Merge tag 'iommu-updates-v5.11' of git://git.kernel.org/pub/scm/linux…

…/kernel/git/arm64/linux

Pull IOMMU updates from Will Deacon:
 "There's a good mixture of improvements to the core code and driver
  changes across the board.

  One thing worth pointing out is that this includes a quirk to work
  around behaviour in the i915 driver (see 65f746e ("iommu: Add
  quirk for Intel graphic devices in map_sg")), which otherwise
  interacts badly with the conversion of the intel IOMMU driver over to
  the DMA-IOMMU APU but has being fixed properly in the DRM tree.

  We'll revert the quirk later this cycle once we've confirmed that
  things don't fall apart without it.

  Summary:

   - IOVA allocation optimisations and removal of unused code

   - Introduction of DOMAIN_ATTR_IO_PGTABLE_CFG for parameterising the
     page-table of an IOMMU domain

   - Support for changing the default domain type in sysfs

   - Optimisation to the way in which identity-mapped regions are
     created

   - Driver updates:
       * Arm SMMU updates, including continued work on Shared Virtual
         Memory
       * Tegra SMMU updates, including support for PCI devices
       * Intel VT-D updates, including conversion to the IOMMU-DMA API

   - Cleanup, kerneldoc and minor refactoring"

* tag 'iommu-updates-v5.11' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux: (50 commits)
  iommu/amd: Add sanity check for interrupt remapping table length macros
  dma-iommu: remove __iommu_dma_mmap
  iommu/io-pgtable: Remove tlb_flush_leaf
  iommu: Stop exporting free_iova_mem()
  iommu: Stop exporting alloc_iova_mem()
  iommu: Delete split_and_remove_iova()
  iommu/io-pgtable-arm: Remove unused 'level' parameter from iopte_type() macro
  iommu: Defer the early return in arm_(v7s/lpae)_map
  iommu: Improve the performance for direct_mapping
  iommu: avoid taking iova_rbtree_lock twice
  iommu/vt-d: Avoid GFP_ATOMIC where it is not needed
  iommu/vt-d: Remove set but not used variable
  iommu: return error code when it can't get group
  iommu: Fix htmldocs warnings in sysfs-kernel-iommu_groups
  iommu: arm-smmu-impl: Add a space before open parenthesis
  iommu: arm-smmu-impl: Use table to list QCOM implementations
  iommu/arm-smmu: Move non-strict mode to use io_pgtable_domain_attr
  iommu/arm-smmu: Add support for pagetable config domain attribute
  iommu: Document usage of "/sys/kernel/iommu_groups/<grp_id>/type" file
  iommu: Take lock before reading iommu group default domain type
  ...

Documentation/ABI/testing/sysfs-kernel-iommu_groups

@@ -33,3 +33,33 @@ Description:    In case an RMRR is used only by graphics or USB devices
 		it is now exposed as "direct-relaxable" instead of "direct".
 		In device assignment use case, for instance, those RMRR
 		are considered to be relaxable and safe.
+
+What:		/sys/kernel/iommu_groups/<grp_id>/type
+Date:		November 2020
+KernelVersion:	v5.11
+Contact:	Sai Praneeth Prakhya <sai.praneeth.prakhya@intel.com>
+Description:	/sys/kernel/iommu_groups/<grp_id>/type shows the type of default
+		domain in use by iommu for this group. See include/linux/iommu.h
+		for possible read values. A privileged user could request kernel to
+		change the group type by writing to this file. Valid write values:
+
+		========  ======================================================
+		DMA       All the DMA transactions from the device in this group
+		          are translated by the iommu.
+		identity  All the DMA transactions from the device in this group
+		          are not translated by the iommu.
+		auto      Change to the type the device was booted with.
+		========  ======================================================
+
+		The default domain type of a group may be modified only when
+
+		- The group has only one device.
+		- The device in the group is not bound to any device driver.
+		  So, the users must unbind the appropriate driver before
+		  changing the default domain type.
+
+		Unbinding a device driver will take away the driver's control
+		over the device and if done on devices that host root file
+		system could lead to catastrophic effects (the users might
+		need to reboot the machine to get it to normal state). So, it's
+		expected that the users understand what they're doing.

