Merge branch 'next' of git://git.kernel.org/pub/scm/linux/kernel/git/benh/powerpc

Pull powerpc updates from Ben Herrenschmidt:
 "This is the powerpc changes for the 3.11 merge window.  In addition to
  the usual bug fixes and small updates, the main highlights are:

   - Support for transparent huge pages by Aneesh Kumar for 64-bit
     server processors.  This allows the use of 16M pages as transparent
     huge pages on kernels compiled with a 64K base page size.

   - Base VFIO support for KVM on power by Alexey Kardashevskiy

   - Wiring up of our nvram to the pstore infrastructure, including
     putting compressed oopses in there by Aruna Balakrishnaiah

   - Move, rework and improve our "EEH" (basically PCI error handling
     and recovery) infrastructure.  It is no longer specific to pseries
     but is now usable by the new "powernv" platform as well (no
     hypervisor) by Gavin Shan.

   - I fixed some bugs in our math-emu instruction decoding and made it
     usable to emulate some optional FP instructions on processors with
     hard FP that lack them (such as fsqrt on Freescale embedded
     processors).

   - Support for Power8 "Event Based Branch" facility by Michael
     Ellerman.  This facility allows what is basically "userspace
     interrupts" for performance monitor events.

   - A bunch of Transactional Memory vs.  Signals bug fixes and HW
     breakpoint/watchpoint fixes by Michael Neuling.

  And more ...  I appologize in advance if I've failed to highlight
  something that somebody deemed worth it."

* 'next' of git://git.kernel.org/pub/scm/linux/kernel/git/benh/powerpc: (156 commits)
  pstore: Add hsize argument in write_buf call of pstore_ftrace_call
  powerpc/fsl: add MPIC timer wakeup support
  powerpc/mpic: create mpic subsystem object
  powerpc/mpic: add global timer support
  powerpc/mpic: add irq_set_wake support
  powerpc/85xx: enable coreint for all the 64bit boards
  powerpc/8xx: Erroneous double irq_eoi() on CPM IRQ in MPC8xx
  powerpc/fsl: Enable CONFIG_E1000E in mpc85xx_smp_defconfig
  powerpc/mpic: Add get_version API both for internal and external use
  powerpc: Handle both new style and old style reserve maps
  powerpc/hw_brk: Fix off by one error when validating DAWR region end
  powerpc/pseries: Support compression of oops text via pstore
  powerpc/pseries: Re-organise the oops compression code
  pstore: Pass header size in the pstore write callback
  powerpc/powernv: Fix iommu initialization again
  powerpc/pseries: Inform the hypervisor we are using EBB regs
  powerpc/perf: Add power8 EBB support
  powerpc/perf: Core EBB support for 64-bit book3s
  powerpc/perf: Drop MMCRA from thread_struct
  powerpc/perf: Don't enable if we have zero events
  ...

16 files changed, 433 insertions, 13 deletions

diff --git a/drivers/acpi/apei/erst.c b/drivers/acpi/apei/erst.c
index f7b3b39e94f..88d0b0f9f92 100644
--- a/drivers/acpi/apei/erst.c
+++ b/drivers/acpi/apei/erst.c
@@ -935,7 +935,7 @@ static ssize_t erst_reader(u64 *id, enum pstore_type_id *type, int *count,
 			   struct timespec *time, char **buf,
 			   struct pstore_info *psi);
 static int erst_writer(enum pstore_type_id type, enum kmsg_dump_reason reason,
-		       u64 *id, unsigned int part, int count,
+		       u64 *id, unsigned int part, int count, size_t hsize,
 		       size_t size, struct pstore_info *psi);
 static int erst_clearer(enum pstore_type_id type, u64 id, int count,
 			struct timespec time, struct pstore_info *psi);
@@ -1055,7 +1055,7 @@ out:
 }
 
