Merge tag 'iommu-updates-v3.8' of git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu

Pull IOMMU updates from Joerg Roedel:
 "A few new features this merge-window.  The most important one is
  probably, that dma-debug now warns if a dma-handle is not checked with
  dma_mapping_error by the device driver.  This requires minor changes
  to some architectures which make use of dma-debug.  Most of these
  changes have the respective Acks by the Arch-Maintainers.

  Besides that there are updates to the AMD IOMMU driver for refactor
  the IOMMU-Groups support and to make sure it does not trigger a
  hardware erratum.

  The OMAP changes (for which I pulled in a branch from Tony Lindgren's
  tree) have a conflict in linux-next with the arm-soc tree.  The
  conflict is in the file arch/arm/mach-omap2/clock44xx_data.c which is
  deleted in the arm-soc tree.  It is safe to delete the file too so
  solve the conflict.  Similar changes are done in the arm-soc tree in
  the common clock framework migration.  A missing hunk from the patch
  in the IOMMU tree will be submitted as a seperate patch when the
  merge-window is closed."

* tag 'iommu-updates-v3.8' of git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu: (29 commits)
  ARM: dma-mapping: support debug_dma_mapping_error
  ARM: OMAP4: hwmod data: ipu and dsp to use parent clocks instead of leaf clocks
  iommu/omap: Adapt to runtime pm
  iommu/omap: Migrate to hwmod framework
  iommu/omap: Keep mmu enabled when requested
  iommu/omap: Remove redundant clock handling on ISR
  iommu/amd: Remove obsolete comment
  iommu/amd: Don't use 512GB pages
  iommu/tegra: smmu: Move bus_set_iommu after probe for multi arch
  iommu/tegra: gart: Move bus_set_iommu after probe for multi arch
  iommu/tegra: smmu: Remove unnecessary PTC/TLB flush all
  tile: dma_debug: add debug_dma_mapping_error support
  sh: dma_debug: add debug_dma_mapping_error support
  powerpc: dma_debug: add debug_dma_mapping_error support
  mips: dma_debug: add debug_dma_mapping_error support
  microblaze: dma-mapping: support debug_dma_mapping_error
  ia64: dma_debug: add debug_dma_mapping_error support
  c6x: dma_debug: add debug_dma_mapping_error support
  ARM64: dma_debug: add debug_dma_mapping_error support
  intel-iommu: Prevent devices with RMRRs from being placed into SI Domain
  ...

8 files changed, 215 insertions, 128 deletions

diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c
index 55074cb..c1c74e0 100644
--- a/drivers/iommu/amd_iommu.c
+++ b/drivers/iommu/amd_iommu.c
@@ -57,17 +57,9 @@
  * physically contiguous memory regions it is mapping into page sizes
  * that we support.
  *
- * Traditionally the IOMMU core just handed us the mappings directly,
- * after making sure the size is an order of a 4KiB page and that the
- * mapping has natural alignment.
- *
- * To retain this behavior, we currently advertise that we support
- * all page sizes that are an order of 4KiB.
- *
- * If at some point we'd like to utilize the IOMMU core's new behavior,
- * we could change this to advertise the real page sizes we support.
+ * 512GB Pages are not supported due to a hardware bug
  */
-#define AMD_IOMMU_PGSIZES	(~0xFFFUL)
+#define AMD_IOMMU_PGSIZES	((~0xFFFUL) & ~(2ULL << 38))
 
 static DEFINE_RWLOCK(amd_iommu_devtable_lock);
 
@@ -140,6 +132,9 @@ static void free_dev_data(struct iommu_dev_data *dev_data)
 	list_del(&dev_data->dev_data_list);
 	spin_unlock_irqrestore(&dev_data_list_lock, flags);
 
+	if (dev_data->group)
+		iommu_group_put(dev_data->group);
+
 	kfree(dev_data);
 }
 
@@ -274,41 +269,23 @@ static void swap_pci_ref(struct pci_dev **from, struct pci_dev *to)
 	*from = to;
 }
 