Documentation/admin-guide/kernel-parameters.txt

@@ -1883,11 +1883,6 @@
 			Note that using this option lowers the security
 			provided by tboot because it makes the system
 			vulnerable to DMA attacks.
-		nobounce [Default off]
-			Disable bounce buffer for untrusted devices such as
-			the Thunderbolt devices. This will treat the untrusted
-			devices as the trusted ones, hence might expose security
-			risks of DMA attacks.
 
 	intel_idle.max_cstate=	[KNL,HW,ACPI,X86]
 			0	disables intel_idle and fall back on acpi_idle.

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

@@ -28,8 +28,6 @@ properties:
           - enum:
               - qcom,msm8996-smmu-v2
               - qcom,msm8998-smmu-v2
-              - qcom,sc7180-smmu-v2
-              - qcom,sdm845-smmu-v2
           - const: qcom,smmu-v2
 
       - description: Qcom SoCs implementing "arm,mmu-500"
@@ -40,6 +38,13 @@ properties:
               - qcom,sm8150-smmu-500
               - qcom,sm8250-smmu-500
           - const: arm,mmu-500
+      - description: Qcom Adreno GPUs implementing "arm,smmu-v2"
+        items:
+          - enum:
+              - qcom,sc7180-smmu-v2
+              - qcom,sdm845-smmu-v2
+          - const: qcom,adreno-smmu
+          - const: qcom,smmu-v2
       - description: Marvell SoCs implementing "arm,mmu-500"
         items:
           - const: marvell,ap806-smmu-500

drivers/gpu/drm/msm/msm_iommu.c

@@ -139,7 +139,6 @@ static void msm_iommu_tlb_add_page(struct iommu_iotlb_gather *gather,
 static const struct iommu_flush_ops null_tlb_ops = {
 	.tlb_flush_all = msm_iommu_tlb_flush_all,
 	.tlb_flush_walk = msm_iommu_tlb_flush_walk,
-	.tlb_flush_leaf = msm_iommu_tlb_flush_walk,
 	.tlb_add_page = msm_iommu_tlb_add_page,
 };
 

drivers/gpu/drm/panfrost/panfrost_mmu.c

@@ -347,16 +347,9 @@ static void mmu_tlb_flush_walk(unsigned long iova, size_t size, size_t granule,
 	mmu_tlb_sync_context(cookie);
 }
 
-static void mmu_tlb_flush_leaf(unsigned long iova, size_t size, size_t granule,
-			       void *cookie)
-{
-	mmu_tlb_sync_context(cookie);
-}
-
 static const struct iommu_flush_ops mmu_tlb_ops = {
 	.tlb_flush_all	= mmu_tlb_inv_context_s1,
 	.tlb_flush_walk = mmu_tlb_flush_walk,
-	.tlb_flush_leaf = mmu_tlb_flush_leaf,
 };
 
 int panfrost_mmu_pgtable_alloc(struct panfrost_file_priv *priv)

drivers/iommu/Kconfig

@@ -103,6 +103,11 @@ config IOMMU_DMA
 	select IRQ_MSI_IOMMU
 	select NEED_SG_DMA_LENGTH
 
+# Shared Virtual Addressing library
+config IOMMU_SVA_LIB
+	bool
+	select IOASID
+
 config FSL_PAMU
 	bool "Freescale IOMMU support"
 	depends on PCI
@@ -311,6 +316,8 @@ config ARM_SMMU_V3
 config ARM_SMMU_V3_SVA
 	bool "Shared Virtual Addressing support for the ARM SMMUv3"
 	depends on ARM_SMMU_V3
+	select IOMMU_SVA_LIB
+	select MMU_NOTIFIER
 	help
 	  Support for sharing process address spaces with devices using the
 	  SMMUv3.