 static int erst_writer(enum pstore_type_id type, enum kmsg_dump_reason reason,
-		       u64 *id, unsigned int part, int count,
+		       u64 *id, unsigned int part, int count, size_t hsize,
 		       size_t size, struct pstore_info *psi)
 {
 	struct cper_pstore_record *rcd = (struct cper_pstore_record *)
diff --git a/drivers/firmware/efi/efi-pstore.c b/drivers/firmware/efi/efi-pstore.c
index 91864ad200f..73de5a9c224 100644
--- a/drivers/firmware/efi/efi-pstore.c
+++ b/drivers/firmware/efi/efi-pstore.c
@@ -103,7 +103,7 @@ static ssize_t efi_pstore_read(u64 *id, enum pstore_type_id *type,
 
 static int efi_pstore_write(enum pstore_type_id type,
 		enum kmsg_dump_reason reason, u64 *id,
-		unsigned int part, int count, size_t size,
+		unsigned int part, int count, size_t hsize, size_t size,
 		struct pstore_info *psi)
 {
 	char name[DUMP_NAME_LEN];
diff --git a/drivers/i2c/busses/i2c-cpm.c b/drivers/i2c/busses/i2c-cpm.c
index 3823623baa4..9e600210872 100644
--- a/drivers/i2c/busses/i2c-cpm.c
+++ b/drivers/i2c/busses/i2c-cpm.c
@@ -338,6 +338,14 @@ static int cpm_i2c_xfer(struct i2c_adapter *adap, struct i2c_msg *msgs, int num)
 	tptr = 0;
 	rptr = 0;
 
+	/*
+	 * If there was a collision in the last i2c transaction,
+	 * Set I2COM_MASTER as it was cleared during collision.
+	 */
+	if (in_be16(&tbdf->cbd_sc) & BD_SC_CL) {
+		out_8(&cpm->i2c_reg->i2com, I2COM_MASTER);
+	}
+
 	while (tptr < num) {
 		pmsg = &msgs[tptr];
 		dev_dbg(&adap->dev, "R: %d T: %d\n", rptr, tptr);
diff --git a/drivers/iommu/Kconfig b/drivers/iommu/Kconfig
index c332fb98480..01730b2b995 100644
--- a/drivers/iommu/Kconfig
+++ b/drivers/iommu/Kconfig
@@ -261,4 +261,12 @@ config SHMOBILE_IOMMU_L1SIZE
 	default 256 if SHMOBILE_IOMMU_ADDRSIZE_64MB
 	default 128 if SHMOBILE_IOMMU_ADDRSIZE_32MB
 
+config SPAPR_TCE_IOMMU
+	bool "sPAPR TCE IOMMU Support"
+	depends on PPC_POWERNV || PPC_PSERIES
+	select IOMMU_API
+	help
+	  Enables bits of IOMMU API required by VFIO. The iommu_ops
+	  is not implemented as it is not necessary for VFIO.
+
 endif # IOMMU_SUPPORT
diff --git a/drivers/macintosh/adb.c b/drivers/macintosh/adb.c
index b026896206c..04a50498f25 100644
--- a/drivers/macintosh/adb.c
+++ b/drivers/macintosh/adb.c
@@ -697,7 +697,7 @@ static ssize_t adb_read(struct file *file, char __user *buf,
 	int ret = 0;
 	struct adbdev_state *state = file->private_data;
 	struct adb_request *req;
-	wait_queue_t wait = __WAITQUEUE_INITIALIZER(wait,current);
+	DECLARE_WAITQUEUE(wait,current);
 	unsigned long flags;
 
 	if (count < 2)
diff --git a/drivers/macintosh/mac_hid.c b/drivers/macintosh/mac_hid.c
index 6a82388505f..80d30e8e338 100644
--- a/drivers/macintosh/mac_hid.c
+++ b/drivers/macintosh/mac_hid.c
@@ -181,7 +181,7 @@ static void mac_hid_stop_emulation(void)
 	mac_hid_destroy_emumouse();
 }
 