-#define REQ_ACS_FLAGS	(PCI_ACS_SV | PCI_ACS_RR | PCI_ACS_CR | PCI_ACS_UF)
-
-static int iommu_init_device(struct device *dev)
+static struct pci_bus *find_hosted_bus(struct pci_bus *bus)
 {
-	struct pci_dev *dma_pdev = NULL, *pdev = to_pci_dev(dev);
-	struct iommu_dev_data *dev_data;
-	struct iommu_group *group;
-	u16 alias;
-	int ret;
-
-	if (dev->archdata.iommu)
-		return 0;
-
-	dev_data = find_dev_data(get_device_id(dev));
-	if (!dev_data)
-		return -ENOMEM;
-
-	alias = amd_iommu_alias_table[dev_data->devid];
-	if (alias != dev_data->devid) {
-		struct iommu_dev_data *alias_data;
+	while (!bus->self) {
+		if (!pci_is_root_bus(bus))
+			bus = bus->parent;
+		else
+			return ERR_PTR(-ENODEV);
+	}
 
-		alias_data = find_dev_data(alias);
-		if (alias_data == NULL) {
-			pr_err("AMD-Vi: Warning: Unhandled device %s\n",
-					dev_name(dev));
-			free_dev_data(dev_data);
-			return -ENOTSUPP;
-		}
-		dev_data->alias_data = alias_data;
+	return bus;
+}
 
-		dma_pdev = pci_get_bus_and_slot(alias >> 8, alias & 0xff);
-	}
+#define REQ_ACS_FLAGS	(PCI_ACS_SV | PCI_ACS_RR | PCI_ACS_CR | PCI_ACS_UF)
 
-	if (dma_pdev == NULL)
-		dma_pdev = pci_dev_get(pdev);
+static struct pci_dev *get_isolation_root(struct pci_dev *pdev)
+{
+	struct pci_dev *dma_pdev = pdev;
 
 	/* Account for quirked devices */
 	swap_pci_ref(&dma_pdev, pci_get_dma_source(dma_pdev));
@@ -330,14 +307,9 @@ static int iommu_init_device(struct device *dev)
 	 * Finding the next device may require skipping virtual buses.
 	 */
 	while (!pci_is_root_bus(dma_pdev->bus)) {
-		struct pci_bus *bus = dma_pdev->bus;
-
-		while (!bus->self) {
-			if (!pci_is_root_bus(bus))
-				bus = bus->parent;
-			else
-				goto root_bus;
-		}
+		struct pci_bus *bus = find_hosted_bus(dma_pdev->bus);
+		if (IS_ERR(bus))
+			break;
 
 		if (pci_acs_path_enabled(bus->self, NULL, REQ_ACS_FLAGS))
 			break;
@@ -345,19 +317,137 @@ static int iommu_init_device(struct device *dev)
 		swap_pci_ref(&dma_pdev, pci_dev_get(bus->self));
 	}
 
-root_bus:
-	group = iommu_group_get(&dma_pdev->dev);
-	pci_dev_put(dma_pdev);
+	return dma_pdev;
+}
+
+static int use_pdev_iommu_group(struct pci_dev *pdev, struct device *dev)
+{
+	struct iommu_group *group = iommu_group_get(&pdev->dev);
+	int ret;
+
 	if (!group) {
 		group = iommu_group_alloc();
 		if (IS_ERR(group))
 			return PTR_ERR(group);
+
+		WARN_ON(&pdev->dev != dev);
 	}
 
