Update Linux to v5.4.148

Sourced from [1]

[1] https://cdn.kernel.org/pub/linux/kernel/v5.x/linux-5.4.148.tar.gz

Change-Id: Ib3d26c5ba9b022e2e03533005c4fed4d7c30b61b
Signed-off-by: Olivier Deprez <olivier.deprez@arm.com>
diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c
index dd55507..c392930 100644
--- a/drivers/iommu/amd_iommu.c
+++ b/drivers/iommu/amd_iommu.c
@@ -226,71 +226,58 @@
 	return NULL;
 }
 
-static int __last_alias(struct pci_dev *pdev, u16 alias, void *data)
+static int clone_alias(struct pci_dev *pdev, u16 alias, void *data)
 {
-	*(u16 *)data = alias;
+	u16 devid = pci_dev_id(pdev);
+
+	if (devid == alias)
+		return 0;
+
+	amd_iommu_rlookup_table[alias] =
+		amd_iommu_rlookup_table[devid];
+	memcpy(amd_iommu_dev_table[alias].data,
+	       amd_iommu_dev_table[devid].data,
+	       sizeof(amd_iommu_dev_table[alias].data));
+
 	return 0;
 }
 
-static u16 get_alias(struct device *dev)
+static void clone_aliases(struct pci_dev *pdev)
+{
+	if (!pdev)
+		return;
+
+	/*
+	 * The IVRS alias stored in the alias table may not be
+	 * part of the PCI DMA aliases if it's bus differs
+	 * from the original device.
+	 */
+	clone_alias(pdev, amd_iommu_alias_table[pci_dev_id(pdev)], NULL);
+
+	pci_for_each_dma_alias(pdev, clone_alias, NULL);
+}
+
+static struct pci_dev *setup_aliases(struct device *dev)
 {
 	struct pci_dev *pdev = to_pci_dev(dev);
-	u16 devid, ivrs_alias, pci_alias;
+	u16 ivrs_alias;
 
-	/* The callers make sure that get_device_id() does not fail here */
-	devid = get_device_id(dev);
-
-	/* For ACPI HID devices, we simply return the devid as such */
+	/* For ACPI HID devices, there are no aliases */
 	if (!dev_is_pci(dev))
-		return devid;
-
-	ivrs_alias = amd_iommu_alias_table[devid];
-
-	pci_for_each_dma_alias(pdev, __last_alias, &pci_alias);
-
-	if (ivrs_alias == pci_alias)
-		return ivrs_alias;
+		return NULL;
 
 	/*
-	 * DMA alias showdown
-	 *
-	 * The IVRS is fairly reliable in telling us about aliases, but it
-	 * can't know about every screwy device.  If we don't have an IVRS
-	 * reported alias, use the PCI reported alias.  In that case we may
-	 * still need to initialize the rlookup and dev_table entries if the
-	 * alias is to a non-existent device.
+	 * Add the IVRS alias to the pci aliases if it is on the same
+	 * bus. The IVRS table may know about a quirk that we don't.
 	 */
-	if (ivrs_alias == devid) {
-		if (!amd_iommu_rlookup_table[pci_alias]) {
-			amd_iommu_rlookup_table[pci_alias] =
-				amd_iommu_rlookup_table[devid];
-			memcpy(amd_iommu_dev_table[pci_alias].data,
-			       amd_iommu_dev_table[devid].data,
-			       sizeof(amd_iommu_dev_table[pci_alias].data));
-		}
+	ivrs_alias = amd_iommu_alias_table[pci_dev_id(pdev)];
+	if (ivrs_alias != pci_dev_id(pdev) &&
+	    PCI_BUS_NUM(ivrs_alias) == pdev->bus->number)
+		pci_add_dma_alias(pdev, ivrs_alias & 0xff, 1);
 
-		return pci_alias;
-	}
+	clone_aliases(pdev);
 
