5 files changed, 143 insertions, 20 deletions

diff --git a/arch/x86/include/asm/amd_iommu.h b/arch/x86/include/asm/amd_iommu.h
index bdf96f119f06..ac95995b7bad 100644
--- a/arch/x86/include/asm/amd_iommu.h
+++ b/arch/x86/include/asm/amd_iommu.h
@@ -25,6 +25,7 @@
 #ifdef CONFIG_AMD_IOMMU
 extern int amd_iommu_init(void);
 extern int amd_iommu_init_dma_ops(void);
+extern int amd_iommu_init_passthrough(void);
 extern void amd_iommu_detect(void);
 extern irqreturn_t amd_iommu_int_handler(int irq, void *data);
 extern void amd_iommu_flush_all_domains(void);
diff --git a/arch/x86/include/asm/amd_iommu_types.h b/arch/x86/include/asm/amd_iommu_types.h
index 3a6a3259e1eb..86a56b49f2c6 100644
--- a/arch/x86/include/asm/amd_iommu_types.h
+++ b/arch/x86/include/asm/amd_iommu_types.h
@@ -143,6 +143,7 @@
 #define EVT_BUFFER_SIZE         8192 /* 512 entries */
 #define EVT_LEN_MASK            (0x9ULL << 56)
 
+#define PAGE_MODE_NONE    0x00
 #define PAGE_MODE_1_LEVEL 0x01
 #define PAGE_MODE_2_LEVEL 0x02
 #define PAGE_MODE_3_LEVEL 0x03
@@ -194,6 +195,9 @@
 #define PD_DMA_OPS_MASK         (1UL << 0) /* domain used for dma_ops */
 #define PD_DEFAULT_MASK         (1UL << 1) /* domain is a default dma_ops
                                               domain for an IOMMU */
+#define PD_PASSTHROUGH_MASK     (1UL << 2) /* domain has no page
+                                              translation */
+
 extern bool amd_iommu_dump;
 #define DUMP_printk(format, arg...)                                     \
         do {                                                            \
diff --git a/arch/x86/kernel/amd_iommu.c b/arch/x86/kernel/amd_iommu.c
index 8c93b7c7735e..dc19ed43b54e 100644
--- a/arch/x86/kernel/amd_iommu.c
+++ b/arch/x86/kernel/amd_iommu.c
@@ -41,6 +41,13 @@ static DEFINE_RWLOCK(amd_iommu_devtable_lock);
 static LIST_HEAD(iommu_pd_list);
 static DEFINE_SPINLOCK(iommu_pd_list_lock);
 
+/*
+ * Domain for untranslated devices - only allocated
+ * if iommu=pt passed on kernel cmd line.
+ */
+static struct protection_domain *pt_domain;
+
+#ifdef CONFIG_IOMMU_API
 static struct iommu_ops amd_iommu_ops;
 
 /*
@@ -1130,32 +1137,48 @@ static struct protection_domain *domain_for_device(u16 devid)
  * If a device is not yet associated with a domain, this function does
  * assigns it visible for the hardware
  */
-static void attach_device(struct amd_iommu *iommu,
-                          struct protection_domain *domain,
-                          u16 devid)
+static void __attach_device(struct amd_iommu *iommu,
+                            struct protection_domain *domain,
+                            u16 devid)
 {
-        unsigned long flags;
-        u64 pte_root = virt_to_phys(domain->pt_root);
+        u64 pte_root;
 
-        domain->dev_cnt += 1;
+        /* lock domain */
+        spin_lock(&domain->lock);
+
+        pte_root = virt_to_phys(domain->pt_root);
 
         pte_root |= (domain->mode & DEV_ENTRY_MODE_MASK)
                     << DEV_ENTRY_MODE_SHIFT;
         pte_root |= IOMMU_PTE_IR | IOMMU_PTE_IW | IOMMU_PTE_P | IOMMU_PTE_TV;
 
-        write_lock_irqsave(&amd_iommu_devtable_lock, flags);
-        amd_iommu_dev_table[devid].data[0] = lower_32_bits(pte_root);
-        amd_iommu_dev_table[devid].data[1] = upper_32_bits(pte_root);
         amd_iommu_dev_table[devid].data[2] = domain->id;
+        amd_iommu_dev_table[devid].data[1] = upper_32_bits(pte_root);
+        amd_iommu_dev_table[devid].data[0] = lower_32_bits(pte_root);
 
         amd_iommu_pd_table[devid] = domain;
+
+        domain->dev_cnt += 1;
+
+        /* ready */
+        spin_unlock(&domain->lock);
+}
+
+static void attach_device(struct amd_iommu *iommu,
+                          struct protection_domain *domain,
+                          u16 devid)
+{
+        unsigned long flags;
+
+        write_lock_irqsave(&amd_iommu_devtable_lock, flags);
+        __attach_device(iommu, domain, devid);
         write_unlock_irqrestore(&amd_iommu_devtable_lock, flags);
 
-       /*
-        * We might boot into a crash-kernel here. The crashed kernel
-        * left the caches in the IOMMU dirty. So we have to flush
-        * here to evict all dirty stuff.
-        */
+        /*
+         * We might boot into a crash-kernel here. The crashed kernel
+         * left the caches in the IOMMU dirty. So we have to flush
+         * here to evict all dirty stuff.
+         */
         iommu_queue_inv_dev_entry(iommu, devid);
         iommu_flush_tlb_pde(iommu, domain->id);
 }
@@ -1182,6 +1205,15 @@ static void __detach_device(struct protection_domain *domain, u16 devid)
 