-static int mac_hid_toggle_emumouse(ctl_table *table, int write,
+static int mac_hid_toggle_emumouse(struct ctl_table *table, int write,
 				   void __user *buffer, size_t *lenp,
 				   loff_t *ppos)
 {
@@ -214,7 +214,7 @@ static int mac_hid_toggle_emumouse(ctl_table *table, int write,
 }
 
 /* file(s) in /proc/sys/dev/mac_hid */
-static ctl_table mac_hid_files[] = {
+static struct ctl_table mac_hid_files[] = {
 	{
 		.procname	= "mouse_button_emulation",
 		.data		= &mouse_emulate_buttons,
@@ -240,7 +240,7 @@ static ctl_table mac_hid_files[] = {
 };
 
 /* dir in /proc/sys/dev */
-static ctl_table mac_hid_dir[] = {
+static struct ctl_table mac_hid_dir[] = {
 	{
 		.procname	= "mac_hid",
 		.maxlen		= 0,
@@ -251,7 +251,7 @@ static ctl_table mac_hid_dir[] = {
 };
 
 /* /proc/sys/dev itself, in case that is not there yet */
-static ctl_table mac_hid_root_dir[] = {
+static struct ctl_table mac_hid_root_dir[] = {
 	{
 		.procname	= "dev",
 		.maxlen		= 0,
diff --git a/drivers/macintosh/via-cuda.c b/drivers/macintosh/via-cuda.c
index 86511c570dd..d61f271d220 100644
--- a/drivers/macintosh/via-cuda.c
+++ b/drivers/macintosh/via-cuda.c
@@ -259,7 +259,7 @@ cuda_probe(void)
     } while (0)
 
 static int
-cuda_init_via(void)
+__init cuda_init_via(void)
 {
     out_8(&via[DIRB], (in_8(&via[DIRB]) | TACK | TIP) & ~TREQ);	/* TACK & TIP out */
     out_8(&via[B], in_8(&via[B]) | TACK | TIP);			/* negate them */
diff --git a/drivers/macintosh/windfarm_pm121.c b/drivers/macintosh/windfarm_pm121.c
index af605e915d4..7fe58b0ae8b 100644
--- a/drivers/macintosh/windfarm_pm121.c
+++ b/drivers/macintosh/windfarm_pm121.c
@@ -276,6 +276,7 @@ static const char *loop_names[N_LOOPS] = {
 
 static unsigned int pm121_failure_state;
 static int pm121_readjust, pm121_skipping;
+static bool pm121_overtemp;
 static s32 average_power;
 
 struct pm121_correction {
@@ -847,6 +848,7 @@ static void pm121_tick(void)
 	if (new_failure & FAILURE_OVERTEMP) {
 		wf_set_overtemp();
 		pm121_skipping = 2;
+		pm121_overtemp = true;
 	}
 
 	/* We only clear the overtemp condition if overtemp is cleared
@@ -855,8 +857,10 @@ static void pm121_tick(void)
 	 * the control loop levels, but we don't want to keep it clear
 	 * here in this case
 	 */
-	if (new_failure == 0 && last_failure & FAILURE_OVERTEMP)
+	if (!pm121_failure_state && pm121_overtemp) {
 		wf_clear_overtemp();
+		pm121_overtemp = false;
+	}
 }
 
 
diff --git a/drivers/macintosh/windfarm_pm81.c b/drivers/macintosh/windfarm_pm81.c
index f84933ff329..2a5e1b15b1d 100644
--- a/drivers/macintosh/windfarm_pm81.c
+++ b/drivers/macintosh/windfarm_pm81.c
@@ -149,6 +149,7 @@ static int wf_smu_all_controls_ok, wf_smu_all_sensors_ok, wf_smu_started;
 
 static unsigned int wf_smu_failure_state;
 static int wf_smu_readjust, wf_smu_skipping;
+static bool wf_smu_overtemp;
 
