Merge tag 'iommu-updates-v6.15' of git://git.kernel.org/pub/scm/linux/kernel/git/iommu/linux

Pull iommu updates from Joerg Roedel:
 "Core iommufd dependencies from Jason:
   - Change the iommufd fault handle into an always present hwpt handle
     in the domain
   - Give iommufd its own SW_MSI implementation along with some IRQ
     layer rework
   - Improvements to the handle attach API

  Core fixes for probe-issues from Robin

  Intel VT-d changes:
   - Checking for SVA support in domain allocation and attach paths
   - Move PCI ATS and PRI configuration into probe paths
   - Fix a pentential hang on reboot -f
   - Miscellaneous cleanups

  AMD-Vi changes:
   - Support for up to 2k IRQs per PCI device function
   - Set of smaller fixes

  ARM-SMMU changes:
   - SMMUv2 devicetree binding updates for Qualcomm implementations
     (QCS8300 GPU and MSM8937)
   - Clean up SMMUv2 runtime PM implementation to help with wider rework
     of pm_runtime_put_autosuspend()

  Rockchip driver changes:
   - Driver adjustments for recent DT probing changes

  S390 IOMMU changes:
   - Support for IOMMU passthrough

  Apple Dart changes:
   - Driver adjustments to meet ISP device requirements
   - Null-ptr deref fix
   - Disable subpage protection for DART 1"

* tag 'iommu-updates-v6.15' of git://git.kernel.org/pub/scm/linux/kernel/git/iommu/linux: (54 commits)
  iommu/vt-d: Fix possible circular locking dependency
  iommu/vt-d: Don't clobber posted vCPU IRTE when host IRQ affinity changes
  iommu/vt-d: Put IRTE back into posted MSI mode if vCPU posting is disabled
  iommu: apple-dart: fix potential null pointer deref
  iommu/rockchip: Retire global dma_dev workaround
  iommu/rockchip: Register in a sensible order
  iommu/rockchip: Allocate per-device data sensibly
  iommu/mediatek-v1: Support COMPILE_TEST
  iommu/amd: Enable support for up to 2K interrupts per function
  iommu/amd: Rename DTE_INTTABLEN* and MAX_IRQS_PER_TABLE macro
  iommu/amd: Replace slab cache allocator with page allocator
  iommu/amd: Introduce generic function to set multibit feature value
  iommu: Don't warn prematurely about dodgy probes
  iommu/arm-smmu: Set rpm auto_suspend once during probe
  dt-bindings: arm-smmu: Document QCS8300 GPU SMMU
  iommu: Get DT/ACPI parsing into the proper probe path
  iommu: Keep dev->iommu state consistent
  iommu: Resolve ops in iommu_init_device()
  iommu: Handle race with default domain setup
  iommu: Unexport iommu_fwspec_free()
  ...

Author: torvalds

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

@@ -90,6 +90,7 @@ properties:
           - enum:
               - qcom,qcm2290-smmu-500
               - qcom,qcs615-smmu-500
+              - qcom,qcs8300-smmu-500
               - qcom,sa8255p-smmu-500
               - qcom,sa8775p-smmu-500
               - qcom,sar2130p-smmu-500
@@ -397,6 +398,7 @@ allOf:
         compatible:
           contains:
             enum:
+              - qcom,qcs8300-smmu-500
               - qcom,sa8775p-smmu-500
               - qcom,sc7280-smmu-500
               - qcom,sc8280xp-smmu-500
@@ -581,7 +583,6 @@ allOf:
               - cavium,smmu-v2
               - marvell,ap806-smmu-500
               - nvidia,smmu-500
-              - qcom,qcs8300-smmu-500
               - qcom,qdu1000-smmu-500
               - qcom,sa8255p-smmu-500
               - qcom,sc7180-smmu-500

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

@@ -22,6 +22,7 @@ properties:
           - enum:
               - qcom,msm8916-iommu
               - qcom,msm8917-iommu
+              - qcom,msm8937-iommu
               - qcom,msm8953-iommu
           - const: qcom,msm-iommu-v1
       - items:

arch/s390/include/asm/pci.h

@@ -144,7 +144,7 @@ struct zpci_dev {
 	u8		util_str_avail	: 1;
 	u8		irqs_registered	: 1;
 	u8		tid_avail	: 1;
-	u8		reserved	: 1;
+	u8		rtr_avail	: 1; /* Relaxed translation allowed */
 	unsigned int	devfn;		/* DEVFN part of the RID*/
 
