1 files changed, 235 insertions, 73 deletions

diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c
index a27d6cb1a793..1232336b960e 100644
--- a/drivers/iommu/intel-iommu.c
+++ b/drivers/iommu/intel-iommu.c
@@ -195,6 +195,7 @@ static inline void set_root_present(struct root_entry *root)
 }
 static inline void set_root_value(struct root_entry *root, unsigned long value)
 {
+	root->val &= ~VTD_PAGE_MASK;
 	root->val |= value & VTD_PAGE_MASK;
 }
 
@@ -247,6 +248,7 @@ static inline void context_set_translation_type(struct context_entry *context,
 static inline void context_set_address_root(struct context_entry *context,
 					    unsigned long value)
 {
+	context->lo &= ~VTD_PAGE_MASK;
 	context->lo |= value & VTD_PAGE_MASK;
 }
 
@@ -328,17 +330,10 @@ 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 */
@@ -1132,8 +1127,11 @@ 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);
 
@@ -1473,7 +1471,7 @@ 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;
@@ -1497,11 +1495,16 @@ 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;
 
@@ -1983,7 +1986,7 @@ static int __domain_mapping(struct dmar_domain *domain, unsigned long iov_pfn,
 {
 	struct dma_pte *first_pte = NULL, *pte = NULL;
 	phys_addr_t uninitialized_var(pteval);
-	unsigned long sg_res;
+	unsigned long sg_res = 0;
 	unsigned int largepage_lvl = 0;
 	unsigned long lvl_pages = 0;
 
@@ -1994,10 +1997,8 @@ static int __domain_mapping(struct dmar_domain *domain, unsigned long iov_pfn,
 
 	prot &= DMA_PTE_READ | DMA_PTE_WRITE | DMA_PTE_SNP;
 
-	if (sg)
-		sg_res = 0;
-	else {
-		sg_res = nr_pages + 1;
+	if (!sg) {
+		sg_res = nr_pages;
 		pteval = ((phys_addr_t)phys_pfn << VTD_PAGE_SHIFT) | prot;
 	}
 
@@ -2708,6 +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;
@@ -2728,14 +2764,18 @@ 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);
 	}
 
+	/* 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) {
@@ -2764,58 +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;
@@ -2901,8 +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);
@@ -3682,7 +3680,7 @@ 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;
@@ -3708,17 +3706,48 @@ int __init dmar_parse_one_rmrr(struct acpi_dmar_header *header)
 	return 0;
 }
 
-int __init dmar_parse_one_atsr(struct acpi_dmar_header *hdr)
+static struct dmar_atsr_unit *dmar_find_atsr(struct acpi_dmar_atsr *atsr)
+{
+	struct dmar_atsr_unit *atsru;
+	struct acpi_dmar_atsr *tmp;
+
+	list_for_each_entry_rcu(atsru, &dmar_atsr_units, list) {
+		tmp = (struct acpi_dmar_atsr *)atsru->hdr;
+		if (atsr->segment != tmp->segment)
+			continue;
+		if (atsr->header.length != tmp->header.length)
+			continue;
+		if (memcmp(atsr, tmp, atsr->header.length) == 0)
+			return atsru;
+	}
+
+	return NULL;
+}
+
+int dmar_parse_one_atsr(struct acpi_dmar_header *hdr, void *arg)
 {
 	struct acpi_dmar_atsr *atsr;
 	struct dmar_atsr_unit *atsru;
 
+	if (system_state != SYSTEM_BOOTING && !intel_iommu_enabled)
+		return 0;
+
 	atsr = container_of(hdr, struct acpi_dmar_atsr, header);
-	atsru = kzalloc(sizeof(*atsru), GFP_KERNEL);
+	atsru = dmar_find_atsr(atsr);
+	if (atsru)
+		return 0;
+
+	atsru = kzalloc(sizeof(*atsru) + hdr->length, GFP_KERNEL);
 	if (!atsru)
 		return -ENOMEM;
 
-	atsru->hdr = hdr;
+	/*
+	 * If memory is allocated from slab by ACPI _DSM method, we need to
+	 * copy the memory content because the memory buffer will be freed
+	 * on return.
+	 */
+	atsru->hdr = (void *)(atsru + 1);
+	memcpy(atsru->hdr, hdr, hdr->length);
 	atsru->include_all = atsr->flags & 0x1;
 	if (!atsru->include_all) {
 		atsru->devices = dmar_alloc_dev_scope((void *)(atsr + 1),
@@ -3741,6 +3770,138 @@ static void intel_iommu_free_atsr(struct dmar_atsr_unit *atsru)
 	kfree(atsru);
 }
 
+int dmar_release_one_atsr(struct acpi_dmar_header *hdr, void *arg)
+{
+	struct acpi_dmar_atsr *atsr;
+	struct dmar_atsr_unit *atsru;
+
+	atsr = container_of(hdr, struct acpi_dmar_atsr, header);
+	atsru = dmar_find_atsr(atsr);
+	if (atsru) {
+		list_del_rcu(&atsru->list);
+		synchronize_rcu();
+		intel_iommu_free_atsr(atsru);
+	}
+
+	return 0;
+}
+
+int dmar_check_one_atsr(struct acpi_dmar_header *hdr, void *arg)
+{
+	int i;
+	struct device *dev;
+	struct acpi_dmar_atsr *atsr;
+	struct dmar_atsr_unit *atsru;
+
+	atsr = container_of(hdr, struct acpi_dmar_atsr, header);
+	atsru = dmar_find_atsr(atsr);
+	if (!atsru)
+		return 0;
+
+	if (!atsru->include_all && atsru->devices && atsru->devices_cnt)
+		for_each_active_dev_scope(atsru->devices, atsru->devices_cnt,
+					  i, dev)
+			return -EBUSY;
+
+	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)
+{
+	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)
 {
 	struct dmar_rmrr_unit *rmrru, *rmrr_n;
@@ -4467,6 +4628,7 @@ static const struct iommu_ops intel_iommu_ops = {
 	.detach_dev	= intel_iommu_detach_device,
 	.map		= intel_iommu_map,
 	.unmap		= intel_iommu_unmap,
+	.map_sg		= default_iommu_map_sg,
 	.iova_to_phys	= intel_iommu_iova_to_phys,
 	.add_device	= intel_iommu_add_device,
 	.remove_device	= intel_iommu_remove_device,