Merge branch 'linus' into stackprotector

Conflicts:
	arch/x86/kernel/Makefile
	include/asm-x86/pda.h

24 files changed, 932 insertions, 196 deletions

diff --git a/arch/powerpc/platforms/cell/Kconfig b/arch/powerpc/platforms/cell/Kconfig
index 3959fcfe731c..c14d7d8d96c8 100644
--- a/arch/powerpc/platforms/cell/Kconfig
+++ b/arch/powerpc/platforms/cell/Kconfig
@@ -83,6 +83,22 @@ config CBE_RAS
 	depends on PPC_CELL_NATIVE
 	default y
 
+config PPC_IBM_CELL_RESETBUTTON
+	bool "IBM Cell Blade Pinhole reset button"
+	depends on CBE_RAS && PPC_IBM_CELL_BLADE
+	default y
+	help
+	  Support Pinhole Resetbutton on IBM Cell blades.
+	  This adds a method to trigger system reset via front panel pinhole button.
+
+config PPC_IBM_CELL_POWERBUTTON
+	tristate "IBM Cell Blade power button"
+	depends on PPC_IBM_CELL_BLADE && PPC_PMI && INPUT_EVDEV
+	default y
+	help
+	  Support Powerbutton on IBM Cell blades.
+	  This will enable the powerbutton as an input device.
+
 config CBE_THERM
 	tristate "CBE thermal support"
 	default m
@@ -107,6 +123,15 @@ config CBE_CPUFREQ_PMI
 	  processor will not only be able to run at lower speed,
 	  but also at lower core voltage.
 
+config CBE_CPUFREQ_SPU_GOVERNOR
+	tristate "CBE frequency scaling based on SPU usage"
+	depends on SPU_FS && CPU_FREQ
+	default m
+	help
+	  This governor checks for spu usage to adjust the cpu frequency.
+	  If no spu is running on a given cpu, that cpu will be throttled to
+	  the minimal possible frequency.
+
 endmenu
 
 config OPROFILE_CELL
diff --git a/arch/powerpc/platforms/cell/Makefile b/arch/powerpc/platforms/cell/Makefile
index c2a7e4e5ddf9..7fd830872c43 100644
--- a/arch/powerpc/platforms/cell/Makefile
+++ b/arch/powerpc/platforms/cell/Makefile
@@ -8,6 +8,9 @@ obj-$(CONFIG_CBE_THERM)			+= cbe_thermal.o
 obj-$(CONFIG_CBE_CPUFREQ_PMI)		+= cbe_cpufreq_pmi.o
 obj-$(CONFIG_CBE_CPUFREQ)		+= cbe-cpufreq.o
 cbe-cpufreq-y				+= cbe_cpufreq_pervasive.o cbe_cpufreq.o
+obj-$(CONFIG_CBE_CPUFREQ_SPU_GOVERNOR)	+= cpufreq_spudemand.o
+
+obj-$(CONFIG_PPC_IBM_CELL_POWERBUTTON)	+= cbe_powerbutton.o
 
 ifeq ($(CONFIG_SMP),y)
 obj-$(CONFIG_PPC_CELL_NATIVE)		+= smp.o
diff --git a/arch/powerpc/platforms/cell/axon_msi.c b/arch/powerpc/platforms/cell/axon_msi.c
index c39f5c225f2e..896548ba1ca1 100644
--- a/arch/powerpc/platforms/cell/axon_msi.c
+++ b/arch/powerpc/platforms/cell/axon_msi.c
@@ -14,6 +14,7 @@
 #include <linux/pci.h>
 #include <linux/msi.h>
 #include <linux/of_platform.h>
+#include <linux/debugfs.h>
 
 #include <asm/dcr.h>
 #include <asm/machdep.h>
@@ -69,8 +70,19 @@ struct axon_msic {
 	dma_addr_t fifo_phys;
 	dcr_host_t dcr_host;
 	u32 read_offset;
+#ifdef DEBUG
+	u32 __iomem *trigger;
+#endif
 };
 
+#ifdef DEBUG
+void axon_msi_debug_setup(struct device_node *dn, struct axon_msic *msic);
+#else
+static inline void axon_msi_debug_setup(struct device_node *dn,
+					struct axon_msic *msic) { }
+#endif
+
+
 static void msic_dcr_write(struct axon_msic *msic, unsigned int dcr_n, u32 val)
 {
 	pr_debug("axon_msi: dcr_write(0x%x, 0x%x)\n", val, dcr_n);
@@ -346,7 +358,14 @@ static int axon_msi_probe(struct of_device *device,
 		goto out_free_msic;
 	}
 
-	msic->irq_host = irq_alloc_host(of_node_get(dn), IRQ_HOST_MAP_NOMAP,
+	virq = irq_of_parse_and_map(dn, 0);
+	if (virq == NO_IRQ) {
+		printk(KERN_ERR "axon_msi: irq parse and map failed for %s\n",
+		       dn->full_name);
+		goto out_free_fifo;
+	}
+
+	msic->irq_host = irq_alloc_host(dn, IRQ_HOST_MAP_NOMAP,
 					NR_IRQS, &msic_host_ops, 0);
 	if (!msic->irq_host) {
 		printk(KERN_ERR "axon_msi: couldn't allocate irq_host for %s\n",
@@ -356,13 +375,6 @@ static int axon_msi_probe(struct of_device *device,
 
 	msic->irq_host->host_data = msic;
 
-	virq = irq_of_parse_and_map(dn, 0);
-	if (virq == NO_IRQ) {
-		printk(KERN_ERR "axon_msi: irq parse and map failed for %s\n",
-		       dn->full_name);
-		goto out_free_host;
-	}
-
 	set_irq_data(virq, msic);
 	set_irq_chained_handler(virq, axon_msi_cascade);
 	pr_debug("axon_msi: irq 0x%x setup for axon_msi\n", virq);
@@ -381,12 +393,12 @@ static int axon_msi_probe(struct of_device *device,
 	ppc_md.teardown_msi_irqs = axon_msi_teardown_msi_irqs;
 	ppc_md.msi_check_device = axon_msi_check_device;
 
+	axon_msi_debug_setup(dn, msic);
+
 	printk(KERN_DEBUG "axon_msi: setup MSIC on %s\n", dn->full_name);
 
 	return 0;
 
-out_free_host:
-	kfree(msic->irq_host);
 out_free_fifo:
 	dma_free_coherent(&device->dev, MSIC_FIFO_SIZE_BYTES, msic->fifo_virt,
 			  msic->fifo_phys);
@@ -418,3 +430,47 @@ static int __init axon_msi_init(void)
 	return of_register_platform_driver(&axon_msi_driver);
 }
 subsys_initcall(axon_msi_init);
+
+
+#ifdef DEBUG
+static int msic_set(void *data, u64 val)
+{
+	struct axon_msic *msic = data;
+	out_le32(msic->trigger, val);
+	return 0;
+}
+
+static int msic_get(void *data, u64 *val)
+{
+	*val = 0;
+	return 0;
+}
+
+DEFINE_SIMPLE_ATTRIBUTE(fops_msic, msic_get, msic_set, "%llu\n");
+
+void axon_msi_debug_setup(struct device_node *dn, struct axon_msic *msic)
+{
+	char name[8];
+	u64 addr;
+
+	addr = of_translate_address(dn, of_get_property(dn, "reg", NULL));
+	if (addr == OF_BAD_ADDR) {
+		pr_debug("axon_msi: couldn't translate reg property\n");
+		return;
+	}
+
+	msic->trigger = ioremap(addr, 0x4);
+	if (!msic->trigger) {
+		pr_debug("axon_msi: ioremap failed\n");
+		return;
+	}
+
+	snprintf(name, sizeof(name), "msic_%d", of_node_to_nid(dn));
+
+	if (!debugfs_create_file(name, 0600, powerpc_debugfs_root,
+				 msic, &fops_msic)) {
+		pr_debug("axon_msi: debugfs_create_file failed!\n");
+		return;
+	}
+}
+#endif /* DEBUG */
diff --git a/arch/powerpc/platforms/cell/beat_htab.c b/arch/powerpc/platforms/cell/beat_htab.c
index 81467ff055c8..2e67bd840e01 100644
--- a/arch/powerpc/platforms/cell/beat_htab.c
+++ b/arch/powerpc/platforms/cell/beat_htab.c
@@ -112,7 +112,7 @@ static long beat_lpar_hpte_insert(unsigned long hpte_group,
 	if (!(vflags & HPTE_V_BOLTED))
 		DBG_LOW(" hpte_v=%016lx, hpte_r=%016lx\n", hpte_v, hpte_r);
 
-	if (rflags & (_PAGE_GUARDED|_PAGE_NO_CACHE))
+	if (rflags & _PAGE_NO_CACHE)
 		hpte_r &= ~_PAGE_COHERENT;
 
 	spin_lock(&beat_htab_lock);
@@ -334,7 +334,7 @@ static long beat_lpar_hpte_insert_v3(unsigned long hpte_group,
 	if (!(vflags & HPTE_V_BOLTED))
 		DBG_LOW(" hpte_v=%016lx, hpte_r=%016lx\n", hpte_v, hpte_r);
 
-	if (rflags & (_PAGE_GUARDED|_PAGE_NO_CACHE))
+	if (rflags & _PAGE_NO_CACHE)
 		hpte_r &= ~_PAGE_COHERENT;
 
 	/* insert into not-volted entry */
diff --git a/arch/powerpc/platforms/cell/cbe_cpufreq_pmi.c b/arch/powerpc/platforms/cell/cbe_cpufreq_pmi.c
index 69288f653144..3233fe84d158 100644
--- a/arch/powerpc/platforms/cell/cbe_cpufreq_pmi.c
+++ b/arch/powerpc/platforms/cell/cbe_cpufreq_pmi.c
@@ -96,6 +96,12 @@ static int pmi_notifier(struct notifier_block *nb,
 	struct cpufreq_frequency_table *cbe_freqs;
 	u8 node;
 
