Merge tag 'iommu-fixes-v5.4-rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu

Pull iommu fixes from Joerg Roedel:

 - Fixes for page-table issues on Mali GPUs

 - Missing free in an error path for ARM-SMMU

 - PASID decoding in the AMD IOMMU Event log code

 - Another update for the locking fixes in the AMD IOMMU driver

 - Reduce the calls to platform_get_irq() in the IPMMU-VMSA and Rockchip
   IOMMUs to get rid of the warning message added to this function
   recently

* tag 'iommu-fixes-v5.4-rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu:
  iommu/amd: Check PM_LEVEL_SIZE() condition in locked section
  iommu/amd: Fix incorrect PASID decoding from event log
  iommu/ipmmu-vmsa: Only call platform_get_irq() when interrupt is mandatory
  iommu/rockchip: Don't use platform_get_irq to implicitly count irqs
  iommu/io-pgtable-arm: Support all Mali configurations
  iommu/io-pgtable-arm: Correct Mali attributes
  iommu/arm-smmu: Free context bitmap in the err path of arm_smmu_init_domain_context

drivers/iommu/amd_iommu.c

@@ -583,7 +583,8 @@ static void iommu_print_event(struct amd_iommu *iommu, void *__evt)
 retry:
 	type    = (event[1] >> EVENT_TYPE_SHIFT)  & EVENT_TYPE_MASK;
 	devid   = (event[0] >> EVENT_DEVID_SHIFT) & EVENT_DEVID_MASK;
-	pasid   = PPR_PASID(*(u64 *)&event[0]);
+	pasid   = (event[0] & EVENT_DOMID_MASK_HI) |
+		  (event[1] & EVENT_DOMID_MASK_LO);
 	flags   = (event[1] >> EVENT_FLAGS_SHIFT) & EVENT_FLAGS_MASK;
 	address = (u64)(((u64)event[3]) << 32) | event[2];
 
@@ -616,7 +617,7 @@ static void iommu_print_event(struct amd_iommu *iommu, void *__evt)
 			address, flags);
 		break;
 	case EVENT_TYPE_PAGE_TAB_ERR:
-		dev_err(dev, "Event logged [PAGE_TAB_HARDWARE_ERROR device=%02x:%02x.%x domain=0x%04x address=0x%llx flags=0x%04x]\n",
+		dev_err(dev, "Event logged [PAGE_TAB_HARDWARE_ERROR device=%02x:%02x.%x pasid=0x%04x address=0x%llx flags=0x%04x]\n",
 			PCI_BUS_NUM(devid), PCI_SLOT(devid), PCI_FUNC(devid),
 			pasid, address, flags);
 		break;
@@ -1463,6 +1464,7 @@ static void free_pagetable(struct protection_domain *domain)
  * to 64 bits.
  */
 static bool increase_address_space(struct protection_domain *domain,
+				   unsigned long address,
 				   gfp_t gfp)
 {
 	unsigned long flags;
@@ -1471,8 +1473,8 @@ static bool increase_address_space(struct protection_domain *domain,
 
 	spin_lock_irqsave(&domain->lock, flags);
 
-	if (WARN_ON_ONCE(domain->mode == PAGE_MODE_6_LEVEL))
-		/* address space already 64 bit large */
+	if (address <= PM_LEVEL_SIZE(domain->mode) ||
+	    WARN_ON_ONCE(domain->mode == PAGE_MODE_6_LEVEL))
 		goto out;
 
 	pte = (void *)get_zeroed_page(gfp);
@@ -1505,7 +1507,7 @@ static u64 *alloc_pte(struct protection_domain *domain,
 	BUG_ON(!is_power_of_2(page_size));
 
 	while (address > PM_LEVEL_SIZE(domain->mode))
-		*updated = increase_address_space(domain, gfp) || *updated;
+		*updated = increase_address_space(domain, address, gfp) || *updated;
 
 	level   = domain->mode - 1;
 	pte     = &domain->pt_root[PM_LEVEL_INDEX(level, address)];

