Merge tag 'iommu-updates-v4.21' of git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu

Pull IOMMU updates from Joerg Roedel:

 - Page table code for AMD IOMMU now supports large pages where smaller
   page-sizes were mapped before. VFIO had to work around that in the
   past and I included a patch to remove it (acked by Alex Williamson)

 - Patches to unmodularize a couple of IOMMU drivers that would never
   work as modules anyway.

 - Work to unify the the iommu-related pointers in 'struct device' into
   one pointer. This work is not finished yet, but will probably be in
   the next cycle.

 - NUMA aware allocation in iommu-dma code

 - Support for r8a774a1 and r8a774c0 in the Renesas IOMMU driver

 - Scalable mode support for the Intel VT-d driver

 - PM runtime improvements for the ARM-SMMU driver

 - Support for the QCOM-SMMUv2 IOMMU hardware from Qualcom

 - Various smaller fixes and improvements

* tag 'iommu-updates-v4.21' of git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu: (78 commits)
  iommu: Check for iommu_ops == NULL in iommu_probe_device()
  ACPI/IORT: Don't call iommu_ops->add_device directly
  iommu/of: Don't call iommu_ops->add_device directly
  iommu: Consolitate ->add/remove_device() calls
  iommu/sysfs: Rename iommu_release_device()
  dmaengine: sh: rcar-dmac: Use device_iommu_mapped()
  xhci: Use device_iommu_mapped()
  powerpc/iommu: Use device_iommu_mapped()
  ACPI/IORT: Use device_iommu_mapped()
  iommu/of: Use device_iommu_mapped()
  driver core: Introduce device_iommu_mapped() function
  iommu/tegra: Use helper functions to access dev->iommu_fwspec
  iommu/qcom: Use helper functions to access dev->iommu_fwspec
  iommu/of: Use helper functions to access dev->iommu_fwspec
  iommu/mediatek: Use helper functions to access dev->iommu_fwspec
  iommu/ipmmu-vmsa: Use helper functions to access dev->iommu_fwspec
  iommu/dma: Use helper functions to access dev->iommu_fwspec
  iommu/arm-smmu: Use helper functions to access dev->iommu_fwspec
  ACPI/IORT: Use helper functions to access dev->iommu_fwspec
  iommu: Introduce wrappers around dev->iommu_fwspec
  ...

Author: torvalds

Documentation/admin-guide/kernel-parameters.txt

@@ -1690,12 +1690,12 @@
 			By default, super page will be supported if Intel IOMMU
 			has the capability. With this option, super page will
 			not be supported.
-		ecs_off [Default Off]
-			By default, extended context tables will be supported if
-			the hardware advertises that it has support both for the
-			extended tables themselves, and also PASID support. With
-			this option set, extended tables will not be used even
-			on hardware which claims to support them.
+		sm_off [Default Off]
+			By default, scalable mode will be supported if the
+			hardware advertises that it has support for the scalable
+			mode translation. With this option set, scalable mode
+			will not be used even on hardware which claims to support
+			it.
 		tboot_noforce [Default Off]
 			Do not force the Intel IOMMU enabled under tboot.
 			By default, tboot will force Intel IOMMU on, which

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

@@ -17,10 +17,20 @@ conditions.
                         "arm,mmu-401"
                         "arm,mmu-500"
                         "cavium,smmu-v2"
+                        "qcom,smmu-v2"
 
                   depending on the particular implementation and/or the
                   version of the architecture implemented.
 
+                  Qcom SoCs must contain, as below, SoC-specific compatibles
+                  along with "qcom,smmu-v2":
+                  "qcom,msm8996-smmu-v2", "qcom,smmu-v2",
+                  "qcom,sdm845-smmu-v2", "qcom,smmu-v2".
+
+                  Qcom SoCs implementing "arm,mmu-500" must also include,
+                  as below, SoC-specific compatibles:
+                  "qcom,sdm845-smmu-500", "arm,mmu-500"
+
 - reg           : Base address and size of the SMMU.
 
 - #global-interrupts : The number of global interrupts exposed by the
@@ -71,6 +81,22 @@ conditions.
                   or using stream matching with #iommu-cells = <2>, and
                   may be ignored if present in such cases.
 
