Merge branch 'stable-linux-3.4.y' into tilt-3.4-up

Conflicts:
	arch/arm/kernel/traps.c
	arch/arm/vfp/entry.S
	drivers/base/power/main.c
	drivers/net/tun.c
	include/linux/rpmsg.h
	net/mac80211/mlme.c

7 files changed, 116 insertions, 57 deletions

diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c
index a5bee8e2dfce..57ed244cf990 100644
--- a/drivers/iommu/amd_iommu.c
+++ b/drivers/iommu/amd_iommu.c
@@ -83,6 +83,8 @@ static struct iommu_ops amd_iommu_ops;
 static ATOMIC_NOTIFIER_HEAD(ppr_notifier);
 int amd_iommu_max_glx_val = -1;
 
+static struct dma_map_ops amd_iommu_dma_ops;
+
 /*
  * general struct to manage commands send to an IOMMU
  */
@@ -450,12 +452,27 @@ static void dump_command(unsigned long phys_addr)
 
 static void iommu_print_event(struct amd_iommu *iommu, void *__evt)
 {
-	u32 *event = __evt;
-	int type  = (event[1] >> EVENT_TYPE_SHIFT)  & EVENT_TYPE_MASK;
-	int devid = (event[0] >> EVENT_DEVID_SHIFT) & EVENT_DEVID_MASK;
-	int domid = (event[1] >> EVENT_DOMID_SHIFT) & EVENT_DOMID_MASK;
-	int flags = (event[1] >> EVENT_FLAGS_SHIFT) & EVENT_FLAGS_MASK;
-	u64 address = (u64)(((u64)event[3]) << 32) | event[2];
+	int type, devid, domid, flags;
+	volatile u32 *event = __evt;
+	int count = 0;
+	u64 address;
+
+retry:
+	type    = (event[1] >> EVENT_TYPE_SHIFT)  & EVENT_TYPE_MASK;
+	devid   = (event[0] >> EVENT_DEVID_SHIFT) & EVENT_DEVID_MASK;
+	domid   = (event[1] >> EVENT_DOMID_SHIFT) & EVENT_DOMID_MASK;
+	flags   = (event[1] >> EVENT_FLAGS_SHIFT) & EVENT_FLAGS_MASK;
+	address = (u64)(((u64)event[3]) << 32) | event[2];
+
+	if (type == 0) {
+		/* Did we hit the erratum? */
+		if (++count == LOOP_TIMEOUT) {
+			pr_err("AMD-Vi: No event written to event log\n");
+			return;
+		}
+		udelay(1);
+		goto retry;
+	}
 
 	printk(KERN_ERR "AMD-Vi: Event logged [");
 
@@ -508,6 +525,8 @@ static void iommu_print_event(struct amd_iommu *iommu, void *__evt)
 	default:
 		printk(KERN_ERR "UNKNOWN type=0x%02x]\n", type);
 	}
+
+	memset(__evt, 0, 4 * sizeof(u32));
 }
 
 static void iommu_poll_events(struct amd_iommu *iommu)
@@ -530,26 +549,12 @@ static void iommu_poll_events(struct amd_iommu *iommu)
 	spin_unlock_irqrestore(&iommu->lock, flags);
 }
 
-static void iommu_handle_ppr_entry(struct amd_iommu *iommu, u32 head)
+static void iommu_handle_ppr_entry(struct amd_iommu *iommu, u64 *raw)
 {
 	struct amd_iommu_fault fault;
-	volatile u64 *raw;
-	int i;
 
 	INC_STATS_COUNTER(pri_requests);
 
-	raw = (u64 *)(iommu->ppr_log + head);
-
-	/*
-	 * Hardware bug: Interrupt may arrive before the entry is written to
-	 * memory. If this happens we need to wait for the entry to arrive.
-	 */
-	for (i = 0; i < LOOP_TIMEOUT; ++i) {
-		if (PPR_REQ_TYPE(raw[0]) != 0)
-			break;
-		udelay(1);
-	}
-
 	if (PPR_REQ_TYPE(raw[0]) != PPR_REQ_FAULT) {
 		pr_err_ratelimited("AMD-Vi: Unknown PPR request received\n");
 		return;
@@ -561,12 +566,6 @@ static void iommu_handle_ppr_entry(struct amd_iommu *iommu, u32 head)
 	fault.tag       = PPR_TAG(raw[0]);
 	fault.flags     = PPR_FLAGS(raw[0]);
 
