Merge branch 'for-6.15/amd_sfh' into for-linus

From: Mario Limonciello <mario.limonciello@amd.com>

Some platforms include a human presence detection (HPD) sensor. When
enabled and a user is detected a wake event will be emitted from the
sensor fusion hub that software can react to.

Example use cases are "wake from suspend on approach" or to "lock
when leaving".

This is currently enabled by default on supported systems, but users
can't control it. This essentially means that wake on approach is
enabled which is a really surprising behavior to users that don't
expect it.

Instead of defaulting to enabled add a sysfs knob that users can
use to enable the feature if desirable and set it to disabled by
default.

10 files changed, 498 insertions, 211 deletions

diff --git a/drivers/pci/controller/dwc/pci-dra7xx.c b/drivers/pci/controller/dwc/pci-dra7xx.c
index 5c62e1a3ba529..33d6bf460ffe5 100644
--- a/drivers/pci/controller/dwc/pci-dra7xx.c
+++ b/drivers/pci/controller/dwc/pci-dra7xx.c
@@ -635,30 +635,20 @@ static int dra7xx_pcie_unaligned_memaccess(struct device *dev)
 {
 	int ret;
 	struct device_node *np = dev->of_node;
-	struct of_phandle_args args;
+	unsigned int args[2];
 	struct regmap *regmap;
 
-	regmap = syscon_regmap_lookup_by_phandle(np,
-						 "ti,syscon-unaligned-access");
+	regmap = syscon_regmap_lookup_by_phandle_args(np, "ti,syscon-unaligned-access",
+						      2, args);
 	if (IS_ERR(regmap)) {
 		dev_dbg(dev, "can't get ti,syscon-unaligned-access\n");
 		return -EINVAL;
 	}
 
-	ret = of_parse_phandle_with_fixed_args(np, "ti,syscon-unaligned-access",
-					       2, 0, &args);
-	if (ret) {
-		dev_err(dev, "failed to parse ti,syscon-unaligned-access\n");
-		return ret;
-	}
-
-	ret = regmap_update_bits(regmap, args.args[0], args.args[1],
-				 args.args[1]);
+	ret = regmap_update_bits(regmap, args[0], args[1], args[1]);
 	if (ret)
 		dev_err(dev, "failed to enable unaligned access\n");
 
-	of_node_put(args.np);
-
 	return ret;
 }
 
@@ -671,18 +661,13 @@ static int dra7xx_pcie_configure_two_lane(struct device *dev,
 	u32 mask;
 	u32 val;
 
-	pcie_syscon = syscon_regmap_lookup_by_phandle(np, "ti,syscon-lane-sel");
+	pcie_syscon = syscon_regmap_lookup_by_phandle_args(np, "ti,syscon-lane-sel",
+							   1, &pcie_reg);
 	if (IS_ERR(pcie_syscon)) {
 		dev_err(dev, "unable to get ti,syscon-lane-sel\n");
 		return -EINVAL;
 	}
 
-	if (of_property_read_u32_index(np, "ti,syscon-lane-sel", 1,
-				       &pcie_reg)) {
-		dev_err(dev, "couldn't get lane selection reg offset\n");
-		return -EINVAL;
-	}
-
 	mask = b1co_mode_sel_mask | PCIE_B0_B1_TSYNCEN;
 	val = PCIE_B1C0_MODE_SEL | PCIE_B0_B1_TSYNCEN;
 	regmap_update_bits(pcie_syscon, pcie_reg, mask, val);
diff --git a/drivers/pci/controller/dwc/pci-imx6.c b/drivers/pci/controller/dwc/pci-imx6.c
index c8d5c90aa4d45..90ace941090f9 100644
--- a/drivers/pci/controller/dwc/pci-imx6.c
+++ b/drivers/pci/controller/dwc/pci-imx6.c
@@ -33,6 +33,7 @@
 #include <linux/pm_domain.h>
 #include <linux/pm_runtime.h>
 
+#include "../../pci.h"
 #include "pcie-designware.h"
 
 #define IMX8MQ_GPR_PCIE_REF_USE_PAD		BIT(9)
@@ -55,6 +56,22 @@
 #define IMX95_PE0_GEN_CTRL_3			0x1058
 #define IMX95_PCIE_LTSSM_EN			BIT(0)
 
+#define IMX95_PE0_LUT_ACSCTRL			0x1008
+#define IMX95_PEO_LUT_RWA			BIT(16)
+#define IMX95_PE0_LUT_ENLOC			GENMASK(4, 0)
+
+#define IMX95_PE0_LUT_DATA1			0x100c
+#define IMX95_PE0_LUT_VLD			BIT(31)
+#define IMX95_PE0_LUT_DAC_ID			GENMASK(10, 8)
+#define IMX95_PE0_LUT_STREAM_ID			GENMASK(5, 0)
+
+#define IMX95_PE0_LUT_DATA2			0x1010
+#define IMX95_PE0_LUT_REQID			GENMASK(31, 16)
+#define IMX95_PE0_LUT_MASK			GENMASK(15, 0)
+
+#define IMX95_SID_MASK				GENMASK(5, 0)
+#define IMX95_MAX_LUT				32
+
 #define to_imx_pcie(x)	dev_get_drvdata((x)->dev)
 
 enum imx_pcie_variants {
@@ -70,6 +87,7 @@ enum imx_pcie_variants {
 	IMX8MQ_EP,
 	IMX8MM_EP,
 	IMX8MP_EP,
+	IMX8Q_EP,
 	IMX95_EP,
 };
 
@@ -87,6 +105,7 @@ enum imx_pcie_variants {
  * workaround suspend resume on some devices which are affected by this errata.
  */
 #define IMX_PCIE_FLAG_BROKEN_SUSPEND		BIT(9)
+#define IMX_PCIE_FLAG_HAS_LUT			BIT(10)
 
 #define imx_check_flag(pci, val)	(pci->drvdata->flags & val)
 
@@ -103,6 +122,7 @@ struct imx_pcie_drvdata {
 	const char *gpr;
 	const char * const *clk_names;
 	const u32 clks_cnt;
+	const u32 clks_optional_cnt;
 	const u32 ltssm_off;
 	const u32 ltssm_mask;
 	const u32 mode_off[IMX_PCIE_MAX_INSTANCES];
@@ -111,19 +131,18 @@ struct imx_pcie_drvdata {
 	int (*init_phy)(struct imx_pcie *pcie);
 	int (*enable_ref_clk)(struct imx_pcie *pcie, bool enable);
 	int (*core_reset)(struct imx_pcie *pcie, bool assert);
+	const struct dw_pcie_host_ops *ops;
 };
 
 struct imx_pcie {
 	struct dw_pcie		*pci;
 	struct gpio_desc	*reset_gpiod;
-	bool			link_is_up;
 	struct clk_bulk_data	clks[IMX_PCIE_MAX_CLKS];
 	struct regmap		*iomuxc_gpr;
 	u16			msi_ctrl;
 	u32			controller_id;
 	struct reset_control	*pciephy_reset;
 	struct reset_control	*apps_reset;
-	struct reset_control	*turnoff_reset;
 	u32			tx_deemph_gen1;
 	u32			tx_deemph_gen2_3p5db;
 	u32			tx_deemph_gen2_6db;
@@ -139,6 +158,9 @@ struct imx_pcie {
 	struct device		*pd_pcie_phy;
 	struct phy		*phy;
 	const struct imx_pcie_drvdata *drvdata;
+
+	/* Ensure that only one device's LUT is configured at any given time */
+	struct mutex		lock;
 };
 
 /* Parameters for the waiting for PCIe PHY PLL to lock on i.MX7 */
@@ -234,11 +256,11 @@ static void imx_pcie_configure_type(struct imx_pcie *imx_pcie)
 
 	id = imx_pcie->controller_id;
 
-	/* If mode_mask is 0, then generic PHY driver is used to set the mode */
+	/* If mode_mask is 0, generic PHY driver is used to set the mode */
 	if (!drvdata->mode_mask[0])
 		return;
 
-	/* If mode_mask[id] is zero, means each controller have its individual gpr */
+	/* If mode_mask[id] is 0, each controller has its individual GPR */
 	if (!drvdata->mode_mask[id])
 		id = 0;
 