 	ret = iommu_group_add_device(group, dev);
-
 	iommu_group_put(group);
+	return ret;
+}
+
+static int use_dev_data_iommu_group(struct iommu_dev_data *dev_data,
+				    struct device *dev)
+{
+	if (!dev_data->group) {
+		struct iommu_group *group = iommu_group_alloc();
+		if (IS_ERR(group))
+			return PTR_ERR(group);
+
+		dev_data->group = group;
+	}
+
+	return iommu_group_add_device(dev_data->group, dev);
+}
+
+static int init_iommu_group(struct device *dev)
+{
+	struct iommu_dev_data *dev_data;
+	struct iommu_group *group;
+	struct pci_dev *dma_pdev;
+	int ret;
+
+	group = iommu_group_get(dev);
+	if (group) {
+		iommu_group_put(group);
+		return 0;
+	}
+
+	dev_data = find_dev_data(get_device_id(dev));
+	if (!dev_data)
+		return -ENOMEM;
+
+	if (dev_data->alias_data) {
+		u16 alias;
+		struct pci_bus *bus;
+
+		if (dev_data->alias_data->group)
+			goto use_group;
+
+		/*
+		 * If the alias device exists, it's effectively just a first
+		 * level quirk for finding the DMA source.
+		 */
+		alias = amd_iommu_alias_table[dev_data->devid];
+		dma_pdev = pci_get_bus_and_slot(alias >> 8, alias & 0xff);
+		if (dma_pdev) {
+			dma_pdev = get_isolation_root(dma_pdev);
+			goto use_pdev;
+		}
+
+		/*
+		 * If the alias is virtual, try to find a parent device
+		 * and test whether the IOMMU group is actualy rooted above
+		 * the alias.  Be careful to also test the parent device if
+		 * we think the alias is the root of the group.
+		 */
+		bus = pci_find_bus(0, alias >> 8);
+		if (!bus)
+			goto use_group;
+
+		bus = find_hosted_bus(bus);
+		if (IS_ERR(bus) || !bus->self)
+			goto use_group;
+
+		dma_pdev = get_isolation_root(pci_dev_get(bus->self));
+		if (dma_pdev != bus->self || (dma_pdev->multifunction &&
+		    !pci_acs_enabled(dma_pdev, REQ_ACS_FLAGS)))
+			goto use_pdev;
+
+		pci_dev_put(dma_pdev);
+		goto use_group;
+	}
+
+	dma_pdev = get_isolation_root(pci_dev_get(to_pci_dev(dev)));
+use_pdev:
+	ret = use_pdev_iommu_group(dma_pdev, dev);
+	pci_dev_put(dma_pdev);
+	return ret;
+use_group:
+	return use_dev_data_iommu_group(dev_data->alias_data, dev);
+}
+
+static int iommu_init_device(struct device *dev)
+{
+	struct pci_dev *pdev = to_pci_dev(dev);
+	struct iommu_dev_data *dev_data;
+	u16 alias;
+	int ret;
+
+	if (dev->archdata.iommu)
+		return 0;
+
+	dev_data = find_dev_data(get_device_id(dev));
+	if (!dev_data)
+		return -ENOMEM;
+
+	alias = amd_iommu_alias_table[dev_data->devid];
+	if (alias != dev_data->devid) {
+		struct iommu_dev_data *alias_data;
+
+		alias_data = find_dev_data(alias);
+		if (alias_data == NULL) {
+			pr_err("AMD-Vi: Warning: Unhandled device %s\n",
+					dev_name(dev));
+			free_dev_data(dev_data);
+			return -ENOTSUPP;
+		}
+		dev_data->alias_data = alias_data;
+	}
 
+	ret = init_iommu_group(dev);
 	if (ret)
 		return ret;
 
diff --git a/drivers/iommu/amd_iommu_types.h b/drivers/iommu/amd_iommu_types.h
index c9aa3d0..e38ab43 100644
--- a/drivers/iommu/amd_iommu_types.h
+++ b/drivers/iommu/amd_iommu_types.h
@@ -426,6 +426,7 @@ struct iommu_dev_data {
 	struct iommu_dev_data *alias_data;/* The alias dev_data */
 	struct protection_domain *domain; /* Domain the device is bound to */
 	atomic_t bind;			  /* Domain attach reference count */
+	struct iommu_group *group;	  /* IOMMU group for virtual aliases */
 	u16 devid;			  /* PCI Device ID */
 	bool iommu_v2;			  /* Device can make use of IOMMUv2 */
 	bool passthrough;		  /* Default for device is pt_domain */
diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c
index 9476c1b..c2c07a4 100644
--- a/drivers/iommu/intel-iommu.c
+++ b/drivers/iommu/intel-iommu.c
@@ -2327,8 +2327,39 @@ static int domain_add_dev_info(struct dmar_domain *domain,
 	return 0;
 }
 
