6 files changed, 125 insertions, 141 deletions

diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c
index 1a041bcf506b..ae13e34f7248 100644
--- a/arch/x86/kernel/pci-dma.c
+++ b/arch/x86/kernel/pci-dma.c
@@ -212,10 +212,8 @@ static __init int iommu_setup(char *p)
                 if (!strncmp(p, "soft", 4))
                         swiotlb = 1;
 #endif
-                if (!strncmp(p, "pt", 2)) {
+                if (!strncmp(p, "pt", 2))
                         iommu_pass_through = 1;
-                        return 1;
-                }
 
                 gart_parse_options(p);
 
diff --git a/arch/x86/kernel/pci-swiotlb.c b/arch/x86/kernel/pci-swiotlb.c
index 6af96ee44200..1e66b18f45cb 100644
--- a/arch/x86/kernel/pci-swiotlb.c
+++ b/arch/x86/kernel/pci-swiotlb.c
@@ -71,9 +71,8 @@ void __init pci_swiotlb_init(void)
 {
         /* don't initialize swiotlb if iommu=off (no_iommu=1) */
 #ifdef CONFIG_X86_64
-        if ((!iommu_detected && !no_iommu && max_pfn > MAX_DMA32_PFN) ||
-                iommu_pass_through)
-               swiotlb = 1;
+        if ((!iommu_detected && !no_iommu && max_pfn > MAX_DMA32_PFN))
+                swiotlb = 1;
 #endif
         if (swiotlb_force)
                 swiotlb = 1;
diff --git a/drivers/pci/dmar.c b/drivers/pci/dmar.c
index 7b287cb38b7a..380b60e677e0 100644
--- a/drivers/pci/dmar.c
+++ b/drivers/pci/dmar.c
@@ -632,20 +632,31 @@ int alloc_iommu(struct dmar_drhd_unit *drhd)
         iommu->cap = dmar_readq(iommu->reg + DMAR_CAP_REG);
         iommu->ecap = dmar_readq(iommu->reg + DMAR_ECAP_REG);
 
+        if (iommu->cap == (uint64_t)-1 && iommu->ecap == (uint64_t)-1) {
+                /* Promote an attitude of violence to a BIOS engineer today */
+                WARN(1, "Your BIOS is broken; DMAR reported at address %llx returns all ones!\n"
+                     "BIOS vendor: %s; Ver: %s; Product Version: %s\n",
+                     drhd->reg_base_addr,
+                     dmi_get_system_info(DMI_BIOS_VENDOR),
+                     dmi_get_system_info(DMI_BIOS_VERSION),
+                     dmi_get_system_info(DMI_PRODUCT_VERSION));
+                goto err_unmap;
+        }
+
 #ifdef CONFIG_DMAR
         agaw = iommu_calculate_agaw(iommu);
         if (agaw < 0) {
                 printk(KERN_ERR
                        "Cannot get a valid agaw for iommu (seq_id = %d)\n",
                        iommu->seq_id);
-                goto error;
+                goto err_unmap;
         }
         msagaw = iommu_calculate_max_sagaw(iommu);
         if (msagaw < 0) {
                 printk(KERN_ERR
                         "Cannot get a valid max agaw for iommu (seq_id = %d)\n",
                         iommu->seq_id);
-                goto error;
+                goto err_unmap;
         }
 #endif
         iommu->agaw = agaw;
@@ -665,7 +676,7 @@ int alloc_iommu(struct dmar_drhd_unit *drhd)
         }
 
         ver = readl(iommu->reg + DMAR_VER_REG);
-        pr_debug("IOMMU %llx: ver %d:%d cap %llx ecap %llx\n",
+        pr_info("IOMMU %llx: ver %d:%d cap %llx ecap %llx\n",
                 (unsigned long long)drhd->reg_base_addr,
                 DMAR_VER_MAJOR(ver), DMAR_VER_MINOR(ver),
                 (unsigned long long)iommu->cap,
@@ -675,7 +686,10 @@ int alloc_iommu(struct dmar_drhd_unit *drhd)
 
