRQ_CORE_INT
 
 /* Transaction types */
@@ -188,10 +266,18 @@
 
 #define MSI_IRQ_NUM			32
 
+#define CFG_RD_CRS_VAL			0xffff0001
+
 struct advk_pcie {
 	struct platform_device *pdev;
 	void __iomem *base;
-	struct list_head resources;
+	struct {
+		phys_addr_t match;
+		phys_addr_t remap;
+		phys_addr_t mask;
+		u32 actions;
+	} wins[OB_WIN_COUNT];
+	u8 wins_count;
 	struct irq_domain *irq_domain;
 	struct irq_chip irq_chip;
 	raw_spinlock_t irq_lock;
@@ -203,8 +289,10 @@
 	DECLARE_BITMAP(msi_used, MSI_IRQ_NUM);
 	struct mutex msi_used_lock;
 	u16 msi_msg;
-	int root_bus_nr;
+	int link_gen;
 	struct pci_bridge_emul bridge;
+	struct gpio_desc *reset_gpio;
+	struct phy *phy;
 };
 
 static inline void advk_writel(struct advk_pcie *pcie, u32 val, u64 reg)
@@ -217,31 +305,63 @@
 	return readl(pcie->base + reg);
 }
 
-static int advk_pcie_link_up(struct advk_pcie *pcie)
+static u8 advk_pcie_ltssm_state(struct advk_pcie *pcie)
 {
-	u32 val, ltssm_state;
+	u32 val;
+	u8 ltssm_state;
 
 	val = advk_readl(pcie, CFG_REG);
 	ltssm_state = (val >> LTSSM_SHIFT) & LTSSM_MASK;
-	return ltssm_state >= LTSSM_L0;
+	return ltssm_state;
+}
+
+static inline bool advk_pcie_link_up(struct advk_pcie *pcie)
+{
+	/* check if LTSSM is in normal operation - some L* state */
+	u8 ltssm_state = advk_pcie_ltssm_state(pcie);
+	return ltssm_state >= LTSSM_L0 && ltssm_state < LTSSM_DISABLED;
+}
+
+static inline bool advk_pcie_link_active(struct advk_pcie *pcie)
+{
+	/*
+	 * According to PCIe Base specification 3.0, Table 4-14: Link
+	 * Status Mapped to the LTSSM, and 4.2.6.3.6 Configuration.Idle
+	 * is Link Up mapped to LTSSM Configuration.Idle, Recovery, L0,
+	 * L0s, L1 and L2 states. And according to 3.2.1. Data Link
+	 * Control and Management State Machine Rules is DL Up status
+	 * reported in DL Active state.
+	 */
+	u8 ltssm_state = advk_pcie_ltssm_state(pcie);
+	return ltssm_state >= LTSSM_CONFIG_IDLE && ltssm_state < LTSSM_DISABLED;
+}
+
+static inline bool advk_pcie_link_training(struct advk_pcie *pcie)
+{
+	/*
+	 * According to PCIe Base specification 3.0, Table 4-14: Link
+	 * Status Mapped to the LTSSM is Link Training mapped to LTSSM
+	 * Configuration and Recovery states.
+	 */
+	u8 ltssm_state = advk_pcie_ltssm_state(pcie);
+	return ((ltssm_state >= LTSSM_CONFIG_LINKWIDTH_START &&
+		 ltssm_state < LTSSM_L0) ||
+		(ltssm_state >= LTSSM_RECOVERY_EQUALIZATION_PHASE0 &&
+		 ltssm_state <= LTSSM_RECOVERY_EQUALIZATION_PHASE3));
 }
 
 static int advk_pcie_wait_for_link(struct advk_pcie *pcie)
 {
-	struct device *dev = &pcie->pdev->dev;
 	int retries;
 
 	/* check if the link is up or not */
 	for (retries = 0; retries < LINK_WAIT_MAX_RETRIES; retries++) {
-		if (advk_pcie_link_up(pcie)) {
-			dev_info(dev, "link up\n");
+		if (advk_pcie_link_up(pcie))
 			return 0;
-		}
 
 		usleep_range(LINK_WAIT_USLEEP_MIN, LINK_WAIT_USLEEP_MAX);
 	}
 
-	dev_err(dev, "link never came up\n");
 	return -ETIMEDOUT;
 }
 
@@ -250,15 +370,132 @@
 	size_t retries;
 
 	for (retries = 0; retries < RETRAIN_WAIT_MAX_RETRIES; ++retries) {
-		if (!advk_pcie_link_up(pcie))
+		if (advk_pcie_link_training(pcie))
 			break;
 		udelay(RETRAIN_WAIT_USLEEP_US);
 	}
 }
 
