Merge branch 'remotes/lorenzo/pci/tegra'

  - Reorganize Tegra AFI/PHY/REFCLK/etc functions (Manikanta Maddireddy)

  - Mask Tegra AFI_INTR in runtime suspend (Manikanta Maddireddy)

  - Fix Tegra AFI/PCIe powerup sequence (Manikanta Maddireddy)

  - Add Tegra124, Tegra132, Tegra210, and Tegra186 support for Gen2 link
    speed (Manikanta Maddireddy)

  - Advertise Tegra AER support (Manikanta Maddireddy)

  - Program Tegra210 UPHY settings (Manikanta Maddireddy)

  - Enable Tegra opportunistic UpdateFC and ACK (Manikanta Maddireddy)

  - Disable Tegra AFI dynamic clock gating (Manikanta Maddireddy)

  - Process Tegra pending DLL transactions before entering L1 or L2 to
    prevent receiver errors (Manikanta Maddireddy)

  - Enable Tegra xclk clock clamping in L1 (Manikanta Maddireddy)

  - Increase Tegra deskew retry time (Manikanta Maddireddy)

  - Work around Tegra hardware RAW erratum (Manikanta Maddireddy)

  - Update Tegra210 flow control timer frequency (Manikanta Maddireddy)

  - Work around Tegra Gen1/Gen2 link number negotiation issue (Manikanta
    Maddireddy)

  - Work around Tegra PLLE power down issue (Manikanta Maddireddy)

  - Program Tegra20 to support cacheable upstream transactions (Manikanta
    Maddireddy)

  - Log Tegra PRSNT_SENSE_IRQ as debug, not err (Manikanta Maddireddy)

  - Add register offset for third Root Port on Tegra186 and Tegra30
    (Manikanta Maddireddy)

  - Document Tegra PCIe DPD pinctrl property (Manikanta Maddireddy)

  - Put Tegra PEX CLK & BIAS pads in DPD mode to reduce power usage when
    powergated (Manikanta Maddireddy)

  - Add generic DT binding for "reset-gpios" property (Manikanta
    Maddireddy)

  - Add Tegra support for GPIO-based PERST# (Manikanta Maddireddy)

  - Enable Relaxed Ordering only for Tegra20 & Tegra30 (Vidya Sagar)

* remotes/lorenzo/pci/tegra:
  PCI: tegra: Enable Relaxed Ordering only for Tegra20 & Tegra30
  PCI: tegra: Change link retry log level to debug
  PCI: tegra: Add support for GPIO based PERST#
  PCI: Add DT binding for "reset-gpios" property
  PCI: tegra: Put PEX CLK & BIAS pads in DPD mode
  dt-bindings: pci: tegra: Document PCIe DPD pinctrl optional prop
  PCI: tegra: Add AFI_PEX2_CTRL reg offset as part of SoC struct
  PCI: tegra: Change PRSNT_SENSE IRQ log to debug
  PCI: tegra: Program AFI_CACHE_BAR_{0,1}_{ST,SZ} registers only for Tegra20
  PCI: tegra: Fix PLLE power down issue due to CLKREQ# signal
  PCI: tegra: Set target speed as Gen1 before starting LTSSM
  PCI: tegra: Update flow control timer frequency in Tegra210
  PCI: tegra: Add SW fixup for RAW violations
  PCI: tegra: Increase the deskew retry time
  PCI: tegra: Enable PCIe xclk clock clamping
  PCI: tegra: Process pending DLL transactions before entering L1 or L2
  PCI: tegra: Disable AFI dynamic clock gating
  PCI: tegra: Enable opportunistic UpdateFC and ACK
  PCI: tegra: Program UPHY electrical settings for Tegra210
  PCI: tegra: Advertise PCIe Advanced Error Reporting (AER) capability
  PCI: tegra: Add PCIe Gen2 link speed support
  PCI: tegra: Fix PCIe host power up sequence
  PCI: tegra: Mask AFI_INTR in runtime suspend
  PCI: tegra: Rearrange Tegra PCIe driver functions
  PCI: tegra: Handle failure cases in tegra_pcie_power_on()
  soc/tegra: pmc: Export tegra_powergate_power_on()

1 files changed, 507 insertions, 82 deletions

diff --git a/drivers/pci/controller/pci-tegra.c b/drivers/pci/controller/pci-tegra.c
index 464ba2538d52..9a917b2456f6 100644
--- a/drivers/pci/controller/pci-tegra.c
+++ b/drivers/pci/controller/pci-tegra.c
@@ -17,6 +17,7 @@
 #include <linux/debugfs.h>
 #include <linux/delay.h>
 #include <linux/export.h>
+#include <linux/gpio/consumer.h>
 #include <linux/interrupt.h>
 #include <linux/iopoll.h>
 #include <linux/irq.h>
@@ -30,6 +31,7 @@
 #include <linux/of_platform.h>
 #include <linux/pci.h>
 #include <linux/phy/phy.h>
+#include <linux/pinctrl/consumer.h>
 #include <linux/platform_device.h>
 #include <linux/reset.h>
 #include <linux/sizes.h>
@@ -95,7 +97,8 @@
 #define AFI_MSI_EN_VEC7		0xa8
 
 #define AFI_CONFIGURATION		0xac
-#define  AFI_CONFIGURATION_EN_FPCI	(1 << 0)
+#define  AFI_CONFIGURATION_EN_FPCI		(1 << 0)
+#define  AFI_CONFIGURATION_CLKEN_OVERRIDE	(1 << 31)
 
 #define AFI_FPCI_ERROR_MASKS	0xb0
 
@@ -159,13 +162,14 @@
 #define  AFI_PCIE_CONFIG_SM2TMS0_XBAR_CONFIG_211	(0x1 << 20)
 #define  AFI_PCIE_CONFIG_SM2TMS0_XBAR_CONFIG_411	(0x2 << 20)
 #define  AFI_PCIE_CONFIG_SM2TMS0_XBAR_CONFIG_111	(0x2 << 20)
+#define  AFI_PCIE_CONFIG_PCIE_CLKREQ_GPIO(x)		(1 << ((x) + 29))
+#define  AFI_PCIE_CONFIG_PCIE_CLKREQ_GPIO_ALL		(0x7 << 29)
 