 	u8 pfip[CLP_PFIP_NR_SEGMENTS];	/* pci function internal path */
@@ -217,6 +217,7 @@ extern struct airq_iv *zpci_aif_sbv;
 struct zpci_dev *zpci_create_device(u32 fid, u32 fh, enum zpci_state state);
 int zpci_add_device(struct zpci_dev *zdev);
 int zpci_enable_device(struct zpci_dev *);
+int zpci_reenable_device(struct zpci_dev *zdev);
 int zpci_disable_device(struct zpci_dev *);
 int zpci_scan_configured_device(struct zpci_dev *zdev, u32 fh);
 int zpci_deconfigure_device(struct zpci_dev *zdev);
@@ -245,6 +246,7 @@ void update_uid_checking(bool new);
 /* IOMMU Interface */
 int zpci_init_iommu(struct zpci_dev *zdev);
 void zpci_destroy_iommu(struct zpci_dev *zdev);
+int zpci_iommu_register_ioat(struct zpci_dev *zdev, u8 *status);
 
 #ifdef CONFIG_PCI
 static inline bool zpci_use_mio(struct zpci_dev *zdev)

arch/s390/include/asm/pci_clp.h

@@ -156,7 +156,9 @@ struct clp_rsp_query_pci_grp {
 	u16			:  4;
 	u16 noi			: 12;	/* number of interrupts */
 	u8 version;
-	u8			:  6;
+	u8			:  2;
+	u8 rtr			:  1;	/* Relaxed translation requirement */
+	u8			:  3;
 	u8 frame		:  1;
 	u8 refresh		:  1;	/* TLB refresh mode */
 	u16			:  3;

arch/s390/kvm/pci.c

@@ -433,7 +433,6 @@ static void kvm_s390_pci_dev_release(struct zpci_dev *zdev)
 static int kvm_s390_pci_register_kvm(void *opaque, struct kvm *kvm)
 {
 	struct zpci_dev *zdev = opaque;
-	u8 status;
 	int rc;
 
 	if (!zdev)
@@ -480,13 +479,7 @@ static int kvm_s390_pci_register_kvm(void *opaque, struct kvm *kvm)
 	 */
 	zdev->gisa = (u32)virt_to_phys(&kvm->arch.sie_page2->gisa);
 
-	rc = zpci_enable_device(zdev);
-	if (rc)
-		goto clear_gisa;
-
-	/* Re-register the IOMMU that was already created */
-	rc = zpci_register_ioat(zdev, 0, zdev->start_dma, zdev->end_dma,
-				virt_to_phys(zdev->dma_table), &status);
+	rc = zpci_reenable_device(zdev);
 	if (rc)
 		goto clear_gisa;
 
@@ -516,7 +509,6 @@ static void kvm_s390_pci_unregister_kvm(void *opaque)
 {
 	struct zpci_dev *zdev = opaque;
 	struct kvm *kvm;
-	u8 status;
 
 	if (!zdev)
 		return;
@@ -550,12 +542,7 @@ static void kvm_s390_pci_unregister_kvm(void *opaque)
 			goto out;
 	}
 
-	if (zpci_enable_device(zdev))
-		goto out;
-
-	/* Re-register the IOMMU that was already created */
-	zpci_register_ioat(zdev, 0, zdev->start_dma, zdev->end_dma,
-			   virt_to_phys(zdev->dma_table), &status);
+	zpci_reenable_device(zdev);
 
 out:
 	spin_lock(&kvm->arch.kzdev_list_lock);

arch/s390/pci/pci.c

@@ -124,14 +124,13 @@ int zpci_register_ioat(struct zpci_dev *zdev, u8 dmaas,
 	struct zpci_fib fib = {0};
 	u8 cc;
 
-	WARN_ON_ONCE(iota & 0x3fff);
 	fib.pba = base;
 	/* Work around off by one in ISM virt device */
 	if (zdev->pft == PCI_FUNC_TYPE_ISM && limit > base)
 		fib.pal = limit + (1 << 12);
 	else
 		fib.pal = limit;
-	fib.iota = iota | ZPCI_IOTA_RTTO_FLAG;
+	fib.iota = iota;
 	fib.gd = zdev->gisa;
 	cc = zpci_mod_fc(req, &fib, status);
 	if (cc)
@@ -690,6 +689,23 @@ int zpci_enable_device(struct zpci_dev *zdev)
 }
 EXPORT_SYMBOL_GPL(zpci_enable_device);
 
