1 files changed, 90 insertions, 59 deletions

diff --git a/drivers/iommu/amd/init.c b/drivers/iommu/amd/init.c
index 14aa0d77df26..7b5af6176de9 100644
--- a/drivers/iommu/amd/init.c
+++ b/drivers/iommu/amd/init.c
@@ -152,6 +152,8 @@ bool amd_iommu_dump;
 bool amd_iommu_irq_remap __read_mostly;
 
 enum protection_domain_mode amd_iommu_pgtable = PD_MODE_V1;
+/* Host page table level */
+u8 amd_iommu_hpt_level;
 /* Guest page table level */
 int amd_iommu_gpt_level = PAGE_MODE_4_LEVEL;
 
@@ -168,6 +170,9 @@ static int amd_iommu_target_ivhd_type;
 u64 amd_iommu_efr;
 u64 amd_iommu_efr2;
 
+/* Host (v1) page table is not supported*/
+bool amd_iommu_hatdis;
+
 /* SNP is enabled on the system? */
 bool amd_iommu_snp_en;
 EXPORT_SYMBOL(amd_iommu_snp_en);
@@ -243,17 +248,14 @@ static void init_translation_status(struct amd_iommu *iommu)
 		iommu->flags |= AMD_IOMMU_FLAG_TRANS_PRE_ENABLED;
 }
 
-static inline unsigned long tbl_size(int entry_size, int last_bdf)
+int amd_iommu_get_num_iommus(void)
 {
-	unsigned shift = PAGE_SHIFT +
-			 get_order((last_bdf + 1) * entry_size);
-
-	return 1UL << shift;
+	return amd_iommus_present;
 }
 
-int amd_iommu_get_num_iommus(void)
+bool amd_iommu_ht_range_ignore(void)
 {
-	return amd_iommus_present;
+	return check_feature2(FEATURE_HT_RANGE_IGNORE);
 }
 
 /*
@@ -634,8 +636,8 @@ static int __init find_last_devid_acpi(struct acpi_table_header *table, u16 pci_
 /* Allocate per PCI segment device table */
 static inline int __init alloc_dev_table(struct amd_iommu_pci_seg *pci_seg)
 {
-	pci_seg->dev_table = iommu_alloc_pages(GFP_KERNEL | GFP_DMA32,
-					       get_order(pci_seg->dev_table_size));
+	pci_seg->dev_table = iommu_alloc_pages_sz(GFP_KERNEL | GFP_DMA32,
+						  pci_seg->dev_table_size);
 	if (!pci_seg->dev_table)
 		return -ENOMEM;
 
@@ -644,16 +646,16 @@ static inline int __init alloc_dev_table(struct amd_iommu_pci_seg *pci_seg)
 
 static inline void free_dev_table(struct amd_iommu_pci_seg *pci_seg)
 {
-	iommu_free_pages(pci_seg->dev_table,
-			 get_order(pci_seg->dev_table_size));
+	iommu_free_pages(pci_seg->dev_table);
 	pci_seg->dev_table = NULL;
 }
 
 /* Allocate per PCI segment IOMMU rlookup table. */
 static inline int __init alloc_rlookup_table(struct amd_iommu_pci_seg *pci_seg)
 {
-	pci_seg->rlookup_table = iommu_alloc_pages(GFP_KERNEL,
-						   get_order(pci_seg->rlookup_table_size));
+	pci_seg->rlookup_table = kvcalloc(pci_seg->last_bdf + 1,
+					  sizeof(*pci_seg->rlookup_table),
+					  GFP_KERNEL);
 	if (pci_seg->rlookup_table == NULL)
 		return -ENOMEM;
 
@@ -662,17 +664,15 @@ static inline int __init alloc_rlookup_table(struct amd_iommu_pci_seg *pci_seg)
 
 static inline void free_rlookup_table(struct amd_iommu_pci_seg *pci_seg)
 {
-	iommu_free_pages(pci_seg->rlookup_table,
-			 get_order(pci_seg->rlookup_table_size));
+	kvfree(pci_seg->rlookup_table);
 	pci_seg->rlookup_table = NULL;
 }
 
 static inline int __init alloc_irq_lookup_table(struct amd_iommu_pci_seg *pci_seg)
 {
-	pci_seg->irq_lookup_table = iommu_alloc_pages(GFP_KERNEL,
-						      get_order(pci_seg->rlookup_table_size));
-	kmemleak_alloc(pci_seg->irq_lookup_table,
-		       pci_seg->rlookup_table_size, 1, GFP_KERNEL);
+	pci_seg->irq_lookup_table = kvcalloc(pci_seg->last_bdf + 1,
+					     sizeof(*pci_seg->irq_lookup_table),
+					     GFP_KERNEL);
 	if (pci_seg->irq_lookup_table == NULL)
 		return -ENOMEM;
 
