7 files changed, 559 insertions, 91 deletions

diff --git a/drivers/iommu/amd/Kconfig b/drivers/iommu/amd/Kconfig
index 994063e5586f..ecef69c11144 100644
--- a/drivers/iommu/amd/Kconfig
+++ b/drivers/iommu/amd/Kconfig
@@ -7,6 +7,7 @@ config AMD_IOMMU
 	select PCI_ATS
 	select PCI_PRI
 	select PCI_PASID
+	select IRQ_MSI_LIB
 	select MMU_NOTIFIER
 	select IOMMU_API
 	select IOMMU_IOVA
diff --git a/drivers/iommu/amd/amd_iommu.h b/drivers/iommu/amd/amd_iommu.h
index 29a8864381c3..9b4b589a54b5 100644
--- a/drivers/iommu/amd/amd_iommu.h
+++ b/drivers/iommu/amd/amd_iommu.h
@@ -28,9 +28,9 @@ void *__init iommu_alloc_4k_pages(struct amd_iommu *iommu,
 				  gfp_t gfp, size_t size);
 
 #ifdef CONFIG_AMD_IOMMU_DEBUGFS
-void amd_iommu_debugfs_setup(struct amd_iommu *iommu);
+void amd_iommu_debugfs_setup(void);
 #else
-static inline void amd_iommu_debugfs_setup(struct amd_iommu *iommu) {}
+static inline void amd_iommu_debugfs_setup(void) {}
 #endif
 
 /* Needed for interrupt remapping */
@@ -42,7 +42,9 @@ int amd_iommu_enable_faulting(unsigned int cpu);
 extern int amd_iommu_guest_ir;
 extern enum protection_domain_mode amd_iommu_pgtable;
 extern int amd_iommu_gpt_level;
+extern u8 amd_iommu_hpt_level;
 extern unsigned long amd_iommu_pgsize_bitmap;
+extern bool amd_iommu_hatdis;
 
 /* Protection domain ops */
 void amd_iommu_init_identity_domain(void);
diff --git a/drivers/iommu/amd/amd_iommu_types.h b/drivers/iommu/amd/amd_iommu_types.h
index ccbab3a4811a..5219d7ddfdaa 100644
--- a/drivers/iommu/amd/amd_iommu_types.h
+++ b/drivers/iommu/amd/amd_iommu_types.h
@@ -94,6 +94,7 @@
 #define FEATURE_GA		BIT_ULL(7)
 #define FEATURE_HE		BIT_ULL(8)
 #define FEATURE_PC		BIT_ULL(9)
+#define FEATURE_HATS		GENMASK_ULL(11, 10)
 #define FEATURE_GATS		GENMASK_ULL(13, 12)
 #define FEATURE_GLX		GENMASK_ULL(15, 14)
 #define FEATURE_GAM_VAPIC	BIT_ULL(21)
@@ -460,6 +461,9 @@
 /* IOMMU Feature Reporting Field (for IVHD type 10h */
 #define IOMMU_FEAT_GASUP_SHIFT	6
 
+/* IOMMU HATDIS for IVHD type 11h and 40h */
+#define IOMMU_IVHD_ATTR_HATDIS_SHIFT	0
+
 /* IOMMU Extended Feature Register (EFR) */
 #define IOMMU_EFR_XTSUP_SHIFT	2
 #define IOMMU_EFR_GASUP_SHIFT	7
@@ -558,7 +562,8 @@ struct amd_io_pgtable {
 };
 
 enum protection_domain_mode {
-	PD_MODE_V1 = 1,
+	PD_MODE_NONE,
+	PD_MODE_V1,
 	PD_MODE_V2,
 };
 
@@ -790,6 +795,8 @@ struct amd_iommu {
 #ifdef CONFIG_AMD_IOMMU_DEBUGFS
 	/* DebugFS Info */
 	struct dentry *debugfs;
+	int dbg_mmio_offset;
+	int dbg_cap_offset;
 #endif
 
 	/* IOPF support */
@@ -891,6 +898,13 @@ struct dev_table_entry {
 };
 
 /*
+ * Structure defining one entry in the command buffer
+ */
+struct iommu_cmd {
+	u32 data[4];
+};
+
+/*
  * Structure to sture persistent DTE flags from IVHD
  */
 struct ivhd_dte_flags {
@@ -1054,7 +1068,6 @@ struct irq_2_irte {
 };
 
 struct amd_ir_data {
-	u32 cached_ga_tag;
 	struct amd_iommu *iommu;
 	struct irq_2_irte irq_2_irte;
 	struct msi_msg msi_entry;
diff --git a/drivers/iommu/amd/debugfs.c b/drivers/iommu/amd/debugfs.c
index 545372fcc72f..10fa217a7119 100644
--- a/drivers/iommu/amd/debugfs.c
+++ b/drivers/iommu/amd/debugfs.c
@@ -11,22 +11,382 @@
 #include <linux/pci.h>
 