         drhd->iommu = iommu;
         return 0;
-error:
+
+ err_unmap:
+        iounmap(iommu->reg);
+ error:
         kfree(iommu);
         return -1;
 }
diff --git a/drivers/pci/intel-iommu.c b/drivers/pci/intel-iommu.c
index 2314ad7ee5fe..3f256b8d83c1 100644
--- a/drivers/pci/intel-iommu.c
+++ b/drivers/pci/intel-iommu.c
@@ -251,7 +251,8 @@ static inline int first_pte_in_page(struct dma_pte *pte)
  *      2. It maps to each iommu if successful.
  *      3. Each iommu mapps to this domain if successful.
  */
-struct dmar_domain *si_domain;
+static struct dmar_domain *si_domain;
+static int hw_pass_through = 1;
 
 /* devices under the same p2p bridge are owned in one domain */
 #define DOMAIN_FLAG_P2P_MULTIPLE_DEVICES (1 << 0)
@@ -1309,7 +1310,6 @@ static void iommu_detach_domain(struct dmar_domain *domain,
 }
 
 static struct iova_domain reserved_iova_list;
-static struct lock_class_key reserved_alloc_key;
 static struct lock_class_key reserved_rbtree_key;
 
 static void dmar_init_reserved_ranges(void)
@@ -1320,8 +1320,6 @@ static void dmar_init_reserved_ranges(void)
 
         init_iova_domain(&reserved_iova_list, DMA_32BIT_PFN);
 
-        lockdep_set_class(&reserved_iova_list.iova_alloc_lock,
-                &reserved_alloc_key);
         lockdep_set_class(&reserved_iova_list.iova_rbtree_lock,
                 &reserved_rbtree_key);
 
@@ -1958,14 +1956,24 @@ static int iommu_prepare_identity_map(struct pci_dev *pdev,
         struct dmar_domain *domain;
         int ret;
 
-        printk(KERN_INFO
-               "IOMMU: Setting identity map for device %s [0x%Lx - 0x%Lx]\n",
-               pci_name(pdev), start, end);
-
         domain = get_domain_for_dev(pdev, DEFAULT_DOMAIN_ADDRESS_WIDTH);
         if (!domain)
                 return -ENOMEM;
 
+        /* For _hardware_ passthrough, don't bother. But for software
+           passthrough, we do it anyway -- it may indicate a memory
+           range which is reserved in E820, so which didn't get set
+           up to start with in si_domain */
+        if (domain == si_domain && hw_pass_through) {
+                printk("Ignoring identity map for HW passthrough device %s [0x%Lx - 0x%Lx]\n",
+                       pci_name(pdev), start, end);
+                return 0;
+        }
+
+        printk(KERN_INFO
+               "IOMMU: Setting identity map for device %s [0x%Lx - 0x%Lx]\n",
+               pci_name(pdev), start, end);
+
         ret = iommu_domain_identity_map(domain, start, end);
         if (ret)
                 goto error;
@@ -2016,23 +2024,6 @@ static inline void iommu_prepare_isa(void)
 }
 #endif /* !CONFIG_DMAR_FLPY_WA */
 
-/* Initialize each context entry as pass through.*/
-static int __init init_context_pass_through(void)
-{
-        struct pci_dev *pdev = NULL;
-        struct dmar_domain *domain;
-        int ret;
-
-        for_each_pci_dev(pdev) {
-                domain = get_domain_for_dev(pdev, DEFAULT_DOMAIN_ADDRESS_WIDTH);
-                ret = domain_context_mapping(domain, pdev,
-                                             CONTEXT_TT_PASS_THROUGH);
-                if (ret)
-                        return ret;
-        }
-        return 0;
-}
-
 static int md_domain_init(struct dmar_domain *domain, int guest_width);
 
 static int __init si_domain_work_fn(unsigned long start_pfn,
@@ -2047,7 +2038,7 @@ static int __init si_domain_work_fn(unsigned long start_pfn,
 