+int zpci_reenable_device(struct zpci_dev *zdev)
+{
+	u8 status;
+	int rc;
+
+	rc = zpci_enable_device(zdev);
+	if (rc)
+		return rc;
+
+	rc = zpci_iommu_register_ioat(zdev, &status);
+	if (rc)
+		zpci_disable_device(zdev);
+
+	return rc;
+}
+EXPORT_SYMBOL_GPL(zpci_reenable_device);
+
 int zpci_disable_device(struct zpci_dev *zdev)
 {
 	u32 fh = zdev->fh;
@@ -739,7 +755,6 @@ EXPORT_SYMBOL_GPL(zpci_disable_device);
  */
 int zpci_hot_reset_device(struct zpci_dev *zdev)
 {
-	u8 status;
 	int rc;
 
 	lockdep_assert_held(&zdev->state_lock);
@@ -758,19 +773,9 @@ int zpci_hot_reset_device(struct zpci_dev *zdev)
 			return rc;
 	}
 
-	rc = zpci_enable_device(zdev);
-	if (rc)
-		return rc;
-
-	if (zdev->dma_table)
-		rc = zpci_register_ioat(zdev, 0, zdev->start_dma, zdev->end_dma,
-					virt_to_phys(zdev->dma_table), &status);
-	if (rc) {
-		zpci_disable_device(zdev);
-		return rc;
-	}
+	rc = zpci_reenable_device(zdev);
 
-	return 0;
+	return rc;
 }
 
 /**

arch/s390/pci/pci_bus.c

@@ -19,6 +19,7 @@
 #include <linux/jump_label.h>
 #include <linux/pci.h>
 #include <linux/printk.h>
+#include <linux/dma-direct.h>
 
 #include <asm/pci_clp.h>
 #include <asm/pci_dma.h>
@@ -283,10 +284,34 @@ static struct zpci_bus *zpci_bus_alloc(int topo, bool topo_is_tid)
 	return zbus;
 }
 
+static void pci_dma_range_setup(struct pci_dev *pdev)
+{
+	struct zpci_dev *zdev = to_zpci(pdev);
+	struct bus_dma_region *map;
+	u64 aligned_end;
+
+	map = kzalloc(sizeof(*map), GFP_KERNEL);
+	if (!map)
+		return;
+
+	map->cpu_start = 0;
+	map->dma_start = PAGE_ALIGN(zdev->start_dma);
+	aligned_end = PAGE_ALIGN_DOWN(zdev->end_dma + 1);
+	if (aligned_end >= map->dma_start)
+		map->size = aligned_end - map->dma_start;
+	else
+		map->size = 0;
+	WARN_ON_ONCE(map->size == 0);
+
+	pdev->dev.dma_range_map = map;
+}
+
 void pcibios_bus_add_device(struct pci_dev *pdev)
 {
 	struct zpci_dev *zdev = to_zpci(pdev);
 
+	pci_dma_range_setup(pdev);
+
 	/*
 	 * With pdev->no_vf_scan the common PCI probing code does not
 	 * perform PF/VF linking.

arch/s390/pci/pci_clp.c

@@ -112,6 +112,7 @@ static void clp_store_query_pci_fngrp(struct zpci_dev *zdev,
 	zdev->version = response->version;
 	zdev->maxstbl = response->maxstbl;
 	zdev->dtsm = response->dtsm;
+	zdev->rtr_avail = response->rtr;
 
 	switch (response->version) {
 	case 1:

arch/s390/pci/pci_sysfs.c

@@ -52,7 +52,6 @@ static DEVICE_ATTR_RO(mio_enabled);
 
 static int _do_recover(struct pci_dev *pdev, struct zpci_dev *zdev)
 {
-	u8 status;
 	int ret;
 
 	pci_stop_and_remove_bus_device(pdev);
@@ -70,16 +69,8 @@ static int _do_recover(struct pci_dev *pdev, struct zpci_dev *zdev)
 			return ret;
 	}
 
-	ret = zpci_enable_device(zdev);
-	if (ret)
-		return ret;
+	ret = zpci_reenable_device(zdev);
 
-	if (zdev->dma_table) {
-		ret = zpci_register_ioat(zdev, 0, zdev->start_dma, zdev->end_dma,
-					 virt_to_phys(zdev->dma_table), &status);
-		if (ret)
-			zpci_disable_device(zdev);
-	}
 	return ret;
 }
 

drivers/acpi/arm64/dma.c

@@ -26,6 +26,11 @@ void acpi_arch_dma_setup(struct device *dev)
 	else
 		end = (1ULL << 32) - 1;
 
+	if (dev->dma_range_map) {
+		dev_dbg(dev, "dma_range_map already set\n");
+		return;
+	}
+
 	ret = acpi_dma_get_range(dev, &map);
 	if (!ret && map) {
 		end = dma_range_map_max(map);

drivers/acpi/scan.c

@@ -1632,13 +1632,6 @@ static int acpi_iommu_configure_id(struct device *dev, const u32 *id_in)
 		err = viot_iommu_configure(dev);
 	mutex_unlock(&iommu_probe_device_lock);
 