+	/* Should this really be called for CPUFREQ_ADJUST, CPUFREQ_INCOMPATIBLE
+	 * and CPUFREQ_NOTIFY policy events?)
+	 */
+	if (event == CPUFREQ_START)
+		return 0;
+
 	cbe_freqs = cpufreq_frequency_get_table(policy->cpu);
 	node = cbe_cpu_to_node(policy->cpu);
 
diff --git a/arch/powerpc/platforms/cell/cbe_powerbutton.c b/arch/powerpc/platforms/cell/cbe_powerbutton.c
new file mode 100644
index 000000000000..dcddaa5fcb66
--- /dev/null
+++ b/arch/powerpc/platforms/cell/cbe_powerbutton.c
@@ -0,0 +1,117 @@
+/*
+ * driver for powerbutton on IBM cell blades
+ *
+ * (C) Copyright IBM Corp. 2005-2008
+ *
+ * Author: Christian Krafft <krafft@de.ibm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2, or (at your option)
+ * any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+ */
+
+#include <linux/input.h>
+#include <linux/platform_device.h>
+#include <asm/pmi.h>
+#include <asm/prom.h>
+
+static struct input_dev *button_dev;
+static struct platform_device *button_pdev;
+
+static void cbe_powerbutton_handle_pmi(pmi_message_t pmi_msg)
+{
+	BUG_ON(pmi_msg.type != PMI_TYPE_POWER_BUTTON);
+
+	input_report_key(button_dev, KEY_POWER, 1);
+	input_sync(button_dev);
+	input_report_key(button_dev, KEY_POWER, 0);
+	input_sync(button_dev);
+}
+
+static struct pmi_handler cbe_pmi_handler = {
+	.type			= PMI_TYPE_POWER_BUTTON,
+	.handle_pmi_message	= cbe_powerbutton_handle_pmi,
+};
+
+static int __init cbe_powerbutton_init(void)
+{
+	int ret = 0;
+	struct input_dev *dev;
+
+	if (!machine_is_compatible("IBM,CBPLUS-1.0")) {
+		printk(KERN_ERR "%s: Not a cell blade.\n", __func__);
+		ret = -ENODEV;
+		goto out;
+	}
+
+	dev = input_allocate_device();
+	if (!dev) {
+		ret = -ENOMEM;
+		printk(KERN_ERR "%s: Not enough memory.\n", __func__);
+		goto out;
+	}
+
+	set_bit(EV_KEY, dev->evbit);
+	set_bit(KEY_POWER, dev->keybit);
+
+	dev->name = "Power Button";
+	dev->id.bustype = BUS_HOST;
+
+	/* this makes the button look like an acpi power button
+	 * no clue whether anyone relies on that though */
+	dev->id.product = 0x02;
+	dev->phys = "LNXPWRBN/button/input0";
+
+	button_pdev = platform_device_register_simple("power_button", 0, NULL, 0);
+	if (IS_ERR(button_pdev)) {
+		ret = PTR_ERR(button_pdev);
+		goto out_free_input;
+	}
+
+	dev->dev.parent = &button_pdev->dev;
+	ret = input_register_device(dev);
+	if (ret) {
+		printk(KERN_ERR "%s: Failed to register device\n", __func__);
+		goto out_free_pdev;
+	}
+
+	button_dev = dev;
+
+	ret = pmi_register_handler(&cbe_pmi_handler);
+	if (ret) {
+		printk(KERN_ERR "%s: Failed to register with pmi.\n", __func__);
+		goto out_free_pdev;
+	}
+
+	goto out;
+
+out_free_pdev:
+	platform_device_unregister(button_pdev);
+out_free_input:
+	input_free_device(dev);
+out:
+	return ret;
+}
+
+static void __exit cbe_powerbutton_exit(void)
+{
+	pmi_unregister_handler(&cbe_pmi_handler);
+	platform_device_unregister(button_pdev);
+	input_free_device(button_dev);
+}
+
+module_init(cbe_powerbutton_init);
+module_exit(cbe_powerbutton_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Christian Krafft <krafft@de.ibm.com>");
diff --git a/arch/powerpc/platforms/cell/cbe_thermal.c b/arch/powerpc/platforms/cell/cbe_thermal.c
index 4852bf312d83..4d4c8c169124 100644
--- a/arch/powerpc/platforms/cell/cbe_thermal.c
+++ b/arch/powerpc/platforms/cell/cbe_thermal.c
@@ -97,7 +97,8 @@ static u8 spu_read_register_value(struct sys_device *sysdev, union spe_reg __iom
 	return value.spe[spu->spe_id];
 }
 
-static ssize_t spu_show_temp(struct sys_device *sysdev, char *buf)
+static ssize_t spu_show_temp(struct sys_device *sysdev, struct sysdev_attribute *attr,
+			char *buf)
 {
 	u8 value;
 	struct cbe_pmd_regs __iomem *pmd_regs;
@@ -146,32 +147,38 @@ static ssize_t store_throttle(struct cbe_pmd_regs __iomem *pmd_regs, const char
 	return size;
 }
 
-static ssize_t spu_show_throttle_end(struct sys_device *sysdev, char *buf)
+static ssize_t spu_show_throttle_end(struct sys_device *sysdev,
+			struct sysdev_attribute *attr, char *buf)
 {
 	return show_throttle(get_pmd_regs(sysdev), buf, 0);
 }
 
-static ssize_t spu_show_throttle_begin(struct sys_device *sysdev, char *buf)
+static ssize_t spu_show_throttle_begin(struct sys_device *sysdev,
+			struct sysdev_attribute *attr, char *buf)
 {
 	return show_throttle(get_pmd_regs(sysdev), buf, 8);
 }
 
-static ssize_t spu_show_throttle_full_stop(struct sys_device *sysdev, char *buf)
+static ssize_t spu_show_throttle_full_stop(struct sys_device *sysdev,
+			struct sysdev_attribute *attr, char *buf)
 {
 	return show_throttle(get_pmd_regs(sysdev), buf, 16);
 }
 
-static ssize_t spu_store_throttle_end(struct sys_device *sysdev, const char *buf, size_t size)
+static ssize_t spu_store_throttle_end(struct sys_device *sysdev,
+			struct sysdev_attribute *attr, const char *buf, size_t size)
 {
 	return store_throttle(get_pmd_regs(sysdev), buf, size, 0);
 }
 
-static ssize_t spu_store_throttle_begin(struct sys_device *sysdev, const char *buf, size_t size)
+static ssize_t spu_store_throttle_begin(struct sys_device *sysdev,
+			struct sysdev_attribute *attr, const char *buf, size_t size)
 {
 	return store_throttle(get_pmd_regs(sysdev), buf, size, 8);
 }
 
-static ssize_t spu_store_throttle_full_stop(struct sys_device *sysdev, const char *buf, size_t size)
+static ssize_t spu_store_throttle_full_stop(struct sys_device *sysdev,
+			struct sysdev_attribute *attr, const char *buf, size_t size)
 {
 	return store_throttle(get_pmd_regs(sysdev), buf, size, 16);
 }
@@ -192,43 +199,51 @@ static ssize_t ppe_show_temp(struct sys_device *sysdev, char *buf, int pos)
 
 /* shows the temperature of the DTS on the PPE,
  * located near the linear thermal sensor */
-static ssize_t ppe_show_temp0(struct sys_device *sysdev, char *buf)
+static ssize_t ppe_show_temp0(struct sys_device *sysdev,
+			struct sysdev_attribute *attr, char *buf)
 {
 	return ppe_show_temp(sysdev, buf, 32);
 }
 
 /* shows the temperature of the second DTS on the PPE */
-static ssize_t ppe_show_temp1(struct sys_device *sysdev, char *buf)
+static ssize_t ppe_show_temp1(struct sys_device *sysdev,
+			struct sysdev_attribute *attr, char *buf)
 {
 	return ppe_show_temp(sysdev, buf, 0);
 }
 
-static ssize_t ppe_show_throttle_end(struct sys_device *sysdev, char *buf)
+static ssize_t ppe_show_throttle_end(struct sys_device *sysdev,
+			struct sysdev_attribute *attr, char *buf)
 {
 	return show_throttle(cbe_get_cpu_pmd_regs(sysdev->id), buf, 32);
 }
 
-static ssize_t ppe_show_throttle_begin(struct sys_device *sysdev, char *buf)
+static ssize_t ppe_show_throttle_begin(struct sys_device *sysdev,
+			struct sysdev_attribute *attr, char *buf)
 {
 	return show_throttle(cbe_get_cpu_pmd_regs(sysdev->id), buf, 40);
 }
 
-static ssize_t ppe_show_throttle_full_stop(struct sys_device *sysdev, char *buf)
+static ssize_t ppe_show_throttle_full_stop(struct sys_device *sysdev,
+			struct sysdev_attribute *attr, char *buf)
 {
 	return show_throttle(cbe_get_cpu_pmd_regs(sysdev->id), buf, 48);
 }
 
-static ssize_t ppe_store_throttle_end(struct sys_device *sysdev, const char *buf, size_t size)
+static ssize_t ppe_store_throttle_end(struct sys_device *sysdev,
+			struct sysdev_attribute *attr, const char *buf, size_t size)
 {
 	return store_throttle(cbe_get_cpu_pmd_regs(sysdev->id), buf, size, 32);
 }
 
-static ssize_t ppe_store_throttle_begin(struct sys_device *sysdev, const char *buf, size_t size)
+static ssize_t ppe_store_throttle_begin(struct sys_device *sysdev,
+			struct sysdev_attribute *attr, const char *buf, size_t size)
 {
 	return store_throttle(cbe_get_cpu_pmd_regs(sysdev->id), buf, size, 40);
 }
 
-static ssize_t ppe_store_throttle_full_stop(struct sys_device *sysdev, const char *buf, size_t size)
+static ssize_t ppe_store_throttle_full_stop(struct sys_device *sysdev,
+			struct sysdev_attribute *attr, const char *buf, size_t size)
 {
 	return store_throttle(cbe_get_cpu_pmd_regs(sysdev->id), buf, size, 48);
 }
diff --git a/arch/powerpc/platforms/cell/celleb_scc_pciex.c b/arch/powerpc/platforms/cell/celleb_scc_pciex.c
index 0e04f8fb152a..3e7e0f1568ef 100644
--- a/arch/powerpc/platforms/cell/celleb_scc_pciex.c
+++ b/arch/powerpc/platforms/cell/celleb_scc_pciex.c
@@ -281,7 +281,7 @@ static int __init scc_pciex_iowa_init(struct iowa_bus *bus, void *data)
 