 #include "amd_iommu.h"
+#include "../irq_remapping.h"
 
 static struct dentry *amd_iommu_debugfs;
-static DEFINE_MUTEX(amd_iommu_debugfs_lock);
 
 #define	MAX_NAME_LEN	20
+#define	OFS_IN_SZ	8
+#define	DEVID_IN_SZ	16
 
-void amd_iommu_debugfs_setup(struct amd_iommu *iommu)
+static int sbdf = -1;
+
+static ssize_t iommu_mmio_write(struct file *filp, const char __user *ubuf,
+				size_t cnt, loff_t *ppos)
+{
+	struct seq_file *m = filp->private_data;
+	struct amd_iommu *iommu = m->private;
+	int ret;
+
+	iommu->dbg_mmio_offset = -1;
+
+	if (cnt > OFS_IN_SZ)
+		return -EINVAL;
+
+	ret = kstrtou32_from_user(ubuf, cnt, 0, &iommu->dbg_mmio_offset);
+	if (ret)
+		return ret;
+
+	if (iommu->dbg_mmio_offset > iommu->mmio_phys_end - 4) {
+		iommu->dbg_mmio_offset = -1;
+		return  -EINVAL;
+	}
+
+	return cnt;
+}
+
+static int iommu_mmio_show(struct seq_file *m, void *unused)
+{
+	struct amd_iommu *iommu = m->private;
+	u64 value;
+
+	if (iommu->dbg_mmio_offset < 0) {
+		seq_puts(m, "Please provide mmio register's offset\n");
+		return 0;
+	}
+
+	value = readq(iommu->mmio_base + iommu->dbg_mmio_offset);
+	seq_printf(m, "Offset:0x%x Value:0x%016llx\n", iommu->dbg_mmio_offset, value);
+
+	return 0;
+}
+DEFINE_SHOW_STORE_ATTRIBUTE(iommu_mmio);
+
+static ssize_t iommu_capability_write(struct file *filp, const char __user *ubuf,
+				      size_t cnt, loff_t *ppos)
+{
+	struct seq_file *m = filp->private_data;
+	struct amd_iommu *iommu = m->private;
+	int ret;
+
+	iommu->dbg_cap_offset = -1;
+
+	if (cnt > OFS_IN_SZ)
+		return -EINVAL;
+
+	ret = kstrtou32_from_user(ubuf, cnt, 0, &iommu->dbg_cap_offset);
+	if (ret)
+		return ret;
+
+	/* Capability register at offset 0x14 is the last IOMMU capability register. */
+	if (iommu->dbg_cap_offset > 0x14) {
+		iommu->dbg_cap_offset = -1;
+		return -EINVAL;
+	}
+
+	return cnt;
+}
+
+static int iommu_capability_show(struct seq_file *m, void *unused)
+{
+	struct amd_iommu *iommu = m->private;
+	u32 value;
+	int err;
+
+	if (iommu->dbg_cap_offset < 0) {
+		seq_puts(m, "Please provide capability register's offset in the range [0x00 - 0x14]\n");
+		return 0;
+	}
+
+	err = pci_read_config_dword(iommu->dev, iommu->cap_ptr + iommu->dbg_cap_offset, &value);
+	if (err) {
+		seq_printf(m, "Not able to read capability register at 0x%x\n",
+			   iommu->dbg_cap_offset);
+		return 0;
+	}
+
+	seq_printf(m, "Offset:0x%x Value:0x%08x\n", iommu->dbg_cap_offset, value);
+
+	return 0;
+}
+DEFINE_SHOW_STORE_ATTRIBUTE(iommu_capability);
+
+static int iommu_cmdbuf_show(struct seq_file *m, void *unused)
+{
+	struct amd_iommu *iommu = m->private;
+	struct iommu_cmd *cmd;
+	unsigned long flag;
+	u32 head, tail;
+	int i;
+
+	raw_spin_lock_irqsave(&iommu->lock, flag);
+	head = readl(iommu->mmio_base + MMIO_CMD_HEAD_OFFSET);
+	tail = readl(iommu->mmio_base + MMIO_CMD_TAIL_OFFSET);
+	seq_printf(m, "CMD Buffer Head Offset:%d Tail Offset:%d\n",
+		   (head >> 4) & 0x7fff, (tail >> 4) & 0x7fff);