 #define AFI_FUSE			0x104
 #define  AFI_FUSE_PCIE_T0_GEN2_DIS	(1 << 2)
 
 #define AFI_PEX0_CTRL			0x110
 #define AFI_PEX1_CTRL			0x118
-#define AFI_PEX2_CTRL			0x128
 #define  AFI_PEX_CTRL_RST		(1 << 0)
 #define  AFI_PEX_CTRL_CLKREQ_EN		(1 << 1)
 #define  AFI_PEX_CTRL_REFCLK_EN		(1 << 3)
@@ -177,20 +181,74 @@
 
 #define AFI_PEXBIAS_CTRL_0		0x168
 
+#define RP_PRIV_XP_DL		0x00000494
+#define  RP_PRIV_XP_DL_GEN2_UPD_FC_TSHOLD	(0x1ff << 1)
+
+#define RP_RX_HDR_LIMIT		0x00000e00
+#define  RP_RX_HDR_LIMIT_PW_MASK	(0xff << 8)
+#define  RP_RX_HDR_LIMIT_PW		(0x0e << 8)
+
+#define RP_ECTL_2_R1	0x00000e84
+#define  RP_ECTL_2_R1_RX_CTLE_1C_MASK		0xffff
+
+#define RP_ECTL_4_R1	0x00000e8c
+#define  RP_ECTL_4_R1_RX_CDR_CTRL_1C_MASK	(0xffff << 16)
+#define  RP_ECTL_4_R1_RX_CDR_CTRL_1C_SHIFT	16
+
+#define RP_ECTL_5_R1	0x00000e90
+#define  RP_ECTL_5_R1_RX_EQ_CTRL_L_1C_MASK	0xffffffff
+
+#define RP_ECTL_6_R1	0x00000e94
+#define  RP_ECTL_6_R1_RX_EQ_CTRL_H_1C_MASK	0xffffffff
+
+#define RP_ECTL_2_R2	0x00000ea4
+#define  RP_ECTL_2_R2_RX_CTLE_1C_MASK	0xffff
+
+#define RP_ECTL_4_R2	0x00000eac
+#define  RP_ECTL_4_R2_RX_CDR_CTRL_1C_MASK	(0xffff << 16)
+#define  RP_ECTL_4_R2_RX_CDR_CTRL_1C_SHIFT	16
+
+#define RP_ECTL_5_R2	0x00000eb0
+#define  RP_ECTL_5_R2_RX_EQ_CTRL_L_1C_MASK	0xffffffff
+
+#define RP_ECTL_6_R2	0x00000eb4
+#define  RP_ECTL_6_R2_RX_EQ_CTRL_H_1C_MASK	0xffffffff
+
 #define RP_VEND_XP	0x00000f00
-#define  RP_VEND_XP_DL_UP	(1 << 30)
+#define  RP_VEND_XP_DL_UP			(1 << 30)
+#define  RP_VEND_XP_OPPORTUNISTIC_ACK		(1 << 27)
+#define  RP_VEND_XP_OPPORTUNISTIC_UPDATEFC	(1 << 28)
+#define  RP_VEND_XP_UPDATE_FC_THRESHOLD_MASK	(0xff << 18)
+
+#define RP_VEND_CTL0	0x00000f44
+#define  RP_VEND_CTL0_DSK_RST_PULSE_WIDTH_MASK	(0xf << 12)
+#define  RP_VEND_CTL0_DSK_RST_PULSE_WIDTH	(0x9 << 12)
+
+#define RP_VEND_CTL1	0x00000f48
+#define  RP_VEND_CTL1_ERPT	(1 << 13)
+
+#define RP_VEND_XP_BIST	0x00000f4c
+#define  RP_VEND_XP_BIST_GOTO_L1_L2_AFTER_DLLP_DONE	(1 << 28)
 
 #define RP_VEND_CTL2 0x00000fa8
 #define  RP_VEND_CTL2_PCA_ENABLE (1 << 7)
 
 #define RP_PRIV_MISC	0x00000fe0
-#define  RP_PRIV_MISC_PRSNT_MAP_EP_PRSNT (0xe << 0)
-#define  RP_PRIV_MISC_PRSNT_MAP_EP_ABSNT (0xf << 0)
+#define  RP_PRIV_MISC_PRSNT_MAP_EP_PRSNT		(0xe << 0)
+#define  RP_PRIV_MISC_PRSNT_MAP_EP_ABSNT		(0xf << 0)
+#define  RP_PRIV_MISC_CTLR_CLK_CLAMP_THRESHOLD_MASK	(0x7f << 16)
+#define  RP_PRIV_MISC_CTLR_CLK_CLAMP_THRESHOLD		(0xf << 16)
+#define  RP_PRIV_MISC_CTLR_CLK_CLAMP_ENABLE		(1 << 23)
+#define  RP_PRIV_MISC_TMS_CLK_CLAMP_THRESHOLD_MASK	(0x7f << 24)
+#define  RP_PRIV_MISC_TMS_CLK_CLAMP_THRESHOLD		(0xf << 24)
+#define  RP_PRIV_MISC_TMS_CLK_CLAMP_ENABLE		(1 << 31)
 
 #define RP_LINK_CONTROL_STATUS			0x00000090
 #define  RP_LINK_CONTROL_STATUS_DL_LINK_ACTIVE	0x20000000
 #define  RP_LINK_CONTROL_STATUS_LINKSTAT_MASK	0x3fff0000
 
+#define RP_LINK_CONTROL_STATUS_2		0x000000b0
+
 #define PADS_CTL_SEL		0x0000009c
 
 #define PADS_CTL		0x000000a0
@@ -226,6 +284,7 @@
 #define PADS_REFCLK_CFG_DRVI_SHIFT		12 /* 15:12 */
 
