Enable support of Intel DMAR device hotplug

index c5c61cabd6e3..586dd2aa2ca2 100644
@@ -44,6 +44,14 @@
 
 #include "irq_remapping.h"
 
+typedef int (*dmar_res_handler_t)(struct acpi_dmar_header *, void *);
+struct dmar_res_callback {
+	dmar_res_handler_t	cb[ACPI_DMAR_TYPE_RESERVED];
+	void			*arg[ACPI_DMAR_TYPE_RESERVED];
+	bool			ignore_unhandled;
+	bool			print_entry;
+};
+
 /*
  * Assumptions:
  * 1) The hotplug framework guarentees that DMAR unit will be hot-added

@@ -350,7 +358,7 @@ static struct notifier_block dmar_pci_bus_nb = {
  * present in the platform
  */
 static int __init
-dmar_parse_one_drhd(struct acpi_dmar_header *header)
+dmar_parse_one_drhd(struct acpi_dmar_header *header, void *arg)
 {
 	struct acpi_dmar_hardware_unit *drhd;
 	struct dmar_drhd_unit *dmaru;

@@ -381,6 +389,10 @@ dmar_parse_one_drhd(struct acpi_dmar_header *header)
 		return ret;
 	}
 	dmar_register_drhd_unit(dmaru);
+
+	if (arg)
+		(*(int *)arg)++;
+
 	return 0;
 }
 

@@ -393,7 +405,8 @@ static void dmar_free_drhd(struct dmar_drhd_unit *dmaru)
 	kfree(dmaru);
 }
 
-static int __init dmar_parse_one_andd(struct acpi_dmar_header *header)
+static int __init dmar_parse_one_andd(struct acpi_dmar_header *header,
+				      void *arg)
 {
 	struct acpi_dmar_andd *andd = (void *)header;
 

@@ -415,7 +428,7 @@ static int __init dmar_parse_one_andd(struct acpi_dmar_header *header)
 
 #ifdef CONFIG_ACPI_NUMA
 static int __init
-dmar_parse_one_rhsa(struct acpi_dmar_header *header)
+dmar_parse_one_rhsa(struct acpi_dmar_header *header, void *arg)
 {
 	struct acpi_dmar_rhsa *rhsa;
 	struct dmar_drhd_unit *drhd;

@@ -442,6 +455,8 @@ dmar_parse_one_rhsa(struct acpi_dmar_header *header)
 
 	return 0;
 }
+#else
+#define	dmar_parse_one_rhsa		dmar_res_noop
 #endif
 
 static void __init

@@ -503,6 +518,52 @@ static int __init dmar_table_detect(void)
 	return (ACPI_SUCCESS(status) ? 1 : 0);
 }
 
+static int dmar_walk_remapping_entries(struct acpi_dmar_header *start,
+				       size_t len, struct dmar_res_callback *cb)
+{
+	int ret = 0;
+	struct acpi_dmar_header *iter, *next;
+	struct acpi_dmar_header *end = ((void *)start) + len;
+
+	for (iter = start; iter < end && ret == 0; iter = next) {
+		next = (void *)iter + iter->length;
+		if (iter->length == 0) {
+			/* Avoid looping forever on bad ACPI tables */
+			pr_debug(FW_BUG "Invalid 0-length structure\n");
+			break;
+		} else if (next > end) {
+			/* Avoid passing table end */
+			pr_warn(FW_BUG "record passes table end\n");
+			ret = -EINVAL;
+			break;
+		}
+
+		if (cb->print_entry)
+			dmar_table_print_dmar_entry(iter);
+
+		if (iter->type >= ACPI_DMAR_TYPE_RESERVED) {
+			/* continue for forward compatibility */
+			pr_debug("Unknown DMAR structure type %d\n",
+				 iter->type);
+		} else if (cb->cb[iter->type]) {
+			ret = cb->cb[iter->type](iter, cb->arg[iter->type]);
+		} else if (!cb->ignore_unhandled) {
+			pr_warn("No handler for DMAR structure type %d\n",
+				iter->type);
+			ret = -EINVAL;
+		}
+	}
+
+	return ret;
+}
+
+static inline int dmar_walk_dmar_table(struct acpi_table_dmar *dmar,
+				       struct dmar_res_callback *cb)
+{
+	return dmar_walk_remapping_entries((void *)(dmar + 1),
+			dmar->header.length - sizeof(*dmar), cb);
+}
+
 /**
  * parse_dmar_table - parses the DMA reporting table
  */

@@ -510,9 +571,18 @@ static int __init
 parse_dmar_table(void)
 {
 	struct acpi_table_dmar *dmar;
-	struct acpi_dmar_header *entry_header;
 	int ret = 0;
 	int drhd_count = 0;
+	struct dmar_res_callback cb = {
+		.print_entry = true,
+		.ignore_unhandled = true,
+		.arg[ACPI_DMAR_TYPE_HARDWARE_UNIT] = &drhd_count,
+		.cb[ACPI_DMAR_TYPE_HARDWARE_UNIT] = &dmar_parse_one_drhd,
+		.cb[ACPI_DMAR_TYPE_RESERVED_MEMORY] = &dmar_parse_one_rmrr,
+		.cb[ACPI_DMAR_TYPE_ROOT_ATS] = &dmar_parse_one_atsr,
+		.cb[ACPI_DMAR_TYPE_HARDWARE_AFFINITY] = &dmar_parse_one_rhsa,
+		.cb[ACPI_DMAR_TYPE_NAMESPACE] = &dmar_parse_one_andd,
+	};
 
 	/*
 	 * Do it again, earlier dmar_tbl mapping could be mapped with

@@ -536,51 +606,10 @@ parse_dmar_table(void)
 	}
 
 	pr_info("Host address width %d\n", dmar->width + 1);
-
-	entry_header = (struct acpi_dmar_header *)(dmar + 1);
-	while (((unsigned long)entry_header) <
-			(((unsigned long)dmar) + dmar_tbl->length)) {
-		/* Avoid looping forever on bad ACPI tables */
-		if (entry_header->length == 0) {
-			pr_warn("Invalid 0-length structure\n");
-			ret = -EINVAL;
-			break;
-		}
-
-		dmar_table_print_dmar_entry(entry_header);
-
-		switch (entry_header->type) {
-		case ACPI_DMAR_TYPE_HARDWARE_UNIT:
-			drhd_count++;
-			ret = dmar_parse_one_drhd(entry_header);
-			break;
-		case ACPI_DMAR_TYPE_RESERVED_MEMORY:
-			ret = dmar_parse_one_rmrr(entry_header);
-			break;
-		case ACPI_DMAR_TYPE_ROOT_ATS:
-			ret = dmar_parse_one_atsr(entry_header);
-			break;
-		case ACPI_DMAR_TYPE_HARDWARE_AFFINITY:
-#ifdef CONFIG_ACPI_NUMA
-			ret = dmar_parse_one_rhsa(entry_header);
-#endif
-			break;
-		case ACPI_DMAR_TYPE_NAMESPACE:
-			ret = dmar_parse_one_andd(entry_header);
-			break;
-		default:
-			pr_warn("Unknown DMAR structure type %d\n",
-				entry_header->type);
-			ret = 0; /* for forward compatibility */
-			break;
-		}
-		if (ret)
-			break;
-
-		entry_header = ((void *)entry_header + entry_header->length);
-	}
-	if (drhd_count == 0)
+	ret = dmar_walk_dmar_table(dmar, &cb);
+	if (ret == 0 && drhd_count == 0)
 		pr_warn(FW_BUG "No DRHD structure found in DMAR table\n");
+
 	return ret;
 }
 

@@ -778,76 +807,60 @@ static void warn_invalid_dmar(u64 addr, const char *message)
 		dmi_get_system_info(DMI_PRODUCT_VERSION));
 }
 
-static int __init check_zero_address(void)
+static int __ref
+dmar_validate_one_drhd(struct acpi_dmar_header *entry, void *arg)
 {
-	struct acpi_table_dmar *dmar;
-	struct acpi_dmar_header *entry_header;
 	struct acpi_dmar_hardware_unit *drhd;
+	void __iomem *addr;
+	u64 cap, ecap;
 