 	dummy_page_da = dma_map_single(bus->phb->parent, dummy_page_va,
 				       PAGE_SIZE, DMA_FROM_DEVICE);
-	if (dma_mapping_error(dummy_page_da)) {
+	if (dma_mapping_error(bus->phb->parent, dummy_page_da)) {
 		pr_err("PCIEX:Map dummy page failed.\n");
 		kfree(dummy_page_va);
 		return -1;
diff --git a/arch/powerpc/platforms/cell/cpufreq_spudemand.c b/arch/powerpc/platforms/cell/cpufreq_spudemand.c
new file mode 100644
index 000000000000..a3c6c01bd6db
--- /dev/null
+++ b/arch/powerpc/platforms/cell/cpufreq_spudemand.c
@@ -0,0 +1,184 @@
+/*
+ * spu aware cpufreq governor for the cell processor
+ *
+ * © Copyright IBM Corporation 2006-2008
+ *
+ * Author: Christian Krafft <krafft@de.ibm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2, or (at your option)
+ * any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+ */
+
+#include <linux/cpufreq.h>
+#include <linux/sched.h>
+#include <linux/timer.h>
+#include <linux/workqueue.h>
+#include <asm/atomic.h>
+#include <asm/machdep.h>
+#include <asm/spu.h>
+
+#define POLL_TIME	100000		/* in µs */
+#define EXP		753		/* exp(-1) in fixed-point */
+
+struct spu_gov_info_struct {
+	unsigned long busy_spus;	/* fixed-point */
+	struct cpufreq_policy *policy;
+	struct delayed_work work;
+	unsigned int poll_int;		/* µs */
+};
+static DEFINE_PER_CPU(struct spu_gov_info_struct, spu_gov_info);
+
+static struct workqueue_struct *kspugov_wq;
+
+static int calc_freq(struct spu_gov_info_struct *info)
+{
+	int cpu;
+	int busy_spus;
+
+	cpu = info->policy->cpu;
+	busy_spus = atomic_read(&cbe_spu_info[cpu_to_node(cpu)].busy_spus);
+
+	CALC_LOAD(info->busy_spus, EXP, busy_spus * FIXED_1);
+	pr_debug("cpu %d: busy_spus=%d, info->busy_spus=%ld\n",
+			cpu, busy_spus, info->busy_spus);
+
+	return info->policy->max * info->busy_spus / FIXED_1;
+}
+
+static void spu_gov_work(struct work_struct *work)
+{
+	struct spu_gov_info_struct *info;
+	int delay;
+	unsigned long target_freq;
+
+	info = container_of(work, struct spu_gov_info_struct, work.work);
+
+	/* after cancel_delayed_work_sync we unset info->policy */
+	BUG_ON(info->policy == NULL);
+
+	target_freq = calc_freq(info);
+	__cpufreq_driver_target(info->policy, target_freq, CPUFREQ_RELATION_H);
+
+	delay = usecs_to_jiffies(info->poll_int);
+	queue_delayed_work_on(info->policy->cpu, kspugov_wq, &info->work, delay);
+}
+
+static void spu_gov_init_work(struct spu_gov_info_struct *info)
+{
+	int delay = usecs_to_jiffies(info->poll_int);
+	INIT_DELAYED_WORK_DEFERRABLE(&info->work, spu_gov_work);
+	queue_delayed_work_on(info->policy->cpu, kspugov_wq, &info->work, delay);
+}
+
+static void spu_gov_cancel_work(struct spu_gov_info_struct *info)
+{
+	cancel_delayed_work_sync(&info->work);
+}
+
+static int spu_gov_govern(struct cpufreq_policy *policy, unsigned int event)
+{
+	unsigned int cpu = policy->cpu;
+	struct spu_gov_info_struct *info, *affected_info;
+	int i;
+	int ret = 0;
+
+	info = &per_cpu(spu_gov_info, cpu);
+
+	switch (event) {
+	case CPUFREQ_GOV_START:
+		if (!cpu_online(cpu)) {
+			printk(KERN_ERR "cpu %d is not online\n", cpu);
+			ret = -EINVAL;
+			break;
+		}
+
+		if (!policy->cur) {
+			printk(KERN_ERR "no cpu specified in policy\n");
+			ret = -EINVAL;
+			break;
+		}
+
+		/* initialize spu_gov_info for all affected cpus */
+		for_each_cpu_mask(i, policy->cpus) {
+			affected_info = &per_cpu(spu_gov_info, i);
+			affected_info->policy = policy;
+		}
+
+		info->poll_int = POLL_TIME;
+
+		/* setup timer */
+		spu_gov_init_work(info);
+
+		break;
+
+	case CPUFREQ_GOV_STOP:
+		/* cancel timer */
+		spu_gov_cancel_work(info);
+
+		/* clean spu_gov_info for all affected cpus */
+		for_each_cpu_mask (i, policy->cpus) {
+			info = &per_cpu(spu_gov_info, i);
+			info->policy = NULL;
+		}
+
+		break;
+	}
+
+	return ret;
+}
+
+static struct cpufreq_governor spu_governor = {
+	.name = "spudemand",
+	.governor = spu_gov_govern,
+	.owner = THIS_MODULE,
+};
+
+/*
+ * module init and destoy
+ */
+
+static int __init spu_gov_init(void)
+{
+	int ret;
+
+	kspugov_wq = create_workqueue("kspugov");
+	if (!kspugov_wq) {
+		printk(KERN_ERR "creation of kspugov failed\n");
+		ret = -EFAULT;
+		goto out;
+	}
+
+	ret = cpufreq_register_governor(&spu_governor);
+	if (ret) {
+		printk(KERN_ERR "registration of governor failed\n");
+		destroy_workqueue(kspugov_wq);
+		goto out;
+	}
+out:
+	return ret;
+}
+
+static void __exit spu_gov_exit(void)
+{
+	cpufreq_unregister_governor(&spu_governor);
+	destroy_workqueue(kspugov_wq);
+}
+
+
+module_init(spu_gov_init);
+module_exit(spu_gov_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Christian Krafft <krafft@de.ibm.com>");
+
diff --git a/arch/powerpc/platforms/cell/interrupt.c b/arch/powerpc/platforms/cell/interrupt.c
index 5bf7df146022..2d5bb22d6c09 100644
--- a/arch/powerpc/platforms/cell/interrupt.c
+++ b/arch/powerpc/platforms/cell/interrupt.c
@@ -218,6 +218,7 @@ void iic_request_IPIs(void)
 {
 	iic_request_ipi(PPC_MSG_CALL_FUNCTION, "IPI-call");
 	iic_request_ipi(PPC_MSG_RESCHEDULE, "IPI-resched");
+	iic_request_ipi(PPC_MSG_CALL_FUNC_SINGLE, "IPI-call-single");
 #ifdef CONFIG_DEBUGGER
 	iic_request_ipi(PPC_MSG_DEBUGGER_BREAK, "IPI-debug");
 #endif /* CONFIG_DEBUGGER */
diff --git a/arch/powerpc/platforms/cell/iommu.c b/arch/powerpc/platforms/cell/iommu.c
index 45646b2b4af4..e06420af5fe9 100644
--- a/arch/powerpc/platforms/cell/iommu.c
+++ b/arch/powerpc/platforms/cell/iommu.c
@@ -172,8 +172,9 @@ static void invalidate_tce_cache(struct cbe_iommu *iommu, unsigned long *pte,
 	}
 }
 
-static void tce_build_cell(struct iommu_table *tbl, long index, long npages,
-		unsigned long uaddr, enum dma_data_direction direction)
+static int tce_build_cell(struct iommu_table *tbl, long index, long npages,
+		unsigned long uaddr, enum dma_data_direction direction,
+		struct dma_attrs *attrs)
 {
 	int i;
 	unsigned long *io_pte, base_pte;
@@ -198,6 +199,8 @@ static void tce_build_cell(struct iommu_table *tbl, long index, long npages,
 	base_pte = IOPTE_PP_W | IOPTE_PP_R | IOPTE_M | IOPTE_SO_RW |
 		(window->ioid & IOPTE_IOID_Mask);
 #endif
+	if (unlikely(dma_get_attr(DMA_ATTR_WEAK_ORDERING, attrs)))
+		base_pte &= ~IOPTE_SO_RW;
 
 	io_pte = (unsigned long *)tbl->it_base + (index - tbl->it_offset);
 
@@ -210,6 +213,7 @@ static void tce_build_cell(struct iommu_table *tbl, long index, long npages,
 
 	pr_debug("tce_build_cell(index=%lx,n=%lx,dir=%d,base_pte=%lx)\n",
 		 index, npages, direction, base_pte);
+	return 0;
 }
 
 static void tce_free_cell(struct iommu_table *tbl, long index, long npages)
@@ -519,7 +523,7 @@ cell_iommu_setup_window(struct cbe_iommu *iommu, struct device_node *np,
 
 	__set_bit(0, window->table.it_map);
 	tce_build_cell(&window->table, window->table.it_offset, 1,
-		       (unsigned long)iommu->pad_page, DMA_TO_DEVICE);
+		       (unsigned long)iommu->pad_page, DMA_TO_DEVICE, NULL);
 	window->table.it_hint = window->table.it_blocksize;
 
 	return window;
@@ -538,9 +542,11 @@ static struct cbe_iommu *cell_iommu_for_node(int nid)
 static unsigned long cell_dma_direct_offset;
 
 static unsigned long dma_iommu_fixed_base;
-struct dma_mapping_ops dma_iommu_fixed_ops;
 
-static void cell_dma_dev_setup_iommu(struct device *dev)
+/* iommu_fixed_is_weak is set if booted with iommu_fixed=weak */
+static int iommu_fixed_is_weak;
+
+static struct iommu_table *cell_get_iommu_table(struct device *dev)
 {
 	struct iommu_window *window;
 	struct cbe_iommu *iommu;
@@ -555,13 +561,105 @@ static void cell_dma_dev_setup_iommu(struct device *dev)
 		printk(KERN_ERR "iommu: missing iommu for %s (node %d)\n",
 		       archdata->of_node ? archdata->of_node->full_name : "?",
 		       archdata->numa_node);
-		return;
+		return NULL;
 	}
 	window = list_entry(iommu->windows.next, struct iommu_window, list);
 
-	archdata->dma_data = &window->table;
+	return &window->table;
+}
+
+/* A coherent allocation implies strong ordering */
+
+static void *dma_fixed_alloc_coherent(struct device *dev, size_t size,
+				      dma_addr_t *dma_handle, gfp_t flag)
+{
+	if (iommu_fixed_is_weak)
+		return iommu_alloc_coherent(dev, cell_get_iommu_table(dev),
+					    size, dma_handle,
+					    device_to_mask(dev), flag,
+					    dev->archdata.numa_node);
+	else
+		return dma_direct_ops.alloc_coherent(dev, size, dma_handle,
+						     flag);
+}
+
+static void dma_fixed_free_coherent(struct device *dev, size_t size,
+				    void *vaddr, dma_addr_t dma_handle)
+{
+	if (iommu_fixed_is_weak)
+		iommu_free_coherent(cell_get_iommu_table(dev), size, vaddr,
+				    dma_handle);
+	else
+		dma_direct_ops.free_coherent(dev, size, vaddr, dma_handle);
+}
+
+static dma_addr_t dma_fixed_map_single(struct device *dev, void *ptr,
+				       size_t size,
+				       enum dma_data_direction direction,
+				       struct dma_attrs *attrs)
+{
+	if (iommu_fixed_is_weak == dma_get_attr(DMA_ATTR_WEAK_ORDERING, attrs))
+		return dma_direct_ops.map_single(dev, ptr, size, direction,
+						 attrs);
+	else
+		return iommu_map_single(dev, cell_get_iommu_table(dev), ptr,
+					size, device_to_mask(dev), direction,
+					attrs);
 }
 