@@ -375,14 +397,15 @@ static int pcie_phy_write(struct imx_pcie *imx_pcie, int addr, u16 data)
 
 static int imx8mq_pcie_init_phy(struct imx_pcie *imx_pcie)
 {
-	/* TODO: Currently this code assumes external oscillator is being used */
+	/* TODO: This code assumes external oscillator is being used */
 	regmap_update_bits(imx_pcie->iomuxc_gpr,
 			   imx_pcie_grp_offset(imx_pcie),
 			   IMX8MQ_GPR_PCIE_REF_USE_PAD,
 			   IMX8MQ_GPR_PCIE_REF_USE_PAD);
 	/*
-	 * Regarding the datasheet, the PCIE_VPH is suggested to be 1.8V. If the PCIE_VPH is
-	 * supplied by 3.3V, the VREG_BYPASS should be cleared to zero.
+	 * Per the datasheet, the PCIE_VPH is suggested to be 1.8V.  If the
+	 * PCIE_VPH is supplied by 3.3V, the VREG_BYPASS should be cleared
+	 * to zero.
 	 */
 	if (imx_pcie->vph && regulator_get_voltage(imx_pcie->vph) > 3000000)
 		regmap_update_bits(imx_pcie->iomuxc_gpr,
@@ -393,13 +416,6 @@ static int imx8mq_pcie_init_phy(struct imx_pcie *imx_pcie)
 	return 0;
 }
 
-static int imx7d_pcie_init_phy(struct imx_pcie *imx_pcie)
-{
-	regmap_update_bits(imx_pcie->iomuxc_gpr, IOMUXC_GPR12, IMX7D_GPR12_PCIE_PHY_REFCLK_SEL, 0);
-
-	return 0;
-}
-
 static int imx_pcie_init_phy(struct imx_pcie *imx_pcie)
 {
 	regmap_update_bits(imx_pcie->iomuxc_gpr, IOMUXC_GPR12,
@@ -576,7 +592,7 @@ static int imx_pcie_attach_pd(struct device *dev)
 			DL_FLAG_PM_RUNTIME |
 			DL_FLAG_RPM_ACTIVE);
 	if (!link) {
-		dev_err(dev, "Failed to add device_link to pcie pd.\n");
+		dev_err(dev, "Failed to add device_link to pcie pd\n");
 		return -EINVAL;
 	}
 
@@ -589,7 +605,7 @@ static int imx_pcie_attach_pd(struct device *dev)
 			DL_FLAG_PM_RUNTIME |
 			DL_FLAG_RPM_ACTIVE);
 	if (!link) {
-		dev_err(dev, "Failed to add device_link to pcie_phy pd.\n");
+		dev_err(dev, "Failed to add device_link to pcie_phy pd\n");
 		return -EINVAL;
 	}
 
@@ -598,10 +614,9 @@ static int imx_pcie_attach_pd(struct device *dev)
 
 static int imx6sx_pcie_enable_ref_clk(struct imx_pcie *imx_pcie, bool enable)
 {
-	if (enable)
-		regmap_clear_bits(imx_pcie->iomuxc_gpr, IOMUXC_GPR12,
-				  IMX6SX_GPR12_PCIE_TEST_POWERDOWN);
-
+	regmap_update_bits(imx_pcie->iomuxc_gpr, IOMUXC_GPR12,
+			   IMX6SX_GPR12_PCIE_TEST_POWERDOWN,
+			   enable ? 0 : IMX6SX_GPR12_PCIE_TEST_POWERDOWN);
 	return 0;
 }
 
@@ -611,10 +626,10 @@ static int imx6q_pcie_enable_ref_clk(struct imx_pcie *imx_pcie, bool enable)
 		/* power up core phy and enable ref clock */
 		regmap_clear_bits(imx_pcie->iomuxc_gpr, IOMUXC_GPR1, IMX6Q_GPR1_PCIE_TEST_PD);
 		/*
-		 * the async reset input need ref clock to sync internally,
+		 * The async reset input need ref clock to sync internally,
 		 * when the ref clock comes after reset, internal synced
 		 * reset time is too short, cannot meet the requirement.
-		 * add one ~10us delay here.
+		 * Add a ~10us delay here.
 		 */
 		usleep_range(10, 100);
 		regmap_set_bits(imx_pcie->iomuxc_gpr, IOMUXC_GPR1, IMX6Q_GPR1_PCIE_REF_CLK_EN);
@@ -630,19 +645,20 @@ static int imx8mm_pcie_enable_ref_clk(struct imx_pcie *imx_pcie, bool enable)
 {
 	int offset = imx_pcie_grp_offset(imx_pcie);
 
-	if (enable) {
-		regmap_clear_bits(imx_pcie->iomuxc_gpr, offset, IMX8MQ_GPR_PCIE_CLK_REQ_OVERRIDE);
-		regmap_set_bits(imx_pcie->iomuxc_gpr, offset, IMX8MQ_GPR_PCIE_CLK_REQ_OVERRIDE_EN);
-	}
-
+	regmap_update_bits(imx_pcie->iomuxc_gpr, offset,
+			   IMX8MQ_GPR_PCIE_CLK_REQ_OVERRIDE,
+			   enable ? 0 : IMX8MQ_GPR_PCIE_CLK_REQ_OVERRIDE);
+	regmap_update_bits(imx_pcie->iomuxc_gpr, offset,
+			   IMX8MQ_GPR_PCIE_CLK_REQ_OVERRIDE_EN,
+			   enable ? IMX8MQ_GPR_PCIE_CLK_REQ_OVERRIDE_EN : 0);
 	return 0;
 }
 
 static int imx7d_pcie_enable_ref_clk(struct imx_pcie *imx_pcie, bool enable)
 {
-	if (!enable)
-		regmap_set_bits(imx_pcie->iomuxc_gpr, IOMUXC_GPR12,
-				IMX7D_GPR12_PCIE_PHY_REFCLK_SEL);
+	regmap_update_bits(imx_pcie->iomuxc_gpr, IOMUXC_GPR12,
+			   IMX7D_GPR12_PCIE_PHY_REFCLK_SEL,
+			   enable ? 0 : IMX7D_GPR12_PCIE_PHY_REFCLK_SEL);
 	return 0;
 }
 
@@ -775,6 +791,7 @@ static void imx_pcie_assert_core_reset(struct imx_pcie *imx_pcie)
 static int imx_pcie_deassert_core_reset(struct imx_pcie *imx_pcie)
 {
 	reset_control_deassert(imx_pcie->pciephy_reset);
+	reset_control_deassert(imx_pcie->apps_reset);
 
 	if (imx_pcie->drvdata->core_reset)
 		imx_pcie->drvdata->core_reset(imx_pcie, false);
@@ -884,6 +901,7 @@ static int imx_pcie_start_link(struct dw_pcie *pci)
 
 		if (imx_pcie->drvdata->flags &
 		    IMX_PCIE_FLAG_IMX_SPEED_CHANGE) {
+
 			/*
 			 * On i.MX7, DIRECT_SPEED_CHANGE behaves differently
 			 * from i.MX6 family when no link speed transition
@@ -892,7 +910,6 @@ static int imx_pcie_start_link(struct dw_pcie *pci)
 			 * which will cause the following code to report false
 			 * failure.
 			 */
-
 			ret = imx_pcie_wait_for_speed_change(imx_pcie);
 			if (ret) {
 				dev_err(dev, "Failed to bring link up!\n");
@@ -908,13 +925,11 @@ static int imx_pcie_start_link(struct dw_pcie *pci)
 		dev_info(dev, "Link: Only Gen1 is enabled\n");
 	}
 
-	imx_pcie->link_is_up = true;
 	tmp = dw_pcie_readw_dbi(pci, offset + PCI_EXP_LNKSTA);
 	dev_info(dev, "Link up, Gen%i\n", tmp & PCI_EXP_LNKSTA_CLS);
 	return 0;
 
 err_reset_phy:
-	imx_pcie->link_is_up = false;
 	dev_dbg(dev, "PHY DEBUG_R0=0x%08x DEBUG_R1=0x%08x\n",
 		dw_pcie_readl_dbi(pci, PCIE_PORT_DEBUG0),
 		dw_pcie_readl_dbi(pci, PCIE_PORT_DEBUG1));
@@ -930,6 +945,184 @@ static void imx_pcie_stop_link(struct dw_pcie *pci)
 	imx_pcie_ltssm_disable(dev);
 }
 
