Merge tag 'iommu-fixes-v6.0-rc4' of git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu

Pull iommu fixes from Joerg Roedel:

 - Intel VT-d fixes from Lu Baolu:
     - Boot kdump kernels with VT-d scalable mode on
     - Calculate the right page table levels
     - Fix two recursive locking issues
     - Fix a lockdep splat issue

 - AMD IOMMU fixes:
     - Fix for completion-wait command to use full 64 bits of data
     - Fix PASID related issue where GPU sound devices failed to
       initialize

 - Fix for Virtio-IOMMU to report correct caching behavior, needed for
   use with VFIO

* tag 'iommu-fixes-v6.0-rc4' of git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu:
  iommu: Fix false ownership failure on AMD systems with PASID activated
  iommu/vt-d: Fix possible recursive locking in intel_iommu_init()
  iommu/virtio: Fix interaction with VFIO
  iommu/vt-d: Fix lockdep splat due to klist iteration in atomic context
  iommu/vt-d: Fix recursive lock issue in iommu_flush_dev_iotlb()
  iommu/vt-d: Correctly calculate sagaw value of IOMMU
  iommu/vt-d: Fix kdump kernels boot failure with scalable mode
  iommu/amd: use full 64-bit value in build_completion_wait()

drivers/iommu/amd/iommu.c

@@ -939,7 +939,8 @@ static void build_completion_wait(struct iommu_cmd *cmd,
 	memset(cmd, 0, sizeof(*cmd));
 	cmd->data[0] = lower_32_bits(paddr) | CMD_COMPL_WAIT_STORE_MASK;
 	cmd->data[1] = upper_32_bits(paddr);
-	cmd->data[2] = data;
+	cmd->data[2] = lower_32_bits(data);
+	cmd->data[3] = upper_32_bits(data);
 	CMD_SET_TYPE(cmd, CMD_COMPL_WAIT);
 }
 

drivers/iommu/amd/iommu_v2.c

@@ -777,6 +777,8 @@ int amd_iommu_init_device(struct pci_dev *pdev, int pasids)
 	if (dev_state->domain == NULL)
 		goto out_free_states;
 
+	/* See iommu_is_default_domain() */
+	dev_state->domain->type = IOMMU_DOMAIN_IDENTITY;
 	amd_iommu_domain_direct_map(dev_state->domain);
 
 	ret = amd_iommu_domain_enable_v2(dev_state->domain, pasids);

drivers/iommu/intel/dmar.c

@@ -2349,6 +2349,13 @@ static int dmar_device_hotplug(acpi_handle handle, bool insert)
 	if (!dmar_in_use())
 		return 0;
 
+	/*
+	 * It's unlikely that any I/O board is hot added before the IOMMU
+	 * subsystem is initialized.
+	 */
+	if (IS_ENABLED(CONFIG_INTEL_IOMMU) && !intel_iommu_enabled)
+		return -EOPNOTSUPP;
+
 	if (dmar_detect_dsm(handle, DMAR_DSM_FUNC_DRHD)) {
 		tmp = handle;
 	} else {

drivers/iommu/intel/iommu.h

@@ -197,7 +197,6 @@
 #define ecap_dis(e)		(((e) >> 27) & 0x1)
 #define ecap_nest(e)		(((e) >> 26) & 0x1)
 #define ecap_mts(e)		(((e) >> 25) & 0x1)
-#define ecap_ecs(e)		(((e) >> 24) & 0x1)
 #define ecap_iotlb_offset(e) 	((((e) >> 8) & 0x3ff) * 16)
 #define ecap_max_iotlb_offset(e) (ecap_iotlb_offset(e) + 16)
 #define ecap_coherent(e)	((e) & 0x1)
@@ -265,7 +264,6 @@
 #define DMA_GSTS_CFIS (((u32)1) << 23)
 
 /* DMA_RTADDR_REG */
-#define DMA_RTADDR_RTT (((u64)1) << 11)
 #define DMA_RTADDR_SMT (((u64)1) << 10)
 