+static bool device_has_rmrr(struct pci_dev *dev)
+{
+	struct dmar_rmrr_unit *rmrr;
+	int i;
+
+	for_each_rmrr_units(rmrr) {
+		for (i = 0; i < rmrr->devices_cnt; i++) {
+			/*
+			 * Return TRUE if this RMRR contains the device that
+			 * is passed in.
+			 */
+			if (rmrr->devices[i] == dev)
+				return true;
+		}
+	}
+	return false;
+}
+
 static int iommu_should_identity_map(struct pci_dev *pdev, int startup)
 {
+
+	/*
+	 * We want to prevent any device associated with an RMRR from
+	 * getting placed into the SI Domain. This is done because
+	 * problems exist when devices are moved in and out of domains
+	 * and their respective RMRR info is lost. We exempt USB devices
+	 * from this process due to their usage of RMRRs that are known
+	 * to not be needed after BIOS hand-off to OS.
+	 */
+	if (device_has_rmrr(pdev) &&
+	    (pdev->class >> 8) != PCI_CLASS_SERIAL_USB)
+		return 0;
+
 	if ((iommu_identity_mapping & IDENTMAP_AZALIA) && IS_AZALIA(pdev))
 		return 1;
 
diff --git a/drivers/iommu/omap-iommu.c b/drivers/iommu/omap-iommu.c
index badc17c..18108c14 100644
--- a/drivers/iommu/omap-iommu.c
+++ b/drivers/iommu/omap-iommu.c
@@ -16,13 +16,13 @@
 #include <linux/slab.h>
 #include <linux/interrupt.h>
 #include <linux/ioport.h>
-#include <linux/clk.h>
 #include <linux/platform_device.h>
 #include <linux/iommu.h>
 #include <linux/omap-iommu.h>
 #include <linux/mutex.h>
 #include <linux/spinlock.h>
 #include <linux/io.h>
+#include <linux/pm_runtime.h>
 
 #include <asm/cacheflush.h>
 
@@ -143,31 +143,44 @@ EXPORT_SYMBOL_GPL(omap_iommu_arch_version);
 static int iommu_enable(struct omap_iommu *obj)
 {
 	int err;
+	struct platform_device *pdev = to_platform_device(obj->dev);
+	struct iommu_platform_data *pdata = pdev->dev.platform_data;
 
-	if (!obj)
+	if (!obj || !pdata)
 		return -EINVAL;
 
 	if (!arch_iommu)
 		return -ENODEV;
 
-	clk_enable(obj->clk);
+	if (pdata->deassert_reset) {
+		err = pdata->deassert_reset(pdev, pdata->reset_name);
+		if (err) {
+			dev_err(obj->dev, "deassert_reset failed: %d\n", err);
+			return err;
+		}
+	}
+
+	pm_runtime_get_sync(obj->dev);
 
 	err = arch_iommu->enable(obj);
 
-	clk_disable(obj->clk);
 	return err;
 }
 
 static void iommu_disable(struct omap_iommu *obj)
 {
-	if (!obj)
-		return;
+	struct platform_device *pdev = to_platform_device(obj->dev);
+	struct iommu_platform_data *pdata = pdev->dev.platform_data;
 
-	clk_enable(obj->clk);
+	if (!obj || !pdata)
+		return;
 
 	arch_iommu->disable(obj);
 
-	clk_disable(obj->clk);
+	pm_runtime_put_sync(obj->dev);
+
+	if (pdata->assert_reset)
+		pdata->assert_reset(pdev, pdata->reset_name);
 }
 
 /*
@@ -290,7 +303,7 @@ static int load_iotlb_entry(struct omap_iommu *obj, struct iotlb_entry *e)
 	if (!obj || !obj->nr_tlb_entries || !e)
 		return -EINVAL;
 
-	clk_enable(obj->clk);
+	pm_runtime_get_sync(obj->dev);
 
 	iotlb_lock_get(obj, &l);
 	if (l.base == obj->nr_tlb_entries) {
@@ -320,7 +333,7 @@ static int load_iotlb_entry(struct omap_iommu *obj, struct iotlb_entry *e)
 
 	cr = iotlb_alloc_cr(obj, e);
 	if (IS_ERR(cr)) {
-		clk_disable(obj->clk);
+		pm_runtime_put_sync(obj->dev);
 		return PTR_ERR(cr);
 	}
 