-	/*
-	 * To detect the hardware bug we need to clear the entry
-	 * to back to zero.
-	 */
-	raw[0] = raw[1] = 0;
-
 	atomic_notifier_call_chain(&ppr_notifier, 0, &fault);
 }
 
@@ -578,25 +577,62 @@ static void iommu_poll_ppr_log(struct amd_iommu *iommu)
 	if (iommu->ppr_log == NULL)
 		return;
 
+	/* enable ppr interrupts again */
+	writel(MMIO_STATUS_PPR_INT_MASK, iommu->mmio_base + MMIO_STATUS_OFFSET);
+
 	spin_lock_irqsave(&iommu->lock, flags);
 
 	head = readl(iommu->mmio_base + MMIO_PPR_HEAD_OFFSET);
 	tail = readl(iommu->mmio_base + MMIO_PPR_TAIL_OFFSET);
 
 	while (head != tail) {
+		volatile u64 *raw;
+		u64 entry[2];
+		int i;
 
-		/* Handle PPR entry */
-		iommu_handle_ppr_entry(iommu, head);
+		raw = (u64 *)(iommu->ppr_log + head);
+
+		/*
+		 * Hardware bug: Interrupt may arrive before the entry is
+		 * written to memory. If this happens we need to wait for the
+		 * entry to arrive.
+		 */
+		for (i = 0; i < LOOP_TIMEOUT; ++i) {
+			if (PPR_REQ_TYPE(raw[0]) != 0)
+				break;
+			udelay(1);
+		}
 
-		/* Update and refresh ring-buffer state*/
+		/* Avoid memcpy function-call overhead */
+		entry[0] = raw[0];
+		entry[1] = raw[1];
+
+		/*
+		 * To detect the hardware bug we need to clear the entry
+		 * back to zero.
+		 */
+		raw[0] = raw[1] = 0UL;
+
+		/* Update head pointer of hardware ring-buffer */
 		head = (head + PPR_ENTRY_SIZE) % PPR_LOG_SIZE;
 		writel(head, iommu->mmio_base + MMIO_PPR_HEAD_OFFSET);
+
+		/*
+		 * Release iommu->lock because ppr-handling might need to
+		 * re-aquire it
+		 */
+		spin_unlock_irqrestore(&iommu->lock, flags);
+
+		/* Handle PPR entry */
+		iommu_handle_ppr_entry(iommu, entry);
+
+		spin_lock_irqsave(&iommu->lock, flags);
+
+		/* Refresh ring-buffer information */
+		head = readl(iommu->mmio_base + MMIO_PPR_HEAD_OFFSET);
 		tail = readl(iommu->mmio_base + MMIO_PPR_TAIL_OFFSET);
 	}
 
-	/* enable ppr interrupts again */
-	writel(MMIO_STATUS_PPR_INT_MASK, iommu->mmio_base + MMIO_STATUS_OFFSET);
-
 	spin_unlock_irqrestore(&iommu->lock, flags);
 }
 
@@ -2035,20 +2071,20 @@ out_err:
 }
 
 /* FIXME: Move this to PCI code */
-#define PCI_PRI_TLP_OFF		(1 << 2)
+#define PCI_PRI_TLP_OFF		(1 << 15)
 
 bool pci_pri_tlp_required(struct pci_dev *pdev)
 {
-	u16 control;
+	u16 status;
 	int pos;
 
 	pos = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_PRI);
 	if (!pos)
 		return false;
 
-	pci_read_config_word(pdev, pos + PCI_PRI_CTRL, &control);
+	pci_read_config_word(pdev, pos + PCI_PRI_STATUS, &status);
 
-	return (control & PCI_PRI_TLP_OFF) ? true : false;
+	return (status & PCI_PRI_TLP_OFF) ? true : false;
 }
 
 /*
@@ -2218,6 +2254,18 @@ static int device_change_notifier(struct notifier_block *nb,
 
 		iommu_init_device(dev);
 