+- clock-names:    List of the names of clocks input to the device. The
+                  required list depends on particular implementation and
+                  is as follows:
+                  - for "qcom,smmu-v2":
+                    - "bus": clock required for downstream bus access and
+                             for the smmu ptw,
+                    - "iface": clock required to access smmu's registers
+                               through the TCU's programming interface.
+                  - unspecified for other implementations.
+
+- clocks:         Specifiers for all clocks listed in the clock-names property,
+                  as per generic clock bindings.
+
+- power-domains:  Specifiers for power domains required to be powered on for
+                  the SMMU to operate, as per generic power domain bindings.
+
 ** Deprecated properties:
 
 - mmu-masters (deprecated in favour of the generic "iommus" binding) :
@@ -137,3 +163,20 @@ conditions.
                 iommu-map = <0 &smmu3 0 0x400>;
                 ...
         };
+
+	/* Qcom's arm,smmu-v2 implementation */
+	smmu4: iommu@d00000 {
+		compatible = "qcom,msm8996-smmu-v2", "qcom,smmu-v2";
+		reg = <0xd00000 0x10000>;
+
+		#global-interrupts = <1>;
+		interrupts = <GIC_SPI 73 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 320 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 321 IRQ_TYPE_LEVEL_HIGH>;
+		#iommu-cells = <1>;
+		power-domains = <&mmcc MDSS_GDSC>;
+
+		clocks = <&mmcc SMMU_MDP_AXI_CLK>,
+			 <&mmcc SMMU_MDP_AHB_CLK>;
+		clock-names = "bus", "iface";
+	};

Documentation/devicetree/bindings/iommu/renesas,ipmmu-vmsa.txt

@@ -14,6 +14,8 @@ Required Properties:
     - "renesas,ipmmu-r8a7743" for the R8A7743 (RZ/G1M) IPMMU.
     - "renesas,ipmmu-r8a7744" for the R8A7744 (RZ/G1N) IPMMU.
     - "renesas,ipmmu-r8a7745" for the R8A7745 (RZ/G1E) IPMMU.
+    - "renesas,ipmmu-r8a774a1" for the R8A774A1 (RZ/G2M) IPMMU.
+    - "renesas,ipmmu-r8a774c0" for the R8A774C0 (RZ/G2E) IPMMU.
     - "renesas,ipmmu-r8a7790" for the R8A7790 (R-Car H2) IPMMU.
     - "renesas,ipmmu-r8a7791" for the R8A7791 (R-Car M2-W) IPMMU.
     - "renesas,ipmmu-r8a7793" for the R8A7793 (R-Car M2-N) IPMMU.

arch/powerpc/kernel/eeh.c

@@ -1472,7 +1472,7 @@ static int dev_has_iommu_table(struct device *dev, void *data)
 	if (!dev)
 		return 0;
 
-	if (dev->iommu_group) {
+	if (device_iommu_mapped(dev)) {
 		*ppdev = pdev;
 		return 1;
 	}

arch/powerpc/kernel/iommu.c

@@ -1088,7 +1088,7 @@ int iommu_add_device(struct iommu_table_group *table_group, struct device *dev)
 	if (!device_is_registered(dev))
 		return -ENOENT;
 
-	if (dev->iommu_group) {
+	if (device_iommu_mapped(dev)) {
 		pr_debug("%s: Skipping device %s with iommu group %d\n",
 			 __func__, dev_name(dev),
 			 iommu_group_id(dev->iommu_group));
@@ -1109,7 +1109,7 @@ void iommu_del_device(struct device *dev)
 	 * and we needn't detach them from the associated
 	 * IOMMU groups
 	 */
-	if (!dev->iommu_group) {
+	if (!device_iommu_mapped(dev)) {
 		pr_debug("iommu_tce: skipping device %s with no tbl\n",
 			 dev_name(dev));
 		return;

arch/x86/kernel/tboot.c

@@ -19,7 +19,7 @@
  *
  */
 
-#include <linux/dma_remapping.h>
+#include <linux/intel-iommu.h>
 #include <linux/init_task.h>
 #include <linux/spinlock.h>
 #include <linux/export.h>

drivers/acpi/arm64/iort.c

@@ -779,7 +779,7 @@ static inline bool iort_iommu_driver_enabled(u8 type)
 static struct acpi_iort_node *iort_get_msi_resv_iommu(struct device *dev)
 {
 	struct acpi_iort_node *iommu;
-	struct iommu_fwspec *fwspec = dev->iommu_fwspec;
+	struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev);
 
 	iommu = iort_get_iort_node(fwspec->iommu_fwnode);
 
@@ -794,9 +794,10 @@ static struct acpi_iort_node *iort_get_msi_resv_iommu(struct device *dev)
 	return NULL;
 }
 
-static inline const struct iommu_ops *iort_fwspec_iommu_ops(
-				struct iommu_fwspec *fwspec)
+static inline const struct iommu_ops *iort_fwspec_iommu_ops(struct device *dev)
 {
+	struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev);
+
 	return (fwspec && fwspec->ops) ? fwspec->ops : NULL;
 }
 