@@ -334,7 +347,7 @@ static int load_iotlb_entry(struct omap_iommu *obj, struct iotlb_entry *e)
 		l.vict = l.base;
 	iotlb_lock_set(obj, &l);
 out:
-	clk_disable(obj->clk);
+	pm_runtime_put_sync(obj->dev);
 	return err;
 }
 
@@ -364,7 +377,7 @@ static void flush_iotlb_page(struct omap_iommu *obj, u32 da)
 	int i;
 	struct cr_regs cr;
 
-	clk_enable(obj->clk);
+	pm_runtime_get_sync(obj->dev);
 
 	for_each_iotlb_cr(obj, obj->nr_tlb_entries, i, cr) {
 		u32 start;
@@ -383,7 +396,7 @@ static void flush_iotlb_page(struct omap_iommu *obj, u32 da)
 			iommu_write_reg(obj, 1, MMU_FLUSH_ENTRY);
 		}
 	}
-	clk_disable(obj->clk);
+	pm_runtime_put_sync(obj->dev);
 
 	if (i == obj->nr_tlb_entries)
 		dev_dbg(obj->dev, "%s: no page for %08x\n", __func__, da);
@@ -397,7 +410,7 @@ static void flush_iotlb_all(struct omap_iommu *obj)
 {
 	struct iotlb_lock l;
 
-	clk_enable(obj->clk);
+	pm_runtime_get_sync(obj->dev);
 
 	l.base = 0;
 	l.vict = 0;
@@ -405,7 +418,7 @@ static void flush_iotlb_all(struct omap_iommu *obj)
 
 	iommu_write_reg(obj, 1, MMU_GFLUSH);
 
-	clk_disable(obj->clk);
+	pm_runtime_put_sync(obj->dev);
 }
 
 #if defined(CONFIG_OMAP_IOMMU_DEBUG) || defined(CONFIG_OMAP_IOMMU_DEBUG_MODULE)
@@ -415,11 +428,11 @@ ssize_t omap_iommu_dump_ctx(struct omap_iommu *obj, char *buf, ssize_t bytes)
 	if (!obj || !buf)
 		return -EINVAL;
 
-	clk_enable(obj->clk);
+	pm_runtime_get_sync(obj->dev);
 
 	bytes = arch_iommu->dump_ctx(obj, buf, bytes);
 
-	clk_disable(obj->clk);
+	pm_runtime_put_sync(obj->dev);
 
 	return bytes;
 }
@@ -433,7 +446,7 @@ __dump_tlb_entries(struct omap_iommu *obj, struct cr_regs *crs, int num)
 	struct cr_regs tmp;
 	struct cr_regs *p = crs;
 
-	clk_enable(obj->clk);
+	pm_runtime_get_sync(obj->dev);
 	iotlb_lock_get(obj, &saved);
 
 	for_each_iotlb_cr(obj, num, i, tmp) {
@@ -443,7 +456,7 @@ __dump_tlb_entries(struct omap_iommu *obj, struct cr_regs *crs, int num)
 	}
 
 	iotlb_lock_set(obj, &saved);
-	clk_disable(obj->clk);
+	pm_runtime_put_sync(obj->dev);
 
 	return  p - crs;
 }
@@ -807,9 +820,7 @@ static irqreturn_t iommu_fault_handler(int irq, void *data)
 	if (!obj->refcount)
 		return IRQ_NONE;
 
-	clk_enable(obj->clk);
 	errs = iommu_report_fault(obj, &da);
-	clk_disable(obj->clk);
 	if (errs == 0)
 		return IRQ_HANDLED;
 
@@ -931,17 +942,10 @@ static int __devinit omap_iommu_probe(struct platform_device *pdev)
 	struct resource *res;
 	struct iommu_platform_data *pdata = pdev->dev.platform_data;
 
-	if (pdev->num_resources != 2)
-		return -EINVAL;
-
 	obj = kzalloc(sizeof(*obj) + MMU_REG_SIZE, GFP_KERNEL);
 	if (!obj)
 		return -ENOMEM;
 
-	obj->clk = clk_get(&pdev->dev, pdata->clk_name);
-	if (IS_ERR(obj->clk))
-		goto err_clk;
-
 	obj->nr_tlb_entries = pdata->nr_tlb_entries;
 	obj->name = pdata->name;
 	obj->dev = &pdev->dev;
@@ -984,6 +988,9 @@ static int __devinit omap_iommu_probe(struct platform_device *pdev)
 		goto err_irq;
 	platform_set_drvdata(pdev, obj);
 
