Merge tag 'iommu-updates-v6.6' of git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu

Pull iommu updates from Joerg Roedel:
"Core changes:

- Consolidate probe_device path

- Make the PCI-SAC IOVA allocation trick PCI-only

AMD IOMMU:

- Consolidate PPR log handling

- Interrupt handling improvements

- Refcount fixes for amd_iommu_v2 driver

Intel VT-d driver:

- Enable idxd device DMA with pasid through iommu dma ops

- Lift RESV_DIRECT check from VT-d driver to core

- Miscellaneous cleanups and fixes

ARM-SMMU drivers:

- Device-tree binding updates:
- Add additional compatible strings for Qualcomm SoCs
- Allow ASIDs to be configured in the DT to work around Qualcomm's
broken hypervisor
- Fix clocks for Qualcomm's MSM8998 SoC

- SMMUv2:
- Support for Qualcomm's legacy firmware implementation featured
on at least MSM8956 and MSM8976
- Match compatible strings for Qualcomm SM6350 and SM6375 SoC
variants

- SMMUv3:
- Use 'ida' instead of a bitmap for VMID allocation

- Rockchip IOMMU:
- Lift page-table allocation restrictions on newer hardware

- Mediatek IOMMU:
- Add MT8188 IOMMU Support

- Renesas IOMMU:
- Allow PCIe devices

.. and the usual set of cleanups an smaller fixes"

* tag 'iommu-updates-v6.6' of git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu: (64 commits)
iommu: Explicitly include correct DT includes
iommu/amd: Remove unused declarations
iommu/arm-smmu-qcom: Add SM6375 SMMUv2
iommu/arm-smmu-qcom: Add SM6350 DPU compatible
iommu/arm-smmu-qcom: Add SM6375 DPU compatible
iommu/arm-smmu-qcom: Sort the compatible list alphabetically
dt-bindings: arm-smmu: Fix MSM8998 clocks description
iommu/vt-d: Remove unused extern declaration dmar_parse_dev_scope()
iommu/vt-d: Fix to convert mm pfn to dma pfn
iommu/vt-d: Fix to flush cache of PASID directory table
iommu/vt-d: Remove rmrr check in domain attaching device path
iommu: Prevent RESV_DIRECT devices from blocking domains
dmaengine/idxd: Re-enable kernel workqueue under DMA API
iommu/vt-d: Add set_dev_pasid callback for dma domain
iommu/vt-d: Prepare for set_dev_pasid callback
iommu/vt-d: Make prq draining code generic
iommu/vt-d: Remove pasid_mutex
iommu/vt-d: Add domain_flush_pasid_iotlb()
iommu: Move global PASID allocation from SVA to core
iommu: Generalize PASID 0 for normal DMA w/o PASID
...

Documentation/devicetree/bindings/iommu/arm,smmu.yaml

···
           contains:
             enum:
               - qcom,msm8998-smmu-v2
+    then:
+      anyOf:
+        - properties:
+            clock-names:
+              items:
+                - const: bus
+            clocks:
+              items:
+                - description: bus clock required for downstream bus access and for
+                    the smmu ptw
+        - properties:
+            clock-names:
+              items:
+                - const: iface
+                - const: mem
+                - const: mem_iface
+            clocks:
+              items:
+                - description: interface clock required to access smmu's registers
+                    through the TCU's programming interface.
+                - description: bus clock required for memory access
+                - description: bus clock required for GPU memory access
+        - properties:
+            clock-names:
+              items:
+                - const: iface-mm
+                - const: iface-smmu
+                - const: bus-smmu
+            clocks:
+              items:
+                - description: interface clock required to access mnoc's registers
+                    through the TCU's programming interface.
+                - description: interface clock required to access smmu's registers
+                    through the TCU's programming interface.
+                - description: bus clock required for the smmu ptw
+
+  - if:
+      properties:
+        compatible:
+          contains:
+            enum:
               - qcom,sdm630-smmu-v2
               - qcom,sm6375-smmu-v2
     then:

Documentation/devicetree/bindings/iommu/mediatek,iommu.yaml

···
           - mediatek,mt8173-m4u  # generation two
           - mediatek,mt8183-m4u  # generation two
           - mediatek,mt8186-iommu-mm         # generation two
+          - mediatek,mt8188-iommu-vdo        # generation two
+          - mediatek,mt8188-iommu-vpp        # generation two
+          - mediatek,mt8188-iommu-infra      # generation two
           - mediatek,mt8192-m4u  # generation two
           - mediatek,mt8195-iommu-vdo        # generation two
           - mediatek,mt8195-iommu-vpp        # generation two
···
     description: |
       This is the mtk_m4u_id according to the HW. Specifies the mtk_m4u_id as
       defined in
+      dt-binding/memory/mediatek,mt8188-memory-port.h for mt8188,
       dt-binding/memory/mt2701-larb-port.h for mt2701 and mt7623,
       dt-binding/memory/mt2712-larb-port.h for mt2712,
       dt-binding/memory/mt6779-larb-port.h for mt6779,
···
               - mediatek,mt6795-m4u
               - mediatek,mt8173-m4u
               - mediatek,mt8186-iommu-mm
+              - mediatek,mt8188-iommu-vdo
+              - mediatek,mt8188-iommu-vpp
               - mediatek,mt8192-m4u
               - mediatek,mt8195-iommu-vdo
               - mediatek,mt8195-iommu-vpp
···
         compatible:
           enum:
             - mediatek,mt8186-iommu-mm
+            - mediatek,mt8188-iommu-vdo
+            - mediatek,mt8188-iommu-vpp
             - mediatek,mt8192-m4u
             - mediatek,mt8195-iommu-vdo
             - mediatek,mt8195-iommu-vpp
···
         properties:
           compatible:
             contains:
-              const: mediatek,mt8195-iommu-infra
+              enum:
+                - mediatek,mt8188-iommu-infra
+                - mediatek,mt8195-iommu-infra
 
     then:
       required:

Documentation/devicetree/bindings/iommu/qcom,iommu.yaml

···
 
 properties:
   compatible:
-    items:
-      - enum:
-          - qcom,msm8916-iommu
-          - qcom,msm8953-iommu
-      - const: qcom,msm-iommu-v1
+    oneOf:
+      - items:
+          - enum:
+              - qcom,msm8916-iommu
+              - qcom,msm8953-iommu
+          - const: qcom,msm-iommu-v1
+      - items:
+          - enum:
+              - qcom,msm8976-iommu
+          - const: qcom,msm-iommu-v2
 
   clocks:
     items:
···
         enum:
           - qcom,msm-iommu-v1-ns
           - qcom,msm-iommu-v1-sec
+          - qcom,msm-iommu-v2-ns
+          - qcom,msm-iommu-v2-sec
 
       interrupts:
         maxItems: 1
 
       reg:
         maxItems: 1
+
+      qcom,ctx-asid:
+        $ref: /schemas/types.yaml#/definitions/uint32
+        description:
+          The ASID number associated to the context bank.
 
     required:
       - compatible

MAINTAINERS

···
 S:	Supported
 F:	Documentation/devicetree/bindings/iommu/mediatek*
 F:	drivers/iommu/mtk_iommu*
+F:	include/dt-bindings/memory/mediatek,mt*-port.h
 F:	include/dt-bindings/memory/mt*-port.h
 
 MEDIATEK JPEG DRIVER

drivers/acpi/scan.c

···
 	 * If we have reason to believe the IOMMU driver missed the initial
 	 * iommu_probe_device() call for dev, replay it to get things in order.
 	 */
-	if (!err && dev->bus && !device_iommu_mapped(dev))
+	if (!err && dev->bus)
 		err = iommu_probe_device(dev);
 
 	/* Ignore all other errors apart from EPROBE_DEFER */

drivers/dma/idxd/device.c

···
 	}
 }
 
-static void __idxd_wq_set_priv_locked(struct idxd_wq *wq, int priv)
-{
-	struct idxd_device *idxd = wq->idxd;
-	union wqcfg wqcfg;
-	unsigned int offset;
-
-	offset = WQCFG_OFFSET(idxd, wq->id, WQCFG_PRIVL_IDX);
-	spin_lock(&idxd->dev_lock);
-	wqcfg.bits[WQCFG_PRIVL_IDX] = ioread32(idxd->reg_base + offset);
-	wqcfg.priv = priv;
-	wq->wqcfg->bits[WQCFG_PRIVL_IDX] = wqcfg.bits[WQCFG_PRIVL_IDX];
-	iowrite32(wqcfg.bits[WQCFG_PRIVL_IDX], idxd->reg_base + offset);
-	spin_unlock(&idxd->dev_lock);
-}
-
 static void __idxd_wq_set_pasid_locked(struct idxd_wq *wq, int pasid)
 {
 	struct idxd_device *idxd = wq->idxd;
···
 	}
 
 	/*
-	 * In the event that the WQ is configurable for pasid and priv bits.
-	 * For kernel wq, the driver should setup the pasid, pasid_en, and priv bit.
-	 * However, for non-kernel wq, the driver should only set the pasid_en bit for
-	 * shared wq. A dedicated wq that is not 'kernel' type will configure pasid and
+	 * In the event that the WQ is configurable for pasid, the driver
+	 * should setup the pasid, pasid_en bit. This is true for both kernel
+	 * and user shared workqueues. There is no need to setup priv bit in
+	 * that in-kernel DMA will also do user privileged requests.
+	 * A dedicated wq that is not 'kernel' type will configure pasid and
 	 * pasid_en later on so there is no need to setup.
 	 */
 	if (test_bit(IDXD_FLAG_CONFIGURABLE, &idxd->flags)) {
-		int priv = 0;
-
 		if (wq_pasid_enabled(wq)) {
 			if (is_idxd_wq_kernel(wq) || wq_shared(wq)) {
 				u32 pasid = wq_dedicated(wq) ? idxd->pasid : 0;
···
 				__idxd_wq_set_pasid_locked(wq, pasid);
 			}
 		}
-
-		if (is_idxd_wq_kernel(wq))
-			priv = 1;
-		__idxd_wq_set_priv_locked(wq, priv);
 	}
 
 	rc = 0;
···
 	spin_unlock(&idxd->dev_lock);
 	if (rc < 0)
 		return -ENXIO;
+
+	/*
+	 * System PASID is preserved across device disable/enable cycle, but
+	 * genconfig register content gets cleared during device reset. We
+	 * need to re-enable user interrupts for kernel work queue completion
+	 * IRQ to function.
+	 */
+	if (idxd->pasid != IOMMU_PASID_INVALID)
+		idxd_set_user_intr(idxd, 1);
 
 	rc = idxd_device_evl_setup(idxd);
 	if (rc < 0) {

drivers/dma/idxd/dma.c

···
 	hw->xfer_size = len;
 	/*
 	 * For dedicated WQ, this field is ignored and HW will use the WQCFG.priv
-	 * field instead. This field should be set to 1 for kernel descriptors.
+	 * field instead. This field should be set to 0 for kernel descriptors
+	 * since kernel DMA on VT-d supports "user" privilege only.
 	 */
-	hw->priv = 1;
+	hw->priv = 0;
 	hw->completion_addr = compl;
 }
 

drivers/dma/idxd/idxd.h

···
 	return container_of(ie, struct idxd_device, ie);
 }
 
+static inline void idxd_set_user_intr(struct idxd_device *idxd, bool enable)
+{
+	union gencfg_reg reg;
+
+	reg.bits = ioread32(idxd->reg_base + IDXD_GENCFG_OFFSET);
+	reg.user_int_en = enable;
+	iowrite32(reg.bits, idxd->reg_base + IDXD_GENCFG_OFFSET);
+}
+
 extern struct bus_type dsa_bus_type;
 
 extern bool support_enqcmd;

drivers/dma/idxd/init.c

···
 
 static int idxd_enable_system_pasid(struct idxd_device *idxd)
 {
-	return -EOPNOTSUPP;
+	struct pci_dev *pdev = idxd->pdev;
+	struct device *dev = &pdev->dev;
+	struct iommu_domain *domain;
+	ioasid_t pasid;
+	int ret;
+
+	/*
+	 * Attach a global PASID to the DMA domain so that we can use ENQCMDS
+	 * to submit work on buffers mapped by DMA API.
+	 */
+	domain = iommu_get_domain_for_dev(dev);
+	if (!domain)
+		return -EPERM;
+
+	pasid = iommu_alloc_global_pasid(dev);
+	if (pasid == IOMMU_PASID_INVALID)
+		return -ENOSPC;
+
+	/*
+	 * DMA domain is owned by the driver, it should support all valid
+	 * types such as DMA-FQ, identity, etc.
+	 */
+	ret = iommu_attach_device_pasid(domain, dev, pasid);
+	if (ret) {
+		dev_err(dev, "failed to attach device pasid %d, domain type %d",
+			pasid, domain->type);
+		iommu_free_global_pasid(pasid);
+		return ret;
+	}
+
+	/* Since we set user privilege for kernel DMA, enable completion IRQ */
+	idxd_set_user_intr(idxd, 1);
+	idxd->pasid = pasid;
+
+	return ret;
 }
 
 static void idxd_disable_system_pasid(struct idxd_device *idxd)
 {
+	struct pci_dev *pdev = idxd->pdev;
+	struct device *dev = &pdev->dev;
+	struct iommu_domain *domain;
 
-	iommu_sva_unbind_device(idxd->sva);
+	domain = iommu_get_domain_for_dev(dev);
+	if (!domain)
+		return;
+
+	iommu_detach_device_pasid(domain, dev, idxd->pasid);
+	iommu_free_global_pasid(idxd->pasid);
+
+	idxd_set_user_intr(idxd, 0);
 	idxd->sva = NULL;
+	idxd->pasid = IOMMU_PASID_INVALID;
 }
 
 static int idxd_enable_sva(struct pci_dev *pdev)
···
 		} else {
 			set_bit(IDXD_FLAG_USER_PASID_ENABLED, &idxd->flags);
 
-			if (idxd_enable_system_pasid(idxd))
-				dev_warn(dev, "No in-kernel DMA with PASID.\n");
+			rc = idxd_enable_system_pasid(idxd);
+			if (rc)
+				dev_warn(dev, "No in-kernel DMA with PASID. %d\n", rc);
 			else
 				set_bit(IDXD_FLAG_PASID_ENABLED, &idxd->flags);
 		}

drivers/dma/idxd/sysfs.c

···
 	if (strlen(buf) > WQ_NAME_SIZE || strlen(buf) == 0)
 		return -EINVAL;
 
-	/*
-	 * This is temporarily placed here until we have SVM support for
-	 * dmaengine.
-	 */
-	if (wq->type == IDXD_WQT_KERNEL && device_pasid_enabled(wq->idxd))
-		return -EOPNOTSUPP;
-
 	input = kstrndup(buf, count, GFP_KERNEL);
 	if (!input)
 		return -ENOMEM;

drivers/iommu/amd/amd_iommu.h

···
 #include "amd_iommu_types.h"
 
 irqreturn_t amd_iommu_int_thread(int irq, void *data);
+irqreturn_t amd_iommu_int_thread_evtlog(int irq, void *data);
+irqreturn_t amd_iommu_int_thread_pprlog(int irq, void *data);
+irqreturn_t amd_iommu_int_thread_galog(int irq, void *data);
 irqreturn_t amd_iommu_int_handler(int irq, void *data);
 void amd_iommu_apply_erratum_63(struct amd_iommu *iommu, u16 devid);
 void amd_iommu_restart_event_logging(struct amd_iommu *iommu);
 void amd_iommu_restart_ga_log(struct amd_iommu *iommu);
-int amd_iommu_init_devices(void);
-void amd_iommu_uninit_devices(void);
-void amd_iommu_init_notifier(void);
+void amd_iommu_restart_ppr_log(struct amd_iommu *iommu);
 void amd_iommu_set_rlookup_table(struct amd_iommu *iommu, u16 devid);
 
 #ifdef CONFIG_AMD_IOMMU_DEBUGFS

drivers/iommu/amd/amd_iommu_types.h

···
 #define PASID_MASK		0x0000ffff
 
 /* MMIO status bits */
-#define MMIO_STATUS_EVT_OVERFLOW_INT_MASK	BIT(0)
+#define MMIO_STATUS_EVT_OVERFLOW_MASK		BIT(0)
 #define MMIO_STATUS_EVT_INT_MASK		BIT(1)
 #define MMIO_STATUS_COM_WAIT_INT_MASK		BIT(2)
+#define MMIO_STATUS_EVT_RUN_MASK		BIT(3)
+#define MMIO_STATUS_PPR_OVERFLOW_MASK		BIT(5)
 #define MMIO_STATUS_PPR_INT_MASK		BIT(6)
+#define MMIO_STATUS_PPR_RUN_MASK		BIT(7)
 #define MMIO_STATUS_GALOG_RUN_MASK		BIT(8)
 #define MMIO_STATUS_GALOG_OVERFLOW_MASK		BIT(9)
 #define MMIO_STATUS_GALOG_INT_MASK		BIT(10)
···
  */
 #define DTE_FLAG_V	BIT_ULL(0)
 #define DTE_FLAG_TV	BIT_ULL(1)
+#define DTE_FLAG_GIOV	BIT_ULL(54)
+#define DTE_FLAG_GV	BIT_ULL(55)
+#define DTE_GLX_SHIFT	(56)
+#define DTE_GLX_MASK	(3)
 #define DTE_FLAG_IR	BIT_ULL(61)
 #define DTE_FLAG_IW	BIT_ULL(62)
 
 #define DTE_FLAG_IOTLB	BIT_ULL(32)
-#define DTE_FLAG_GIOV	BIT_ULL(54)
-#define DTE_FLAG_GV	BIT_ULL(55)
 #define DTE_FLAG_MASK	(0x3ffULL << 32)
-#define DTE_GLX_SHIFT	(56)
-#define DTE_GLX_MASK	(3)
 #define DEV_DOMID_MASK	0xffffULL
 
 #define DTE_GCR3_VAL_A(x)	(((x) >> 12) & 0x00007ULL)
···
 	/* event buffer virtual address */
 	u8 *evt_buf;
 
+	/* Name for event log interrupt */
+	unsigned char evt_irq_name[16];
+
 	/* Base of the PPR log, if present */
 	u8 *ppr_log;
 
+	/* Name for PPR log interrupt */
+	unsigned char ppr_irq_name[16];
+
 	/* Base of the GA log, if present */
 	u8 *ga_log;
+
+	/* Name for GA log interrupt */
+	unsigned char ga_irq_name[16];
 
 	/* Tail of the GA log, if present */
 	u8 *ga_log_tail;

drivers/iommu/amd/init.c

···
 	iommu_feature_disable(iommu, CONTROL_GALOG_EN);
 	iommu_feature_disable(iommu, CONTROL_GAINT_EN);
 
+	/* Disable IOMMU PPR logging */
+	iommu_feature_disable(iommu, CONTROL_PPRLOG_EN);
+	iommu_feature_disable(iommu, CONTROL_PPRINT_EN);
+
 	/* Disable IOMMU hardware itself */
 	iommu_feature_disable(iommu, CONTROL_IOMMU_EN);
 
···
 }
 
 /*
+ * Interrupt handler has processed all pending events and adjusted head
+ * and tail pointer. Reset overflow mask and restart logging again.
+ */
+static void amd_iommu_restart_log(struct amd_iommu *iommu, const char *evt_type,
+				  u8 cntrl_intr, u8 cntrl_log,
+				  u32 status_run_mask, u32 status_overflow_mask)
+{
+	u32 status;
+
+	status = readl(iommu->mmio_base + MMIO_STATUS_OFFSET);
+	if (status & status_run_mask)
+		return;
+
+	pr_info_ratelimited("IOMMU %s log restarting\n", evt_type);
+
+	iommu_feature_disable(iommu, cntrl_log);
+	iommu_feature_disable(iommu, cntrl_intr);
+
+	writel(status_overflow_mask, iommu->mmio_base + MMIO_STATUS_OFFSET);
+
+	iommu_feature_enable(iommu, cntrl_intr);
+	iommu_feature_enable(iommu, cntrl_log);
+}
+
+/*
  * This function restarts event logging in case the IOMMU experienced
  * an event log buffer overflow.
  */
 void amd_iommu_restart_event_logging(struct amd_iommu *iommu)
 {
-	iommu_feature_disable(iommu, CONTROL_EVT_LOG_EN);
-	iommu_feature_enable(iommu, CONTROL_EVT_LOG_EN);
+	amd_iommu_restart_log(iommu, "Event", CONTROL_EVT_INT_EN,
+			      CONTROL_EVT_LOG_EN, MMIO_STATUS_EVT_RUN_MASK,
+			      MMIO_STATUS_EVT_OVERFLOW_MASK);
 }
 
 /*
  * This function restarts event logging in case the IOMMU experienced
- * an GA log overflow.
+ * GA log overflow.
  */
 void amd_iommu_restart_ga_log(struct amd_iommu *iommu)
 {
-	u32 status;
+	amd_iommu_restart_log(iommu, "GA", CONTROL_GAINT_EN,
+			      CONTROL_GALOG_EN, MMIO_STATUS_GALOG_RUN_MASK,
+			      MMIO_STATUS_GALOG_OVERFLOW_MASK);
+}
 
-	status = readl(iommu->mmio_base + MMIO_STATUS_OFFSET);
-	if (status & MMIO_STATUS_GALOG_RUN_MASK)
-		return;
-
-	pr_info_ratelimited("IOMMU GA Log restarting\n");
-
-	iommu_feature_disable(iommu, CONTROL_GALOG_EN);
-	iommu_feature_disable(iommu, CONTROL_GAINT_EN);
-
-	writel(MMIO_STATUS_GALOG_OVERFLOW_MASK,
-	       iommu->mmio_base + MMIO_STATUS_OFFSET);
-
-	iommu_feature_enable(iommu, CONTROL_GAINT_EN);
-	iommu_feature_enable(iommu, CONTROL_GALOG_EN);
+/*
+ * This function restarts ppr logging in case the IOMMU experienced
+ * PPR log overflow.
+ */
+void amd_iommu_restart_ppr_log(struct amd_iommu *iommu)
+{
+	amd_iommu_restart_log(iommu, "PPR", CONTROL_PPRINT_EN,
+			      CONTROL_PPRLOG_EN, MMIO_STATUS_PPR_RUN_MASK,
+			      MMIO_STATUS_PPR_OVERFLOW_MASK);
 }
 
