PCI: imx6: Add IOMMU and ITS MSI support for i.MX95

For the i.MX95, the configuration of a LUT is necessary to convert PCIe
Requester IDs (RIDs) to StreamIDs, which are used by both IOMMU and ITS.
This involves checking msi-map and iommu-map device tree properties to
ensure consistent mapping of Requester IDs to the same StreamIDs.

Subsequently, LUT-related registers are configured. If a msi-map isn't
detected, the platform relies on DWC built-in controller for MSIs that
do not need StreamIDs.

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

Known limitations:

  - If iommu-map exists in the device tree but the IOMMU controller is
    disabled, StreamIDs are programmed into the LUT. However, if a RID
    is out of range of the iommu-map, enabling the PCI device would
    result in a failure, although the PCI device can work without the
    IOMMU.

  - If msi-map exists in the device tree but the MSI controller is
    disabled, MSIs will not work. The DWC driver skips initializing the
    built-in MSI controller, falling back to legacy PCI INTx only.

Link: https://lore.kernel.org/r/20250114-imx95_lut-v9-2-39f58dbed03a@nxp.com
Signed-off-by: Frank Li <Frank.Li@nxp.com>
[kwilczynski: commit log]
Signed-off-by: Krzysztof Wilczyński <kwilczynski@kernel.org>
[bhelgaas: fix uninitialized "sid" in imx_pcie_enable_device()]
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Acked-by: Richard Zhu <hongxing.zhu@nxp.com>

1 files changed, 207 insertions, 1 deletions

diff --git a/drivers/pci/controller/dwc/pci-imx6.c b/drivers/pci/controller/dwc/pci-imx6.c
index c8d5c90aa4d4..6ed56ff390d9 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 {
@@ -87,6 +103,7 @@ 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)
 
@@ -139,6 +156,9 @@ 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 */
@@ -930,6 +950,184 @@ 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 +1144,11 @@ 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)
@@ -1330,6 +1533,8 @@ 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) {
@@ -1627,7 +1832,8 @@ 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,