drivers/iommu/amd_iommu_types.h

@@ -130,8 +130,8 @@
 #define EVENT_TYPE_INV_PPR_REQ	0x9
 #define EVENT_DEVID_MASK	0xffff
 #define EVENT_DEVID_SHIFT	0
-#define EVENT_DOMID_MASK	0xffff
-#define EVENT_DOMID_SHIFT	0
+#define EVENT_DOMID_MASK_LO	0xffff
+#define EVENT_DOMID_MASK_HI	0xf0000
 #define EVENT_FLAGS_MASK	0xfff
 #define EVENT_FLAGS_SHIFT	0x10
 

drivers/iommu/arm-smmu.c

@@ -812,6 +812,7 @@ static int arm_smmu_init_domain_context(struct iommu_domain *domain,
 	return 0;
 
 out_clear_smmu:
+	__arm_smmu_free_bitmap(smmu->context_map, cfg->cbndx);
 	smmu_domain->smmu = NULL;
 out_unlock:
 	mutex_unlock(&smmu_domain->init_mutex);

drivers/iommu/io-pgtable-arm.c

@@ -166,6 +166,9 @@
 #define ARM_MALI_LPAE_TTBR_READ_INNER	BIT(2)
 #define ARM_MALI_LPAE_TTBR_SHARE_OUTER	BIT(4)
 
+#define ARM_MALI_LPAE_MEMATTR_IMP_DEF	0x88ULL
+#define ARM_MALI_LPAE_MEMATTR_WRITE_ALLOC 0x8DULL
+
 /* IOPTE accessors */
 #define iopte_deref(pte,d) __va(iopte_to_paddr(pte, d))
 
@@ -1015,27 +1018,56 @@ arm_32_lpae_alloc_pgtable_s2(struct io_pgtable_cfg *cfg, void *cookie)
 static struct io_pgtable *
 arm_mali_lpae_alloc_pgtable(struct io_pgtable_cfg *cfg, void *cookie)
 {
-	struct io_pgtable *iop;
+	struct arm_lpae_io_pgtable *data;
 
-	if (cfg->ias != 48 || cfg->oas > 40)
+	/* No quirks for Mali (hopefully) */
+	if (cfg->quirks)
+		return NULL;
+
+	if (cfg->ias > 48 || cfg->oas > 40)
 		return NULL;
 
 	cfg->pgsize_bitmap &= (SZ_4K | SZ_2M | SZ_1G);
-	iop = arm_64_lpae_alloc_pgtable_s1(cfg, cookie);
-	if (iop) {
-		u64 mair, ttbr;
 
-		/* Copy values as union fields overlap */
-		mair = cfg->arm_lpae_s1_cfg.mair[0];
-		ttbr = cfg->arm_lpae_s1_cfg.ttbr[0];
+	data = arm_lpae_alloc_pgtable(cfg);
+	if (!data)
+		return NULL;
 
-		cfg->arm_mali_lpae_cfg.memattr = mair;
-		cfg->arm_mali_lpae_cfg.transtab = ttbr |
-			ARM_MALI_LPAE_TTBR_READ_INNER |
-			ARM_MALI_LPAE_TTBR_ADRMODE_TABLE;
+	/* Mali seems to need a full 4-level table regardless of IAS */
+	if (data->levels < ARM_LPAE_MAX_LEVELS) {
+		data->levels = ARM_LPAE_MAX_LEVELS;
+		data->pgd_size = sizeof(arm_lpae_iopte);
 	}
+	/*
+	 * MEMATTR: Mali has no actual notion of a non-cacheable type, so the
+	 * best we can do is mimic the out-of-tree driver and hope that the
+	 * "implementation-defined caching policy" is good enough. Similarly,
+	 * we'll use it for the sake of a valid attribute for our 'device'
+	 * index, although callers should never request that in practice.
+	 */
+	cfg->arm_mali_lpae_cfg.memattr =
+		(ARM_MALI_LPAE_MEMATTR_IMP_DEF
+		 << ARM_LPAE_MAIR_ATTR_SHIFT(ARM_LPAE_MAIR_ATTR_IDX_NC)) |
+		(ARM_MALI_LPAE_MEMATTR_WRITE_ALLOC
+		 << ARM_LPAE_MAIR_ATTR_SHIFT(ARM_LPAE_MAIR_ATTR_IDX_CACHE)) |
+		(ARM_MALI_LPAE_MEMATTR_IMP_DEF
+		 << ARM_LPAE_MAIR_ATTR_SHIFT(ARM_LPAE_MAIR_ATTR_IDX_DEV));
 