 /*
···
 	if (iommu->ppr_log == NULL)
 		return;
 
+	iommu_feature_enable(iommu, CONTROL_PPR_EN);
+
 	entry = iommu_virt_to_phys(iommu->ppr_log) | PPR_LOG_SIZE_512;
 
 	memcpy_toio(iommu->mmio_base + MMIO_PPR_LOG_OFFSET,
···
 	writel(0x00, iommu->mmio_base + MMIO_PPR_TAIL_OFFSET);
 
 	iommu_feature_enable(iommu, CONTROL_PPRLOG_EN);
-	iommu_feature_enable(iommu, CONTROL_PPR_EN);
+	iommu_feature_enable(iommu, CONTROL_PPRINT_EN);
 }
 
 static void __init free_ppr_log(struct amd_iommu *iommu)
···
 		struct irq_data *irqd = irq_domain_get_irq_data(domain, i);
 
 		irqd->chip = &intcapxt_controller;
+		irqd->hwirq = info->hwirq;
 		irqd->chip_data = info->data;
 		__irq_set_handler(i, handle_edge_irq, 0, "edge");
 	}
···
 	xt.destid_0_23 = cfg->dest_apicid & GENMASK(23, 0);
 	xt.destid_24_31 = cfg->dest_apicid >> 24;
 
-	/**
-	 * Current IOMMU implementation uses the same IRQ for all
-	 * 3 IOMMU interrupts.
-	 */
-	writeq(xt.capxt, iommu->mmio_base + MMIO_INTCAPXT_EVT_OFFSET);
-	writeq(xt.capxt, iommu->mmio_base + MMIO_INTCAPXT_PPR_OFFSET);
-	writeq(xt.capxt, iommu->mmio_base + MMIO_INTCAPXT_GALOG_OFFSET);
+	writeq(xt.capxt, iommu->mmio_base + irqd->hwirq);
 }
 
 static void intcapxt_mask_irq(struct irq_data *irqd)
 {
 	struct amd_iommu *iommu = irqd->chip_data;
 
-	writeq(0, iommu->mmio_base + MMIO_INTCAPXT_EVT_OFFSET);
-	writeq(0, iommu->mmio_base + MMIO_INTCAPXT_PPR_OFFSET);
-	writeq(0, iommu->mmio_base + MMIO_INTCAPXT_GALOG_OFFSET);
+	writeq(0, iommu->mmio_base + irqd->hwirq);
 }
 
 
···
 	return iommu_irqdomain;
 }
 
-static int iommu_setup_intcapxt(struct amd_iommu *iommu)
+static int __iommu_setup_intcapxt(struct amd_iommu *iommu, const char *devname,
+				  int hwirq, irq_handler_t thread_fn)
 {
 	struct irq_domain *domain;
 	struct irq_alloc_info info;
···
 	init_irq_alloc_info(&info, NULL);
 	info.type = X86_IRQ_ALLOC_TYPE_AMDVI;
 	info.data = iommu;
+	info.hwirq = hwirq;
 
 	irq = irq_domain_alloc_irqs(domain, 1, node, &info);
 	if (irq < 0) {
···
 	}
 
 	ret = request_threaded_irq(irq, amd_iommu_int_handler,
-				   amd_iommu_int_thread, 0, "AMD-Vi", iommu);
+				   thread_fn, 0, devname, iommu);
 	if (ret) {
 		irq_domain_free_irqs(irq, 1);
 		irq_domain_remove(domain);
···
 	}
 
 	return 0;
+}
+
+static int iommu_setup_intcapxt(struct amd_iommu *iommu)
+{
+	int ret;
+
+	snprintf(iommu->evt_irq_name, sizeof(iommu->evt_irq_name),
+		 "AMD-Vi%d-Evt", iommu->index);
+	ret = __iommu_setup_intcapxt(iommu, iommu->evt_irq_name,
+				     MMIO_INTCAPXT_EVT_OFFSET,
+				     amd_iommu_int_thread_evtlog);
+	if (ret)
+		return ret;
+
+	snprintf(iommu->ppr_irq_name, sizeof(iommu->ppr_irq_name),
+		 "AMD-Vi%d-PPR", iommu->index);
+	ret = __iommu_setup_intcapxt(iommu, iommu->ppr_irq_name,
+				     MMIO_INTCAPXT_PPR_OFFSET,
+				     amd_iommu_int_thread_pprlog);
+	if (ret)
+		return ret;
+
+#ifdef CONFIG_IRQ_REMAP
+	snprintf(iommu->ga_irq_name, sizeof(iommu->ga_irq_name),
+		 "AMD-Vi%d-GA", iommu->index);
+	ret = __iommu_setup_intcapxt(iommu, iommu->ga_irq_name,
+				     MMIO_INTCAPXT_GALOG_OFFSET,
+				     amd_iommu_int_thread_galog);
+#endif
+
+	return ret;
 }
 
 static int iommu_init_irq(struct amd_iommu *iommu)
···
 
 	iommu_feature_enable(iommu, CONTROL_EVT_INT_EN);
 
-	if (iommu->ppr_log != NULL)
-		iommu_feature_enable(iommu, CONTROL_PPRINT_EN);
 	return 0;
 }
 
···
 static void enable_iommus(void)
 {
 	early_enable_iommus();
-	enable_iommus_vapic();
-	enable_iommus_v2();
 }
 
 static void disable_iommus(void)
···
 			goto out;
 	}
 
+	/*
+	 * Interrupt handler is ready to process interrupts. Enable
+	 * PPR and GA log interrupt for all IOMMUs.
+	 */
+	enable_iommus_vapic();
+	enable_iommus_v2();
+
 out:
 	return ret;
 }
···
 		register_syscore_ops(&amd_iommu_syscore_ops);
 		ret = amd_iommu_init_pci();
 		init_state = ret ? IOMMU_INIT_ERROR : IOMMU_PCI_INIT;
-		enable_iommus_vapic();
-		enable_iommus_v2();
 		break;
 	case IOMMU_PCI_INIT:
 		ret = amd_iommu_enable_interrupts();

drivers/iommu/amd/iommu.c

···
 amd_iommu_set_pci_msi_domain(struct device *dev, struct amd_iommu *iommu) { }
 #endif /* !CONFIG_IRQ_REMAP */
 
-#define AMD_IOMMU_INT_MASK	\
-	(MMIO_STATUS_EVT_OVERFLOW_INT_MASK | \
-	 MMIO_STATUS_EVT_INT_MASK | \
-	 MMIO_STATUS_PPR_INT_MASK | \
-	 MMIO_STATUS_GALOG_OVERFLOW_MASK | \
-	 MMIO_STATUS_GALOG_INT_MASK)
-
-irqreturn_t amd_iommu_int_thread(int irq, void *data)
+static void amd_iommu_handle_irq(void *data, const char *evt_type,
+				 u32 int_mask, u32 overflow_mask,
+				 void (*int_handler)(struct amd_iommu *),
+				 void (*overflow_handler)(struct amd_iommu *))
 {
 	struct amd_iommu *iommu = (struct amd_iommu *) data;
 	u32 status = readl(iommu->mmio_base + MMIO_STATUS_OFFSET);
+	u32 mask = int_mask | overflow_mask;
 
-	while (status & AMD_IOMMU_INT_MASK) {
+	while (status & mask) {
 		/* Enable interrupt sources again */
-		writel(AMD_IOMMU_INT_MASK,
-			iommu->mmio_base + MMIO_STATUS_OFFSET);
+		writel(mask, iommu->mmio_base + MMIO_STATUS_OFFSET);
 
-		if (status & MMIO_STATUS_EVT_INT_MASK) {
-			pr_devel("Processing IOMMU Event Log\n");
-			iommu_poll_events(iommu);
+		if (int_handler) {
+			pr_devel("Processing IOMMU (ivhd%d) %s Log\n",
+				 iommu->index, evt_type);
+			int_handler(iommu);
 		}
 
-		if (status & MMIO_STATUS_PPR_INT_MASK) {
-			pr_devel("Processing IOMMU PPR Log\n");
-			iommu_poll_ppr_log(iommu);
-		}
-
-#ifdef CONFIG_IRQ_REMAP
-		if (status & (MMIO_STATUS_GALOG_INT_MASK |
-			      MMIO_STATUS_GALOG_OVERFLOW_MASK)) {
-			pr_devel("Processing IOMMU GA Log\n");
-			iommu_poll_ga_log(iommu);
-		}
-
-		if (status & MMIO_STATUS_GALOG_OVERFLOW_MASK) {
-			pr_info_ratelimited("IOMMU GA Log overflow\n");
-			amd_iommu_restart_ga_log(iommu);
-		}
-#endif
-
-		if (status & MMIO_STATUS_EVT_OVERFLOW_INT_MASK) {
-			pr_info_ratelimited("IOMMU event log overflow\n");
-			amd_iommu_restart_event_logging(iommu);
-		}
+		if ((status & overflow_mask) && overflow_handler)
+			overflow_handler(iommu);
 
 		/*
 		 * Hardware bug: ERBT1312
···
 		 */
 		status = readl(iommu->mmio_base + MMIO_STATUS_OFFSET);
 	}
+}
+
+irqreturn_t amd_iommu_int_thread_evtlog(int irq, void *data)
+{
+	amd_iommu_handle_irq(data, "Evt", MMIO_STATUS_EVT_INT_MASK,
+			     MMIO_STATUS_EVT_OVERFLOW_MASK,
+			     iommu_poll_events, amd_iommu_restart_event_logging);
+
+	return IRQ_HANDLED;
+}
+
+irqreturn_t amd_iommu_int_thread_pprlog(int irq, void *data)
+{
+	amd_iommu_handle_irq(data, "PPR", MMIO_STATUS_PPR_INT_MASK,
+			     MMIO_STATUS_PPR_OVERFLOW_MASK,
+			     iommu_poll_ppr_log, amd_iommu_restart_ppr_log);
+
+	return IRQ_HANDLED;
+}
+
+irqreturn_t amd_iommu_int_thread_galog(int irq, void *data)
+{
+#ifdef CONFIG_IRQ_REMAP
+	amd_iommu_handle_irq(data, "GA", MMIO_STATUS_GALOG_INT_MASK,
+			     MMIO_STATUS_GALOG_OVERFLOW_MASK,
+			     iommu_poll_ga_log, amd_iommu_restart_ga_log);
+#endif
+
+	return IRQ_HANDLED;
+}
+
+irqreturn_t amd_iommu_int_thread(int irq, void *data)
+{
+	amd_iommu_int_thread_evtlog(irq, data);
+	amd_iommu_int_thread_pprlog(irq, data);
+	amd_iommu_int_thread_galog(irq, data);
+
 	return IRQ_HANDLED;
 }
 

drivers/iommu/amd/iommu_v2.c

···
 
 static void put_pasid_state_wait(struct pasid_state *pasid_state)
 {
-	refcount_dec(&pasid_state->count);
-	wait_event(pasid_state->wq, !refcount_read(&pasid_state->count));
+	if (!refcount_dec_and_test(&pasid_state->count))
+		wait_event(pasid_state->wq, !refcount_read(&pasid_state->count));
 	free_pasid_state(pasid_state);
 }
 
···
 			continue;
 
 		put_pasid_state(pasid_state);
+
+		/* Clear the pasid state so that the pasid can be re-used */
+		clear_pasid_state(dev_state, pasid_state->pasid);
 
 		/*
 		 * This will call the mn_release function and

drivers/iommu/apple-dart.c

···
 	return 0;
 }
 
-DEFINE_SIMPLE_DEV_PM_OPS(apple_dart_pm_ops, apple_dart_suspend, apple_dart_resume);
+static DEFINE_SIMPLE_DEV_PM_OPS(apple_dart_pm_ops, apple_dart_suspend, apple_dart_resume);
 
 static const struct of_device_id apple_dart_of_match[] = {
 	{ .compatible = "apple,t8103-dart", .data = &apple_dart_hw_t8103 },

drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c

···
 	 * be some overlap between use of both ASIDs, until we invalidate the
 	 * TLB.
 	 */
-	arm_smmu_write_ctx_desc(smmu_domain, 0, cd);
+	arm_smmu_write_ctx_desc(smmu_domain, IOMMU_NO_PASID, cd);
 
 	/* Invalidate TLB entries previously associated with that context */
 	arm_smmu_tlb_inv_asid(smmu, asid);

drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c

···
 	/*
 	 * This function handles the following cases:
 	 *
-	 * (1) Install primary CD, for normal DMA traffic (SSID = 0).
+	 * (1) Install primary CD, for normal DMA traffic (SSID = IOMMU_NO_PASID = 0).
 	 * (2) Install a secondary CD, for SID+SSID traffic.
 	 * (3) Update ASID of a CD. Atomically write the first 64 bits of the
 	 *     CD, then invalidate the old entry and mappings.
···
 
 	sid = FIELD_GET(PRIQ_0_SID, evt[0]);
 	ssv = FIELD_GET(PRIQ_0_SSID_V, evt[0]);
-	ssid = ssv ? FIELD_GET(PRIQ_0_SSID, evt[0]) : 0;
+	ssid = ssv ? FIELD_GET(PRIQ_0_SSID, evt[0]) : IOMMU_NO_PASID;
 	last = FIELD_GET(PRIQ_0_PRG_LAST, evt[0]);
 	grpid = FIELD_GET(PRIQ_1_PRG_IDX, evt[1]);
 
···
 	 */
 	*cmd = (struct arm_smmu_cmdq_ent) {
 		.opcode			= CMDQ_OP_ATC_INV,
-		.substream_valid	= !!ssid,
+		.substream_valid	= (ssid != IOMMU_NO_PASID),
 		.atc.ssid		= ssid,
 	};
 
···
 	struct arm_smmu_cmdq_ent cmd;
 	struct arm_smmu_cmdq_batch cmds;
 
-	arm_smmu_atc_inv_to_cmd(0, 0, 0, &cmd);
+	arm_smmu_atc_inv_to_cmd(IOMMU_NO_PASID, 0, 0, &cmd);
 
 	cmds.num = 0;
 	for (i = 0; i < master->num_streams; i++) {
···
 		cmd.tlbi.vmid	= smmu_domain->s2_cfg.vmid;
 		arm_smmu_cmdq_issue_cmd_with_sync(smmu, &cmd);
 	}
-	arm_smmu_atc_inv_domain(smmu_domain, 0, 0, 0);
+	arm_smmu_atc_inv_domain(smmu_domain, IOMMU_NO_PASID, 0, 0);
 }
 
 static void __arm_smmu_tlb_inv_range(struct arm_smmu_cmdq_ent *cmd,
···
 	 * Unfortunately, this can't be leaf-only since we may have
 	 * zapped an entire table.
 	 */
-	arm_smmu_atc_inv_domain(smmu_domain, 0, iova, size);
+	arm_smmu_atc_inv_domain(smmu_domain, IOMMU_NO_PASID, iova, size);
 }
 
 void arm_smmu_tlb_inv_range_asid(unsigned long iova, size_t size, int asid,
···
 	return &smmu_domain->domain;
 }
 
-static int arm_smmu_bitmap_alloc(unsigned long *map, int span)
-{
-	int idx, size = 1 << span;
-
-	do {
-		idx = find_first_zero_bit(map, size);
-		if (idx == size)
-			return -ENOSPC;
-	} while (test_and_set_bit(idx, map));
-
-	return idx;
-}
-
-static void arm_smmu_bitmap_free(unsigned long *map, int idx)
-{
-	clear_bit(idx, map);
-}
-
 static void arm_smmu_domain_free(struct iommu_domain *domain)
 {
 	struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);
···
 	} else {
 		struct arm_smmu_s2_cfg *cfg = &smmu_domain->s2_cfg;
 		if (cfg->vmid)
-			arm_smmu_bitmap_free(smmu->vmid_map, cfg->vmid);
+			ida_free(&smmu->vmid_map, cfg->vmid);
 	}
 
 	kfree(smmu_domain);
···
 	 * the master has been added to the devices list for this domain.
 	 * This isn't an issue because the STE hasn't been installed yet.
 	 */
-	ret = arm_smmu_write_ctx_desc(smmu_domain, 0, &cfg->cd);
+	ret = arm_smmu_write_ctx_desc(smmu_domain, IOMMU_NO_PASID, &cfg->cd);
 	if (ret)
 		goto out_free_cd_tables;
 
···
 	struct arm_smmu_s2_cfg *cfg = &smmu_domain->s2_cfg;
 	typeof(&pgtbl_cfg->arm_lpae_s2_cfg.vtcr) vtcr;
 
-	vmid = arm_smmu_bitmap_alloc(smmu->vmid_map, smmu->vmid_bits);
+	/* Reserve VMID 0 for stage-2 bypass STEs */
+	vmid = ida_alloc_range(&smmu->vmid_map, 1, (1 << smmu->vmid_bits) - 1,
+			       GFP_KERNEL);
 	if (vmid < 0)
 		return vmid;
 
···
 	pdev = to_pci_dev(master->dev);
 
 	atomic_inc(&smmu_domain->nr_ats_masters);
-	arm_smmu_atc_inv_domain(smmu_domain, 0, 0, 0);
+	arm_smmu_atc_inv_domain(smmu_domain, IOMMU_NO_PASID, 0, 0);
 	if (pci_enable_ats(pdev, stu))
 		dev_err(master->dev, "Failed to enable ATS (STU %zu)\n", stu);
 }
···
 	reg |= STRTAB_BASE_RA;
 	smmu->strtab_cfg.strtab_base = reg;
 
-	/* Allocate the first VMID for stage-2 bypass STEs */
-	set_bit(0, smmu->vmid_map);
+	ida_init(&smmu->vmid_map);
+
 	return 0;
 }
 
···
 	iommu_device_sysfs_remove(&smmu->iommu);
 	arm_smmu_device_disable(smmu);
 	iopf_queue_free(smmu->evtq.iopf);
+	ida_destroy(&smmu->vmid_map);
 }
 
 static void arm_smmu_device_shutdown(struct platform_device *pdev)

drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h

···
 
 #define ARM_SMMU_MAX_VMIDS		(1 << 16)
 	unsigned int			vmid_bits;
-	DECLARE_BITMAP(vmid_map, ARM_SMMU_MAX_VMIDS);
+	struct ida			vmid_map;
 
 	unsigned int			ssid_bits;
 	unsigned int			sid_bits;

drivers/iommu/arm/arm-smmu/arm-smmu-qcom-debug.c

···
  * Copyright (c) 2022 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
-#include <linux/of_device.h>
+#include <linux/device.h>
 #include <linux/firmware/qcom/qcom_scm.h>
 #include <linux/ratelimit.h>
 

drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c

···
 	{ .compatible = "qcom,sc7280-mss-pil" },
 	{ .compatible = "qcom,sc8180x-mdss" },
 	{ .compatible = "qcom,sc8280xp-mdss" },
-	{ .compatible = "qcom,sm8150-mdss" },
-	{ .compatible = "qcom,sm8250-mdss" },
 	{ .compatible = "qcom,sdm845-mdss" },
 	{ .compatible = "qcom,sdm845-mss-pil" },
+	{ .compatible = "qcom,sm6350-mdss" },
+	{ .compatible = "qcom,sm6375-mdss" },
+	{ .compatible = "qcom,sm8150-mdss" },
+	{ .compatible = "qcom,sm8250-mdss" },
 	{ }
 };
 
···
 	{ .compatible = "qcom,sm6125-smmu-500", .data = &qcom_smmu_500_impl0_data },
 	{ .compatible = "qcom,sm6350-smmu-v2", .data = &qcom_smmu_v2_data },
 	{ .compatible = "qcom,sm6350-smmu-500", .data = &qcom_smmu_500_impl0_data },
+	{ .compatible = "qcom,sm6375-smmu-v2", .data = &qcom_smmu_v2_data },
 	{ .compatible = "qcom,sm6375-smmu-500", .data = &qcom_smmu_500_impl0_data },
 	{ .compatible = "qcom,sm8150-smmu-500", .data = &qcom_smmu_500_impl0_data },
 	{ .compatible = "qcom,sm8250-smmu-500", .data = &qcom_smmu_500_impl0_data },

drivers/iommu/arm/arm-smmu/arm-smmu.c

···
 #include <linux/module.h>
 #include <linux/of.h>
 #include <linux/of_address.h>
-#include <linux/of_device.h>
 #include <linux/pci.h>
 #include <linux/platform_device.h>
 #include <linux/pm_runtime.h>

drivers/iommu/arm/arm-smmu/qcom_iommu.c

···
 #include <linux/init.h>
 #include <linux/mutex.h>
 #include <linux/of.h>
-#include <linux/of_address.h>
-#include <linux/of_device.h>
+#include <linux/of_platform.h>
 #include <linux/platform_device.h>
 #include <linux/pm.h>
 #include <linux/pm_runtime.h>
···
 	struct clk_bulk_data clks[CLK_NUM];
 	void __iomem		*local_base;
 	u32			 sec_id;
-	u8			 num_ctxs;
-	struct qcom_iommu_ctx	*ctxs[];   /* indexed by asid-1 */
+	u8			 max_asid;
+	struct qcom_iommu_ctx	*ctxs[];   /* indexed by asid */
 };
 
 struct qcom_iommu_ctx {
 	struct device		*dev;
 	void __iomem		*base;
 	bool			 secure_init;
+	bool			 secured_ctx;
 	u8			 asid;      /* asid and ctx bank # are 1:1 */
 	struct iommu_domain	*domain;
 };
···
 	struct qcom_iommu_dev *qcom_iommu = d->iommu;
 	if (!qcom_iommu)
 		return NULL;
-	return qcom_iommu->ctxs[asid - 1];
+	return qcom_iommu->ctxs[asid];
 }
 
 static inline void
···
 			}
 			ctx->secure_init = true;
 		}
+
+		/* Secured QSMMU-500/QSMMU-v2 contexts cannot be programmed */
+		if (ctx->secured_ctx) {
+			ctx->domain = domain;
+			continue;
+		}
+
+		/* Disable context bank before programming */
+		iommu_writel(ctx, ARM_SMMU_CB_SCTLR, 0);
+
+		/* Clear context bank fault address fault status registers */
+		iommu_writel(ctx, ARM_SMMU_CB_FAR, 0);
+		iommu_writel(ctx, ARM_SMMU_CB_FSR, ARM_SMMU_FSR_FAULT);
 