+static void advk_pcie_issue_perst(struct advk_pcie *pcie)
+{
+	if (!pcie->reset_gpio)
+		return;
+
+	/* 10ms delay is needed for some cards */
+	dev_info(&pcie->pdev->dev, "issuing PERST via reset GPIO for 10ms\n");
+	gpiod_set_value_cansleep(pcie->reset_gpio, 1);
+	usleep_range(10000, 11000);
+	gpiod_set_value_cansleep(pcie->reset_gpio, 0);
+}
+
+static void advk_pcie_train_link(struct advk_pcie *pcie)
+{
+	struct device *dev = &pcie->pdev->dev;
+	u32 reg;
+	int ret;
+
+	/*
+	 * Setup PCIe rev / gen compliance based on device tree property
+	 * 'max-link-speed' which also forces maximal link speed.
+	 */
+	reg = advk_readl(pcie, PCIE_CORE_CTRL0_REG);
+	reg &= ~PCIE_GEN_SEL_MSK;
+	if (pcie->link_gen == 3)
+		reg |= SPEED_GEN_3;
+	else if (pcie->link_gen == 2)
+		reg |= SPEED_GEN_2;
+	else
+		reg |= SPEED_GEN_1;
+	advk_writel(pcie, reg, PCIE_CORE_CTRL0_REG);
+
+	/*
+	 * Set maximal link speed value also into PCIe Link Control 2 register.
+	 * Armada 3700 Functional Specification says that default value is based
+	 * on SPEED_GEN but tests showed that default value is always 8.0 GT/s.
+	 */
+	reg = advk_readl(pcie, PCIE_CORE_PCIEXP_CAP + PCI_EXP_LNKCTL2);
+	reg &= ~PCI_EXP_LNKCTL2_TLS;
+	if (pcie->link_gen == 3)
+		reg |= PCI_EXP_LNKCTL2_TLS_8_0GT;
+	else if (pcie->link_gen == 2)
+		reg |= PCI_EXP_LNKCTL2_TLS_5_0GT;
+	else
+		reg |= PCI_EXP_LNKCTL2_TLS_2_5GT;
+	advk_writel(pcie, reg, PCIE_CORE_PCIEXP_CAP + PCI_EXP_LNKCTL2);
+
+	/* Enable link training after selecting PCIe generation */
+	reg = advk_readl(pcie, PCIE_CORE_CTRL0_REG);
+	reg |= LINK_TRAINING_EN;
+	advk_writel(pcie, reg, PCIE_CORE_CTRL0_REG);
+
+	/*
+	 * Reset PCIe card via PERST# signal. Some cards are not detected
+	 * during link training when they are in some non-initial state.
+	 */
+	advk_pcie_issue_perst(pcie);
+
+	/*
+	 * PERST# signal could have been asserted by pinctrl subsystem before
+	 * probe() callback has been called or issued explicitly by reset gpio
+	 * function advk_pcie_issue_perst(), making the endpoint going into
+	 * fundamental reset. As required by PCI Express spec (PCI Express
+	 * Base Specification, REV. 4.0 PCI Express, February 19 2014, 6.6.1
+	 * Conventional Reset) a delay for at least 100ms after such a reset
+	 * before sending a Configuration Request to the device is needed.
+	 * So wait until PCIe link is up. Function advk_pcie_wait_for_link()
+	 * waits for link at least 900ms.
+	 */
+	ret = advk_pcie_wait_for_link(pcie);
+	if (ret < 0)
+		dev_err(dev, "link never came up\n");
+	else
+		dev_info(dev, "link up\n");
+}
+
+/*
+ * Set PCIe address window register which could be used for memory
+ * mapping.
+ */
+static void advk_pcie_set_ob_win(struct advk_pcie *pcie, u8 win_num,
+				 phys_addr_t match, phys_addr_t remap,
+				 phys_addr_t mask, u32 actions)
+{
+	advk_writel(pcie, OB_WIN_ENABLE |
+			  lower_32_bits(match), OB_WIN_MATCH_LS(win_num));
+	advk_writel(pcie, upper_32_bits(match), OB_WIN_MATCH_MS(win_num));
+	advk_writel(pcie, lower_32_bits(remap), OB_WIN_REMAP_LS(win_num));
+	advk_writel(pcie, upper_32_bits(remap), OB_WIN_REMAP_MS(win_num));
+	advk_writel(pcie, lower_32_bits(mask), OB_WIN_MASK_LS(win_num));
+	advk_writel(pcie, upper_32_bits(mask), OB_WIN_MASK_MS(win_num));
+	advk_writel(pcie, actions, OB_WIN_ACTIONS(win_num));
+}
+
+static void advk_pcie_disable_ob_win(struct advk_pcie *pcie, u8 win_num)
+{
+	advk_writel(pcie, 0, OB_WIN_MATCH_LS(win_num));
+	advk_writel(pcie, 0, OB_WIN_MATCH_MS(win_num));
+	advk_writel(pcie, 0, OB_WIN_REMAP_LS(win_num));
+	advk_writel(pcie, 0, OB_WIN_REMAP_MS(win_num));
+	advk_writel(pcie, 0, OB_WIN_MASK_LS(win_num));
+	advk_writel(pcie, 0, OB_WIN_MASK_MS(win_num));
+	advk_writel(pcie, 0, OB_WIN_ACTIONS(win_num));
+}
+
 static void advk_pcie_setup_hw(struct advk_pcie *pcie)
 {
 	u32 reg;
+	int i;
+
+	/*
+	 * Configure PCIe Reference clock. Direction is from the PCIe
+	 * controller to the endpoint card, so enable transmitting of
+	 * Reference clock differential signal off-chip and disable
+	 * receiving off-chip differential signal.
+	 */
+	reg = advk_readl(pcie, PCIE_CORE_REF_CLK_REG);
+	reg |= PCIE_CORE_REF_CLK_TX_ENABLE;
+	reg &= ~PCIE_CORE_REF_CLK_RX_ENABLE;
+	advk_writel(pcie, reg, PCIE_CORE_REF_CLK_REG);
 
 	/* Set to Direct mode */
 	reg = advk_readl(pcie, CTRL_CONFIG_REG);
@@ -281,6 +518,31 @@
 	reg = (PCI_VENDOR_ID_MARVELL << 16) | PCI_VENDOR_ID_MARVELL;
 	advk_writel(pcie, reg, VENDOR_ID_REG);
 
+	/*
+	 * Change Class Code of PCI Bridge device to PCI Bridge (0x600400),
+	 * because the default value is Mass storage controller (0x010400).
+	 *
+	 * Note that this Aardvark PCI Bridge does not have compliant Type 1
+	 * Configuration Space and it even cannot be accessed via Aardvark's
+	 * PCI config space access method. Something like config space is
+	 * available in internal Aardvark registers starting at offset 0x0
+	 * and is reported as Type 0. In range 0x10 - 0x34 it has totally
+	 * different registers.
+	 *
+	 * Therefore driver uses emulation of PCI Bridge which emulates
+	 * access to configuration space via internal Aardvark registers or
+	 * emulated configuration buffer.
+	 */
+	reg = advk_readl(pcie, PCIE_CORE_DEV_REV_REG);
+	reg &= ~0xffffff00;
+	reg |= (PCI_CLASS_BRIDGE_PCI << 8) << 8;
+	advk_writel(pcie, reg, PCIE_CORE_DEV_REV_REG);
+
+	/* Disable Root Bridge I/O space, memory space and bus mastering */
+	reg = advk_readl(pcie, PCIE_CORE_CMD_STATUS_REG);
+	reg &= ~(PCI_COMMAND_IO | PCI_COMMAND_MEMORY | PCI_COMMAND_MASTER);
+	advk_writel(pcie, reg, PCIE_CORE_CMD_STATUS_REG);
+
 	/* Set Advanced Error Capabilities and Control PF0 register */
 	reg = PCIE_CORE_ERR_CAPCTL_ECRC_CHK_TX |
 		PCIE_CORE_ERR_CAPCTL_ECRC_CHK_TX_EN |
@@ -288,36 +550,27 @@
 		PCIE_CORE_ERR_CAPCTL_ECRC_CHCK_RCV;
 	advk_writel(pcie, reg, PCIE_CORE_ERR_CAPCTL_REG);
 