+		/*
+		 * dev_data is still NULL and
+		 * got initialized in iommu_init_device
+		 */
+		dev_data = get_dev_data(dev);
+
+		if (iommu_pass_through || dev_data->iommu_v2) {
+			dev_data->passthrough = true;
+			attach_device(dev, pt_domain);
+			break;
+		}
+
 		domain = domain_for_device(dev);
 
 		/* allocate a protection domain if a device is added */
@@ -2233,6 +2281,10 @@ static int device_change_notifier(struct notifier_block *nb,
 		list_add_tail(&dma_domain->list, &iommu_pd_list);
 		spin_unlock_irqrestore(&iommu_pd_list_lock, flags);
 
+		dev_data = get_dev_data(dev);
+
+		dev->archdata.dma_ops = &amd_iommu_dma_ops;
+
 		break;
 	case BUS_NOTIFY_DEL_DEVICE:
 
diff --git a/drivers/iommu/amd_iommu_init.c b/drivers/iommu/amd_iommu_init.c
index c56790375e0f..c04ddca7f12f 100644
--- a/drivers/iommu/amd_iommu_init.c
+++ b/drivers/iommu/amd_iommu_init.c
@@ -1029,6 +1029,9 @@ static int __init init_iommu_one(struct amd_iommu *iommu, struct ivhd_header *h)
 	if (!iommu->dev)
 		return 1;
 
+	iommu->root_pdev = pci_get_bus_and_slot(iommu->dev->bus->number,
+						PCI_DEVFN(0, 0));
+
 	iommu->cap_ptr = h->cap_ptr;
 	iommu->pci_seg = h->pci_seg;
 	iommu->mmio_phys = h->mmio_phys;
@@ -1323,20 +1326,16 @@ static void iommu_apply_resume_quirks(struct amd_iommu *iommu)
 {
 	int i, j;
 	u32 ioc_feature_control;
-	struct pci_dev *pdev = NULL;
+	struct pci_dev *pdev = iommu->root_pdev;
 
 	/* RD890 BIOSes may not have completely reconfigured the iommu */
-	if (!is_rd890_iommu(iommu->dev))
+	if (!is_rd890_iommu(iommu->dev) || !pdev)
 		return;
 
 	/*
 	 * First, we need to ensure that the iommu is enabled. This is
 	 * controlled by a register in the northbridge
 	 */
-	pdev = pci_get_bus_and_slot(iommu->dev->bus->number, PCI_DEVFN(0, 0));
-
-	if (!pdev)
-		return;
 
 	/* Select Northbridge indirect register 0x75 and enable writing */
 	pci_write_config_dword(pdev, 0x60, 0x75 | (1 << 7));
@@ -1346,8 +1345,6 @@ static void iommu_apply_resume_quirks(struct amd_iommu *iommu)
 	if (!(ioc_feature_control & 0x1))
 		pci_write_config_dword(pdev, 0x64, ioc_feature_control | 1);
 
-	pci_dev_put(pdev);
-
 	/* Restore the iommu BAR */
 	pci_write_config_dword(iommu->dev, iommu->cap_ptr + 4,
 			       iommu->stored_addr_lo);
@@ -1644,6 +1641,8 @@ static int __init amd_iommu_init(void)
 
 	amd_iommu_init_api();
 
+	x86_platform.iommu_shutdown = disable_iommus;
+
 	if (iommu_pass_through)
 		goto out;
 
@@ -1652,8 +1651,6 @@ static int __init amd_iommu_init(void)
 	else
 		printk(KERN_INFO "AMD-Vi: Lazy IO/TLB flushing enabled\n");
 
-	x86_platform.iommu_shutdown = disable_iommus;
-
 out:
 	return ret;
 
diff --git a/drivers/iommu/amd_iommu_types.h b/drivers/iommu/amd_iommu_types.h
index 2452f3b71736..24355559a2ad 100644
--- a/drivers/iommu/amd_iommu_types.h
+++ b/drivers/iommu/amd_iommu_types.h
@@ -481,6 +481,9 @@ struct amd_iommu {
 	/* Pointer to PCI device of this IOMMU */
 	struct pci_dev *dev;
 