 		/* TTBRs */
 		iommu_writeq(ctx, ARM_SMMU_CB_TTBR0,
···
 	qcom_iommu = platform_get_drvdata(iommu_pdev);
 
 	/* make sure the asid specified in dt is valid, so we don't have
-	 * to sanity check this elsewhere, since 'asid - 1' is used to
-	 * index into qcom_iommu->ctxs:
+	 * to sanity check this elsewhere:
 	 */
-	if (WARN_ON(asid < 1) ||
-	    WARN_ON(asid > qcom_iommu->num_ctxs)) {
+	if (WARN_ON(asid > qcom_iommu->max_asid) ||
+	    WARN_ON(qcom_iommu->ctxs[asid] == NULL)) {
 		put_device(&iommu_pdev->dev);
 		return -EINVAL;
 	}
···
 
 static int get_asid(const struct device_node *np)
 {
-	u32 reg;
+	u32 reg, val;
+	int asid;
 
 	/* read the "reg" property directly to get the relative address
 	 * of the context bank, and calculate the asid from that:
···
 	if (of_property_read_u32_index(np, "reg", 0, &reg))
 		return -ENODEV;
 
-	return reg / 0x1000;      /* context banks are 0x1000 apart */
+	/*
+	 * Context banks are 0x1000 apart but, in some cases, the ASID
+	 * number doesn't match to this logic and needs to be passed
+	 * from the DT configuration explicitly.
+	 */
+	if (!of_property_read_u32(np, "qcom,ctx-asid", &val))
+		asid = val;
+	else
+		asid = reg / 0x1000;
+
+	return asid;
 }
 
 static int qcom_iommu_ctx_probe(struct platform_device *pdev)
···
 	struct qcom_iommu_ctx *ctx;
 	struct device *dev = &pdev->dev;
 	struct qcom_iommu_dev *qcom_iommu = dev_get_drvdata(dev->parent);
-	struct resource *res;
 	int ret, irq;
 
 	ctx = devm_kzalloc(dev, sizeof(*ctx), GFP_KERNEL);
···
 	ctx->dev = dev;
 	platform_set_drvdata(pdev, ctx);
 
-	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	ctx->base = devm_ioremap_resource(dev, res);
+	ctx->base = devm_platform_ioremap_resource(pdev, 0);
 	if (IS_ERR(ctx->base))
 		return PTR_ERR(ctx->base);
 
 	irq = platform_get_irq(pdev, 0);
 	if (irq < 0)
-		return -ENODEV;
+		return irq;
+
+	if (of_device_is_compatible(dev->of_node, "qcom,msm-iommu-v2-sec"))
+		ctx->secured_ctx = true;
 
 	/* clear IRQs before registering fault handler, just in case the
 	 * boot-loader left us a surprise:
 	 */
-	iommu_writel(ctx, ARM_SMMU_CB_FSR, iommu_readl(ctx, ARM_SMMU_CB_FSR));
+	if (!ctx->secured_ctx)
+		iommu_writel(ctx, ARM_SMMU_CB_FSR, iommu_readl(ctx, ARM_SMMU_CB_FSR));
 
 	ret = devm_request_irq(dev, irq,
 			       qcom_iommu_fault,
···
 
 	dev_dbg(dev, "found asid %u\n", ctx->asid);
 
-	qcom_iommu->ctxs[ctx->asid - 1] = ctx;
+	qcom_iommu->ctxs[ctx->asid] = ctx;
 
 	return 0;
 }
···
 
 	platform_set_drvdata(pdev, NULL);
 
-	qcom_iommu->ctxs[ctx->asid - 1] = NULL;
+	qcom_iommu->ctxs[ctx->asid] = NULL;
 }
 
 static const struct of_device_id ctx_of_match[] = {
 	{ .compatible = "qcom,msm-iommu-v1-ns" },
 	{ .compatible = "qcom,msm-iommu-v1-sec" },
+	{ .compatible = "qcom,msm-iommu-v2-ns" },
+	{ .compatible = "qcom,msm-iommu-v2-sec" },
 	{ /* sentinel */ }
 };
 
···
 	struct device_node *child;
 
 	for_each_child_of_node(qcom_iommu->dev->of_node, child) {
-		if (of_device_is_compatible(child, "qcom,msm-iommu-v1-sec")) {
+		if (of_device_is_compatible(child, "qcom,msm-iommu-v1-sec") ||
+		    of_device_is_compatible(child, "qcom,msm-iommu-v2-sec")) {
 			of_node_put(child);
 			return true;
 		}
···
 	for_each_child_of_node(dev->of_node, child)
 		max_asid = max(max_asid, get_asid(child));
 
-	qcom_iommu = devm_kzalloc(dev, struct_size(qcom_iommu, ctxs, max_asid),
+	qcom_iommu = devm_kzalloc(dev, struct_size(qcom_iommu, ctxs, max_asid + 1),
 				  GFP_KERNEL);
 	if (!qcom_iommu)
 		return -ENOMEM;
-	qcom_iommu->num_ctxs = max_asid;
+	qcom_iommu->max_asid = max_asid;
 	qcom_iommu->dev = dev;
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
···
 
 static const struct of_device_id qcom_iommu_of_match[] = {
 	{ .compatible = "qcom,msm-iommu-v1" },
+	{ .compatible = "qcom,msm-iommu-v2" },
 	{ /* sentinel */ }
 };
 

drivers/iommu/dma-iommu.c

···
 {
 	struct iommu_dma_cookie *cookie = domain->iova_cookie;
 	struct iova_domain *iovad = &cookie->iovad;
-	unsigned long shift, iova_len, iova = 0;
+	unsigned long shift, iova_len, iova;
 
 	if (cookie->type == IOMMU_DMA_MSI_COOKIE) {
 		cookie->msi_iova += size;
···
 	if (domain->geometry.force_aperture)
 		dma_limit = min(dma_limit, (u64)domain->geometry.aperture_end);
 
-	/* Try to get PCI devices a SAC address */
-	if (dma_limit > DMA_BIT_MASK(32) && !iommu_dma_forcedac && dev_is_pci(dev))
+	/*
+	 * Try to use all the 32-bit PCI addresses first. The original SAC vs.
+	 * DAC reasoning loses relevance with PCIe, but enough hardware and
+	 * firmware bugs are still lurking out there that it's safest not to
+	 * venture into the 64-bit space until necessary.
+	 *
+	 * If your device goes wrong after seeing the notice then likely either
+	 * its driver is not setting DMA masks accurately, the hardware has
+	 * some inherent bug in handling >32-bit addresses, or not all the
+	 * expected address bits are wired up between the device and the IOMMU.
+	 */
+	if (dma_limit > DMA_BIT_MASK(32) && dev->iommu->pci_32bit_workaround) {
 		iova = alloc_iova_fast(iovad, iova_len,
 				       DMA_BIT_MASK(32) >> shift, false);
+		if (iova)
+			goto done;
 
-	if (!iova)
-		iova = alloc_iova_fast(iovad, iova_len, dma_limit >> shift,
-				       true);
+		dev->iommu->pci_32bit_workaround = false;
+		dev_notice(dev, "Using %d-bit DMA addresses\n", bits_per(dma_limit));
+	}
 
+	iova = alloc_iova_fast(iovad, iova_len, dma_limit >> shift, true);
+done:
 	return (dma_addr_t)iova << shift;
 }
 

drivers/iommu/dma-iommu.h

···
 void iommu_dma_get_resv_regions(struct device *dev, struct list_head *list);
 
 extern bool iommu_dma_forcedac;
+static inline void iommu_dma_set_pci_32bit_workaround(struct device *dev)
+{
+	dev->iommu->pci_32bit_workaround = !iommu_dma_forcedac;
+}
 
 #else /* CONFIG_IOMMU_DMA */
 
···
 }
 
 static inline void iommu_dma_get_resv_regions(struct device *dev, struct list_head *list)
+{
+}
+
+static inline void iommu_dma_set_pci_32bit_workaround(struct device *dev)
 {
 }
 

drivers/iommu/intel/iommu.c

···
 
 /* VT-d pages must always be _smaller_ than MM pages. Otherwise things
    are never going to work. */
-static inline unsigned long mm_to_dma_pfn(unsigned long mm_pfn)
+static inline unsigned long mm_to_dma_pfn_start(unsigned long mm_pfn)
 {
 	return mm_pfn << (PAGE_SHIFT - VTD_PAGE_SHIFT);
 }
+static inline unsigned long mm_to_dma_pfn_end(unsigned long mm_pfn)
+{
+	return ((mm_pfn + 1) << (PAGE_SHIFT - VTD_PAGE_SHIFT)) - 1;
+}
 static inline unsigned long page_to_dma_pfn(struct page *pg)
 {
-	return mm_to_dma_pfn(page_to_pfn(pg));
+	return mm_to_dma_pfn_start(page_to_pfn(pg));
 }
 static inline unsigned long virt_to_dma_pfn(void *p)
 {
···
 	}
 	/* For request-without-pasid, get the pasid from context entry */
 	if (intel_iommu_sm && pasid == IOMMU_PASID_INVALID)
-		pasid = PASID_RID2PASID;
+		pasid = IOMMU_NO_PASID;
 
 	dir_index = pasid >> PASID_PDE_SHIFT;
 	pde = &dir[dir_index];
···
 
 static void domain_update_iotlb(struct dmar_domain *domain)
 {
+	struct dev_pasid_info *dev_pasid;
 	struct device_domain_info *info;
 	bool has_iotlb_device = false;
 	unsigned long flags;
 
 	spin_lock_irqsave(&domain->lock, flags);
 	list_for_each_entry(info, &domain->devices, link) {
+		if (info->ats_enabled) {
+			has_iotlb_device = true;
+			break;
+		}
+	}
+
+	list_for_each_entry(dev_pasid, &domain->dev_pasids, link_domain) {
+		info = dev_iommu_priv_get(dev_pasid->dev);
 		if (info->ats_enabled) {
 			has_iotlb_device = true;
 			break;
···
 	qdep = info->ats_qdep;
 	qi_flush_dev_iotlb(info->iommu, sid, info->pfsid,
 			   qdep, addr, mask);
-	quirk_extra_dev_tlb_flush(info, addr, mask, PASID_RID2PASID, qdep);
+	quirk_extra_dev_tlb_flush(info, addr, mask, IOMMU_NO_PASID, qdep);
 }
 
 static void iommu_flush_dev_iotlb(struct dmar_domain *domain,
 				  u64 addr, unsigned mask)
 {
+	struct dev_pasid_info *dev_pasid;
 	struct device_domain_info *info;
 	unsigned long flags;
 
···
 	spin_lock_irqsave(&domain->lock, flags);
 	list_for_each_entry(info, &domain->devices, link)
 		__iommu_flush_dev_iotlb(info, addr, mask);
+
+	list_for_each_entry(dev_pasid, &domain->dev_pasids, link_domain) {
+		info = dev_iommu_priv_get(dev_pasid->dev);
+
+		if (!info->ats_enabled)
+			continue;
+
+		qi_flush_dev_iotlb_pasid(info->iommu,
+					 PCI_DEVID(info->bus, info->devfn),
+					 info->pfsid, dev_pasid->pasid,
+					 info->ats_qdep, addr,
+					 mask);
+	}
+	spin_unlock_irqrestore(&domain->lock, flags);
+}
+
+static void domain_flush_pasid_iotlb(struct intel_iommu *iommu,
+				     struct dmar_domain *domain, u64 addr,
+				     unsigned long npages, bool ih)
+{
+	u16 did = domain_id_iommu(domain, iommu);
+	struct dev_pasid_info *dev_pasid;
+	unsigned long flags;
+
+	spin_lock_irqsave(&domain->lock, flags);
+	list_for_each_entry(dev_pasid, &domain->dev_pasids, link_domain)
+		qi_flush_piotlb(iommu, did, dev_pasid->pasid, addr, npages, ih);
+
+	if (!list_empty(&domain->devices))
+		qi_flush_piotlb(iommu, did, IOMMU_NO_PASID, addr, npages, ih);
 	spin_unlock_irqrestore(&domain->lock, flags);
 }
 
···
 		ih = 1 << 6;
 
 	if (domain->use_first_level) {
-		qi_flush_piotlb(iommu, did, PASID_RID2PASID, addr, pages, ih);
+		domain_flush_pasid_iotlb(iommu, domain, addr, pages, ih);
 	} else {
 		unsigned long bitmask = aligned_pages - 1;
 
···
 		u16 did = domain_id_iommu(dmar_domain, iommu);
 
 		if (dmar_domain->use_first_level)
-			qi_flush_piotlb(iommu, did, PASID_RID2PASID, 0, -1, 0);
+			domain_flush_pasid_iotlb(iommu, dmar_domain, 0, -1, 0);
 		else
 			iommu->flush.flush_iotlb(iommu, did, 0, 0,
 						 DMA_TLB_DSI_FLUSH);
···
 		domain->use_first_level = true;
 	domain->has_iotlb_device = false;
 	INIT_LIST_HEAD(&domain->devices);
+	INIT_LIST_HEAD(&domain->dev_pasids);
 	spin_lock_init(&domain->lock);
 	xa_init(&domain->iommu_array);
 
···
 				context_pdts(pds);
 
 		/* Setup the RID_PASID field: */
-		context_set_sm_rid2pasid(context, PASID_RID2PASID);
+		context_set_sm_rid2pasid(context, IOMMU_NO_PASID);
 
 		/*
 		 * Setup the Device-TLB enable bit and Page request
···
 
 		for_each_mem_pfn_range(i, nid, &start_pfn, &end_pfn, NULL) {
 			ret = iommu_domain_identity_map(si_domain,
-					mm_to_dma_pfn(start_pfn),
-					mm_to_dma_pfn(end_pfn));
+					mm_to_dma_pfn_start(start_pfn),
+					mm_to_dma_pfn_end(end_pfn));
 			if (ret)
 				return ret;
 		}
···
 				continue;
 
 			ret = iommu_domain_identity_map(si_domain,
-					mm_to_dma_pfn(start >> PAGE_SHIFT),
-					mm_to_dma_pfn(end >> PAGE_SHIFT));
+					mm_to_dma_pfn_start(start >> PAGE_SHIFT),
+					mm_to_dma_pfn_end(end >> PAGE_SHIFT));
 			if (ret)
 				return ret;
 		}
···
 		/* Setup the PASID entry for requests without PASID: */
 		if (hw_pass_through && domain_type_is_si(domain))
 			ret = intel_pasid_setup_pass_through(iommu, domain,
-					dev, PASID_RID2PASID);
+					dev, IOMMU_NO_PASID);
 		else if (domain->use_first_level)
 			ret = domain_setup_first_level(iommu, domain, dev,
-					PASID_RID2PASID);
+					IOMMU_NO_PASID);
 		else
 			ret = intel_pasid_setup_second_level(iommu, domain,
-					dev, PASID_RID2PASID);
+					dev, IOMMU_NO_PASID);
 		if (ret) {
 			dev_err(dev, "Setup RID2PASID failed\n");
 			device_block_translation(dev);
···
 	iommu_enable_pci_caps(info);
 
 	return 0;
-}
-
-static bool device_has_rmrr(struct device *dev)
-{
-	struct dmar_rmrr_unit *rmrr;
-	struct device *tmp;
-	int i;
-
-	rcu_read_lock();
-	for_each_rmrr_units(rmrr) {
-		/*
-		 * Return TRUE if this RMRR contains the device that
-		 * is passed in.
-		 */
-		for_each_active_dev_scope(rmrr->devices,
-					  rmrr->devices_cnt, i, tmp)
-			if (tmp == dev ||
-			    is_downstream_to_pci_bridge(dev, tmp)) {
-				rcu_read_unlock();
-				return true;
-			}
-	}
-	rcu_read_unlock();
-	return false;
 }
 
 /**
···
 		return true;
 	else
 		return false;
-}
-
-/*
- * There are a couple cases where we need to restrict the functionality of
- * devices associated with RMRRs.  The first is when evaluating a device for
- * identity mapping because problems exist when devices are moved in and out
- * of domains and their respective RMRR information is lost.  This means that
- * a device with associated RMRRs will never be in a "passthrough" domain.
- * The second is use of the device through the IOMMU API.  This interface
- * expects to have full control of the IOVA space for the device.  We cannot
- * satisfy both the requirement that RMRR access is maintained and have an
- * unencumbered IOVA space.  We also have no ability to quiesce the device's
- * use of the RMRR space or even inform the IOMMU API user of the restriction.
- * We therefore prevent devices associated with an RMRR from participating in
- * the IOMMU API, which eliminates them from device assignment.
- *
- * In both cases, devices which have relaxable RMRRs are not concerned by this
- * restriction. See device_rmrr_is_relaxable comment.
- */
-static bool device_is_rmrr_locked(struct device *dev)
-{
-	if (!device_has_rmrr(dev))
-		return false;
-
-	if (device_rmrr_is_relaxable(dev))
-		return false;
-
-	return true;
 }
 
 /*
···
 				       unsigned long val, void *v)
 {
 	struct memory_notify *mhp = v;
-	unsigned long start_vpfn = mm_to_dma_pfn(mhp->start_pfn);
-	unsigned long last_vpfn = mm_to_dma_pfn(mhp->start_pfn +
+	unsigned long start_vpfn = mm_to_dma_pfn_start(mhp->start_pfn);
+	unsigned long last_vpfn = mm_to_dma_pfn_end(mhp->start_pfn +
 			mhp->nr_pages - 1);
 
 	switch (val) {
···
 		for_each_active_dev_scope(drhd->devices,
 					  drhd->devices_cnt, i, dev) {
 			struct acpi_device_physical_node *pn;
-			struct iommu_group *group;
 			struct acpi_device *adev;
 
 			if (dev->bus != &acpi_bus_type)
···
 			mutex_lock(&adev->physical_node_lock);
 			list_for_each_entry(pn,
 					    &adev->physical_node_list, node) {
-				group = iommu_group_get(pn->dev);
-				if (group) {
-					iommu_group_put(group);
-					continue;
-				}
-
 				ret = iommu_probe_device(pn->dev);
 				if (ret)
 					break;
···
 	if (!dev_is_real_dma_subdevice(info->dev)) {
 		if (dev_is_pci(info->dev) && sm_supported(iommu))
 			intel_pasid_tear_down_entry(iommu, info->dev,
-					PASID_RID2PASID, false);
+					IOMMU_NO_PASID, false);
 
 		iommu_disable_pci_caps(info);
 		domain_context_clear(info);
···
 	if (!dev_is_real_dma_subdevice(dev)) {
 		if (sm_supported(iommu))
 			intel_pasid_tear_down_entry(iommu, dev,
-						    PASID_RID2PASID, false);
+						    IOMMU_NO_PASID, false);
 		else
 			domain_context_clear(info);
 	}
···
 	struct device_domain_info *info = dev_iommu_priv_get(dev);
 	int ret;
 
-	if (domain->type == IOMMU_DOMAIN_UNMANAGED &&
-	    device_is_rmrr_locked(dev)) {
-		dev_warn(dev, "Device is ineligible for IOMMU domain attach due to platform RMRR requirement.  Contact your platform vendor.\n");
-		return -EPERM;
-	}
-
 	if (info->domain)
 		device_block_translation(dev);
 
···
 	unsigned long i;
 
 	nrpages = aligned_nrpages(gather->start, size);
-	start_pfn = mm_to_dma_pfn(iova_pfn);
+	start_pfn = mm_to_dma_pfn_start(iova_pfn);
 
 	xa_for_each(&dmar_domain->iommu_array, i, info)
 		iommu_flush_iotlb_psi(info->iommu, dmar_domain,
···
 
 	list_for_each_entry(info, &domain->devices, link)
 		intel_pasid_setup_page_snoop_control(info->iommu, info->dev,
-						     PASID_RID2PASID);
+						     IOMMU_NO_PASID);
 }
 
 static bool intel_iommu_enforce_cache_coherency(struct iommu_domain *domain)
···
 static void intel_iommu_remove_dev_pasid(struct device *dev, ioasid_t pasid)
 {
 	struct intel_iommu *iommu = device_to_iommu(dev, NULL, NULL);
+	struct dev_pasid_info *curr, *dev_pasid = NULL;
+	struct dmar_domain *dmar_domain;
 	struct iommu_domain *domain;
+	unsigned long flags;
 
-	/* Domain type specific cleanup: */
 	domain = iommu_get_domain_for_dev_pasid(dev, pasid, 0);
-	if (domain) {
-		switch (domain->type) {
-		case IOMMU_DOMAIN_SVA:
-			intel_svm_remove_dev_pasid(dev, pasid);
-			break;
-		default:
-			/* should never reach here */
-			WARN_ON(1);
+	if (WARN_ON_ONCE(!domain))
+		goto out_tear_down;
+
+	/*
+	 * The SVA implementation needs to handle its own stuffs like the mm
+	 * notification. Before consolidating that code into iommu core, let
+	 * the intel sva code handle it.
+	 */
+	if (domain->type == IOMMU_DOMAIN_SVA) {
+		intel_svm_remove_dev_pasid(dev, pasid);
+		goto out_tear_down;
+	}
+
+	dmar_domain = to_dmar_domain(domain);
+	spin_lock_irqsave(&dmar_domain->lock, flags);
+	list_for_each_entry(curr, &dmar_domain->dev_pasids, link_domain) {
+		if (curr->dev == dev && curr->pasid == pasid) {
+			list_del(&curr->link_domain);
+			dev_pasid = curr;
 			break;
 		}
 	}
+	WARN_ON_ONCE(!dev_pasid);
+	spin_unlock_irqrestore(&dmar_domain->lock, flags);
 