-	pci_info(pdev, "Using IVRS reported alias %02x:%02x.%d "
-		"for device [%04x:%04x], kernel reported alias "
-		"%02x:%02x.%d\n", PCI_BUS_NUM(ivrs_alias), PCI_SLOT(ivrs_alias),
-		PCI_FUNC(ivrs_alias), pdev->vendor, pdev->device,
-		PCI_BUS_NUM(pci_alias), PCI_SLOT(pci_alias),
-		PCI_FUNC(pci_alias));
-
-	/*
-	 * If we don't have a PCI DMA alias and the IVRS alias is on the same
-	 * bus, then the IVRS table may know about a quirk that we don't.
-	 */
-	if (pci_alias == devid &&
-	    PCI_BUS_NUM(ivrs_alias) == pdev->bus->number) {
-		pci_add_dma_alias(pdev, ivrs_alias & 0xff);
-		pci_info(pdev, "Added PCI DMA alias %02x.%d\n",
-			PCI_SLOT(ivrs_alias), PCI_FUNC(ivrs_alias));
-	}
-
-	return ivrs_alias;
+	return pdev;
 }
 
 static struct iommu_dev_data *find_dev_data(u16 devid)
@@ -428,7 +415,7 @@
 	if (!dev_data)
 		return -ENOMEM;
 
-	dev_data->alias = get_alias(dev);
+	dev_data->pdev = setup_aliases(dev);
 
 	/*
 	 * By default we use passthrough mode for IOMMUv2 capable device.
@@ -453,20 +440,16 @@
 
 static void iommu_ignore_device(struct device *dev)
 {
-	u16 alias;
 	int devid;
 
 	devid = get_device_id(dev);
 	if (devid < 0)
 		return;
 
-	alias = get_alias(dev);
-
-	memset(&amd_iommu_dev_table[devid], 0, sizeof(struct dev_table_entry));
-	memset(&amd_iommu_dev_table[alias], 0, sizeof(struct dev_table_entry));
-
 	amd_iommu_rlookup_table[devid] = NULL;
-	amd_iommu_rlookup_table[alias] = NULL;
+	memset(&amd_iommu_dev_table[devid], 0, sizeof(struct dev_table_entry));
+
+	setup_aliases(dev);
 }
 
 static void iommu_uninit_device(struct device *dev)
@@ -1236,6 +1219,13 @@
 	return iommu_queue_command(iommu, &cmd);
 }
 
+static int device_flush_dte_alias(struct pci_dev *pdev, u16 alias, void *data)
+{
+	struct amd_iommu *iommu = data;
+
+	return iommu_flush_dte(iommu, alias);
+}
+
 /*
  * Command send function for invalidating a device table entry
  */
@@ -1246,14 +1236,22 @@
 	int ret;
 
 	iommu = amd_iommu_rlookup_table[dev_data->devid];
-	alias = dev_data->alias;
 
-	ret = iommu_flush_dte(iommu, dev_data->devid);
-	if (!ret && alias != dev_data->devid)
-		ret = iommu_flush_dte(iommu, alias);
+	if (dev_data->pdev)
+		ret = pci_for_each_dma_alias(dev_data->pdev,
+					     device_flush_dte_alias, iommu);
+	else
+		ret = iommu_flush_dte(iommu, dev_data->devid);
 	if (ret)
 		return ret;
 
+	alias = amd_iommu_alias_table[dev_data->devid];
+	if (alias != dev_data->devid) {
+		ret = iommu_flush_dte(iommu, alias);
+		if (ret)
+			return ret;
+	}
+
 	if (dev_data->ats.enabled)
 		ret = device_flush_iotlb(dev_data, 0, ~0UL);
 
@@ -1471,25 +1469,27 @@
 	bool ret = false;
 	u64 *pte;
 
+	pte = (void *)get_zeroed_page(gfp);
+	if (!pte)
+		return false;
+
 	spin_lock_irqsave(&domain->lock, flags);
 
 	if (address <= PM_LEVEL_SIZE(domain->mode) ||
 	    WARN_ON_ONCE(domain->mode == PAGE_MODE_6_LEVEL))
 		goto out;
 
-	pte = (void *)get_zeroed_page(gfp);
-	if (!pte)
-		goto out;
-
 	*pte             = PM_LEVEL_PDE(domain->mode,
 					iommu_virt_to_phys(domain->pt_root));
 	domain->pt_root  = pte;
 	domain->mode    += 1;
 