 #define PME_ACK_TIMEOUT 10000
+#define LINK_RETRAIN_TIMEOUT 100000 /* in usec */
 
 struct tegra_msi {
 	struct msi_controller chip;
@@ -249,10 +308,12 @@ struct tegra_pcie_soc {
 	unsigned int num_ports;
 	const struct tegra_pcie_port_soc *ports;
 	unsigned int msi_base_shift;
+	unsigned long afi_pex2_ctrl;
 	u32 pads_pll_ctl;
 	u32 tx_ref_sel;
 	u32 pads_refclk_cfg0;
 	u32 pads_refclk_cfg1;
+	u32 update_fc_threshold;
 	bool has_pex_clkreq_en;
 	bool has_pex_bias_ctrl;
 	bool has_intr_prsnt_sense;
@@ -260,6 +321,24 @@ struct tegra_pcie_soc {
 	bool has_gen2;
 	bool force_pca_enable;
 	bool program_uphy;
+	bool update_clamp_threshold;
+	bool program_deskew_time;
+	bool raw_violation_fixup;
+	bool update_fc_timer;
+	bool has_cache_bars;
+	struct {
+		struct {
+			u32 rp_ectl_2_r1;
+			u32 rp_ectl_4_r1;
+			u32 rp_ectl_5_r1;
+			u32 rp_ectl_6_r1;
+			u32 rp_ectl_2_r2;
+			u32 rp_ectl_4_r2;
+			u32 rp_ectl_5_r2;
+			u32 rp_ectl_6_r2;
+		} regs;
+		bool enable;
+	} ectl;
 };
 
 static inline struct tegra_msi *to_tegra_msi(struct msi_controller *chip)
@@ -321,6 +400,8 @@ struct tegra_pcie_port {
 	unsigned int lanes;
 
 	struct phy **phys;
+
+	struct gpio_desc *reset_gpio;
 };
 
 struct tegra_pcie_bus {
@@ -440,6 +521,7 @@ static struct pci_ops tegra_pcie_ops = {
 
 static unsigned long tegra_pcie_port_get_pex_ctrl(struct tegra_pcie_port *port)
 {
+	const struct tegra_pcie_soc *soc = port->pcie->soc;
 	unsigned long ret = 0;
 
 	switch (port->index) {
@@ -452,7 +534,7 @@ static unsigned long tegra_pcie_port_get_pex_ctrl(struct tegra_pcie_port *port)
 		break;
 
 	case 2:
-		ret = AFI_PEX2_CTRL;
+		ret = soc->afi_pex2_ctrl;
 		break;
 	}
 
@@ -465,15 +547,162 @@ static void tegra_pcie_port_reset(struct tegra_pcie_port *port)
 	unsigned long value;
 
 	/* pulse reset signal */
-	value = afi_readl(port->pcie, ctrl);
-	value &= ~AFI_PEX_CTRL_RST;
-	afi_writel(port->pcie, value, ctrl);
+	if (port->reset_gpio) {
+		gpiod_set_value(port->reset_gpio, 1);
+	} else {
+		value = afi_readl(port->pcie, ctrl);
+		value &= ~AFI_PEX_CTRL_RST;
+		afi_writel(port->pcie, value, ctrl);
+	}
 
 	usleep_range(1000, 2000);
 