+	domain_detach_iommu(dmar_domain, iommu);
+	kfree(dev_pasid);
+out_tear_down:
 	intel_pasid_tear_down_entry(iommu, dev, pasid, false);
+	intel_drain_pasid_prq(dev, pasid);
+}
+
+static int intel_iommu_set_dev_pasid(struct iommu_domain *domain,
+				     struct device *dev, ioasid_t pasid)
+{
+	struct device_domain_info *info = dev_iommu_priv_get(dev);
+	struct dmar_domain *dmar_domain = to_dmar_domain(domain);
+	struct intel_iommu *iommu = info->iommu;
+	struct dev_pasid_info *dev_pasid;
+	unsigned long flags;
+	int ret;
+
+	if (!pasid_supported(iommu) || dev_is_real_dma_subdevice(dev))
+		return -EOPNOTSUPP;
+
+	if (context_copied(iommu, info->bus, info->devfn))
+		return -EBUSY;
+
+	ret = prepare_domain_attach_device(domain, dev);
+	if (ret)
+		return ret;
+
+	dev_pasid = kzalloc(sizeof(*dev_pasid), GFP_KERNEL);
+	if (!dev_pasid)
+		return -ENOMEM;
+
+	ret = domain_attach_iommu(dmar_domain, iommu);
+	if (ret)
+		goto out_free;
+
+	if (domain_type_is_si(dmar_domain))
+		ret = intel_pasid_setup_pass_through(iommu, dmar_domain,
+						     dev, pasid);
+	else if (dmar_domain->use_first_level)
+		ret = domain_setup_first_level(iommu, dmar_domain,
+					       dev, pasid);
+	else
+		ret = intel_pasid_setup_second_level(iommu, dmar_domain,
+						     dev, pasid);
+	if (ret)
+		goto out_detach_iommu;
+
+	dev_pasid->dev = dev;
+	dev_pasid->pasid = pasid;
+	spin_lock_irqsave(&dmar_domain->lock, flags);
+	list_add(&dev_pasid->link_domain, &dmar_domain->dev_pasids);
+	spin_unlock_irqrestore(&dmar_domain->lock, flags);
+
+	return 0;
+out_detach_iommu:
+	domain_detach_iommu(dmar_domain, iommu);
+out_free:
+	kfree(dev_pasid);
+	return ret;
 }
 
 static void *intel_iommu_hw_info(struct device *dev, u32 *length, u32 *type)
···
 #endif
 	.default_domain_ops = &(const struct iommu_domain_ops) {
 		.attach_dev		= intel_iommu_attach_device,
+		.set_dev_pasid		= intel_iommu_set_dev_pasid,
 		.map_pages		= intel_iommu_map_pages,
 		.unmap_pages		= intel_iommu_unmap_pages,
 		.iotlb_sync_map		= intel_iommu_iotlb_sync_map,
···
 		return;
 
 	sid = PCI_DEVID(info->bus, info->devfn);
-	if (pasid == PASID_RID2PASID) {
+	if (pasid == IOMMU_NO_PASID) {
 		qi_flush_dev_iotlb(info->iommu, sid, info->pfsid,
 				   qdep, address, mask);
 	} else {

drivers/iommu/intel/iommu.h

···
 
 	spinlock_t lock;		/* Protect device tracking lists */
 	struct list_head devices;	/* all devices' list */
+	struct list_head dev_pasids;	/* all attached pasids */
 
 	struct dma_pte	*pgd;		/* virtual address */
 	int		gaw;		/* max guest address width */
···
 	struct intel_iommu *iommu; /* IOMMU used by this device */
 	struct dmar_domain *domain; /* pointer to domain */
 	struct pasid_table *pasid_table; /* pasid table */
+};
+
+struct dev_pasid_info {
+	struct list_head link_domain;	/* link to domain siblings */
+	struct device *dev;
+	ioasid_t pasid;
 };
 
 static inline void __iommu_flush_cache(
···
 			    struct iommu_page_response *msg);
 struct iommu_domain *intel_svm_domain_alloc(void);
 void intel_svm_remove_dev_pasid(struct device *dev, ioasid_t pasid);
+void intel_drain_pasid_prq(struct device *dev, u32 pasid);
 
 struct intel_svm_dev {
 	struct list_head list;
···
 };
 #else
 static inline void intel_svm_check(struct intel_iommu *iommu) {}
+static inline void intel_drain_pasid_prq(struct device *dev, u32 pasid) {}
 static inline struct iommu_domain *intel_svm_domain_alloc(void)
 {
 	return NULL;

drivers/iommu/intel/pasid.c

···
 	info->pasid_table = pasid_table;
 
 	if (!ecap_coherent(info->iommu->ecap))
-		clflush_cache_range(pasid_table->table, size);
+		clflush_cache_range(pasid_table->table, (1 << order) * PAGE_SIZE);
 
 	return 0;
 }
···
 	 * SVA usage, device could do DMA with multiple PASIDs. It is more
 	 * efficient to flush devTLB specific to the PASID.
 	 */
-	if (pasid == PASID_RID2PASID)
+	if (pasid == IOMMU_NO_PASID)
 		qi_flush_dev_iotlb(iommu, sid, pfsid, qdep, 0, 64 - VTD_PAGE_SHIFT);
 	else
 		qi_flush_dev_iotlb_pasid(iommu, sid, pfsid, pasid, qdep, 0, 64 - VTD_PAGE_SHIFT);

drivers/iommu/intel/pasid.h

···
 #ifndef __INTEL_PASID_H
 #define __INTEL_PASID_H
 
-#define PASID_RID2PASID			0x0
-#define PASID_MIN			0x1
 #define PASID_MAX			0x100000
 #define PASID_PTE_MASK			0x3F
 #define PASID_PTE_PRESENT		1

drivers/iommu/intel/svm.c

···
 #include "trace.h"
 
 static irqreturn_t prq_event_thread(int irq, void *d);
-static void intel_svm_drain_prq(struct device *dev, u32 pasid);
-#define to_intel_svm_dev(handle) container_of(handle, struct intel_svm_dev, sva)
 
 static DEFINE_XARRAY_ALLOC(pasid_private_array);
 static int pasid_private_add(ioasid_t pasid, void *priv)
···
 	.arch_invalidate_secondary_tlbs = intel_arch_invalidate_secondary_tlbs,
 };
 
-static DEFINE_MUTEX(pasid_mutex);
-
 static int pasid_to_svm_sdev(struct device *dev, unsigned int pasid,
 			     struct intel_svm **rsvm,
 			     struct intel_svm_dev **rsdev)
 {
 	struct intel_svm_dev *sdev = NULL;
 	struct intel_svm *svm;
-
-	/* The caller should hold the pasid_mutex lock */
-	if (WARN_ON(!mutex_is_locked(&pasid_mutex)))
-		return -EINVAL;
 
 	if (pasid == IOMMU_PASID_INVALID || pasid >= PASID_MAX)
 		return -EINVAL;
···
 	return ret;
 }
 
-/* Caller must hold pasid_mutex */
-static int intel_svm_unbind_mm(struct device *dev, u32 pasid)
+void intel_svm_remove_dev_pasid(struct device *dev, u32 pasid)
 {
 	struct intel_svm_dev *sdev;
 	struct intel_iommu *iommu;
 	struct intel_svm *svm;
 	struct mm_struct *mm;
-	int ret = -EINVAL;
 
 	iommu = device_to_iommu(dev, NULL, NULL);
 	if (!iommu)
-		goto out;
+		return;
 
-	ret = pasid_to_svm_sdev(dev, pasid, &svm, &sdev);
-	if (ret)
-		goto out;
+	if (pasid_to_svm_sdev(dev, pasid, &svm, &sdev))
+		return;
 	mm = svm->mm;
 
 	if (sdev) {
 		list_del_rcu(&sdev->list);
-		/*
-		 * Flush the PASID cache and IOTLB for this device.
-		 * Note that we do depend on the hardware *not* using
-		 * the PASID any more. Just as we depend on other
-		 * devices never using PASIDs that they have no right
-		 * to use. We have a *shared* PASID table, because it's
-		 * large and has to be physically contiguous. So it's
-		 * hard to be as defensive as we might like.
-		 */
-		intel_pasid_tear_down_entry(iommu, dev, svm->pasid, false);
-		intel_svm_drain_prq(dev, svm->pasid);
 		kfree_rcu(sdev, rcu);
 
 		if (list_empty(&svm->devs)) {
···
 			kfree(svm);
 		}
 	}
-out:
-	return ret;
 }
 
 /* Page request queue descriptor */
···
 }
 
 /**
- * intel_svm_drain_prq - Drain page requests and responses for a pasid
+ * intel_drain_pasid_prq - Drain page requests and responses for a pasid
  * @dev: target device
  * @pasid: pasid for draining
  *
···
  * described in VT-d spec CH7.10 to drain all page requests and page
  * responses pending in the hardware.
  */
-static void intel_svm_drain_prq(struct device *dev, u32 pasid)
+void intel_drain_pasid_prq(struct device *dev, u32 pasid)
 {
 	struct device_domain_info *info;
 	struct dmar_domain *domain;
···
 		goto prq_retry;
 	}
 
-	/*
-	 * A work in IO page fault workqueue may try to lock pasid_mutex now.
-	 * Holding pasid_mutex while waiting in iopf_queue_flush_dev() for
-	 * all works in the workqueue to finish may cause deadlock.
-	 *
-	 * It's unnecessary to hold pasid_mutex in iopf_queue_flush_dev().
-	 * Unlock it to allow the works to be handled while waiting for
-	 * them to finish.
-	 */
-	lockdep_assert_held(&pasid_mutex);
-	mutex_unlock(&pasid_mutex);
 	iopf_queue_flush_dev(dev);
-	mutex_lock(&pasid_mutex);
 
 	/*
 	 * Perform steps described in VT-d spec CH7.10 to drain page
···
 	return ret;
 }
 
-void intel_svm_remove_dev_pasid(struct device *dev, ioasid_t pasid)
-{
-	mutex_lock(&pasid_mutex);
-	intel_svm_unbind_mm(dev, pasid);
-	mutex_unlock(&pasid_mutex);
-}
-
 static int intel_svm_set_dev_pasid(struct iommu_domain *domain,
 				   struct device *dev, ioasid_t pasid)
 {
 	struct device_domain_info *info = dev_iommu_priv_get(dev);
 	struct intel_iommu *iommu = info->iommu;
 	struct mm_struct *mm = domain->mm;
-	int ret;
 
-	mutex_lock(&pasid_mutex);
-	ret = intel_svm_bind_mm(iommu, dev, mm);
-	mutex_unlock(&pasid_mutex);
-
-	return ret;
+	return intel_svm_bind_mm(iommu, dev, mm);
 }
 
 static void intel_svm_domain_free(struct iommu_domain *domain)

drivers/iommu/iommu-sva.c

···
 #include "iommu-sva.h"
 
 static DEFINE_MUTEX(iommu_sva_lock);
-static DEFINE_IDA(iommu_global_pasid_ida);
 
 /* Allocate a PASID for the mm within range (inclusive) */
-static int iommu_sva_alloc_pasid(struct mm_struct *mm, ioasid_t min, ioasid_t max)
+static int iommu_sva_alloc_pasid(struct mm_struct *mm, struct device *dev)
 {
+	ioasid_t pasid;
 	int ret = 0;
-
-	if (min == IOMMU_PASID_INVALID ||
-	    max == IOMMU_PASID_INVALID ||
-	    min == 0 || max < min)
-		return -EINVAL;
 
 	if (!arch_pgtable_dma_compat(mm))
 		return -EBUSY;
···
 	mutex_lock(&iommu_sva_lock);
 	/* Is a PASID already associated with this mm? */
 	if (mm_valid_pasid(mm)) {
-		if (mm->pasid < min || mm->pasid > max)
+		if (mm->pasid >= dev->iommu->max_pasids)
 			ret = -EOVERFLOW;
 		goto out;
 	}
 
-	ret = ida_alloc_range(&iommu_global_pasid_ida, min, max, GFP_KERNEL);
-	if (ret < 0)
+	pasid = iommu_alloc_global_pasid(dev);
+	if (pasid == IOMMU_PASID_INVALID) {
+		ret = -ENOSPC;
 		goto out;
-
-	mm->pasid = ret;
+	}
+	mm->pasid = pasid;
 	ret = 0;
 out:
 	mutex_unlock(&iommu_sva_lock);
···
 {
 	struct iommu_domain *domain;
 	struct iommu_sva *handle;
-	ioasid_t max_pasids;
 	int ret;
 
-	max_pasids = dev->iommu->max_pasids;
-	if (!max_pasids)
-		return ERR_PTR(-EOPNOTSUPP);
-
 	/* Allocate mm->pasid if necessary. */
-	ret = iommu_sva_alloc_pasid(mm, 1, max_pasids - 1);
+	ret = iommu_sva_alloc_pasid(mm, dev);
 	if (ret)
 		return ERR_PTR(ret);
 
···
 	if (likely(!mm_valid_pasid(mm)))
 		return;
 
-	ida_free(&iommu_global_pasid_ida, mm->pasid);
+	iommu_free_global_pasid(mm->pasid);
 }

drivers/iommu/iommu-sysfs.c

···
 {
 	int ret;
 
-	if (!iommu || IS_ERR(iommu))
-		return -ENODEV;
-
 	ret = sysfs_add_link_to_group(&iommu->dev->kobj, "devices",
 				      &link->kobj, dev_name(link));
 	if (ret)
···
 
 	return ret;
 }
-EXPORT_SYMBOL_GPL(iommu_device_link);
 
 void iommu_device_unlink(struct iommu_device *iommu, struct device *link)
 {
-	if (!iommu || IS_ERR(iommu))
-		return;
-
 	sysfs_remove_link(&link->kobj, "iommu");
 	sysfs_remove_link_from_group(&iommu->dev->kobj, "devices", dev_name(link));
 }
-EXPORT_SYMBOL_GPL(iommu_device_unlink);

drivers/iommu/iommu.c

···
 
 static struct kset *iommu_group_kset;
 static DEFINE_IDA(iommu_group_ida);
+static DEFINE_IDA(iommu_global_pasid_ida);
 
 static unsigned int iommu_def_domain_type __read_mostly;
 static bool iommu_dma_strict __read_mostly = IS_ENABLED(CONFIG_IOMMU_DEFAULT_DMA_STRICT);
···
 				      int target_type);
 static int iommu_create_device_direct_mappings(struct iommu_domain *domain,
 					       struct device *dev);
-static struct iommu_group *iommu_group_get_for_dev(struct device *dev);
 static ssize_t iommu_group_store_type(struct iommu_group *group,
 				      const char *buf, size_t count);
+static struct group_device *iommu_group_alloc_device(struct iommu_group *group,
+						     struct device *dev);
+static void __iommu_group_free_device(struct iommu_group *group,
+				      struct group_device *grp_dev);
 
 #define IOMMU_GROUP_ATTR(_name, _mode, _show, _store)		\
 struct iommu_group_attribute iommu_group_attr_##_name =		\
···
 	return min_t(u32, max_pasids, dev->iommu->iommu_dev->max_pasids);
 }
 
+/*
+ * Init the dev->iommu and dev->iommu_group in the struct device and get the
+ * driver probed
+ */
+static int iommu_init_device(struct device *dev, const struct iommu_ops *ops)
+{
+	struct iommu_device *iommu_dev;
+	struct iommu_group *group;
+	int ret;
+
+	if (!dev_iommu_get(dev))
+		return -ENOMEM;
+
+	if (!try_module_get(ops->owner)) {
+		ret = -EINVAL;
+		goto err_free;
+	}
+
+	iommu_dev = ops->probe_device(dev);
+	if (IS_ERR(iommu_dev)) {
+		ret = PTR_ERR(iommu_dev);
+		goto err_module_put;
+	}
+
+	ret = iommu_device_link(iommu_dev, dev);
+	if (ret)
+		goto err_release;
+
+	group = ops->device_group(dev);
+	if (WARN_ON_ONCE(group == NULL))
+		group = ERR_PTR(-EINVAL);
+	if (IS_ERR(group)) {
+		ret = PTR_ERR(group);
+		goto err_unlink;
+	}
+	dev->iommu_group = group;
+
+	dev->iommu->iommu_dev = iommu_dev;
+	dev->iommu->max_pasids = dev_iommu_get_max_pasids(dev);
+	if (ops->is_attach_deferred)
+		dev->iommu->attach_deferred = ops->is_attach_deferred(dev);
+	return 0;
+
+err_unlink:
+	iommu_device_unlink(iommu_dev, dev);
+err_release:
+	if (ops->release_device)
+		ops->release_device(dev);
+err_module_put:
+	module_put(ops->owner);
+err_free:
+	dev_iommu_free(dev);
+	return ret;
+}
+
+static void iommu_deinit_device(struct device *dev)
+{
+	struct iommu_group *group = dev->iommu_group;
+	const struct iommu_ops *ops = dev_iommu_ops(dev);
+
+	lockdep_assert_held(&group->mutex);
+
+	iommu_device_unlink(dev->iommu->iommu_dev, dev);
+
+	/*
+	 * release_device() must stop using any attached domain on the device.
+	 * If there are still other devices in the group they are not effected
+	 * by this callback.
+	 *
+	 * The IOMMU driver must set the device to either an identity or
+	 * blocking translation and stop using any domain pointer, as it is
+	 * going to be freed.
+	 */
+	if (ops->release_device)
+		ops->release_device(dev);
+
+	/*
+	 * If this is the last driver to use the group then we must free the
+	 * domains before we do the module_put().
+	 */
+	if (list_empty(&group->devices)) {
+		if (group->default_domain) {
+			iommu_domain_free(group->default_domain);
+			group->default_domain = NULL;
+		}
+		if (group->blocking_domain) {
+			iommu_domain_free(group->blocking_domain);
+			group->blocking_domain = NULL;
+		}
+		group->domain = NULL;
+	}
+
+	/* Caller must put iommu_group */
+	dev->iommu_group = NULL;
+	module_put(ops->owner);
+	dev_iommu_free(dev);
+}
+
 static int __iommu_probe_device(struct device *dev, struct list_head *group_list)
 {
 	const struct iommu_ops *ops = dev->bus->iommu_ops;
-	struct iommu_device *iommu_dev;
 	struct iommu_group *group;
 	static DEFINE_MUTEX(iommu_probe_device_lock);
+	struct group_device *gdev;
 	int ret;
 
 	if (!ops)
···
 	 * but for now enforcing a simple global ordering is fine.
 	 */
 	mutex_lock(&iommu_probe_device_lock);
-	if (!dev_iommu_get(dev)) {
-		ret = -ENOMEM;
-		goto err_unlock;
+
+	/* Device is probed already if in a group */
+	if (dev->iommu_group) {
+		ret = 0;
+		goto out_unlock;
 	}
 
-	if (!try_module_get(ops->owner)) {
-		ret = -EINVAL;
-		goto err_free;
-	}
+	ret = iommu_init_device(dev, ops);
+	if (ret)
+		goto out_unlock;
 
-	iommu_dev = ops->probe_device(dev);
-	if (IS_ERR(iommu_dev)) {
-		ret = PTR_ERR(iommu_dev);
-		goto out_module_put;
-	}
-
-	dev->iommu->iommu_dev = iommu_dev;
-	dev->iommu->max_pasids = dev_iommu_get_max_pasids(dev);
-	if (ops->is_attach_deferred)
-		dev->iommu->attach_deferred = ops->is_attach_deferred(dev);
-
-	group = iommu_group_get_for_dev(dev);
-	if (IS_ERR(group)) {
-		ret = PTR_ERR(group);
-		goto out_release;
-	}
-
+	group = dev->iommu_group;
+	gdev = iommu_group_alloc_device(group, dev);
 	mutex_lock(&group->mutex);
-	if (group_list && !group->default_domain && list_empty(&group->entry))
-		list_add_tail(&group->entry, group_list);
-	mutex_unlock(&group->mutex);
-	iommu_group_put(group);
+	if (IS_ERR(gdev)) {
+		ret = PTR_ERR(gdev);
+		goto err_put_group;
+	}
 
+	/*
+	 * The gdev must be in the list before calling
+	 * iommu_setup_default_domain()
+	 */
+	list_add_tail(&gdev->list, &group->devices);
+	WARN_ON(group->default_domain && !group->domain);
+	if (group->default_domain)
+		iommu_create_device_direct_mappings(group->default_domain, dev);
+	if (group->domain) {
+		ret = __iommu_device_set_domain(group, dev, group->domain, 0);
+		if (ret)
+			goto err_remove_gdev;
+	} else if (!group->default_domain && !group_list) {
+		ret = iommu_setup_default_domain(group, 0);
+		if (ret)
+			goto err_remove_gdev;
+	} else if (!group->default_domain) {
+		/*
+		 * With a group_list argument we defer the default_domain setup
+		 * to the caller by providing a de-duplicated list of groups
+		 * that need further setup.
+		 */
+		if (list_empty(&group->entry))
+			list_add_tail(&group->entry, group_list);
+	}
+	mutex_unlock(&group->mutex);
 	mutex_unlock(&iommu_probe_device_lock);
-	iommu_device_link(iommu_dev, dev);
+
+	if (dev_is_pci(dev))
+		iommu_dma_set_pci_32bit_workaround(dev);
 
 	return 0;
 
-out_release:
-	if (ops->release_device)
-		ops->release_device(dev);
-
-out_module_put:
-	module_put(ops->owner);
-
-err_free:
-	dev_iommu_free(dev);
-
-err_unlock:
+err_remove_gdev:
+	list_del(&gdev->list);
+	__iommu_group_free_device(group, gdev);
+err_put_group:
+	iommu_deinit_device(dev);
+	mutex_unlock(&group->mutex);
+	iommu_group_put(group);
+out_unlock:
 	mutex_unlock(&iommu_probe_device_lock);
 
 	return ret;
···
 int iommu_probe_device(struct device *dev)
 {
 	const struct iommu_ops *ops;
-	struct iommu_group *group;
 	int ret;
 
 	ret = __iommu_probe_device(dev, NULL);
 	if (ret)
-		goto err_out;
-
-	group = iommu_group_get(dev);
-	if (!group) {
-		ret = -ENODEV;
-		goto err_release;
-	}
-
-	mutex_lock(&group->mutex);
-
-	if (group->default_domain)
-		iommu_create_device_direct_mappings(group->default_domain, dev);
-
-	if (group->domain) {
-		ret = __iommu_device_set_domain(group, dev, group->domain, 0);
-		if (ret)
-			goto err_unlock;
-	} else if (!group->default_domain) {
-		ret = iommu_setup_default_domain(group, 0);
-		if (ret)
-			goto err_unlock;
-	}
-
-	mutex_unlock(&group->mutex);
-	iommu_group_put(group);
+		return ret;
 
 	ops = dev_iommu_ops(dev);
 	if (ops->probe_finalize)
 		ops->probe_finalize(dev);
 
 	return 0;
-
-err_unlock:
-	mutex_unlock(&group->mutex);
-	iommu_group_put(group);
-err_release:
-	iommu_release_device(dev);
-
-err_out:
-	return ret;
-
 }
 