-	/* Set PCIe Device Control and Status 1 PF0 register */
-	reg = PCIE_CORE_DEV_CTRL_STATS_RELAX_ORDER_DISABLE |
-		(7 << PCIE_CORE_DEV_CTRL_STATS_MAX_PAYLOAD_SZ_SHIFT) |
-		PCIE_CORE_DEV_CTRL_STATS_SNOOP_DISABLE |
-		(PCIE_CORE_DEV_CTRL_STATS_MAX_RD_REQ_SZ <<
-		 PCIE_CORE_DEV_CTRL_STATS_MAX_RD_REQ_SIZE_SHIFT);
-	advk_writel(pcie, reg, PCIE_CORE_DEV_CTRL_STATS_REG);
+	/* Set PCIe Device Control register */
+	reg = advk_readl(pcie, PCIE_CORE_PCIEXP_CAP + PCI_EXP_DEVCTL);
+	reg &= ~PCI_EXP_DEVCTL_RELAX_EN;
+	reg &= ~PCI_EXP_DEVCTL_NOSNOOP_EN;
+	reg &= ~PCI_EXP_DEVCTL_PAYLOAD;
+	reg &= ~PCI_EXP_DEVCTL_READRQ;
+	reg |= PCI_EXP_DEVCTL_PAYLOAD_512B;
+	reg |= PCI_EXP_DEVCTL_READRQ_512B;
+	advk_writel(pcie, reg, PCIE_CORE_PCIEXP_CAP + PCI_EXP_DEVCTL);
 
 	/* Program PCIe Control 2 to disable strict ordering */
 	reg = PCIE_CORE_CTRL2_RESERVED |
 		PCIE_CORE_CTRL2_TD_ENABLE;
 	advk_writel(pcie, reg, PCIE_CORE_CTRL2_REG);
 
-	/* Set GEN2 */
-	reg = advk_readl(pcie, PCIE_CORE_CTRL0_REG);
-	reg &= ~PCIE_GEN_SEL_MSK;
-	reg |= SPEED_GEN_2;
-	advk_writel(pcie, reg, PCIE_CORE_CTRL0_REG);
-
 	/* Set lane X1 */
 	reg = advk_readl(pcie, PCIE_CORE_CTRL0_REG);
 	reg &= ~LANE_CNT_MSK;
 	reg |= LANE_COUNT_1;
 	advk_writel(pcie, reg, PCIE_CORE_CTRL0_REG);
 
-	/* Enable link training */
-	reg = advk_readl(pcie, PCIE_CORE_CTRL0_REG);
-	reg |= LINK_TRAINING_EN;
-	advk_writel(pcie, reg, PCIE_CORE_CTRL0_REG);
-
 	/* Enable MSI */
 	reg = advk_readl(pcie, PCIE_CORE_CTRL2_REG);
 	reg |= PCIE_CORE_CTRL2_MSI_ENABLE;
@@ -342,35 +595,61 @@
 	reg = PCIE_IRQ_ALL_MASK & (~PCIE_IRQ_ENABLE_INTS_MASK);
 	advk_writel(pcie, reg, HOST_CTRL_INT_MASK_REG);
 
+	/*
+	 * Enable AXI address window location generation:
+	 * When it is enabled, the default outbound window
+	 * configurations (Default User Field: 0xD0074CFC)
+	 * are used to transparent address translation for
+	 * the outbound transactions. Thus, PCIe address
+	 * windows are not required for transparent memory
+	 * access when default outbound window configuration
+	 * is set for memory access.
+	 */
 	reg = advk_readl(pcie, PCIE_CORE_CTRL2_REG);
 	reg |= PCIE_CORE_CTRL2_OB_WIN_ENABLE;
 	advk_writel(pcie, reg, PCIE_CORE_CTRL2_REG);
 
-	/* Bypass the address window mapping for PIO */
+	/*
+	 * Set memory access in Default User Field so it
+	 * is not required to configure PCIe address for
+	 * transparent memory access.
+	 */
+	advk_writel(pcie, OB_WIN_TYPE_MEM, OB_WIN_DEFAULT_ACTIONS);
+
+	/*
+	 * Bypass the address window mapping for PIO:
+	 * Since PIO access already contains all required
+	 * info over AXI interface by PIO registers, the
+	 * address window is not required.
+	 */
 	reg = advk_readl(pcie, PIO_CTRL);
 	reg |= PIO_CTRL_ADDR_WIN_DISABLE;
 	advk_writel(pcie, reg, PIO_CTRL);
 
-	/* Start link training */
-	reg = advk_readl(pcie, PCIE_CORE_LINK_CTRL_STAT_REG);
-	reg |= PCIE_CORE_LINK_TRAINING;
-	advk_writel(pcie, reg, PCIE_CORE_LINK_CTRL_STAT_REG);
+	/*
+	 * Configure PCIe address windows for non-memory or
+	 * non-transparent access as by default PCIe uses
+	 * transparent memory access.
+	 */
+	for (i = 0; i < pcie->wins_count; i++)
+		advk_pcie_set_ob_win(pcie, i,
+				     pcie->wins[i].match, pcie->wins[i].remap,
+				     pcie->wins[i].mask, pcie->wins[i].actions);
 
-	advk_pcie_wait_for_link(pcie);
+	/* Disable remaining PCIe outbound windows */
+	for (i = pcie->wins_count; i < OB_WIN_COUNT; i++)
+		advk_pcie_disable_ob_win(pcie, i);
 
-	reg = advk_readl(pcie, PCIE_CORE_CMD_STATUS_REG);
-	reg |= PCIE_CORE_CMD_MEM_ACCESS_EN |
-		PCIE_CORE_CMD_IO_ACCESS_EN |
-		PCIE_CORE_CMD_MEM_IO_REQ_EN;
-	advk_writel(pcie, reg, PCIE_CORE_CMD_STATUS_REG);
+	advk_pcie_train_link(pcie);
 }
 