+static void dma_fixed_unmap_single(struct device *dev, dma_addr_t dma_addr,
+				   size_t size,
+				   enum dma_data_direction direction,
+				   struct dma_attrs *attrs)
+{
+	if (iommu_fixed_is_weak == dma_get_attr(DMA_ATTR_WEAK_ORDERING, attrs))
+		dma_direct_ops.unmap_single(dev, dma_addr, size, direction,
+					    attrs);
+	else
+		iommu_unmap_single(cell_get_iommu_table(dev), dma_addr, size,
+				   direction, attrs);
+}
+
+static int dma_fixed_map_sg(struct device *dev, struct scatterlist *sg,
+			   int nents, enum dma_data_direction direction,
+			   struct dma_attrs *attrs)
+{
+	if (iommu_fixed_is_weak == dma_get_attr(DMA_ATTR_WEAK_ORDERING, attrs))
+		return dma_direct_ops.map_sg(dev, sg, nents, direction, attrs);
+	else
+		return iommu_map_sg(dev, cell_get_iommu_table(dev), sg, nents,
+				    device_to_mask(dev), direction, attrs);
+}
+
+static void dma_fixed_unmap_sg(struct device *dev, struct scatterlist *sg,
+			       int nents, enum dma_data_direction direction,
+			       struct dma_attrs *attrs)
+{
+	if (iommu_fixed_is_weak == dma_get_attr(DMA_ATTR_WEAK_ORDERING, attrs))
+		dma_direct_ops.unmap_sg(dev, sg, nents, direction, attrs);
+	else
+		iommu_unmap_sg(cell_get_iommu_table(dev), sg, nents, direction,
+			       attrs);
+}
+
+static int dma_fixed_dma_supported(struct device *dev, u64 mask)
+{
+	return mask == DMA_64BIT_MASK;
+}
+
+static int dma_set_mask_and_switch(struct device *dev, u64 dma_mask);
+
+struct dma_mapping_ops dma_iommu_fixed_ops = {
+	.alloc_coherent = dma_fixed_alloc_coherent,
+	.free_coherent  = dma_fixed_free_coherent,
+	.map_single     = dma_fixed_map_single,
+	.unmap_single   = dma_fixed_unmap_single,
+	.map_sg         = dma_fixed_map_sg,
+	.unmap_sg       = dma_fixed_unmap_sg,
+	.dma_supported  = dma_fixed_dma_supported,
+	.set_dma_mask   = dma_set_mask_and_switch,
+};
+
 static void cell_dma_dev_setup_fixed(struct device *dev);
 
 static void cell_dma_dev_setup(struct device *dev)
@@ -572,7 +670,7 @@ static void cell_dma_dev_setup(struct device *dev)
 	if (get_dma_ops(dev) == &dma_iommu_fixed_ops)
 		cell_dma_dev_setup_fixed(dev);
 	else if (get_pci_dma_ops() == &dma_iommu_ops)
-		cell_dma_dev_setup_iommu(dev);
+		archdata->dma_data = cell_get_iommu_table(dev);
 	else if (get_pci_dma_ops() == &dma_direct_ops)
 		archdata->dma_data = (void *)cell_dma_direct_offset;
 	else
@@ -918,9 +1016,16 @@ static void cell_iommu_setup_fixed_ptab(struct cbe_iommu *iommu,
 
 	pr_debug("iommu: mapping 0x%lx pages from 0x%lx\n", fsize, fbase);
 
-	base_pte = IOPTE_PP_W | IOPTE_PP_R | IOPTE_M | IOPTE_SO_RW
+	base_pte = IOPTE_PP_W | IOPTE_PP_R | IOPTE_M
 		    | (cell_iommu_get_ioid(np) & IOPTE_IOID_Mask);
 
+	if (iommu_fixed_is_weak)
+		pr_info("IOMMU: Using weak ordering for fixed mapping\n");
+	else {
+		pr_info("IOMMU: Using strong ordering for fixed mapping\n");
+		base_pte |= IOPTE_SO_RW;
+	}
+
 	for (uaddr = 0; uaddr < fsize; uaddr += (1 << 24)) {
 		/* Don't touch the dynamic region */
 		ioaddr = uaddr + fbase;
@@ -1036,9 +1141,6 @@ static int __init cell_iommu_fixed_mapping_init(void)
 		cell_iommu_setup_window(iommu, np, dbase, dsize, 0);
 	}
 
-	dma_iommu_fixed_ops = dma_direct_ops;
-	dma_iommu_fixed_ops.set_dma_mask = dma_set_mask_and_switch;
-
 	dma_iommu_ops.set_dma_mask = dma_set_mask_and_switch;
 	set_pci_dma_ops(&dma_iommu_ops);
 
@@ -1049,9 +1151,23 @@ static int iommu_fixed_disabled;
 
 static int __init setup_iommu_fixed(char *str)
 {
+	struct device_node *pciep;
+
 	if (strcmp(str, "off") == 0)
 		iommu_fixed_disabled = 1;
 
+	/* If we can find a pcie-endpoint in the device tree assume that
+	 * we're on a triblade or a CAB so by default the fixed mapping
+	 * should be set to be weakly ordered; but only if the boot
+	 * option WASN'T set for strong ordering
+	 */
+	pciep = of_find_node_by_type(NULL, "pcie-endpoint");
+
+	if (strcmp(str, "weak") == 0 || (pciep && strcmp(str, "strong") != 0))
+		iommu_fixed_is_weak = 1;
+
+	of_node_put(pciep);
+
 	return 1;
 }
 __setup("iommu_fixed=", setup_iommu_fixed);
diff --git a/arch/powerpc/platforms/cell/pervasive.c b/arch/powerpc/platforms/cell/pervasive.c
index 8a3631ce912b..efdacc829576 100644
--- a/arch/powerpc/platforms/cell/pervasive.c
+++ b/arch/powerpc/platforms/cell/pervasive.c
@@ -38,8 +38,6 @@
 
 #include "pervasive.h"
 
-static int sysreset_hack;
-
 static void cbe_power_save(void)
 {
 	unsigned long ctrl, thread_switch_control;
@@ -87,9 +85,6 @@ static void cbe_power_save(void)
 
 static int cbe_system_reset_exception(struct pt_regs *regs)
 {
-	int cpu;
-	struct cbe_pmd_regs __iomem *pmd;
-
 	switch (regs->msr & SRR1_WAKEMASK) {
 	case SRR1_WAKEEE:
 		do_IRQ(regs);
@@ -98,19 +93,7 @@ static int cbe_system_reset_exception(struct pt_regs *regs)
 		timer_interrupt(regs);
 		break;
 	case SRR1_WAKEMT:
-		/*
-		 * The BMC can inject user triggered system reset exceptions,
-		 * but cannot set the system reset reason in srr1,
-		 * so check an extra register here.
-		 */
-		if (sysreset_hack && (cpu = smp_processor_id()) == 0) {
-			pmd = cbe_get_cpu_pmd_regs(cpu);
-			if (in_be64(&pmd->ras_esc_0) & 0xffff) {
-				out_be64(&pmd->ras_esc_0, 0);
-				return 0;
-			}
-		}
-		break;
+		return cbe_sysreset_hack();
 #ifdef CONFIG_CBE_RAS
 	case SRR1_WAKESYSERR:
 		cbe_system_error_exception(regs);
@@ -134,8 +117,6 @@ void __init cbe_pervasive_init(void)
 	if (!cpu_has_feature(CPU_FTR_PAUSE_ZERO))
 		return;
 
-	sysreset_hack = machine_is_compatible("IBM,CBPLUS-1.0");
-
 	for_each_possible_cpu(cpu) {
 		struct cbe_pmd_regs __iomem *regs = cbe_get_cpu_pmd_regs(cpu);
 		if (!regs)
@@ -144,12 +125,6 @@ void __init cbe_pervasive_init(void)
 		 /* Enable Pause(0) control bit */
 		out_be64(&regs->pmcr, in_be64(&regs->pmcr) |
 					    CBE_PMD_PAUSE_ZERO_CONTROL);
-
-		/* Enable JTAG system-reset hack */
-		if (sysreset_hack)
-			out_be32(&regs->fir_mode_reg,
-				in_be32(&regs->fir_mode_reg) |
-				CBE_PMD_FIR_MODE_M8);
 	}
 
 	ppc_md.power_save = cbe_power_save;
diff --git a/arch/powerpc/platforms/cell/pervasive.h b/arch/powerpc/platforms/cell/pervasive.h
index 7b50947f8044..fd4d7b7092b4 100644
--- a/arch/powerpc/platforms/cell/pervasive.h
+++ b/arch/powerpc/platforms/cell/pervasive.h
@@ -30,4 +30,13 @@ extern void cbe_system_error_exception(struct pt_regs *regs);
 extern void cbe_maintenance_exception(struct pt_regs *regs);
 extern void cbe_thermal_exception(struct pt_regs *regs);
 
+#ifdef CONFIG_PPC_IBM_CELL_RESETBUTTON
+extern int cbe_sysreset_hack(void);
+#else
+static inline int cbe_sysreset_hack(void)
+{
+	return 1;
+}
+#endif /* CONFIG_PPC_IBM_CELL_RESETBUTTON */
+
 #endif
diff --git a/arch/powerpc/platforms/cell/ras.c b/arch/powerpc/platforms/cell/ras.c
index 655704ad03cf..2a14b052abcd 100644
--- a/arch/powerpc/platforms/cell/ras.c
+++ b/arch/powerpc/platforms/cell/ras.c
@@ -17,6 +17,7 @@
 #include <asm/reg.h>
 #include <asm/io.h>
 #include <asm/prom.h>
+#include <asm/kexec.h>
 #include <asm/machdep.h>
 #include <asm/rtas.h>
 #include <asm/cell-regs.h>
@@ -226,10 +227,61 @@ static int cbe_ptcal_notify_reboot(struct notifier_block *nb,
 	return cbe_ptcal_disable();
 }
 
+static void cbe_ptcal_crash_shutdown(void)
+{
+	cbe_ptcal_disable();
+}
+
 static struct notifier_block cbe_ptcal_reboot_notifier = {
 	.notifier_call = cbe_ptcal_notify_reboot
 };
 