-	value = afi_readl(port->pcie, ctrl);
-	value |= AFI_PEX_CTRL_RST;
-	afi_writel(port->pcie, value, ctrl);
+	if (port->reset_gpio) {
+		gpiod_set_value(port->reset_gpio, 0);
+	} else {
+		value = afi_readl(port->pcie, ctrl);
+		value |= AFI_PEX_CTRL_RST;
+		afi_writel(port->pcie, value, ctrl);
+	}
+}
+
+static void tegra_pcie_enable_rp_features(struct tegra_pcie_port *port)
+{
+	const struct tegra_pcie_soc *soc = port->pcie->soc;
+	u32 value;
+
+	/* Enable AER capability */
+	value = readl(port->base + RP_VEND_CTL1);
+	value |= RP_VEND_CTL1_ERPT;
+	writel(value, port->base + RP_VEND_CTL1);
+
+	/* Optimal settings to enhance bandwidth */
+	value = readl(port->base + RP_VEND_XP);
+	value |= RP_VEND_XP_OPPORTUNISTIC_ACK;
+	value |= RP_VEND_XP_OPPORTUNISTIC_UPDATEFC;
+	writel(value, port->base + RP_VEND_XP);
+
+	/*
+	 * LTSSM will wait for DLLP to finish before entering L1 or L2,
+	 * to avoid truncation of PM messages which results in receiver errors
+	 */
+	value = readl(port->base + RP_VEND_XP_BIST);
+	value |= RP_VEND_XP_BIST_GOTO_L1_L2_AFTER_DLLP_DONE;
+	writel(value, port->base + RP_VEND_XP_BIST);
+
+	value = readl(port->base + RP_PRIV_MISC);
+	value |= RP_PRIV_MISC_CTLR_CLK_CLAMP_ENABLE;
+	value |= RP_PRIV_MISC_TMS_CLK_CLAMP_ENABLE;
+
+	if (soc->update_clamp_threshold) {
+		value &= ~(RP_PRIV_MISC_CTLR_CLK_CLAMP_THRESHOLD_MASK |
+				RP_PRIV_MISC_TMS_CLK_CLAMP_THRESHOLD_MASK);
+		value |= RP_PRIV_MISC_CTLR_CLK_CLAMP_THRESHOLD |
+			RP_PRIV_MISC_TMS_CLK_CLAMP_THRESHOLD;
+	}
+
+	writel(value, port->base + RP_PRIV_MISC);
+}
+
+static void tegra_pcie_program_ectl_settings(struct tegra_pcie_port *port)
+{
+	const struct tegra_pcie_soc *soc = port->pcie->soc;
+	u32 value;
+
+	value = readl(port->base + RP_ECTL_2_R1);
+	value &= ~RP_ECTL_2_R1_RX_CTLE_1C_MASK;
+	value |= soc->ectl.regs.rp_ectl_2_r1;
+	writel(value, port->base + RP_ECTL_2_R1);
+
+	value = readl(port->base + RP_ECTL_4_R1);
+	value &= ~RP_ECTL_4_R1_RX_CDR_CTRL_1C_MASK;
+	value |= soc->ectl.regs.rp_ectl_4_r1 <<
+				RP_ECTL_4_R1_RX_CDR_CTRL_1C_SHIFT;
+	writel(value, port->base + RP_ECTL_4_R1);
+
+	value = readl(port->base + RP_ECTL_5_R1);
+	value &= ~RP_ECTL_5_R1_RX_EQ_CTRL_L_1C_MASK;
+	value |= soc->ectl.regs.rp_ectl_5_r1;
+	writel(value, port->base + RP_ECTL_5_R1);
+
+	value = readl(port->base + RP_ECTL_6_R1);
+	value &= ~RP_ECTL_6_R1_RX_EQ_CTRL_H_1C_MASK;
+	value |= soc->ectl.regs.rp_ectl_6_r1;
+	writel(value, port->base + RP_ECTL_6_R1);
+
+	value = readl(port->base + RP_ECTL_2_R2);
+	value &= ~RP_ECTL_2_R2_RX_CTLE_1C_MASK;
+	value |= soc->ectl.regs.rp_ectl_2_r2;
+	writel(value, port->base + RP_ECTL_2_R2);
+
+	value = readl(port->base + RP_ECTL_4_R2);
+	value &= ~RP_ECTL_4_R2_RX_CDR_CTRL_1C_MASK;
+	value |= soc->ectl.regs.rp_ectl_4_r2 <<
+				RP_ECTL_4_R2_RX_CDR_CTRL_1C_SHIFT;
+	writel(value, port->base + RP_ECTL_4_R2);
+
+	value = readl(port->base + RP_ECTL_5_R2);
+	value &= ~RP_ECTL_5_R2_RX_EQ_CTRL_L_1C_MASK;
+	value |= soc->ectl.regs.rp_ectl_5_r2;
+	writel(value, port->base + RP_ECTL_5_R2);
+
+	value = readl(port->base + RP_ECTL_6_R2);
+	value &= ~RP_ECTL_6_R2_RX_EQ_CTRL_H_1C_MASK;
+	value |= soc->ectl.regs.rp_ectl_6_r2;
+	writel(value, port->base + RP_ECTL_6_R2);
+}
+
+static void tegra_pcie_apply_sw_fixup(struct tegra_pcie_port *port)
+{
+	const struct tegra_pcie_soc *soc = port->pcie->soc;
+	u32 value;
+
+	/*
+	 * Sometimes link speed change from Gen2 to Gen1 fails due to
+	 * instability in deskew logic on lane-0. Increase the deskew
+	 * retry time to resolve this issue.
+	 */
+	if (soc->program_deskew_time) {
+		value = readl(port->base + RP_VEND_CTL0);
+		value &= ~RP_VEND_CTL0_DSK_RST_PULSE_WIDTH_MASK;
+		value |= RP_VEND_CTL0_DSK_RST_PULSE_WIDTH;
+		writel(value, port->base + RP_VEND_CTL0);
+	}
+
+	/* Fixup for read after write violation. */
+	if (soc->raw_violation_fixup) {
+		value = readl(port->base + RP_RX_HDR_LIMIT);
+		value &= ~RP_RX_HDR_LIMIT_PW_MASK;
+		value |= RP_RX_HDR_LIMIT_PW;
+		writel(value, port->base + RP_RX_HDR_LIMIT);
+
+		value = readl(port->base + RP_PRIV_XP_DL);
+		value |= RP_PRIV_XP_DL_GEN2_UPD_FC_TSHOLD;
+		writel(value, port->base + RP_PRIV_XP_DL);
+
+		value = readl(port->base + RP_VEND_XP);
+		value &= ~RP_VEND_XP_UPDATE_FC_THRESHOLD_MASK;
+		value |= soc->update_fc_threshold;
+		writel(value, port->base + RP_VEND_XP);
+	}
+
+	if (soc->update_fc_timer) {
+		value = readl(port->base + RP_VEND_XP);
+		value &= ~RP_VEND_XP_UPDATE_FC_THRESHOLD_MASK;
+		value |= soc->update_fc_threshold;
+		writel(value, port->base + RP_VEND_XP);
+	}
+
+	/*
+	 * PCIe link doesn't come up with few legacy PCIe endpoints if
+	 * root port advertises both Gen-1 and Gen-2 speeds in Tegra.
+	 * Hence, the strategy followed here is to initially advertise
+	 * only Gen-1 and after link is up, retrain link to Gen-2 speed
+	 */
+	value = readl(port->base + RP_LINK_CONTROL_STATUS_2);
+	value &= ~PCI_EXP_LNKSTA_CLS;
+	value |= PCI_EXP_LNKSTA_CLS_2_5GB;
+	writel(value, port->base + RP_LINK_CONTROL_STATUS_2);
 }
 
 static void tegra_pcie_port_enable(struct tegra_pcie_port *port)
@@ -500,6 +729,13 @@ static void tegra_pcie_port_enable(struct tegra_pcie_port *port)
 		value |= RP_VEND_CTL2_PCA_ENABLE;
 		writel(value, port->base + RP_VEND_CTL2);
 	}
+
+	tegra_pcie_enable_rp_features(port);
+
+	if (soc->ectl.enable)
+		tegra_pcie_program_ectl_settings(port);
+
+	tegra_pcie_apply_sw_fixup(port);
 }
 
 static void tegra_pcie_port_disable(struct tegra_pcie_port *port)
@@ -521,6 +757,12 @@ static void tegra_pcie_port_disable(struct tegra_pcie_port *port)
 
 	value &= ~AFI_PEX_CTRL_REFCLK_EN;
 	afi_writel(port->pcie, value, ctrl);
+
+	/* disable PCIe port and set CLKREQ# as GPIO to allow PLLE power down */
+	value = afi_readl(port->pcie, AFI_PCIE_CONFIG);
+	value |= AFI_PCIE_CONFIG_PCIE_DISABLE(port->index);
+	value |= AFI_PCIE_CONFIG_PCIE_CLKREQ_GPIO(port->index);
+	afi_writel(port->pcie, value, AFI_PCIE_CONFIG);
 }
 
 static void tegra_pcie_port_free(struct tegra_pcie_port *port)
@@ -545,12 +787,15 @@ DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_NVIDIA, 0x0bf1, tegra_pcie_fixup_class);
 DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_NVIDIA, 0x0e1c, tegra_pcie_fixup_class);
 DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_NVIDIA, 0x0e1d, tegra_pcie_fixup_class);
 