-	dmar = (struct acpi_table_dmar *)dmar_tbl;
-	entry_header = (struct acpi_dmar_header *)(dmar + 1);
-
-	while (((unsigned long)entry_header) <
-			(((unsigned long)dmar) + dmar_tbl->length)) {
-		/* Avoid looping forever on bad ACPI tables */
-		if (entry_header->length == 0) {
-			pr_warn("Invalid 0-length structure\n");
-			return 0;
-		}
-
-		if (entry_header->type == ACPI_DMAR_TYPE_HARDWARE_UNIT) {
-			void __iomem *addr;
-			u64 cap, ecap;
-
-			drhd = (void *)entry_header;
-			if (!drhd->address) {
-				warn_invalid_dmar(0, "");
-				goto failed;
-			}
+	drhd = (void *)entry;
+	if (!drhd->address) {
+		warn_invalid_dmar(0, "");
+		return -EINVAL;
+	}
 
-			addr = early_ioremap(drhd->address, VTD_PAGE_SIZE);
-			if (!addr ) {
-				printk("IOMMU: can't validate: %llx\n", drhd->address);
-				goto failed;
-			}
-			cap = dmar_readq(addr + DMAR_CAP_REG);
-			ecap = dmar_readq(addr + DMAR_ECAP_REG);
-			early_iounmap(addr, VTD_PAGE_SIZE);
-			if (cap == (uint64_t)-1 && ecap == (uint64_t)-1) {
-				warn_invalid_dmar(drhd->address,
-						  " returns all ones");
-				goto failed;
-			}
-		}
+	addr = early_ioremap(drhd->address, VTD_PAGE_SIZE);
+	if (!addr) {
+		pr_warn("IOMMU: can't validate: %llx\n", drhd->address);
+		return -EINVAL;
+	}
+	cap = dmar_readq(addr + DMAR_CAP_REG);
+	ecap = dmar_readq(addr + DMAR_ECAP_REG);
+	early_iounmap(addr, VTD_PAGE_SIZE);
 
-		entry_header = ((void *)entry_header + entry_header->length);
+	if (cap == (uint64_t)-1 && ecap == (uint64_t)-1) {
+		warn_invalid_dmar(drhd->address, " returns all ones");
+		return -EINVAL;
 	}
-	return 1;
 
-failed:
 	return 0;
 }
 
 int __init detect_intel_iommu(void)
 {
 	int ret;
+	struct dmar_res_callback validate_drhd_cb = {
+		.cb[ACPI_DMAR_TYPE_HARDWARE_UNIT] = &dmar_validate_one_drhd,
+		.ignore_unhandled = true,
+	};
 
 	down_write(&dmar_global_lock);
 	ret = dmar_table_detect();
 	if (ret)
-		ret = check_zero_address();
-	{
-		if (ret && !no_iommu && !iommu_detected && !dmar_disabled) {
-			iommu_detected = 1;
-			/* Make sure ACS will be enabled */
-			pci_request_acs();
-		}
+		ret = !dmar_walk_dmar_table((struct acpi_table_dmar *)dmar_tbl,
+					    &validate_drhd_cb);
+	if (ret && !no_iommu && !iommu_detected && !dmar_disabled) {
+		iommu_detected = 1;
+		/* Make sure ACS will be enabled */
+		pci_request_acs();
+	}
 
 #ifdef CONFIG_X86
-		if (ret)
-			x86_init.iommu.iommu_init = intel_iommu_init;
+	if (ret)
+		x86_init.iommu.iommu_init = intel_iommu_init;
 #endif
-	}
+
 	early_acpi_os_unmap_memory((void __iomem *)dmar_tbl, dmar_tbl_size);
 	dmar_tbl = NULL;
 	up_write(&dmar_global_lock);

index a27d6cb1a793..041f6e727337 100644
@@ -3682,7 +3682,7 @@ static inline void init_iommu_pm_ops(void) {}
 #endif	/* CONFIG_PM */
 
 
-int __init dmar_parse_one_rmrr(struct acpi_dmar_header *header)
+int __init dmar_parse_one_rmrr(struct acpi_dmar_header *header, void *arg)
 {
 	struct acpi_dmar_reserved_memory *rmrr;
 	struct dmar_rmrr_unit *rmrru;

@@ -3708,7 +3708,7 @@ int __init dmar_parse_one_rmrr(struct acpi_dmar_header *header)
 	return 0;
 }
 
-int __init dmar_parse_one_atsr(struct acpi_dmar_header *hdr)
+int __init dmar_parse_one_atsr(struct acpi_dmar_header *hdr, void *arg)
 {
 	struct acpi_dmar_atsr *atsr;
 	struct dmar_atsr_unit *atsru;

index 593fff99e6bf..495df5e48f80 100644
@@ -121,22 +121,21 @@ extern int dmar_remove_dev_scope(struct dmar_pci_notify_info *info,
 extern int detect_intel_iommu(void);
 extern int enable_drhd_fault_handling(void);
 
+static inline int dmar_res_noop(struct acpi_dmar_header *hdr, void *arg)
+{
+	return 0;
+}
+
 #ifdef CONFIG_INTEL_IOMMU
 extern int iommu_detected, no_iommu;
 extern int intel_iommu_init(void);
-extern int dmar_parse_one_rmrr(struct acpi_dmar_header *header);
-extern int dmar_parse_one_atsr(struct acpi_dmar_header *header);
+extern int dmar_parse_one_rmrr(struct acpi_dmar_header *header, void *arg);
+extern int dmar_parse_one_atsr(struct acpi_dmar_header *header, void *arg);
 extern int dmar_iommu_notify_scope_dev(struct dmar_pci_notify_info *info);
 #else /* !CONFIG_INTEL_IOMMU: */
 static inline int intel_iommu_init(void) { return -ENODEV; }
-static inline int dmar_parse_one_rmrr(struct acpi_dmar_header *header)
-{
-	return 0;
-}
-static inline int dmar_parse_one_atsr(struct acpi_dmar_header *header)
-{
-	return 0;
-}
+#define	dmar_parse_one_rmrr		dmar_res_noop
+#define	dmar_parse_one_atsr		dmar_res_noop
 static inline int dmar_iommu_notify_scope_dev(struct dmar_pci_notify_info *info)
 {
 	return 0;

index 586dd2aa2ca2..78aa1b2af113 100644
@@ -70,6 +70,7 @@ LIST_HEAD(dmar_drhd_units);
 struct acpi_table_header * __initdata dmar_tbl;
 static acpi_size dmar_tbl_size;
 static int dmar_dev_scope_status = 1;
+static unsigned long dmar_seq_ids[BITS_TO_LONGS(DMAR_UNITS_SUPPORTED)];
 
 static int alloc_iommu(struct dmar_drhd_unit *drhd);
 static void free_iommu(struct intel_iommu *iommu);

@@ -944,11 +945,32 @@ out:
 	return err;
 }
 
+static int dmar_alloc_seq_id(struct intel_iommu *iommu)
+{
+	iommu->seq_id = find_first_zero_bit(dmar_seq_ids,
+					    DMAR_UNITS_SUPPORTED);
+	if (iommu->seq_id >= DMAR_UNITS_SUPPORTED) {
+		iommu->seq_id = -1;
+	} else {
+		set_bit(iommu->seq_id, dmar_seq_ids);
+		sprintf(iommu->name, "dmar%d", iommu->seq_id);
+	}
+
+	return iommu->seq_id;
+}
+
+static void dmar_free_seq_id(struct intel_iommu *iommu)
+{
+	if (iommu->seq_id >= 0) {
+		clear_bit(iommu->seq_id, dmar_seq_ids);
+		iommu->seq_id = -1;
+	}
+}
+
 static int alloc_iommu(struct dmar_drhd_unit *drhd)
 {
 	struct intel_iommu *iommu;
 	u32 ver, sts;
-	static int iommu_allocated = 0;
 	int agaw = 0;
 	int msagaw = 0;
 	int err;

@@ -962,13 +984,16 @@ static int alloc_iommu(struct dmar_drhd_unit *drhd)
 	if (!iommu)
 		return -ENOMEM;
 