 }
 
-static int si_domain_init(void)
+static int si_domain_init(int hw)
 {
         struct dmar_drhd_unit *drhd;
         struct intel_iommu *iommu;
@@ -2074,6 +2065,9 @@ static int si_domain_init(void)
 
         si_domain->flags = DOMAIN_FLAG_STATIC_IDENTITY;
 
+        if (hw)
+                return 0;
+
         for_each_online_node(nid) {
                 work_with_active_regions(nid, si_domain_work_fn, &ret);
                 if (ret)
@@ -2165,24 +2159,26 @@ static int iommu_should_identity_map(struct pci_dev *pdev, int startup)
         return 1;
 }
 
-static int iommu_prepare_static_identity_mapping(void)
+static int iommu_prepare_static_identity_mapping(int hw)
 {
         struct pci_dev *pdev = NULL;
         int ret;
 
-        ret = si_domain_init();
+        ret = si_domain_init(hw);
         if (ret)
                 return -EFAULT;
 
         for_each_pci_dev(pdev) {
                 if (iommu_should_identity_map(pdev, 1)) {
-                        printk(KERN_INFO "IOMMU: identity mapping for device %s\n",
-                               pci_name(pdev));
+                        printk(KERN_INFO "IOMMU: %s identity mapping for device %s\n",
+                               hw ? "hardware" : "software", pci_name(pdev));
 
                         ret = domain_context_mapping(si_domain, pdev,
+                                                     hw ? CONTEXT_TT_PASS_THROUGH :
                                                      CONTEXT_TT_MULTI_LEVEL);
                         if (ret)
                                 return ret;
+
                         ret = domain_add_dev_info(si_domain, pdev);
                         if (ret)
                                 return ret;
@@ -2199,14 +2195,6 @@ int __init init_dmars(void)
         struct pci_dev *pdev;
         struct intel_iommu *iommu;
         int i, ret;
-        int pass_through = 1;
-
-        /*
-         * In case pass through can not be enabled, iommu tries to use identity
-         * mapping.
-         */
-        if (iommu_pass_through)
-                iommu_identity_mapping = 1;
 
         /*
          * for each drhd
@@ -2234,7 +2222,6 @@ int __init init_dmars(void)
         deferred_flush = kzalloc(g_num_of_iommus *
                 sizeof(struct deferred_flush_tables), GFP_KERNEL);
         if (!deferred_flush) {
-                kfree(g_iommus);
                 ret = -ENOMEM;
                 goto error;
         }
@@ -2261,14 +2248,8 @@ int __init init_dmars(void)
                         goto error;
                 }
                 if (!ecap_pass_through(iommu->ecap))
-                        pass_through = 0;
+                        hw_pass_through = 0;
         }
-        if (iommu_pass_through)
-                if (!pass_through) {
-                        printk(KERN_INFO
-                               "Pass Through is not supported by hardware.\n");
-                        iommu_pass_through = 0;
-                }
 
         /*
          * Start from the sane iommu hardware state.
@@ -2323,64 +2304,57 @@ int __init init_dmars(void)
                 }
         }
 