+#ifdef CONFIG_PPC_IBM_CELL_RESETBUTTON
+static int sysreset_hack;
+
+static int __init cbe_sysreset_init(void)
+{
+	struct cbe_pmd_regs __iomem *regs;
+
+	sysreset_hack = machine_is_compatible("IBM,CBPLUS-1.0");
+	if (!sysreset_hack)
+		return 0;
+
+	regs = cbe_get_cpu_pmd_regs(0);
+	if (!regs)
+		return 0;
+
+	/* Enable JTAG system-reset hack */
+	out_be32(&regs->fir_mode_reg,
+		in_be32(&regs->fir_mode_reg) |
+		CBE_PMD_FIR_MODE_M8);
+
+	return 0;
+}
+device_initcall(cbe_sysreset_init);
+
+int cbe_sysreset_hack(void)
+{
+	struct cbe_pmd_regs __iomem *regs;
+
+	/*
+	 * The BMC can inject user triggered system reset exceptions,
+	 * but cannot set the system reset reason in srr1,
+	 * so check an extra register here.
+	 */
+	if (sysreset_hack && (smp_processor_id() == 0)) {
+		regs = cbe_get_cpu_pmd_regs(0);
+		if (!regs)
+			return 0;
+		if (in_be64(&regs->ras_esc_0) & 0x0000ffff) {
+			out_be64(&regs->ras_esc_0, 0);
+			return 0;
+		}
+	}
+	return 1;
+}
+#endif /* CONFIG_PPC_IBM_CELL_RESETBUTTON */
+
 int __init cbe_ptcal_init(void)
 {
 	int ret;
@@ -241,12 +293,20 @@ int __init cbe_ptcal_init(void)
 		return -ENODEV;
 
 	ret = register_reboot_notifier(&cbe_ptcal_reboot_notifier);
-	if (ret) {
-		printk(KERN_ERR "Can't disable PTCAL, so not enabling\n");
-		return ret;
-	}
+	if (ret)
+		goto out1;
+
+	ret = crash_shutdown_register(&cbe_ptcal_crash_shutdown);
+	if (ret)
+		goto out2;
 
 	return cbe_ptcal_enable();
+
+out2:
+	unregister_reboot_notifier(&cbe_ptcal_reboot_notifier);
+out1:
+	printk(KERN_ERR "Can't disable PTCAL, so not enabling\n");
+	return ret;
 }
 
 arch_initcall(cbe_ptcal_init);
diff --git a/arch/powerpc/platforms/cell/spider-pci.c b/arch/powerpc/platforms/cell/spider-pci.c
index 418b605ac35a..5122ec145271 100644
--- a/arch/powerpc/platforms/cell/spider-pci.c
+++ b/arch/powerpc/platforms/cell/spider-pci.c
@@ -111,7 +111,7 @@ static int __init spiderpci_pci_setup_chip(struct pci_controller *phb,
 
 	dummy_page_da = dma_map_single(phb->parent, dummy_page_va,
 				       PAGE_SIZE, DMA_FROM_DEVICE);
-	if (dma_mapping_error(dummy_page_da)) {
+	if (dma_mapping_error(phb->parent, dummy_page_da)) {
 		pr_err("SPIDER-IOWA:Map dummy page filed.\n");
 		kfree(dummy_page_va);
 		return -1;
diff --git a/arch/powerpc/platforms/cell/spider-pic.c b/arch/powerpc/platforms/cell/spider-pic.c
index 3f4b4aef756d..4e5655624ae8 100644
--- a/arch/powerpc/platforms/cell/spider-pic.c
+++ b/arch/powerpc/platforms/cell/spider-pic.c
@@ -300,7 +300,7 @@ static void __init spider_init_one(struct device_node *of_node, int chip,
 		panic("spider_pic: can't map registers !");
 
 	/* Allocate a host */
-	pic->host = irq_alloc_host(of_node_get(of_node), IRQ_HOST_MAP_LINEAR,
+	pic->host = irq_alloc_host(of_node, IRQ_HOST_MAP_LINEAR,
 				   SPIDER_SRC_COUNT, &spider_host_ops,
 				   SPIDER_IRQ_INVALID);
 	if (pic->host == NULL)
diff --git a/arch/powerpc/platforms/cell/spu_base.c b/arch/powerpc/platforms/cell/spu_base.c
index 78f905bc6a42..a5bdb89a17c3 100644
--- a/arch/powerpc/platforms/cell/spu_base.c
+++ b/arch/powerpc/platforms/cell/spu_base.c
@@ -703,7 +703,8 @@ static unsigned long long spu_acct_time(struct spu *spu,
 }
 
 
-static ssize_t spu_stat_show(struct sys_device *sysdev, char *buf)
+static ssize_t spu_stat_show(struct sys_device *sysdev,
+				struct sysdev_attribute *attr, char *buf)
 {
 	struct spu *spu = container_of(sysdev, struct spu, sysdev);
 
diff --git a/arch/powerpc/platforms/cell/spufs/context.c b/arch/powerpc/platforms/cell/spufs/context.c
index 177735f79317..6653ddbed048 100644
--- a/arch/powerpc/platforms/cell/spufs/context.c
+++ b/arch/powerpc/platforms/cell/spufs/context.c
@@ -130,17 +130,17 @@ void spu_unmap_mappings(struct spu_context *ctx)
 	if (ctx->local_store)
 		unmap_mapping_range(ctx->local_store, 0, LS_SIZE, 1);
 	if (ctx->mfc)
-		unmap_mapping_range(ctx->mfc, 0, 0x1000, 1);
+		unmap_mapping_range(ctx->mfc, 0, SPUFS_MFC_MAP_SIZE, 1);
 	if (ctx->cntl)
-		unmap_mapping_range(ctx->cntl, 0, 0x1000, 1);
+		unmap_mapping_range(ctx->cntl, 0, SPUFS_CNTL_MAP_SIZE, 1);
 	if (ctx->signal1)
-		unmap_mapping_range(ctx->signal1, 0, PAGE_SIZE, 1);
+		unmap_mapping_range(ctx->signal1, 0, SPUFS_SIGNAL_MAP_SIZE, 1);
 	if (ctx->signal2)
-		unmap_mapping_range(ctx->signal2, 0, PAGE_SIZE, 1);
+		unmap_mapping_range(ctx->signal2, 0, SPUFS_SIGNAL_MAP_SIZE, 1);
 	if (ctx->mss)
-		unmap_mapping_range(ctx->mss, 0, 0x1000, 1);
+		unmap_mapping_range(ctx->mss, 0, SPUFS_MSS_MAP_SIZE, 1);
 	if (ctx->psmap)
-		unmap_mapping_range(ctx->psmap, 0, 0x20000, 1);
+		unmap_mapping_range(ctx->psmap, 0, SPUFS_PS_MAP_SIZE, 1);
 	mutex_unlock(&ctx->mapping_lock);
 }
 
diff --git a/arch/powerpc/platforms/cell/spufs/file.c b/arch/powerpc/platforms/cell/spufs/file.c
index c81341ff75b5..010a51f59796 100644
--- a/arch/powerpc/platforms/cell/spufs/file.c
+++ b/arch/powerpc/platforms/cell/spufs/file.c
@@ -238,11 +238,13 @@ spufs_mem_write(struct file *file, const char __user *buffer,
 	return size;
 }
 
-static unsigned long spufs_mem_mmap_nopfn(struct vm_area_struct *vma,
-					  unsigned long address)
+static int
+spufs_mem_mmap_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 {
 	struct spu_context *ctx	= vma->vm_file->private_data;
-	unsigned long pfn, offset, addr0 = address;
+	unsigned long address = (unsigned long)vmf->virtual_address;
+	unsigned long pfn, offset;
+
 #ifdef CONFIG_SPU_FS_64K_LS
 	struct spu_state *csa = &ctx->csa;
 	int psize;
@@ -260,15 +262,15 @@ static unsigned long spufs_mem_mmap_nopfn(struct vm_area_struct *vma,
 	}
 #endif /* CONFIG_SPU_FS_64K_LS */
 
-	offset = (address - vma->vm_start) + (vma->vm_pgoff << PAGE_SHIFT);
+	offset = vmf->pgoff << PAGE_SHIFT;
 	if (offset >= LS_SIZE)
-		return NOPFN_SIGBUS;
+		return VM_FAULT_SIGBUS;
 
-	pr_debug("spufs_mem_mmap_nopfn address=0x%lx -> 0x%lx, offset=0x%lx\n",
-		 addr0, address, offset);
+	pr_debug("spufs_mem_mmap_fault address=0x%lx, offset=0x%lx\n",
+			address, offset);
 
 	if (spu_acquire(ctx))
-		return NOPFN_REFAULT;
+		return VM_FAULT_NOPAGE;
 
 	if (ctx->state == SPU_STATE_SAVED) {
 		vma->vm_page_prot = __pgprot(pgprot_val(vma->vm_page_prot)
@@ -283,12 +285,35 @@ static unsigned long spufs_mem_mmap_nopfn(struct vm_area_struct *vma,
 
 	spu_release(ctx);
 
-	return NOPFN_REFAULT;
+	return VM_FAULT_NOPAGE;
 }
 
+static int spufs_mem_mmap_access(struct vm_area_struct *vma,
+				unsigned long address,
+				void *buf, int len, int write)
+{
+	struct spu_context *ctx = vma->vm_file->private_data;
+	unsigned long offset = address - vma->vm_start;
+	char *local_store;
+
+	if (write && !(vma->vm_flags & VM_WRITE))
+		return -EACCES;
+	if (spu_acquire(ctx))
+		return -EINTR;
+	if ((offset + len) > vma->vm_end)
+		len = vma->vm_end - offset;
+	local_store = ctx->ops->get_ls(ctx);
+	if (write)
+		memcpy_toio(local_store + offset, buf, len);
+	else
+		memcpy_fromio(buf, local_store + offset, len);
+	spu_release(ctx);
+	return len;
+}
 
 static struct vm_operations_struct spufs_mem_mmap_vmops = {
-	.nopfn = spufs_mem_mmap_nopfn,
+	.fault = spufs_mem_mmap_fault,
+	.access = spufs_mem_mmap_access,
 };
 
 static int spufs_mem_mmap(struct file *file, struct vm_area_struct *vma)
@@ -351,20 +376,19 @@ static const struct file_operations spufs_mem_fops = {
 #endif
 };
 
-static unsigned long spufs_ps_nopfn(struct vm_area_struct *vma,
-				    unsigned long address,
+static int spufs_ps_fault(struct vm_area_struct *vma,
+				    struct vm_fault *vmf,
 				    unsigned long ps_offs,
 				    unsigned long ps_size)
 {
 	struct spu_context *ctx = vma->vm_file->private_data;
-	unsigned long area, offset = address - vma->vm_start;
+	unsigned long area, offset = vmf->pgoff << PAGE_SHIFT;
 	int ret = 0;
 