 /*
  * ****** System Fans Control Loop ******
@@ -593,6 +594,7 @@ static void wf_smu_tick(void)
 	if (new_failure & FAILURE_OVERTEMP) {
 		wf_set_overtemp();
 		wf_smu_skipping = 2;
+		wf_smu_overtemp = true;
 	}
 
 	/* We only clear the overtemp condition if overtemp is cleared
@@ -601,8 +603,10 @@ static void wf_smu_tick(void)
 	 * the control loop levels, but we don't want to keep it clear
 	 * here in this case
 	 */
-	if (new_failure == 0 && last_failure & FAILURE_OVERTEMP)
+	if (!wf_smu_failure_state && wf_smu_overtemp) {
 		wf_clear_overtemp();
+		wf_smu_overtemp = false;
+	}
 }
 
 static void wf_smu_new_control(struct wf_control *ct)
diff --git a/drivers/macintosh/windfarm_pm91.c b/drivers/macintosh/windfarm_pm91.c
index 2eb484f213c..a8ac66cd3b1 100644
--- a/drivers/macintosh/windfarm_pm91.c
+++ b/drivers/macintosh/windfarm_pm91.c
@@ -76,6 +76,7 @@ static struct wf_control *cpufreq_clamp;
 
 /* Set to kick the control loop into life */
 static int wf_smu_all_controls_ok, wf_smu_all_sensors_ok, wf_smu_started;
+static bool wf_smu_overtemp;
 
 /* Failure handling.. could be nicer */
 #define FAILURE_FAN		0x01
@@ -517,6 +518,7 @@ static void wf_smu_tick(void)
 	if (new_failure & FAILURE_OVERTEMP) {
 		wf_set_overtemp();
 		wf_smu_skipping = 2;
+		wf_smu_overtemp = true;
 	}
 
 	/* We only clear the overtemp condition if overtemp is cleared
@@ -525,8 +527,10 @@ static void wf_smu_tick(void)
 	 * the control loop levels, but we don't want to keep it clear
 	 * here in this case
 	 */
-	if (new_failure == 0 && last_failure & FAILURE_OVERTEMP)
+	if (!wf_smu_failure_state && wf_smu_overtemp) {
 		wf_clear_overtemp();
+		wf_smu_overtemp = false;
+	}
 }
 
 
diff --git a/drivers/macintosh/windfarm_smu_sat.c b/drivers/macintosh/windfarm_smu_sat.c
index d87f5ee04ca..ad6223e8834 100644
--- a/drivers/macintosh/windfarm_smu_sat.c
+++ b/drivers/macintosh/windfarm_smu_sat.c
@@ -343,7 +343,6 @@ static int wf_sat_remove(struct i2c_client *client)
 		wf_unregister_sensor(&sens->sens);
 	}
 	sat->i2c = NULL;
-	i2c_set_clientdata(client, NULL);
 	kref_put(&sat->ref, wf_sat_release);
 
 	return 0;
diff --git a/drivers/vfio/Kconfig b/drivers/vfio/Kconfig
index 7cd5dec0abd..26b3d9d1409 100644
--- a/drivers/vfio/Kconfig
+++ b/drivers/vfio/Kconfig
@@ -3,10 +3,16 @@ config VFIO_IOMMU_TYPE1
 	depends on VFIO
 	default n
 