-	iommu->seq_id = iommu_allocated++;
-	sprintf (iommu->name, "dmar%d", iommu->seq_id);
+	if (dmar_alloc_seq_id(iommu) < 0) {
+		pr_err("IOMMU: failed to allocate seq_id\n");
+		err = -ENOSPC;
+		goto error;
+	}
 
 	err = map_iommu(iommu, drhd->reg_base_addr);
 	if (err) {
 		pr_err("IOMMU: failed to map %s\n", iommu->name);
-		goto error;
+		goto error_free_seq_id;
 	}
 
 	err = -EINVAL;

@@ -1018,9 +1043,11 @@ static int alloc_iommu(struct dmar_drhd_unit *drhd)
 
 	return 0;
 
- err_unmap:
+err_unmap:
 	unmap_iommu(iommu);
- error:
+error_free_seq_id:
+	dmar_free_seq_id(iommu);
+error:
 	kfree(iommu);
 	return err;
 }

@@ -1044,6 +1071,7 @@ static void free_iommu(struct intel_iommu *iommu)
 	if (iommu->reg)
 		unmap_iommu(iommu);
 
+	dmar_free_seq_id(iommu);
 	kfree(iommu);
 }
 

index 041f6e727337..39870414f657 100644
@@ -328,17 +328,10 @@ static int hw_pass_through = 1;
 /* si_domain contains mulitple devices */
 #define DOMAIN_FLAG_STATIC_IDENTITY	(1 << 1)
 
-/* define the limit of IOMMUs supported in each domain */
-#ifdef	CONFIG_X86
-# define	IOMMU_UNITS_SUPPORTED	MAX_IO_APICS
-#else
-# define	IOMMU_UNITS_SUPPORTED	64
-#endif
-
 struct dmar_domain {
 	int	id;			/* domain id */
 	int	nid;			/* node id */
-	DECLARE_BITMAP(iommu_bmp, IOMMU_UNITS_SUPPORTED);
+	DECLARE_BITMAP(iommu_bmp, DMAR_UNITS_SUPPORTED);
 					/* bitmap of iommus this domain uses*/
 
 	struct list_head devices; 	/* all devices' list */

@@ -2728,12 +2721,12 @@ static int __init init_dmars(void)
 		 * threaded kernel __init code path all other access are read
 		 * only
 		 */
-		if (g_num_of_iommus < IOMMU_UNITS_SUPPORTED) {
+		if (g_num_of_iommus < DMAR_UNITS_SUPPORTED) {
 			g_num_of_iommus++;
 			continue;
 		}
 		printk_once(KERN_ERR "intel-iommu: exceeded %d IOMMUs\n",
-			  IOMMU_UNITS_SUPPORTED);
+			  DMAR_UNITS_SUPPORTED);
 	}
 
 	g_iommus = kcalloc(g_num_of_iommus, sizeof(struct intel_iommu *),

index 495df5e48f80..725204fc433e 100644
@@ -30,6 +30,12 @@
 
 struct acpi_dmar_header;
 
+#ifdef	CONFIG_X86
+# define	DMAR_UNITS_SUPPORTED	MAX_IO_APICS
+#else
+# define	DMAR_UNITS_SUPPORTED	64
+#endif
+
 /* DMAR Flags */
 #define DMAR_INTR_REMAP		0x1
 #define DMAR_X2APIC_OPT_OUT	0x2

index 78aa1b2af113..0bd536d769a9 100644
@@ -75,7 +75,7 @@ static unsigned long dmar_seq_ids[BITS_TO_LONGS(DMAR_UNITS_SUPPORTED)];
 static int alloc_iommu(struct dmar_drhd_unit *drhd);
 static void free_iommu(struct intel_iommu *iommu);
 
-static void __init dmar_register_drhd_unit(struct dmar_drhd_unit *drhd)
+static void dmar_register_drhd_unit(struct dmar_drhd_unit *drhd)
 {
 	/*
 	 * add INCLUDE_ALL at the tail, so scan the list will find it at

@@ -353,24 +353,45 @@ static struct notifier_block dmar_pci_bus_nb = {
 	.priority = INT_MIN,
 };
 
+static struct dmar_drhd_unit *
+dmar_find_dmaru(struct acpi_dmar_hardware_unit *drhd)
+{
+	struct dmar_drhd_unit *dmaru;
+
+	list_for_each_entry_rcu(dmaru, &dmar_drhd_units, list)
+		if (dmaru->segment == drhd->segment &&
+		    dmaru->reg_base_addr == drhd->address)
+			return dmaru;
+
+	return NULL;
+}
+
 /**
  * dmar_parse_one_drhd - parses exactly one DMA remapping hardware definition
  * structure which uniquely represent one DMA remapping hardware unit
  * present in the platform
  */
-static int __init
-dmar_parse_one_drhd(struct acpi_dmar_header *header, void *arg)
+static int dmar_parse_one_drhd(struct acpi_dmar_header *header, void *arg)
 {
 	struct acpi_dmar_hardware_unit *drhd;
 	struct dmar_drhd_unit *dmaru;
 	int ret = 0;
 
 	drhd = (struct acpi_dmar_hardware_unit *)header;
-	dmaru = kzalloc(sizeof(*dmaru), GFP_KERNEL);
+	dmaru = dmar_find_dmaru(drhd);
+	if (dmaru)
+		goto out;
+
+	dmaru = kzalloc(sizeof(*dmaru) + header->length, GFP_KERNEL);
 	if (!dmaru)
 		return -ENOMEM;
 
-	dmaru->hdr = header;
+	/*
+	 * If header is allocated from slab by ACPI _DSM method, we need to
+	 * copy the content because the memory buffer will be freed on return.
+	 */
+	dmaru->hdr = (void *)(dmaru + 1);
+	memcpy(dmaru->hdr, header, header->length);
 	dmaru->reg_base_addr = drhd->address;
 	dmaru->segment = drhd->segment;
 	dmaru->include_all = drhd->flags & 0x1; /* BIT0: INCLUDE_ALL */

@@ -391,6 +412,7 @@ dmar_parse_one_drhd(struct acpi_dmar_header *header, void *arg)
 	}
 	dmar_register_drhd_unit(dmaru);
 
+out:
 	if (arg)
 		(*(int *)arg)++;
 

@@ -428,8 +450,7 @@ static int __init dmar_parse_one_andd(struct acpi_dmar_header *header,
 }
 
 #ifdef CONFIG_ACPI_NUMA
-static int __init
-dmar_parse_one_rhsa(struct acpi_dmar_header *header, void *arg)
+static int dmar_parse_one_rhsa(struct acpi_dmar_header *header, void *arg)
 {
 	struct acpi_dmar_rhsa *rhsa;
 	struct dmar_drhd_unit *drhd;

@@ -821,14 +842,22 @@ dmar_validate_one_drhd(struct acpi_dmar_header *entry, void *arg)
 		return -EINVAL;
 	}
 
-	addr = early_ioremap(drhd->address, VTD_PAGE_SIZE);
+	if (arg)
+		addr = ioremap(drhd->address, VTD_PAGE_SIZE);
+	else
+		addr = early_ioremap(drhd->address, VTD_PAGE_SIZE);
 	if (!addr) {
 		pr_warn("IOMMU: can't validate: %llx\n", drhd->address);
 		return -EINVAL;
 	}
+
 	cap = dmar_readq(addr + DMAR_CAP_REG);
 	ecap = dmar_readq(addr + DMAR_ECAP_REG);
-	early_iounmap(addr, VTD_PAGE_SIZE);
+
+	if (arg)
+		iounmap(addr);
+	else
+		early_iounmap(addr, VTD_PAGE_SIZE);
 
 	if (cap == (uint64_t)-1 && ecap == (uint64_t)-1) {
 		warn_invalid_dmar(drhd->address, " returns all ones");

@@ -1702,12 +1731,17 @@ int __init dmar_ir_support(void)
 	return dmar->flags & 0x1;
 }
 
+/* Check whether DMAR units are in use */
+static inline bool dmar_in_use(void)
+{
+	return irq_remapping_enabled || intel_iommu_enabled;
+}
+
 static int __init dmar_free_unused_resources(void)
 {
 	struct dmar_drhd_unit *dmaru, *dmaru_n;
 
-	/* DMAR units are in use */
-	if (irq_remapping_enabled || intel_iommu_enabled)
+	if (dmar_in_use())
 		return 0;
 
 	if (dmar_dev_scope_status != 1 && !list_empty(&dmar_drhd_units))