+	for (i = 0; i < CMD_BUFFER_ENTRIES; i++) {
+		cmd = (struct iommu_cmd *)(iommu->cmd_buf + i * sizeof(*cmd));
+		seq_printf(m, "%3d: %08x %08x %08x %08x\n", i, cmd->data[0],
+			   cmd->data[1], cmd->data[2], cmd->data[3]);
+	}
+	raw_spin_unlock_irqrestore(&iommu->lock, flag);
+
+	return 0;
+}
+DEFINE_SHOW_ATTRIBUTE(iommu_cmdbuf);
+
+static ssize_t devid_write(struct file *filp, const char __user *ubuf,
+			   size_t cnt, loff_t *ppos)
+{
+	struct amd_iommu_pci_seg *pci_seg;
+	int seg, bus, slot, func;
+	struct amd_iommu *iommu;
+	char *srcid_ptr;
+	u16 devid;
+	int i;
+
+	sbdf = -1;
+
+	if (cnt >= DEVID_IN_SZ)
+		return -EINVAL;
+
+	srcid_ptr = memdup_user_nul(ubuf, cnt);
+	if (IS_ERR(srcid_ptr))
+		return PTR_ERR(srcid_ptr);
+
+	i = sscanf(srcid_ptr, "%x:%x:%x.%x", &seg, &bus, &slot, &func);
+	if (i != 4) {
+		i = sscanf(srcid_ptr, "%x:%x.%x", &bus, &slot, &func);
+		if (i != 3) {
+			kfree(srcid_ptr);
+			return -EINVAL;
+		}
+		seg = 0;
+	}
+
+	devid = PCI_DEVID(bus, PCI_DEVFN(slot, func));
+
+	/* Check if user device id input is a valid input */
+	for_each_pci_segment(pci_seg) {
+		if (pci_seg->id != seg)
+			continue;
+		if (devid > pci_seg->last_bdf) {
+			kfree(srcid_ptr);
+			return -EINVAL;
+		}
+		iommu = pci_seg->rlookup_table[devid];
+		if (!iommu) {
+			kfree(srcid_ptr);
+			return -ENODEV;
+		}
+		break;
+	}
+
+	if (pci_seg->id != seg) {
+		kfree(srcid_ptr);
+		return -EINVAL;
+	}
+
+	sbdf = PCI_SEG_DEVID_TO_SBDF(seg, devid);
+
+	kfree(srcid_ptr);
+
+	return cnt;
+}
+
+static int devid_show(struct seq_file *m, void *unused)
 {
+	u16 devid;
+
+	if (sbdf >= 0) {
+		devid = PCI_SBDF_TO_DEVID(sbdf);
+		seq_printf(m, "%04x:%02x:%02x.%x\n", PCI_SBDF_TO_SEGID(sbdf),
+			   PCI_BUS_NUM(devid), PCI_SLOT(devid), PCI_FUNC(devid));
+	} else
+		seq_puts(m, "No or Invalid input provided\n");
+
+	return 0;
+}
+DEFINE_SHOW_STORE_ATTRIBUTE(devid);
+
+static void dump_dte(struct seq_file *m, struct amd_iommu_pci_seg *pci_seg, u16 devid)
+{
+	struct dev_table_entry *dev_table;
+	struct amd_iommu *iommu;
+
+	iommu = pci_seg->rlookup_table[devid];
+	if (!iommu)
+		return;
+
+	dev_table = get_dev_table(iommu);
+	if (!dev_table) {
+		seq_puts(m, "Device table not found");
+		return;
+	}
+
+	seq_printf(m, "%-12s %16s %16s %16s %16s iommu\n", "DeviceId",
+		   "QWORD[3]", "QWORD[2]", "QWORD[1]", "QWORD[0]");
+	seq_printf(m, "%04x:%02x:%02x.%x ", pci_seg->id, PCI_BUS_NUM(devid),
+		   PCI_SLOT(devid), PCI_FUNC(devid));
+	for (int i = 3; i >= 0; --i)
+		seq_printf(m, "%016llx ", dev_table[devid].data[i]);
+	seq_printf(m, "iommu%d\n", iommu->index);
+}
+
+static int iommu_devtbl_show(struct seq_file *m, void *unused)
+{
+	struct amd_iommu_pci_seg *pci_seg;
+	u16 seg, devid;
+
+	if (sbdf < 0) {
+		seq_puts(m, "Enter a valid device ID to 'devid' file\n");
+		return 0;
+	}
+	seg = PCI_SBDF_TO_SEGID(sbdf);
+	devid = PCI_SBDF_TO_DEVID(sbdf);
+
+	for_each_pci_segment(pci_seg) {
+		if (pci_seg->id != seg)