@@ -805,8 +806,8 @@ static inline int iort_add_device_replay(const struct iommu_ops *ops,
 {
 	int err = 0;
 
-	if (ops->add_device && dev->bus && !dev->iommu_group)
-		err = ops->add_device(dev);
+	if (dev->bus && !device_iommu_mapped(dev))
+		err = iommu_probe_device(dev);
 
 	return err;
 }
@@ -824,6 +825,7 @@ static inline int iort_add_device_replay(const struct iommu_ops *ops,
  */
 int iort_iommu_msi_get_resv_regions(struct device *dev, struct list_head *head)
 {
+	struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev);
 	struct acpi_iort_its_group *its;
 	struct acpi_iort_node *iommu_node, *its_node = NULL;
 	int i, resv = 0;
@@ -841,9 +843,9 @@ int iort_iommu_msi_get_resv_regions(struct device *dev, struct list_head *head)
 	 * a given PCI or named component may map IDs to.
 	 */
 
-	for (i = 0; i < dev->iommu_fwspec->num_ids; i++) {
+	for (i = 0; i < fwspec->num_ids; i++) {
 		its_node = iort_node_map_id(iommu_node,
-					dev->iommu_fwspec->ids[i],
+					fwspec->ids[i],
 					NULL, IORT_MSI_TYPE);
 		if (its_node)
 			break;
@@ -874,8 +876,7 @@ int iort_iommu_msi_get_resv_regions(struct device *dev, struct list_head *head)
 	return (resv == its->its_count) ? resv : -ENODEV;
 }
 #else
-static inline const struct iommu_ops *iort_fwspec_iommu_ops(
-				struct iommu_fwspec *fwspec)
+static inline const struct iommu_ops *iort_fwspec_iommu_ops(struct device *dev);
 { return NULL; }
 static inline int iort_add_device_replay(const struct iommu_ops *ops,
 					 struct device *dev)
@@ -1045,7 +1046,7 @@ const struct iommu_ops *iort_iommu_configure(struct device *dev)
 	 * If we already translated the fwspec there
 	 * is nothing left to do, return the iommu_ops.
 	 */
-	ops = iort_fwspec_iommu_ops(dev->iommu_fwspec);
+	ops = iort_fwspec_iommu_ops(dev);
 	if (ops)
 		return ops;
 
@@ -1084,7 +1085,7 @@ const struct iommu_ops *iort_iommu_configure(struct device *dev)
 	 * add_device callback for dev, replay it to get things in order.
 	 */
 	if (!err) {
-		ops = iort_fwspec_iommu_ops(dev->iommu_fwspec);
+		ops = iort_fwspec_iommu_ops(dev);
 		err = iort_add_device_replay(ops, dev);
 	}
 

drivers/dma/sh/rcar-dmac.c

@@ -1809,7 +1809,7 @@ static int rcar_dmac_probe(struct platform_device *pdev)
 	 * level we can't disable it selectively, so ignore channel 0 for now if
 	 * the device is part of an IOMMU group.
 	 */
-	if (pdev->dev.iommu_group) {
+	if (device_iommu_mapped(&pdev->dev)) {
 		dmac->n_channels--;
 		channels_offset = 1;
 	}

drivers/gpu/drm/i915/i915_gem_execbuffer.c

@@ -26,7 +26,7 @@
  *
  */
 
-#include <linux/dma_remapping.h>
+#include <linux/intel-iommu.h>
 #include <linux/reservation.h>
 #include <linux/sync_file.h>
 #include <linux/uaccess.h>

drivers/gpu/drm/i915/intel_display.c

@@ -46,7 +46,7 @@
 #include <drm/drm_plane_helper.h>
 #include <drm/drm_rect.h>
 #include <drm/drm_atomic_uapi.h>
-#include <linux/dma_remapping.h>
+#include <linux/intel-iommu.h>
 #include <linux/reservation.h>
 
 /* Primary plane formats for gen <= 3 */

drivers/gpu/drm/vmwgfx/vmwgfx_drv.c

@@ -34,7 +34,7 @@
 #include <drm/ttm/ttm_placement.h>
 #include <drm/ttm/ttm_bo_driver.h>
 #include <drm/ttm/ttm_module.h>
-#include <linux/dma_remapping.h>
+#include <linux/intel-iommu.h>
 
 #define VMWGFX_DRIVER_DESC "Linux drm driver for VMware graphics devices"
 #define VMWGFX_CHIP_SVGAII 0