-	return iop;
+	data->pgd = __arm_lpae_alloc_pages(data->pgd_size, GFP_KERNEL, cfg);
+	if (!data->pgd)
+		goto out_free_data;
+
+	/* Ensure the empty pgd is visible before TRANSTAB can be written */
+	wmb();
+
+	cfg->arm_mali_lpae_cfg.transtab = virt_to_phys(data->pgd) |
+					  ARM_MALI_LPAE_TTBR_READ_INNER |
+					  ARM_MALI_LPAE_TTBR_ADRMODE_TABLE;
+	return &data->iop;
+
+out_free_data:
+	kfree(data);
+	return NULL;
 }
 
 struct io_pgtable_init_fns io_pgtable_arm_64_lpae_s1_init_fns = {

drivers/iommu/ipmmu-vmsa.c

@@ -1086,8 +1086,6 @@ static int ipmmu_probe(struct platform_device *pdev)
 
 	mmu->num_ctx = min(IPMMU_CTX_MAX, mmu->features->number_of_contexts);
 
-	irq = platform_get_irq(pdev, 0);
-
 	/*
 	 * Determine if this IPMMU instance is a root device by checking for
 	 * the lack of has_cache_leaf_nodes flag or renesas,ipmmu-main property.
@@ -1106,6 +1104,7 @@ static int ipmmu_probe(struct platform_device *pdev)
 
 	/* Root devices have mandatory IRQs */
 	if (ipmmu_is_root(mmu)) {
+		irq = platform_get_irq(pdev, 0);
 		if (irq < 0) {
 			dev_err(&pdev->dev, "no IRQ found\n");
 			return irq;

drivers/iommu/rockchip-iommu.c

@@ -100,6 +100,7 @@ struct rk_iommu {
 	struct device *dev;
 	void __iomem **bases;
 	int num_mmu;
+	int num_irq;
 	struct clk_bulk_data *clocks;
 	int num_clocks;
 	bool reset_disabled;
@@ -1136,7 +1137,7 @@ static int rk_iommu_probe(struct platform_device *pdev)
 	struct rk_iommu *iommu;
 	struct resource *res;
 	int num_res = pdev->num_resources;
-	int err, i, irq;
+	int err, i;
 
 	iommu = devm_kzalloc(dev, sizeof(*iommu), GFP_KERNEL);
 	if (!iommu)
@@ -1163,6 +1164,10 @@ static int rk_iommu_probe(struct platform_device *pdev)
 	if (iommu->num_mmu == 0)
 		return PTR_ERR(iommu->bases[0]);
 
+	iommu->num_irq = platform_irq_count(pdev);
+	if (iommu->num_irq < 0)
+		return iommu->num_irq;
+
 	iommu->reset_disabled = device_property_read_bool(dev,
 					"rockchip,disable-mmu-reset");
 
@@ -1219,8 +1224,9 @@ static int rk_iommu_probe(struct platform_device *pdev)
 
 	pm_runtime_enable(dev);
 
-	i = 0;
-	while ((irq = platform_get_irq(pdev, i++)) != -ENXIO) {
+	for (i = 0; i < iommu->num_irq; i++) {
+		int irq = platform_get_irq(pdev, i);
+
 		if (irq < 0)
 			return irq;
 
@@ -1245,10 +1251,13 @@ static int rk_iommu_probe(struct platform_device *pdev)
 static void rk_iommu_shutdown(struct platform_device *pdev)
 {
 	struct rk_iommu *iommu = platform_get_drvdata(pdev);
-	int i = 0, irq;
+	int i;
+
+	for (i = 0; i < iommu->num_irq; i++) {
+		int irq = platform_get_irq(pdev, i);
 
-	while ((irq = platform_get_irq(pdev, i++)) != -ENXIO)
 		devm_free_irq(iommu->dev, irq, iommu);
+	}
 
 	pm_runtime_force_suspend(&pdev->dev);
 }