-static int advk_pcie_check_pio_status(struct advk_pcie *pcie, u32 *val)
+static int advk_pcie_check_pio_status(struct advk_pcie *pcie, bool allow_crs, u32 *val)
 {
 	struct device *dev = &pcie->pdev->dev;
 	u32 reg;
 	unsigned int status;
 	char *strcomp_status, *str_posted;
+	int ret;
 
 	reg = advk_readl(pcie, PIO_STAT);
 	status = (reg & PIO_COMPLETION_STATUS_MASK) >>
@@ -395,6 +674,7 @@
 	case PIO_COMPLETION_STATUS_OK:
 		if (reg & PIO_ERR_STATUS) {
 			strcomp_status = "COMP_ERR";
+			ret = -EFAULT;
 			break;
 		}
 		/* Get the read result */
@@ -402,45 +682,72 @@
 			*val = advk_readl(pcie, PIO_RD_DATA);
 		/* No error */
 		strcomp_status = NULL;
+		ret = 0;
 		break;
 	case PIO_COMPLETION_STATUS_UR:
 		strcomp_status = "UR";
+		ret = -EOPNOTSUPP;
 		break;
 	case PIO_COMPLETION_STATUS_CRS:
+		if (allow_crs && val) {
+			/* PCIe r4.0, sec 2.3.2, says:
+			 * If CRS Software Visibility is enabled:
+			 * For a Configuration Read Request that includes both
+			 * bytes of the Vendor ID field of a device Function's
+			 * Configuration Space Header, the Root Complex must
+			 * complete the Request to the host by returning a
+			 * read-data value of 0001h for the Vendor ID field and
+			 * all '1's for any additional bytes included in the
+			 * request.
+			 *
+			 * So CRS in this case is not an error status.
+			 */
+			*val = CFG_RD_CRS_VAL;
+			strcomp_status = NULL;
+			ret = 0;
+			break;
+		}
 		/* PCIe r4.0, sec 2.3.2, says:
 		 * If CRS Software Visibility is not enabled, the Root Complex
 		 * must re-issue the Configuration Request as a new Request.
+		 * If CRS Software Visibility is enabled: For a Configuration
+		 * Write Request or for any other Configuration Read Request,
+		 * the Root Complex must re-issue the Configuration Request as
+		 * a new Request.
 		 * A Root Complex implementation may choose to limit the number
 		 * of Configuration Request/CRS Completion Status loops before
 		 * determining that something is wrong with the target of the
 		 * Request and taking appropriate action, e.g., complete the
 		 * Request to the host as a failed transaction.
 		 *
-		 * To simplify implementation do not re-issue the Configuration
-		 * Request and complete the Request as a failed transaction.
+		 * So return -EAGAIN and caller (pci-aardvark.c driver) will
+		 * re-issue request again up to the PIO_RETRY_CNT retries.
 		 */
 		strcomp_status = "CRS";
+		ret = -EAGAIN;
 		break;
 	case PIO_COMPLETION_STATUS_CA:
 		strcomp_status = "CA";
+		ret = -ECANCELED;
 		break;
 	default:
 		strcomp_status = "Unknown";
+		ret = -EINVAL;
 		break;
 	}
 
 	if (!strcomp_status)
-		return 0;
+		return ret;
 
 	if (reg & PIO_NON_POSTED_REQ)
 		str_posted = "Non-posted";
 	else
 		str_posted = "Posted";
 
-	dev_err(dev, "%s PIO Response Status: %s, %#x @ %#x\n",
+	dev_dbg(dev, "%s PIO Response Status: %s, %#x @ %#x\n",
 		str_posted, strcomp_status, reg, advk_readl(pcie, PIO_ADDR_LS));
 
-	return -EFAULT;
+	return ret;
 }
 
 static int advk_pcie_wait_pio(struct advk_pcie *pcie)
@@ -448,13 +755,13 @@
 	struct device *dev = &pcie->pdev->dev;
 	int i;
 
-	for (i = 0; i < PIO_RETRY_CNT; i++) {
+	for (i = 1; i <= PIO_RETRY_CNT; i++) {
 		u32 start, isr;
 
 		start = advk_readl(pcie, PIO_START);
 		isr = advk_readl(pcie, PIO_ISR);
 		if (!start && isr)
-			return 0;
+			return i;
 		udelay(PIO_RETRY_DELAY);
 	}
 
@@ -462,6 +769,64 @@
 	return -ETIMEDOUT;
 }
 
+static pci_bridge_emul_read_status_t
+advk_pci_bridge_emul_base_conf_read(struct pci_bridge_emul *bridge,
+				    int reg, u32 *value)
+{
+	struct advk_pcie *pcie = bridge->data;
+
+	switch (reg) {
+	case PCI_COMMAND:
+		*value = advk_readl(pcie, PCIE_CORE_CMD_STATUS_REG);
+		return PCI_BRIDGE_EMUL_HANDLED;
+
+	case PCI_INTERRUPT_LINE: {
+		/*
+		 * From the whole 32bit register we support reading from HW only
+		 * one bit: PCI_BRIDGE_CTL_BUS_RESET.
+		 * Other bits are retrieved only from emulated config buffer.
+		 */
+		__le32 *cfgspace = (__le32 *)&bridge->conf;
+		u32 val = le32_to_cpu(cfgspace[PCI_INTERRUPT_LINE / 4]);
+		if (advk_readl(pcie, PCIE_CORE_CTRL1_REG) & HOT_RESET_GEN)
+			val |= PCI_BRIDGE_CTL_BUS_RESET << 16;
+		else
+			val &= ~(PCI_BRIDGE_CTL_BUS_RESET << 16);
+		*value = val;
+		return PCI_BRIDGE_EMUL_HANDLED;
+	}
+
+	default:
+		return PCI_BRIDGE_EMUL_NOT_HANDLED;
+	}
+}
+
+static void
+advk_pci_bridge_emul_base_conf_write(struct pci_bridge_emul *bridge,
+				     int reg, u32 old, u32 new, u32 mask)
+{
+	struct advk_pcie *pcie = bridge->data;
+
+	switch (reg) {
+	case PCI_COMMAND:
+		advk_writel(pcie, new, PCIE_CORE_CMD_STATUS_REG);
+		break;
+
+	case PCI_INTERRUPT_LINE:
+		if (mask & (PCI_BRIDGE_CTL_BUS_RESET << 16)) {
+			u32 val = advk_readl(pcie, PCIE_CORE_CTRL1_REG);
+			if (new & (PCI_BRIDGE_CTL_BUS_RESET << 16))
+				val |= HOT_RESET_GEN;
+			else
+				val &= ~HOT_RESET_GEN;
+			advk_writel(pcie, val, PCIE_CORE_CTRL1_REG);
+		}
+		break;
+
+	default:
+		break;
+	}
+}
 