-/*
- * Remove a device from a group's device list and return the group device
- * if successful.
- */
-static struct group_device *
-__iommu_group_remove_device(struct iommu_group *group, struct device *dev)
-{
-	struct group_device *device;
-
-	lockdep_assert_held(&group->mutex);
-	for_each_group_device(group, device) {
-		if (device->dev == dev) {
-			list_del(&device->list);
-			return device;
-		}
-	}
-
-	return NULL;
-}
-
-/*
- * Release a device from its group and decrements the iommu group reference
- * count.
- */
-static void __iommu_group_release_device(struct iommu_group *group,
-					 struct group_device *grp_dev)
+static void __iommu_group_free_device(struct iommu_group *group,
+				      struct group_device *grp_dev)
 {
 	struct device *dev = grp_dev->dev;
 
···
 
 	trace_remove_device_from_group(group->id, dev);
 
-	kfree(grp_dev->name);
-	kfree(grp_dev);
-	dev->iommu_group = NULL;
-	kobject_put(group->devices_kobj);
-}
-
-static void iommu_release_device(struct device *dev)
-{
-	struct iommu_group *group = dev->iommu_group;
-	struct group_device *device;
-	const struct iommu_ops *ops;
-
-	if (!dev->iommu || !group)
-		return;
-
-	iommu_device_unlink(dev->iommu->iommu_dev, dev);
-
-	mutex_lock(&group->mutex);
-	device = __iommu_group_remove_device(group, dev);
-
 	/*
-	 * If the group has become empty then ownership must have been released,
-	 * and the current domain must be set back to NULL or the default
-	 * domain.
+	 * If the group has become empty then ownership must have been
+	 * released, and the current domain must be set back to NULL or
+	 * the default domain.
 	 */
 	if (list_empty(&group->devices))
 		WARN_ON(group->owner_cnt ||
 			group->domain != group->default_domain);
 
-	/*
-	 * release_device() must stop using any attached domain on the device.
-	 * If there are still other devices in the group they are not effected
-	 * by this callback.
-	 *
-	 * The IOMMU driver must set the device to either an identity or
-	 * blocking translation and stop using any domain pointer, as it is
-	 * going to be freed.
-	 */
-	ops = dev_iommu_ops(dev);
-	if (ops->release_device)
-		ops->release_device(dev);
+	kfree(grp_dev->name);
+	kfree(grp_dev);
+}
+
+/* Remove the iommu_group from the struct device. */
+static void __iommu_group_remove_device(struct device *dev)
+{
+	struct iommu_group *group = dev->iommu_group;
+	struct group_device *device;
+
+	mutex_lock(&group->mutex);
+	for_each_group_device(group, device) {
+		if (device->dev != dev)
+			continue;
+
+		list_del(&device->list);
+		__iommu_group_free_device(group, device);
+		if (dev->iommu && dev->iommu->iommu_dev)
+			iommu_deinit_device(dev);
+		else
+			dev->iommu_group = NULL;
+		break;
+	}
 	mutex_unlock(&group->mutex);
 
-	if (device)
-		__iommu_group_release_device(group, device);
+	/*
+	 * Pairs with the get in iommu_init_device() or
+	 * iommu_group_add_device()
+	 */
+	iommu_group_put(group);
+}
 
-	module_put(ops->owner);
-	dev_iommu_free(dev);
+static void iommu_release_device(struct device *dev)
+{
+	struct iommu_group *group = dev->iommu_group;
+
+	if (group)
+		__iommu_group_remove_device(dev);
+
+	/* Free any fwspec if no iommu_driver was ever attached */
+	if (dev->iommu)
+		dev_iommu_free(dev);
 }
 
 static int __init iommu_set_def_domain_type(char *str)
···
 
 	ida_free(&iommu_group_ida, group->id);
 
-	if (group->default_domain)
-		iommu_domain_free(group->default_domain);
-	if (group->blocking_domain)
-		iommu_domain_free(group->blocking_domain);
+	/* Domains are free'd by iommu_deinit_device() */
+	WARN_ON(group->default_domain);
+	WARN_ON(group->blocking_domain);
 
 	kfree(group->name);
 	kfree(group);
···
 	unsigned long pg_size;
 	int ret = 0;
 
-	if (!iommu_is_dma_domain(domain))
-		return 0;
-
-	BUG_ON(!domain->pgsize_bitmap);
-
-	pg_size = 1UL << __ffs(domain->pgsize_bitmap);
+	pg_size = domain->pgsize_bitmap ? 1UL << __ffs(domain->pgsize_bitmap) : 0;
 	INIT_LIST_HEAD(&mappings);
+
+	if (WARN_ON_ONCE(iommu_is_dma_domain(domain) && !pg_size))
+		return -EINVAL;
 
 	iommu_get_resv_regions(dev, &mappings);
 
···
 		dma_addr_t start, end, addr;
 		size_t map_size = 0;
 
+		if (entry->type == IOMMU_RESV_DIRECT)
+			dev->iommu->require_direct = 1;
+
+		if ((entry->type != IOMMU_RESV_DIRECT &&
+		     entry->type != IOMMU_RESV_DIRECT_RELAXABLE) ||
+		    !iommu_is_dma_domain(domain))
+			continue;
+
 		start = ALIGN(entry->start, pg_size);
 		end   = ALIGN(entry->start + entry->length, pg_size);
-
-		if (entry->type != IOMMU_RESV_DIRECT &&
-		    entry->type != IOMMU_RESV_DIRECT_RELAXABLE)
-			continue;
 
 		for (addr = start; addr <= end; addr += pg_size) {
 			phys_addr_t phys_addr;
···
 	return ret;
 }
 
-/**
- * iommu_group_add_device - add a device to an iommu group
- * @group: the group into which to add the device (reference should be held)
- * @dev: the device
- *
- * This function is called by an iommu driver to add a device into a
- * group.  Adding a device increments the group reference count.
- */
-int iommu_group_add_device(struct iommu_group *group, struct device *dev)
+/* This is undone by __iommu_group_free_device() */
+static struct group_device *iommu_group_alloc_device(struct iommu_group *group,
+						     struct device *dev)
 {
 	int ret, i = 0;
 	struct group_device *device;
 
 	device = kzalloc(sizeof(*device), GFP_KERNEL);
 	if (!device)
-		return -ENOMEM;
+		return ERR_PTR(-ENOMEM);
 
 	device->dev = dev;
 
···
 		goto err_free_name;
 	}
 
-	kobject_get(group->devices_kobj);
-
-	dev->iommu_group = group;
-
-	mutex_lock(&group->mutex);
-	list_add_tail(&device->list, &group->devices);
-	mutex_unlock(&group->mutex);
 	trace_add_device_to_group(group->id, dev);
 
 	dev_info(dev, "Adding to iommu group %d\n", group->id);
 
-	return 0;
+	return device;
 
 err_free_name:
 	kfree(device->name);
···
 err_free_device:
 	kfree(device);
 	dev_err(dev, "Failed to add to iommu group %d: %d\n", group->id, ret);
-	return ret;
+	return ERR_PTR(ret);
+}
+
+/**
+ * iommu_group_add_device - add a device to an iommu group
+ * @group: the group into which to add the device (reference should be held)
+ * @dev: the device
+ *
+ * This function is called by an iommu driver to add a device into a
+ * group.  Adding a device increments the group reference count.
+ */
+int iommu_group_add_device(struct iommu_group *group, struct device *dev)
+{
+	struct group_device *gdev;
+
+	gdev = iommu_group_alloc_device(group, dev);
+	if (IS_ERR(gdev))
+		return PTR_ERR(gdev);
+
+	iommu_group_ref_get(group);
+	dev->iommu_group = group;
+
+	mutex_lock(&group->mutex);
+	list_add_tail(&gdev->list, &group->devices);
+	mutex_unlock(&group->mutex);
+	return 0;
 }
 EXPORT_SYMBOL_GPL(iommu_group_add_device);
 
···
 void iommu_group_remove_device(struct device *dev)
 {
 	struct iommu_group *group = dev->iommu_group;
-	struct group_device *device;
 
 	if (!group)
 		return;
 
 	dev_info(dev, "Removing from iommu group %d\n", group->id);
 
-	mutex_lock(&group->mutex);
-	device = __iommu_group_remove_device(group, dev);
-	mutex_unlock(&group->mutex);
-
-	if (device)
-		__iommu_group_release_device(group, device);
+	__iommu_group_remove_device(dev);
 }
 EXPORT_SYMBOL_GPL(iommu_group_remove_device);
 
···
 	return dom;
 }
 
-/**
- * iommu_group_get_for_dev - Find or create the IOMMU group for a device
- * @dev: target device
- *
- * This function is intended to be called by IOMMU drivers and extended to
- * support common, bus-defined algorithms when determining or creating the
- * IOMMU group for a device.  On success, the caller will hold a reference
- * to the returned IOMMU group, which will already include the provided
- * device.  The reference should be released with iommu_group_put().
- */
-static struct iommu_group *iommu_group_get_for_dev(struct device *dev)
-{
-	const struct iommu_ops *ops = dev_iommu_ops(dev);
-	struct iommu_group *group;
-	int ret;
-
-	group = iommu_group_get(dev);
-	if (group)
-		return group;
-
-	group = ops->device_group(dev);
-	if (WARN_ON_ONCE(group == NULL))
-		return ERR_PTR(-EINVAL);
-
-	if (IS_ERR(group))
-		return group;
-
-	ret = iommu_group_add_device(group, dev);
-	if (ret)
-		goto out_put_group;
-
-	return group;
-
-out_put_group:
-	iommu_group_put(group);
-
-	return ERR_PTR(ret);
-}
-
 struct iommu_domain *iommu_group_default_domain(struct iommu_group *group)
 {
 	return group->default_domain;
···
 static int probe_iommu_group(struct device *dev, void *data)
 {
 	struct list_head *group_list = data;
-	struct iommu_group *group;
 	int ret;
-
-	/* Device is probed already if in a group */
-	group = iommu_group_get(dev);
-	if (group) {
-		iommu_group_put(group);
-		return 0;
-	}
 
 	ret = __iommu_probe_device(dev, group_list);
 	if (ret == -ENODEV)
···
 	LIST_HEAD(group_list);
 	int ret;
 
-	/*
-	 * This code-path does not allocate the default domain when
-	 * creating the iommu group, so do it after the groups are
-	 * created.
-	 */
 	ret = bus_for_each_dev(bus, NULL, &group_list, probe_iommu_group);
 	if (ret)
 		return ret;
···
 		/* Remove item from the list */
 		list_del_init(&group->entry);
 
+		/*
+		 * We go to the trouble of deferred default domain creation so
+		 * that the cross-group default domain type and the setup of the
+		 * IOMMU_RESV_DIRECT will work correctly in non-hotpug scenarios.
+		 */
 		ret = iommu_setup_default_domain(group, 0);
 		if (ret) {
 			mutex_unlock(&group->mutex);
···
 				     unsigned int flags)
 {
 	int ret;
+
+	/*
+	 * If the device requires IOMMU_RESV_DIRECT then we cannot allow
+	 * the blocking domain to be attached as it does not contain the
+	 * required 1:1 mapping. This test effectively excludes the device
+	 * being used with iommu_group_claim_dma_owner() which will block
+	 * vfio and iommufd as well.
+	 */
+	if (dev->iommu->require_direct &&
+	    (new_domain->type == IOMMU_DOMAIN_BLOCKED ||
+	     new_domain == group->blocking_domain)) {
+		dev_warn(dev,
+			 "Firmware has requested this device have a 1:1 IOMMU mapping, rejecting configuring the device without a 1:1 mapping. Contact your platform vendor.\n");
+		return -EINVAL;
+	}
 
 	if (dev->iommu->attach_deferred) {
 		if (new_domain == group->default_domain)
···
 
 /**
  * iommu_group_release_dma_owner() - Release DMA ownership of a group
- * @dev: The device
+ * @group: The group
  *
  * Release the DMA ownership claimed by iommu_group_claim_dma_owner().
  */
···
 
 /**
  * iommu_device_release_dma_owner() - Release DMA ownership of a device
- * @group: The device.
+ * @dev: The device.
  *
  * Release the DMA ownership claimed by iommu_device_claim_dma_owner().
  */
···
 
 	return domain;
 }
+
+ioasid_t iommu_alloc_global_pasid(struct device *dev)
+{
+	int ret;
+
+	/* max_pasids == 0 means that the device does not support PASID */
+	if (!dev->iommu->max_pasids)
+		return IOMMU_PASID_INVALID;
+
+	/*
+	 * max_pasids is set up by vendor driver based on number of PASID bits
+	 * supported but the IDA allocation is inclusive.
+	 */
+	ret = ida_alloc_range(&iommu_global_pasid_ida, IOMMU_FIRST_GLOBAL_PASID,
+			      dev->iommu->max_pasids - 1, GFP_KERNEL);
+	return ret < 0 ? IOMMU_PASID_INVALID : ret;
+}
+EXPORT_SYMBOL_GPL(iommu_alloc_global_pasid);
+
+void iommu_free_global_pasid(ioasid_t pasid)
+{
+	if (WARN_ON(pasid == IOMMU_PASID_INVALID))
+		return;
+
+	ida_free(&iommu_global_pasid_ida, pasid);
+}
+EXPORT_SYMBOL_GPL(iommu_free_global_pasid);

drivers/iommu/ipmmu-vmsa.c

···
 #include <linux/init.h>
 #include <linux/interrupt.h>
 #include <linux/io.h>
+#include <linux/iopoll.h>
 #include <linux/io-pgtable.h>
 #include <linux/iommu.h>
 #include <linux/of.h>
-#include <linux/of_device.h>
 #include <linux/of_platform.h>
+#include <linux/pci.h>
 #include <linux/platform_device.h>
 #include <linux/sizes.h>
 #include <linux/slab.h>
···
 /* Wait for any pending TLB invalidations to complete */
 static void ipmmu_tlb_sync(struct ipmmu_vmsa_domain *domain)
 {
-	unsigned int count = 0;
+	u32 val;
 
-	while (ipmmu_ctx_read_root(domain, IMCTR) & IMCTR_FLUSH) {
-		cpu_relax();
-		if (++count == TLB_LOOP_TIMEOUT) {
-			dev_err_ratelimited(domain->mmu->dev,
+	if (read_poll_timeout_atomic(ipmmu_ctx_read_root, val,
+				     !(val & IMCTR_FLUSH), 1, TLB_LOOP_TIMEOUT,
+				     false, domain, IMCTR))
+		dev_err_ratelimited(domain->mmu->dev,
 			"TLB sync timed out -- MMU may be deadlocked\n");
-			return;
-		}
-		udelay(1);
-	}
 }
 
 static void ipmmu_tlb_invalidate(struct ipmmu_vmsa_domain *domain)
···
 	/* Check whether this SoC can use the IPMMU correctly or not */
 	if (soc_device_match(soc_denylist))
 		return false;
+
+	/* Check whether this device is a PCI device */
+	if (dev_is_pci(dev))
+		return true;
 
 	/* Check whether this device can work with the IPMMU */
 	for (i = 0; i < ARRAY_SIZE(devices_allowlist); i++) {

drivers/iommu/mtk_iommu.c

···
  * Copyright (c) 2015-2016 MediaTek Inc.
  * Author: Yong Wu <[e-mail]>
  */
+#include <linux/arm-smccc.h>
 #include <linux/bitfield.h>
 #include <linux/bug.h>
 #include <linux/clk.h>
···
 #include <linux/slab.h>
 #include <linux/spinlock.h>
 #include <linux/soc/mediatek/infracfg.h>
+#include <linux/soc/mediatek/mtk_sip_svc.h>
 #include <asm/barrier.h>
 #include <soc/mediatek/smi.h>
 
···
 #define PGTABLE_PA_35_EN		BIT(17)
 #define TF_PORT_TO_ADDR_MT8173		BIT(18)
 #define INT_ID_PORT_WIDTH_6		BIT(19)
+#define CFG_IFA_MASTER_IN_ATF		BIT(20)
 
 #define MTK_IOMMU_HAS_FLAG_MASK(pdata, _x, mask)	\
 				((((pdata)->flags) & (mask)) == (_x))
···
 	M4U_MT8173,
 	M4U_MT8183,
 	M4U_MT8186,
+	M4U_MT8188,
 	M4U_MT8192,
 	M4U_MT8195,
 	M4U_MT8365,
···
 	struct device			*smicomm_dev;
 
 	struct mtk_iommu_bank_data	*bank;
+	struct mtk_iommu_domain		*share_dom; /* For 2 HWs share pgtable */
+
 	struct regmap			*pericfg;
 	struct mutex			mutex; /* Protect m4u_group/m4u_dom above */
 
···
 	unsigned int                 larbid, portid;
 	struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev);
 	const struct mtk_iommu_iova_region *region;
-	u32 peri_mmuen, peri_mmuen_msk;
+	unsigned long portid_msk = 0;
+	struct arm_smccc_res res;
 	int i, ret = 0;
 
 	for (i = 0; i < fwspec->num_ids; ++i) {
-		larbid = MTK_M4U_TO_LARB(fwspec->ids[i]);
 		portid = MTK_M4U_TO_PORT(fwspec->ids[i]);
+		portid_msk |= BIT(portid);
+	}
 
-		if (MTK_IOMMU_IS_TYPE(data->plat_data, MTK_IOMMU_TYPE_MM)) {
-			larb_mmu = &data->larb_imu[larbid];
+	if (MTK_IOMMU_IS_TYPE(data->plat_data, MTK_IOMMU_TYPE_MM)) {
+		/* All ports should be in the same larb. just use 0 here */
+		larbid = MTK_M4U_TO_LARB(fwspec->ids[0]);
+		larb_mmu = &data->larb_imu[larbid];
+		region = data->plat_data->iova_region + regionid;
 
-			region = data->plat_data->iova_region + regionid;
+		for_each_set_bit(portid, &portid_msk, 32)
 			larb_mmu->bank[portid] = upper_32_bits(region->iova_base);
 
-			dev_dbg(dev, "%s iommu for larb(%s) port %d region %d rgn-bank %d.\n",
-				enable ? "enable" : "disable", dev_name(larb_mmu->dev),
-				portid, regionid, larb_mmu->bank[portid]);
+		dev_dbg(dev, "%s iommu for larb(%s) port 0x%lx region %d rgn-bank %d.\n",
+			enable ? "enable" : "disable", dev_name(larb_mmu->dev),
+			portid_msk, regionid, upper_32_bits(region->iova_base));
 
-			if (enable)
-				larb_mmu->mmu |= MTK_SMI_MMU_EN(portid);
-			else
-				larb_mmu->mmu &= ~MTK_SMI_MMU_EN(portid);
-		} else if (MTK_IOMMU_IS_TYPE(data->plat_data, MTK_IOMMU_TYPE_INFRA)) {
-			peri_mmuen_msk = BIT(portid);
+		if (enable)
+			larb_mmu->mmu |= portid_msk;
+		else
+			larb_mmu->mmu &= ~portid_msk;
+	} else if (MTK_IOMMU_IS_TYPE(data->plat_data, MTK_IOMMU_TYPE_INFRA)) {
+		if (MTK_IOMMU_HAS_FLAG(data->plat_data, CFG_IFA_MASTER_IN_ATF)) {
+			arm_smccc_smc(MTK_SIP_KERNEL_IOMMU_CONTROL,
+				      IOMMU_ATF_CMD_CONFIG_INFRA_IOMMU,
+				      portid_msk, enable, 0, 0, 0, 0, &res);
+			ret = res.a0;
+		} else {
 			/* PCI dev has only one output id, enable the next writing bit for PCIe */
-			if (dev_is_pci(dev))
-				peri_mmuen_msk |= BIT(portid + 1);
+			if (dev_is_pci(dev)) {
+				if (fwspec->num_ids != 1) {
+					dev_err(dev, "PCI dev can only have one port.\n");
+					return -ENODEV;
+				}
+				portid_msk |= BIT(portid + 1);
+			}
 
-			peri_mmuen = enable ? peri_mmuen_msk : 0;
 			ret = regmap_update_bits(data->pericfg, PERICFG_IOMMU_1,
-						 peri_mmuen_msk, peri_mmuen);
-			if (ret)
-				dev_err(dev, "%s iommu(%s) inframaster 0x%x fail(%d).\n",
-					enable ? "enable" : "disable",
-					dev_name(data->dev), peri_mmuen_msk, ret);
+						 (u32)portid_msk, enable ? (u32)portid_msk : 0);
 		}
+		if (ret)
+			dev_err(dev, "%s iommu(%s) inframaster 0x%lx fail(%d).\n",
+				enable ? "enable" : "disable",
+				dev_name(data->dev), portid_msk, ret);
 	}
 	return ret;
 }
···
 				     struct mtk_iommu_data *data,
 				     unsigned int region_id)
 {
+	struct mtk_iommu_domain	*share_dom = data->share_dom;
 	const struct mtk_iommu_iova_region *region;
-	struct mtk_iommu_domain	*m4u_dom;
 
-	/* Always use bank0 in sharing pgtable case */
-	m4u_dom = data->bank[0].m4u_dom;
-	if (m4u_dom) {
-		dom->iop = m4u_dom->iop;
-		dom->cfg = m4u_dom->cfg;
-		dom->domain.pgsize_bitmap = m4u_dom->cfg.pgsize_bitmap;
+	/* Always use share domain in sharing pgtable case */
+	if (MTK_IOMMU_HAS_FLAG(data->plat_data, SHARE_PGTABLE) && share_dom) {
+		dom->iop = share_dom->iop;
+		dom->cfg = share_dom->cfg;
+		dom->domain.pgsize_bitmap = share_dom->cfg.pgsize_bitmap;
 		goto update_iova_region;
 	}
 
