Merge branch 'pci/controller/iommu-map'

- Add host bridge .enable_device() and .disable_device() hooks for bridges
  that need to configure things like Requester ID to StreamID mapping when
  enabling devices (Frank Li)

- Add imx6 Requester ID to StreamID mapping configuration when enabling
  devices (Frank Li)

- Extend struct pci_ecam_ops with .enable_device() and .disable_device()
  hooks so drivers that use pci_host_common_probe() instead of their own
  .probe() have a way to set the .enable_device() callbacks (Marc Zyngier)

- Convert pcie-apple StreamID mapping configuration from a bus notifier to
  the .enable_device() and .disable_device() callbacks (Marc Zyngier)

* pci/controller/iommu-map:
  PCI: apple: Convert to {en,dis}able_device() callbacks
  PCI: host-generic: Allow {en,dis}able_device() to be provided via pci_ecam_ops
  PCI: imx6: Add IOMMU and ITS MSI support for i.MX95
  PCI: Add enable_device() and disable_device() callbacks for bridges

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,

drivers/pci/controller/pci-host-common.c

@@ -75,6 +75,8 @@ int pci_host_common_probe(struct platform_device *pdev)
 
 	bridge->sysdata = cfg;
 	bridge->ops = (struct pci_ops *)&ops->pci_ops;
+	bridge->enable_device = ops->enable_device;
+	bridge->disable_device = ops->disable_device;
 	bridge->msi_domain = true;
 
 	return pci_host_probe(bridge);

drivers/pci/controller/pcie-apple.c

@@ -26,7 +26,6 @@
 #include <linux/list.h>
 #include <linux/module.h>
 #include <linux/msi.h>
-#include <linux/notifier.h>
 #include <linux/of_irq.h>
 #include <linux/pci-ecam.h>
 
@@ -667,12 +666,16 @@ static struct apple_pcie_port *apple_pcie_get_port(struct pci_dev *pdev)
 	return NULL;
 }
 
-static int apple_pcie_add_device(struct apple_pcie_port *port,
-				 struct pci_dev *pdev)
+static int apple_pcie_enable_device(struct pci_host_bridge *bridge, struct pci_dev *pdev)
 {
 	u32 sid, rid = pci_dev_id(pdev);
+	struct apple_pcie_port *port;
 	int idx, err;
 
+	port = apple_pcie_get_port(pdev);
+	if (!port)
+		return 0;
+
 	dev_dbg(&pdev->dev, "added to bus %s, index %d\n",
 		pci_name(pdev->bus->self), port->idx);
 
@@ -698,12 +701,16 @@ static int apple_pcie_add_device(struct apple_pcie_port *port,
 	return idx >= 0 ? 0 : -ENOSPC;
 }
 
-static void apple_pcie_release_device(struct apple_pcie_port *port,
-				      struct pci_dev *pdev)
+static void apple_pcie_disable_device(struct pci_host_bridge *bridge, struct pci_dev *pdev)
 {
+	struct apple_pcie_port *port;
 	u32 rid = pci_dev_id(pdev);
 	int idx;
 
+	port = apple_pcie_get_port(pdev);
+	if (!port)
+		return;
+
 	mutex_lock(&port->pcie->lock);
 
 	for_each_set_bit(idx, port->sid_map, port->sid_map_sz) {
@@ -721,45 +728,6 @@ static void apple_pcie_release_device(struct apple_pcie_port *port,
 	mutex_unlock(&port->pcie->lock);
 }
 
-static int apple_pcie_bus_notifier(struct notifier_block *nb,
-				   unsigned long action,
-				   void *data)
-{
-	struct device *dev = data;
-	struct pci_dev *pdev = to_pci_dev(dev);
-	struct apple_pcie_port *port;
-	int err;
-
-	/*
-	 * This is a bit ugly. We assume that if we get notified for
-	 * any PCI device, we must be in charge of it, and that there
-	 * is no other PCI controller in the whole system. It probably
-	 * holds for now, but who knows for how long?
-	 */
-	port = apple_pcie_get_port(pdev);
-	if (!port)
-		return NOTIFY_DONE;
-
-	switch (action) {
-	case BUS_NOTIFY_ADD_DEVICE:
-		err = apple_pcie_add_device(port, pdev);
-		if (err)
-			return notifier_from_errno(err);
-		break;
-	case BUS_NOTIFY_DEL_DEVICE:
-		apple_pcie_release_device(port, pdev);
-		break;
-	default:
-		return NOTIFY_DONE;
-	}
-
-	return NOTIFY_OK;
-}
-
-static struct notifier_block apple_pcie_nb = {
-	.notifier_call = apple_pcie_bus_notifier,
-};
-
 static int apple_pcie_init(struct pci_config_window *cfg)
 {
 	struct device *dev = cfg->parent;
@@ -799,23 +767,10 @@ static int apple_pcie_init(struct pci_config_window *cfg)
 	return 0;
 }
 