+        if (iommu_pass_through)
+                iommu_identity_mapping = 1;
+#ifdef CONFIG_DMAR_BROKEN_GFX_WA
+        else
+                iommu_identity_mapping = 2;
+#endif
         /*
-         * If pass through is set and enabled, context entries of all pci
-         * devices are intialized by pass through translation type.
+         * If pass through is not set or not enabled, setup context entries for
+         * identity mappings for rmrr, gfx, and isa and may fall back to static
+         * identity mapping if iommu_identity_mapping is set.
          */
-        if (iommu_pass_through) {
-                ret = init_context_pass_through();
+        if (iommu_identity_mapping) {
+                ret = iommu_prepare_static_identity_mapping(hw_pass_through);
                 if (ret) {
-                        printk(KERN_ERR "IOMMU: Pass through init failed.\n");
-                        iommu_pass_through = 0;
+                        printk(KERN_CRIT "Failed to setup IOMMU pass-through\n");
+                        goto error;
                 }
         }
-
         /*
-         * If pass through is not set or not enabled, setup context entries for
-         * identity mappings for rmrr, gfx, and isa and may fall back to static
-         * identity mapping if iommu_identity_mapping is set.
+         * For each rmrr
+         *   for each dev attached to rmrr
+         *   do
+         *     locate drhd for dev, alloc domain for dev
+         *     allocate free domain
+         *     allocate page table entries for rmrr
+         *     if context not allocated for bus
+         *           allocate and init context
+         *           set present in root table for this bus
+         *     init context with domain, translation etc
+         *    endfor
+         * endfor
          */
-        if (!iommu_pass_through) {
-#ifdef CONFIG_DMAR_BROKEN_GFX_WA
-                if (!iommu_identity_mapping)
-                        iommu_identity_mapping = 2;
-#endif
-                if (iommu_identity_mapping)
-                        iommu_prepare_static_identity_mapping();
-                /*
-                 * For each rmrr
-                 *   for each dev attached to rmrr
-                 *   do
-                 *     locate drhd for dev, alloc domain for dev
-                 *     allocate free domain
-                 *     allocate page table entries for rmrr
-                 *     if context not allocated for bus
-                 *           allocate and init context
-                 *           set present in root table for this bus
-                 *     init context with domain, translation etc
-                 *    endfor
-                 * endfor
-                 */
-                printk(KERN_INFO "IOMMU: Setting RMRR:\n");
-                for_each_rmrr_units(rmrr) {
-                        for (i = 0; i < rmrr->devices_cnt; i++) {
-                                pdev = rmrr->devices[i];
-                                /*
-                                 * some BIOS lists non-exist devices in DMAR
-                                 * table.
-                                 */
-                                if (!pdev)
-                                        continue;
-                                ret = iommu_prepare_rmrr_dev(rmrr, pdev);
-                                if (ret)
-                                        printk(KERN_ERR
-                                 "IOMMU: mapping reserved region failed\n");
-                        }
+        printk(KERN_INFO "IOMMU: Setting RMRR:\n");
+        for_each_rmrr_units(rmrr) {
+                for (i = 0; i < rmrr->devices_cnt; i++) {
+                        pdev = rmrr->devices[i];
+                        /*
+                         * some BIOS lists non-exist devices in DMAR
+                         * table.
+                         */
+                        if (!pdev)
+                                continue;
+                        ret = iommu_prepare_rmrr_dev(rmrr, pdev);
+                        if (ret)
+                                printk(KERN_ERR
+                                       "IOMMU: mapping reserved region failed\n");
                 }
-
-                iommu_prepare_isa();
         }
 
+        iommu_prepare_isa();
+
         /*
          * for each drhd
          *   enable fault log
@@ -2454,8 +2428,7 @@ static struct iova *intel_alloc_iova(struct device *dev,
         return iova;
 }
 
-static struct dmar_domain *
-get_valid_domain_for_dev(struct pci_dev *pdev)
+static struct dmar_domain *__get_valid_domain_for_dev(struct pci_dev *pdev)
 {
         struct dmar_domain *domain;
         int ret;
@@ -2483,6 +2456,18 @@ get_valid_domain_for_dev(struct pci_dev *pdev)
         return domain;
 }
 
