Merge tag 'iommu-updates-v3.5' of git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu

Pull IOMMU updates from Joerg Roedel:
 "Not much stuff this time.  The only change to the IOMMU core code is
  the addition of a handle to the fault handling code.  A few updates to
  the AMD IOMMU driver to work around new errata.  The other patches are
  mostly fixes and enhancements to the existing ARM IOMMU drivers and
  documentation updates.

  A new IOMMU driver for the Exynos platform was also underway but got
  merged via the Samsung tree and is not part of this tree."

* tag 'iommu-updates-v3.5' of git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu:
  Documentation: kernel-parameters.txt Add amd_iommu_dump
  iommu/core: pass a user-provided token to fault handlers
  iommu/tegra: gart: Fix register offset correctly
  iommu: OMAP: device detach on domain destroy
  iommu: tegra/gart: Add device tree support
  iommu: tegra/gart: use correct gart_device
  iommu/tegra: smmu: Print device name correctly
  iommu/amd: Add workaround for event log erratum
  iommu/amd: Check for the right TLP prefix bit
  dma-debug: release free_entries_lock before saving stack trace

Documentation/devicetree/bindings/iommu/nvidia,tegra20-gart.txt

@@ -0,0 +1,14 @@
+NVIDIA Tegra 20 GART
+
+Required properties:
+- compatible: "nvidia,tegra20-gart"
+- reg: Two pairs of cells specifying the physical address and size of
+  the memory controller registers and the GART aperture respectively.
+
+Example:
+
+	gart {
+		compatible = "nvidia,tegra20-gart";
+		reg = <0x7000f024 0x00000018	/* controller registers */
+		       0x58000000 0x02000000>;	/* GART aperture */
+	};

Documentation/kernel-parameters.txt

@@ -335,6 +335,12 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 					  requirements as needed. This option
 					  does not override iommu=pt
 
+	amd_iommu_dump=	[HW,X86-64]
+			Enable AMD IOMMU driver option to dump the ACPI table
+			for AMD IOMMU. With this option enabled, AMD IOMMU
+			driver will print ACPI tables for AMD IOMMU during
+			IOMMU initialization.
+
 	amijoy.map=	[HW,JOY] Amiga joystick support
 			Map of devices attached to JOY0DAT and JOY1DAT
 			Format: <a>,<b>

drivers/iommu/amd_iommu.c

@@ -450,12 +450,27 @@ 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 +523,8 @@ 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)
@@ -2035,20 +2052,20 @@ 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;
 }
 
 /*

drivers/iommu/iommu.c

@@ -119,6 +119,7 @@ EXPORT_SYMBOL_GPL(iommu_present);
  * iommu_set_fault_handler() - set a fault handler for an iommu domain
  * @domain: iommu domain
  * @handler: fault handler
+ * @token: user data, will be passed back to the fault handler
  *
  * This function should be used by IOMMU users which want to be notified
  * whenever an IOMMU fault happens.
@@ -127,11 +128,13 @@ EXPORT_SYMBOL_GPL(iommu_present);
  * error code otherwise.
  */
 void iommu_set_fault_handler(struct iommu_domain *domain,
-					iommu_fault_handler_t handler)
+					iommu_fault_handler_t handler,
+					void *token)
 {
 	BUG_ON(!domain);
 
 	domain->handler = handler;
+	domain->handler_token = token;
 }
 EXPORT_SYMBOL_GPL(iommu_set_fault_handler);
 

drivers/iommu/omap-iommu.c

@@ -41,11 +41,13 @@
  * @pgtable:	the page table
  * @iommu_dev:	an omap iommu device attached to this domain. only a single
  *		iommu device can be attached for now.
+ * @dev:	Device using this domain.
  * @lock:	domain lock, should be taken when attaching/detaching
  */
 struct omap_iommu_domain {
 	u32 *pgtable;
 	struct omap_iommu *iommu_dev;
+	struct device *dev;
 	spinlock_t lock;
 };
 
@@ -1081,6 +1083,7 @@ omap_iommu_attach_dev(struct iommu_domain *domain, struct device *dev)
 	}
 
 	omap_domain->iommu_dev = arch_data->iommu_dev = oiommu;
+	omap_domain->dev = dev;
 	oiommu->domain = domain;
 
 out:
@@ -1088,19 +1091,16 @@ out:
 	return ret;
 }
 
-static void omap_iommu_detach_dev(struct iommu_domain *domain,
-				 struct device *dev)
+static void _omap_iommu_detach_dev(struct omap_iommu_domain *omap_domain,
+			struct device *dev)
 {
-	struct omap_iommu_domain *omap_domain = domain->priv;
-	struct omap_iommu_arch_data *arch_data = dev->archdata.iommu;
 	struct omap_iommu *oiommu = dev_to_omap_iommu(dev);
-
-	spin_lock(&omap_domain->lock);
+	struct omap_iommu_arch_data *arch_data = dev->archdata.iommu;
 