@@ -681,9 +681,7 @@ static inline int __init alloc_irq_lookup_table(struct amd_iommu_pci_seg *pci_se
 
 static inline void free_irq_lookup_table(struct amd_iommu_pci_seg *pci_seg)
 {
-	kmemleak_free(pci_seg->irq_lookup_table);
-	iommu_free_pages(pci_seg->irq_lookup_table,
-			 get_order(pci_seg->rlookup_table_size));
+	kvfree(pci_seg->irq_lookup_table);
 	pci_seg->irq_lookup_table = NULL;
 }
 
@@ -691,8 +689,9 @@ static int __init alloc_alias_table(struct amd_iommu_pci_seg *pci_seg)
 {
 	int i;
 
-	pci_seg->alias_table = iommu_alloc_pages(GFP_KERNEL,
-						 get_order(pci_seg->alias_table_size));
+	pci_seg->alias_table = kvmalloc_array(pci_seg->last_bdf + 1,
+					      sizeof(*pci_seg->alias_table),
+					      GFP_KERNEL);
 	if (!pci_seg->alias_table)
 		return -ENOMEM;
 
@@ -707,8 +706,7 @@ static int __init alloc_alias_table(struct amd_iommu_pci_seg *pci_seg)
 
 static void __init free_alias_table(struct amd_iommu_pci_seg *pci_seg)
 {
-	iommu_free_pages(pci_seg->alias_table,
-			 get_order(pci_seg->alias_table_size));
+	kvfree(pci_seg->alias_table);
 	pci_seg->alias_table = NULL;
 }
 
@@ -719,8 +717,7 @@ static void __init free_alias_table(struct amd_iommu_pci_seg *pci_seg)
  */
 static int __init alloc_command_buffer(struct amd_iommu *iommu)
 {
-	iommu->cmd_buf = iommu_alloc_pages(GFP_KERNEL,
-					   get_order(CMD_BUFFER_SIZE));
+	iommu->cmd_buf = iommu_alloc_pages_sz(GFP_KERNEL, CMD_BUFFER_SIZE);
 
 	return iommu->cmd_buf ? 0 : -ENOMEM;
 }
@@ -817,20 +814,22 @@ static void iommu_disable_command_buffer(struct amd_iommu *iommu)
 
 static void __init free_command_buffer(struct amd_iommu *iommu)
 {
-	iommu_free_pages(iommu->cmd_buf, get_order(CMD_BUFFER_SIZE));
+	iommu_free_pages(iommu->cmd_buf);
 }
 
 void *__init iommu_alloc_4k_pages(struct amd_iommu *iommu, gfp_t gfp,
 				  size_t size)
 {
-	int order = get_order(size);
-	void *buf = iommu_alloc_pages(gfp, order);
+	void *buf;
 
-	if (buf &&
-	    check_feature(FEATURE_SNP) &&
-	    set_memory_4k((unsigned long)buf, (1 << order))) {
-		iommu_free_pages(buf, order);
-		buf = NULL;
+	size = PAGE_ALIGN(size);
+	buf = iommu_alloc_pages_sz(gfp, size);
+	if (!buf)
+		return NULL;
+	if (check_feature(FEATURE_SNP) &&
+	    set_memory_4k((unsigned long)buf, size / PAGE_SIZE)) {
+		iommu_free_pages(buf);
+		return NULL;
 	}
 
 	return buf;
@@ -873,14 +872,14 @@ static void iommu_disable_event_buffer(struct amd_iommu *iommu)
 
 static void __init free_event_buffer(struct amd_iommu *iommu)
 {
-	iommu_free_pages(iommu->evt_buf, get_order(EVT_BUFFER_SIZE));
+	iommu_free_pages(iommu->evt_buf);
 }
 
 static void free_ga_log(struct amd_iommu *iommu)
 {
 #ifdef CONFIG_IRQ_REMAP
-	iommu_free_pages(iommu->ga_log, get_order(GA_LOG_SIZE));
-	iommu_free_pages(iommu->ga_log_tail, get_order(8));
+	iommu_free_pages(iommu->ga_log);
+	iommu_free_pages(iommu->ga_log_tail);
 #endif
 }
 