+config VFIO_IOMMU_SPAPR_TCE
+	tristate
+	depends on VFIO && SPAPR_TCE_IOMMU
+	default n
+
 menuconfig VFIO
 	tristate "VFIO Non-Privileged userspace driver framework"
 	depends on IOMMU_API
 	select VFIO_IOMMU_TYPE1 if X86
+	select VFIO_IOMMU_SPAPR_TCE if (PPC_POWERNV || PPC_PSERIES)
 	help
 	  VFIO provides a framework for secure userspace device drivers.
 	  See Documentation/vfio.txt for more details.
diff --git a/drivers/vfio/Makefile b/drivers/vfio/Makefile
index 2398d4a0e38..72bfabc8629 100644
--- a/drivers/vfio/Makefile
+++ b/drivers/vfio/Makefile
@@ -1,3 +1,4 @@
 obj-$(CONFIG_VFIO) += vfio.o
 obj-$(CONFIG_VFIO_IOMMU_TYPE1) += vfio_iommu_type1.o
+obj-$(CONFIG_VFIO_IOMMU_SPAPR_TCE) += vfio_iommu_spapr_tce.o
 obj-$(CONFIG_VFIO_PCI) += pci/
diff --git a/drivers/vfio/vfio.c b/drivers/vfio/vfio.c
index 6d78736563d..259ad282ae5 100644
--- a/drivers/vfio/vfio.c
+++ b/drivers/vfio/vfio.c
@@ -1415,6 +1415,7 @@ static int __init vfio_init(void)
 	 * drivers.
 	 */
 	request_module_nowait("vfio_iommu_type1");
+	request_module_nowait("vfio_iommu_spapr_tce");
 
 	return 0;
 