-/* Tegra PCIE requires relaxed ordering */
+/* Tegra20 and Tegra30 PCIE requires relaxed ordering */
 static void tegra_pcie_relax_enable(struct pci_dev *dev)
 {
 	pcie_capability_set_word(dev, PCI_EXP_DEVCTL, PCI_EXP_DEVCTL_RELAX_EN);
 }
-DECLARE_PCI_FIXUP_FINAL(PCI_ANY_ID, PCI_ANY_ID, tegra_pcie_relax_enable);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_NVIDIA, 0x0bf0, tegra_pcie_relax_enable);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_NVIDIA, 0x0bf1, tegra_pcie_relax_enable);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_NVIDIA, 0x0e1c, tegra_pcie_relax_enable);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_NVIDIA, 0x0e1d, tegra_pcie_relax_enable);
 
 static int tegra_pcie_request_resources(struct tegra_pcie *pcie)
 {
@@ -635,7 +880,7 @@ static irqreturn_t tegra_pcie_isr(int irq, void *arg)
 	 * do not pollute kernel log with master abort reports since they
 	 * happen a lot during enumeration
 	 */
-	if (code == AFI_INTR_MASTER_ABORT)
+	if (code == AFI_INTR_MASTER_ABORT || code == AFI_INTR_PE_PRSNT_SENSE)
 		dev_dbg(dev, "%s, signature: %08x\n", err_msg[code], signature);
 	else
 		dev_err(dev, "%s, signature: %08x\n", err_msg[code], signature);
@@ -704,11 +949,13 @@ static void tegra_pcie_setup_translations(struct tegra_pcie *pcie)
 	afi_writel(pcie, 0, AFI_AXI_BAR5_SZ);
 	afi_writel(pcie, 0, AFI_FPCI_BAR5);
 
-	/* map all upstream transactions as uncached */
-	afi_writel(pcie, 0, AFI_CACHE_BAR0_ST);
-	afi_writel(pcie, 0, AFI_CACHE_BAR0_SZ);
-	afi_writel(pcie, 0, AFI_CACHE_BAR1_ST);
-	afi_writel(pcie, 0, AFI_CACHE_BAR1_SZ);
+	if (pcie->soc->has_cache_bars) {
+		/* map all upstream transactions as uncached */
+		afi_writel(pcie, 0, AFI_CACHE_BAR0_ST);
+		afi_writel(pcie, 0, AFI_CACHE_BAR0_SZ);
+		afi_writel(pcie, 0, AFI_CACHE_BAR1_ST);
+		afi_writel(pcie, 0, AFI_CACHE_BAR1_SZ);
+	}
 
 	/* MSI translations are setup only when needed */
 	afi_writel(pcie, 0, AFI_MSI_FPCI_BAR_ST);
@@ -852,7 +1099,6 @@ static int tegra_pcie_port_phy_power_off(struct tegra_pcie_port *port)
 static int tegra_pcie_phy_power_on(struct tegra_pcie *pcie)
 {
 	struct device *dev = pcie->dev;
-	const struct tegra_pcie_soc *soc = pcie->soc;
 	struct tegra_pcie_port *port;
 	int err;
 
@@ -878,12 +1124,6 @@ static int tegra_pcie_phy_power_on(struct tegra_pcie *pcie)
 		}
 	}
 
-	/* Configure the reference clock driver */
-	pads_writel(pcie, soc->pads_refclk_cfg0, PADS_REFCLK_CFG0);
-
-	if (soc->num_ports > 2)
-		pads_writel(pcie, soc->pads_refclk_cfg1, PADS_REFCLK_CFG1);
-
 	return 0;
 }
 
@@ -918,13 +1158,11 @@ static int tegra_pcie_phy_power_off(struct tegra_pcie *pcie)
 	return 0;
 }
 
-static int tegra_pcie_enable_controller(struct tegra_pcie *pcie)
+static void tegra_pcie_enable_controller(struct tegra_pcie *pcie)
 {
-	struct device *dev = pcie->dev;
 	const struct tegra_pcie_soc *soc = pcie->soc;
 	struct tegra_pcie_port *port;
 	unsigned long value;
-	int err;
 
 	/* enable PLL power down */
 	if (pcie->phy) {
@@ -942,9 +1180,12 @@ static int tegra_pcie_enable_controller(struct tegra_pcie *pcie)
 	value = afi_readl(pcie, AFI_PCIE_CONFIG);
 	value &= ~AFI_PCIE_CONFIG_SM2TMS0_XBAR_CONFIG_MASK;
 	value |= AFI_PCIE_CONFIG_PCIE_DISABLE_ALL | pcie->xbar_config;
+	value |= AFI_PCIE_CONFIG_PCIE_CLKREQ_GPIO_ALL;
 
-	list_for_each_entry(port, &pcie->ports, list)
+	list_for_each_entry(port, &pcie->ports, list) {
 		value &= ~AFI_PCIE_CONFIG_PCIE_DISABLE(port->index);
+		value &= ~AFI_PCIE_CONFIG_PCIE_CLKREQ_GPIO(port->index);
+	}
 
 	afi_writel(pcie, value, AFI_PCIE_CONFIG);
 
@@ -958,20 +1199,10 @@ static int tegra_pcie_enable_controller(struct tegra_pcie *pcie)
 		afi_writel(pcie, value, AFI_FUSE);
 	}
 
-	if (soc->program_uphy) {
-		err = tegra_pcie_phy_power_on(pcie);
-		if (err < 0) {
-			dev_err(dev, "failed to power on PHY(s): %d\n", err);
-			return err;
-		}
-	}
-
-	/* take the PCIe interface module out of reset */
-	reset_control_deassert(pcie->pcie_xrst);
-
-	/* finally enable PCIe */
+	/* Disable AFI dynamic clock gating and enable PCIe */
 	value = afi_readl(pcie, AFI_CONFIGURATION);
 	value |= AFI_CONFIGURATION_EN_FPCI;
+	value |= AFI_CONFIGURATION_CLKEN_OVERRIDE;
 	afi_writel(pcie, value, AFI_CONFIGURATION);
 
 	value = AFI_INTR_EN_INI_SLVERR | AFI_INTR_EN_INI_DECERR |
@@ -989,22 +1220,6 @@ static int tegra_pcie_enable_controller(struct tegra_pcie *pcie)
 