-	/*
-	 * 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)
-		err = iommu_probe_device(dev);
-
 	return err;
 }
 

drivers/amba/bus.c

@@ -364,7 +364,8 @@ static int amba_dma_configure(struct device *dev)
 		ret = acpi_dma_configure(dev, attr);
 	}
 
-	if (!ret && !drv->driver_managed_dma) {
+	/* @drv may not be valid when we're called from the IOMMU layer */
+	if (!ret && dev->driver && !drv->driver_managed_dma) {
 		ret = iommu_device_use_default_domain(dev);
 		if (ret)
 			arch_teardown_dma_ops(dev);

drivers/base/platform.c

@@ -1451,7 +1451,8 @@ static int platform_dma_configure(struct device *dev)
 		attr = acpi_get_dma_attr(to_acpi_device_node(fwnode));
 		ret = acpi_dma_configure(dev, attr);
 	}
-	if (ret || drv->driver_managed_dma)
+	/* @drv may not be valid when we're called from the IOMMU layer */
+	if (ret || !dev->driver || drv->driver_managed_dma)
 		return ret;
 
 	ret = iommu_device_use_default_domain(dev);

drivers/bus/fsl-mc/fsl-mc-bus.c

@@ -153,7 +153,8 @@ static int fsl_mc_dma_configure(struct device *dev)
 	else
 		ret = acpi_dma_configure_id(dev, DEV_DMA_COHERENT, &input_id);
 
-	if (!ret && !mc_drv->driver_managed_dma) {
+	/* @mc_drv may not be valid when we're called from the IOMMU layer */
+	if (!ret && dev->driver && !mc_drv->driver_managed_dma) {
 		ret = iommu_device_use_default_domain(dev);
 		if (ret)
 			arch_teardown_dma_ops(dev);

drivers/cdx/cdx.c

@@ -360,7 +360,8 @@ static int cdx_dma_configure(struct device *dev)
 		return ret;
 	}
 
-	if (!ret && !cdx_drv->driver_managed_dma) {
+	/* @cdx_drv may not be valid when we're called from the IOMMU layer */
+	if (!ret && dev->driver && !cdx_drv->driver_managed_dma) {
 		ret = iommu_device_use_default_domain(dev);
 		if (ret)
 			arch_teardown_dma_ops(dev);

drivers/iommu/Kconfig

@@ -154,7 +154,6 @@ config IOMMU_DMA
 	select DMA_OPS_HELPERS
 	select IOMMU_API
 	select IOMMU_IOVA
-	select IRQ_MSI_IOMMU
 	select NEED_SG_DMA_LENGTH
 	select NEED_SG_DMA_FLAGS if SWIOTLB
 
@@ -483,8 +482,7 @@ config MTK_IOMMU
 
 config MTK_IOMMU_V1
 	tristate "MediaTek IOMMU Version 1 (M4U gen1) Support"
-	depends on ARM
-	depends on ARCH_MEDIATEK || COMPILE_TEST
+	depends on (ARCH_MEDIATEK && ARM) || COMPILE_TEST
 	select ARM_DMA_USE_IOMMU
 	select IOMMU_API
 	select MEMORY

drivers/iommu/amd/amd_iommu.h

@@ -47,7 +47,6 @@ extern unsigned long amd_iommu_pgsize_bitmap;
 /* Protection domain ops */
 void amd_iommu_init_identity_domain(void);
 struct protection_domain *protection_domain_alloc(void);
-void protection_domain_free(struct protection_domain *domain);
 struct iommu_domain *amd_iommu_domain_alloc_sva(struct device *dev,
 						struct mm_struct *mm);
 void amd_iommu_domain_free(struct iommu_domain *dom);
@@ -176,12 +175,11 @@ void amd_iommu_apply_ivrs_quirks(void);
 #else
 static inline void amd_iommu_apply_ivrs_quirks(void) { }
 #endif
+struct dev_table_entry *amd_iommu_get_ivhd_dte_flags(u16 segid, u16 devid);
 
 void amd_iommu_domain_set_pgtable(struct protection_domain *domain,
 				  u64 *root, int mode);
 struct dev_table_entry *get_dev_table(struct amd_iommu *iommu);
-
-#endif
-
-struct dev_table_entry *amd_iommu_get_ivhd_dte_flags(u16 segid, u16 devid);
 struct iommu_dev_data *search_dev_data(struct amd_iommu *iommu, u16 devid);
+
+#endif /* AMD_IOMMU_H */