 static pci_bridge_emul_read_status_t
 advk_pci_bridge_emul_pcie_conf_read(struct pci_bridge_emul *bridge,
@@ -478,6 +843,8 @@
 	case PCI_EXP_RTCTL: {
 		u32 val = advk_readl(pcie, PCIE_ISR0_MASK_REG);
 		*value = (val & PCIE_MSG_PM_PME_MASK) ? 0 : PCI_EXP_RTCTL_PMEIE;
+		*value |= le16_to_cpu(bridge->pcie_conf.rootctl) & PCI_EXP_RTCTL_CRSSVE;
+		*value |= PCI_EXP_RTCAP_CRSVIS << 16;
 		return PCI_BRIDGE_EMUL_HANDLED;
 	}
 
@@ -488,20 +855,32 @@
 		return PCI_BRIDGE_EMUL_HANDLED;
 	}
 
-	case PCI_EXP_LNKCTL: {
-		/* u32 contains both PCI_EXP_LNKCTL and PCI_EXP_LNKSTA */
-		u32 val = advk_readl(pcie, PCIE_CORE_PCIEXP_CAP + reg) &
-			~(PCI_EXP_LNKSTA_LT << 16);
-		if (!advk_pcie_link_up(pcie))
-			val |= (PCI_EXP_LNKSTA_LT << 16);
+	case PCI_EXP_LNKCAP: {
+		u32 val = advk_readl(pcie, PCIE_CORE_PCIEXP_CAP + reg);
+		/*
+		 * PCI_EXP_LNKCAP_DLLLARC bit is hardwired in aardvark HW to 0.
+		 * But support for PCI_EXP_LNKSTA_DLLLA is emulated via ltssm
+		 * state so explicitly enable PCI_EXP_LNKCAP_DLLLARC flag.
+		 */
+		val |= PCI_EXP_LNKCAP_DLLLARC;
 		*value = val;
 		return PCI_BRIDGE_EMUL_HANDLED;
 	}
 
-	case PCI_CAP_LIST_ID:
+	case PCI_EXP_LNKCTL: {
+		/* u32 contains both PCI_EXP_LNKCTL and PCI_EXP_LNKSTA */
+		u32 val = advk_readl(pcie, PCIE_CORE_PCIEXP_CAP + reg) &
+			~(PCI_EXP_LNKSTA_LT << 16);
+		if (advk_pcie_link_training(pcie))
+			val |= (PCI_EXP_LNKSTA_LT << 16);
+		if (advk_pcie_link_active(pcie))
+			val |= (PCI_EXP_LNKSTA_DLLLA << 16);
+		*value = val;
+		return PCI_BRIDGE_EMUL_HANDLED;
+	}
+
 	case PCI_EXP_DEVCAP:
 	case PCI_EXP_DEVCTL:
-	case PCI_EXP_LNKCAP:
 		*value = advk_readl(pcie, PCIE_CORE_PCIEXP_CAP + reg);
 		return PCI_BRIDGE_EMUL_HANDLED;
 	default:
@@ -548,6 +927,8 @@
 }
 
 static struct pci_bridge_emul_ops advk_pci_bridge_emul_ops = {
+	.read_base = advk_pci_bridge_emul_base_conf_read,
+	.write_base = advk_pci_bridge_emul_base_conf_write,
 	.read_pcie = advk_pci_bridge_emul_pcie_conf_read,
 	.write_pcie = advk_pci_bridge_emul_pcie_conf_write,
 };
@@ -560,22 +941,30 @@
 {
 	struct pci_bridge_emul *bridge = &pcie->bridge;
 
-	bridge->conf.vendor = advk_readl(pcie, PCIE_CORE_DEV_ID_REG) & 0xffff;
-	bridge->conf.device = advk_readl(pcie, PCIE_CORE_DEV_ID_REG) >> 16;
+	bridge->conf.vendor =
+		cpu_to_le16(advk_readl(pcie, PCIE_CORE_DEV_ID_REG) & 0xffff);
+	bridge->conf.device =
+		cpu_to_le16(advk_readl(pcie, PCIE_CORE_DEV_ID_REG) >> 16);
 	bridge->conf.class_revision =
-		advk_readl(pcie, PCIE_CORE_DEV_REV_REG) & 0xff;
+		cpu_to_le32(advk_readl(pcie, PCIE_CORE_DEV_REV_REG) & 0xff);
 
 	/* Support 32 bits I/O addressing */
 	bridge->conf.iobase = PCI_IO_RANGE_TYPE_32;
 	bridge->conf.iolimit = PCI_IO_RANGE_TYPE_32;
 
 	/* Support 64 bits memory pref */
-	bridge->conf.pref_mem_base = PCI_PREF_RANGE_TYPE_64;
-	bridge->conf.pref_mem_limit = PCI_PREF_RANGE_TYPE_64;
+	bridge->conf.pref_mem_base = cpu_to_le16(PCI_PREF_RANGE_TYPE_64);
+	bridge->conf.pref_mem_limit = cpu_to_le16(PCI_PREF_RANGE_TYPE_64);
 
 	/* Support interrupt A for MSI feature */
 	bridge->conf.intpin = PCIE_CORE_INT_A_ASSERT_ENABLE;
 
+	/* Aardvark HW provides PCIe Capability structure in version 2 */
+	bridge->pcie_conf.cap = cpu_to_le16(2);
+
+	/* Indicates supports for Completion Retry Status */
+	bridge->pcie_conf.rootcap = cpu_to_le16(PCI_EXP_RTCAP_CRSVIS);
+
 	bridge->has_pcie = true;
 	bridge->data = pcie;
 	bridge->ops = &advk_pci_bridge_emul_ops;
@@ -586,7 +975,14 @@
 static bool advk_pcie_valid_device(struct advk_pcie *pcie, struct pci_bus *bus,
 				  int devfn)
 {
-	if ((bus->number == pcie->root_bus_nr) && PCI_SLOT(devfn) != 0)
+	if (pci_is_root_bus(bus) && PCI_SLOT(devfn) != 0)
+		return false;
+
+	/*
+	 * If the link goes down after we check for link-up, nothing bad
+	 * happens but the config access times out.
+	 */
+	if (!pci_is_root_bus(bus) && !advk_pcie_link_up(pcie))
 		return false;
 
 	return true;
@@ -625,6 +1021,8 @@
 			     int where, int size, u32 *val)
 {
 	struct advk_pcie *pcie = bus->sysdata;
+	int retry_count;
+	bool allow_crs;
 	u32 reg;
 	int ret;
 