···
 
 	/* Update our support page sizes bitmap */
 	dom->domain.pgsize_bitmap = dom->cfg.pgsize_bitmap;
+
+	if (MTK_IOMMU_HAS_FLAG(data->plat_data, SHARE_PGTABLE))
+		data->share_dom = dom;
 
 update_iova_region:
 	/* Update the iova region for this domain */
···
 		/* Data is in the frstdata in sharing pgtable case. */
 		frstdata = mtk_iommu_get_frst_data(hw_list);
 
+		mutex_lock(&frstdata->mutex);
 		ret = mtk_iommu_domain_finalise(dom, frstdata, region_id);
+		mutex_unlock(&frstdata->mutex);
 		if (ret) {
 			mutex_unlock(&dom->mutex);
 			return ret;
···
 			dev_err_probe(dev, ret, "mm dts parse fail\n");
 			goto out_runtime_disable;
 		}
-	} else if (MTK_IOMMU_IS_TYPE(data->plat_data, MTK_IOMMU_TYPE_INFRA)) {
+	} else if (MTK_IOMMU_IS_TYPE(data->plat_data, MTK_IOMMU_TYPE_INFRA) &&
+		   !MTK_IOMMU_HAS_FLAG(data->plat_data, CFG_IFA_MASTER_IN_ATF)) {
 		p = data->plat_data->pericfg_comp_str;
 		data->pericfg = syscon_regmap_lookup_by_compatible(p);
 		if (IS_ERR(data->pericfg)) {
···
 	.iova_region_larb_msk = mt8186_larb_region_msk,
 };
 
+static const struct mtk_iommu_plat_data mt8188_data_infra = {
+	.m4u_plat         = M4U_MT8188,
+	.flags            = WR_THROT_EN | DCM_DISABLE | STD_AXI_MODE | PM_CLK_AO |
+			    MTK_IOMMU_TYPE_INFRA | IFA_IOMMU_PCIE_SUPPORT |
+			    PGTABLE_PA_35_EN | CFG_IFA_MASTER_IN_ATF,
+	.inv_sel_reg      = REG_MMU_INV_SEL_GEN2,
+	.banks_num        = 1,
+	.banks_enable     = {true},
+	.iova_region      = single_domain,
+	.iova_region_nr   = ARRAY_SIZE(single_domain),
+};
+
+static const u32 mt8188_larb_region_msk[MT8192_MULTI_REGION_NR_MAX][MTK_LARB_NR_MAX] = {
+	[0] = {~0, ~0, ~0, ~0},               /* Region0: all ports for larb0/1/2/3 */
+	[1] = {0, 0, 0, 0, 0, 0, 0, 0,
+	       0, 0, 0, 0, 0, 0, 0, 0,
+	       0, 0, 0, 0, 0, ~0, ~0, ~0},    /* Region1: larb19(21)/21(22)/23 */
+	[2] = {0, 0, 0, 0, ~0, ~0, ~0, ~0,    /* Region2: the other larbs. */
+	       ~0, ~0, ~0, ~0, ~0, ~0, ~0, ~0,
+	       ~0, ~0, ~0, ~0, ~0, 0, 0, 0,
+	       0, ~0},
+	[3] = {0},
+	[4] = {[24] = BIT(0) | BIT(1)},       /* Only larb27(24) port0/1 */
+	[5] = {[24] = BIT(2) | BIT(3)},       /* Only larb27(24) port2/3 */
+};
+
+static const struct mtk_iommu_plat_data mt8188_data_vdo = {
+	.m4u_plat       = M4U_MT8188,
+	.flags          = HAS_BCLK | HAS_SUB_COMM_3BITS | OUT_ORDER_WR_EN |
+			  WR_THROT_EN | IOVA_34_EN | SHARE_PGTABLE |
+			  PGTABLE_PA_35_EN | MTK_IOMMU_TYPE_MM,
+	.hw_list        = &m4ulist,
+	.inv_sel_reg    = REG_MMU_INV_SEL_GEN2,
+	.banks_num      = 1,
+	.banks_enable   = {true},
+	.iova_region    = mt8192_multi_dom,
+	.iova_region_nr = ARRAY_SIZE(mt8192_multi_dom),
+	.iova_region_larb_msk = mt8188_larb_region_msk,
+	.larbid_remap   = {{2}, {0}, {21}, {0}, {19}, {9, 10,
+			   11 /* 11a */, 25 /* 11c */},
+			   {13, 0, 29 /* 16b */, 30 /* 17b */, 0}, {5}},
+};
+
+static const struct mtk_iommu_plat_data mt8188_data_vpp = {
+	.m4u_plat       = M4U_MT8188,
+	.flags          = HAS_BCLK | HAS_SUB_COMM_3BITS | OUT_ORDER_WR_EN |
+			  WR_THROT_EN | IOVA_34_EN | SHARE_PGTABLE |
+			  PGTABLE_PA_35_EN | MTK_IOMMU_TYPE_MM,
+	.hw_list        = &m4ulist,
+	.inv_sel_reg    = REG_MMU_INV_SEL_GEN2,
+	.banks_num      = 1,
+	.banks_enable   = {true},
+	.iova_region    = mt8192_multi_dom,
+	.iova_region_nr = ARRAY_SIZE(mt8192_multi_dom),
+	.iova_region_larb_msk = mt8188_larb_region_msk,
+	.larbid_remap   = {{1}, {3}, {23}, {7}, {MTK_INVALID_LARBID},
+			   {12, 15, 24 /* 11b */}, {14, MTK_INVALID_LARBID,
+			   16 /* 16a */, 17 /* 17a */, MTK_INVALID_LARBID,
+			   27, 28 /* ccu0 */, MTK_INVALID_LARBID}, {4, 6}},
+};
+
 static const unsigned int mt8192_larb_region_msk[MT8192_MULTI_REGION_NR_MAX][MTK_LARB_NR_MAX] = {
 	[0] = {~0, ~0},				/* Region0: larb0/1 */
 	[1] = {0, 0, 0, 0, ~0, ~0, 0, ~0},	/* Region1: larb4/5/7 */
···
 	{ .compatible = "mediatek,mt8173-m4u", .data = &mt8173_data},
 	{ .compatible = "mediatek,mt8183-m4u", .data = &mt8183_data},
 	{ .compatible = "mediatek,mt8186-iommu-mm",    .data = &mt8186_data_mm}, /* mm: m4u */
+	{ .compatible = "mediatek,mt8188-iommu-infra", .data = &mt8188_data_infra},
+	{ .compatible = "mediatek,mt8188-iommu-vdo",   .data = &mt8188_data_vdo},
+	{ .compatible = "mediatek,mt8188-iommu-vpp",   .data = &mt8188_data_vpp},
 	{ .compatible = "mediatek,mt8192-m4u", .data = &mt8192_data},
 	{ .compatible = "mediatek,mt8195-iommu-infra", .data = &mt8195_data_infra},
 	{ .compatible = "mediatek,mt8195-iommu-vdo",   .data = &mt8195_data_vdo},

drivers/iommu/of_iommu.c

···
 	 * If we have reason to believe the IOMMU driver missed the initial
 	 * probe for dev, replay it to get things in order.
 	 */
-	if (!err && dev->bus && !device_iommu_mapped(dev))
+	if (!err && dev->bus)
 		err = iommu_probe_device(dev);
 
 	/* Ignore all other errors apart from EPROBE_DEFER */

drivers/iommu/rockchip-iommu.c

···
 	phys_addr_t (*pt_address)(u32 dte);
 	u32 (*mk_dtentries)(dma_addr_t pt_dma);
 	u32 (*mk_ptentries)(phys_addr_t page, int prot);
-	phys_addr_t (*dte_addr_phys)(u32 addr);
-	u32 (*dma_addr_dte)(dma_addr_t dt_dma);
 	u64 dma_bit_mask;
+	gfp_t gfp_flags;
 };
 
 struct rk_iommu {
···
 /*
  * In v2:
  * 31:12 - Page address bit 31:0
- *  11:9 - Page address bit 34:32
- *   8:4 - Page address bit 39:35
+ * 11: 8 - Page address bit 35:32
+ *  7: 4 - Page address bit 39:36
  *     3 - Security
  *     2 - Writable
  *     1 - Readable
···
 
 	/*
 	 * Check if register DTE_ADDR is working by writing DTE_ADDR_DUMMY
-	 * and verifying that upper 5 nybbles are read back.
+	 * and verifying that upper 5 (v1) or 7 (v2) nybbles are read back.
 	 */
 	for (i = 0; i < iommu->num_mmu; i++) {
 		dte_addr = rk_ops->pt_address(DTE_ADDR_DUMMY);
···
 	return 0;
 }
 
-static inline phys_addr_t rk_dte_addr_phys(u32 addr)
-{
-	return (phys_addr_t)addr;
-}
-
-static inline u32 rk_dma_addr_dte(dma_addr_t dt_dma)
-{
-	return dt_dma;
-}
-
-#define DT_HI_MASK GENMASK_ULL(39, 32)
-#define DTE_BASE_HI_MASK GENMASK(11, 4)
-#define DT_SHIFT   28
-
-static inline phys_addr_t rk_dte_addr_phys_v2(u32 addr)
-{
-	u64 addr64 = addr;
-	return (phys_addr_t)(addr64 & RK_DTE_PT_ADDRESS_MASK) |
-	       ((addr64 & DTE_BASE_HI_MASK) << DT_SHIFT);
-}
-
-static inline u32 rk_dma_addr_dte_v2(dma_addr_t dt_dma)
-{
-	return (dt_dma & RK_DTE_PT_ADDRESS_MASK) |
-	       ((dt_dma & DT_HI_MASK) >> DT_SHIFT);
-}
-
 static void log_iova(struct rk_iommu *iommu, int index, dma_addr_t iova)
 {
 	void __iomem *base = iommu->bases[index];
···
 	page_offset = rk_iova_page_offset(iova);
 
 	mmu_dte_addr = rk_iommu_read(base, RK_MMU_DTE_ADDR);
-	mmu_dte_addr_phys = rk_ops->dte_addr_phys(mmu_dte_addr);
+	mmu_dte_addr_phys = rk_ops->pt_address(mmu_dte_addr);
 
 	dte_addr_phys = mmu_dte_addr_phys + (4 * dte_index);
 	dte_addr = phys_to_virt(dte_addr_phys);
···
 	if (rk_dte_is_pt_valid(dte))
 		goto done;
 
-	page_table = (u32 *)get_zeroed_page(GFP_ATOMIC | GFP_DMA32);
+	page_table = (u32 *)get_zeroed_page(GFP_ATOMIC | rk_ops->gfp_flags);
 	if (!page_table)
 		return ERR_PTR(-ENOMEM);
 
···
 
 	for (i = 0; i < iommu->num_mmu; i++) {
 		rk_iommu_write(iommu->bases[i], RK_MMU_DTE_ADDR,
-			       rk_ops->dma_addr_dte(rk_domain->dt_dma));
+			       rk_ops->mk_dtentries(rk_domain->dt_dma));
 		rk_iommu_base_command(iommu->bases[i], RK_MMU_CMD_ZAP_CACHE);
 		rk_iommu_write(iommu->bases[i], RK_MMU_INT_MASK, RK_MMU_IRQ_MASK);
 	}
···
 	 * Each level1 (dt) and level2 (pt) table has 1024 4-byte entries.
 	 * Allocate one 4 KiB page for each table.
 	 */
-	rk_domain->dt = (u32 *)get_zeroed_page(GFP_KERNEL | GFP_DMA32);
+	rk_domain->dt = (u32 *)get_zeroed_page(GFP_KERNEL | rk_ops->gfp_flags);
 	if (!rk_domain->dt)
 		goto err_free_domain;
 
···
 	.pt_address = &rk_dte_pt_address,
 	.mk_dtentries = &rk_mk_dte,
 	.mk_ptentries = &rk_mk_pte,
-	.dte_addr_phys = &rk_dte_addr_phys,
-	.dma_addr_dte = &rk_dma_addr_dte,
 	.dma_bit_mask = DMA_BIT_MASK(32),
+	.gfp_flags = GFP_DMA32,
 };
 
 static struct rk_iommu_ops iommu_data_ops_v2 = {
 	.pt_address = &rk_dte_pt_address_v2,
 	.mk_dtentries = &rk_mk_dte_v2,
 	.mk_ptentries = &rk_mk_pte_v2,
-	.dte_addr_phys = &rk_dte_addr_phys_v2,
-	.dma_addr_dte = &rk_dma_addr_dte_v2,
 	.dma_bit_mask = DMA_BIT_MASK(40),
+	.gfp_flags = 0,
 };
 
 static const struct of_device_id rk_iommu_dt_ids[] = {

drivers/iommu/sprd-iommu.c

···
 #include <linux/mfd/syscon.h>
 #include <linux/module.h>
 #include <linux/of_platform.h>
+#include <linux/platform_device.h>
 #include <linux/regmap.h>
 #include <linux/slab.h>
 
···
 
 	dom->domain.geometry.aperture_start = 0;
 	dom->domain.geometry.aperture_end = SZ_256M - 1;
+	dom->domain.geometry.force_aperture = true;
 
 	return &dom->domain;
 }

drivers/iommu/tegra-smmu.c

···
 #include <linux/iommu.h>
 #include <linux/kernel.h>
 #include <linux/of.h>
-#include <linux/of_device.h>
+#include <linux/of_platform.h>
 #include <linux/pci.h>
 #include <linux/platform_device.h>
 #include <linux/slab.h>

drivers/iommu/virtio-iommu.c

···
 #include <linux/interval_tree.h>
 #include <linux/iommu.h>
 #include <linux/module.h>
-#include <linux/of_platform.h>
+#include <linux/of.h>
 #include <linux/pci.h>
 #include <linux/virtio.h>
 #include <linux/virtio_config.h>