-	spu_context_nospu_trace(spufs_ps_nopfn__enter, ctx);
+	spu_context_nospu_trace(spufs_ps_fault__enter, ctx);
 
-	offset += vma->vm_pgoff << PAGE_SHIFT;
 	if (offset >= ps_size)
-		return NOPFN_SIGBUS;
+		return VM_FAULT_SIGBUS;
 
 	/*
 	 * Because we release the mmap_sem, the context may be destroyed while
@@ -378,7 +402,7 @@ static unsigned long spufs_ps_nopfn(struct vm_area_struct *vma,
 	 * pages to hand out to the user, but we don't want to wait
 	 * with the mmap_sem held.
 	 * It is possible to drop the mmap_sem here, but then we need
-	 * to return NOPFN_REFAULT because the mappings may have
+	 * to return VM_FAULT_NOPAGE because the mappings may have
 	 * hanged.
 	 */
 	if (spu_acquire(ctx))
@@ -386,14 +410,15 @@ static unsigned long spufs_ps_nopfn(struct vm_area_struct *vma,
 
 	if (ctx->state == SPU_STATE_SAVED) {
 		up_read(&current->mm->mmap_sem);
-		spu_context_nospu_trace(spufs_ps_nopfn__sleep, ctx);
+		spu_context_nospu_trace(spufs_ps_fault__sleep, ctx);
 		ret = spufs_wait(ctx->run_wq, ctx->state == SPU_STATE_RUNNABLE);
-		spu_context_trace(spufs_ps_nopfn__wake, ctx, ctx->spu);
+		spu_context_trace(spufs_ps_fault__wake, ctx, ctx->spu);
 		down_read(&current->mm->mmap_sem);
 	} else {
 		area = ctx->spu->problem_phys + ps_offs;
-		vm_insert_pfn(vma, address, (area + offset) >> PAGE_SHIFT);
-		spu_context_trace(spufs_ps_nopfn__insert, ctx, ctx->spu);
+		vm_insert_pfn(vma, (unsigned long)vmf->virtual_address,
+					(area + offset) >> PAGE_SHIFT);
+		spu_context_trace(spufs_ps_fault__insert, ctx, ctx->spu);
 	}
 
 	if (!ret)
@@ -401,18 +426,18 @@ static unsigned long spufs_ps_nopfn(struct vm_area_struct *vma,
 
 refault:
 	put_spu_context(ctx);
-	return NOPFN_REFAULT;
+	return VM_FAULT_NOPAGE;
 }
 
 #if SPUFS_MMAP_4K
-static unsigned long spufs_cntl_mmap_nopfn(struct vm_area_struct *vma,
-					   unsigned long address)
+static int spufs_cntl_mmap_fault(struct vm_area_struct *vma,
+					   struct vm_fault *vmf)
 {
-	return spufs_ps_nopfn(vma, address, 0x4000, 0x1000);
+	return spufs_ps_fault(vma, vmf, 0x4000, SPUFS_CNTL_MAP_SIZE);
 }
 
 static struct vm_operations_struct spufs_cntl_mmap_vmops = {
-	.nopfn = spufs_cntl_mmap_nopfn,
+	.fault = spufs_cntl_mmap_fault,
 };
 
 /*
@@ -1097,23 +1122,23 @@ static ssize_t spufs_signal1_write(struct file *file, const char __user *buf,
 	return 4;
 }
 
-static unsigned long spufs_signal1_mmap_nopfn(struct vm_area_struct *vma,
-					      unsigned long address)
+static int
+spufs_signal1_mmap_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 {
-#if PAGE_SIZE == 0x1000
-	return spufs_ps_nopfn(vma, address, 0x14000, 0x1000);
-#elif PAGE_SIZE == 0x10000
+#if SPUFS_SIGNAL_MAP_SIZE == 0x1000
+	return spufs_ps_fault(vma, vmf, 0x14000, SPUFS_SIGNAL_MAP_SIZE);
+#elif SPUFS_SIGNAL_MAP_SIZE == 0x10000
 	/* For 64k pages, both signal1 and signal2 can be used to mmap the whole
 	 * signal 1 and 2 area
 	 */
-	return spufs_ps_nopfn(vma, address, 0x10000, 0x10000);
+	return spufs_ps_fault(vma, vmf, 0x10000, SPUFS_SIGNAL_MAP_SIZE);
 #else
 #error unsupported page size
 #endif
 }
 
 static struct vm_operations_struct spufs_signal1_mmap_vmops = {
-	.nopfn = spufs_signal1_mmap_nopfn,
+	.fault = spufs_signal1_mmap_fault,
 };
 
 static int spufs_signal1_mmap(struct file *file, struct vm_area_struct *vma)
@@ -1234,23 +1259,23 @@ static ssize_t spufs_signal2_write(struct file *file, const char __user *buf,
 }
 
 #if SPUFS_MMAP_4K
-static unsigned long spufs_signal2_mmap_nopfn(struct vm_area_struct *vma,
-					      unsigned long address)
+static int
+spufs_signal2_mmap_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 {
-#if PAGE_SIZE == 0x1000
-	return spufs_ps_nopfn(vma, address, 0x1c000, 0x1000);
-#elif PAGE_SIZE == 0x10000
+#if SPUFS_SIGNAL_MAP_SIZE == 0x1000
+	return spufs_ps_fault(vma, vmf, 0x1c000, SPUFS_SIGNAL_MAP_SIZE);
+#elif SPUFS_SIGNAL_MAP_SIZE == 0x10000
 	/* For 64k pages, both signal1 and signal2 can be used to mmap the whole
 	 * signal 1 and 2 area
 	 */
-	return spufs_ps_nopfn(vma, address, 0x10000, 0x10000);
+	return spufs_ps_fault(vma, vmf, 0x10000, SPUFS_SIGNAL_MAP_SIZE);
 #else
 #error unsupported page size
 #endif
 }
 
 static struct vm_operations_struct spufs_signal2_mmap_vmops = {
-	.nopfn = spufs_signal2_mmap_nopfn,
+	.fault = spufs_signal2_mmap_fault,
 };
 
 static int spufs_signal2_mmap(struct file *file, struct vm_area_struct *vma)
@@ -1362,14 +1387,14 @@ DEFINE_SPUFS_ATTRIBUTE(spufs_signal2_type, spufs_signal2_type_get,
 		       spufs_signal2_type_set, "%llu\n", SPU_ATTR_ACQUIRE);
 
 #if SPUFS_MMAP_4K
-static unsigned long spufs_mss_mmap_nopfn(struct vm_area_struct *vma,
-					  unsigned long address)
+static int
+spufs_mss_mmap_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 {
-	return spufs_ps_nopfn(vma, address, 0x0000, 0x1000);
+	return spufs_ps_fault(vma, vmf, 0x0000, SPUFS_MSS_MAP_SIZE);
 }
 
 static struct vm_operations_struct spufs_mss_mmap_vmops = {
-	.nopfn = spufs_mss_mmap_nopfn,
+	.fault = spufs_mss_mmap_fault,
 };
 
 /*
@@ -1424,14 +1449,14 @@ static const struct file_operations spufs_mss_fops = {
 	.mmap	 = spufs_mss_mmap,
 };
 
-static unsigned long spufs_psmap_mmap_nopfn(struct vm_area_struct *vma,
-					    unsigned long address)
+static int
+spufs_psmap_mmap_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 {
-	return spufs_ps_nopfn(vma, address, 0x0000, 0x20000);
+	return spufs_ps_fault(vma, vmf, 0x0000, SPUFS_PS_MAP_SIZE);
 }
 
 static struct vm_operations_struct spufs_psmap_mmap_vmops = {
-	.nopfn = spufs_psmap_mmap_nopfn,
+	.fault = spufs_psmap_mmap_fault,
 };
 
 /*
@@ -1484,14 +1509,14 @@ static const struct file_operations spufs_psmap_fops = {
 
 
 #if SPUFS_MMAP_4K
-static unsigned long spufs_mfc_mmap_nopfn(struct vm_area_struct *vma,
-					  unsigned long address)
+static int
+spufs_mfc_mmap_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 {
-	return spufs_ps_nopfn(vma, address, 0x3000, 0x1000);
+	return spufs_ps_fault(vma, vmf, 0x3000, SPUFS_MFC_MAP_SIZE);
 }
 
 static struct vm_operations_struct spufs_mfc_mmap_vmops = {
-	.nopfn = spufs_mfc_mmap_nopfn,
+	.fault = spufs_mfc_mmap_fault,
 };
 
 /*
@@ -2553,22 +2578,74 @@ void spu_switch_log_notify(struct spu *spu, struct spu_context *ctx,
 	wake_up(&ctx->switch_log->wait);
 }
 