@@ -1725,3 +1759,215 @@ static int __init dmar_free_unused_resources(void)
 
 late_initcall(dmar_free_unused_resources);
 IOMMU_INIT_POST(detect_intel_iommu);
+
+/*
+ * DMAR Hotplug Support
+ * For more details, please refer to Intel(R) Virtualization Technology
+ * for Directed-IO Architecture Specifiction, Rev 2.2, Section 8.8
+ * "Remapping Hardware Unit Hot Plug".
+ */
+static u8 dmar_hp_uuid[] = {
+	/* 0000 */    0xA6, 0xA3, 0xC1, 0xD8, 0x9B, 0xBE, 0x9B, 0x4C,
+	/* 0008 */    0x91, 0xBF, 0xC3, 0xCB, 0x81, 0xFC, 0x5D, 0xAF
+};
+
+/*
+ * Currently there's only one revision and BIOS will not check the revision id,
+ * so use 0 for safety.
+ */
+#define	DMAR_DSM_REV_ID			0
+#define	DMAR_DSM_FUNC_DRHD		1
+#define	DMAR_DSM_FUNC_ATSR		2
+#define	DMAR_DSM_FUNC_RHSA		3
+
+static inline bool dmar_detect_dsm(acpi_handle handle, int func)
+{
+	return acpi_check_dsm(handle, dmar_hp_uuid, DMAR_DSM_REV_ID, 1 << func);
+}
+
+static int dmar_walk_dsm_resource(acpi_handle handle, int func,
+				  dmar_res_handler_t handler, void *arg)
+{
+	int ret = -ENODEV;
+	union acpi_object *obj;
+	struct acpi_dmar_header *start;
+	struct dmar_res_callback callback;
+	static int res_type[] = {
+		[DMAR_DSM_FUNC_DRHD] = ACPI_DMAR_TYPE_HARDWARE_UNIT,
+		[DMAR_DSM_FUNC_ATSR] = ACPI_DMAR_TYPE_ROOT_ATS,
+		[DMAR_DSM_FUNC_RHSA] = ACPI_DMAR_TYPE_HARDWARE_AFFINITY,
+	};
+
+	if (!dmar_detect_dsm(handle, func))
+		return 0;
+
+	obj = acpi_evaluate_dsm_typed(handle, dmar_hp_uuid, DMAR_DSM_REV_ID,
+				      func, NULL, ACPI_TYPE_BUFFER);
+	if (!obj)
+		return -ENODEV;
+
+	memset(&callback, 0, sizeof(callback));
+	callback.cb[res_type[func]] = handler;
+	callback.arg[res_type[func]] = arg;
+	start = (struct acpi_dmar_header *)obj->buffer.pointer;
+	ret = dmar_walk_remapping_entries(start, obj->buffer.length, &callback);
+
+	ACPI_FREE(obj);
+
+	return ret;
+}
+
+static int dmar_hp_add_drhd(struct acpi_dmar_header *header, void *arg)
+{
+	int ret;
+	struct dmar_drhd_unit *dmaru;
+
+	dmaru = dmar_find_dmaru((struct acpi_dmar_hardware_unit *)header);
+	if (!dmaru)
+		return -ENODEV;
+
+	ret = dmar_ir_hotplug(dmaru, true);
+	if (ret == 0)
+		ret = dmar_iommu_hotplug(dmaru, true);
+
+	return ret;
+}
+
+static int dmar_hp_remove_drhd(struct acpi_dmar_header *header, void *arg)
+{
+	int i, ret;
+	struct device *dev;
+	struct dmar_drhd_unit *dmaru;
+
+	dmaru = dmar_find_dmaru((struct acpi_dmar_hardware_unit *)header);
+	if (!dmaru)
+		return 0;
+
+	/*
+	 * All PCI devices managed by this unit should have been destroyed.
+	 */
+	if (!dmaru->include_all && dmaru->devices && dmaru->devices_cnt)
+		for_each_active_dev_scope(dmaru->devices,
+					  dmaru->devices_cnt, i, dev)
+			return -EBUSY;
+
+	ret = dmar_ir_hotplug(dmaru, false);
+	if (ret == 0)
+		ret = dmar_iommu_hotplug(dmaru, false);
+
+	return ret;
+}
+
+static int dmar_hp_release_drhd(struct acpi_dmar_header *header, void *arg)
+{
+	struct dmar_drhd_unit *dmaru;
+
+	dmaru = dmar_find_dmaru((struct acpi_dmar_hardware_unit *)header);
+	if (dmaru) {
+		list_del_rcu(&dmaru->list);
+		synchronize_rcu();
+		dmar_free_drhd(dmaru);
+	}
+
+	return 0;
+}
+
+static int dmar_hotplug_insert(acpi_handle handle)
+{
+	int ret;
+	int drhd_count = 0;
+
+	ret = dmar_walk_dsm_resource(handle, DMAR_DSM_FUNC_DRHD,
+				     &dmar_validate_one_drhd, (void *)1);
+	if (ret)
+		goto out;
+
+	ret = dmar_walk_dsm_resource(handle, DMAR_DSM_FUNC_DRHD,
+				     &dmar_parse_one_drhd, (void *)&drhd_count);
+	if (ret == 0 && drhd_count == 0) {
+		pr_warn(FW_BUG "No DRHD structures in buffer returned by _DSM method\n");
+		goto out;
+	} else if (ret) {
+		goto release_drhd;
+	}
+
+	ret = dmar_walk_dsm_resource(handle, DMAR_DSM_FUNC_RHSA,
+				     &dmar_parse_one_rhsa, NULL);
+	if (ret)
+		goto release_drhd;
+
+	ret = dmar_walk_dsm_resource(handle, DMAR_DSM_FUNC_ATSR,
+				     &dmar_parse_one_atsr, NULL);
+	if (ret)
+		goto release_atsr;
+
+	ret = dmar_walk_dsm_resource(handle, DMAR_DSM_FUNC_DRHD,
+				     &dmar_hp_add_drhd, NULL);
+	if (!ret)
+		return 0;
+
+	dmar_walk_dsm_resource(handle, DMAR_DSM_FUNC_DRHD,
+			       &dmar_hp_remove_drhd, NULL);
+release_atsr:
+	dmar_walk_dsm_resource(handle, DMAR_DSM_FUNC_ATSR,
+			       &dmar_release_one_atsr, NULL);
+release_drhd:
+	dmar_walk_dsm_resource(handle, DMAR_DSM_FUNC_DRHD,
+			       &dmar_hp_release_drhd, NULL);
+out:
+	return ret;
+}
+
+static int dmar_hotplug_remove(acpi_handle handle)
+{
+	int ret;
+
+	ret = dmar_walk_dsm_resource(handle, DMAR_DSM_FUNC_ATSR,
+				     &dmar_check_one_atsr, NULL);
+	if (ret)
+		return ret;
+
+	ret = dmar_walk_dsm_resource(handle, DMAR_DSM_FUNC_DRHD,
+				     &dmar_hp_remove_drhd, NULL);
+	if (ret == 0) {
+		WARN_ON(dmar_walk_dsm_resource(handle, DMAR_DSM_FUNC_ATSR,
+					       &dmar_release_one_atsr, NULL));
+		WARN_ON(dmar_walk_dsm_resource(handle, DMAR_DSM_FUNC_DRHD,
+					       &dmar_hp_release_drhd, NULL));
+	} else {
+		dmar_walk_dsm_resource(handle, DMAR_DSM_FUNC_DRHD,
+				       &dmar_hp_add_drhd, NULL);
+	}
+
+	return ret;
+}
+
+static int dmar_device_hotplug(acpi_handle handle, bool insert)
+{
+	int ret;
+
+	if (!dmar_in_use())
+		return 0;
+
+	if (!dmar_detect_dsm(handle, DMAR_DSM_FUNC_DRHD))
+		return 0;
+
+	down_write(&dmar_global_lock);
+	if (insert)
+		ret = dmar_hotplug_insert(handle);
+	else
+		ret = dmar_hotplug_remove(handle);
+	up_write(&dmar_global_lock);
+
+	return ret;
+}
+
+int dmar_device_add(acpi_handle handle)
+{
+	return dmar_device_hotplug(handle, true);
+}
+
+int dmar_device_remove(acpi_handle handle)
+{
+	return dmar_device_hotplug(handle, false);
+}