+	pte = NULL;
 	ret = true;
 
 out:
 	spin_unlock_irqrestore(&domain->lock, flags);
+	free_page((unsigned long)pte);
 
 	return ret;
 }
@@ -2035,11 +2035,9 @@
 		      struct protection_domain *domain)
 {
 	struct amd_iommu *iommu;
-	u16 alias;
 	bool ats;
 
 	iommu = amd_iommu_rlookup_table[dev_data->devid];
-	alias = dev_data->alias;
 	ats   = dev_data->ats.enabled;
 
 	/* Update data structures */
@@ -2052,8 +2050,7 @@
 
 	/* Update device table */
 	set_dte_entry(dev_data->devid, domain, ats, dev_data->iommu_v2);
-	if (alias != dev_data->devid)
-		set_dte_entry(alias, domain, ats, dev_data->iommu_v2);
+	clone_aliases(dev_data->pdev);
 
 	device_flush_dte(dev_data);
 }
@@ -2062,17 +2059,14 @@
 {
 	struct protection_domain *domain = dev_data->domain;
 	struct amd_iommu *iommu;
-	u16 alias;
 
 	iommu = amd_iommu_rlookup_table[dev_data->devid];
-	alias = dev_data->alias;
 
 	/* Update data structures */
 	dev_data->domain = NULL;
 	list_del(&dev_data->list);
 	clear_dte_entry(dev_data->devid);
-	if (alias != dev_data->devid)
-		clear_dte_entry(alias);
+	clone_aliases(dev_data->pdev);
 
 	/* Flush the DTE entry */
 	device_flush_dte(dev_data);
@@ -2384,13 +2378,7 @@
 	list_for_each_entry(dev_data, &domain->dev_list, list) {
 		set_dte_entry(dev_data->devid, domain, dev_data->ats.enabled,
 			      dev_data->iommu_v2);
-
-		if (dev_data->devid == dev_data->alias)
-			continue;
-
-		/* There is an alias, update device table entry for it */
-		set_dte_entry(dev_data->alias, domain, dev_data->ats.enabled,
-			      dev_data->iommu_v2);
+		clone_aliases(dev_data->pdev);
 	}
 }
 
@@ -2400,6 +2388,7 @@
 
 	domain_flush_devices(domain);
 	domain_flush_tlb_pde(domain);
+	domain_flush_complete(domain);
 }
 
 static int dir2prot(enum dma_data_direction direction)
@@ -3752,7 +3741,20 @@
 	iommu_flush_dte(iommu, devid);
 }
 
-static struct irq_remap_table *alloc_irq_table(u16 devid)
+static int set_remap_table_entry_alias(struct pci_dev *pdev, u16 alias,
+				       void *data)
+{
+	struct irq_remap_table *table = data;
+
+	irq_lookup_table[alias] = table;
+	set_dte_irq_entry(alias, table);
+
+	iommu_flush_dte(amd_iommu_rlookup_table[alias], alias);
+
+	return 0;
+}
+
+static struct irq_remap_table *alloc_irq_table(u16 devid, struct pci_dev *pdev)
 {
 	struct irq_remap_table *table = NULL;
 	struct irq_remap_table *new_table = NULL;
@@ -3798,7 +3800,12 @@
 	table = new_table;
 	new_table = NULL;
 
-	set_remap_table_entry(iommu, devid, table);
+	if (pdev)
+		pci_for_each_dma_alias(pdev, set_remap_table_entry_alias,
+				       table);
+	else
+		set_remap_table_entry(iommu, devid, table);
+
 	if (devid != alias)
 		set_remap_table_entry(iommu, alias, table);
 
@@ -3815,7 +3822,8 @@
 	return table;
 }
 
-static int alloc_irq_index(u16 devid, int count, bool align)
+static int alloc_irq_index(u16 devid, int count, bool align,
+			   struct pci_dev *pdev)
 {
 	struct irq_remap_table *table;
 	int index, c, alignment = 1;
@@ -3825,7 +3833,7 @@
 	if (!iommu)
 		return -ENODEV;
 
-	table = alloc_irq_table(devid);
+	table = alloc_irq_table(devid, pdev);
 	if (!table)
 		return -ENODEV;
 