+static int imx_pcie_add_lut(struct imx_pcie *imx_pcie, u16 rid, u8 sid)
+{
+	struct dw_pcie *pci = imx_pcie->pci;
+	struct device *dev = pci->dev;
+	u32 data1, data2;
+	int free = -1;
+	int i;
+
+	if (sid >= 64) {
+		dev_err(dev, "Invalid SID for index %d\n", sid);
+		return -EINVAL;
+	}
+
+	guard(mutex)(&imx_pcie->lock);
+
+	/*
+	 * Iterate through all LUT entries to check for duplicate RID and
+	 * identify the first available entry. Configure this available entry
+	 * immediately after verification to avoid rescanning it.
+	 */
+	for (i = 0; i < IMX95_MAX_LUT; i++) {
+		regmap_write(imx_pcie->iomuxc_gpr,
+			     IMX95_PE0_LUT_ACSCTRL, IMX95_PEO_LUT_RWA | i);
+		regmap_read(imx_pcie->iomuxc_gpr, IMX95_PE0_LUT_DATA1, &data1);
+
+		if (!(data1 & IMX95_PE0_LUT_VLD)) {
+			if (free < 0)
+				free = i;
+			continue;
+		}
+
+		regmap_read(imx_pcie->iomuxc_gpr, IMX95_PE0_LUT_DATA2, &data2);
+
+		/* Do not add duplicate RID */
+		if (rid == FIELD_GET(IMX95_PE0_LUT_REQID, data2)) {
+			dev_warn(dev, "Existing LUT entry available for RID (%d)", rid);
+			return 0;
+		}
+	}
+
+	if (free < 0) {
+		dev_err(dev, "LUT entry is not available\n");
+		return -ENOSPC;
+	}
+
+	data1 = FIELD_PREP(IMX95_PE0_LUT_DAC_ID, 0);
+	data1 |= FIELD_PREP(IMX95_PE0_LUT_STREAM_ID, sid);
+	data1 |= IMX95_PE0_LUT_VLD;
+	regmap_write(imx_pcie->iomuxc_gpr, IMX95_PE0_LUT_DATA1, data1);
+
+	data2 = IMX95_PE0_LUT_MASK; /* Match all bits of RID */
+	data2 |= FIELD_PREP(IMX95_PE0_LUT_REQID, rid);
+	regmap_write(imx_pcie->iomuxc_gpr, IMX95_PE0_LUT_DATA2, data2);
+
+	regmap_write(imx_pcie->iomuxc_gpr, IMX95_PE0_LUT_ACSCTRL, free);
+
+	return 0;
+}
+
+static void imx_pcie_remove_lut(struct imx_pcie *imx_pcie, u16 rid)
+{
+	u32 data2;
+	int i;
+
+	guard(mutex)(&imx_pcie->lock);
+
+	for (i = 0; i < IMX95_MAX_LUT; i++) {
+		regmap_write(imx_pcie->iomuxc_gpr,
+			     IMX95_PE0_LUT_ACSCTRL, IMX95_PEO_LUT_RWA | i);
+		regmap_read(imx_pcie->iomuxc_gpr, IMX95_PE0_LUT_DATA2, &data2);
+		if (FIELD_GET(IMX95_PE0_LUT_REQID, data2) == rid) {
+			regmap_write(imx_pcie->iomuxc_gpr,
+				     IMX95_PE0_LUT_DATA1, 0);
+			regmap_write(imx_pcie->iomuxc_gpr,
+				     IMX95_PE0_LUT_DATA2, 0);
+			regmap_write(imx_pcie->iomuxc_gpr,
+				     IMX95_PE0_LUT_ACSCTRL, i);
+
+			break;
+		}
+	}
+}
+
+static int imx_pcie_enable_device(struct pci_host_bridge *bridge,
+				  struct pci_dev *pdev)
+{
+	struct imx_pcie *imx_pcie = to_imx_pcie(to_dw_pcie_from_pp(bridge->sysdata));
+	u32 sid_i, sid_m, rid = pci_dev_id(pdev);
+	struct device_node *target;
+	struct device *dev;
+	int err_i, err_m;
+	u32 sid = 0;
+
+	dev = imx_pcie->pci->dev;
+
+	target = NULL;
+	err_i = of_map_id(dev->of_node, rid, "iommu-map", "iommu-map-mask",
+			  &target, &sid_i);
+	if (target) {
+		of_node_put(target);
+	} else {
+		/*
+		 * "target == NULL && err_i == 0" means RID out of map range.
+		 * Use 1:1 map RID to streamID. Hardware can't support this
+		 * because the streamID is only 6 bits
+		 */
+		err_i = -EINVAL;
+	}
+
+	target = NULL;
+	err_m = of_map_id(dev->of_node, rid, "msi-map", "msi-map-mask",
+			  &target, &sid_m);
+
+	/*
+	 *   err_m      target
+	 *	0	NULL		RID out of range. Use 1:1 map RID to
+	 *				streamID, Current hardware can't
+	 *				support it, so return -EINVAL.
+	 *      != 0    NULL		msi-map does not exist, use built-in MSI
+	 *	0	!= NULL		Get correct streamID from RID
+	 *	!= 0	!= NULL		Invalid combination
+	 */
+	if (!err_m && !target)
+		return -EINVAL;
+	else if (target)
+		of_node_put(target); /* Find streamID map entry for RID in msi-map */
+
+	/*
+	 * msi-map        iommu-map
+	 *   N                N            DWC MSI Ctrl
+	 *   Y                Y            ITS + SMMU, require the same SID
+	 *   Y                N            ITS
+	 *   N                Y            DWC MSI Ctrl + SMMU
+	 */
+	if (err_i && err_m)
+		return 0;
+
+	if (!err_i && !err_m) {
+		/*
+		 *	    Glue Layer
+		 *          <==========>
+		 * ┌─────┐                  ┌──────────┐
+		 * │ LUT │ 6-bit streamID   │          │
+		 * │     │─────────────────►│  MSI     │
+		 * └─────┘   2-bit ctrl ID  │          │
+		 *             ┌───────────►│          │
+		 *  (i.MX95)   │            │          │
+		 *  00 PCIe0   │            │          │
+		 *  01 ENETC   │            │          │
+		 *  10 PCIe1   │            │          │
+		 *             │            └──────────┘
+		 * The MSI glue layer auto adds 2 bits controller ID ahead of
+		 * streamID, so mask these 2 bits to get streamID. The
+		 * IOMMU glue layer doesn't do that.
+		 */
+		if (sid_i != (sid_m & IMX95_SID_MASK)) {
+			dev_err(dev, "iommu-map and msi-map entries mismatch!\n");
+			return -EINVAL;
+		}
+	}
+
+	if (!err_i)
+		sid = sid_i;
+	else if (!err_m)
+		sid = sid_m & IMX95_SID_MASK;
+
+	return imx_pcie_add_lut(imx_pcie, rid, sid);
+}
+
+static void imx_pcie_disable_device(struct pci_host_bridge *bridge,
+				    struct pci_dev *pdev)
+{
+	struct imx_pcie *imx_pcie;
+
+	imx_pcie = to_imx_pcie(to_dw_pcie_from_pp(bridge->sysdata));
+	imx_pcie_remove_lut(imx_pcie, pci_dev_id(pdev));
+}
+
 static int imx_pcie_host_init(struct dw_pcie_rp *pp)
 {
 	struct dw_pcie *pci = to_dw_pcie_from_pp(pp);
@@ -946,6 +1139,11 @@ static int imx_pcie_host_init(struct dw_pcie_rp *pp)
 		}
 	}
 
+	if (pp->bridge && imx_check_flag(imx_pcie, IMX_PCIE_FLAG_HAS_LUT)) {
+		pp->bridge->enable_device = imx_pcie_enable_device;
+		pp->bridge->disable_device = imx_pcie_disable_device;
+	}
+
 	imx_pcie_assert_core_reset(imx_pcie);
 
 	if (imx_pcie->drvdata->init_phy)
@@ -966,7 +1164,9 @@ static int imx_pcie_host_init(struct dw_pcie_rp *pp)
 			goto err_clk_disable;
 		}
 
-		ret = phy_set_mode_ext(imx_pcie->phy, PHY_MODE_PCIE, PHY_MODE_PCIE_RC);
+		ret = phy_set_mode_ext(imx_pcie->phy, PHY_MODE_PCIE,
+				       imx_pcie->drvdata->mode == DW_PCIE_EP_TYPE ?
+						PHY_MODE_PCIE_EP : PHY_MODE_PCIE_RC);
 		if (ret) {
 			dev_err(dev, "unable to set PCIe PHY mode\n");
 			goto err_phy_exit;
@@ -1033,9 +1233,31 @@ static u64 imx_pcie_cpu_addr_fixup(struct dw_pcie *pcie, u64 cpu_addr)
 	return cpu_addr - entry->offset;
 }
 