include/dt-bindings/memory/mediatek,mt8188-memory-port.h

···
+/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */
+/*
+ * Copyright (c) 2022 MediaTek Inc.
+ * Author: Chengci Xu <[e-mail]>
+ */
+#ifndef _DT_BINDINGS_MEMORY_MEDIATEK_MT8188_LARB_PORT_H_
+#define _DT_BINDINGS_MEMORY_MEDIATEK_MT8188_LARB_PORT_H_
+
+#include <dt-bindings/memory/mtk-memory-port.h>
+
+/*
+ * MM IOMMU larbs:
+ * From below, for example larb11 has larb11a/larb11b/larb11c,
+ * the index of larb is not in order. So we reindexed these larbs from a
+ * software view.
+ */
+#define SMI_L0_ID		0
+#define SMI_L1_ID		1
+#define SMI_L2_ID		2
+#define SMI_L3_ID		3
+#define SMI_L4_ID		4
+#define SMI_L5_ID		5
+#define SMI_L6_ID		6
+#define SMI_L7_ID		7
+#define SMI_L9_ID		8
+#define SMI_L10_ID		9
+#define SMI_L11A_ID		10
+#define SMI_L11B_ID		11
+#define SMI_L11C_ID		12
+#define SMI_L12_ID		13
+#define SMI_L13_ID		14
+#define SMI_L14_ID		15
+#define SMI_L15_ID		16
+#define SMI_L16A_ID		17
+#define SMI_L16B_ID		18
+#define SMI_L17A_ID		19
+#define SMI_L17B_ID		20
+#define SMI_L19_ID		21
+#define SMI_L21_ID		22
+#define SMI_L23_ID		23
+#define SMI_L27_ID		24
+#define SMI_L28_ID		25
+
+/*
+ * MM IOMMU supports 16GB dma address. We separate it to four ranges:
+ * 0 ~ 4G; 4G ~ 8G; 8G ~ 12G; 12G ~ 16G, we could adjust these masters
+ * locate in anyone region. BUT:
+ * a) Make sure all the ports inside a larb are in one range.
+ * b) The iova of any master can NOT cross the 4G/8G/12G boundary.
+ *
+ * This is the suggested mapping in this SoC:
+ *
+ * modules    dma-address-region	larbs-ports
+ * disp         0 ~ 4G                  larb0/1/2/3
+ * vcodec      4G ~ 8G                  larb19(21)[1]/21(22)/23
+ * cam/mdp     8G ~ 12G                 the other larbs.
+ * N/A         12G ~ 16G
+ * CCU0   0x24000_0000 ~ 0x243ff_ffff   larb27(24): port 0/1
+ * CCU1   0x24400_0000 ~ 0x247ff_ffff   larb27(24): port 2/3
+ *
+ * This SoC have two MM IOMMU HWs, this is the connected information:
+ * iommu-vdo: larb0/2/5/9/10/11A/11C/13/16B/17B/19/21
+ * iommu-vpp: larb1/3/4/6/7/11B/12/14/15/16A/17A/23/27
+ *
+ * [1]: This is larb19, but the index is 21 from the SW view.
+ */
+
+/* MM IOMMU ports */
+/* LARB 0 -- VDO-0 */
+#define M4U_PORT_L0_DISP_RDMA1			MTK_M4U_ID(SMI_L0_ID, 0)
+#define M4U_PORT_L0_DISP_WDMA0			MTK_M4U_ID(SMI_L0_ID, 1)
+#define M4U_PORT_L0_DISP_OVL0_RDMA0		MTK_M4U_ID(SMI_L0_ID, 2)
+#define M4U_PORT_L0_DISP_OVL0_RDMA1		MTK_M4U_ID(SMI_L0_ID, 3)
+#define M4U_PORT_L0_DISP_OVL0_HDR		MTK_M4U_ID(SMI_L0_ID, 4)
+#define M4U_PORT_L0_DISP_POSTMASK0		MTK_M4U_ID(SMI_L0_ID, 5)
+#define M4U_PORT_L0_DISP_FAKE_ENG0		MTK_M4U_ID(SMI_L0_ID, 6)
+
+/* LARB 1 -- VD0-0 */
+#define M4U_PORT_L1_DISP_RDMA0			MTK_M4U_ID(SMI_L1_ID, 0)
+#define M4U_PORT_L1_DISP_WDMA1			MTK_M4U_ID(SMI_L1_ID, 1)
+#define M4U_PORT_L1_DISP_OVL1_RDMA0		MTK_M4U_ID(SMI_L1_ID, 2)
+#define M4U_PORT_L1_DISP_OVL1_RDMA1		MTK_M4U_ID(SMI_L1_ID, 3)
+#define M4U_PORT_L1_DISP_OVL1_HDR		MTK_M4U_ID(SMI_L1_ID, 4)
+#define M4U_PORT_L1_DISP_WROT0			MTK_M4U_ID(SMI_L1_ID, 5)
+#define M4U_PORT_L1_DISP_FAKE_ENG1		MTK_M4U_ID(SMI_L1_ID, 6)
+
+/* LARB 2 -- VDO-1 */
+#define M4U_PORT_L2_MDP_RDMA0			MTK_M4U_ID(SMI_L2_ID, 0)
+#define M4U_PORT_L2_MDP_RDMA2			MTK_M4U_ID(SMI_L2_ID, 1)
+#define M4U_PORT_L2_MDP_RDMA4			MTK_M4U_ID(SMI_L2_ID, 2)
+#define M4U_PORT_L2_MDP_RDMA6			MTK_M4U_ID(SMI_L2_ID, 3)
+#define M4U_PORT_L2_DISP_FAKE1			MTK_M4U_ID(SMI_L2_ID, 4)
+
+/* LARB 3 -- VDO-1 */
+#define M4U_PORT_L3_MDP_RDMA1			MTK_M4U_ID(SMI_L3_ID, 0)
+#define M4U_PORT_L3_MDP_RDMA3			MTK_M4U_ID(SMI_L3_ID, 1)
+#define M4U_PORT_L3_MDP_RDMA5			MTK_M4U_ID(SMI_L3_ID, 2)
+#define M4U_PORT_L3_MDP_RDMA7			MTK_M4U_ID(SMI_L3_ID, 3)
+#define M4U_PORT_L3_HDR_DS_SMI			MTK_M4U_ID(SMI_L3_ID, 4)
+#define M4U_PORT_L3_HDR_ADL_SMI			MTK_M4U_ID(SMI_L3_ID, 5)
+#define M4U_PORT_L3_DISP_FAKE1			MTK_M4U_ID(SMI_L3_ID, 6)
+
+/* LARB 4 -- VPP-0 */
+#define M4U_PORT_L4_MDP_RDMA			MTK_M4U_ID(SMI_L4_ID, 0)
+#define M4U_PORT_L4_MDP_FG			MTK_M4U_ID(SMI_L4_ID, 1)
+#define M4U_PORT_L4_MDP_OVL			MTK_M4U_ID(SMI_L4_ID, 2)
+#define M4U_PORT_L4_MDP_WROT			MTK_M4U_ID(SMI_L4_ID, 3)
+#define M4U_PORT_L4_FAKE_ENG			MTK_M4U_ID(SMI_L4_ID, 4)
+#define M4U_PORT_L4_DISP_RDMA			MTK_M4U_ID(SMI_L4_ID, 5)
+#define M4U_PORT_L4_DISP_WDMA			MTK_M4U_ID(SMI_L4_ID, 6)
+
+/* LARB 5 -- VPP-1 */
+#define M4U_PORT_L5_SVPP1_MDP_RDMA		MTK_M4U_ID(SMI_L5_ID, 0)
+#define M4U_PORT_L5_SVPP1_MDP_FG		MTK_M4U_ID(SMI_L5_ID, 1)
+#define M4U_PORT_L5_SVPP1_MDP_OVL		MTK_M4U_ID(SMI_L5_ID, 2)
+#define M4U_PORT_L5_SVPP1_MDP_WROT		MTK_M4U_ID(SMI_L5_ID, 3)
+#define M4U_PORT_L5_SVPP2_MDP_RDMA		MTK_M4U_ID(SMI_L5_ID, 4)
+#define M4U_PORT_L5_SVPP2_MDP_FG		MTK_M4U_ID(SMI_L5_ID, 5)
+#define M4U_PORT_L5_SVPP2_MDP_WROT		MTK_M4U_ID(SMI_L5_ID, 6)
+#define M4U_PORT_L5_LARB5_FAKE_ENG		MTK_M4U_ID(SMI_L5_ID, 7)
+
+/* LARB 6 -- VPP-1 */
+#define M4U_PORT_L6_SVPP3_MDP_RDMA		MTK_M4U_ID(SMI_L6_ID, 0)
+#define M4U_PORT_L6_SVPP3_MDP_FG		MTK_M4U_ID(SMI_L6_ID, 1)
+#define M4U_PORT_L6_SVPP3_MDP_WROT		MTK_M4U_ID(SMI_L6_ID, 2)
+#define M4U_PORT_L6_LARB6_FAKE_ENG		MTK_M4U_ID(SMI_L6_ID, 3)
+
+/* LARB 7 -- WPE */
+#define M4U_PORT_L7_WPE_RDMA_0			MTK_M4U_ID(SMI_L7_ID, 0)
+#define M4U_PORT_L7_WPE_RDMA_1			MTK_M4U_ID(SMI_L7_ID, 1)
+#define M4U_PORT_L7_WPE_WDMA_0			MTK_M4U_ID(SMI_L7_ID, 2)
+
+/* LARB 9 -- IMG-M */
+#define M4U_PORT_L9_IMGI_T1_A			MTK_M4U_ID(SMI_L9_ID, 0)
+#define M4U_PORT_L9_UFDI_T1_A			MTK_M4U_ID(SMI_L9_ID, 1)
+#define M4U_PORT_L9_IMGBI_T1_A			MTK_M4U_ID(SMI_L9_ID, 2)
+#define M4U_PORT_L9_IMGCI_T1_A			MTK_M4U_ID(SMI_L9_ID, 3)
+#define M4U_PORT_L9_SMTI_T1_A			MTK_M4U_ID(SMI_L9_ID, 4)
+#define M4U_PORT_L9_SMTI_T4_A			MTK_M4U_ID(SMI_L9_ID, 5)
+#define M4U_PORT_L9_TNCSTI_T1_A			MTK_M4U_ID(SMI_L9_ID, 6)
+#define M4U_PORT_L9_TNCSTI_T4_A			MTK_M4U_ID(SMI_L9_ID, 7)
+#define M4U_PORT_L9_YUVO_T1_A			MTK_M4U_ID(SMI_L9_ID, 8)
+#define M4U_PORT_L9_YUVBO_T1_A			MTK_M4U_ID(SMI_L9_ID, 9)
+#define M4U_PORT_L9_YUVCO_T1_A			MTK_M4U_ID(SMI_L9_ID, 10)
+#define M4U_PORT_L9_TIMGO_T1_A			MTK_M4U_ID(SMI_L9_ID, 11)
+#define M4U_PORT_L9_YUVO_T2_A			MTK_M4U_ID(SMI_L9_ID, 12)
+#define M4U_PORT_L9_YUVO_T5_A			MTK_M4U_ID(SMI_L9_ID, 13)
+#define M4U_PORT_L9_IMGI_T1_B			MTK_M4U_ID(SMI_L9_ID, 14)
+#define M4U_PORT_L9_IMGBI_T1_B			MTK_M4U_ID(SMI_L9_ID, 15)
+#define M4U_PORT_L9_IMGCI_T1_B			MTK_M4U_ID(SMI_L9_ID, 16)
+#define M4U_PORT_L9_SMTI_T4_B			MTK_M4U_ID(SMI_L9_ID, 17)
+#define M4U_PORT_L9_TNCSO_T1_A			MTK_M4U_ID(SMI_L9_ID, 18)
+#define M4U_PORT_L9_SMTO_T1_A			MTK_M4U_ID(SMI_L9_ID, 19)
+#define M4U_PORT_L9_SMTO_T4_A			MTK_M4U_ID(SMI_L9_ID, 20)
+#define M4U_PORT_L9_TNCSTO_T1_A			MTK_M4U_ID(SMI_L9_ID, 21)
+#define M4U_PORT_L9_YUVO_T2_B			MTK_M4U_ID(SMI_L9_ID, 22)
+#define M4U_PORT_L9_YUVO_T5_B			MTK_M4U_ID(SMI_L9_ID, 23)
+#define M4U_PORT_L9_SMTO_T4_B			MTK_M4U_ID(SMI_L9_ID, 24)
+
+/* LARB 10 -- IMG-D */
+#define M4U_PORT_L10_IMGI_D1			MTK_M4U_ID(SMI_L10_ID, 0)
+#define M4U_PORT_L10_IMGBI_D1			MTK_M4U_ID(SMI_L10_ID, 1)
+#define M4U_PORT_L10_IMGCI_D1			MTK_M4U_ID(SMI_L10_ID, 2)
+#define M4U_PORT_L10_IMGDI_D1			MTK_M4U_ID(SMI_L10_ID, 3)
+#define M4U_PORT_L10_DEPI_D1			MTK_M4U_ID(SMI_L10_ID, 4)
+#define M4U_PORT_L10_DMGI_D1			MTK_M4U_ID(SMI_L10_ID, 5)
+#define M4U_PORT_L10_SMTI_D1			MTK_M4U_ID(SMI_L10_ID, 6)
+#define M4U_PORT_L10_RECI_D1			MTK_M4U_ID(SMI_L10_ID, 7)
+#define M4U_PORT_L10_RECI_D1_N			MTK_M4U_ID(SMI_L10_ID, 8)
+#define M4U_PORT_L10_TNRWI_D1			MTK_M4U_ID(SMI_L10_ID, 9)
+#define M4U_PORT_L10_TNRCI_D1			MTK_M4U_ID(SMI_L10_ID, 10)
+#define M4U_PORT_L10_TNRCI_D1_N			MTK_M4U_ID(SMI_L10_ID, 11)
+#define M4U_PORT_L10_IMG4O_D1			MTK_M4U_ID(SMI_L10_ID, 12)
+#define M4U_PORT_L10_IMG4BO_D1			MTK_M4U_ID(SMI_L10_ID, 13)
+#define M4U_PORT_L10_SMTI_D8			MTK_M4U_ID(SMI_L10_ID, 14)
+#define M4U_PORT_L10_SMTO_D1			MTK_M4U_ID(SMI_L10_ID, 15)
+#define M4U_PORT_L10_TNRMO_D1			MTK_M4U_ID(SMI_L10_ID, 16)
+#define M4U_PORT_L10_TNRMO_D1_N			MTK_M4U_ID(SMI_L10_ID, 17)
+#define M4U_PORT_L10_SMTO_D8			MTK_M4U_ID(SMI_L10_ID, 18)
+#define M4U_PORT_L10_DBGO_D1			MTK_M4U_ID(SMI_L10_ID, 19)
+
+/* LARB 11A -- IMG-D */
+#define M4U_PORT_L11A_WPE_RDMA_0		MTK_M4U_ID(SMI_L11A_ID, 0)
+#define M4U_PORT_L11A_WPE_RDMA_1		MTK_M4U_ID(SMI_L11A_ID, 1)
+#define M4U_PORT_L11A_WPE_RDMA_4P_0		MTK_M4U_ID(SMI_L11A_ID, 2)
+#define M4U_PORT_L11A_WPE_RDMA_4P_1		MTK_M4U_ID(SMI_L11A_ID, 3)
+#define M4U_PORT_L11A_WPE_CQ0			MTK_M4U_ID(SMI_L11A_ID, 4)
+#define M4U_PORT_L11A_WPE_CQ1			MTK_M4U_ID(SMI_L11A_ID, 5)
+#define M4U_PORT_L11A_PIMGI_P1			MTK_M4U_ID(SMI_L11A_ID, 6)
+#define M4U_PORT_L11A_PIMGBI_P1			MTK_M4U_ID(SMI_L11A_ID, 7)
+#define M4U_PORT_L11A_PIMGCI_P1			MTK_M4U_ID(SMI_L11A_ID, 8)
+#define M4U_PORT_L11A_IMGI_T1_C			MTK_M4U_ID(SMI_L11A_ID, 9)
+#define M4U_PORT_L11A_IMGBI_T1_C		MTK_M4U_ID(SMI_L11A_ID, 10)
+#define M4U_PORT_L11A_IMGCI_T1_C		MTK_M4U_ID(SMI_L11A_ID, 11)
+#define M4U_PORT_L11A_SMTI_T1_C			MTK_M4U_ID(SMI_L11A_ID, 12)
+#define M4U_PORT_L11A_SMTI_T4_C			MTK_M4U_ID(SMI_L11A_ID, 13)
+#define M4U_PORT_L11A_SMTI_T6_C			MTK_M4U_ID(SMI_L11A_ID, 14)
+#define M4U_PORT_L11A_YUVO_T1_C			MTK_M4U_ID(SMI_L11A_ID, 15)
+#define M4U_PORT_L11A_YUVBO_T1_C		MTK_M4U_ID(SMI_L11A_ID, 16)
+#define M4U_PORT_L11A_YUVCO_T1_C		MTK_M4U_ID(SMI_L11A_ID, 17)
+#define M4U_PORT_L11A_WPE_WDMA_0		MTK_M4U_ID(SMI_L11A_ID, 18)
+#define M4U_PORT_L11A_WPE_WDMA_4P_0		MTK_M4U_ID(SMI_L11A_ID, 19)
+#define M4U_PORT_L11A_WROT_P1			MTK_M4U_ID(SMI_L11A_ID, 20)
+#define M4U_PORT_L11A_TCCSO_P1			MTK_M4U_ID(SMI_L11A_ID, 21)
+#define M4U_PORT_L11A_TCCSI_P1			MTK_M4U_ID(SMI_L11A_ID, 22)
+#define M4U_PORT_L11A_TIMGO_T1_C		MTK_M4U_ID(SMI_L11A_ID, 23)
+#define M4U_PORT_L11A_YUVO_T2_C			MTK_M4U_ID(SMI_L11A_ID, 24)
+#define M4U_PORT_L11A_YUVO_T5_C			MTK_M4U_ID(SMI_L11A_ID, 25)
+#define M4U_PORT_L11A_SMTO_T1_C			MTK_M4U_ID(SMI_L11A_ID, 26)
+#define M4U_PORT_L11A_SMTO_T4_C			MTK_M4U_ID(SMI_L11A_ID, 27)
+#define M4U_PORT_L11A_SMTO_T6_C			MTK_M4U_ID(SMI_L11A_ID, 28)
+#define M4U_PORT_L11A_DBGO_T1_C			MTK_M4U_ID(SMI_L11A_ID, 29)
+
+/* LARB 11B -- IMG-D */
+#define M4U_PORT_L11B_WPE_RDMA_0		MTK_M4U_ID(SMI_L11B_ID, 0)
+#define M4U_PORT_L11B_WPE_RDMA_1		MTK_M4U_ID(SMI_L11B_ID, 1)
+#define M4U_PORT_L11B_WPE_RDMA_4P_0		MTK_M4U_ID(SMI_L11B_ID, 2)
+#define M4U_PORT_L11B_WPE_RDMA_4P_1		MTK_M4U_ID(SMI_L11B_ID, 3)
+#define M4U_PORT_L11B_WPE_CQ0			MTK_M4U_ID(SMI_L11B_ID, 4)
+#define M4U_PORT_L11B_WPE_CQ1			MTK_M4U_ID(SMI_L11B_ID, 5)
+#define M4U_PORT_L11B_PIMGI_P1			MTK_M4U_ID(SMI_L11B_ID, 6)
+#define M4U_PORT_L11B_PIMGBI_P1			MTK_M4U_ID(SMI_L11B_ID, 7)
+#define M4U_PORT_L11B_PIMGCI_P1			MTK_M4U_ID(SMI_L11B_ID, 8)
+#define M4U_PORT_L11B_IMGI_T1_C			MTK_M4U_ID(SMI_L11B_ID, 9)
+#define M4U_PORT_L11B_IMGBI_T1_C		MTK_M4U_ID(SMI_L11B_ID, 10)
+#define M4U_PORT_L11B_IMGCI_T1_C		MTK_M4U_ID(SMI_L11B_ID, 11)
+#define M4U_PORT_L11B_SMTI_T1_C			MTK_M4U_ID(SMI_L11B_ID, 12)
+#define M4U_PORT_L11B_SMTI_T4_C			MTK_M4U_ID(SMI_L11B_ID, 13)
+#define M4U_PORT_L11B_SMTI_T6_C			MTK_M4U_ID(SMI_L11B_ID, 14)
+#define M4U_PORT_L11B_YUVO_T1_C			MTK_M4U_ID(SMI_L11B_ID, 15)
+#define M4U_PORT_L11B_YUVBO_T1_C		MTK_M4U_ID(SMI_L11B_ID, 16)
+#define M4U_PORT_L11B_YUVCO_T1_C		MTK_M4U_ID(SMI_L11B_ID, 17)
+#define M4U_PORT_L11B_WPE_WDMA_0		MTK_M4U_ID(SMI_L11B_ID, 18)
+#define M4U_PORT_L11B_WPE_WDMA_4P_0		MTK_M4U_ID(SMI_L11B_ID, 19)
+#define M4U_PORT_L11B_WROT_P1			MTK_M4U_ID(SMI_L11B_ID, 20)
+#define M4U_PORT_L11B_TCCSO_P1			MTK_M4U_ID(SMI_L11B_ID, 21)
+#define M4U_PORT_L11B_TCCSI_P1			MTK_M4U_ID(SMI_L11B_ID, 22)
+#define M4U_PORT_L11B_TIMGO_T1_C		MTK_M4U_ID(SMI_L11B_ID, 23)
+#define M4U_PORT_L11B_YUVO_T2_C			MTK_M4U_ID(SMI_L11B_ID, 24)
+#define M4U_PORT_L11B_YUVO_T5_C			MTK_M4U_ID(SMI_L11B_ID, 25)
+#define M4U_PORT_L11B_SMTO_T1_C			MTK_M4U_ID(SMI_L11B_ID, 26)
+#define M4U_PORT_L11B_SMTO_T4_C			MTK_M4U_ID(SMI_L11B_ID, 27)
+#define M4U_PORT_L11B_SMTO_T6_C			MTK_M4U_ID(SMI_L11B_ID, 28)
+#define M4U_PORT_L11B_DBGO_T1_C			MTK_M4U_ID(SMI_L11B_ID, 29)
+
+/* LARB 11C -- IMG-D */
+#define M4U_PORT_L11C_WPE_RDMA_0		MTK_M4U_ID(SMI_L11C_ID, 0)
+#define M4U_PORT_L11C_WPE_RDMA_1		MTK_M4U_ID(SMI_L11C_ID, 1)
+#define M4U_PORT_L11C_WPE_RDMA_4P_0		MTK_M4U_ID(SMI_L11C_ID, 2)
+#define M4U_PORT_L11C_WPE_RDMA_4P_1		MTK_M4U_ID(SMI_L11C_ID, 3)
+#define M4U_PORT_L11C_WPE_CQ0			MTK_M4U_ID(SMI_L11C_ID, 4)
+#define M4U_PORT_L11C_WPE_CQ1			MTK_M4U_ID(SMI_L11C_ID, 5)
+#define M4U_PORT_L11C_PIMGI_P1			MTK_M4U_ID(SMI_L11C_ID, 6)
+#define M4U_PORT_L11C_PIMGBI_P1			MTK_M4U_ID(SMI_L11C_ID, 7)
+#define M4U_PORT_L11C_PIMGCI_P1			MTK_M4U_ID(SMI_L11C_ID, 8)
+#define M4U_PORT_L11C_IMGI_T1_C			MTK_M4U_ID(SMI_L11C_ID, 9)
+#define M4U_PORT_L11C_IMGBI_T1_C		MTK_M4U_ID(SMI_L11C_ID, 10)
+#define M4U_PORT_L11C_IMGCI_T1_C		MTK_M4U_ID(SMI_L11C_ID, 11)
+#define M4U_PORT_L11C_SMTI_T1_C			MTK_M4U_ID(SMI_L11C_ID, 12)
+#define M4U_PORT_L11C_SMTI_T4_C			MTK_M4U_ID(SMI_L11C_ID, 13)
+#define M4U_PORT_L11C_SMTI_T6_C			MTK_M4U_ID(SMI_L11C_ID, 14)
+#define M4U_PORT_L11C_YUVO_T1_C			MTK_M4U_ID(SMI_L11C_ID, 15)
+#define M4U_PORT_L11C_YUVBO_T1_C		MTK_M4U_ID(SMI_L11C_ID, 16)
+#define M4U_PORT_L11C_YUVCO_T1_C		MTK_M4U_ID(SMI_L11C_ID, 17)
+#define M4U_PORT_L11C_WPE_WDMA_0		MTK_M4U_ID(SMI_L11C_ID, 18)
+#define M4U_PORT_L11C_WPE_WDMA_4P_0		MTK_M4U_ID(SMI_L11C_ID, 19)
+#define M4U_PORT_L11C_WROT_P1			MTK_M4U_ID(SMI_L11C_ID, 20)
+#define M4U_PORT_L11C_TCCSO_P1			MTK_M4U_ID(SMI_L11C_ID, 21)
+#define M4U_PORT_L11C_TCCSI_P1			MTK_M4U_ID(SMI_L11C_ID, 22)
+#define M4U_PORT_L11C_TIMGO_T1_C		MTK_M4U_ID(SMI_L11C_ID, 23)
+#define M4U_PORT_L11C_YUVO_T2_C			MTK_M4U_ID(SMI_L11C_ID, 24)
+#define M4U_PORT_L11C_YUVO_T5_C			MTK_M4U_ID(SMI_L11C_ID, 25)
+#define M4U_PORT_L11C_SMTO_T1_C			MTK_M4U_ID(SMI_L11C_ID, 26)
+#define M4U_PORT_L11C_SMTO_T4_C			MTK_M4U_ID(SMI_L11C_ID, 27)
+#define M4U_PORT_L11C_SMTO_T6_C			MTK_M4U_ID(SMI_L11C_ID, 28)
+#define M4U_PORT_L11C_DBGO_T1_C			MTK_M4U_ID(SMI_L11C_ID, 29)
+
+/* LARB 12 -- IPE */
+#define M4U_PORT_L12_FDVT_RDA_0			MTK_M4U_ID(SMI_L12_ID, 0)
+#define M4U_PORT_L12_FDVT_RDB_0			MTK_M4U_ID(SMI_L12_ID, 1)
+#define M4U_PORT_L12_FDVT_WRA_0			MTK_M4U_ID(SMI_L12_ID, 2)
+#define M4U_PORT_L12_FDVT_WRB_0			MTK_M4U_ID(SMI_L12_ID, 3)
+#define M4U_PORT_L12_ME_RDMA			MTK_M4U_ID(SMI_L12_ID, 4)
+#define M4U_PORT_L12_ME_WDMA			MTK_M4U_ID(SMI_L12_ID, 5)
+#define M4U_PORT_L12_DVS_RDMA			MTK_M4U_ID(SMI_L12_ID, 6)
+#define M4U_PORT_L12_DVS_WDMA			MTK_M4U_ID(SMI_L12_ID, 7)
+#define M4U_PORT_L12_DVP_RDMA			MTK_M4U_ID(SMI_L12_ID, 8)
+#define M4U_PORT_L12_DVP_WDMA			MTK_M4U_ID(SMI_L12_ID, 9)
+#define M4U_PORT_L12_FDVT_2ND_RDA_0		MTK_M4U_ID(SMI_L12_ID, 10)
+#define M4U_PORT_L12_FDVT_2ND_RDB_0		MTK_M4U_ID(SMI_L12_ID, 11)
+#define M4U_PORT_L12_FDVT_2ND_WRA_0		MTK_M4U_ID(SMI_L12_ID, 12)
+#define M4U_PORT_L12_FDVT_2ND_WRB_0		MTK_M4U_ID(SMI_L12_ID, 13)
+#define M4U_PORT_L12_DHZEI_E1			MTK_M4U_ID(SMI_L12_ID, 14)
+#define M4U_PORT_L12_DHZEO_E1			MTK_M4U_ID(SMI_L12_ID, 15)
+
+/* LARB 13 -- CAM-1 */
+#define M4U_PORT_L13_CAMSV_CQI_E1		MTK_M4U_ID(SMI_L13_ID, 0)
+#define M4U_PORT_L13_CAMSV_CQI_E2		MTK_M4U_ID(SMI_L13_ID, 1)
+#define M4U_PORT_L13_GCAMSV_A_IMGO_1		MTK_M4U_ID(SMI_L13_ID, 2)
+#define M4U_PORT_L13_GCAMSV_C_IMGO_1		MTK_M4U_ID(SMI_L13_ID, 3)
+#define M4U_PORT_L13_GCAMSV_A_IMGO_2		MTK_M4U_ID(SMI_L13_ID, 4)
+#define M4U_PORT_L13_GCAMSV_C_IMGO_2		MTK_M4U_ID(SMI_L13_ID, 5)
+#define M4U_PORT_L13_PDAI_A_0			MTK_M4U_ID(SMI_L13_ID, 6)
+#define M4U_PORT_L13_PDAI_A_1			MTK_M4U_ID(SMI_L13_ID, 7)
+#define M4U_PORT_L13_CAMSV_CQI_B_E1		MTK_M4U_ID(SMI_L13_ID, 8)
+#define M4U_PORT_L13_CAMSV_CQI_B_E2		MTK_M4U_ID(SMI_L13_ID, 9)
+#define M4U_PORT_L13_CAMSV_CQI_C_E1		MTK_M4U_ID(SMI_L13_ID, 10)
+#define M4U_PORT_L13_CAMSV_CQI_C_E2		MTK_M4U_ID(SMI_L13_ID, 11)
+#define M4U_PORT_L13_GCAMSV_E_IMGO_1		MTK_M4U_ID(SMI_L13_ID, 12)
+#define M4U_PORT_L13_GCAMSV_E_IMGO_2		MTK_M4U_ID(SMI_L13_ID, 13)
+#define M4U_PORT_L13_GCAMSV_A_UFEO_1		MTK_M4U_ID(SMI_L13_ID, 14)
+#define M4U_PORT_L13_GCAMSV_C_UFEO_1		MTK_M4U_ID(SMI_L13_ID, 15)
+#define M4U_PORT_L13_GCAMSV_A_UFEO_2		MTK_M4U_ID(SMI_L13_ID, 16)
+#define M4U_PORT_L13_GCAMSV_C_UFEO_2		MTK_M4U_ID(SMI_L13_ID, 17)
+#define M4U_PORT_L13_GCAMSV_E_UFEO_1		MTK_M4U_ID(SMI_L13_ID, 18)
+#define M4U_PORT_L13_GCAMSV_E_UFEO_2		MTK_M4U_ID(SMI_L13_ID, 19)
+#define M4U_PORT_L13_GCAMSV_G_IMGO_1		MTK_M4U_ID(SMI_L13_ID, 20)
+#define M4U_PORT_L13_GCAMSV_G_IMGO_2		MTK_M4U_ID(SMI_L13_ID, 21)
+#define M4U_PORT_L13_PDAO_A			MTK_M4U_ID(SMI_L13_ID, 22)
+#define M4U_PORT_L13_PDAO_C			MTK_M4U_ID(SMI_L13_ID, 23)
+
+/* LARB 14 -- CAM-1 */
+#define M4U_PORT_L14_GCAMSV_B_IMGO_1		MTK_M4U_ID(SMI_L14_ID, 0)
+#define M4U_PORT_L14_GCAMSV_B_IMGO_2		MTK_M4U_ID(SMI_L14_ID, 1)
+#define M4U_PORT_L14_SCAMSV_A_IMGO_1		MTK_M4U_ID(SMI_L14_ID, 2)
+#define M4U_PORT_L14_SCAMSV_A_IMGO_2		MTK_M4U_ID(SMI_L14_ID, 3)
+#define M4U_PORT_L14_SCAMSV_B_IMGO_1		MTK_M4U_ID(SMI_L14_ID, 4)
+#define M4U_PORT_L14_SCAMSV_B_IMGO_2		MTK_M4U_ID(SMI_L14_ID, 5)
+#define M4U_PORT_L14_PDAI_B_0			MTK_M4U_ID(SMI_L14_ID, 6)
+#define M4U_PORT_L14_PDAI_B_1			MTK_M4U_ID(SMI_L14_ID, 7)
+#define M4U_PORT_L14_GCAMSV_D_IMGO_1		MTK_M4U_ID(SMI_L14_ID, 8)
+#define M4U_PORT_L14_GCAMSV_D_IMGO_2		MTK_M4U_ID(SMI_L14_ID, 9)
+#define M4U_PORT_L14_GCAMSV_F_IMGO_1		MTK_M4U_ID(SMI_L14_ID, 10)
+#define M4U_PORT_L14_GCAMSV_F_IMGO_2		MTK_M4U_ID(SMI_L14_ID, 11)
+#define M4U_PORT_L14_GCAMSV_H_IMGO_1		MTK_M4U_ID(SMI_L14_ID, 12)
+#define M4U_PORT_L14_GCAMSV_H_IMGO_2		MTK_M4U_ID(SMI_L14_ID, 13)
+#define M4U_PORT_L14_GCAMSV_B_UFEO_1		MTK_M4U_ID(SMI_L14_ID, 14)
+#define M4U_PORT_L14_GCAMSV_B_UFEO_2		MTK_M4U_ID(SMI_L14_ID, 15)
+#define M4U_PORT_L14_GCAMSV_D_UFEO_1		MTK_M4U_ID(SMI_L14_ID, 16)
+#define M4U_PORT_L14_GCAMSV_D_UFEO_2		MTK_M4U_ID(SMI_L14_ID, 17)
+#define M4U_PORT_L14_PDAO_B			MTK_M4U_ID(SMI_L14_ID, 18)
+#define M4U_PORT_L14_IPUI			MTK_M4U_ID(SMI_L14_ID, 19)
+#define M4U_PORT_L14_IPUO			MTK_M4U_ID(SMI_L14_ID, 20)
+#define M4U_PORT_L14_IPU3O			MTK_M4U_ID(SMI_L14_ID, 21)
+#define M4U_PORT_L14_FAKE			MTK_M4U_ID(SMI_L14_ID, 22)
+
+/* LARB 15 -- IMG-D */
+#define M4U_PORT_L15_VIPI_D1			MTK_M4U_ID(SMI_L15_ID, 0)
+#define M4U_PORT_L15_VIPBI_D1			MTK_M4U_ID(SMI_L15_ID, 1)
+#define M4U_PORT_L15_SMTI_D6			MTK_M4U_ID(SMI_L15_ID, 2)
+#define M4U_PORT_L15_TNCSTI_D1			MTK_M4U_ID(SMI_L15_ID, 3)
+#define M4U_PORT_L15_TNCSTI_D4			MTK_M4U_ID(SMI_L15_ID, 4)
+#define M4U_PORT_L15_SMTI_D4			MTK_M4U_ID(SMI_L15_ID, 5)
+#define M4U_PORT_L15_IMG3O_D1			MTK_M4U_ID(SMI_L15_ID, 6)
+#define M4U_PORT_L15_IMG3BO_D1			MTK_M4U_ID(SMI_L15_ID, 7)
+#define M4U_PORT_L15_IMG3CO_D1			MTK_M4U_ID(SMI_L15_ID, 8)
+#define M4U_PORT_L15_IMG2O_D1			MTK_M4U_ID(SMI_L15_ID, 9)
+#define M4U_PORT_L15_SMTI_D9			MTK_M4U_ID(SMI_L15_ID, 10)
+#define M4U_PORT_L15_SMTO_D4			MTK_M4U_ID(SMI_L15_ID, 11)
+#define M4U_PORT_L15_FEO_D1			MTK_M4U_ID(SMI_L15_ID, 12)
+#define M4U_PORT_L15_TNCSO_D1			MTK_M4U_ID(SMI_L15_ID, 13)
+#define M4U_PORT_L15_TNCSTO_D1			MTK_M4U_ID(SMI_L15_ID, 14)
+#define M4U_PORT_L15_SMTO_D6			MTK_M4U_ID(SMI_L15_ID, 15)
+#define M4U_PORT_L15_SMTO_D9			MTK_M4U_ID(SMI_L15_ID, 16)
+#define M4U_PORT_L15_TNCO_D1			MTK_M4U_ID(SMI_L15_ID, 17)
+#define M4U_PORT_L15_TNCO_D1_N			MTK_M4U_ID(SMI_L15_ID, 18)
+
+/* LARB 16A -- CAM */
+#define M4U_PORT_L16A_IMGO_R1			MTK_M4U_ID(SMI_L16A_ID, 0)
+#define M4U_PORT_L16A_CQI_R1			MTK_M4U_ID(SMI_L16A_ID, 1)
+#define M4U_PORT_L16A_CQI_R2			MTK_M4U_ID(SMI_L16A_ID, 2)
+#define M4U_PORT_L16A_BPCI_R1			MTK_M4U_ID(SMI_L16A_ID, 3)
+#define M4U_PORT_L16A_LSCI_R1			MTK_M4U_ID(SMI_L16A_ID, 4)
+#define M4U_PORT_L16A_RAWI_R2			MTK_M4U_ID(SMI_L16A_ID, 5)
+#define M4U_PORT_L16A_RAWI_R3			MTK_M4U_ID(SMI_L16A_ID, 6)
+#define M4U_PORT_L16A_UFDI_R2			MTK_M4U_ID(SMI_L16A_ID, 7)
+#define M4U_PORT_L16A_UFDI_R3			MTK_M4U_ID(SMI_L16A_ID, 8)
+#define M4U_PORT_L16A_RAWI_R4			MTK_M4U_ID(SMI_L16A_ID, 9)
+#define M4U_PORT_L16A_RAWI_R5			MTK_M4U_ID(SMI_L16A_ID, 10)
+#define M4U_PORT_L16A_AAI_R1			MTK_M4U_ID(SMI_L16A_ID, 11)
+#define M4U_PORT_L16A_UFDI_R5			MTK_M4U_ID(SMI_L16A_ID, 12)
+#define M4U_PORT_L16A_FHO_R1			MTK_M4U_ID(SMI_L16A_ID, 13)
+#define M4U_PORT_L16A_AAO_R1			MTK_M4U_ID(SMI_L16A_ID, 14)
+#define M4U_PORT_L16A_TSFSO_R1			MTK_M4U_ID(SMI_L16A_ID, 15)
+#define M4U_PORT_L16A_FLKO_R1			MTK_M4U_ID(SMI_L16A_ID, 16)
+
+/* LARB 16B -- CAM */
+#define M4U_PORT_L16B_IMGO_R1			MTK_M4U_ID(SMI_L16B_ID, 0)
+#define M4U_PORT_L16B_CQI_R1			MTK_M4U_ID(SMI_L16B_ID, 1)
+#define M4U_PORT_L16B_CQI_R2			MTK_M4U_ID(SMI_L16B_ID, 2)
+#define M4U_PORT_L16B_BPCI_R1			MTK_M4U_ID(SMI_L16B_ID, 3)
+#define M4U_PORT_L16B_LSCI_R1			MTK_M4U_ID(SMI_L16B_ID, 4)
+#define M4U_PORT_L16B_RAWI_R2			MTK_M4U_ID(SMI_L16B_ID, 5)
+#define M4U_PORT_L16B_RAWI_R3			MTK_M4U_ID(SMI_L16B_ID, 6)
+#define M4U_PORT_L16B_UFDI_R2			MTK_M4U_ID(SMI_L16B_ID, 7)
+#define M4U_PORT_L16B_UFDI_R3			MTK_M4U_ID(SMI_L16B_ID, 8)
+#define M4U_PORT_L16B_RAWI_R4			MTK_M4U_ID(SMI_L16B_ID, 9)
+#define M4U_PORT_L16B_RAWI_R5			MTK_M4U_ID(SMI_L16B_ID, 10)
+#define M4U_PORT_L16B_AAI_R1			MTK_M4U_ID(SMI_L16B_ID, 11)
+#define M4U_PORT_L16B_UFDI_R5			MTK_M4U_ID(SMI_L16B_ID, 12)
+#define M4U_PORT_L16B_FHO_R1			MTK_M4U_ID(SMI_L16B_ID, 13)
+#define M4U_PORT_L16B_AAO_R1			MTK_M4U_ID(SMI_L16B_ID, 14)
+#define M4U_PORT_L16B_TSFSO_R1			MTK_M4U_ID(SMI_L16B_ID, 15)
+#define M4U_PORT_L16B_FLKO_R1			MTK_M4U_ID(SMI_L16B_ID, 16)
+
+/* LARB 17A -- CAM */
+#define M4U_PORT_L17A_YUVO_R1			MTK_M4U_ID(SMI_L17A_ID, 0)
+#define M4U_PORT_L17A_YUVO_R3			MTK_M4U_ID(SMI_L17A_ID, 1)
+#define M4U_PORT_L17A_YUVCO_R1			MTK_M4U_ID(SMI_L17A_ID, 2)
+#define M4U_PORT_L17A_YUVO_R2			MTK_M4U_ID(SMI_L17A_ID, 3)
+#define M4U_PORT_L17A_RZH1N2TO_R1		MTK_M4U_ID(SMI_L17A_ID, 4)
+#define M4U_PORT_L17A_DRZS4NO_R1		MTK_M4U_ID(SMI_L17A_ID, 5)
+#define M4U_PORT_L17A_TNCSO_R1			MTK_M4U_ID(SMI_L17A_ID, 6)
+
+/* LARB 17B -- CAM */
+#define M4U_PORT_L17B_YUVO_R1			MTK_M4U_ID(SMI_L17B_ID, 0)
+#define M4U_PORT_L17B_YUVO_R3			MTK_M4U_ID(SMI_L17B_ID, 1)
+#define M4U_PORT_L17B_YUVCO_R1			MTK_M4U_ID(SMI_L17B_ID, 2)
+#define M4U_PORT_L17B_YUVO_R2			MTK_M4U_ID(SMI_L17B_ID, 3)
+#define M4U_PORT_L17B_RZH1N2TO_R1		MTK_M4U_ID(SMI_L17B_ID, 4)
+#define M4U_PORT_L17B_DRZS4NO_R1		MTK_M4U_ID(SMI_L17B_ID, 5)
+#define M4U_PORT_L17B_TNCSO_R1			MTK_M4U_ID(SMI_L17B_ID, 6)
+
+/* LARB 19 -- VENC */
+#define M4U_PORT_L19_VENC_RCPU			MTK_M4U_ID(SMI_L19_ID, 0)
+#define M4U_PORT_L19_VENC_REC			MTK_M4U_ID(SMI_L19_ID, 1)
+#define M4U_PORT_L19_VENC_BSDMA			MTK_M4U_ID(SMI_L19_ID, 2)
+#define M4U_PORT_L19_VENC_SV_COMV		MTK_M4U_ID(SMI_L19_ID, 3)
+#define M4U_PORT_L19_VENC_RD_COMV		MTK_M4U_ID(SMI_L19_ID, 4)
+#define M4U_PORT_L19_VENC_NBM_RDMA		MTK_M4U_ID(SMI_L19_ID, 5)
+#define M4U_PORT_L19_VENC_NBM_RDMA_LITE		MTK_M4U_ID(SMI_L19_ID, 6)
+#define M4U_PORT_L19_JPGENC_Y_RDMA		MTK_M4U_ID(SMI_L19_ID, 7)
+#define M4U_PORT_L19_JPGENC_C_RDMA		MTK_M4U_ID(SMI_L19_ID, 8)
+#define M4U_PORT_L19_JPGENC_Q_TABLE		MTK_M4U_ID(SMI_L19_ID, 9)
+#define M4U_PORT_L19_VENC_SUB_W_LUMA		MTK_M4U_ID(SMI_L19_ID, 10)
+#define M4U_PORT_L19_VENC_FCS_NBM_RDMA		MTK_M4U_ID(SMI_L19_ID, 11)
+#define M4U_PORT_L19_JPGENC_BSDMA		MTK_M4U_ID(SMI_L19_ID, 12)
+#define M4U_PORT_L19_JPGDEC_WDMA_0		MTK_M4U_ID(SMI_L19_ID, 13)
+#define M4U_PORT_L19_JPGDEC_BSDMA_0		MTK_M4U_ID(SMI_L19_ID, 14)
+#define M4U_PORT_L19_VENC_NBM_WDMA		MTK_M4U_ID(SMI_L19_ID, 15)
+#define M4U_PORT_L19_VENC_NBM_WDMA_LITE		MTK_M4U_ID(SMI_L19_ID, 16)
+#define M4U_PORT_L19_VENC_FCS_NBM_WDMA		MTK_M4U_ID(SMI_L19_ID, 17)
+#define M4U_PORT_L19_JPGDEC_WDMA_1		MTK_M4U_ID(SMI_L19_ID, 18)
+#define M4U_PORT_L19_JPGDEC_BSDMA_1		MTK_M4U_ID(SMI_L19_ID, 19)
+#define M4U_PORT_L19_JPGDEC_HUFF_OFFSET_1	MTK_M4U_ID(SMI_L19_ID, 20)
+#define M4U_PORT_L19_JPGDEC_HUFF_OFFSET_0	MTK_M4U_ID(SMI_L19_ID, 21)
+#define M4U_PORT_L19_VENC_CUR_LUMA		MTK_M4U_ID(SMI_L19_ID, 22)
+#define M4U_PORT_L19_VENC_CUR_CHROMA		MTK_M4U_ID(SMI_L19_ID, 23)
+#define M4U_PORT_L19_VENC_REF_LUMA		MTK_M4U_ID(SMI_L19_ID, 24)
+#define M4U_PORT_L19_VENC_REF_CHROMA		MTK_M4U_ID(SMI_L19_ID, 25)
+#define M4U_PORT_L19_VENC_SUB_R_LUMA		MTK_M4U_ID(SMI_L19_ID, 26)
+
+/* LARB 21 -- VDEC-CORE0 */
+#define M4U_PORT_L21_HW_VDEC_MC_EXT		MTK_M4U_ID(SMI_L21_ID, 0)
+#define M4U_PORT_L21_HW_VDEC_UFO_EXT		MTK_M4U_ID(SMI_L21_ID, 1)
+#define M4U_PORT_L21_HW_VDEC_PP_EXT		MTK_M4U_ID(SMI_L21_ID, 2)
+#define M4U_PORT_L21_HW_VDEC_PRED_RD_EXT	MTK_M4U_ID(SMI_L21_ID, 3)
+#define M4U_PORT_L21_HW_VDEC_PRED_WR_EXT	MTK_M4U_ID(SMI_L21_ID, 4)
+#define M4U_PORT_L21_HW_VDEC_PPWRAP_EXT		MTK_M4U_ID(SMI_L21_ID, 5)
+#define M4U_PORT_L21_HW_VDEC_TILE_EXT		MTK_M4U_ID(SMI_L21_ID, 6)
+#define M4U_PORT_L21_HW_VDEC_VLD_EXT		MTK_M4U_ID(SMI_L21_ID, 7)
+#define M4U_PORT_L21_HW_VDEC_VLD2_EXT		MTK_M4U_ID(SMI_L21_ID, 8)
+#define M4U_PORT_L21_HW_VDEC_AVC_MV_EXT		MTK_M4U_ID(SMI_L21_ID, 9)
+#define M4U_PORT_L21_HW_VDEC_UFO_EXT_C		MTK_M4U_ID(SMI_L21_ID, 10)
+
+/* LARB 23 -- VDEC-SOC */
+#define M4U_PORT_L23_HW_VDEC_LAT0_VLD_EXT	MTK_M4U_ID(SMI_L23_ID, 0)
+#define M4U_PORT_L23_HW_VDEC_LAT0_VLD2_EXT	MTK_M4U_ID(SMI_L23_ID, 1)
+#define M4U_PORT_L23_HW_VDEC_LAT0_AVC_MV_EXT	MTK_M4U_ID(SMI_L23_ID, 2)
+#define M4U_PORT_L23_HW_VDEC_LAT0_PRED_RD_EXT	MTK_M4U_ID(SMI_L23_ID, 3)
+#define M4U_PORT_L23_HW_VDEC_LAT0_TILE_EXT	MTK_M4U_ID(SMI_L23_ID, 4)
+#define M4U_PORT_L23_HW_VDEC_LAT0_WDMA_EXT	MTK_M4U_ID(SMI_L23_ID, 5)
+#define M4U_PORT_L23_HW_VDEC_UFO_ENC_EXT	MTK_M4U_ID(SMI_L23_ID, 6)
+#define M4U_PORT_L23_HW_VDEC_UFO_ENC_EXT_C	MTK_M4U_ID(SMI_L23_ID, 7)
+#define M4U_PORT_L23_HW_VDEC_MC_EXT_C		MTK_M4U_ID(SMI_L23_ID, 8)
+
+/* LARB 27 -- CCU */
+#define M4U_PORT_L27_CCUI			MTK_M4U_ID(SMI_L27_ID, 0)
+#define M4U_PORT_L27_CCUO			MTK_M4U_ID(SMI_L27_ID, 1)
+#define M4U_PORT_L27_CCUI2			MTK_M4U_ID(SMI_L27_ID, 2)
+#define M4U_PORT_L27_CCUO2			MTK_M4U_ID(SMI_L27_ID, 3)
+
+/* LARB 28 -- AXI-CCU */
+#define M4U_PORT_L28_CCU_AXI_0			MTK_M4U_ID(SMI_L28_ID, 0)
+
+/* infra/peri */
+#define IFR_IOMMU_PORT_PCIE_0			MTK_IFAIOMMU_PERI_ID(0)
+
+#endif