@@ -925,11 +924,11 @@ static int iommu_init_ga_log(struct amd_iommu *iommu)
 	if (!AMD_IOMMU_GUEST_IR_VAPIC(amd_iommu_guest_ir))
 		return 0;
 
-	iommu->ga_log = iommu_alloc_pages(GFP_KERNEL, get_order(GA_LOG_SIZE));
+	iommu->ga_log = iommu_alloc_pages_sz(GFP_KERNEL, GA_LOG_SIZE);
 	if (!iommu->ga_log)
 		goto err_out;
 
-	iommu->ga_log_tail = iommu_alloc_pages(GFP_KERNEL, get_order(8));
+	iommu->ga_log_tail = iommu_alloc_pages_sz(GFP_KERNEL, 8);
 	if (!iommu->ga_log_tail)
 		goto err_out;
 
@@ -950,7 +949,7 @@ static int __init alloc_cwwb_sem(struct amd_iommu *iommu)
 static void __init free_cwwb_sem(struct amd_iommu *iommu)
 {
 	if (iommu->cmd_sem)
-		iommu_free_page((void *)iommu->cmd_sem);
+		iommu_free_pages((void *)iommu->cmd_sem);
 }
 
 static void iommu_enable_xt(struct amd_iommu *iommu)
@@ -1024,8 +1023,8 @@ static bool __copy_device_table(struct amd_iommu *iommu)
 	if (!old_devtb)
 		return false;
 
-	pci_seg->old_dev_tbl_cpy = iommu_alloc_pages(GFP_KERNEL | GFP_DMA32,
-						     get_order(pci_seg->dev_table_size));
+	pci_seg->old_dev_tbl_cpy = iommu_alloc_pages_sz(
+		GFP_KERNEL | GFP_DMA32, pci_seg->dev_table_size);
 	if (pci_seg->old_dev_tbl_cpy == NULL) {
 		pr_err("Failed to allocate memory for copying old device table!\n");
 		memunmap(old_devtb);
@@ -1599,9 +1598,9 @@ static struct amd_iommu_pci_seg *__init alloc_pci_segment(u16 id,
 
 	pci_seg->last_bdf = last_bdf;
 	DUMP_printk("PCI segment : 0x%0x, last bdf : 0x%04x\n", id, last_bdf);
-	pci_seg->dev_table_size     = tbl_size(DEV_TABLE_ENTRY_SIZE, last_bdf);
-	pci_seg->alias_table_size   = tbl_size(ALIAS_TABLE_ENTRY_SIZE, last_bdf);
-	pci_seg->rlookup_table_size = tbl_size(RLOOKUP_TABLE_ENTRY_SIZE, last_bdf);
+	pci_seg->dev_table_size =
+		max(roundup_pow_of_two((last_bdf + 1) * DEV_TABLE_ENTRY_SIZE),
+		    SZ_4K);
 
 	pci_seg->id = id;
 	init_llist_head(&pci_seg->dev_data_list);
@@ -1798,6 +1797,11 @@ static int __init init_iommu_one(struct amd_iommu *iommu, struct ivhd_header *h,
 		if (h->efr_reg & BIT(IOMMU_EFR_XTSUP_SHIFT))
 			amd_iommu_xt_mode = IRQ_REMAP_X2APIC_MODE;
 
+		if (h->efr_attr & BIT(IOMMU_IVHD_ATTR_HATDIS_SHIFT)) {
+			pr_warn_once("Host Address Translation is not supported.\n");
+			amd_iommu_hatdis = true;
+		}
+
 		early_iommu_features_init(iommu, h);
 
 		break;
@@ -2030,9 +2034,6 @@ static int __init iommu_init_pci(struct amd_iommu *iommu)
 	if (!iommu->dev)
 		return -ENODEV;
 
-	/* Prevent binding other PCI device drivers to IOMMU devices */
-	iommu->dev->match_driver = false;
-
 	/* ACPI _PRT won't have an IRQ for IOMMU */
 	iommu->dev->irq_managed = 1;
 
@@ -2121,7 +2122,15 @@ static int __init iommu_init_pci(struct amd_iommu *iommu)
 			return ret;
 	}
 