+	/* Cache pdev to root device for resume quirks */
+	struct pci_dev *root_pdev;
+
 	/* physical address of MMIO space */
 	u64 mmio_phys;
 	/* virtual address of MMIO space */
diff --git a/drivers/iommu/amd_iommu_v2.c b/drivers/iommu/amd_iommu_v2.c
index 036fe9bf157e..a1f1bc876043 100644
--- a/drivers/iommu/amd_iommu_v2.c
+++ b/drivers/iommu/amd_iommu_v2.c
@@ -681,6 +681,8 @@ int amd_iommu_bind_pasid(struct pci_dev *pdev, int pasid,
 
 	atomic_set(&pasid_state->count, 1);
 	init_waitqueue_head(&pasid_state->wq);
+	spin_lock_init(&pasid_state->lock);
+
 	pasid_state->task         = task;
 	pasid_state->mm           = get_task_mm(task);
 	pasid_state->device_state = dev_state;
diff --git a/drivers/iommu/dmar.c b/drivers/iommu/dmar.c
index 35c1e17fce1d..97b2e21ac46a 100644
--- a/drivers/iommu/dmar.c
+++ b/drivers/iommu/dmar.c
@@ -1056,8 +1056,8 @@ static const char *intr_remap_fault_reasons[] =
 
 const char *dmar_get_fault_reason(u8 fault_reason, int *fault_type)
 {
-	if (fault_reason >= 0x20 && (fault_reason <= 0x20 +
-				     ARRAY_SIZE(intr_remap_fault_reasons))) {
+	if (fault_reason >= 0x20 && (fault_reason - 0x20 <
+					ARRAY_SIZE(intr_remap_fault_reasons))) {
 		*fault_type = INTR_REMAP;
 		return intr_remap_fault_reasons[fault_reason - 0x20];
 	} else if (fault_reason < ARRAY_SIZE(dma_remap_fault_reasons)) {
diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c
index f93d5ac8f81c..5fda348702c1 100644
--- a/drivers/iommu/intel-iommu.c
+++ b/drivers/iommu/intel-iommu.c
@@ -2286,12 +2286,6 @@ static int domain_add_dev_info(struct dmar_domain *domain,
 	if (!info)
 		return -ENOMEM;
 
-	ret = domain_context_mapping(domain, pdev, translation);
-	if (ret) {
-		free_devinfo_mem(info);
-		return ret;
-	}
-
 	info->segment = pci_domain_nr(pdev->bus);
 	info->bus = pdev->bus->number;
 	info->devfn = pdev->devfn;
@@ -2304,6 +2298,17 @@ static int domain_add_dev_info(struct dmar_domain *domain,
 	pdev->dev.archdata.iommu = info;
 	spin_unlock_irqrestore(&device_domain_lock, flags);
 
+	ret = domain_context_mapping(domain, pdev, translation);
+	if (ret) {
+		spin_lock_irqsave(&device_domain_lock, flags);
+		list_del(&info->link);
+		list_del(&info->global);
+		pdev->dev.archdata.iommu = NULL;
+		spin_unlock_irqrestore(&device_domain_lock, flags);
+		free_devinfo_mem(info);
+		return ret;
+	}
+
 	return 0;
 }
 
diff --git a/drivers/iommu/tegra-smmu.c b/drivers/iommu/tegra-smmu.c
index eb93c821f592..17ef6c493662 100644
--- a/drivers/iommu/tegra-smmu.c
+++ b/drivers/iommu/tegra-smmu.c
@@ -550,13 +550,13 @@ static int alloc_pdir(struct smmu_as *as)
 		return 0;
 
 	as->pte_count = devm_kzalloc(smmu->dev,
-		     sizeof(as->pte_count[0]) * SMMU_PDIR_COUNT, GFP_KERNEL);
+		     sizeof(as->pte_count[0]) * SMMU_PDIR_COUNT, GFP_ATOMIC);
 	if (!as->pte_count) {
 		dev_err(smmu->dev,
 			"failed to allocate smmu_device PTE cunters\n");
 		return -ENOMEM;
 	}
-	as->pdir_page = alloc_page(GFP_KERNEL | __GFP_DMA);
+	as->pdir_page = alloc_page(GFP_ATOMIC | __GFP_DMA);
 	if (!as->pdir_page) {
 		dev_err(smmu->dev,
 			"failed to allocate smmu_device page directory\n");