+			continue;
+		dump_dte(m, pci_seg, devid);
+		break;
+	}
+
+	return 0;
+}
+DEFINE_SHOW_ATTRIBUTE(iommu_devtbl);
+
+static void dump_128_irte(struct seq_file *m, struct irq_remap_table *table, u16 int_tab_len)
+{
+	struct irte_ga *ptr, *irte;
+	int index;
+
+	for (index = 0; index < int_tab_len; index++) {
+		ptr = (struct irte_ga *)table->table;
+		irte = &ptr[index];
+
+		if (AMD_IOMMU_GUEST_IR_VAPIC(amd_iommu_guest_ir) &&
+		    !irte->lo.fields_vapic.valid)
+			continue;
+		else if (!irte->lo.fields_remap.valid)
+			continue;
+		seq_printf(m, "IRT[%04d] %016llx %016llx\n", index, irte->hi.val, irte->lo.val);
+	}
+}
+
+static void dump_32_irte(struct seq_file *m, struct irq_remap_table *table, u16 int_tab_len)
+{
+	union irte *ptr, *irte;
+	int index;
+
+	for (index = 0; index < int_tab_len; index++) {
+		ptr = (union irte *)table->table;
+		irte = &ptr[index];
+
+		if (!irte->fields.valid)
+			continue;
+		seq_printf(m, "IRT[%04d] %08x\n", index, irte->val);
+	}
+}
+
+static void dump_irte(struct seq_file *m, u16 devid, struct amd_iommu_pci_seg *pci_seg)
+{
+	struct dev_table_entry *dev_table;
+	struct irq_remap_table *table;
+	struct amd_iommu *iommu;
+	unsigned long flags;
+	u16 int_tab_len;
+
+	table = pci_seg->irq_lookup_table[devid];
+	if (!table) {
+		seq_printf(m, "IRQ lookup table not set for %04x:%02x:%02x:%x\n",
+			   pci_seg->id, PCI_BUS_NUM(devid), PCI_SLOT(devid), PCI_FUNC(devid));
+		return;
+	}
+
+	iommu = pci_seg->rlookup_table[devid];
+	if (!iommu)
+		return;
+
+	dev_table = get_dev_table(iommu);
+	if (!dev_table) {
+		seq_puts(m, "Device table not found");
+		return;
+	}
+
+	int_tab_len = dev_table[devid].data[2] & DTE_INTTABLEN_MASK;
+	if (int_tab_len != DTE_INTTABLEN_512 && int_tab_len != DTE_INTTABLEN_2K) {
+		seq_puts(m, "The device's DTE contains an invalid IRT length value.");
+		return;
+	}
+
+	seq_printf(m, "DeviceId %04x:%02x:%02x.%x\n", pci_seg->id, PCI_BUS_NUM(devid),
+		   PCI_SLOT(devid), PCI_FUNC(devid));
+
+	raw_spin_lock_irqsave(&table->lock, flags);
+	if (AMD_IOMMU_GUEST_IR_GA(amd_iommu_guest_ir))
+		dump_128_irte(m, table, BIT(int_tab_len >> 1));
+	else
+		dump_32_irte(m, table, BIT(int_tab_len >> 1));
+	seq_puts(m, "\n");
+	raw_spin_unlock_irqrestore(&table->lock, flags);
+}
+
+static int iommu_irqtbl_show(struct seq_file *m, void *unused)
+{
+	struct amd_iommu_pci_seg *pci_seg;
+	u16 devid, seg;
+
+	if (!irq_remapping_enabled) {
+		seq_puts(m, "Interrupt remapping is disabled\n");
+		return 0;
+	}
+
+	if (sbdf < 0) {
+		seq_puts(m, "Enter a valid device ID to 'devid' file\n");
+		return 0;
+	}
+
+	seg = PCI_SBDF_TO_SEGID(sbdf);
+	devid = PCI_SBDF_TO_DEVID(sbdf);
+
+	for_each_pci_segment(pci_seg) {
+		if (pci_seg->id != seg)
+			continue;
+		dump_irte(m, devid, pci_seg);
+		break;
+	}
+
+	return 0;
+}
+DEFINE_SHOW_ATTRIBUTE(iommu_irqtbl);
+
+void amd_iommu_debugfs_setup(void)
+{
+	struct amd_iommu *iommu;
 	char name[MAX_NAME_LEN + 1];
 