+/*
+ * In old DWC implementations, PCIE_ATU_INHIBIT_PAYLOAD in iATU Ctrl2
+ * register is reserved, so the generic DWC implementation of sending the
+ * PME_Turn_Off message using a dummy MMIO write cannot be used.
+ */
+static void imx_pcie_pme_turn_off(struct dw_pcie_rp *pp)
+{
+	struct dw_pcie *pci = to_dw_pcie_from_pp(pp);
+	struct imx_pcie *imx_pcie = to_imx_pcie(pci);
+
+	regmap_set_bits(imx_pcie->iomuxc_gpr, IOMUXC_GPR12, IMX6SX_GPR12_PCIE_PM_TURN_OFF);
+	regmap_clear_bits(imx_pcie->iomuxc_gpr, IOMUXC_GPR12, IMX6SX_GPR12_PCIE_PM_TURN_OFF);
+
+	usleep_range(PCIE_PME_TO_L2_TIMEOUT_US/10, PCIE_PME_TO_L2_TIMEOUT_US);
+}
+
 static const struct dw_pcie_host_ops imx_pcie_host_ops = {
 	.init = imx_pcie_host_init,
 	.deinit = imx_pcie_host_exit,
+	.pme_turn_off = imx_pcie_pme_turn_off,
+};
+
+static const struct dw_pcie_host_ops imx_pcie_host_dw_pme_ops = {
+	.init = imx_pcie_host_init,
+	.deinit = imx_pcie_host_exit,
 };
 
 static const struct dw_pcie_ops dw_pcie_ops = {
@@ -1082,16 +1304,27 @@ static const struct pci_epc_features imx8m_pcie_epc_features = {
 	.align = SZ_64K,
 };
 
+static const struct pci_epc_features imx8q_pcie_epc_features = {
+	.linkup_notifier = false,
+	.msi_capable = true,
+	.msix_capable = false,
+	.bar[BAR_1] = { .type = BAR_RESERVED, },
+	.bar[BAR_3] = { .type = BAR_RESERVED, },
+	.bar[BAR_5] = { .type = BAR_RESERVED, },
+	.align = SZ_64K,
+};
+
 /*
- * BAR#	| Default BAR enable	| Default BAR Type	| Default BAR Size	| BAR Sizing Scheme
- * ================================================================================================
- * BAR0	| Enable		| 64-bit		| 1 MB			| Programmable Size
- * BAR1	| Disable		| 32-bit		| 64 KB			| Fixed Size
- *        BAR1 should be disabled if BAR0 is 64bit.
- * BAR2	| Enable		| 32-bit		| 1 MB			| Programmable Size
- * BAR3	| Enable		| 32-bit		| 64 KB			| Programmable Size
- * BAR4	| Enable		| 32-bit		| 1M			| Programmable Size
- * BAR5	| Enable		| 32-bit		| 64 KB			| Programmable Size
+ *     	| Default  | Default | Default | BAR Sizing
+ * BAR#	| Enable?  | Type    | Size    | Scheme
+ * =======================================================
+ * BAR0	| Enable   | 64-bit  |  1 MB   | Programmable Size
+ * BAR1	| Disable  | 32-bit  | 64 KB   | Fixed Size
+ *       (BAR1 should be disabled if BAR0 is 64-bit)
+ * BAR2	| Enable   | 32-bit  |  1 MB   | Programmable Size
+ * BAR3	| Enable   | 32-bit  | 64 KB   | Programmable Size
+ * BAR4	| Enable   | 32-bit  |  1 MB   | Programmable Size
+ * BAR5	| Enable   | 32-bit  | 64 KB   | Programmable Size
  */
 static const struct pci_epc_features imx95_pcie_epc_features = {
 	.msi_capable = true,
@@ -1118,7 +1351,6 @@ static int imx_add_pcie_ep(struct imx_pcie *imx_pcie,
 			   struct platform_device *pdev)
 {
 	int ret;
-	unsigned int pcie_dbi2_offset;
 	struct dw_pcie_ep *ep;
 	struct dw_pcie *pci = imx_pcie->pci;
 	struct dw_pcie_rp *pp = &pci->pp;
@@ -1128,28 +1360,6 @@ static int imx_add_pcie_ep(struct imx_pcie *imx_pcie,
 	ep = &pci->ep;
 	ep->ops = &pcie_ep_ops;
 
-	switch (imx_pcie->drvdata->variant) {
-	case IMX8MQ_EP:
-	case IMX8MM_EP:
-	case IMX8MP_EP:
-		pcie_dbi2_offset = SZ_1M;
-		break;
-	default:
-		pcie_dbi2_offset = SZ_4K;
-		break;
-	}
-
-	pci->dbi_base2 = pci->dbi_base + pcie_dbi2_offset;
-
-	/*
-	 * FIXME: Ideally, dbi2 base address should come from DT. But since only IMX95 is defining
-	 * "dbi2" in DT, "dbi_base2" is set to NULL here for that platform alone so that the DWC
-	 * core code can fetch that from DT. But once all platform DTs were fixed, this and the
-	 * above "dbi_base2" setting should be removed.
-	 */
-	if (device_property_match_string(dev, "reg-names", "dbi2") >= 0)
-		pci->dbi_base2 = NULL;
-
 	if (imx_check_flag(imx_pcie, IMX_PCIE_FLAG_SUPPORT_64BIT))
 		dma_set_mask_and_coherent(dev, DMA_BIT_MASK(64));
 
@@ -1176,43 +1386,6 @@ static int imx_add_pcie_ep(struct imx_pcie *imx_pcie,
 	return 0;
 }
 
-static void imx_pcie_pm_turnoff(struct imx_pcie *imx_pcie)
-{
-	struct device *dev = imx_pcie->pci->dev;
-
-	/* Some variants have a turnoff reset in DT */
-	if (imx_pcie->turnoff_reset) {
-		reset_control_assert(imx_pcie->turnoff_reset);
-		reset_control_deassert(imx_pcie->turnoff_reset);
-		goto pm_turnoff_sleep;
-	}
-
-	/* Others poke directly at IOMUXC registers */
-	switch (imx_pcie->drvdata->variant) {
-	case IMX6SX:
-	case IMX6QP:
-		regmap_update_bits(imx_pcie->iomuxc_gpr, IOMUXC_GPR12,
-				IMX6SX_GPR12_PCIE_PM_TURN_OFF,
-				IMX6SX_GPR12_PCIE_PM_TURN_OFF);
-		regmap_update_bits(imx_pcie->iomuxc_gpr, IOMUXC_GPR12,
-				IMX6SX_GPR12_PCIE_PM_TURN_OFF, 0);
-		break;
-	default:
-		dev_err(dev, "PME_Turn_Off not implemented\n");
-		return;
-	}
-
-	/*
-	 * Components with an upstream port must respond to
-	 * PME_Turn_Off with PME_TO_Ack but we can't check.
-	 *
-	 * The standard recommends a 1-10ms timeout after which to
-	 * proceed anyway as if acks were received.
-	 */
-pm_turnoff_sleep:
-	usleep_range(1000, 10000);
-}
-
 static void imx_pcie_msi_save_restore(struct imx_pcie *imx_pcie, bool save)
 {
 	u8 offset;
@@ -1236,7 +1409,6 @@ static void imx_pcie_msi_save_restore(struct imx_pcie *imx_pcie, bool save)
 static int imx_pcie_suspend_noirq(struct device *dev)
 {
 	struct imx_pcie *imx_pcie = dev_get_drvdata(dev);
-	struct dw_pcie_rp *pp = &imx_pcie->pci->pp;
 
 	if (!(imx_pcie->drvdata->flags & IMX_PCIE_FLAG_SUPPORTS_SUSPEND))
 		return 0;
@@ -1251,9 +1423,7 @@ static int imx_pcie_suspend_noirq(struct device *dev)
 		imx_pcie_assert_core_reset(imx_pcie);
 		imx_pcie->drvdata->enable_ref_clk(imx_pcie, false);
 	} else {
-		imx_pcie_pm_turnoff(imx_pcie);
-		imx_pcie_stop_link(imx_pcie->pci);
-		imx_pcie_host_exit(pp);
+		return dw_pcie_suspend_noirq(imx_pcie->pci);
 	}
 
 	return 0;
@@ -1263,7 +1433,6 @@ static int imx_pcie_resume_noirq(struct device *dev)
 {
 	int ret;
 	struct imx_pcie *imx_pcie = dev_get_drvdata(dev);
-	struct dw_pcie_rp *pp = &imx_pcie->pci->pp;
 