98 lines not on this page · raw message

index 7c80661b35c1..1cbdb509bc7b 100644
@@ -1171,3 +1171,8 @@ struct irq_remap_ops intel_irq_remap_ops = {
 	.msi_setup_irq		= intel_msi_setup_irq,
 	.alloc_hpet_msi		= intel_alloc_hpet_msi,
 };
+
+int dmar_ir_hotplug(struct dmar_drhd_unit *dmaru, bool insert)
+{
+	return irq_remapping_enabled ? -ENOSYS : 0;
+}

index 725204fc433e..30624954dec5 100644
@@ -126,6 +126,8 @@ extern int dmar_remove_dev_scope(struct dmar_pci_notify_info *info,
 /* Intel IOMMU detection */
 extern int detect_intel_iommu(void);
 extern int enable_drhd_fault_handling(void);
+extern int dmar_device_add(acpi_handle handle);
+extern int dmar_device_remove(acpi_handle handle);
 
 static inline int dmar_res_noop(struct acpi_dmar_header *hdr, void *arg)
 {

@@ -137,17 +139,48 @@ extern int iommu_detected, no_iommu;
 extern int intel_iommu_init(void);
 extern int dmar_parse_one_rmrr(struct acpi_dmar_header *header, void *arg);
 extern int dmar_parse_one_atsr(struct acpi_dmar_header *header, void *arg);
+extern int dmar_check_one_atsr(struct acpi_dmar_header *hdr, void *arg);
+extern int dmar_release_one_atsr(struct acpi_dmar_header *hdr, void *arg);
+extern int dmar_iommu_hotplug(struct dmar_drhd_unit *dmaru, bool insert);
 extern int dmar_iommu_notify_scope_dev(struct dmar_pci_notify_info *info);
 #else /* !CONFIG_INTEL_IOMMU: */
 static inline int intel_iommu_init(void) { return -ENODEV; }
+
 #define	dmar_parse_one_rmrr		dmar_res_noop
 #define	dmar_parse_one_atsr		dmar_res_noop
+#define	dmar_check_one_atsr		dmar_res_noop
+#define	dmar_release_one_atsr		dmar_res_noop
+
 static inline int dmar_iommu_notify_scope_dev(struct dmar_pci_notify_info *info)
 {
 	return 0;
 }
+
+static inline int dmar_iommu_hotplug(struct dmar_drhd_unit *dmaru, bool insert)
+{
+	return 0;
+}
 #endif /* CONFIG_INTEL_IOMMU */
 
+#ifdef CONFIG_IRQ_REMAP
+extern int dmar_ir_hotplug(struct dmar_drhd_unit *dmaru, bool insert);
+#else  /* CONFIG_IRQ_REMAP */
+static inline int dmar_ir_hotplug(struct dmar_drhd_unit *dmaru, bool insert)
+{ return 0; }
+#endif /* CONFIG_IRQ_REMAP */
+
+#else /* CONFIG_DMAR_TABLE */
+
+static inline int dmar_device_add(void *handle)
+{
+	return 0;
+}
+
+static inline int dmar_device_remove(void *handle)
+{
+	return 0;
+}
+
 #endif /* CONFIG_DMAR_TABLE */
 
 struct irte {

index 0bd536d769a9..9847613085e1 100644
@@ -1942,21 +1942,48 @@ static int dmar_hotplug_remove(acpi_handle handle)
 	return ret;
 }
 
+static acpi_status dmar_get_dsm_handle(acpi_handle handle, u32 lvl,
+				       void *context, void **retval)
+{
+	acpi_handle *phdl = retval;
+
+	if (dmar_detect_dsm(handle, DMAR_DSM_FUNC_DRHD)) {
+		*phdl = handle;
+		return AE_CTRL_TERMINATE;
+	}
+
+	return AE_OK;
+}
+
 static int dmar_device_hotplug(acpi_handle handle, bool insert)
 {
 	int ret;
+	acpi_handle tmp = NULL;
+	acpi_status status;
 
 	if (!dmar_in_use())
 		return 0;
 
-	if (!dmar_detect_dsm(handle, DMAR_DSM_FUNC_DRHD))
+	if (dmar_detect_dsm(handle, DMAR_DSM_FUNC_DRHD)) {
+		tmp = handle;
+	} else {
+		status = acpi_walk_namespace(ACPI_TYPE_DEVICE, handle,
+					     ACPI_UINT32_MAX,
+					     dmar_get_dsm_handle,
+					     NULL, NULL, &tmp);
+		if (ACPI_FAILURE(status)) {
+			pr_warn("Failed to locate _DSM method.\n");
+			return -ENXIO;
+		}
+	}
+	if (tmp == NULL)
 		return 0;
 
 	down_write(&dmar_global_lock);
 	if (insert)
-		ret = dmar_hotplug_insert(handle);
+		ret = dmar_hotplug_insert(tmp);
 	else
-		ret = dmar_hotplug_remove(handle);
+		ret = dmar_hotplug_remove(tmp);
 	up_write(&dmar_global_lock);
 
 	return ret;

index 1cbdb509bc7b..7af0b56dc2d1 100644
@@ -36,7 +36,6 @@ struct hpet_scope {
 
 static struct ioapic_scope ir_ioapic[MAX_IO_APICS];
 static struct hpet_scope ir_hpet[MAX_HPET_TBS];
-static int ir_ioapic_num, ir_hpet_num;
 
 /*
  * Lock ordering:

@@ -206,7 +205,7 @@ static struct intel_iommu *map_hpet_to_ir(u8 hpet_id)
 	int i;
 
 	for (i = 0; i < MAX_HPET_TBS; i++)
-		if (ir_hpet[i].id == hpet_id)
+		if (ir_hpet[i].id == hpet_id && ir_hpet[i].iommu)
 			return ir_hpet[i].iommu;
 	return NULL;
 }

@@ -216,7 +215,7 @@ static struct intel_iommu *map_ioapic_to_ir(int apic)
 	int i;
 
 	for (i = 0; i < MAX_IO_APICS; i++)
-		if (ir_ioapic[i].id == apic)
+		if (ir_ioapic[i].id == apic && ir_ioapic[i].iommu)
 			return ir_ioapic[i].iommu;
 	return NULL;
 }

@@ -325,7 +324,7 @@ static int set_ioapic_sid(struct irte *irte, int apic)
 
 	down_read(&dmar_global_lock);
 	for (i = 0; i < MAX_IO_APICS; i++) {
-		if (ir_ioapic[i].id == apic) {
+		if (ir_ioapic[i].iommu && ir_ioapic[i].id == apic) {
 			sid = (ir_ioapic[i].bus << 8) | ir_ioapic[i].devfn;
 			break;
 		}

@@ -352,7 +351,7 @@ static int set_hpet_sid(struct irte *irte, u8 id)
 
 	down_read(&dmar_global_lock);
 	for (i = 0; i < MAX_HPET_TBS; i++) {
-		if (ir_hpet[i].id == id) {
+		if (ir_hpet[i].iommu && ir_hpet[i].id == id) {
 			sid = (ir_hpet[i].bus << 8) | ir_hpet[i].devfn;
 			break;
 		}

@@ -473,17 +472,17 @@ static void iommu_set_irq_remapping(struct intel_iommu *iommu, int mode)
 	raw_spin_unlock_irqrestore(&iommu->register_lock, flags);
 }
 
-
-static int intel_setup_irq_remapping(struct intel_iommu *iommu, int mode)
+static int intel_setup_irq_remapping(struct intel_iommu *iommu)
 {
 	struct ir_table *ir_table;
 	struct page *pages;
 	unsigned long *bitmap;
 
-	ir_table = iommu->ir_table = kzalloc(sizeof(struct ir_table),
-					     GFP_ATOMIC);
+	if (iommu->ir_table)
+		return 0;
 
