Merge tag 'iommu-fixes-v5.2-rc4' of git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu

Pull iommu fixes from Joerg Roedel:

 - three fixes for Intel VT-d to fix a potential dead-lock, a formatting
   fix and a bit setting fix

 - one fix for the ARM-SMMU to make it work on some platforms with
   sub-optimal SMMU emulation

* tag 'iommu-fixes-v5.2-rc4' of git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu:
  iommu/arm-smmu: Avoid constant zero in TLBI writes
  iommu/vt-d: Set the right field for Page Walk Snoop
  iommu/vt-d: Fix lock inversion between iommu->lock and device_domain_lock
  iommu: Add missing new line for dma type

drivers/iommu/arm-smmu.c

@@ -47,6 +47,15 @@
 
 #include "arm-smmu-regs.h"
 
+/*
+ * Apparently, some Qualcomm arm64 platforms which appear to expose their SMMU
+ * global register space are still, in fact, using a hypervisor to mediate it
+ * by trapping and emulating register accesses. Sadly, some deployed versions
+ * of said trapping code have bugs wherein they go horribly wrong for stores
+ * using r31 (i.e. XZR/WZR) as the source register.
+ */
+#define QCOM_DUMMY_VAL -1
+
 #define ARM_MMU500_ACTLR_CPRE		(1 << 1)
 
 #define ARM_MMU500_ACR_CACHE_LOCK	(1 << 26)
@@ -411,7 +420,7 @@ static void __arm_smmu_tlb_sync(struct arm_smmu_device *smmu,
 {
 	unsigned int spin_cnt, delay;
 
-	writel_relaxed(0, sync);
+	writel_relaxed(QCOM_DUMMY_VAL, sync);
 	for (delay = 1; delay < TLB_LOOP_TIMEOUT; delay *= 2) {
 		for (spin_cnt = TLB_SPIN_COUNT; spin_cnt > 0; spin_cnt--) {
 			if (!(readl_relaxed(status) & sTLBGSTATUS_GSACTIVE))
@@ -1751,8 +1760,8 @@ static void arm_smmu_device_reset(struct arm_smmu_device *smmu)
 	}
 
 	/* Invalidate the TLB, just in case */
-	writel_relaxed(0, gr0_base + ARM_SMMU_GR0_TLBIALLH);
+	writel_relaxed(QCOM_DUMMY_VAL, gr0_base + ARM_SMMU_GR0_TLBIALLH);
-	writel_relaxed(0, gr0_base + ARM_SMMU_GR0_TLBIALLNSNH);
+	writel_relaxed(QCOM_DUMMY_VAL, gr0_base + ARM_SMMU_GR0_TLBIALLNSNH);
 
 	reg = readl_relaxed(ARM_SMMU_GR0_NS(smmu) + ARM_SMMU_GR0_sCR0);
 

drivers/iommu/intel-iommu.c

@@ -2504,6 +2504,7 @@ static struct dmar_domain *dmar_insert_one_dev_info(struct intel_iommu *iommu,
 		}
 	}
 
+	spin_lock(&iommu->lock);
 	spin_lock_irqsave(&device_domain_lock, flags);
 	if (dev)
 		found = find_domain(dev);
@@ -2519,17 +2520,16 @@ static struct dmar_domain *dmar_insert_one_dev_info(struct intel_iommu *iommu,
 
 	if (found) {
 		spin_unlock_irqrestore(&device_domain_lock, flags);
+		spin_unlock(&iommu->lock);
 		free_devinfo_mem(info);
 		/* Caller must free the original domain */
 		return found;
 	}
 
-	spin_lock(&iommu->lock);
 	ret = domain_attach_iommu(domain, iommu);
-	spin_unlock(&iommu->lock);
-
 	if (ret) {
 		spin_unlock_irqrestore(&device_domain_lock, flags);
+		spin_unlock(&iommu->lock);
 		free_devinfo_mem(info);
 		return NULL;
 	}
@@ -2539,6 +2539,7 @@ static struct dmar_domain *dmar_insert_one_dev_info(struct intel_iommu *iommu,
 	if (dev)
 		dev->archdata.iommu = info;
 	spin_unlock_irqrestore(&device_domain_lock, flags);
+	spin_unlock(&iommu->lock);
 
 	/* PASID table is mandatory for a PCI device in scalable mode. */
 	if (dev && dev_is_pci(dev) && sm_supported(iommu)) {

drivers/iommu/intel-pasid.c

@@ -389,7 +389,7 @@ static inline void pasid_set_present(struct pasid_entry *pe)
  */
 static inline void pasid_set_page_snoop(struct pasid_entry *pe, bool value)
 {
-	pasid_set_bits(&pe->val[1], 1 << 23, value);
+	pasid_set_bits(&pe->val[1], 1 << 23, value << 23);
 }
 
 /*

drivers/iommu/iommu.c

@@ -329,7 +329,7 @@ static ssize_t iommu_group_show_type(struct iommu_group *group,
 			type = "unmanaged\n";
 			break;
 		case IOMMU_DOMAIN_DMA:
-			type = "DMA";
+			type = "DMA\n";
 			break;
 		}
 	}