 	if (!(imx_pcie->drvdata->flags & IMX_PCIE_FLAG_SUPPORTS_SUSPEND))
 		return 0;
@@ -1275,6 +1444,7 @@ static int imx_pcie_resume_noirq(struct device *dev)
 		ret = imx_pcie_deassert_core_reset(imx_pcie);
 		if (ret)
 			return ret;
+
 		/*
 		 * Using PCIE_TEST_PD seems to disable MSI and powers down the
 		 * root complex. This is why we have to setup the rc again and
@@ -1283,17 +1453,12 @@ static int imx_pcie_resume_noirq(struct device *dev)
 		ret = dw_pcie_setup_rc(&imx_pcie->pci->pp);
 		if (ret)
 			return ret;
-		imx_pcie_msi_save_restore(imx_pcie, false);
 	} else {
-		ret = imx_pcie_host_init(pp);
+		ret = dw_pcie_resume_noirq(imx_pcie->pci);
 		if (ret)
 			return ret;
-		imx_pcie_msi_save_restore(imx_pcie, false);
-		dw_pcie_setup_rc(pp);
-
-		if (imx_pcie->link_is_up)
-			imx_pcie_start_link(imx_pcie->pci);
 	}
+	imx_pcie_msi_save_restore(imx_pcie, false);
 
 	return 0;
 }
@@ -1311,9 +1476,8 @@ static int imx_pcie_probe(struct platform_device *pdev)
 	struct device_node *np;
 	struct resource *dbi_base;
 	struct device_node *node = dev->of_node;
-	int ret;
+	int i, ret, req_cnt;
 	u16 val;
-	int i;
 
 	imx_pcie = devm_kzalloc(dev, sizeof(*imx_pcie), GFP_KERNEL);
 	if (!imx_pcie)
@@ -1325,11 +1489,17 @@ static int imx_pcie_probe(struct platform_device *pdev)
 
 	pci->dev = dev;
 	pci->ops = &dw_pcie_ops;
-	pci->pp.ops = &imx_pcie_host_ops;
 
 	imx_pcie->pci = pci;
 	imx_pcie->drvdata = of_device_get_match_data(dev);
 
+	mutex_init(&imx_pcie->lock);
+
+	if (imx_pcie->drvdata->ops)
+		pci->pp.ops = imx_pcie->drvdata->ops;
+	else
+		pci->pp.ops = &imx_pcie_host_dw_pme_ops;
+
 	/* Find the PHY if one is defined, only imx7d uses it */
 	np = of_parse_phandle(node, "fsl,imx7d-pcie-phy", 0);
 	if (np) {
@@ -1363,9 +1533,13 @@ static int imx_pcie_probe(struct platform_device *pdev)
 		imx_pcie->clks[i].id = imx_pcie->drvdata->clk_names[i];
 
 	/* Fetch clocks */
-	ret = devm_clk_bulk_get(dev, imx_pcie->drvdata->clks_cnt, imx_pcie->clks);
+	req_cnt = imx_pcie->drvdata->clks_cnt - imx_pcie->drvdata->clks_optional_cnt;
+	ret = devm_clk_bulk_get(dev, req_cnt, imx_pcie->clks);
 	if (ret)
 		return ret;
+	imx_pcie->clks[req_cnt].clk = devm_clk_get_optional(dev, "ref");
+	if (IS_ERR(imx_pcie->clks[req_cnt].clk))
+		return PTR_ERR(imx_pcie->clks[req_cnt].clk);
 
 	if (imx_check_flag(imx_pcie, IMX_PCIE_FLAG_HAS_PHYDRV)) {
 		imx_pcie->phy = devm_phy_get(dev, "pcie-phy");
@@ -1391,7 +1565,6 @@ static int imx_pcie_probe(struct platform_device *pdev)
 	switch (imx_pcie->drvdata->variant) {
 	case IMX8MQ:
 	case IMX8MQ_EP:
-	case IMX7D:
 		if (dbi_base->start == IMX8MQ_PCIE2_BASE_ADDR)
 			imx_pcie->controller_id = 1;
 		break;
@@ -1399,13 +1572,6 @@ static int imx_pcie_probe(struct platform_device *pdev)
 		break;
 	}
 
-	/* Grab turnoff reset */
-	imx_pcie->turnoff_reset = devm_reset_control_get_optional_exclusive(dev, "turnoff");
-	if (IS_ERR(imx_pcie->turnoff_reset)) {
-		dev_err(dev, "Failed to get TURNOFF reset control\n");
-		return PTR_ERR(imx_pcie->turnoff_reset);
-	}
-
 	if (imx_pcie->drvdata->gpr) {
 	/* Grab GPR config register range */
 		imx_pcie->iomuxc_gpr =
@@ -1484,6 +1650,7 @@ static int imx_pcie_probe(struct platform_device *pdev)
 		if (ret < 0)
 			return ret;
 	} else {
+		pci->pp.use_atu_msg = true;
 		ret = dw_pcie_host_init(&pci->pp);
 		if (ret < 0)
 			return ret;
@@ -1513,6 +1680,7 @@ static const char * const imx8mm_clks[] = {"pcie_bus", "pcie", "pcie_aux"};
 static const char * const imx8mq_clks[] = {"pcie_bus", "pcie", "pcie_phy", "pcie_aux"};
 static const char * const imx6sx_clks[] = {"pcie_bus", "pcie", "pcie_phy", "pcie_inbound_axi"};
 static const char * const imx8q_clks[] = {"mstr", "slv", "dbi"};
+static const char * const imx95_clks[] = {"pcie_bus", "pcie", "pcie_phy", "pcie_aux", "ref"};
 
 static const struct imx_pcie_drvdata drvdata[] = {
 	[IMX6Q] = {
@@ -1548,6 +1716,7 @@ static const struct imx_pcie_drvdata drvdata[] = {
 		.init_phy = imx6sx_pcie_init_phy,
 		.enable_ref_clk = imx6sx_pcie_enable_ref_clk,
 		.core_reset = imx6sx_pcie_core_reset,
+		.ops = &imx_pcie_host_ops,
 	},
 	[IMX6QP] = {
 		.variant = IMX6QP,
@@ -1565,6 +1734,7 @@ static const struct imx_pcie_drvdata drvdata[] = {
 		.init_phy = imx_pcie_init_phy,
 		.enable_ref_clk = imx6q_pcie_enable_ref_clk,
 		.core_reset = imx6qp_pcie_core_reset,
+		.ops = &imx_pcie_host_ops,
 	},
 	[IMX7D] = {
 		.variant = IMX7D,
@@ -1576,14 +1746,14 @@ static const struct imx_pcie_drvdata drvdata[] = {
 		.clks_cnt = ARRAY_SIZE(imx6q_clks),
 		.mode_off[0] = IOMUXC_GPR12,
 		.mode_mask[0] = IMX6Q_GPR12_DEVICE_TYPE,
-		.init_phy = imx7d_pcie_init_phy,
 		.enable_ref_clk = imx7d_pcie_enable_ref_clk,
 		.core_reset = imx7d_pcie_core_reset,
 	},
 	[IMX8MQ] = {
 		.variant = IMX8MQ,
 		.flags = IMX_PCIE_FLAG_HAS_APP_RESET |
-			 IMX_PCIE_FLAG_HAS_PHY_RESET,
+			 IMX_PCIE_FLAG_HAS_PHY_RESET |
+			 IMX_PCIE_FLAG_SUPPORTS_SUSPEND,
 		.gpr = "fsl,imx8mq-iomuxc-gpr",
 		.clk_names = imx8mq_clks,
 		.clks_cnt = ARRAY_SIZE(imx8mq_clks),
@@ -1621,15 +1791,19 @@ static const struct imx_pcie_drvdata drvdata[] = {
 	[IMX8Q] = {
 		.variant = IMX8Q,
 		.flags = IMX_PCIE_FLAG_HAS_PHYDRV |
-			 IMX_PCIE_FLAG_CPU_ADDR_FIXUP,
+			 IMX_PCIE_FLAG_CPU_ADDR_FIXUP |
+			 IMX_PCIE_FLAG_SUPPORTS_SUSPEND,
 		.clk_names = imx8q_clks,
 		.clks_cnt = ARRAY_SIZE(imx8q_clks),
 	},
 	[IMX95] = {
 		.variant = IMX95,
-		.flags = IMX_PCIE_FLAG_HAS_SERDES,
-		.clk_names = imx8mq_clks,
-		.clks_cnt = ARRAY_SIZE(imx8mq_clks),
+		.flags = IMX_PCIE_FLAG_HAS_SERDES |
+			 IMX_PCIE_FLAG_HAS_LUT |
+			 IMX_PCIE_FLAG_SUPPORTS_SUSPEND,
+		.clk_names = imx95_clks,
+		.clks_cnt = ARRAY_SIZE(imx95_clks),
+		.clks_optional_cnt = 1,
 		.ltssm_off = IMX95_PE0_GEN_CTRL_3,
 		.ltssm_mask = IMX95_PCIE_LTSSM_EN,
 		.mode_off[0]  = IMX95_PE0_GEN_CTRL_1,
@@ -1678,6 +1852,14 @@ static const struct imx_pcie_drvdata drvdata[] = {
 		.epc_features = &imx8m_pcie_epc_features,
 		.enable_ref_clk = imx8mm_pcie_enable_ref_clk,
 	},
+	[IMX8Q_EP] = {
+		.variant = IMX8Q_EP,
+		.flags = IMX_PCIE_FLAG_HAS_PHYDRV,
+		.mode = DW_PCIE_EP_TYPE,
+		.epc_features = &imx8q_pcie_epc_features,
+		.clk_names = imx8q_clks,
+		.clks_cnt = ARRAY_SIZE(imx8q_clks),
+	},
 	[IMX95_EP] = {
 		.variant = IMX95_EP,
 		.flags = IMX_PCIE_FLAG_HAS_SERDES |
@@ -1707,6 +1889,7 @@ static const struct of_device_id imx_pcie_of_match[] = {
 	{ .compatible = "fsl,imx8mq-pcie-ep", .data = &drvdata[IMX8MQ_EP], },
 	{ .compatible = "fsl,imx8mm-pcie-ep", .data = &drvdata[IMX8MM_EP], },
 	{ .compatible = "fsl,imx8mp-pcie-ep", .data = &drvdata[IMX8MP_EP], },
+	{ .compatible = "fsl,imx8q-pcie-ep", .data = &drvdata[IMX8Q_EP], },
 	{ .compatible = "fsl,imx95-pcie-ep", .data = &drvdata[IMX95_EP], },
 	{},
 };
diff --git a/drivers/pci/controller/dwc/pci-layerscape.c b/drivers/pci/controller/dwc/pci-layerscape.c
index ee6f525681337..239a05b36e8e6 100644
--- a/drivers/pci/controller/dwc/pci-layerscape.c
+++ b/drivers/pci/controller/dwc/pci-layerscape.c
@@ -329,7 +329,6 @@ static int ls_pcie_probe(struct platform_device *pdev)
 	struct ls_pcie *pcie;
 	struct resource *dbi_base;
 	u32 index[2];
-	int ret;
 