@@ -3867,6 +3875,7 @@
 static int modify_irte_ga(u16 devid, int index, struct irte_ga *irte,
 			  struct amd_ir_data *data)
 {
+	bool ret;
 	struct irq_remap_table *table;
 	struct amd_iommu *iommu;
 	unsigned long flags;
@@ -3884,10 +3893,18 @@
 
 	entry = (struct irte_ga *)table->table;
 	entry = &entry[index];
-	entry->lo.fields_remap.valid = 0;
-	entry->hi.val = irte->hi.val;
-	entry->lo.val = irte->lo.val;
-	entry->lo.fields_remap.valid = 1;
+
+	ret = cmpxchg_double(&entry->lo.val, &entry->hi.val,
+			     entry->lo.val, entry->hi.val,
+			     irte->lo.val, irte->hi.val);
+	/*
+	 * We use cmpxchg16 to atomically update the 128-bit IRTE,
+	 * and it cannot be updated by the hardware or other processors
+	 * behind us, so the return value of cmpxchg16 should be the
+	 * same as the old value.
+	 */
+	WARN_ON(!ret);
+
 	if (data)
 		data->ref = entry;
 
@@ -4258,7 +4275,7 @@
 		struct irq_remap_table *table;
 		struct amd_iommu *iommu;
 
-		table = alloc_irq_table(devid);
+		table = alloc_irq_table(devid, NULL);
 		if (table) {
 			if (!table->min_index) {
 				/*
@@ -4275,11 +4292,15 @@
 		} else {
 			index = -ENOMEM;
 		}
-	} else {
+	} else if (info->type == X86_IRQ_ALLOC_TYPE_MSI ||
+		   info->type == X86_IRQ_ALLOC_TYPE_MSIX) {
 		bool align = (info->type == X86_IRQ_ALLOC_TYPE_MSI);
 
-		index = alloc_irq_index(devid, nr_irqs, align);
+		index = alloc_irq_index(devid, nr_irqs, align, info->msi_dev);
+	} else {
+		index = alloc_irq_index(devid, nr_irqs, false, NULL);
 	}
+
 	if (index < 0) {
 		pr_warn("Failed to allocate IRTE\n");
 		ret = index;
@@ -4412,7 +4433,7 @@
 	entry->lo.fields_vapic.ga_tag      = ir_data->ga_tag;
 
 	return modify_irte_ga(ir_data->irq_2_irte.devid,
-			      ir_data->irq_2_irte.index, entry, NULL);
+			      ir_data->irq_2_irte.index, entry, ir_data);
 }
 EXPORT_SYMBOL(amd_iommu_activate_guest_mode);
 
@@ -4421,14 +4442,18 @@
 	struct amd_ir_data *ir_data = (struct amd_ir_data *)data;
 	struct irte_ga *entry = (struct irte_ga *) ir_data->entry;
 	struct irq_cfg *cfg = ir_data->cfg;
+	u64 valid;
 
 	if (!AMD_IOMMU_GUEST_IR_VAPIC(amd_iommu_guest_ir) ||
 	    !entry || !entry->lo.fields_vapic.guest_mode)
 		return 0;
 
+	valid = entry->lo.fields_remap.valid;
+
 	entry->lo.val = 0;
 	entry->hi.val = 0;
 
+	entry->lo.fields_remap.valid       = valid;
 	entry->lo.fields_remap.dm          = apic->irq_dest_mode;
 	entry->lo.fields_remap.int_type    = apic->irq_delivery_mode;
 	entry->hi.fields.vector            = cfg->vector;
@@ -4438,7 +4463,7 @@
 				APICID_TO_IRTE_DEST_HI(cfg->dest_apicid);
 
 	return modify_irte_ga(ir_data->irq_2_irte.devid,
-			      ir_data->irq_2_irte.index, entry, NULL);
+			      ir_data->irq_2_irte.index, entry, ir_data);
 }
 EXPORT_SYMBOL(amd_iommu_deactivate_guest_mode);
 
@@ -4565,9 +4590,10 @@
 	if (!fn)
 		return -ENOMEM;
 	iommu->ir_domain = irq_domain_create_tree(fn, &amd_ir_domain_ops, iommu);
-	irq_domain_free_fwnode(fn);
-	if (!iommu->ir_domain)
+	if (!iommu->ir_domain) {
+		irq_domain_free_fwnode(fn);
 		return -ENOMEM;
+	}
 
 	iommu->ir_domain->parent = arch_get_ir_parent_domain();
 	iommu->msi_domain = arch_create_remap_msi_irq_domain(iommu->ir_domain,