@@ -633,19 +1031,26 @@
 		return PCIBIOS_DEVICE_NOT_FOUND;
 	}
 
-	if (bus->number == pcie->root_bus_nr)
+	if (pci_is_root_bus(bus))
 		return pci_bridge_emul_conf_read(&pcie->bridge, where,
 						 size, val);
 
-	if (advk_pcie_pio_is_running(pcie)) {
-		*val = 0xffffffff;
-		return PCIBIOS_SET_FAILED;
-	}
+	/*
+	 * Completion Retry Status is possible to return only when reading all
+	 * 4 bytes from PCI_VENDOR_ID and PCI_DEVICE_ID registers at once and
+	 * CRSSVE flag on Root Bridge is enabled.
+	 */
+	allow_crs = (where == PCI_VENDOR_ID) && (size == 4) &&
+		    (le16_to_cpu(pcie->bridge.pcie_conf.rootctl) &
+		     PCI_EXP_RTCTL_CRSSVE);
+
+	if (advk_pcie_pio_is_running(pcie))
+		goto try_crs;
 
 	/* Program the control register */
 	reg = advk_readl(pcie, PIO_CTRL);
 	reg &= ~PIO_CTRL_TYPE_MASK;
-	if (bus->primary ==  pcie->root_bus_nr)
+	if (pci_is_root_bus(bus->parent))
 		reg |= PCIE_CONFIG_RD_TYPE0;
 	else
 		reg |= PCIE_CONFIG_RD_TYPE1;
@@ -659,20 +1064,24 @@
 	/* Program the data strobe */
 	advk_writel(pcie, 0xf, PIO_WR_DATA_STRB);
 
-	/* Clear PIO DONE ISR and start the transfer */
-	advk_writel(pcie, 1, PIO_ISR);
-	advk_writel(pcie, 1, PIO_START);
+	retry_count = 0;
+	do {
+		/* Clear PIO DONE ISR and start the transfer */
+		advk_writel(pcie, 1, PIO_ISR);
+		advk_writel(pcie, 1, PIO_START);
 
-	ret = advk_pcie_wait_pio(pcie);
+		ret = advk_pcie_wait_pio(pcie);
+		if (ret < 0)
+			goto try_crs;
+
+		retry_count += ret;
+
+		/* Check PIO status and get the read result */
+		ret = advk_pcie_check_pio_status(pcie, allow_crs, val);
+	} while (ret == -EAGAIN && retry_count < PIO_RETRY_CNT);
+
 	if (ret < 0)
-		return PCIBIOS_SET_FAILED;
-
-	/* Check PIO status and get the read result */
-	ret = advk_pcie_check_pio_status(pcie, val);
-	if (ret < 0) {
-		*val = 0xffffffff;
-		return PCIBIOS_SET_FAILED;
-	}
+		goto fail;
 
 	if (size == 1)
 		*val = (*val >> (8 * (where & 3))) & 0xff;
@@ -680,6 +1089,20 @@
 		*val = (*val >> (8 * (where & 3))) & 0xffff;
 
 	return PCIBIOS_SUCCESSFUL;
+
+try_crs:
+	/*
+	 * If it is possible, return Completion Retry Status so that caller
+	 * tries to issue the request again instead of failing.
+	 */
+	if (allow_crs) {
+		*val = CFG_RD_CRS_VAL;
+		return PCIBIOS_SUCCESSFUL;
+	}
+
+fail:
+	*val = 0xffffffff;
+	return PCIBIOS_SET_FAILED;
 }
 
 static int advk_pcie_wr_conf(struct pci_bus *bus, u32 devfn,
@@ -688,13 +1111,14 @@
 	struct advk_pcie *pcie = bus->sysdata;
 	u32 reg;
 	u32 data_strobe = 0x0;
+	int retry_count;
 	int offset;
 	int ret;
 
 	if (!advk_pcie_valid_device(pcie, bus, devfn))
 		return PCIBIOS_DEVICE_NOT_FOUND;
 
-	if (bus->number == pcie->root_bus_nr)
+	if (pci_is_root_bus(bus))
 		return pci_bridge_emul_conf_write(&pcie->bridge, where,
 						  size, val);
 
@@ -707,7 +1131,7 @@
 	/* Program the control register */
 	reg = advk_readl(pcie, PIO_CTRL);
 	reg &= ~PIO_CTRL_TYPE_MASK;
-	if (bus->primary == pcie->root_bus_nr)
+	if (pci_is_root_bus(bus->parent))
 		reg |= PCIE_CONFIG_WR_TYPE0;
 	else
 		reg |= PCIE_CONFIG_WR_TYPE1;
@@ -729,19 +1153,22 @@
 	/* Program the data strobe */
 	advk_writel(pcie, data_strobe, PIO_WR_DATA_STRB);
 
-	/* Clear PIO DONE ISR and start the transfer */
-	advk_writel(pcie, 1, PIO_ISR);
-	advk_writel(pcie, 1, PIO_START);
+	retry_count = 0;
+	do {
+		/* Clear PIO DONE ISR and start the transfer */
+		advk_writel(pcie, 1, PIO_ISR);
+		advk_writel(pcie, 1, PIO_START);
 
-	ret = advk_pcie_wait_pio(pcie);
-	if (ret < 0)
-		return PCIBIOS_SET_FAILED;
+		ret = advk_pcie_wait_pio(pcie);
+		if (ret < 0)
+			return PCIBIOS_SET_FAILED;
 
-	ret = advk_pcie_check_pio_status(pcie, NULL);
-	if (ret < 0)
-		return PCIBIOS_SET_FAILED;
+		retry_count += ret;
 
-	return PCIBIOS_SUCCESSFUL;
+		ret = advk_pcie_check_pio_status(pcie, false, NULL);
+	} while (ret == -EAGAIN && retry_count < PIO_RETRY_CNT);
+
+	return ret < 0 ? PCIBIOS_SET_FAILED : PCIBIOS_SUCCESSFUL;
 }
 
 static struct pci_ops advk_pcie_ops = {
@@ -790,7 +1217,7 @@
 				    domain->host_data, handle_simple_irq,
 				    NULL, NULL);
 