drivers/iommu/Makefile

@@ -27,3 +27,4 @@ obj-$(CONFIG_FSL_PAMU) += fsl_pamu.o fsl_pamu_domain.o
 obj-$(CONFIG_S390_IOMMU) += s390-iommu.o
 obj-$(CONFIG_HYPERV_IOMMU) += hyperv-iommu.o
 obj-$(CONFIG_VIRTIO_IOMMU) += virtio-iommu.o
+obj-$(CONFIG_IOMMU_SVA_LIB) += iommu-sva-lib.o

drivers/iommu/amd/amd_iommu_types.h

@@ -255,11 +255,19 @@
 /* Bit value definition for dte irq remapping fields*/
 #define DTE_IRQ_PHYS_ADDR_MASK	(((1ULL << 45)-1) << 6)
 #define DTE_IRQ_REMAP_INTCTL_MASK	(0x3ULL << 60)
-#define DTE_IRQ_TABLE_LEN_MASK	(0xfULL << 1)
 #define DTE_IRQ_REMAP_INTCTL    (2ULL << 60)
-#define DTE_IRQ_TABLE_LEN       (9ULL << 1)
 #define DTE_IRQ_REMAP_ENABLE    1ULL
 
+/*
+ * AMD IOMMU hardware only support 512 IRTEs despite
+ * the architectural limitation of 2048 entries.
+ */
+#define DTE_INTTAB_ALIGNMENT    128
+#define DTE_INTTABLEN_VALUE     9ULL
+#define DTE_INTTABLEN           (DTE_INTTABLEN_VALUE << 1)
+#define DTE_INTTABLEN_MASK      (0xfULL << 1)
+#define MAX_IRQS_PER_TABLE      (1 << DTE_INTTABLEN_VALUE)
+
 #define PAGE_MODE_NONE    0x00
 #define PAGE_MODE_1_LEVEL 0x01
 #define PAGE_MODE_2_LEVEL 0x02
@@ -409,13 +417,6 @@ extern bool amd_iommu_np_cache;
 /* Only true if all IOMMUs support device IOTLBs */
 extern bool amd_iommu_iotlb_sup;
 
-/*
- * AMD IOMMU hardware only support 512 IRTEs despite
- * the architectural limitation of 2048 entries.
- */
-#define MAX_IRQS_PER_TABLE	512
-#define IRQ_TABLE_ALIGNMENT	128
-
 struct irq_remap_table {
 	raw_spinlock_t lock;
 	unsigned min_index;

drivers/iommu/amd/init.c

@@ -989,10 +989,10 @@ static bool copy_device_table(void)
 
 		irq_v = old_devtb[devid].data[2] & DTE_IRQ_REMAP_ENABLE;
 		int_ctl = old_devtb[devid].data[2] & DTE_IRQ_REMAP_INTCTL_MASK;
-		int_tab_len = old_devtb[devid].data[2] & DTE_IRQ_TABLE_LEN_MASK;
+		int_tab_len = old_devtb[devid].data[2] & DTE_INTTABLEN_MASK;
 		if (irq_v && (int_ctl || int_tab_len)) {
 			if ((int_ctl != DTE_IRQ_REMAP_INTCTL) ||
-			    (int_tab_len != DTE_IRQ_TABLE_LEN)) {
+			    (int_tab_len != DTE_INTTABLEN)) {
 				pr_err("Wrong old irq remapping flag: %#x\n", devid);
 				return false;
 			}
@@ -2757,7 +2757,7 @@ static int __init early_amd_iommu_init(void)
 			remap_cache_sz = MAX_IRQS_PER_TABLE * (sizeof(u64) * 2);
 		amd_iommu_irq_cache = kmem_cache_create("irq_remap_cache",
 							remap_cache_sz,
-							IRQ_TABLE_ALIGNMENT,
+							DTE_INTTAB_ALIGNMENT,
 							0, NULL);
 		if (!amd_iommu_irq_cache)
 			goto out;

drivers/iommu/amd/iommu.c

@@ -3190,7 +3190,7 @@ static void set_dte_irq_entry(u16 devid, struct irq_remap_table *table)
 	dte	&= ~DTE_IRQ_PHYS_ADDR_MASK;
 	dte	|= iommu_virt_to_phys(table->table);
 	dte	|= DTE_IRQ_REMAP_INTCTL;
-	dte	|= DTE_IRQ_TABLE_LEN;
+	dte	|= DTE_INTTABLEN;
 	dte	|= DTE_IRQ_REMAP_ENABLE;
 
 	amd_iommu_dev_table[devid].data[2] = dte;