-	if (!iommu->ir_table)
+	ir_table = kzalloc(sizeof(struct ir_table), GFP_ATOMIC);
+	if (!ir_table)
 		return -ENOMEM;
 
 	pages = alloc_pages_node(iommu->node, GFP_ATOMIC | __GFP_ZERO,

@@ -492,24 +491,37 @@ static int intel_setup_irq_remapping(struct intel_iommu *iommu, int mode)
 	if (!pages) {
 		pr_err("IR%d: failed to allocate pages of order %d\n",
 		       iommu->seq_id, INTR_REMAP_PAGE_ORDER);
-		kfree(iommu->ir_table);
-		return -ENOMEM;
+		goto out_free_table;
 	}
 
 	bitmap = kcalloc(BITS_TO_LONGS(INTR_REMAP_TABLE_ENTRIES),
 			 sizeof(long), GFP_ATOMIC);
 	if (bitmap == NULL) {
 		pr_err("IR%d: failed to allocate bitmap\n", iommu->seq_id);
-		__free_pages(pages, INTR_REMAP_PAGE_ORDER);
-		kfree(ir_table);
-		return -ENOMEM;
+		goto out_free_pages;
 	}
 
 	ir_table->base = page_address(pages);
 	ir_table->bitmap = bitmap;
-
-	iommu_set_irq_remapping(iommu, mode);
+	iommu->ir_table = ir_table;
 	return 0;
+
+out_free_pages:
+	__free_pages(pages, INTR_REMAP_PAGE_ORDER);
+out_free_table:
+	kfree(ir_table);
+	return -ENOMEM;
+}
+
+static void intel_teardown_irq_remapping(struct intel_iommu *iommu)
+{
+	if (iommu && iommu->ir_table) {
+		free_pages((unsigned long)iommu->ir_table->base,
+			   INTR_REMAP_PAGE_ORDER);
+		kfree(iommu->ir_table->bitmap);
+		kfree(iommu->ir_table);
+		iommu->ir_table = NULL;
+	}
 }
 
 /*

@@ -666,9 +678,10 @@ static int __init intel_enable_irq_remapping(void)
 		if (!ecap_ir_support(iommu->ecap))
 			continue;
 
-		if (intel_setup_irq_remapping(iommu, eim))
+		if (intel_setup_irq_remapping(iommu))
 			goto error;
 
+		iommu_set_irq_remapping(iommu, eim);
 		setup = 1;
 	}
 

@@ -699,12 +712,13 @@ error:
 	return -1;
 }
 
-static void ir_parse_one_hpet_scope(struct acpi_dmar_device_scope *scope,
-				      struct intel_iommu *iommu)
+static int ir_parse_one_hpet_scope(struct acpi_dmar_device_scope *scope,
+				   struct intel_iommu *iommu,
+				   struct acpi_dmar_hardware_unit *drhd)
 {
 	struct acpi_dmar_pci_path *path;
 	u8 bus;
-	int count;
+	int count, free = -1;
 
 	bus = scope->bus;
 	path = (struct acpi_dmar_pci_path *)(scope + 1);

@@ -720,19 +734,36 @@ static void ir_parse_one_hpet_scope(struct acpi_dmar_device_scope *scope,
 					   PCI_SECONDARY_BUS);
 		path++;
 	}
-	ir_hpet[ir_hpet_num].bus   = bus;
-	ir_hpet[ir_hpet_num].devfn = PCI_DEVFN(path->device, path->function);
-	ir_hpet[ir_hpet_num].iommu = iommu;
-	ir_hpet[ir_hpet_num].id    = scope->enumeration_id;
-	ir_hpet_num++;
+
+	for (count = 0; count < MAX_HPET_TBS; count++) {
+		if (ir_hpet[count].iommu == iommu &&
+		    ir_hpet[count].id == scope->enumeration_id)
+			return 0;
+		else if (ir_hpet[count].iommu == NULL && free == -1)
+			free = count;
+	}
+	if (free == -1) {
+		pr_warn("Exceeded Max HPET blocks\n");
+		return -ENOSPC;
+	}
+
+	ir_hpet[free].iommu = iommu;
+	ir_hpet[free].id    = scope->enumeration_id;
+	ir_hpet[free].bus   = bus;
+	ir_hpet[free].devfn = PCI_DEVFN(path->device, path->function);
+	pr_info("HPET id %d under DRHD base 0x%Lx\n",
+		scope->enumeration_id, drhd->address);
+
+	return 0;
 }
 
-static void ir_parse_one_ioapic_scope(struct acpi_dmar_device_scope *scope,
-				      struct intel_iommu *iommu)
+static int ir_parse_one_ioapic_scope(struct acpi_dmar_device_scope *scope,
+				     struct intel_iommu *iommu,
+				     struct acpi_dmar_hardware_unit *drhd)
 {
 	struct acpi_dmar_pci_path *path;
 	u8 bus;
-	int count;
+	int count, free = -1;
 
 	bus = scope->bus;
 	path = (struct acpi_dmar_pci_path *)(scope + 1);

@@ -749,54 +780,63 @@ static void ir_parse_one_ioapic_scope(struct acpi_dmar_device_scope *scope,
 		path++;
 	}
 
-	ir_ioapic[ir_ioapic_num].bus   = bus;
-	ir_ioapic[ir_ioapic_num].devfn = PCI_DEVFN(path->device, path->function);
-	ir_ioapic[ir_ioapic_num].iommu = iommu;
-	ir_ioapic[ir_ioapic_num].id    = scope->enumeration_id;
-	ir_ioapic_num++;
+	for (count = 0; count < MAX_IO_APICS; count++) {
+		if (ir_ioapic[count].iommu == iommu &&
+		    ir_ioapic[count].id == scope->enumeration_id)
+			return 0;
+		else if (ir_ioapic[count].iommu == NULL && free == -1)
+			free = count;
+	}
+	if (free == -1) {
+		pr_warn("Exceeded Max IO APICS\n");
+		return -ENOSPC;
+	}
+
+	ir_ioapic[free].bus   = bus;
+	ir_ioapic[free].devfn = PCI_DEVFN(path->device, path->function);
+	ir_ioapic[free].iommu = iommu;
+	ir_ioapic[free].id    = scope->enumeration_id;
+	pr_info("IOAPIC id %d under DRHD base  0x%Lx IOMMU %d\n",
+		scope->enumeration_id, drhd->address, iommu->seq_id);
+
+	return 0;
 }
 
 static int ir_parse_ioapic_hpet_scope(struct acpi_dmar_header *header,
 				      struct intel_iommu *iommu)
 {
+	int ret = 0;
 	struct acpi_dmar_hardware_unit *drhd;
 	struct acpi_dmar_device_scope *scope;
 	void *start, *end;
 
 	drhd = (struct acpi_dmar_hardware_unit *)header;
-
 	start = (void *)(drhd + 1);
 	end = ((void *)drhd) + header->length;
 
-	while (start < end) {
+	while (start < end && ret == 0) {
 		scope = start;
-		if (scope->entry_type == ACPI_DMAR_SCOPE_TYPE_IOAPIC) {
-			if (ir_ioapic_num == MAX_IO_APICS) {
-				printk(KERN_WARNING "Exceeded Max IO APICS\n");
-				return -1;
-			}
-
-			printk(KERN_INFO "IOAPIC id %d under DRHD base "
-			       " 0x%Lx IOMMU %d\n", scope->enumeration_id,
-			       drhd->address, iommu->seq_id);
+		if (scope->entry_type == ACPI_DMAR_SCOPE_TYPE_IOAPIC)
+			ret = ir_parse_one_ioapic_scope(scope, iommu, drhd);
+		else if (scope->entry_type == ACPI_DMAR_SCOPE_TYPE_HPET)
+			ret = ir_parse_one_hpet_scope(scope, iommu, drhd);
+		start += scope->length;
+	}
 
-			ir_parse_one_ioapic_scope(scope, iommu);
-		} else if (scope->entry_type == ACPI_DMAR_SCOPE_TYPE_HPET) {
-			if (ir_hpet_num == MAX_HPET_TBS) {
-				printk(KERN_WARNING "Exceeded Max HPET blocks\n");
-				return -1;
-			}
+	return ret;
+}
 
-			printk(KERN_INFO "HPET id %d under DRHD base"
-			       " 0x%Lx\n", scope->enumeration_id,
-			       drhd->address);
+static void ir_remove_ioapic_hpet_scope(struct intel_iommu *iommu)
+{
+	int i;
 
-			ir_parse_one_hpet_scope(scope, iommu);
-		}
-		start += scope->length;
-	}
+	for (i = 0; i < MAX_HPET_TBS; i++)
+		if (ir_hpet[i].iommu == iommu)
+			ir_hpet[i].iommu = NULL;
 