+static inline struct dmar_domain *get_valid_domain_for_dev(struct pci_dev *dev)
+{
+        struct device_domain_info *info;
+
+        /* No lock here, assumes no domain exit in normal case */
+        info = dev->dev.archdata.iommu;
+        if (likely(info))
+                return info->domain;
+
+        return __get_valid_domain_for_dev(dev);
+}
+
 static int iommu_dummy(struct pci_dev *pdev)
 {
         return pdev->dev.archdata.iommu == DUMMY_DEVICE_DOMAIN_INFO;
@@ -2528,7 +2513,10 @@ static int iommu_no_mapping(struct device *dev)
                         ret = domain_add_dev_info(si_domain, pdev);
                         if (ret)
                                 return 0;
-                        ret = domain_context_mapping(si_domain, pdev, CONTEXT_TT_MULTI_LEVEL);
+                        ret = domain_context_mapping(si_domain, pdev,
+                                                     hw_pass_through ?
+                                                     CONTEXT_TT_PASS_THROUGH :
+                                                     CONTEXT_TT_MULTI_LEVEL);
                         if (!ret) {
                                 printk(KERN_INFO "64bit %s uses identity mapping\n",
                                        pci_name(pdev));
@@ -2733,12 +2721,6 @@ static void intel_unmap_page(struct device *dev, dma_addr_t dev_addr,
         }
 }
 
-static void intel_unmap_single(struct device *dev, dma_addr_t dev_addr, size_t size,
-                               int dir)
-{
-        intel_unmap_page(dev, dev_addr, size, dir, NULL);
-}
-
 static void *intel_alloc_coherent(struct device *hwdev, size_t size,
                                   dma_addr_t *dma_handle, gfp_t flags)
 {
@@ -2771,7 +2753,7 @@ static void intel_free_coherent(struct device *hwdev, size_t size, void *vaddr,
         size = PAGE_ALIGN(size);
         order = get_order(size);
 
-        intel_unmap_single(hwdev, dma_handle, size, DMA_BIDIRECTIONAL);
+        intel_unmap_page(hwdev, dma_handle, size, DMA_BIDIRECTIONAL, NULL);
         free_pages((unsigned long)vaddr, order);
 }
 
@@ -2807,11 +2789,18 @@ static void intel_unmap_sg(struct device *hwdev, struct scatterlist *sglist,
         /* free page tables */
         dma_pte_free_pagetable(domain, start_pfn, last_pfn);
 
-        iommu_flush_iotlb_psi(iommu, domain->id, start_pfn,
-                              (last_pfn - start_pfn + 1));
-
-        /* free iova */
-        __free_iova(&domain->iovad, iova);
+        if (intel_iommu_strict) {
+                iommu_flush_iotlb_psi(iommu, domain->id, start_pfn,
+                                      last_pfn - start_pfn + 1);
+                /* free iova */
+                __free_iova(&domain->iovad, iova);
+        } else {
+                add_unmap(domain, iova);
+                /*
+                 * queue up the release of the unmap to save the 1/6th of the
+                 * cpu used up by the iotlb flush operation...
+                 */
+        }
 }
 
 static int intel_nontranslate_map_sg(struct device *hddev,
@@ -3194,7 +3183,7 @@ int __init intel_iommu_init(void)
          * Check the need for DMA-remapping initialization now.
          * Above initialization will also be used by Interrupt-remapping.
          */
-        if (no_iommu || (swiotlb && !iommu_pass_through) || dmar_disabled)
+        if (no_iommu || swiotlb || dmar_disabled)
                 return -ENODEV;
 
         iommu_init_mempool();
@@ -3214,14 +3203,7 @@ int __init intel_iommu_init(void)
 
         init_timer(&unmap_timer);
         force_iommu = 1;
-
-        if (!iommu_pass_through) {
-                printk(KERN_INFO
-                       "Multi-level page-table translation for DMAR.\n");
-                dma_ops = &intel_dma_ops;
-        } else
-                printk(KERN_INFO
-                       "DMAR: Pass through translation for DMAR.\n");
+        dma_ops = &intel_dma_ops;
 
         init_iommu_sysfs();
 