-	mutex_lock(&amd_iommu_debugfs_lock);
-	if (!amd_iommu_debugfs)
-		amd_iommu_debugfs = debugfs_create_dir("amd",
-						       iommu_debugfs_dir);
-	mutex_unlock(&amd_iommu_debugfs_lock);
+	amd_iommu_debugfs = debugfs_create_dir("amd", iommu_debugfs_dir);
+
+	for_each_iommu(iommu) {
+		iommu->dbg_mmio_offset = -1;
+		iommu->dbg_cap_offset = -1;
+
+		snprintf(name, MAX_NAME_LEN, "iommu%02d", iommu->index);
+		iommu->debugfs = debugfs_create_dir(name, amd_iommu_debugfs);
+
+		debugfs_create_file("mmio", 0644, iommu->debugfs, iommu,
+				    &iommu_mmio_fops);
+		debugfs_create_file("capability", 0644, iommu->debugfs, iommu,
+				    &iommu_capability_fops);
+		debugfs_create_file("cmdbuf", 0444, iommu->debugfs, iommu,
+				    &iommu_cmdbuf_fops);
+	}
 
-	snprintf(name, MAX_NAME_LEN, "iommu%02d", iommu->index);
-	iommu->debugfs = debugfs_create_dir(name, amd_iommu_debugfs);
+	debugfs_create_file("devid", 0644, amd_iommu_debugfs, NULL,
+			    &devid_fops);
+	debugfs_create_file("devtbl", 0444, amd_iommu_debugfs, NULL,
+			    &iommu_devtbl_fops);
+	debugfs_create_file("irqtbl", 0444, amd_iommu_debugfs, NULL,
+			    &iommu_irqtbl_fops);
 }
diff --git a/drivers/iommu/amd/init.c b/drivers/iommu/amd/init.c
index 9c17dfa76703..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);
@@ -1792,6 +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;
@@ -2112,7 +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);
 }
@@ -2573,7 +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) {
@@ -3033,6 +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;
@@ -3077,6 +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");
@@ -3084,6 +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();
@@ -3376,7 +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);
@@ -3390,8 +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;
 }
diff --git a/drivers/iommu/amd/io_pgtable.c b/drivers/iommu/amd/io_pgtable.c
index 4d308c071134..a91e71f981ef 100644
--- a/drivers/iommu/amd/io_pgtable.c
+++ b/drivers/iommu/amd/io_pgtable.c
@@ -125,7 +125,7 @@ static bool increase_address_space(struct amd_io_pgtable *pgtable,
 		goto out;
 
 	ret = false;
-	if (WARN_ON_ONCE(pgtable->mode == PAGE_MODE_6_LEVEL))
+	if (WARN_ON_ONCE(pgtable->mode == amd_iommu_hpt_level))
 		goto out;
 
 	*pte = PM_LEVEL_PDE(pgtable->mode, iommu_virt_to_phys(pgtable->root));
@@ -526,7 +526,7 @@ static void v1_free_pgtable(struct io_pgtable *iop)
 
 	/* Page-table is not visible to IOMMU anymore, so free it */
 	BUG_ON(pgtable->mode < PAGE_MODE_NONE ||
-	       pgtable->mode > PAGE_MODE_6_LEVEL);
+	       pgtable->mode > amd_iommu_hpt_level);
 
 	free_sub_pt(pgtable->root, pgtable->mode, &freelist);
 	iommu_put_pages_list(&freelist);
diff --git a/drivers/iommu/amd/iommu.c b/drivers/iommu/amd/iommu.c
index 3117d99cf83d..eb348c63a8d0 100644
--- a/drivers/iommu/amd/iommu.c
+++ b/drivers/iommu/amd/iommu.c
@@ -25,6 +25,7 @@
 #include <linux/notifier.h>
 #include <linux/export.h>
 #include <linux/irq.h>
+#include <linux/irqchip/irq-msi-lib.h>
 #include <linux/msi.h>
 #include <linux/irqdomain.h>
 #include <linux/percpu.h>
@@ -63,13 +64,6 @@ static const struct iommu_dirty_ops amd_dirty_ops;
 int amd_iommu_max_glx_val = -1;
 
