For the i.MX95, configuration of a LUT is necessary to convert Bus Device
Function (BDF) to stream IDs, which are utilized by both IOMMU and ITS.
This involves examining the msi-map and smmu-map to ensure consistent
mapping of PCI BDF to the same stream IDs. Subsequently, LUT-related
registers are configured. In the absence of an msi-map, the built-in MSI
controller is utilized as a fallback.

Register a PCI bus callback function to handle enable_device() and
disable_device() operations, setting up the LUT whenever a new PCI device
is enabled.

Acked-by: Richard Zhu <hongxing.zhu@nxp.com>
Signed-off-by: Frank Li <Frank.Li@nxp.com>
---
Change from v5 to v6
- change comment rid to RID
- some mini change according to mani's feedback

Change from v4 to v5
- rework commt message
- add comment for mutex
- s/reqid/rid/
- keep only one loop when enable lut
- add warning when try to add duplicate rid
- Replace hardcode 0xffff with IMX95_PE0_LUT_MASK
- Fix some error message

Change from v3 to v4
- Check target value at of_map_id().
- of_node_put() for target.
- add case for msi-map exist, but rid entry is not exist.

Change from v2 to v3
- Use the "target" argument of of_map_id()
- Check if rid already in lut table when enable device

change from v1 to v2
- set callback to pci_host_bridge instead pci->ops.
---
 drivers/pci/controller/dwc/pci-imx6.c | 178 +++++++++++++++++++++++++++++++++-
 1 file changed, 177 insertions(+), 1 deletion(-)

diff --git a/drivers/pci/controller/dwc/pci-imx6.c b/drivers/pci/controller/dwc/pci-imx6.c
index 94f3411352bf0..725db9987fba8 100644
--- a/drivers/pci/controller/dwc/pci-imx6.c
+++ b/drivers/pci/controller/dwc/pci-imx6.c
@@ -55,6 +55,22 @@
 #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 {
@@ -82,6 +98,7 @@ enum imx_pcie_variants {
 #define IMX_PCIE_FLAG_HAS_PHY_RESET		BIT(5)
 #define IMX_PCIE_FLAG_HAS_SERDES		BIT(6)
 #define IMX_PCIE_FLAG_SUPPORT_64BIT		BIT(7)
+#define IMX_PCIE_FLAG_HAS_LUT			BIT(8)
 
 #define imx_check_flag(pci, val)	(pci->drvdata->flags & val)
 
@@ -134,6 +151,9 @@ 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 */
@@ -925,6 +945,154 @@ 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);
+
+	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;
+
+	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
+		err_i = -EINVAL;
+
+	target = NULL;
+	err_m = of_map_id(dev->of_node, rid, "msi-map", "msi-map-mask", &target, &sid_m);
+
+	/*
+	 * Return failure if msi-map exist and no entry for RID because dwc common
+	 * driver will skip setting up built-in MSI controller if msi-map existed.
+	 *
+	 *   err_m      target
+	 *	0	NULL		Return failure, function not work.
+	 *      !0      NULL		msi-map not exist, use built-in MSI.
+	 *	0	!NULL		Find one entry.
+	 *	!0	!NULL		Invalidate case.
+	 */
+	if (!err_m && !target)
+		return -EINVAL;
+	else if (target)
+		of_node_put(target); /* Find entry for RID in msi-map */
+
+	/*
+	 * msi-map        iommu-map
+	 *   Y                Y            ITS + SMMU, require the same sid
+	 *   Y                N            ITS
+	 *   N                Y            DWC MSI Ctrl + SMMU
+	 *   N                N            DWC MSI Ctrl
+	 */
+	if (!err_i && !err_m)
+		if ((sid_i & IMX95_SID_MASK) != (sid_m & IMX95_SID_MASK)) {
+			dev_err(dev, "iommu-map and msi-map entries mismatch!\n");
+			return -EINVAL;
+		}
+
+	/*
+	 * Both iommu-map and msi-map not exist, use dwc built-in MSI
+	 * controller, do nothing here.
+	 */
+	if (err_i && err_m)
+		return 0;
+
+	if (!err_i)
+		return imx_pcie_add_lut(imx_pcie, rid, sid_i);
+	else if (!err_m)
+		/*
+		 * Hardware auto add 2 bits controller id ahead of stream ID,
+		 * so mask this 2bits to get stream ID.
+		 */
+		return imx_pcie_add_lut(imx_pcie, rid, sid_m & IMX95_SID_MASK);
+
+	return 0;
+}
+
+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);
@@ -941,6 +1109,11 @@ 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)
@@ -1292,6 +1465,8 @@ static int imx_pcie_probe(struct platform_device *pdev)
 	imx_pcie->pci = pci;
 	imx_pcie->drvdata = of_device_get_match_data(dev);
 
+	mutex_init(&imx_pcie->lock);
+
 	/* Find the PHY if one is defined, only imx7d uses it */
 	np = of_parse_phandle(node, "fsl,imx7d-pcie-phy", 0);
 	if (np) {
@@ -1587,7 +1762,8 @@ static const struct imx_pcie_drvdata drvdata[] = {
 	},
 	[IMX95] = {
 		.variant = IMX95,
-		.flags = IMX_PCIE_FLAG_HAS_SERDES,
+		.flags = IMX_PCIE_FLAG_HAS_SERDES |
+			 IMX_PCIE_FLAG_HAS_LUT,
 		.clk_names = imx8mq_clks,
 		.clks_cnt = ARRAY_SIZE(imx8mq_clks),
 		.ltssm_off = IMX95_PE0_GEN_CTRL_3,

-- 
2.34.1