-	iommu_device_register(&iommu->iommu, &amd_iommu_ops, NULL);
+	ret = iommu_device_register(&iommu->iommu, &amd_iommu_ops, NULL);
+	if (ret || amd_iommu_pgtable == PD_MODE_NONE) {
+		/*
+		 * Remove sysfs if DMA translation is not supported by the
+		 * IOMMU. Do not return an error to enable IRQ remapping
+		 * in state_next(), DTE[V, TV] must eventually be set to 0.
+		 */
+		iommu_device_sysfs_remove(&iommu->iommu);
+	}
 
 	return pci_enable_device(iommu->dev);
 }
@@ -2582,7 +2591,7 @@ static void init_device_table_dma(struct amd_iommu_pci_seg *pci_seg)
 	u32 devid;
 	struct dev_table_entry *dev_table = pci_seg->dev_table;
 
-	if (dev_table == NULL)
+	if (!dev_table || amd_iommu_pgtable == PD_MODE_NONE)
 		return;
 
 	for (devid = 0; devid <= pci_seg->last_bdf; ++devid) {
@@ -2789,8 +2798,7 @@ static void early_enable_iommus(void)
 
 		for_each_pci_segment(pci_seg) {
 			if (pci_seg->old_dev_tbl_cpy != NULL) {
-				iommu_free_pages(pci_seg->old_dev_tbl_cpy,
-						 get_order(pci_seg->dev_table_size));
+				iommu_free_pages(pci_seg->old_dev_tbl_cpy);
 				pci_seg->old_dev_tbl_cpy = NULL;
 			}
 		}
@@ -2803,8 +2811,7 @@ static void early_enable_iommus(void)
 		pr_info("Copied DEV table from previous kernel.\n");
 
 		for_each_pci_segment(pci_seg) {
-			iommu_free_pages(pci_seg->dev_table,
-					 get_order(pci_seg->dev_table_size));
+			iommu_free_pages(pci_seg->dev_table);
 			pci_seg->dev_table = pci_seg->old_dev_tbl_cpy;
 		}
 
@@ -3044,6 +3051,7 @@ static int __init early_amd_iommu_init(void)
 	struct acpi_table_header *ivrs_base;
 	int ret;
 	acpi_status status;
+	u8 efr_hats;
 
 	if (!amd_iommu_detected)
 		return -ENODEV;
@@ -3088,6 +3096,19 @@ static int __init early_amd_iommu_init(void)
 	    FIELD_GET(FEATURE_GATS, amd_iommu_efr) == GUEST_PGTABLE_5_LEVEL)
 		amd_iommu_gpt_level = PAGE_MODE_5_LEVEL;
 
+	efr_hats = FIELD_GET(FEATURE_HATS, amd_iommu_efr);
+	if (efr_hats != 0x3) {
+		/*
+		 * efr[HATS] bits specify the maximum host translation level
+		 * supported, with LEVEL 4 being initial max level.
+		 */
+		amd_iommu_hpt_level = efr_hats + PAGE_MODE_4_LEVEL;
+	} else {
+		pr_warn_once(FW_BUG "Disable host address translation due to invalid translation level (%#x).\n",
+			     efr_hats);
+		amd_iommu_hatdis = true;
+	}
+
 	if (amd_iommu_pgtable == PD_MODE_V2) {
 		if (!amd_iommu_v2_pgtbl_supported()) {
 			pr_warn("Cannot enable v2 page table for DMA-API. Fallback to v1.\n");
@@ -3095,6 +3116,17 @@ static int __init early_amd_iommu_init(void)
 		}
 	}
 
+	if (amd_iommu_hatdis) {
+		/*
+		 * Host (v1) page table is not available. Attempt to use
+		 * Guest (v2) page table.
+		 */
+		if (amd_iommu_v2_pgtbl_supported())
+			amd_iommu_pgtable = PD_MODE_V2;
+		else
+			amd_iommu_pgtable = PD_MODE_NONE;
+	}
+
 	/* Disable any previously enabled IOMMUs */
 	if (!is_kdump_kernel() || amd_iommu_disabled)
 		disable_iommus();
@@ -3387,7 +3419,6 @@ int amd_iommu_enable_faulting(unsigned int cpu)
  */
 static int __init amd_iommu_init(void)
 {
-	struct amd_iommu *iommu;
 	int ret;
 
 	ret = iommu_go_to_state(IOMMU_INITIALIZED);
@@ -3401,8 +3432,8 @@ static int __init amd_iommu_init(void)
 	}
 #endif
 
-	for_each_iommu(iommu)
-		amd_iommu_debugfs_setup(iommu);
+	if (!ret)
+		amd_iommu_debugfs_setup();
 
 	return ret;
 }