diff --git a/drivers/pci/iova.c b/drivers/pci/iova.c
index 46dd440e2315..7914951ef29a 100644
--- a/drivers/pci/iova.c
+++ b/drivers/pci/iova.c
@@ -22,7 +22,6 @@
 void
 init_iova_domain(struct iova_domain *iovad, unsigned long pfn_32bit)
 {
-        spin_lock_init(&iovad->iova_alloc_lock);
         spin_lock_init(&iovad->iova_rbtree_lock);
         iovad->rbroot = RB_ROOT;
         iovad->cached32_node = NULL;
@@ -205,7 +204,6 @@ alloc_iova(struct iova_domain *iovad, unsigned long size,
         unsigned long limit_pfn,
         bool size_aligned)
 {
-        unsigned long flags;
         struct iova *new_iova;
         int ret;
 
@@ -219,11 +217,9 @@ alloc_iova(struct iova_domain *iovad, unsigned long size,
         if (size_aligned)
                 size = __roundup_pow_of_two(size);
 
-        spin_lock_irqsave(&iovad->iova_alloc_lock, flags);
         ret = __alloc_and_insert_iova_range(iovad, size, limit_pfn,
                         new_iova, size_aligned);
 
-        spin_unlock_irqrestore(&iovad->iova_alloc_lock, flags);
         if (ret) {
                 free_iova_mem(new_iova);
                 return NULL;
@@ -381,8 +377,7 @@ reserve_iova(struct iova_domain *iovad,
         struct iova *iova;
         unsigned int overlap = 0;
 
-        spin_lock_irqsave(&iovad->iova_alloc_lock, flags);
-        spin_lock(&iovad->iova_rbtree_lock);
+        spin_lock_irqsave(&iovad->iova_rbtree_lock, flags);
         for (node = rb_first(&iovad->rbroot); node; node = rb_next(node)) {
                 if (__is_range_overlap(node, pfn_lo, pfn_hi)) {
                         iova = container_of(node, struct iova, node);
@@ -402,8 +397,7 @@ reserve_iova(struct iova_domain *iovad,
         iova = __insert_new_range(iovad, pfn_lo, pfn_hi);
 finish:
 
-        spin_unlock(&iovad->iova_rbtree_lock);
-        spin_unlock_irqrestore(&iovad->iova_alloc_lock, flags);
+        spin_unlock_irqrestore(&iovad->iova_rbtree_lock, flags);
         return iova;
 }
 
@@ -420,8 +414,7 @@ copy_reserved_iova(struct iova_domain *from, struct iova_domain *to)
         unsigned long flags;
         struct rb_node *node;
 
-        spin_lock_irqsave(&from->iova_alloc_lock, flags);
-        spin_lock(&from->iova_rbtree_lock);
+        spin_lock_irqsave(&from->iova_rbtree_lock, flags);
         for (node = rb_first(&from->rbroot); node; node = rb_next(node)) {
                 struct iova *iova = container_of(node, struct iova, node);
                 struct iova *new_iova;
@@ -430,6 +423,5 @@ copy_reserved_iova(struct iova_domain *from, struct iova_domain *to)
                         printk(KERN_ERR "Reserve iova range %lx@%lx failed\n",
                                 iova->pfn_lo, iova->pfn_lo);
         }
-        spin_unlock(&from->iova_rbtree_lock);
-        spin_unlock_irqrestore(&from->iova_alloc_lock, flags);
+        spin_unlock_irqrestore(&from->iova_rbtree_lock, flags);
 }
diff --git a/include/linux/iova.h b/include/linux/iova.h
index 228f6c94b69c..76a0759e88ec 100644
--- a/include/linux/iova.h
+++ b/include/linux/iova.h
@@ -28,7 +28,6 @@ struct iova {
 
 /* holds all the iova translations for a domain */
 struct iova_domain {
-        spinlock_t      iova_alloc_lock;/* Lock to protect iova  allocation */
         spinlock_t      iova_rbtree_lock; /* Lock to protect update of rbtree */
         struct rb_root  rbroot;         /* iova domain rbtree root */
         struct rb_node  *cached32_node; /* Save last alloced node */