 /*
- * general struct to manage commands send to an IOMMU
- */
-struct iommu_cmd {
-	u32 data[4];
-};
-
-/*
  * AMD IOMMU allows up to 2^16 different protection domains. This is a bitmap
  * to know which ones are already in use.
  */
@@ -634,8 +628,8 @@ static inline void pdev_disable_cap_pasid(struct pci_dev *pdev)
 
 static void pdev_enable_caps(struct pci_dev *pdev)
 {
-	pdev_enable_cap_ats(pdev);
 	pdev_enable_cap_pasid(pdev);
+	pdev_enable_cap_ats(pdev);
 	pdev_enable_cap_pri(pdev);
 }
 
@@ -2424,6 +2418,13 @@ static struct iommu_device *amd_iommu_probe_device(struct device *dev)
 					     pci_max_pasids(to_pci_dev(dev)));
 	}
 
+	if (amd_iommu_pgtable == PD_MODE_NONE) {
+		pr_warn_once("%s: DMA translation not supported by iommu.\n",
+			     __func__);
+		iommu_dev = ERR_PTR(-ENODEV);
+		goto out_err;
+	}
+
 out_err:
 
 	iommu_completion_wait(iommu);
@@ -2511,6 +2512,9 @@ static int pdom_setup_pgtable(struct protection_domain *domain,
 	case PD_MODE_V2:
 		fmt = AMD_IOMMU_V2;
 		break;
+	case PD_MODE_NONE:
+		WARN_ON_ONCE(1);
+		return -EPERM;
 	}
 
 	domain->iop.pgtbl.cfg.amd.nid = dev_to_node(dev);
@@ -2524,14 +2528,30 @@ static int pdom_setup_pgtable(struct protection_domain *domain,
 static inline u64 dma_max_address(enum protection_domain_mode pgtable)
 {
 	if (pgtable == PD_MODE_V1)
-		return ~0ULL;
+		return PM_LEVEL_SIZE(amd_iommu_hpt_level);
 
-	/* V2 with 4/5 level page table */
-	return ((1ULL << PM_LEVEL_SHIFT(amd_iommu_gpt_level)) - 1);
+	/*
+	 * V2 with 4/5 level page table. Note that "2.2.6.5 AMD64 4-Kbyte Page
+	 * Translation" shows that the V2 table sign extends the top of the
+	 * address space creating a reserved region in the middle of the
+	 * translation, just like the CPU does. Further Vasant says the docs are
+	 * incomplete and this only applies to non-zero PASIDs. If the AMDv2
+	 * page table is assigned to the 0 PASID then there is no sign extension
+	 * check.
+	 *
+	 * Since the IOMMU must have a fixed geometry, and the core code does
+	 * not understand sign extended addressing, we have to chop off the high
+	 * bit to get consistent behavior with attachments of the domain to any
+	 * PASID.
+	 */
+	return ((1ULL << (PM_LEVEL_SHIFT(amd_iommu_gpt_level) - 1)) - 1);
 }
 
 static bool amd_iommu_hd_support(struct amd_iommu *iommu)
 {
+	if (amd_iommu_hatdis)
+		return false;
+
 	return iommu && (iommu->features & FEATURE_HDSUP);
 }
 
@@ -3804,13 +3824,70 @@ static const struct irq_domain_ops amd_ir_domain_ops = {
 	.deactivate = irq_remapping_deactivate,
 };
 