-	return 0;
+	for (i = 0; i < MAX_IO_APICS; i++)
+		if (ir_ioapic[i].iommu == iommu)
+			ir_ioapic[i].iommu = NULL;
 }
 
 /*

@@ -1172,7 +1212,85 @@ struct irq_remap_ops intel_irq_remap_ops = {
 	.alloc_hpet_msi		= intel_alloc_hpet_msi,
 };
 
+/*
+ * Support of Interrupt Remapping Unit Hotplug
+ */
+static int dmar_ir_add(struct dmar_drhd_unit *dmaru, struct intel_iommu *iommu)
+{
+	int ret;
+	int eim = x2apic_enabled();
+
+	if (eim && !ecap_eim_support(iommu->ecap)) {
+		pr_info("DRHD %Lx: EIM not supported by DRHD, ecap %Lx\n",
+			iommu->reg_phys, iommu->ecap);
+		return -ENODEV;
+	}
+
+	if (ir_parse_ioapic_hpet_scope(dmaru->hdr, iommu)) {
+		pr_warn("DRHD %Lx: failed to parse managed IOAPIC/HPET\n",
+			iommu->reg_phys);
+		return -ENODEV;
+	}
+
+	/* TODO: check all IOAPICs are covered by IOMMU */
+
+	/* Setup Interrupt-remapping now. */
+	ret = intel_setup_irq_remapping(iommu);
+	if (ret) {
+		pr_err("DRHD %Lx: failed to allocate resource\n",
+		       iommu->reg_phys);
+		ir_remove_ioapic_hpet_scope(iommu);
+		return ret;
+	}
+
+	if (!iommu->qi) {
+		/* Clear previous faults. */
+		dmar_fault(-1, iommu);
+		iommu_disable_irq_remapping(iommu);
+		dmar_disable_qi(iommu);
+	}
+
+	/* Enable queued invalidation */
+	ret = dmar_enable_qi(iommu);
+	if (!ret) {
+		iommu_set_irq_remapping(iommu, eim);
+	} else {
+		pr_err("DRHD %Lx: failed to enable queued invalidation, ecap %Lx, ret %d\n",
+		       iommu->reg_phys, iommu->ecap, ret);
+		intel_teardown_irq_remapping(iommu);
+		ir_remove_ioapic_hpet_scope(iommu);
+	}
+
+	return ret;
+}
+
 int dmar_ir_hotplug(struct dmar_drhd_unit *dmaru, bool insert)
 {
-	return irq_remapping_enabled ? -ENOSYS : 0;
+	int ret = 0;
+	struct intel_iommu *iommu = dmaru->iommu;
+
+	if (!irq_remapping_enabled)
+		return 0;
+	if (iommu == NULL)
+		return -EINVAL;
+	if (!ecap_ir_support(iommu->ecap))
+		return 0;
+
+	if (insert) {
+		if (!iommu->ir_table)
+			ret = dmar_ir_add(dmaru, iommu);
+	} else {
+		if (iommu->ir_table) {
+			if (!bitmap_empty(iommu->ir_table->bitmap,
+					  INTR_REMAP_TABLE_ENTRIES)) {
+				ret = -EBUSY;
+			} else {
+				iommu_disable_irq_remapping(iommu);
+				intel_teardown_irq_remapping(iommu);
+				ir_remove_ioapic_hpet_scope(iommu);
+			}
+		}
+	}
+
+	return ret;
 }

index 7af0b56dc2d1..27541d440849 100644
@@ -702,9 +702,11 @@ static int __init intel_enable_irq_remapping(void)
 	return eim ? IRQ_REMAP_X2APIC_MODE : IRQ_REMAP_XAPIC_MODE;
 
 error:
-	/*
-	 * handle error condition gracefully here!
-	 */
+	for_each_iommu(iommu, drhd)
+		if (ecap_ir_support(iommu->ecap)) {
+			iommu_disable_irq_remapping(iommu);
+			intel_teardown_irq_remapping(iommu);
+		}
 
 	if (x2apic_present)
 		pr_warn("Failed to enable irq remapping.  You are vulnerable to irq-injection attacks.\n");

index ca7075014ee3..9a4fee8122c4 100644
@@ -1125,8 +1125,11 @@ static int iommu_alloc_root_entry(struct intel_iommu *iommu)
 	unsigned long flags;
 
 	root = (struct root_entry *)alloc_pgtable_page(iommu->node);
-	if (!root)
+	if (!root) {
+		pr_err("IOMMU: allocating root entry for %s failed\n",
+			iommu->name);
 		return -ENOMEM;
+	}
 
 	__iommu_flush_cache(iommu, root, ROOT_SIZE);
 

@@ -1466,7 +1469,7 @@ static int iommu_init_domains(struct intel_iommu *iommu)
 	return 0;
 }
 
-static void free_dmar_iommu(struct intel_iommu *iommu)
+static void disable_dmar_iommu(struct intel_iommu *iommu)
 {
 	struct dmar_domain *domain;
 	int i;

@@ -1490,11 +1493,16 @@ static void free_dmar_iommu(struct intel_iommu *iommu)
 
 	if (iommu->gcmd & DMA_GCMD_TE)
 		iommu_disable_translation(iommu);
+}
 
-	kfree(iommu->domains);
-	kfree(iommu->domain_ids);
-	iommu->domains = NULL;
-	iommu->domain_ids = NULL;
+static void free_dmar_iommu(struct intel_iommu *iommu)
+{
+	if ((iommu->domains) && (iommu->domain_ids)) {
+		kfree(iommu->domains);
+		kfree(iommu->domain_ids);
+		iommu->domains = NULL;
+		iommu->domain_ids = NULL;
+	}
 
 	g_iommus[iommu->seq_id] = NULL;
 

@@ -2701,6 +2709,41 @@ static int __init iommu_prepare_static_identity_mapping(int hw)
 	return 0;
 }
 
+static void intel_iommu_init_qi(struct intel_iommu *iommu)
+{
+	/*
+	 * Start from the sane iommu hardware state.
+	 * If the queued invalidation is already initialized by us
+	 * (for example, while enabling interrupt-remapping) then
+	 * we got the things already rolling from a sane state.
+	 */
+	if (!iommu->qi) {
+		/*
+		 * Clear any previous faults.
+		 */
+		dmar_fault(-1, iommu);
+		/*
+		 * Disable queued invalidation if supported and already enabled
+		 * before OS handover.
+		 */
+		dmar_disable_qi(iommu);
+	}
+
+	if (dmar_enable_qi(iommu)) {
+		/*
+		 * Queued Invalidate not enabled, use Register Based Invalidate
+		 */
+		iommu->flush.flush_context = __iommu_flush_context;
+		iommu->flush.flush_iotlb = __iommu_flush_iotlb;
+		pr_info("IOMMU: %s using Register based invalidation\n",
+			iommu->name);
+	} else {
+		iommu->flush.flush_context = qi_flush_context;
+		iommu->flush.flush_iotlb = qi_flush_iotlb;
+		pr_info("IOMMU: %s using Queued invalidation\n", iommu->name);
+	}
+}
+
 static int __init init_dmars(void)
 {
 	struct dmar_drhd_unit *drhd;

@@ -2729,6 +2772,10 @@ static int __init init_dmars(void)
 			  DMAR_UNITS_SUPPORTED);
 	}
 
+	/* Preallocate enough resources for IOMMU hot-addition */
+	if (g_num_of_iommus < DMAR_UNITS_SUPPORTED)
+		g_num_of_iommus = DMAR_UNITS_SUPPORTED;
+
 	g_iommus = kcalloc(g_num_of_iommus, sizeof(struct intel_iommu *),
 			GFP_KERNEL);
 	if (!g_iommus) {

@@ -2757,58 +2804,14 @@ static int __init init_dmars(void)
 		 * among all IOMMU's. Need to Split it later.
 		 */
 		ret = iommu_alloc_root_entry(iommu);
-		if (ret) {
-			printk(KERN_ERR "IOMMU: allocate root entry failed\n");
+		if (ret)
 			goto free_iommu;
-		}
 		if (!ecap_pass_through(iommu->ecap))
 			hw_pass_through = 0;
 	}
 