 /* CCMD_REG */
@@ -579,6 +577,7 @@ struct intel_iommu {
 
 #ifdef CONFIG_INTEL_IOMMU
 	unsigned long 	*domain_ids; /* bitmap of domains */
+	unsigned long	*copied_tables; /* bitmap of copied tables */
 	spinlock_t	lock; /* protect context, domain ids */
 	struct root_entry *root_entry; /* virtual address */
 
@@ -701,6 +700,11 @@ static inline int nr_pte_to_next_page(struct dma_pte *pte)
 		(struct dma_pte *)ALIGN((unsigned long)pte, VTD_PAGE_SIZE) - pte;
 }
 
+static inline bool context_present(struct context_entry *context)
+{
+	return (context->lo & 1);
+}
+
 extern struct dmar_drhd_unit * dmar_find_matched_drhd_unit(struct pci_dev *dev);
 
 extern int dmar_enable_qi(struct intel_iommu *iommu);
@@ -784,7 +788,6 @@ static inline void intel_iommu_debugfs_init(void) {}
 #endif /* CONFIG_INTEL_IOMMU_DEBUGFS */
 
 extern const struct attribute_group *intel_iommu_groups[];
-bool context_present(struct context_entry *context);
 struct context_entry *iommu_context_addr(struct intel_iommu *iommu, u8 bus,
 					 u8 devfn, int alloc);
 

drivers/iommu/iommu.c

@@ -3076,6 +3076,24 @@ static ssize_t iommu_group_store_type(struct iommu_group *group,
 	return ret;
 }
 
+static bool iommu_is_default_domain(struct iommu_group *group)
+{
+	if (group->domain == group->default_domain)
+		return true;
+
+	/*
+	 * If the default domain was set to identity and it is still an identity
+	 * domain then we consider this a pass. This happens because of
+	 * amd_iommu_init_device() replacing the default idenytity domain with an
+	 * identity domain that has a different configuration for AMDGPU.
+	 */
+	if (group->default_domain &&
+	    group->default_domain->type == IOMMU_DOMAIN_IDENTITY &&
+	    group->domain && group->domain->type == IOMMU_DOMAIN_IDENTITY)
+		return true;
+	return false;
+}
+
 /**
  * iommu_device_use_default_domain() - Device driver wants to handle device
  *                                     DMA through the kernel DMA API.
@@ -3094,8 +3112,7 @@ int iommu_device_use_default_domain(struct device *dev)
 
 	mutex_lock(&group->mutex);
 	if (group->owner_cnt) {
-		if (group->domain != group->default_domain ||
-		    group->owner) {
+		if (group->owner || !iommu_is_default_domain(group)) {
 			ret = -EBUSY;
 			goto unlock_out;
 		}

drivers/iommu/virtio-iommu.c

@@ -1006,7 +1006,18 @@ static int viommu_of_xlate(struct device *dev, struct of_phandle_args *args)
 	return iommu_fwspec_add_ids(dev, args->args, 1);
 }
 
+static bool viommu_capable(enum iommu_cap cap)
+{
+	switch (cap) {
+	case IOMMU_CAP_CACHE_COHERENCY:
+		return true;
+	default:
+		return false;
+	}
+}
+
 static struct iommu_ops viommu_ops = {
+	.capable		= viommu_capable,
 	.domain_alloc		= viommu_domain_alloc,
 	.probe_device		= viommu_probe_device,
 	.probe_finalize		= viommu_probe_finalize,

include/linux/dmar.h

@@ -65,6 +65,7 @@ struct dmar_pci_notify_info {
 
 extern struct rw_semaphore dmar_global_lock;
 extern struct list_head dmar_drhd_units;
+extern int intel_iommu_enabled;
 
 #define for_each_drhd_unit(drhd)					\
 	list_for_each_entry_rcu(drhd, &dmar_drhd_units, list,		\
@@ -88,7 +89,8 @@ extern struct list_head dmar_drhd_units;
 static inline bool dmar_rcu_check(void)
 {
 	return rwsem_is_locked(&dmar_global_lock) ||
-	       system_state == SYSTEM_BOOTING;
+	       system_state == SYSTEM_BOOTING ||
+	       (IS_ENABLED(CONFIG_INTEL_IOMMU) && !intel_iommu_enabled);
 }
 
 #define	dmar_rcu_dereference(p)	rcu_dereference_check((p), dmar_rcu_check())