include/linux/amd-iommu.h

···
 struct pci_dev;
 
 extern int amd_iommu_detect(void);
-extern int amd_iommu_init_hardware(void);
 
 /**
  * amd_iommu_init_device() - Init device for use with IOMMUv2 driver

include/linux/dmar.h

···
 extern int dmar_table_init(void);
 extern int dmar_dev_scope_init(void);
 extern void dmar_register_bus_notifier(void);
-extern int dmar_parse_dev_scope(void *start, void *end, int *cnt,
-				struct dmar_dev_scope **devices, u16 segment);
 extern void *dmar_alloc_dev_scope(void *start, void *end, int *cnt);
 extern void dmar_free_dev_scope(struct dmar_dev_scope **devices, int *cnt);
 extern int dmar_insert_dev_scope(struct dmar_pci_notify_info *info,

include/linux/iommu.h

···
 	IOMMU_DEV_FEAT_IOPF,
 };
 
+#define IOMMU_NO_PASID	(0U) /* Reserved for DMA w/o PASID */
+#define IOMMU_FIRST_GLOBAL_PASID	(1U) /*starting range for allocation */
 #define IOMMU_PASID_INVALID	(-1U)
 typedef unsigned int ioasid_t;
 
···
  * @priv:	 IOMMU Driver private data
  * @max_pasids:  number of PASIDs this device can consume
  * @attach_deferred: the dma domain attachment is deferred
+ * @pci_32bit_workaround: Limit DMA allocations to 32-bit IOVAs
+ * @require_direct: device requires IOMMU_RESV_DIRECT regions
  *
  * TODO: migrate other per device data pointers under iommu_dev_data, e.g.
  *	struct iommu_group	*iommu_group;
···
 	void				*priv;
 	u32				max_pasids;
 	u32				attach_deferred:1;
+	u32				pci_32bit_workaround:1;
+	u32				require_direct:1;
 };
 
 int iommu_device_register(struct iommu_device *iommu,
···
 struct iommu_domain *
 iommu_get_domain_for_dev_pasid(struct device *dev, ioasid_t pasid,
 			       unsigned int type);
+ioasid_t iommu_alloc_global_pasid(struct device *dev);
+void iommu_free_global_pasid(ioasid_t pasid);
 #else /* CONFIG_IOMMU_API */
 
 struct iommu_ops {};
···
 {
 	return NULL;
 }
+
+static inline ioasid_t iommu_alloc_global_pasid(struct device *dev)
+{
+	return IOMMU_PASID_INVALID;
+}
+
+static inline void iommu_free_global_pasid(ioasid_t pasid) {}
 #endif /* CONFIG_IOMMU_API */
 
 /**

include/soc/mediatek/smi.h

···
 
 enum iommu_atf_cmd {
 	IOMMU_ATF_CMD_CONFIG_SMI_LARB,		/* For mm master to en/disable iommu */
+	IOMMU_ATF_CMD_CONFIG_INFRA_IOMMU,	/* For infra master to enable iommu */
 	IOMMU_ATF_CMD_MAX,
 };