-	/*
-	 * Start from the sane iommu hardware state.
-	 */
-	for_each_active_iommu(iommu, drhd) {
-		/*
-		 * If the queued invalidation is already initialized by us
-		 * (for example, while enabling interrupt-remapping) then
-		 * we got the things already rolling from a sane state.
-		 */
-		if (iommu->qi)
-			continue;
-
-		/*
-		 * Clear any previous faults.
-		 */
-		dmar_fault(-1, iommu);
-		/*
-		 * Disable queued invalidation if supported and already enabled
-		 * before OS handover.
-		 */
-		dmar_disable_qi(iommu);
-	}
-
-	for_each_active_iommu(iommu, drhd) {
-		if (dmar_enable_qi(iommu)) {
-			/*
-			 * Queued Invalidate not enabled, use Register Based
-			 * Invalidate
-			 */
-			iommu->flush.flush_context = __iommu_flush_context;
-			iommu->flush.flush_iotlb = __iommu_flush_iotlb;
-			printk(KERN_INFO "IOMMU %d 0x%Lx: using Register based "
-			       "invalidation\n",
-				iommu->seq_id,
-			       (unsigned long long)drhd->reg_base_addr);
-		} else {
-			iommu->flush.flush_context = qi_flush_context;
-			iommu->flush.flush_iotlb = qi_flush_iotlb;
-			printk(KERN_INFO "IOMMU %d 0x%Lx: using Queued "
-			       "invalidation\n",
-				iommu->seq_id,
-			       (unsigned long long)drhd->reg_base_addr);
-		}
-	}
+	for_each_active_iommu(iommu, drhd)
+		intel_iommu_init_qi(iommu);
 
 	if (iommu_pass_through)
 		iommu_identity_mapping |= IDENTMAP_ALL;

@@ -2894,8 +2897,10 @@ static int __init init_dmars(void)
 	return 0;
 
 free_iommu:
-	for_each_active_iommu(iommu, drhd)
+	for_each_active_iommu(iommu, drhd) {
+		disable_dmar_iommu(iommu);
 		free_dmar_iommu(iommu);
+	}
 	kfree(deferred_flush);
 free_g_iommus:
 	kfree(g_iommus);

@@ -3801,9 +3806,100 @@ int dmar_check_one_atsr(struct acpi_dmar_header *hdr, void *arg)
 	return 0;
 }
 
+static int intel_iommu_add(struct dmar_drhd_unit *dmaru)
+{
+	int sp, ret = 0;
+	struct intel_iommu *iommu = dmaru->iommu;
+
+	if (g_iommus[iommu->seq_id])
+		return 0;
+
+	if (hw_pass_through && !ecap_pass_through(iommu->ecap)) {
+		pr_warn("IOMMU: %s doesn't support hardware pass through.\n",
+			iommu->name);
+		return -ENXIO;
+	}
+	if (!ecap_sc_support(iommu->ecap) &&
+	    domain_update_iommu_snooping(iommu)) {
+		pr_warn("IOMMU: %s doesn't support snooping.\n",
+			iommu->name);
+		return -ENXIO;
+	}
+	sp = domain_update_iommu_superpage(iommu) - 1;
+	if (sp >= 0 && !(cap_super_page_val(iommu->cap) & (1 << sp))) {
+		pr_warn("IOMMU: %s doesn't support large page.\n",
+			iommu->name);
+		return -ENXIO;
+	}
+
+	/*
+	 * Disable translation if already enabled prior to OS handover.
+	 */
+	if (iommu->gcmd & DMA_GCMD_TE)
+		iommu_disable_translation(iommu);
+
+	g_iommus[iommu->seq_id] = iommu;
+	ret = iommu_init_domains(iommu);
+	if (ret == 0)
+		ret = iommu_alloc_root_entry(iommu);
+	if (ret)
+		goto out;
+
+	if (dmaru->ignored) {
+		/*
+		 * we always have to disable PMRs or DMA may fail on this device
+		 */
+		if (force_on)
+			iommu_disable_protect_mem_regions(iommu);
+		return 0;
+	}
+
+	intel_iommu_init_qi(iommu);
+	iommu_flush_write_buffer(iommu);
+	ret = dmar_set_interrupt(iommu);
+	if (ret)
+		goto disable_iommu;
+
+	iommu_set_root_entry(iommu);
+	iommu->flush.flush_context(iommu, 0, 0, 0, DMA_CCMD_GLOBAL_INVL);
+	iommu->flush.flush_iotlb(iommu, 0, 0, 0, DMA_TLB_GLOBAL_FLUSH);
+	iommu_enable_translation(iommu);
+
+	if (si_domain) {
+		ret = iommu_attach_domain(si_domain, iommu);
+		if (ret < 0 || si_domain->id != ret)
+			goto disable_iommu;
+		domain_attach_iommu(si_domain, iommu);
+	}
+
+	iommu_disable_protect_mem_regions(iommu);
+	return 0;
+
+disable_iommu:
+	disable_dmar_iommu(iommu);
+out:
+	free_dmar_iommu(iommu);
+	return ret;
+}
+
 int dmar_iommu_hotplug(struct dmar_drhd_unit *dmaru, bool insert)
 {
-	return intel_iommu_enabled ? -ENOSYS : 0;
+	int ret = 0;
+	struct intel_iommu *iommu = dmaru->iommu;
+
+	if (!intel_iommu_enabled)
+		return 0;
+	if (iommu == NULL)
+		return -EINVAL;
+
+	if (insert) {
+		ret = intel_iommu_add(dmaru);
+	} else {
+		disable_dmar_iommu(iommu);
+		free_dmar_iommu(iommu);
+	}
+
+	return ret;
 }
 
 static void intel_iommu_free_dmars(void)

index cd4de7e038ea..c6bcb8c719d8 100644
@@ -33,6 +33,7 @@
 #include <linux/pci.h>
 #include <linux/pci-acpi.h>
 #include <linux/pci-aspm.h>
+#include <linux/dmar.h>
 #include <linux/acpi.h>
 #include <linux/slab.h>
 #include <linux/dmi.h>

@@ -525,6 +526,7 @@ static int acpi_pci_root_add(struct acpi_device *device,
 	struct acpi_pci_root *root;
 	acpi_handle handle = device->handle;
 	int no_aspm = 0, clear_aspm = 0;
+	bool hotadd = system_state != SYSTEM_BOOTING;
 
 	root = kzalloc(sizeof(struct acpi_pci_root), GFP_KERNEL);
 	if (!root)

@@ -571,6 +573,11 @@ static int acpi_pci_root_add(struct acpi_device *device,
 	strcpy(acpi_device_class(device), ACPI_PCI_ROOT_CLASS);
 	device->driver_data = root;
 
+	if (hotadd && dmar_device_add(handle)) {
+		result = -ENXIO;
+		goto end;
+	}
+
 	pr_info(PREFIX "%s [%s] (domain %04x %pR)\n",
 	       acpi_device_name(device), acpi_device_bid(device),
 	       root->segment, &root->secondary);

@@ -597,7 +604,7 @@ static int acpi_pci_root_add(struct acpi_device *device,
 			root->segment, (unsigned int)root->secondary.start);
 		device->driver_data = NULL;
 		result = -ENODEV;
-		goto end;
+		goto remove_dmar;
 	}
 
 	if (clear_aspm) {

@@ -611,7 +618,7 @@ static int acpi_pci_root_add(struct acpi_device *device,
 	if (device->wakeup.flags.run_wake)
 		device_set_run_wake(root->bus->bridge, true);
 
-	if (system_state != SYSTEM_BOOTING) {
+	if (hotadd) {
 		pcibios_resource_survey_bus(root->bus);
 		pci_assign_unassigned_root_bus_resources(root->bus);
 	}

@@ -621,6 +628,9 @@ static int acpi_pci_root_add(struct acpi_device *device,
 	pci_unlock_rescan_remove();
 	return 1;
 
+remove_dmar:
+	if (hotadd)
+		dmar_device_remove(handle);
 end:
 	kfree(root);
 	return result;

@@ -639,6 +649,8 @@ static void acpi_pci_root_remove(struct acpi_device *device)
 
 	pci_remove_root_bus(root->bus);
 
+	dmar_device_remove(device->handle);
+
 	pci_unlock_rescan_remove();
 
 	kfree(root);