diff --git a/drivers/vfio/vfio_iommu_spapr_tce.c b/drivers/vfio/vfio_iommu_spapr_tce.c
new file mode 100644
index 00000000000..bdae7a04af7
--- /dev/null
+++ b/drivers/vfio/vfio_iommu_spapr_tce.c
@@ -0,0 +1,377 @@
+/*
+ * VFIO: IOMMU DMA mapping support for TCE on POWER
+ *
+ * Copyright (C) 2013 IBM Corp.  All rights reserved.
+ *     Author: Alexey Kardashevskiy <aik@ozlabs.ru>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * Derived from original vfio_iommu_type1.c:
+ * Copyright (C) 2012 Red Hat, Inc.  All rights reserved.
+ *     Author: Alex Williamson <alex.williamson@redhat.com>
+ */
+
+#include <linux/module.h>
+#include <linux/pci.h>
+#include <linux/slab.h>
+#include <linux/uaccess.h>
+#include <linux/err.h>
+#include <linux/vfio.h>
+#include <asm/iommu.h>
+#include <asm/tce.h>
+
+#define DRIVER_VERSION  "0.1"
+#define DRIVER_AUTHOR   "aik@ozlabs.ru"
+#define DRIVER_DESC     "VFIO IOMMU SPAPR TCE"
+
+static void tce_iommu_detach_group(void *iommu_data,
+		struct iommu_group *iommu_group);
+
+/*
+ * VFIO IOMMU fd for SPAPR_TCE IOMMU implementation
+ *
+ * This code handles mapping and unmapping of user data buffers
+ * into DMA'ble space using the IOMMU
+ */
+
+/*
+ * The container descriptor supports only a single group per container.
+ * Required by the API as the container is not supplied with the IOMMU group
+ * at the moment of initialization.
+ */
+struct tce_container {
+	struct mutex lock;
+	struct iommu_table *tbl;
+	bool enabled;
+};
+
+static int tce_iommu_enable(struct tce_container *container)
+{
+	int ret = 0;
+	unsigned long locked, lock_limit, npages;
+	struct iommu_table *tbl = container->tbl;
+
+	if (!container->tbl)
+		return -ENXIO;
+
+	if (!current->mm)
+		return -ESRCH; /* process exited */
+
+	if (container->enabled)
+		return -EBUSY;
+
+	/*
+	 * When userspace pages are mapped into the IOMMU, they are effectively
+	 * locked memory, so, theoretically, we need to update the accounting
+	 * of locked pages on each map and unmap.  For powerpc, the map unmap
+	 * paths can be very hot, though, and the accounting would kill
+	 * performance, especially since it would be difficult to impossible
+	 * to handle the accounting in real mode only.
+	 *
+	 * To address that, rather than precisely accounting every page, we
+	 * instead account for a worst case on locked memory when the iommu is
+	 * enabled and disabled.  The worst case upper bound on locked memory
+	 * is the size of the whole iommu window, which is usually relatively
+	 * small (compared to total memory sizes) on POWER hardware.
+	 *
+	 * Also we don't have a nice way to fail on H_PUT_TCE due to ulimits,
+	 * that would effectively kill the guest at random points, much better
+	 * enforcing the limit based on the max that the guest can map.
+	 */
+	down_write(&current->mm->mmap_sem);
+	npages = (tbl->it_size << IOMMU_PAGE_SHIFT) >> PAGE_SHIFT;
+	locked = current->mm->locked_vm + npages;
+	lock_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT;
+	if (locked > lock_limit && !capable(CAP_IPC_LOCK)) {
+		pr_warn("RLIMIT_MEMLOCK (%ld) exceeded\n",
+				rlimit(RLIMIT_MEMLOCK));
+		ret = -ENOMEM;
+	} else {
+
+		current->mm->locked_vm += npages;
+		container->enabled = true;
+	}
+	up_write(&current->mm->mmap_sem);
+
+	return ret;
+}
+
+static void tce_iommu_disable(struct tce_container *container)
+{
+	if (!container->enabled)
+		return;
+
+	container->enabled = false;
+
+	if (!container->tbl || !current->mm)
+		return;
+
+	down_write(&current->mm->mmap_sem);
+	current->mm->locked_vm -= (container->tbl->it_size <<