+	pm_runtime_irq_safe(obj->dev);
+	pm_runtime_enable(obj->dev);
+
 	dev_info(&pdev->dev, "%s registered\n", obj->name);
 	return 0;
 
@@ -992,8 +999,6 @@ err_irq:
 err_ioremap:
 	release_mem_region(res->start, resource_size(res));
 err_mem:
-	clk_put(obj->clk);
-err_clk:
 	kfree(obj);
 	return err;
 }
@@ -1014,7 +1019,8 @@ static int __devexit omap_iommu_remove(struct platform_device *pdev)
 	release_mem_region(res->start, resource_size(res));
 	iounmap(obj->regbase);
 
-	clk_put(obj->clk);
+	pm_runtime_disable(obj->dev);
+
 	dev_info(&pdev->dev, "%s removed\n", obj->name);
 	kfree(obj);
 	return 0;
diff --git a/drivers/iommu/omap-iommu.h b/drivers/iommu/omap-iommu.h
index 2b5f3c0..1200842 100644
--- a/drivers/iommu/omap-iommu.h
+++ b/drivers/iommu/omap-iommu.h
@@ -29,7 +29,6 @@ struct iotlb_entry {
 struct omap_iommu {
 	const char	*name;
 	struct module	*owner;
-	struct clk	*clk;
 	void __iomem	*regbase;
 	struct device	*dev;
 	void		*isr_priv;
@@ -116,8 +115,6 @@ static inline struct omap_iommu *dev_to_omap_iommu(struct device *dev)
  * MMU Register offsets
  */
 #define MMU_REVISION		0x00
-#define MMU_SYSCONFIG		0x10
-#define MMU_SYSSTATUS		0x14
 #define MMU_IRQSTATUS		0x18
 #define MMU_IRQENABLE		0x1c
 #define MMU_WALKING_ST		0x40
diff --git a/drivers/iommu/omap-iommu2.c b/drivers/iommu/omap-iommu2.c
index c020202..d745094 100644
--- a/drivers/iommu/omap-iommu2.c
+++ b/drivers/iommu/omap-iommu2.c
@@ -28,19 +28,6 @@
  */
 #define IOMMU_ARCH_VERSION	0x00000011
 
-/* SYSCONF */
-#define MMU_SYS_IDLE_SHIFT	3
-#define MMU_SYS_IDLE_FORCE	(0 << MMU_SYS_IDLE_SHIFT)
-#define MMU_SYS_IDLE_NONE	(1 << MMU_SYS_IDLE_SHIFT)
-#define MMU_SYS_IDLE_SMART	(2 << MMU_SYS_IDLE_SHIFT)
-#define MMU_SYS_IDLE_MASK	(3 << MMU_SYS_IDLE_SHIFT)
-
-#define MMU_SYS_SOFTRESET	(1 << 1)
-#define MMU_SYS_AUTOIDLE	1
-
-/* SYSSTATUS */
-#define MMU_SYS_RESETDONE	1
-
 /* IRQSTATUS & IRQENABLE */
 #define MMU_IRQ_MULTIHITFAULT	(1 << 4)
 #define MMU_IRQ_TABLEWALKFAULT	(1 << 3)
@@ -97,7 +84,6 @@ static void __iommu_set_twl(struct omap_iommu *obj, bool on)
 static int omap2_iommu_enable(struct omap_iommu *obj)
 {
 	u32 l, pa;
-	unsigned long timeout;
 
 	if (!obj->iopgd || !IS_ALIGNED((u32)obj->iopgd,  SZ_16K))
 		return -EINVAL;
@@ -106,29 +92,10 @@ static int omap2_iommu_enable(struct omap_iommu *obj)
 	if (!IS_ALIGNED(pa, SZ_16K))
 		return -EINVAL;
 