 	/* only a single device is supported per domain for now */
 	if (omap_domain->iommu_dev != oiommu) {
 		dev_err(dev, "invalid iommu device\n");
-		goto out;
+		return;
 	}
 
 	iopgtable_clear_entry_all(oiommu);
@@ -1108,8 +1108,16 @@ static void omap_iommu_detach_dev(struct iommu_domain *domain,
 	omap_iommu_detach(oiommu);
 
 	omap_domain->iommu_dev = arch_data->iommu_dev = NULL;
+	omap_domain->dev = NULL;
+}
 
-out:
+static void omap_iommu_detach_dev(struct iommu_domain *domain,
+				 struct device *dev)
+{
+	struct omap_iommu_domain *omap_domain = domain->priv;
+
+	spin_lock(&omap_domain->lock);
+	_omap_iommu_detach_dev(omap_domain, dev);
 	spin_unlock(&omap_domain->lock);
 }
 
@@ -1148,13 +1156,19 @@ out:
 	return -ENOMEM;
 }
 
-/* assume device was already detached */
 static void omap_iommu_domain_destroy(struct iommu_domain *domain)
 {
 	struct omap_iommu_domain *omap_domain = domain->priv;
 
 	domain->priv = NULL;
 
+	/*
+	 * An iommu device is still attached
+	 * (currently, only one device can be attached) ?
+	 */
+	if (omap_domain->iommu_dev)
+		_omap_iommu_detach_dev(omap_domain, omap_domain->dev);
+
 	kfree(omap_domain->pgtable);
 	kfree(omap_domain);
 }

drivers/iommu/tegra-gart.c

@@ -29,15 +29,17 @@
 #include <linux/device.h>
 #include <linux/io.h>
 #include <linux/iommu.h>
+#include <linux/of.h>
 
 #include <asm/cacheflush.h>
 
 /* bitmap of the page sizes currently supported */
 #define GART_IOMMU_PGSIZES	(SZ_4K)
 
-#define GART_CONFIG		0x24
-#define GART_ENTRY_ADDR		0x28
-#define GART_ENTRY_DATA		0x2c
+#define GART_REG_BASE		0x24
+#define GART_CONFIG		(0x24 - GART_REG_BASE)
+#define GART_ENTRY_ADDR		(0x28 - GART_REG_BASE)
+#define GART_ENTRY_DATA		(0x2c - GART_REG_BASE)
 #define GART_ENTRY_PHYS_ADDR_VALID	(1 << 31)
 
 #define GART_PAGE_SHIFT		12
@@ -158,7 +160,7 @@ static int gart_iommu_attach_dev(struct iommu_domain *domain,
 	struct gart_client *client, *c;
 	int err = 0;
 
-	gart = dev_get_drvdata(dev->parent);
+	gart = gart_handle;
 	if (!gart)
 		return -EINVAL;
 	domain->priv = gart;
@@ -422,6 +424,14 @@ const struct dev_pm_ops tegra_gart_pm_ops = {
 	.resume		= tegra_gart_resume,
 };
 
+#ifdef CONFIG_OF
+static struct of_device_id tegra_gart_of_match[] __devinitdata = {
+	{ .compatible = "nvidia,tegra20-gart", },
+	{ },
+};
+MODULE_DEVICE_TABLE(of, tegra_gart_of_match);
+#endif
+
 static struct platform_driver tegra_gart_driver = {
 	.probe		= tegra_gart_probe,
 	.remove		= tegra_gart_remove,
@@ -429,6 +439,7 @@ static struct platform_driver tegra_gart_driver = {
 		.owner	= THIS_MODULE,
 		.name	= "tegra-gart",
 		.pm	= &tegra_gart_pm_ops,
+		.of_match_table = of_match_ptr(tegra_gart_of_match),
 	},
 };
 
@@ -448,4 +459,5 @@ module_exit(tegra_gart_exit);
 