-struct tree_descr spufs_dir_contents[] = {
+static int spufs_show_ctx(struct seq_file *s, void *private)
+{
+	struct spu_context *ctx = s->private;
+	u64 mfc_control_RW;
+
+	mutex_lock(&ctx->state_mutex);
+	if (ctx->spu) {
+		struct spu *spu = ctx->spu;
+		struct spu_priv2 __iomem *priv2 = spu->priv2;
+
+		spin_lock_irq(&spu->register_lock);
+		mfc_control_RW = in_be64(&priv2->mfc_control_RW);
+		spin_unlock_irq(&spu->register_lock);
+	} else {
+		struct spu_state *csa = &ctx->csa;
+
+		mfc_control_RW = csa->priv2.mfc_control_RW;
+	}
+
+	seq_printf(s, "%c flgs(%lx) sflgs(%lx) pri(%d) ts(%d) spu(%02d)"
+		" %c %lx %lx %lx %lx %x %x\n",
+		ctx->state == SPU_STATE_SAVED ? 'S' : 'R',
+		ctx->flags,
+		ctx->sched_flags,
+		ctx->prio,
+		ctx->time_slice,
+		ctx->spu ? ctx->spu->number : -1,
+		!list_empty(&ctx->rq) ? 'q' : ' ',
+		ctx->csa.class_0_pending,
+		ctx->csa.class_0_dar,
+		ctx->csa.class_1_dsisr,
+		mfc_control_RW,
+		ctx->ops->runcntl_read(ctx),
+		ctx->ops->status_read(ctx));
+
+	mutex_unlock(&ctx->state_mutex);
+
+	return 0;
+}
+
+static int spufs_ctx_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, spufs_show_ctx, SPUFS_I(inode)->i_ctx);
+}
+
+static const struct file_operations spufs_ctx_fops = {
+	.open           = spufs_ctx_open,
+	.read           = seq_read,
+	.llseek         = seq_lseek,
+	.release        = single_release,
+};
+
+struct spufs_tree_descr spufs_dir_contents[] = {
 	{ "capabilities", &spufs_caps_fops, 0444, },
-	{ "mem",  &spufs_mem_fops,  0666, },
-	{ "regs", &spufs_regs_fops,  0666, },
+	{ "mem",  &spufs_mem_fops,  0666, LS_SIZE, },
+	{ "regs", &spufs_regs_fops,  0666, sizeof(struct spu_reg128[128]), },
 	{ "mbox", &spufs_mbox_fops, 0444, },
 	{ "ibox", &spufs_ibox_fops, 0444, },
 	{ "wbox", &spufs_wbox_fops, 0222, },
-	{ "mbox_stat", &spufs_mbox_stat_fops, 0444, },
-	{ "ibox_stat", &spufs_ibox_stat_fops, 0444, },
-	{ "wbox_stat", &spufs_wbox_stat_fops, 0444, },
+	{ "mbox_stat", &spufs_mbox_stat_fops, 0444, sizeof(u32), },
+	{ "ibox_stat", &spufs_ibox_stat_fops, 0444, sizeof(u32), },
+	{ "wbox_stat", &spufs_wbox_stat_fops, 0444, sizeof(u32), },
 	{ "signal1", &spufs_signal1_fops, 0666, },
 	{ "signal2", &spufs_signal2_fops, 0666, },
 	{ "signal1_type", &spufs_signal1_type, 0666, },
 	{ "signal2_type", &spufs_signal2_type, 0666, },
 	{ "cntl", &spufs_cntl_fops,  0666, },
-	{ "fpcr", &spufs_fpcr_fops, 0666, },
+	{ "fpcr", &spufs_fpcr_fops, 0666, sizeof(struct spu_reg128), },
 	{ "lslr", &spufs_lslr_ops, 0444, },
 	{ "mfc", &spufs_mfc_fops, 0666, },
 	{ "mss", &spufs_mss_fops, 0666, },
@@ -2578,29 +2655,31 @@ struct tree_descr spufs_dir_contents[] = {
 	{ "decr_status", &spufs_decr_status_ops, 0666, },
 	{ "event_mask", &spufs_event_mask_ops, 0666, },
 	{ "event_status", &spufs_event_status_ops, 0444, },
-	{ "psmap", &spufs_psmap_fops, 0666, },
+	{ "psmap", &spufs_psmap_fops, 0666, SPUFS_PS_MAP_SIZE, },
 	{ "phys-id", &spufs_id_ops, 0666, },
 	{ "object-id", &spufs_object_id_ops, 0666, },
-	{ "mbox_info", &spufs_mbox_info_fops, 0444, },
-	{ "ibox_info", &spufs_ibox_info_fops, 0444, },
-	{ "wbox_info", &spufs_wbox_info_fops, 0444, },
-	{ "dma_info", &spufs_dma_info_fops, 0444, },
-	{ "proxydma_info", &spufs_proxydma_info_fops, 0444, },
+	{ "mbox_info", &spufs_mbox_info_fops, 0444, sizeof(u32), },
+	{ "ibox_info", &spufs_ibox_info_fops, 0444, sizeof(u32), },
+	{ "wbox_info", &spufs_wbox_info_fops, 0444, sizeof(u32), },
+	{ "dma_info", &spufs_dma_info_fops, 0444,
+		sizeof(struct spu_dma_info), },
+	{ "proxydma_info", &spufs_proxydma_info_fops, 0444,
+		sizeof(struct spu_proxydma_info)},
 	{ "tid", &spufs_tid_fops, 0444, },
 	{ "stat", &spufs_stat_fops, 0444, },
 	{ "switch_log", &spufs_switch_log_fops, 0444 },
 	{},
 };
 
-struct tree_descr spufs_dir_nosched_contents[] = {
+struct spufs_tree_descr spufs_dir_nosched_contents[] = {
 	{ "capabilities", &spufs_caps_fops, 0444, },
-	{ "mem",  &spufs_mem_fops,  0666, },
+	{ "mem",  &spufs_mem_fops,  0666, LS_SIZE, },
 	{ "mbox", &spufs_mbox_fops, 0444, },
 	{ "ibox", &spufs_ibox_fops, 0444, },
 	{ "wbox", &spufs_wbox_fops, 0222, },
-	{ "mbox_stat", &spufs_mbox_stat_fops, 0444, },
-	{ "ibox_stat", &spufs_ibox_stat_fops, 0444, },
-	{ "wbox_stat", &spufs_wbox_stat_fops, 0444, },
+	{ "mbox_stat", &spufs_mbox_stat_fops, 0444, sizeof(u32), },
+	{ "ibox_stat", &spufs_ibox_stat_fops, 0444, sizeof(u32), },
+	{ "wbox_stat", &spufs_wbox_stat_fops, 0444, sizeof(u32), },
 	{ "signal1", &spufs_signal1_nosched_fops, 0222, },
 	{ "signal2", &spufs_signal2_nosched_fops, 0222, },
 	{ "signal1_type", &spufs_signal1_type, 0666, },
@@ -2609,7 +2688,7 @@ struct tree_descr spufs_dir_nosched_contents[] = {
 	{ "mfc", &spufs_mfc_fops, 0666, },
 	{ "cntl", &spufs_cntl_fops,  0666, },
 	{ "npc", &spufs_npc_ops, 0666, },
-	{ "psmap", &spufs_psmap_fops, 0666, },
+	{ "psmap", &spufs_psmap_fops, 0666, SPUFS_PS_MAP_SIZE, },
 	{ "phys-id", &spufs_id_ops, 0666, },
 	{ "object-id", &spufs_object_id_ops, 0666, },
 	{ "tid", &spufs_tid_fops, 0444, },
@@ -2617,6 +2696,11 @@ struct tree_descr spufs_dir_nosched_contents[] = {
 	{},
 };
 
+struct spufs_tree_descr spufs_dir_debug_contents[] = {
+	{ ".ctx", &spufs_ctx_fops, 0444, },
+	{},
+};
+
 struct spufs_coredump_reader spufs_coredump_read[] = {
 	{ "regs", __spufs_regs_read, NULL, sizeof(struct spu_reg128[128])},
 	{ "fpcr", __spufs_fpcr_read, NULL, sizeof(struct spu_reg128) },
diff --git a/arch/powerpc/platforms/cell/spufs/inode.c b/arch/powerpc/platforms/cell/spufs/inode.c
index f407b2471855..2c8b8091250f 100644
--- a/arch/powerpc/platforms/cell/spufs/inode.c
+++ b/arch/powerpc/platforms/cell/spufs/inode.c
@@ -42,10 +42,19 @@
 
 #include "spufs.h"
 
+struct spufs_sb_info {
+	int debug;
+};
+
 static struct kmem_cache *spufs_inode_cache;
 char *isolated_loader;
 static int isolated_loader_size;
 
+static struct spufs_sb_info *spufs_get_sb_info(struct super_block *sb)
+{
+	return sb->s_fs_info;
+}
+
 static struct inode *
 spufs_alloc_inode(struct super_block *sb)
 {
@@ -69,7 +78,7 @@ spufs_destroy_inode(struct inode *inode)
 }
 
 static void
-spufs_init_once(struct kmem_cache *cachep, void *p)
+spufs_init_once(void *p)
 {
 	struct spufs_inode_info *ei = p;
 
@@ -109,7 +118,7 @@ spufs_setattr(struct dentry *dentry, struct iattr *attr)
 static int
 spufs_new_file(struct super_block *sb, struct dentry *dentry,
 		const struct file_operations *fops, int mode,
-		struct spu_context *ctx)
+		size_t size, struct spu_context *ctx)
 {
 	static struct inode_operations spufs_file_iops = {
 		.setattr = spufs_setattr,
@@ -125,6 +134,7 @@ spufs_new_file(struct super_block *sb, struct dentry *dentry,
 	ret = 0;
 	inode->i_op = &spufs_file_iops;
 	inode->i_fop = fops;
+	inode->i_size = size;
 	inode->i_private = SPUFS_I(inode)->i_ctx = get_spu_context(ctx);
 	d_add(dentry, inode);
 out:
@@ -177,7 +187,7 @@ static int spufs_rmdir(struct inode *parent, struct dentry *dir)
 	return simple_rmdir(parent, dir);
 }
 
-static int spufs_fill_dir(struct dentry *dir, struct tree_descr *files,
+static int spufs_fill_dir(struct dentry *dir, struct spufs_tree_descr *files,
 			  int mode, struct spu_context *ctx)
 {
 	struct dentry *dentry, *tmp;
@@ -189,7 +199,7 @@ static int spufs_fill_dir(struct dentry *dir, struct tree_descr *files,
 		if (!dentry)
 			goto out;
 		ret = spufs_new_file(dir->d_sb, dentry, files->ops,
-					files->mode & mode, ctx);
+					files->mode & mode, files->size, ctx);
 		if (ret)
 			goto out;
 		files++;
@@ -279,6 +289,13 @@ spufs_mkdir(struct inode *dir, struct dentry *dentry, unsigned int flags,
 	if (ret)
 		goto out_free_ctx;
 
+	if (spufs_get_sb_info(dir->i_sb)->debug)
+		ret = spufs_fill_dir(dentry, spufs_dir_debug_contents,
+				mode, ctx);
+
+	if (ret)
+		goto out_free_ctx;
+
 	d_instantiate(dentry, inode);
 	dget(dentry);
 	dir->i_nlink++;
@@ -639,18 +656,19 @@ out:
 
 /* File system initialization */
 enum {
-	Opt_uid, Opt_gid, Opt_mode, Opt_err,
+	Opt_uid, Opt_gid, Opt_mode, Opt_debug, Opt_err,
 };
 
-static match_table_t spufs_tokens = {
-	{ Opt_uid,  "uid=%d" },
-	{ Opt_gid,  "gid=%d" },
-	{ Opt_mode, "mode=%o" },
-	{ Opt_err,   NULL  },
+static const match_table_t spufs_tokens = {
+	{ Opt_uid,   "uid=%d" },
+	{ Opt_gid,   "gid=%d" },
+	{ Opt_mode,  "mode=%o" },
+	{ Opt_debug, "debug" },
+	{ Opt_err,    NULL  },
 };
 
 static int
-spufs_parse_options(char *options, struct inode *root)
+spufs_parse_options(struct super_block *sb, char *options, struct inode *root)
 {
 	char *p;
 	substring_t args[MAX_OPT_ARGS];
@@ -678,6 +696,9 @@ spufs_parse_options(char *options, struct inode *root)
 				return 0;
 			root->i_mode = option | S_IFDIR;
 			break;
+		case Opt_debug:
+			spufs_get_sb_info(sb)->debug = 1;
+			break;
 		default:
 			return 0;
 		}
@@ -736,7 +757,7 @@ spufs_create_root(struct super_block *sb, void *data)
 	SPUFS_I(inode)->i_ctx = NULL;
 
 	ret = -EINVAL;
-	if (!spufs_parse_options(data, inode))
+	if (!spufs_parse_options(sb, data, inode))
 		goto out_iput;
 
 	ret = -ENOMEM;
@@ -754,6 +775,7 @@ out:
 static int
 spufs_fill_super(struct super_block *sb, void *data, int silent)
 {
+	struct spufs_sb_info *info;
 	static struct super_operations s_ops = {
 		.alloc_inode = spufs_alloc_inode,
 		.destroy_inode = spufs_destroy_inode,
@@ -765,11 +787,16 @@ spufs_fill_super(struct super_block *sb, void *data, int silent)
 
 	save_mount_options(sb, data);
 