 	pcie = devm_kzalloc(dev, sizeof(*pcie), GFP_KERNEL);
 	if (!pcie)
@@ -355,16 +354,15 @@ static int ls_pcie_probe(struct platform_device *pdev)
 	pcie->pf_lut_base = pci->dbi_base + pcie->drvdata->pf_lut_off;
 
 	if (pcie->drvdata->scfg_support) {
-		pcie->scfg = syscon_regmap_lookup_by_phandle(dev->of_node, "fsl,pcie-scfg");
+		pcie->scfg =
+			syscon_regmap_lookup_by_phandle_args(dev->of_node,
+							     "fsl,pcie-scfg", 2,
+							     index);
 		if (IS_ERR(pcie->scfg)) {
 			dev_err(dev, "No syscfg phandle specified\n");
 			return PTR_ERR(pcie->scfg);
 		}
 
-		ret = of_property_read_u32_array(dev->of_node, "fsl,pcie-scfg", index, 2);
-		if (ret)
-			return ret;
-
 		pcie->index = index[1];
 	}
 
diff --git a/drivers/pci/controller/dwc/pcie-artpec6.c b/drivers/pci/controller/dwc/pcie-artpec6.c
index f8e7283dacd47..234c8cbcae3af 100644
--- a/drivers/pci/controller/dwc/pcie-artpec6.c
+++ b/drivers/pci/controller/dwc/pcie-artpec6.c
@@ -369,9 +369,22 @@ static int artpec6_pcie_raise_irq(struct dw_pcie_ep *ep, u8 func_no,
 	return 0;
 }
 
+static const struct pci_epc_features artpec6_pcie_epc_features = {
+	.linkup_notifier = false,
+	.msi_capable = true,
+	.msix_capable = false,
+};
+
+static const struct pci_epc_features *
+artpec6_pcie_get_features(struct dw_pcie_ep *ep)
+{
+	return &artpec6_pcie_epc_features;
+}
+
 static const struct dw_pcie_ep_ops pcie_ep_ops = {
 	.init = artpec6_pcie_ep_init,
 	.raise_irq = artpec6_pcie_raise_irq,
+	.get_features = artpec6_pcie_get_features,
 };
 
 static int artpec6_pcie_probe(struct platform_device *pdev)
diff --git a/drivers/pci/controller/dwc/pcie-designware-ep.c b/drivers/pci/controller/dwc/pcie-designware-ep.c
index f3ac7d46a855b..8e07d432e74f2 100644
--- a/drivers/pci/controller/dwc/pcie-designware-ep.c
+++ b/drivers/pci/controller/dwc/pcie-designware-ep.c
@@ -128,7 +128,8 @@ static int dw_pcie_ep_write_header(struct pci_epc *epc, u8 func_no, u8 vfunc_no,
 }
 
 static int dw_pcie_ep_inbound_atu(struct dw_pcie_ep *ep, u8 func_no, int type,
-				  dma_addr_t cpu_addr, enum pci_barno bar)
+				  dma_addr_t cpu_addr, enum pci_barno bar,
+				  size_t size)
 {
 	int ret;
 	u32 free_win;
@@ -145,7 +146,7 @@ static int dw_pcie_ep_inbound_atu(struct dw_pcie_ep *ep, u8 func_no, int type,
 	}
 
 	ret = dw_pcie_prog_ep_inbound_atu(pci, func_no, free_win, type,
-					  cpu_addr, bar);
+					  cpu_addr, bar, size);
 	if (ret < 0) {
 		dev_err(pci->dev, "Failed to program IB window\n");
 		return ret;
@@ -222,19 +223,30 @@ static int dw_pcie_ep_set_bar(struct pci_epc *epc, u8 func_no, u8 vfunc_no,
 	if ((flags & PCI_BASE_ADDRESS_MEM_TYPE_64) && (bar & 1))
 		return -EINVAL;
 
-	reg = PCI_BASE_ADDRESS_0 + (4 * bar);
-
-	if (!(flags & PCI_BASE_ADDRESS_SPACE))
-		type = PCIE_ATU_TYPE_MEM;
-	else
-		type = PCIE_ATU_TYPE_IO;
+	/*
+	 * Certain EPF drivers dynamically change the physical address of a BAR
+	 * (i.e. they call set_bar() twice, without ever calling clear_bar(), as
+	 * calling clear_bar() would clear the BAR's PCI address assigned by the
+	 * host).
+	 */
+	if (ep->epf_bar[bar]) {
+		/*
+		 * We can only dynamically change a BAR if the new BAR size and
+		 * BAR flags do not differ from the existing configuration.
+		 */
+		if (ep->epf_bar[bar]->barno != bar ||
+		    ep->epf_bar[bar]->size != size ||
+		    ep->epf_bar[bar]->flags != flags)
+			return -EINVAL;
 
-	ret = dw_pcie_ep_inbound_atu(ep, func_no, type, epf_bar->phys_addr, bar);
-	if (ret)
-		return ret;
+		/*
+		 * When dynamically changing a BAR, skip writing the BAR reg, as
+		 * that would clear the BAR's PCI address assigned by the host.
+		 */
+		goto config_atu;
+	}
 
-	if (ep->epf_bar[bar])
-		return 0;
+	reg = PCI_BASE_ADDRESS_0 + (4 * bar);
 
 	dw_pcie_dbi_ro_wr_en(pci);
 
@@ -246,9 +258,21 @@ static int dw_pcie_ep_set_bar(struct pci_epc *epc, u8 func_no, u8 vfunc_no,
 		dw_pcie_ep_writel_dbi(ep, func_no, reg + 4, 0);
 	}
 
-	ep->epf_bar[bar] = epf_bar;
 	dw_pcie_dbi_ro_wr_dis(pci);
 
+config_atu:
+	if (!(flags & PCI_BASE_ADDRESS_SPACE))
+		type = PCIE_ATU_TYPE_MEM;
+	else
+		type = PCIE_ATU_TYPE_IO;
+
+	ret = dw_pcie_ep_inbound_atu(ep, func_no, type, epf_bar->phys_addr, bar,
+				     size);
+	if (ret)
+		return ret;
+
+	ep->epf_bar[bar] = epf_bar;
+
 	return 0;
 }
 
diff --git a/drivers/pci/controller/dwc/pcie-designware-host.c b/drivers/pci/controller/dwc/pcie-designware-host.c
index d2291c3ceb8be..ffaded8f2df7b 100644
--- a/drivers/pci/controller/dwc/pcie-designware-host.c
+++ b/drivers/pci/controller/dwc/pcie-designware-host.c
@@ -436,18 +436,18 @@ int dw_pcie_host_init(struct dw_pcie_rp *pp)
 		return ret;
 