+			IOMMU_PAGE_SHIFT) >> PAGE_SHIFT;
+	up_write(&current->mm->mmap_sem);
+}
+
+static void *tce_iommu_open(unsigned long arg)
+{
+	struct tce_container *container;
+
+	if (arg != VFIO_SPAPR_TCE_IOMMU) {
+		pr_err("tce_vfio: Wrong IOMMU type\n");
+		return ERR_PTR(-EINVAL);
+	}
+
+	container = kzalloc(sizeof(*container), GFP_KERNEL);
+	if (!container)
+		return ERR_PTR(-ENOMEM);
+
+	mutex_init(&container->lock);
+
+	return container;
+}
+
+static void tce_iommu_release(void *iommu_data)
+{
+	struct tce_container *container = iommu_data;
+
+	WARN_ON(container->tbl && !container->tbl->it_group);
+	tce_iommu_disable(container);
+
+	if (container->tbl && container->tbl->it_group)
+		tce_iommu_detach_group(iommu_data, container->tbl->it_group);
+
+	mutex_destroy(&container->lock);
+
+	kfree(container);
+}
+
+static long tce_iommu_ioctl(void *iommu_data,
+				 unsigned int cmd, unsigned long arg)
+{
+	struct tce_container *container = iommu_data;
+	unsigned long minsz;
+	long ret;
+
+	switch (cmd) {
+	case VFIO_CHECK_EXTENSION:
+		return (arg == VFIO_SPAPR_TCE_IOMMU) ? 1 : 0;
+
+	case VFIO_IOMMU_SPAPR_TCE_GET_INFO: {
+		struct vfio_iommu_spapr_tce_info info;
+		struct iommu_table *tbl = container->tbl;
+
+		if (WARN_ON(!tbl))
+			return -ENXIO;
+
+		minsz = offsetofend(struct vfio_iommu_spapr_tce_info,
+				dma32_window_size);
+
+		if (copy_from_user(&info, (void __user *)arg, minsz))
+			return -EFAULT;
+
+		if (info.argsz < minsz)
+			return -EINVAL;
+
+		info.dma32_window_start = tbl->it_offset << IOMMU_PAGE_SHIFT;
+		info.dma32_window_size = tbl->it_size << IOMMU_PAGE_SHIFT;
+		info.flags = 0;
+
+		if (copy_to_user((void __user *)arg, &info, minsz))
+			return -EFAULT;
+
+		return 0;
+	}
+	case VFIO_IOMMU_MAP_DMA: {
+		struct vfio_iommu_type1_dma_map param;
+		struct iommu_table *tbl = container->tbl;
+		unsigned long tce, i;
+
+		if (!tbl)
+			return -ENXIO;
+
+		BUG_ON(!tbl->it_group);
+
+		minsz = offsetofend(struct vfio_iommu_type1_dma_map, size);
+
+		if (copy_from_user(&param, (void __user *)arg, minsz))
+			return -EFAULT;
+
+		if (param.argsz < minsz)
+			return -EINVAL;
+
+		if (param.flags & ~(VFIO_DMA_MAP_FLAG_READ |
+				VFIO_DMA_MAP_FLAG_WRITE))
+			return -EINVAL;
+
+		if ((param.size & ~IOMMU_PAGE_MASK) ||
+				(param.vaddr & ~IOMMU_PAGE_MASK))
+			return -EINVAL;
+
+		/* iova is checked by the IOMMU API */
+		tce = param.vaddr;
+		if (param.flags & VFIO_DMA_MAP_FLAG_READ)
+			tce |= TCE_PCI_READ;
+		if (param.flags & VFIO_DMA_MAP_FLAG_WRITE)
+			tce |= TCE_PCI_WRITE;
+
+		ret = iommu_tce_put_param_check(tbl, param.iova, tce);
+		if (ret)
+			return ret;
+
+		for (i = 0; i < (param.size >> IOMMU_PAGE_SHIFT); ++i) {
+			ret = iommu_put_tce_user_mode(tbl,
+					(param.iova >> IOMMU_PAGE_SHIFT) + i,
+					tce);
+			if (ret)
+				break;
+			tce += IOMMU_PAGE_SIZE;
+		}
+		if (ret)
+			iommu_clear_tces_and_put_pages(tbl,
+					param.iova >> IOMMU_PAGE_SHIFT,	i);
+
+		iommu_flush_tce(tbl);
+
+		return ret;
+	}
+	case VFIO_IOMMU_UNMAP_DMA: {
+		struct vfio_iommu_type1_dma_unmap param;
+		struct iommu_table *tbl = container->tbl;
+
+		if (WARN_ON(!tbl))
+			return -ENXIO;
+
+		minsz = offsetofend(struct vfio_iommu_type1_dma_unmap,
+				size);
+
+		if (copy_from_user(&param, (void __user *)arg, minsz))
+			return -EFAULT;
+
+		if (param.argsz < minsz)
+			return -EINVAL;
+
+		/* No flag is supported now */
+		if (param.flags)
+			return -EINVAL;
+
+		if (param.size & ~IOMMU_PAGE_MASK)
+			return -EINVAL;
+
+		ret = iommu_tce_clear_param_check(tbl, param.iova, 0,