         /* ready */
         spin_unlock(&domain->lock);
+
+        /*
+         * If we run in passthrough mode the device must be assigned to the
+         * passthrough domain if it is detached from any other domain
+         */
+        if (iommu_pass_through) {
+                struct amd_iommu *iommu = amd_iommu_rlookup_table[devid];
+                __attach_device(iommu, pt_domain, devid);
+        }
 }
 
 /*
@@ -1227,6 +1259,8 @@ static int device_change_notifier(struct notifier_block *nb,
         case BUS_NOTIFY_UNBOUND_DRIVER:
                 if (!domain)
                         goto out;
+                if (iommu_pass_through)
+                        break;
                 detach_device(domain, devid);
                 break;
         case BUS_NOTIFY_ADD_DEVICE:
@@ -2051,19 +2085,47 @@ static void cleanup_domain(struct protection_domain *domain)
         write_unlock_irqrestore(&amd_iommu_devtable_lock, flags);
 }
 
-static int amd_iommu_domain_init(struct iommu_domain *dom)
+static void protection_domain_free(struct protection_domain *domain)
+{
+        if (!domain)
+                return;
+
+        if (domain->id)
+                domain_id_free(domain->id);
+
+        kfree(domain);
+}
+
+static struct protection_domain *protection_domain_alloc(void)
 {
         struct protection_domain *domain;
 
         domain = kzalloc(sizeof(*domain), GFP_KERNEL);
         if (!domain)
-                return -ENOMEM;
+                return NULL;
 
         spin_lock_init(&domain->lock);
-        domain->mode = PAGE_MODE_3_LEVEL;
         domain->id = domain_id_alloc();
         if (!domain->id)
+                goto out_err;
+
+        return domain;
+
+out_err:
+        kfree(domain);
+
+        return NULL;
+}
+
+static int amd_iommu_domain_init(struct iommu_domain *dom)
+{
+        struct protection_domain *domain;
+
+        domain = protection_domain_alloc();
+        if (!domain)
                 goto out_free;
+
+        domain->mode    = PAGE_MODE_3_LEVEL;
         domain->pt_root = (void *)get_zeroed_page(GFP_KERNEL);
         if (!domain->pt_root)
                 goto out_free;
@@ -2073,7 +2135,7 @@ static int amd_iommu_domain_init(struct iommu_domain *dom)
         return 0;
 
 out_free:
-        kfree(domain);
+        protection_domain_free(domain);
 
         return -ENOMEM;
 }
@@ -2254,3 +2316,46 @@ static struct iommu_ops amd_iommu_ops = {
         .domain_has_cap = amd_iommu_domain_has_cap,
 };
 
+/*****************************************************************************
+ *
+ * The next functions do a basic initialization of IOMMU for pass through
+ * mode
+ *
+ * In passthrough mode the IOMMU is initialized and enabled but not used for
+ * DMA-API translation.
+ *
+ *****************************************************************************/
+
+int __init amd_iommu_init_passthrough(void)
+{
+        struct pci_dev *dev = NULL;
+        u16 devid, devid2;
+
+        /* allocate passthroug domain */
+        pt_domain = protection_domain_alloc();
+        if (!pt_domain)
+                return -ENOMEM;
+
+        pt_domain->mode |= PAGE_MODE_NONE;
+
+        while ((dev = pci_get_device(PCI_ANY_ID, PCI_ANY_ID, dev)) != NULL) {
+                struct amd_iommu *iommu;
+
+                devid = calc_devid(dev->bus->number, dev->devfn);
+                if (devid > amd_iommu_last_bdf)
+                        continue;
+
+                devid2 = amd_iommu_alias_table[devid];
+
+                iommu = amd_iommu_rlookup_table[devid2];
+                if (!iommu)
+                        continue;
+
+                __attach_device(iommu, pt_domain, devid);
+                __attach_device(iommu, pt_domain, devid2);
+        }
+
+        pr_info("AMD-Vi: Initialized for Passthrough Mode\n");
+
+        return 0;
+}
diff --git a/arch/x86/kernel/amd_iommu_init.c b/arch/x86/kernel/amd_iommu_init.c
index 779ace292475..b4b61d462dcc 100644
--- a/arch/x86/kernel/amd_iommu_init.c
+++ b/arch/x86/kernel/amd_iommu_init.c
@@ -1252,12 +1252,18 @@ int __init amd_iommu_init(void)
         if (ret)
                 goto free;
 
-        ret = amd_iommu_init_dma_ops();
+        if (iommu_pass_through)
+                ret = amd_iommu_init_passthrough();
+        else
+                ret = amd_iommu_init_dma_ops();
         if (ret)
                 goto free;
 
         enable_iommus();
 
+        if (iommu_pass_through)
+                goto out;
+
         printk(KERN_INFO "AMD-Vi: device isolation ");
         if (amd_iommu_isolate)
                 printk("enabled\n");
diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c
index 1a041bcf506b..873aa079d166 100644
--- a/arch/x86/kernel/pci-dma.c
+++ b/arch/x86/kernel/pci-dma.c
@@ -32,7 +32,14 @@ int no_iommu __read_mostly;
 /* Set this to 1 if there is a HW IOMMU in the system */
 int iommu_detected __read_mostly = 0;
 
-int iommu_pass_through;
+/*
+ * This variable becomes 1 if iommu=pt is passed on the kernel command line.
+ * If this variable is 1, IOMMU implementations do no DMA ranslation for
+ * devices and allow every device to access to whole physical memory. This is
+ * useful if a user want to use an IOMMU only for KVM device assignment to
+ * guests and not for driver dma translation.
+ */
+int iommu_pass_through __read_mostly;
 
 dma_addr_t bad_dma_address __read_mostly = 0;
 EXPORT_SYMBOL(bad_dma_address);