 	/* disable all exceptions */
 	afi_writel(pcie, 0, AFI_FPCI_ERROR_MASKS);
-
-	return 0;
-}
-
-static void tegra_pcie_disable_controller(struct tegra_pcie *pcie)
-{
-	int err;
-
-	reset_control_assert(pcie->pcie_xrst);
-
-	if (pcie->soc->program_uphy) {
-		err = tegra_pcie_phy_power_off(pcie);
-		if (err < 0)
-			dev_err(pcie->dev, "failed to power off PHY(s): %d\n",
-				err);
-	}
 }
 
 static void tegra_pcie_power_off(struct tegra_pcie *pcie)
@@ -1014,13 +1229,11 @@ static void tegra_pcie_power_off(struct tegra_pcie *pcie)
 	int err;
 
 	reset_control_assert(pcie->afi_rst);
-	reset_control_assert(pcie->pex_rst);
 
 	clk_disable_unprepare(pcie->pll_e);
 	if (soc->has_cml_clk)
 		clk_disable_unprepare(pcie->cml_clk);
 	clk_disable_unprepare(pcie->afi_clk);
-	clk_disable_unprepare(pcie->pex_clk);
 
 	if (!dev->pm_domain)
 		tegra_powergate_power_off(TEGRA_POWERGATE_PCIE);
@@ -1048,46 +1261,66 @@ static int tegra_pcie_power_on(struct tegra_pcie *pcie)
 	if (err < 0)
 		dev_err(dev, "failed to enable regulators: %d\n", err);
 
-	if (dev->pm_domain) {
-		err = clk_prepare_enable(pcie->pex_clk);
+	if (!dev->pm_domain) {
+		err = tegra_powergate_power_on(TEGRA_POWERGATE_PCIE);
 		if (err) {
-			dev_err(dev, "failed to enable PEX clock: %d\n", err);
-			return err;
+			dev_err(dev, "failed to power ungate: %d\n", err);
+			goto regulator_disable;
 		}
-		reset_control_deassert(pcie->pex_rst);
-	} else {
-		err = tegra_powergate_sequence_power_up(TEGRA_POWERGATE_PCIE,
-							pcie->pex_clk,
-							pcie->pex_rst);
+		err = tegra_powergate_remove_clamping(TEGRA_POWERGATE_PCIE);
 		if (err) {
-			dev_err(dev, "powerup sequence failed: %d\n", err);
-			return err;
+			dev_err(dev, "failed to remove clamp: %d\n", err);
+			goto powergate;
 		}
 	}
 
-	reset_control_deassert(pcie->afi_rst);
-
 	err = clk_prepare_enable(pcie->afi_clk);
 	if (err < 0) {
 		dev_err(dev, "failed to enable AFI clock: %d\n", err);
-		return err;
+		goto powergate;
 	}
 
 	if (soc->has_cml_clk) {
 		err = clk_prepare_enable(pcie->cml_clk);
 		if (err < 0) {
 			dev_err(dev, "failed to enable CML clock: %d\n", err);
-			return err;
+			goto disable_afi_clk;
 		}
 	}
 
 	err = clk_prepare_enable(pcie->pll_e);
 	if (err < 0) {
 		dev_err(dev, "failed to enable PLLE clock: %d\n", err);
-		return err;
+		goto disable_cml_clk;
 	}
 
+	reset_control_deassert(pcie->afi_rst);
+
 	return 0;
+
+disable_cml_clk:
+	if (soc->has_cml_clk)
+		clk_disable_unprepare(pcie->cml_clk);
+disable_afi_clk:
+	clk_disable_unprepare(pcie->afi_clk);
+powergate:
+	if (!dev->pm_domain)
+		tegra_powergate_power_off(TEGRA_POWERGATE_PCIE);
+regulator_disable:
+	regulator_bulk_disable(pcie->num_supplies, pcie->supplies);
+
+	return err;
+}
+
+static void tegra_pcie_apply_pad_settings(struct tegra_pcie *pcie)
+{
+	const struct tegra_pcie_soc *soc = pcie->soc;
+
+	/* Configure the reference clock driver */
+	pads_writel(pcie, soc->pads_refclk_cfg0, PADS_REFCLK_CFG0);
+
+	if (soc->num_ports > 2)
+		pads_writel(pcie, soc->pads_refclk_cfg1, PADS_REFCLK_CFG1);
 }
 
 static int tegra_pcie_clocks_get(struct tegra_pcie *pcie)
@@ -1647,6 +1880,15 @@ static int tegra_pcie_disable_msi(struct tegra_pcie *pcie)
 	return 0;
 }
 
+static void tegra_pcie_disable_interrupts(struct tegra_pcie *pcie)
+{
+	u32 value;
+
+	value = afi_readl(pcie, AFI_INTR_MASK);
+	value &= ~AFI_INTR_MASK_INT_MASK;
+	afi_writel(pcie, value, AFI_INTR_MASK);
+}
+
 static int tegra_pcie_get_xbar_config(struct tegra_pcie *pcie, u32 lanes,
 				      u32 *xbar)
 {
@@ -1990,6 +2232,7 @@ static int tegra_pcie_parse_dt(struct tegra_pcie *pcie)
 		struct tegra_pcie_port *rp;
 		unsigned int index;
 		u32 value;
+		char *label;
 
 		err = of_pci_get_devfn(port);
 		if (err < 0) {
@@ -2048,6 +2291,31 @@ static int tegra_pcie_parse_dt(struct tegra_pcie *pcie)
 		if (IS_ERR(rp->base))
 			return PTR_ERR(rp->base);
 
+		label = devm_kasprintf(dev, GFP_KERNEL, "pex-reset-%u", index);
+		if (!label) {
+			dev_err(dev, "failed to create reset GPIO label\n");
+			return -ENOMEM;
+		}
+
+		/*
+		 * Returns -ENOENT if reset-gpios property is not populated
+		 * and in this case fall back to using AFI per port register
+		 * to toggle PERST# SFIO line.
+		 */
+		rp->reset_gpio = devm_gpiod_get_from_of_node(dev, port,
+							     "reset-gpios", 0,
+							     GPIOD_OUT_LOW,
+							     label);
+		if (IS_ERR(rp->reset_gpio)) {
+			if (PTR_ERR(rp->reset_gpio) == -ENOENT) {
+				rp->reset_gpio = NULL;
+			} else {
+				dev_err(dev, "failed to get reset GPIO: %d\n",
+					err);
+				return PTR_ERR(rp->reset_gpio);
+			}
+		}
+
 		list_add_tail(&rp->list, &pcie->ports);
 	}
 