-static int apple_pcie_probe(struct platform_device *pdev)
-{
-	int ret;
-
-	ret = bus_register_notifier(&pci_bus_type, &apple_pcie_nb);
-	if (ret)
-		return ret;
-
-	ret = pci_host_common_probe(pdev);
-	if (ret)
-		bus_unregister_notifier(&pci_bus_type, &apple_pcie_nb);
-
-	return ret;
-}
-
 static const struct pci_ecam_ops apple_pcie_cfg_ecam_ops = {
 	.init		= apple_pcie_init,
+	.enable_device	= apple_pcie_enable_device,
+	.disable_device	= apple_pcie_disable_device,
 	.pci_ops	= {
 		.map_bus	= pci_ecam_map_bus,
 		.read		= pci_generic_config_read,
@@ -830,7 +785,7 @@ static const struct of_device_id apple_pcie_of_match[] = {
 MODULE_DEVICE_TABLE(of, apple_pcie_of_match);
 
 static struct platform_driver apple_pcie_driver = {
-	.probe	= apple_pcie_probe,
+	.probe	= pci_host_common_probe,
 	.driver	= {
 		.name			= "pcie-apple",
 		.of_match_table		= apple_pcie_of_match,

drivers/pci/pci.c

@@ -2031,6 +2031,28 @@ int __weak pcibios_enable_device(struct pci_dev *dev, int bars)
 	return pci_enable_resources(dev, bars);
 }
 
+static int pci_host_bridge_enable_device(struct pci_dev *dev)
+{
+	struct pci_host_bridge *host_bridge = pci_find_host_bridge(dev->bus);
+	int err;
+
+	if (host_bridge && host_bridge->enable_device) {
+		err = host_bridge->enable_device(host_bridge, dev);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
+static void pci_host_bridge_disable_device(struct pci_dev *dev)
+{
+	struct pci_host_bridge *host_bridge = pci_find_host_bridge(dev->bus);
+
+	if (host_bridge && host_bridge->disable_device)
+		host_bridge->disable_device(host_bridge, dev);
+}
+
 static int do_pci_enable_device(struct pci_dev *dev, int bars)
 {
 	int err;
@@ -2046,9 +2068,13 @@ static int do_pci_enable_device(struct pci_dev *dev, int bars)
 	if (bridge)
 		pcie_aspm_powersave_config_link(bridge);
 
+	err = pci_host_bridge_enable_device(dev);
+	if (err)
+		return err;
+
 	err = pcibios_enable_device(dev, bars);
 	if (err < 0)
-		return err;
+		goto err_enable;
 	pci_fixup_device(pci_fixup_enable, dev);
 
 	if (dev->msi_enabled || dev->msix_enabled)
@@ -2063,6 +2089,12 @@ static int do_pci_enable_device(struct pci_dev *dev, int bars)
 	}
 
 	return 0;
+
+err_enable:
+	pci_host_bridge_disable_device(dev);
+
+	return err;
+
 }
 
 /**
@@ -2246,6 +2278,8 @@ void pci_disable_device(struct pci_dev *dev)
 	if (atomic_dec_return(&dev->enable_cnt) != 0)
 		return;
 
+	pci_host_bridge_disable_device(dev);
+
 	do_pci_disable_device(dev);
 
 	dev->is_busmaster = 0;

include/linux/pci-ecam.h

@@ -45,6 +45,10 @@ struct pci_ecam_ops {
 	unsigned int			bus_shift;
 	struct pci_ops			pci_ops;
 	int				(*init)(struct pci_config_window *);
+	int				(*enable_device)(struct pci_host_bridge *,
+							 struct pci_dev *);
+	void				(*disable_device)(struct pci_host_bridge *,
+							  struct pci_dev *);
 };
 
 /*

include/linux/pci.h

@@ -595,6 +595,8 @@ struct pci_host_bridge {
 	u8 (*swizzle_irq)(struct pci_dev *, u8 *); /* Platform IRQ swizzler */
 	int (*map_irq)(const struct pci_dev *, u8, u8);
 	void (*release_fn)(struct pci_host_bridge *);
+	int (*enable_device)(struct pci_host_bridge *bridge, struct pci_dev *dev);
+	void (*disable_device)(struct pci_host_bridge *bridge, struct pci_dev *dev);
 	void		*release_data;
 	unsigned int	ignore_reset_delay:1;	/* For entire hierarchy */
 	unsigned int	no_ext_tags:1;		/* No Extended Tags */