-	iommu_write_reg(obj, MMU_SYS_SOFTRESET, MMU_SYSCONFIG);
-
-	timeout = jiffies + msecs_to_jiffies(20);
-	do {
-		l = iommu_read_reg(obj, MMU_SYSSTATUS);
-		if (l & MMU_SYS_RESETDONE)
-			break;
-	} while (!time_after(jiffies, timeout));
-
-	if (!(l & MMU_SYS_RESETDONE)) {
-		dev_err(obj->dev, "can't take mmu out of reset\n");
-		return -ENODEV;
-	}
-
 	l = iommu_read_reg(obj, MMU_REVISION);
 	dev_info(obj->dev, "%s: version %d.%d\n", obj->name,
 		 (l >> 4) & 0xf, l & 0xf);
 
-	l = iommu_read_reg(obj, MMU_SYSCONFIG);
-	l &= ~MMU_SYS_IDLE_MASK;
-	l |= (MMU_SYS_IDLE_SMART | MMU_SYS_AUTOIDLE);
-	iommu_write_reg(obj, l, MMU_SYSCONFIG);
-
 	iommu_write_reg(obj, pa, MMU_TTB);
 
 	__iommu_set_twl(obj, true);
@@ -142,7 +109,6 @@ static void omap2_iommu_disable(struct omap_iommu *obj)
 
 	l &= ~MMU_CNTL_MASK;
 	iommu_write_reg(obj, l, MMU_CNTL);
-	iommu_write_reg(obj, MMU_SYS_IDLE_FORCE, MMU_SYSCONFIG);
 
 	dev_dbg(obj->dev, "%s is shutting down\n", obj->name);
 }
@@ -271,8 +237,6 @@ omap2_iommu_dump_ctx(struct omap_iommu *obj, char *buf, ssize_t len)
 	char *p = buf;
 
 	pr_reg(REVISION);
-	pr_reg(SYSCONFIG);
-	pr_reg(SYSSTATUS);
 	pr_reg(IRQSTATUS);
 	pr_reg(IRQENABLE);
 	pr_reg(WALKING_ST);
diff --git a/drivers/iommu/tegra-gart.c b/drivers/iommu/tegra-gart.c
index c16e8fc..4c9db62 100644
--- a/drivers/iommu/tegra-gart.c
+++ b/drivers/iommu/tegra-gart.c
@@ -398,6 +398,7 @@ static int tegra_gart_probe(struct platform_device *pdev)
 	do_gart_setup(gart, NULL);
 
 	gart_handle = gart;
+	bus_set_iommu(&platform_bus_type, &gart_iommu_ops);
 	return 0;
 
 fail:
@@ -450,7 +451,6 @@ static struct platform_driver tegra_gart_driver = {
 
 static int __devinit tegra_gart_init(void)
 {
-	bus_set_iommu(&platform_bus_type, &gart_iommu_ops);
 	return platform_driver_register(&tegra_gart_driver);
 }
 
diff --git a/drivers/iommu/tegra-smmu.c b/drivers/iommu/tegra-smmu.c
index 4252d74..25c1210 100644
--- a/drivers/iommu/tegra-smmu.c
+++ b/drivers/iommu/tegra-smmu.c
@@ -694,10 +694,8 @@ static void __smmu_iommu_unmap(struct smmu_as *as, dma_addr_t iova)
 	*pte = _PTE_VACANT(iova);
 	FLUSH_CPU_DCACHE(pte, page, sizeof(*pte));
 	flush_ptc_and_tlb(as->smmu, as, iova, pte, page, 0);
-	if (!--(*count)) {
+	if (!--(*count))
 		free_ptbl(as, iova);
-		smmu_flush_regs(as->smmu, 0);
-	}
 }
 
 static void __smmu_iommu_map_pfn(struct smmu_as *as, dma_addr_t iova,
@@ -1232,6 +1230,7 @@ static int tegra_smmu_probe(struct platform_device *pdev)
 
 	smmu_debugfs_create(smmu);
 	smmu_handle = smmu;
+	bus_set_iommu(&platform_bus_type, &smmu_iommu_ops);
 	return 0;
 }
 
@@ -1276,7 +1275,6 @@ static struct platform_driver tegra_smmu_driver = {
 
 static int __devinit tegra_smmu_init(void)
 {
-	bus_set_iommu(&platform_bus_type, &smmu_iommu_ops);
 	return platform_driver_register(&tegra_smmu_driver);
 }