-	return hwirq;
+	return 0;
 }
 
 static void advk_msi_irq_domain_free(struct irq_domain *domain,
@@ -971,8 +1398,12 @@
 		if (!(BIT(msi_idx) & msi_status))
 			continue;
 
+		/*
+		 * msi_idx contains bits [4:0] of the msi_data and msi_data
+		 * contains 16bit MSI interrupt number
+		 */
 		advk_writel(pcie, BIT(msi_idx), PCIE_MSI_STATUS_REG);
-		msi_data = advk_readl(pcie, PCIE_MSI_PAYLOAD_REG) & 0xFF;
+		msi_data = advk_readl(pcie, PCIE_MSI_PAYLOAD_REG) & PCIE_MSI_DATA_MASK;
 		generic_handle_irq(msi_data);
 	}
 
@@ -994,12 +1425,6 @@
 	isr1_mask = advk_readl(pcie, PCIE_ISR1_MASK_REG);
 	isr1_status = isr1_val & ((~isr1_mask) & PCIE_ISR1_ALL_MASK);
 
-	if (!isr0_status && !isr1_status) {
-		advk_writel(pcie, isr0_val, PCIE_ISR0_REG);
-		advk_writel(pcie, isr1_val, PCIE_ISR1_REG);
-		return;
-	}
-
 	/* Process MSI interrupts */
 	if (isr0_status & PCIE_ISR0_MSI_INT_PENDING)
 		advk_pcie_handle_msi(pcie);
@@ -1034,64 +1459,70 @@
 	return IRQ_HANDLED;
 }
 
-static int advk_pcie_parse_request_of_pci_ranges(struct advk_pcie *pcie)
+static void __maybe_unused advk_pcie_disable_phy(struct advk_pcie *pcie)
 {
-	int err, res_valid = 0;
-	struct device *dev = &pcie->pdev->dev;
-	struct resource_entry *win, *tmp;
-	resource_size_t iobase;
+	phy_power_off(pcie->phy);
+	phy_exit(pcie->phy);
+}
 
-	INIT_LIST_HEAD(&pcie->resources);
+static int advk_pcie_enable_phy(struct advk_pcie *pcie)
+{
+	int ret;
 
-	err = devm_of_pci_get_host_bridge_resources(dev, 0, 0xff,
-						    &pcie->resources, &iobase);
-	if (err)
-		return err;
+	if (!pcie->phy)
+		return 0;
 
-	err = devm_request_pci_bus_resources(dev, &pcie->resources);
-	if (err)
-		goto out_release_res;
+	ret = phy_init(pcie->phy);
+	if (ret)
+		return ret;
 
-	resource_list_for_each_entry_safe(win, tmp, &pcie->resources) {
-		struct resource *res = win->res;
-
-		switch (resource_type(res)) {
-		case IORESOURCE_IO:
-			err = devm_pci_remap_iospace(dev, res, iobase);
-			if (err) {
-				dev_warn(dev, "error %d: failed to map resource %pR\n",
-					 err, res);
-				resource_list_destroy_entry(win);
-			}
-			break;
-		case IORESOURCE_MEM:
-			res_valid |= !(res->flags & IORESOURCE_PREFETCH);
-			break;
-		case IORESOURCE_BUS:
-			pcie->root_bus_nr = res->start;
-			break;
-		}
+	ret = phy_set_mode(pcie->phy, PHY_MODE_PCIE);
+	if (ret) {
+		phy_exit(pcie->phy);
+		return ret;
 	}
 
-	if (!res_valid) {
-		dev_err(dev, "non-prefetchable memory resource required\n");
-		err = -EINVAL;
-		goto out_release_res;
+	ret = phy_power_on(pcie->phy);
+	if (ret == -EOPNOTSUPP) {
+		dev_warn(&pcie->pdev->dev, "PHY unsupported by firmware\n");
+	} else if (ret) {
+		phy_exit(pcie->phy);
+		return ret;
 	}
 
 	return 0;
+}
 
-out_release_res:
-	pci_free_resource_list(&pcie->resources);
-	return err;
+static int advk_pcie_setup_phy(struct advk_pcie *pcie)
+{
+	struct device *dev = &pcie->pdev->dev;
+	struct device_node *node = dev->of_node;
+	int ret = 0;
+
+	pcie->phy = devm_of_phy_get(dev, node, NULL);
+	if (IS_ERR(pcie->phy) && (PTR_ERR(pcie->phy) == -EPROBE_DEFER))
+		return PTR_ERR(pcie->phy);
+
+	/* Old bindings miss the PHY handle */
+	if (IS_ERR(pcie->phy)) {
+		dev_warn(dev, "PHY unavailable (%ld)\n", PTR_ERR(pcie->phy));
+		pcie->phy = NULL;
+		return 0;
+	}
+
+	ret = advk_pcie_enable_phy(pcie);
+	if (ret)
+		dev_err(dev, "Failed to initialize PHY (%d)\n", ret);
+
+	return ret;
 }
 
 static int advk_pcie_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
 	struct advk_pcie *pcie;
-	struct resource *res;
 	struct pci_host_bridge *bridge;
+	struct resource_entry *entry;
 	int ret, irq;
 
 	bridge = devm_pci_alloc_host_bridge(dev, sizeof(struct advk_pcie));
@@ -1100,13 +1531,90 @@
 
 	pcie = pci_host_bridge_priv(bridge);
 	pcie->pdev = pdev;
+	platform_set_drvdata(pdev, pcie);
 