@@ -2095,7 +2363,7 @@ static bool tegra_pcie_port_check_link(struct tegra_pcie_port *port)
 		} while (--timeout);
 
 		if (!timeout) {
-			dev_err(dev, "link %u down, retrying\n", port->index);
+			dev_dbg(dev, "link %u down, retrying\n", port->index);
 			goto retry;
 		}
 
@@ -2117,6 +2385,64 @@ retry:
 	return false;
 }
 
+static void tegra_pcie_change_link_speed(struct tegra_pcie *pcie)
+{
+	struct device *dev = pcie->dev;
+	struct tegra_pcie_port *port;
+	ktime_t deadline;
+	u32 value;
+
+	list_for_each_entry(port, &pcie->ports, list) {
+		/*
+		 * "Supported Link Speeds Vector" in "Link Capabilities 2"
+		 * is not supported by Tegra. tegra_pcie_change_link_speed()
+		 * is called only for Tegra chips which support Gen2.
+		 * So there no harm if supported link speed is not verified.
+		 */
+		value = readl(port->base + RP_LINK_CONTROL_STATUS_2);
+		value &= ~PCI_EXP_LNKSTA_CLS;
+		value |= PCI_EXP_LNKSTA_CLS_5_0GB;
+		writel(value, port->base + RP_LINK_CONTROL_STATUS_2);
+
+		/*
+		 * Poll until link comes back from recovery to avoid race
+		 * condition.
+		 */
+		deadline = ktime_add_us(ktime_get(), LINK_RETRAIN_TIMEOUT);
+
+		while (ktime_before(ktime_get(), deadline)) {
+			value = readl(port->base + RP_LINK_CONTROL_STATUS);
+			if ((value & PCI_EXP_LNKSTA_LT) == 0)
+				break;
+
+			usleep_range(2000, 3000);
+		}
+
+		if (value & PCI_EXP_LNKSTA_LT)
+			dev_warn(dev, "PCIe port %u link is in recovery\n",
+				 port->index);
+
+		/* Retrain the link */
+		value = readl(port->base + RP_LINK_CONTROL_STATUS);
+		value |= PCI_EXP_LNKCTL_RL;
+		writel(value, port->base + RP_LINK_CONTROL_STATUS);
+
+		deadline = ktime_add_us(ktime_get(), LINK_RETRAIN_TIMEOUT);
+
+		while (ktime_before(ktime_get(), deadline)) {
+			value = readl(port->base + RP_LINK_CONTROL_STATUS);
+			if ((value & PCI_EXP_LNKSTA_LT) == 0)
+				break;
+
+			usleep_range(2000, 3000);
+		}
+
+		if (value & PCI_EXP_LNKSTA_LT)
+			dev_err(dev, "failed to retrain link of port %u\n",
+				port->index);
+	}
+}
+
 static void tegra_pcie_enable_ports(struct tegra_pcie *pcie)
 {
 	struct device *dev = pcie->dev;
@@ -2127,7 +2453,12 @@ static void tegra_pcie_enable_ports(struct tegra_pcie *pcie)
 			 port->index, port->lanes);
 
 		tegra_pcie_port_enable(port);
+	}
 
+	/* Start LTSSM from Tegra side */
+	reset_control_deassert(pcie->pcie_xrst);
+
+	list_for_each_entry_safe(port, tmp, &pcie->ports, list) {
 		if (tegra_pcie_port_check_link(port))
 			continue;
 
@@ -2136,12 +2467,17 @@ static void tegra_pcie_enable_ports(struct tegra_pcie *pcie)
 		tegra_pcie_port_disable(port);
 		tegra_pcie_port_free(port);
 	}
+
+	if (pcie->soc->has_gen2)
+		tegra_pcie_change_link_speed(pcie);
 }
 
 static void tegra_pcie_disable_ports(struct tegra_pcie *pcie)
 {
 	struct tegra_pcie_port *port, *tmp;
 
+	reset_control_assert(pcie->pcie_xrst);
+
 	list_for_each_entry_safe(port, tmp, &pcie->ports, list)
 		tegra_pcie_port_disable(port);
 }
@@ -2155,6 +2491,7 @@ static const struct tegra_pcie_soc tegra20_pcie = {
 	.num_ports = 2,
 	.ports = tegra20_pcie_ports,
 	.msi_base_shift = 0,
+	.afi_pex2_ctrl = 0x128,
 	.pads_pll_ctl = PADS_PLL_CTL_TEGRA20,
 	.tx_ref_sel = PADS_PLL_CTL_TXCLKREF_DIV10,
 	.pads_refclk_cfg0 = 0xfa5cfa5c,
@@ -2165,6 +2502,12 @@ static const struct tegra_pcie_soc tegra20_pcie = {
 	.has_gen2 = false,
 	.force_pca_enable = false,
 	.program_uphy = true,
+	.update_clamp_threshold = false,
+	.program_deskew_time = false,
+	.raw_violation_fixup = false,
+	.update_fc_timer = false,
+	.has_cache_bars = true,
+	.ectl.enable = false,
 };
 
 static const struct tegra_pcie_port_soc tegra30_pcie_ports[] = {
@@ -2188,6 +2531,12 @@ static const struct tegra_pcie_soc tegra30_pcie = {
 	.has_gen2 = false,
 	.force_pca_enable = false,
 	.program_uphy = true,
+	.update_clamp_threshold = false,
+	.program_deskew_time = false,
+	.raw_violation_fixup = false,
+	.update_fc_timer = false,
+	.has_cache_bars = false,
+	.ectl.enable = false,
 };
 
 static const struct tegra_pcie_soc tegra124_pcie = {
@@ -2197,6 +2546,8 @@ static const struct tegra_pcie_soc tegra124_pcie = {
 	.pads_pll_ctl = PADS_PLL_CTL_TEGRA30,
 	.tx_ref_sel = PADS_PLL_CTL_TXCLKREF_BUF_EN,
 	.pads_refclk_cfg0 = 0x44ac44ac,
+	/* FC threshold is bit[25:18] */
+	.update_fc_threshold = 0x03fc0000,
 	.has_pex_clkreq_en = true,
 	.has_pex_bias_ctrl = true,
 	.has_intr_prsnt_sense = true,
@@ -2204,6 +2555,12 @@ static const struct tegra_pcie_soc tegra124_pcie = {
 	.has_gen2 = true,
 	.force_pca_enable = false,
 	.program_uphy = true,
+	.update_clamp_threshold = true,
+	.program_deskew_time = false,
+	.raw_violation_fixup = true,
+	.update_fc_timer = false,
+	.has_cache_bars = false,
+	.ectl.enable = false,
 };
 