 MODULE_DESCRIPTION("IOMMU API for GART in Tegra20");
 MODULE_AUTHOR("Hiroshi DOYU <hdoyu@nvidia.com>");
+MODULE_ALIAS("platform:tegra-gart");
 MODULE_LICENSE("GPL v2");

drivers/iommu/tegra-smmu.c

@@ -733,7 +733,7 @@ static int smmu_iommu_attach_dev(struct iommu_domain *domain,
 		pr_info("Reserve \"page zero\" for AVP vectors using a common dummy\n");
 	}
 
-	dev_dbg(smmu->dev, "%s is attached\n", dev_name(c->dev));
+	dev_dbg(smmu->dev, "%s is attached\n", dev_name(dev));
 	return 0;
 
 err_client:

drivers/remoteproc/remoteproc_core.c

@@ -78,7 +78,7 @@ typedef int (*rproc_handle_resource_t)(struct rproc *rproc, void *, int avail);
  * the recovery of the remote processor.
  */
 static int rproc_iommu_fault(struct iommu_domain *domain, struct device *dev,
-		unsigned long iova, int flags)
+		unsigned long iova, int flags, void *token)
 {
 	dev_err(dev, "iommu fault: da 0x%lx flags 0x%x\n", iova, flags);
 
@@ -117,7 +117,7 @@ static int rproc_enable_iommu(struct rproc *rproc)
 		return -ENOMEM;
 	}
 
-	iommu_set_fault_handler(domain, rproc_iommu_fault);
+	iommu_set_fault_handler(domain, rproc_iommu_fault, rproc);
 
 	ret = iommu_attach_device(domain, dev);
 	if (ret) {

include/linux/iommu.h

@@ -35,12 +35,13 @@ struct iommu_domain;
 #define IOMMU_FAULT_WRITE	0x1
 
 typedef int (*iommu_fault_handler_t)(struct iommu_domain *,
-				struct device *, unsigned long, int);
+			struct device *, unsigned long, int, void *);
 
 struct iommu_domain {
 	struct iommu_ops *ops;
 	void *priv;
 	iommu_fault_handler_t handler;
+	void *handler_token;
 };
 
 #define IOMMU_CAP_CACHE_COHERENCY	0x1
@@ -95,7 +96,7 @@ extern phys_addr_t iommu_iova_to_phys(struct iommu_domain *domain,
 extern int iommu_domain_has_cap(struct iommu_domain *domain,
 				unsigned long cap);
 extern void iommu_set_fault_handler(struct iommu_domain *domain,
-					iommu_fault_handler_t handler);
+			iommu_fault_handler_t handler, void *token);
 extern int iommu_device_group(struct device *dev, unsigned int *groupid);
 
 /**
@@ -132,7 +133,8 @@ static inline int report_iommu_fault(struct iommu_domain *domain,
 	 * invoke it.
 	 */
 	if (domain->handler)
-		ret = domain->handler(domain, dev, iova, flags);
+		ret = domain->handler(domain, dev, iova, flags,
+						domain->handler_token);
 
 	return ret;
 }
@@ -191,7 +193,7 @@ static inline int domain_has_cap(struct iommu_domain *domain,
 }
 
 static inline void iommu_set_fault_handler(struct iommu_domain *domain,
-					iommu_fault_handler_t handler)
+				iommu_fault_handler_t handler, void *token)
 {
 }
 

lib/dma-debug.c

@@ -430,7 +430,7 @@ static struct dma_debug_entry *__dma_entry_alloc(void)
  */
 static struct dma_debug_entry *dma_entry_alloc(void)
 {
-	struct dma_debug_entry *entry = NULL;
+	struct dma_debug_entry *entry;
 	unsigned long flags;
 
 	spin_lock_irqsave(&free_entries_lock, flags);
@@ -438,11 +438,14 @@ static struct dma_debug_entry *dma_entry_alloc(void)
 	if (list_empty(&free_entries)) {
 		pr_err("DMA-API: debugging out of memory - disabling\n");
 		global_disable = true;
-		goto out;
+		spin_unlock_irqrestore(&free_entries_lock, flags);
+		return NULL;
 	}
 
 	entry = __dma_entry_alloc();
 
+	spin_unlock_irqrestore(&free_entries_lock, flags);
+
 #ifdef CONFIG_STACKTRACE
 	entry->stacktrace.max_entries = DMA_DEBUG_STACKTRACE_ENTRIES;
 	entry->stacktrace.entries = entry->st_entries;
@@ -450,9 +453,6 @@ static struct dma_debug_entry *dma_entry_alloc(void)
 	save_stack_trace(&entry->stacktrace);
 #endif
 
-out:
-	spin_unlock_irqrestore(&free_entries_lock, flags);
-
 	return entry;
 }