 	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "config");
-	if (res) {
-		pp->cfg0_size = resource_size(res);
-		pp->cfg0_base = res->start;
-
-		pp->va_cfg0_base = devm_pci_remap_cfg_resource(dev, res);
-		if (IS_ERR(pp->va_cfg0_base))
-			return PTR_ERR(pp->va_cfg0_base);
-	} else {
-		dev_err(dev, "Missing *config* reg space\n");
+	if (!res) {
+		dev_err(dev, "Missing \"config\" reg space\n");
 		return -ENODEV;
 	}
 
+	pp->cfg0_size = resource_size(res);
+	pp->cfg0_base = res->start;
+
+	pp->va_cfg0_base = devm_pci_remap_cfg_resource(dev, res);
+	if (IS_ERR(pp->va_cfg0_base))
+		return PTR_ERR(pp->va_cfg0_base);
+
 	bridge = devm_pci_alloc_host_bridge(dev, 0);
 	if (!bridge)
 		return -ENOMEM;
@@ -530,8 +530,14 @@ int dw_pcie_host_init(struct dw_pcie_rp *pp)
 			goto err_remove_edma;
 	}
 
-	/* Ignore errors, the link may come up later */
-	dw_pcie_wait_for_link(pci);
+	/*
+	 * Note: Skip the link up delay only when a Link Up IRQ is present.
+	 * If there is no Link Up IRQ, we should not bypass the delay
+	 * because that would require users to manually rescan for devices.
+	 */
+	if (!pp->use_linkup_irq)
+		/* Ignore errors, the link may come up later */
+		dw_pcie_wait_for_link(pci);
 
 	bridge->sysdata = pp;
 
@@ -918,7 +924,7 @@ int dw_pcie_suspend_noirq(struct dw_pcie *pci)
 {
 	u8 offset = dw_pcie_find_capability(pci, PCI_CAP_ID_EXP);
 	u32 val;
-	int ret = 0;
+	int ret;
 
 	/*
 	 * If L1SS is supported, then do not put the link into L2 as some
@@ -927,25 +933,33 @@ int dw_pcie_suspend_noirq(struct dw_pcie *pci)
 	if (dw_pcie_readw_dbi(pci, offset + PCI_EXP_LNKCTL) & PCI_EXP_LNKCTL_ASPM_L1)
 		return 0;
 
-	if (dw_pcie_get_ltssm(pci) <= DW_PCIE_LTSSM_DETECT_ACT)
-		return 0;
-
-	if (pci->pp.ops->pme_turn_off)
+	if (pci->pp.ops->pme_turn_off) {
 		pci->pp.ops->pme_turn_off(&pci->pp);
-	else
+	} else {
 		ret = dw_pcie_pme_turn_off(pci);
+		if (ret)
+			return ret;
+	}
 
-	if (ret)
-		return ret;
-
-	ret = read_poll_timeout(dw_pcie_get_ltssm, val, val == DW_PCIE_LTSSM_L2_IDLE,
+	ret = read_poll_timeout(dw_pcie_get_ltssm, val,
+				val == DW_PCIE_LTSSM_L2_IDLE ||
+				val <= DW_PCIE_LTSSM_DETECT_WAIT,
 				PCIE_PME_TO_L2_TIMEOUT_US/10,
 				PCIE_PME_TO_L2_TIMEOUT_US, false, pci);
 	if (ret) {
+		/* Only log message when LTSSM isn't in DETECT or POLL */
 		dev_err(pci->dev, "Timeout waiting for L2 entry! LTSSM: 0x%x\n", val);
 		return ret;
 	}
 
+	/*
+	 * Per PCIe r6.0, sec 5.3.3.2.1, software should wait at least
+	 * 100ns after L2/L3 Ready before turning off refclock and
+	 * main power. This is harmless when no endpoint is connected.
+	 */
+	udelay(1);
+
+	dw_pcie_stop_link(pci);
 	if (pci->pp.ops->deinit)
 		pci->pp.ops->deinit(&pci->pp);
 
diff --git a/drivers/pci/controller/dwc/pcie-designware.c b/drivers/pci/controller/dwc/pcie-designware.c
index 6d6cbc8b5b2c6..145e7f579072c 100644
--- a/drivers/pci/controller/dwc/pcie-designware.c
+++ b/drivers/pci/controller/dwc/pcie-designware.c
@@ -597,11 +597,12 @@ int dw_pcie_prog_inbound_atu(struct dw_pcie *pci, int index, int type,
 }
 
 int dw_pcie_prog_ep_inbound_atu(struct dw_pcie *pci, u8 func_no, int index,
-				int type, u64 cpu_addr, u8 bar)
+				int type, u64 cpu_addr, u8 bar, size_t size)
 {
 	u32 retries, val;
 
-	if (!IS_ALIGNED(cpu_addr, pci->region_align))
+	if (!IS_ALIGNED(cpu_addr, pci->region_align) ||
+	    !IS_ALIGNED(cpu_addr, size))
 		return -EINVAL;
 
 	dw_pcie_writel_atu_ib(pci, index, PCIE_ATU_LOWER_TARGET,
@@ -970,7 +971,7 @@ static int dw_pcie_edma_irq_verify(struct dw_pcie *pci)
 {
 	struct platform_device *pdev = to_platform_device(pci->dev);
 	u16 ch_cnt = pci->edma.ll_wr_cnt + pci->edma.ll_rd_cnt;
-	char name[6];
+	char name[15];
 	int ret;
 
 	if (pci->edma.nr_irqs == 1)
diff --git a/drivers/pci/controller/dwc/pcie-designware.h b/drivers/pci/controller/dwc/pcie-designware.h
index 347ab74ac35aa..501d9ddfea163 100644
--- a/drivers/pci/controller/dwc/pcie-designware.h
+++ b/drivers/pci/controller/dwc/pcie-designware.h
@@ -330,6 +330,7 @@ enum dw_pcie_ltssm {
 	/* Need to align with PCIE_PORT_DEBUG0 bits 0:5 */
 	DW_PCIE_LTSSM_DETECT_QUIET = 0x0,
 	DW_PCIE_LTSSM_DETECT_ACT = 0x1,
+	DW_PCIE_LTSSM_DETECT_WAIT = 0x6,
 	DW_PCIE_LTSSM_L0 = 0x11,
 	DW_PCIE_LTSSM_L2_IDLE = 0x15,
 
@@ -379,6 +380,7 @@ struct dw_pcie_rp {
 	bool			use_atu_msg;
 	int			msg_atu_index;
 	struct resource		*msg_res;
+	bool			use_linkup_irq;
 };
 
 struct dw_pcie_ep_ops {
@@ -491,16 +493,13 @@ int dw_pcie_prog_outbound_atu(struct dw_pcie *pci,
 int dw_pcie_prog_inbound_atu(struct dw_pcie *pci, int index, int type,
 			     u64 cpu_addr, u64 pci_addr, u64 size);
 int dw_pcie_prog_ep_inbound_atu(struct dw_pcie *pci, u8 func_no, int index,
-				int type, u64 cpu_addr, u8 bar);
+				int type, u64 cpu_addr, u8 bar, size_t size);
 void dw_pcie_disable_atu(struct dw_pcie *pci, u32 dir, int index);
 void dw_pcie_setup(struct dw_pcie *pci);
 void dw_pcie_iatu_detect(struct dw_pcie *pci);
 int dw_pcie_edma_detect(struct dw_pcie *pci);
 void dw_pcie_edma_remove(struct dw_pcie *pci);
 
-int dw_pcie_suspend_noirq(struct dw_pcie *pci);
-int dw_pcie_resume_noirq(struct dw_pcie *pci);
-
 static inline void dw_pcie_writel_dbi(struct dw_pcie *pci, u32 reg, u32 val)
 {
 	dw_pcie_write_dbi(pci, reg, 0x4, val);
@@ -678,6 +677,8 @@ static inline enum dw_pcie_ltssm dw_pcie_get_ltssm(struct dw_pcie *pci)
 }
 