 static const struct tegra_pcie_soc tegra210_pcie = {
@@ -2213,6 +2570,8 @@ static const struct tegra_pcie_soc tegra210_pcie = {
 	.pads_pll_ctl = PADS_PLL_CTL_TEGRA30,
 	.tx_ref_sel = PADS_PLL_CTL_TXCLKREF_BUF_EN,
 	.pads_refclk_cfg0 = 0x90b890b8,
+	/* FC threshold is bit[25:18] */
+	.update_fc_threshold = 0x01800000,
 	.has_pex_clkreq_en = true,
 	.has_pex_bias_ctrl = true,
 	.has_intr_prsnt_sense = true,
@@ -2220,6 +2579,24 @@ static const struct tegra_pcie_soc tegra210_pcie = {
 	.has_gen2 = true,
 	.force_pca_enable = true,
 	.program_uphy = true,
+	.update_clamp_threshold = true,
+	.program_deskew_time = true,
+	.raw_violation_fixup = false,
+	.update_fc_timer = true,
+	.has_cache_bars = false,
+	.ectl = {
+		.regs = {
+			.rp_ectl_2_r1 = 0x0000000f,
+			.rp_ectl_4_r1 = 0x00000067,
+			.rp_ectl_5_r1 = 0x55010000,
+			.rp_ectl_6_r1 = 0x00000001,
+			.rp_ectl_2_r2 = 0x0000008f,
+			.rp_ectl_4_r2 = 0x000000c7,
+			.rp_ectl_5_r2 = 0x55010000,
+			.rp_ectl_6_r2 = 0x00000001,
+		},
+		.enable = true,
+	},
 };
 
 static const struct tegra_pcie_port_soc tegra186_pcie_ports[] = {
@@ -2232,6 +2609,7 @@ static const struct tegra_pcie_soc tegra186_pcie = {
 	.num_ports = 3,
 	.ports = tegra186_pcie_ports,
 	.msi_base_shift = 8,
+	.afi_pex2_ctrl = 0x19c,
 	.pads_pll_ctl = PADS_PLL_CTL_TEGRA30,
 	.tx_ref_sel = PADS_PLL_CTL_TXCLKREF_BUF_EN,
 	.pads_refclk_cfg0 = 0x80b880b8,
@@ -2243,6 +2621,12 @@ static const struct tegra_pcie_soc tegra186_pcie = {
 	.has_gen2 = true,
 	.force_pca_enable = false,
 	.program_uphy = false,
+	.update_clamp_threshold = false,
+	.program_deskew_time = false,
+	.raw_violation_fixup = false,
+	.update_fc_timer = false,
+	.has_cache_bars = false,
+	.ectl.enable = false,
 };
 
 static const struct of_device_id tegra_pcie_of_match[] = {
@@ -2485,16 +2869,32 @@ static int __maybe_unused tegra_pcie_pm_suspend(struct device *dev)
 {
 	struct tegra_pcie *pcie = dev_get_drvdata(dev);
 	struct tegra_pcie_port *port;
+	int err;
 
 	list_for_each_entry(port, &pcie->ports, list)
 		tegra_pcie_pme_turnoff(port);
 
 	tegra_pcie_disable_ports(pcie);
 
+	/*
+	 * AFI_INTR is unmasked in tegra_pcie_enable_controller(), mask it to
+	 * avoid unwanted interrupts raised by AFI after pex_rst is asserted.
+	 */
+	tegra_pcie_disable_interrupts(pcie);
+
+	if (pcie->soc->program_uphy) {
+		err = tegra_pcie_phy_power_off(pcie);
+		if (err < 0)
+			dev_err(dev, "failed to power off PHY(s): %d\n", err);
+	}
+
+	reset_control_assert(pcie->pex_rst);
+	clk_disable_unprepare(pcie->pex_clk);
+
 	if (IS_ENABLED(CONFIG_PCI_MSI))
 		tegra_pcie_disable_msi(pcie);
 
-	tegra_pcie_disable_controller(pcie);
+	pinctrl_pm_select_idle_state(dev);
 	tegra_pcie_power_off(pcie);
 
 	return 0;
@@ -2510,20 +2910,45 @@ static int __maybe_unused tegra_pcie_pm_resume(struct device *dev)
 		dev_err(dev, "tegra pcie power on fail: %d\n", err);
 		return err;
 	}
-	err = tegra_pcie_enable_controller(pcie);
-	if (err) {
-		dev_err(dev, "tegra pcie controller enable fail: %d\n", err);
+
+	err = pinctrl_pm_select_default_state(dev);
+	if (err < 0) {
+		dev_err(dev, "failed to disable PCIe IO DPD: %d\n", err);
 		goto poweroff;
 	}
+
+	tegra_pcie_enable_controller(pcie);
 	tegra_pcie_setup_translations(pcie);
 
 	if (IS_ENABLED(CONFIG_PCI_MSI))
 		tegra_pcie_enable_msi(pcie);
 
+	err = clk_prepare_enable(pcie->pex_clk);
+	if (err) {
+		dev_err(dev, "failed to enable PEX clock: %d\n", err);
+		goto pex_dpd_enable;
+	}
+
+	reset_control_deassert(pcie->pex_rst);
+
+	if (pcie->soc->program_uphy) {
+		err = tegra_pcie_phy_power_on(pcie);
+		if (err < 0) {
+			dev_err(dev, "failed to power on PHY(s): %d\n", err);
+			goto disable_pex_clk;
+		}
+	}
+
+	tegra_pcie_apply_pad_settings(pcie);
 	tegra_pcie_enable_ports(pcie);
 
 	return 0;
 
+disable_pex_clk:
+	reset_control_assert(pcie->pex_rst);
+	clk_disable_unprepare(pcie->pex_clk);
+pex_dpd_enable:
+	pinctrl_pm_select_idle_state(dev);
 poweroff:
 	tegra_pcie_power_off(pcie);