+				param.size >> IOMMU_PAGE_SHIFT);
+		if (ret)
+			return ret;
+
+		ret = iommu_clear_tces_and_put_pages(tbl,
+				param.iova >> IOMMU_PAGE_SHIFT,
+				param.size >> IOMMU_PAGE_SHIFT);
+		iommu_flush_tce(tbl);
+
+		return ret;
+	}
+	case VFIO_IOMMU_ENABLE:
+		mutex_lock(&container->lock);
+		ret = tce_iommu_enable(container);
+		mutex_unlock(&container->lock);
+		return ret;
+
+
+	case VFIO_IOMMU_DISABLE:
+		mutex_lock(&container->lock);
+		tce_iommu_disable(container);
+		mutex_unlock(&container->lock);
+		return 0;
+	}
+
+	return -ENOTTY;
+}
+
+static int tce_iommu_attach_group(void *iommu_data,
+		struct iommu_group *iommu_group)
+{
+	int ret;
+	struct tce_container *container = iommu_data;
+	struct iommu_table *tbl = iommu_group_get_iommudata(iommu_group);
+
+	BUG_ON(!tbl);
+	mutex_lock(&container->lock);
+
+	/* pr_debug("tce_vfio: Attaching group #%u to iommu %p\n",
+			iommu_group_id(iommu_group), iommu_group); */
+	if (container->tbl) {
+		pr_warn("tce_vfio: Only one group per IOMMU container is allowed, existing id=%d, attaching id=%d\n",
+				iommu_group_id(container->tbl->it_group),
+				iommu_group_id(iommu_group));
+		ret = -EBUSY;
+	} else if (container->enabled) {
+		pr_err("tce_vfio: attaching group #%u to enabled container\n",
+				iommu_group_id(iommu_group));
+		ret = -EBUSY;
+	} else {
+		ret = iommu_take_ownership(tbl);
+		if (!ret)
+			container->tbl = tbl;
+	}
+
+	mutex_unlock(&container->lock);
+
+	return ret;
+}
+
+static void tce_iommu_detach_group(void *iommu_data,
+		struct iommu_group *iommu_group)
+{
+	struct tce_container *container = iommu_data;
+	struct iommu_table *tbl = iommu_group_get_iommudata(iommu_group);
+
+	BUG_ON(!tbl);
+	mutex_lock(&container->lock);
+	if (tbl != container->tbl) {
+		pr_warn("tce_vfio: detaching group #%u, expected group is #%u\n",
+				iommu_group_id(iommu_group),
+				iommu_group_id(tbl->it_group));
+	} else {
+		if (container->enabled) {
+			pr_warn("tce_vfio: detaching group #%u from enabled container, forcing disable\n",
+					iommu_group_id(tbl->it_group));
+			tce_iommu_disable(container);
+		}
+
+		/* pr_debug("tce_vfio: detaching group #%u from iommu %p\n",
+				iommu_group_id(iommu_group), iommu_group); */
+		container->tbl = NULL;
+		iommu_release_ownership(tbl);
+	}
+	mutex_unlock(&container->lock);
+}
+
+const struct vfio_iommu_driver_ops tce_iommu_driver_ops = {
+	.name		= "iommu-vfio-powerpc",
+	.owner		= THIS_MODULE,
+	.open		= tce_iommu_open,
+	.release	= tce_iommu_release,
+	.ioctl		= tce_iommu_ioctl,
+	.attach_group	= tce_iommu_attach_group,
+	.detach_group	= tce_iommu_detach_group,
+};
+
+static int __init tce_iommu_init(void)
+{
+	return vfio_register_iommu_driver(&tce_iommu_driver_ops);
+}
+
+static void __exit tce_iommu_cleanup(void)
+{
+	vfio_unregister_iommu_driver(&tce_iommu_driver_ops);
+}
+
+module_init(tce_iommu_init);
+module_exit(tce_iommu_cleanup);
+
+MODULE_VERSION(DRIVER_VERSION);
+MODULE_LICENSE("GPL v2");
+MODULE_AUTHOR(DRIVER_AUTHOR);
+MODULE_DESCRIPTION(DRIVER_DESC);
+
diff --git a/drivers/watchdog/booke_wdt.c b/drivers/watchdog/booke_wdt.c
index a8dbceb3291..f1b8d555080 100644
--- a/drivers/watchdog/booke_wdt.c
+++ b/drivers/watchdog/booke_wdt.c
@@ -138,6 +138,14 @@ static void __booke_wdt_enable(void *data)
 	val &= ~WDTP_MASK;
 	val |= (TCR_WIE|TCR_WRC(WRC_CHIP)|WDTP(booke_wdt_period));
 
+#ifdef CONFIG_PPC_BOOK3E_64
+	/*
+	 * Crit ints are currently broken on PPC64 Book-E, so
+	 * just disable them for now.
+	 */
+	val &= ~TCR_WIE;
+#endif
+
 	mtspr(SPRN_TCR, val);
 }