 #ifdef CONFIG_PCIE_DW_HOST
+int dw_pcie_suspend_noirq(struct dw_pcie *pci);
+int dw_pcie_resume_noirq(struct dw_pcie *pci);
 irqreturn_t dw_handle_msi_irq(struct dw_pcie_rp *pp);
 int dw_pcie_setup_rc(struct dw_pcie_rp *pp);
 int dw_pcie_host_init(struct dw_pcie_rp *pp);
@@ -686,6 +687,16 @@ int dw_pcie_allocate_domains(struct dw_pcie_rp *pp);
 void __iomem *dw_pcie_own_conf_map_bus(struct pci_bus *bus, unsigned int devfn,
 				       int where);
 #else
+static inline int dw_pcie_suspend_noirq(struct dw_pcie *pci)
+{
+	return 0;
+}
+
+static inline int dw_pcie_resume_noirq(struct dw_pcie *pci)
+{
+	return 0;
+}
+
 static inline irqreturn_t dw_handle_msi_irq(struct dw_pcie_rp *pp)
 {
 	return IRQ_NONE;
diff --git a/drivers/pci/controller/dwc/pcie-dw-rockchip.c b/drivers/pci/controller/dwc/pcie-dw-rockchip.c
index 1170e1107508b..93698abff4d9c 100644
--- a/drivers/pci/controller/dwc/pcie-dw-rockchip.c
+++ b/drivers/pci/controller/dwc/pcie-dw-rockchip.c
@@ -389,6 +389,34 @@ static const struct dw_pcie_ops dw_pcie_ops = {
 	.stop_link = rockchip_pcie_stop_link,
 };
 
+static irqreturn_t rockchip_pcie_rc_sys_irq_thread(int irq, void *arg)
+{
+	struct rockchip_pcie *rockchip = arg;
+	struct dw_pcie *pci = &rockchip->pci;
+	struct dw_pcie_rp *pp = &pci->pp;
+	struct device *dev = pci->dev;
+	u32 reg, val;
+
+	reg = rockchip_pcie_readl_apb(rockchip, PCIE_CLIENT_INTR_STATUS_MISC);
+	rockchip_pcie_writel_apb(rockchip, reg, PCIE_CLIENT_INTR_STATUS_MISC);
+
+	dev_dbg(dev, "PCIE_CLIENT_INTR_STATUS_MISC: %#x\n", reg);
+	dev_dbg(dev, "LTSSM_STATUS: %#x\n", rockchip_pcie_get_ltssm(rockchip));
+
+	if (reg & PCIE_RDLH_LINK_UP_CHGED) {
+		val = rockchip_pcie_get_ltssm(rockchip);
+		if ((val & PCIE_LINKUP) == PCIE_LINKUP) {
+			dev_dbg(dev, "Received Link up event. Starting enumeration!\n");
+			/* Rescan the bus to enumerate endpoint devices */
+			pci_lock_rescan_remove();
+			pci_rescan_bus(pp->bridge->bus);
+			pci_unlock_rescan_remove();
+		}
+	}
+
+	return IRQ_HANDLED;
+}
+
 static irqreturn_t rockchip_pcie_ep_sys_irq_thread(int irq, void *arg)
 {
 	struct rockchip_pcie *rockchip = arg;
@@ -418,14 +446,29 @@ static irqreturn_t rockchip_pcie_ep_sys_irq_thread(int irq, void *arg)
 	return IRQ_HANDLED;
 }
 
-static int rockchip_pcie_configure_rc(struct rockchip_pcie *rockchip)
+static int rockchip_pcie_configure_rc(struct platform_device *pdev,
+				      struct rockchip_pcie *rockchip)
 {
+	struct device *dev = &pdev->dev;
 	struct dw_pcie_rp *pp;
+	int irq, ret;
 	u32 val;
 
 	if (!IS_ENABLED(CONFIG_PCIE_ROCKCHIP_DW_HOST))
 		return -ENODEV;
 
+	irq = platform_get_irq_byname(pdev, "sys");
+	if (irq < 0)
+		return irq;
+
+	ret = devm_request_threaded_irq(dev, irq, NULL,
+					rockchip_pcie_rc_sys_irq_thread,
+					IRQF_ONESHOT, "pcie-sys-rc", rockchip);
+	if (ret) {
+		dev_err(dev, "failed to request PCIe sys IRQ\n");
+		return ret;
+	}
+
 	/* LTSSM enable control mode */
 	val = HIWORD_UPDATE_BIT(PCIE_LTSSM_ENABLE_ENHANCE);
 	rockchip_pcie_writel_apb(rockchip, val, PCIE_CLIENT_HOT_RESET_CTRL);
@@ -435,8 +478,19 @@ static int rockchip_pcie_configure_rc(struct rockchip_pcie *rockchip)
 
 	pp = &rockchip->pci.pp;
 	pp->ops = &rockchip_pcie_host_ops;
+	pp->use_linkup_irq = true;
+
+	ret = dw_pcie_host_init(pp);
+	if (ret) {
+		dev_err(dev, "failed to initialize host\n");
+		return ret;
+	}
+
+	/* unmask DLL up/down indicator */
+	val = HIWORD_UPDATE(PCIE_RDLH_LINK_UP_CHGED, 0);
+	rockchip_pcie_writel_apb(rockchip, val, PCIE_CLIENT_INTR_MASK_MISC);
 
-	return dw_pcie_host_init(pp);
+	return ret;
 }
 
 static int rockchip_pcie_configure_ep(struct platform_device *pdev,
@@ -450,14 +504,12 @@ static int rockchip_pcie_configure_ep(struct platform_device *pdev,
 		return -ENODEV;
 
 	irq = platform_get_irq_byname(pdev, "sys");
-	if (irq < 0) {
-		dev_err(dev, "missing sys IRQ resource\n");
+	if (irq < 0)
 		return irq;
-	}
 
 	ret = devm_request_threaded_irq(dev, irq, NULL,
 					rockchip_pcie_ep_sys_irq_thread,
-					IRQF_ONESHOT, "pcie-sys", rockchip);
+					IRQF_ONESHOT, "pcie-sys-ep", rockchip);
 	if (ret) {
 		dev_err(dev, "failed to request PCIe sys IRQ\n");
 		return ret;
@@ -491,7 +543,8 @@ static int rockchip_pcie_configure_ep(struct platform_device *pdev,
 	pci_epc_init_notify(rockchip->pci.ep.epc);
 
 	/* unmask DLL up/down indicator and hot reset/link-down reset */
-	rockchip_pcie_writel_apb(rockchip, 0x60000, PCIE_CLIENT_INTR_MASK_MISC);
+	val = HIWORD_UPDATE(PCIE_RDLH_LINK_UP_CHGED | PCIE_LINK_REQ_RST_NOT_INT, 0);
+	rockchip_pcie_writel_apb(rockchip, val, PCIE_CLIENT_INTR_MASK_MISC);
 
 	return ret;
 }
@@ -553,7 +606,7 @@ static int rockchip_pcie_probe(struct platform_device *pdev)
 
 	switch (data->mode) {
 	case DW_PCIE_RC_TYPE:
-		ret = rockchip_pcie_configure_rc(rockchip);
+		ret = rockchip_pcie_configure_rc(pdev, rockchip);
 		if (ret)
 			goto deinit_clk;
 		break;
diff --git a/drivers/pci/controller/dwc/pcie-qcom.c b/drivers/pci/controller/dwc/pcie-qcom.c
index dc102d8bd58c6..e4d3366ead1f9 100644
--- a/drivers/pci/controller/dwc/pcie-qcom.c
+++ b/drivers/pci/controller/dwc/pcie-qcom.c
@@ -1569,6 +1569,8 @@ static irqreturn_t qcom_pcie_global_irq_thread(int irq, void *data)
 		pci_lock_rescan_remove();
 		pci_rescan_bus(pp->bridge->bus);
 		pci_unlock_rescan_remove();
+
+		qcom_pcie_icc_opp_update(pcie);
 	} else {
 		dev_WARN_ONCE(dev, 1, "Received unknown event. INT_STATUS: 0x%08x\n",
 			      status);
@@ -1703,6 +1705,10 @@ static int qcom_pcie_probe(struct platform_device *pdev)
 
 	platform_set_drvdata(pdev, pcie);
 
+	irq = platform_get_irq_byname_optional(pdev, "global");
+	if (irq > 0)
+		pp->use_linkup_irq = true;
+
 	ret = dw_pcie_host_init(pp);
 	if (ret) {
 		dev_err(dev, "cannot initialize host\n");
@@ -1716,7 +1722,6 @@ static int qcom_pcie_probe(struct platform_device *pdev)
 		goto err_host_deinit;
 	}
 
-	irq = platform_get_irq_byname_optional(pdev, "global");
 	if (irq > 0) {
 		ret = devm_request_threaded_irq(&pdev->dev, irq, NULL,
 						qcom_pcie_global_irq_thread,