-	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	pcie->base = devm_ioremap_resource(dev, res);
+	resource_list_for_each_entry(entry, &bridge->windows) {
+		resource_size_t start = entry->res->start;
+		resource_size_t size = resource_size(entry->res);
+		unsigned long type = resource_type(entry->res);
+		u64 win_size;
+
+		/*
+		 * Aardvark hardware allows to configure also PCIe window
+		 * for config type 0 and type 1 mapping, but driver uses
+		 * only PIO for issuing configuration transfers which does
+		 * not use PCIe window configuration.
+		 */
+		if (type != IORESOURCE_MEM && type != IORESOURCE_MEM_64 &&
+		    type != IORESOURCE_IO)
+			continue;
+
+		/*
+		 * Skip transparent memory resources. Default outbound access
+		 * configuration is set to transparent memory access so it
+		 * does not need window configuration.
+		 */
+		if ((type == IORESOURCE_MEM || type == IORESOURCE_MEM_64) &&
+		    entry->offset == 0)
+			continue;
+
+		/*
+		 * The n-th PCIe window is configured by tuple (match, remap, mask)
+		 * and an access to address A uses this window if A matches the
+		 * match with given mask.
+		 * So every PCIe window size must be a power of two and every start
+		 * address must be aligned to window size. Minimal size is 64 KiB
+		 * because lower 16 bits of mask must be zero. Remapped address
+		 * may have set only bits from the mask.
+		 */
+		while (pcie->wins_count < OB_WIN_COUNT && size > 0) {
+			/* Calculate the largest aligned window size */
+			win_size = (1ULL << (fls64(size)-1)) |
+				   (start ? (1ULL << __ffs64(start)) : 0);
+			win_size = 1ULL << __ffs64(win_size);
+			if (win_size < 0x10000)
+				break;
+
+			dev_dbg(dev,
+				"Configuring PCIe window %d: [0x%llx-0x%llx] as %lu\n",
+				pcie->wins_count, (unsigned long long)start,
+				(unsigned long long)start + win_size, type);
+
+			if (type == IORESOURCE_IO) {
+				pcie->wins[pcie->wins_count].actions = OB_WIN_TYPE_IO;
+				pcie->wins[pcie->wins_count].match = pci_pio_to_address(start);
+			} else {
+				pcie->wins[pcie->wins_count].actions = OB_WIN_TYPE_MEM;
+				pcie->wins[pcie->wins_count].match = start;
+			}
+			pcie->wins[pcie->wins_count].remap = start - entry->offset;
+			pcie->wins[pcie->wins_count].mask = ~(win_size - 1);
+
+			if (pcie->wins[pcie->wins_count].remap & (win_size - 1))
+				break;
+
+			start += win_size;
+			size -= win_size;
+			pcie->wins_count++;
+		}
+
+		if (size > 0) {
+			dev_err(&pcie->pdev->dev,
+				"Invalid PCIe region [0x%llx-0x%llx]\n",
+				(unsigned long long)entry->res->start,
+				(unsigned long long)entry->res->end + 1);
+			return -EINVAL;
+		}
+	}
+
+	pcie->base = devm_platform_ioremap_resource(pdev, 0);
 	if (IS_ERR(pcie->base))
 		return PTR_ERR(pcie->base);
 
 	irq = platform_get_irq(pdev, 0);
+	if (irq < 0)
+		return irq;
+
 	ret = devm_request_irq(dev, irq, advk_pcie_irq_handler,
 			       IRQF_SHARED | IRQF_NO_THREAD, "advk-pcie",
 			       pcie);
@@ -1115,12 +1623,32 @@
 		return ret;
 	}
 
-	ret = advk_pcie_parse_request_of_pci_ranges(pcie);
+	pcie->reset_gpio = devm_gpiod_get_from_of_node(dev, dev->of_node,
+						       "reset-gpios", 0,
+						       GPIOD_OUT_LOW,
+						       "pcie1-reset");
+	ret = PTR_ERR_OR_ZERO(pcie->reset_gpio);
 	if (ret) {
-		dev_err(dev, "Failed to parse resources\n");
-		return ret;
+		if (ret == -ENOENT) {
+			pcie->reset_gpio = NULL;
+		} else {
+			if (ret != -EPROBE_DEFER)
+				dev_err(dev, "Failed to get reset-gpio: %i\n",
+					ret);
+			return ret;
+		}
 	}
 
+	ret = of_pci_get_max_link_speed(dev->of_node);
+	if (ret <= 0 || ret > 3)
+		pcie->link_gen = 3;
+	else
+		pcie->link_gen = ret;
+
+	ret = advk_pcie_setup_phy(pcie);
+	if (ret)
+		return ret;
+
 	advk_pcie_setup_hw(pcie);
 
 	ret = advk_sw_pci_bridge_init(pcie);
@@ -1142,13 +1670,8 @@
 		return ret;
 	}
 
-	list_splice_init(&pcie->resources, &bridge->windows);
-	bridge->dev.parent = dev;
 	bridge->sysdata = pcie;
-	bridge->busnr = 0;
 	bridge->ops = &advk_pcie_ops;
-	bridge->map_irq = of_irq_parse_and_map_pci;
-	bridge->swizzle_irq = pci_common_swizzle;
 
 	ret = pci_host_probe(bridge);
 	if (ret < 0) {
@@ -1160,18 +1683,42 @@
 	return 0;
 }
 
+static int advk_pcie_remove(struct platform_device *pdev)
+{
+	struct advk_pcie *pcie = platform_get_drvdata(pdev);
+	struct pci_host_bridge *bridge = pci_host_bridge_from_priv(pcie);
+	int i;
+
+	pci_lock_rescan_remove();
+	pci_stop_root_bus(bridge->bus);
+	pci_remove_root_bus(bridge->bus);
+	pci_unlock_rescan_remove();
+
+	advk_pcie_remove_msi_irq_domain(pcie);
+	advk_pcie_remove_irq_domain(pcie);
+
+	/* Disable outbound address windows mapping */
+	for (i = 0; i < OB_WIN_COUNT; i++)
+		advk_pcie_disable_ob_win(pcie, i);
+
+	return 0;
+}
+
 static const struct of_device_id advk_pcie_of_match_table[] = {
 	{ .compatible = "marvell,armada-3700-pcie", },
 	{},
 };
+MODULE_DEVICE_TABLE(of, advk_pcie_of_match_table);
 
 static struct platform_driver advk_pcie_driver = {
 	.driver = {
 		.name = "advk-pcie",
 		.of_match_table = advk_pcie_of_match_table,
-		/* Driver unloading/unbinding currently not supported */
-		.suppress_bind_attrs = true,
 	},
 	.probe = advk_pcie_probe,
+	.remove = advk_pcie_remove,
 };
-builtin_platform_driver(advk_pcie_driver);
+module_platform_driver(advk_pcie_driver);
+
+MODULE_DESCRIPTION("Aardvark PCIe controller");
+MODULE_LICENSE("GPL v2");