-int amd_iommu_activate_guest_mode(void *data)
+static void __amd_iommu_update_ga(struct irte_ga *entry, int cpu,
+				  bool ga_log_intr)
+{
+	if (cpu >= 0) {
+		entry->lo.fields_vapic.destination =
+					APICID_TO_IRTE_DEST_LO(cpu);
+		entry->hi.fields.destination =
+					APICID_TO_IRTE_DEST_HI(cpu);
+		entry->lo.fields_vapic.is_run = true;
+		entry->lo.fields_vapic.ga_log_intr = false;
+	} else {
+		entry->lo.fields_vapic.is_run = false;
+		entry->lo.fields_vapic.ga_log_intr = ga_log_intr;
+	}
+}
+
+/*
+ * Update the pCPU information for an IRTE that is configured to post IRQs to
+ * a vCPU, without issuing an IOMMU invalidation for the IRTE.
+ *
+ * If the vCPU is associated with a pCPU (@cpu >= 0), configure the Destination
+ * with the pCPU's APIC ID, set IsRun, and clear GALogIntr.  If the vCPU isn't
+ * associated with a pCPU (@cpu < 0), clear IsRun and set/clear GALogIntr based
+ * on input from the caller (e.g. KVM only requests GALogIntr when the vCPU is
+ * blocking and requires a notification wake event).  I.e. treat vCPUs that are
+ * associated with a pCPU as running.  This API is intended to be used when a
+ * vCPU is scheduled in/out (or stops running for any reason), to do a fast
+ * update of IsRun, GALogIntr, and (conditionally) Destination.
+ *
+ * Per the IOMMU spec, the Destination, IsRun, and GATag fields are not cached
+ * and thus don't require an invalidation to ensure the IOMMU consumes fresh
+ * information.
+ */
+int amd_iommu_update_ga(void *data, int cpu, bool ga_log_intr)
+{
+	struct amd_ir_data *ir_data = (struct amd_ir_data *)data;
+	struct irte_ga *entry = (struct irte_ga *) ir_data->entry;
+
+	if (WARN_ON_ONCE(!AMD_IOMMU_GUEST_IR_VAPIC(amd_iommu_guest_ir)))
+		return -EINVAL;
+
+	if (!entry || !entry->lo.fields_vapic.guest_mode)
+		return 0;
+
+	if (!ir_data->iommu)
+		return -ENODEV;
+
+	__amd_iommu_update_ga(entry, cpu, ga_log_intr);
+
+	return __modify_irte_ga(ir_data->iommu, ir_data->irq_2_irte.devid,
+				ir_data->irq_2_irte.index, entry);
+}
+EXPORT_SYMBOL(amd_iommu_update_ga);
+
+int amd_iommu_activate_guest_mode(void *data, int cpu, bool ga_log_intr)
 {
 	struct amd_ir_data *ir_data = (struct amd_ir_data *)data;
 	struct irte_ga *entry = (struct irte_ga *) ir_data->entry;
 	u64 valid;
 
-	if (!AMD_IOMMU_GUEST_IR_VAPIC(amd_iommu_guest_ir) || !entry)
+	if (WARN_ON_ONCE(!AMD_IOMMU_GUEST_IR_VAPIC(amd_iommu_guest_ir)))
+		return -EINVAL;
+
+	if (!entry)
 		return 0;
 
 	valid = entry->lo.fields_vapic.valid;
@@ -3820,11 +3897,12 @@ int amd_iommu_activate_guest_mode(void *data)
 
 	entry->lo.fields_vapic.valid       = valid;
 	entry->lo.fields_vapic.guest_mode  = 1;
-	entry->lo.fields_vapic.ga_log_intr = 1;
 	entry->hi.fields.ga_root_ptr       = ir_data->ga_root_ptr;
 	entry->hi.fields.vector            = ir_data->ga_vector;
 	entry->lo.fields_vapic.ga_tag      = ir_data->ga_tag;
 
+	__amd_iommu_update_ga(entry, cpu, ga_log_intr);
+
 	return modify_irte_ga(ir_data->iommu, ir_data->irq_2_irte.devid,
 			      ir_data->irq_2_irte.index, entry);
 }
@@ -3837,8 +3915,10 @@ int amd_iommu_deactivate_guest_mode(void *data)
 	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)
+	if (WARN_ON_ONCE(!AMD_IOMMU_GUEST_IR_VAPIC(amd_iommu_guest_ir)))
+		return -EINVAL;
+
+	if (!entry || !entry->lo.fields_vapic.guest_mode)
 		return 0;
 
 	valid = entry->lo.fields_remap.valid;
@@ -3860,11 +3940,10 @@ int amd_iommu_deactivate_guest_mode(void *data)
 }
 EXPORT_SYMBOL(amd_iommu_deactivate_guest_mode);
 
-static int amd_ir_set_vcpu_affinity(struct irq_data *data, void *vcpu_info)
+static int amd_ir_set_vcpu_affinity(struct irq_data *data, void *info)
 {
 	int ret;
-	struct amd_iommu_pi_data *pi_data = vcpu_info;
-	struct vcpu_data *vcpu_pi_info = pi_data->vcpu_data;
+	struct amd_iommu_pi_data *pi_data = info;
 	struct amd_ir_data *ir_data = data->chip_data;
 	struct irq_2_irte *irte_info = &ir_data->irq_2_irte;
 	struct iommu_dev_data *dev_data;
@@ -3885,25 +3964,20 @@ static int amd_ir_set_vcpu_affinity(struct irq_data *data, void *vcpu_info)
 		return -EINVAL;
 
 	ir_data->cfg = irqd_cfg(data);
-	pi_data->ir_data = ir_data;
 
-	pi_data->prev_ga_tag = ir_data->cached_ga_tag;
-	if (pi_data->is_guest_mode) {
-		ir_data->ga_root_ptr = (pi_data->base >> 12);
-		ir_data->ga_vector = vcpu_pi_info->vector;
+	if (pi_data) {
+		pi_data->ir_data = ir_data;
+
+		ir_data->ga_root_ptr = (pi_data->vapic_addr >> 12);
+		ir_data->ga_vector = pi_data->vector;
 		ir_data->ga_tag = pi_data->ga_tag;
-		ret = amd_iommu_activate_guest_mode(ir_data);
-		if (!ret)
-			ir_data->cached_ga_tag = pi_data->ga_tag;
+		if (pi_data->is_guest_mode)
+			ret = amd_iommu_activate_guest_mode(ir_data, pi_data->cpu,
+							    pi_data->ga_log_intr);
+		else
+			ret = amd_iommu_deactivate_guest_mode(ir_data);
 	} else {
 		ret = amd_iommu_deactivate_guest_mode(ir_data);
-
-		/*
-		 * This communicates the ga_tag back to the caller
-		 * so that it can do all the necessary clean up.
-		 */
-		if (!ret)
-			ir_data->cached_ga_tag = 0;
 	}
 
 	return ret;
@@ -3970,54 +4044,30 @@ static struct irq_chip amd_ir_chip = {
 
 static const struct msi_parent_ops amdvi_msi_parent_ops = {
 	.supported_flags	= X86_VECTOR_MSI_FLAGS_SUPPORTED | MSI_FLAG_MULTI_PCI_MSI,
+	.bus_select_token	= DOMAIN_BUS_AMDVI,
+	.bus_select_mask	= MATCH_PCI_MSI,
 	.prefix			= "IR-",
 	.init_dev_msi_info	= msi_parent_init_dev_msi_info,
 };
 
 int amd_iommu_create_irq_domain(struct amd_iommu *iommu)
 {
-	struct fwnode_handle *fn;
+	struct irq_domain_info info = {
+		.fwnode		= irq_domain_alloc_named_id_fwnode("AMD-IR", iommu->index),
+		.ops		= &amd_ir_domain_ops,
+		.domain_flags	= IRQ_DOMAIN_FLAG_ISOLATED_MSI,
+		.host_data	= iommu,
+		.parent		= arch_get_ir_parent_domain(),
+	};
 
-	fn = irq_domain_alloc_named_id_fwnode("AMD-IR", iommu->index);
-	if (!fn)
+	if (!info.fwnode)
 		return -ENOMEM;
-	iommu->ir_domain = irq_domain_create_hierarchy(arch_get_ir_parent_domain(), 0, 0,
-						       fn, &amd_ir_domain_ops, iommu);
+
+	iommu->ir_domain = msi_create_parent_irq_domain(&info, &amdvi_msi_parent_ops);
 	if (!iommu->ir_domain) {
-		irq_domain_free_fwnode(fn);
+		irq_domain_free_fwnode(info.fwnode);
 		return -ENOMEM;
 	}
-
-	irq_domain_update_bus_token(iommu->ir_domain,  DOMAIN_BUS_AMDVI);
-	iommu->ir_domain->flags |= IRQ_DOMAIN_FLAG_MSI_PARENT |
-				   IRQ_DOMAIN_FLAG_ISOLATED_MSI;
-	iommu->ir_domain->msi_parent_ops = &amdvi_msi_parent_ops;
-
 	return 0;
 }
-
-int amd_iommu_update_ga(int cpu, bool is_run, void *data)
-{
-	struct amd_ir_data *ir_data = (struct amd_ir_data *)data;
-	struct irte_ga *entry = (struct irte_ga *) ir_data->entry;
-
-	if (!AMD_IOMMU_GUEST_IR_VAPIC(amd_iommu_guest_ir) ||
-	    !entry || !entry->lo.fields_vapic.guest_mode)
-		return 0;
-
-	if (!ir_data->iommu)
-		return -ENODEV;
-
-	if (cpu >= 0) {
-		entry->lo.fields_vapic.destination =
-					APICID_TO_IRTE_DEST_LO(cpu);
-		entry->hi.fields.destination =
-					APICID_TO_IRTE_DEST_HI(cpu);
-	}
-	entry->lo.fields_vapic.is_run = is_run;
-
-	return __modify_irte_ga(ir_data->iommu, ir_data->irq_2_irte.devid,
-				ir_data->irq_2_irte.index, entry);
-}
-EXPORT_SYMBOL(amd_iommu_update_ga);
 #endif