+	info = kzalloc(sizeof(*info), GFP_KERNEL);
+	if (!info)
+		return -ENOMEM;
+
 	sb->s_maxbytes = MAX_LFS_FILESIZE;
 	sb->s_blocksize = PAGE_CACHE_SIZE;
 	sb->s_blocksize_bits = PAGE_CACHE_SHIFT;
 	sb->s_magic = SPUFS_MAGIC;
 	sb->s_op = &s_ops;
+	sb->s_fs_info = info;
 
 	return spufs_create_root(sb, data);
 }
diff --git a/arch/powerpc/platforms/cell/spufs/run.c b/arch/powerpc/platforms/cell/spufs/run.c
index f7edba6cb795..c9bb7cfd3dca 100644
--- a/arch/powerpc/platforms/cell/spufs/run.c
+++ b/arch/powerpc/platforms/cell/spufs/run.c
@@ -206,11 +206,6 @@ static int spu_run_init(struct spu_context *ctx, u32 *npc)
 			(SPU_RUNCNTL_RUNNABLE | SPU_RUNCNTL_ISOLATE);
 		if (runcntl == 0)
 			runcntl = SPU_RUNCNTL_RUNNABLE;
-	}
-
-	if (ctx->flags & SPU_CREATE_NOSCHED) {
-		spuctx_switch_state(ctx, SPU_UTIL_USER);
-		ctx->ops->runcntl_write(ctx, runcntl);
 	} else {
 		unsigned long privcntl;
 
@@ -219,9 +214,15 @@ static int spu_run_init(struct spu_context *ctx, u32 *npc)
 		else
 			privcntl = SPU_PRIVCNTL_MODE_NORMAL;
 
-		ctx->ops->npc_write(ctx, *npc);
 		ctx->ops->privcntl_write(ctx, privcntl);
-		ctx->ops->runcntl_write(ctx, runcntl);
+		ctx->ops->npc_write(ctx, *npc);
+	}
+
+	ctx->ops->runcntl_write(ctx, runcntl);
+
+	if (ctx->flags & SPU_CREATE_NOSCHED) {
+		spuctx_switch_state(ctx, SPU_UTIL_USER);
+	} else {
 
 		if (ctx->state == SPU_STATE_SAVED) {
 			ret = spu_activate(ctx, 0);
diff --git a/arch/powerpc/platforms/cell/spufs/sched.c b/arch/powerpc/platforms/cell/spufs/sched.c
index e929e70a84e3..67595bc380dc 100644
--- a/arch/powerpc/platforms/cell/spufs/sched.c
+++ b/arch/powerpc/platforms/cell/spufs/sched.c
@@ -312,11 +312,28 @@ static struct spu *aff_ref_location(struct spu_context *ctx, int mem_aff,
 	 */
 	node = cpu_to_node(raw_smp_processor_id());
 	for (n = 0; n < MAX_NUMNODES; n++, node++) {
+		int available_spus;
+
 		node = (node < MAX_NUMNODES) ? node : 0;
 		if (!node_allowed(ctx, node))
 			continue;
+
+		available_spus = 0;
 		mutex_lock(&cbe_spu_info[node].list_mutex);
 		list_for_each_entry(spu, &cbe_spu_info[node].spus, cbe_list) {
+			if (spu->ctx && spu->ctx->gang
+					&& spu->ctx->aff_offset == 0)
+				available_spus -=
+					(spu->ctx->gang->contexts - 1);
+			else
+				available_spus++;
+		}
+		if (available_spus < ctx->gang->contexts) {
+			mutex_unlock(&cbe_spu_info[node].list_mutex);
+			continue;
+		}
+
+		list_for_each_entry(spu, &cbe_spu_info[node].spus, cbe_list) {
 			if ((!mem_aff || spu->has_mem_affinity) &&
 							sched_spu(spu)) {
 				mutex_unlock(&cbe_spu_info[node].list_mutex);
@@ -389,6 +406,9 @@ static int has_affinity(struct spu_context *ctx)
 	if (list_empty(&ctx->aff_list))
 		return 0;
 
+	if (atomic_read(&ctx->gang->aff_sched_count) == 0)
+		ctx->gang->aff_ref_spu = NULL;
+
 	if (!gang->aff_ref_spu) {
 		if (!(gang->aff_flags & AFF_MERGED))
 			aff_merge_remaining_ctxs(gang);
@@ -416,14 +436,8 @@ static void spu_unbind_context(struct spu *spu, struct spu_context *ctx)
  	if (spu->ctx->flags & SPU_CREATE_NOSCHED)
 		atomic_dec(&cbe_spu_info[spu->node].reserved_spus);
 
-	if (ctx->gang){
-		mutex_lock(&ctx->gang->aff_mutex);
-		if (has_affinity(ctx)) {
-			if (atomic_dec_and_test(&ctx->gang->aff_sched_count))
-				ctx->gang->aff_ref_spu = NULL;
-		}
-		mutex_unlock(&ctx->gang->aff_mutex);
-	}
+	if (ctx->gang)
+		atomic_dec_if_positive(&ctx->gang->aff_sched_count);
 
 	spu_switch_notify(spu, NULL);
 	spu_unmap_mappings(ctx);
@@ -562,10 +576,7 @@ static struct spu *spu_get_idle(struct spu_context *ctx)
 				goto found;
 			mutex_unlock(&cbe_spu_info[node].list_mutex);
 
-			mutex_lock(&ctx->gang->aff_mutex);
-			if (atomic_dec_and_test(&ctx->gang->aff_sched_count))
-				ctx->gang->aff_ref_spu = NULL;
-			mutex_unlock(&ctx->gang->aff_mutex);
+			atomic_dec(&ctx->gang->aff_sched_count);
 			goto not_found;
 		}
 		mutex_unlock(&ctx->gang->aff_mutex);
@@ -630,9 +641,12 @@ static struct spu *find_victim(struct spu_context *ctx)
 
 			if (tmp && tmp->prio > ctx->prio &&
 			    !(tmp->flags & SPU_CREATE_NOSCHED) &&
-			    (!victim || tmp->prio > victim->prio))
+			    (!victim || tmp->prio > victim->prio)) {
 				victim = spu->ctx;
+			}
 		}
+		if (victim)
+			get_spu_context(victim);
 		mutex_unlock(&cbe_spu_info[node].list_mutex);
 
 		if (victim) {
@@ -647,6 +661,7 @@ static struct spu *find_victim(struct spu_context *ctx)
 			 * look at another context or give up after X retries.
 			 */
 			if (!mutex_trylock(&victim->state_mutex)) {
+				put_spu_context(victim);
 				victim = NULL;
 				goto restart;
 			}
@@ -659,6 +674,7 @@ static struct spu *find_victim(struct spu_context *ctx)
 				 * restart the search.
 				 */
 				mutex_unlock(&victim->state_mutex);
+				put_spu_context(victim);
 				victim = NULL;
 				goto restart;
 			}
@@ -676,6 +692,7 @@ static struct spu *find_victim(struct spu_context *ctx)
 				spu_add_to_rq(victim);
 
 			mutex_unlock(&victim->state_mutex);
+			put_spu_context(victim);
 
 			return spu;
 		}
@@ -711,17 +728,33 @@ static void spu_schedule(struct spu *spu, struct spu_context *ctx)
 	/* not a candidate for interruptible because it's called either
 	   from the scheduler thread or from spu_deactivate */
 	mutex_lock(&ctx->state_mutex);
-	__spu_schedule(spu, ctx);
+	if (ctx->state == SPU_STATE_SAVED)
+		__spu_schedule(spu, ctx);
 	spu_release(ctx);
 }
 
-static void spu_unschedule(struct spu *spu, struct spu_context *ctx)
+/**
+ * spu_unschedule - remove a context from a spu, and possibly release it.
+ * @spu:	The SPU to unschedule from
+ * @ctx:	The context currently scheduled on the SPU
+ * @free_spu	Whether to free the SPU for other contexts
+ *
+ * Unbinds the context @ctx from the SPU @spu. If @free_spu is non-zero, the
+ * SPU is made available for other contexts (ie, may be returned by
+ * spu_get_idle). If this is zero, the caller is expected to schedule another
+ * context to this spu.
+ *
+ * Should be called with ctx->state_mutex held.
+ */
+static void spu_unschedule(struct spu *spu, struct spu_context *ctx,
+		int free_spu)
 {
 	int node = spu->node;
 
 	mutex_lock(&cbe_spu_info[node].list_mutex);
 	cbe_spu_info[node].nr_active--;
-	spu->alloc_state = SPU_FREE;
+	if (free_spu)
+		spu->alloc_state = SPU_FREE;
 	spu_unbind_context(spu, ctx);
 	ctx->stats.invol_ctx_switch++;
 	spu->stats.invol_ctx_switch++;
@@ -821,7 +854,7 @@ static int __spu_deactivate(struct spu_context *ctx, int force, int max_prio)
 	if (spu) {
 		new = grab_runnable_context(max_prio, spu->node);
 		if (new || force) {
-			spu_unschedule(spu, ctx);
+			spu_unschedule(spu, ctx, new == NULL);
 			if (new) {
 				if (new->flags & SPU_CREATE_NOSCHED)
 					wake_up(&new->stop_wq);
@@ -894,12 +927,13 @@ static noinline void spusched_tick(struct spu_context *ctx)
 
 	new = grab_runnable_context(ctx->prio + 1, spu->node);
 	if (new) {
-		spu_unschedule(spu, ctx);
+		spu_unschedule(spu, ctx, 0);
 		if (test_bit(SPU_SCHED_SPU_RUN, &ctx->sched_flags))
 			spu_add_to_rq(ctx);
 	} else {
 		spu_context_nospu_trace(spusched_tick__newslice, ctx);
-		ctx->time_slice++;
+		if (!ctx->time_slice)
+			ctx->time_slice++;
 	}
 out:
 	spu_release(ctx);
@@ -973,9 +1007,11 @@ static int spusched_thread(void *unused)
 				struct spu_context *ctx = spu->ctx;
 
 				if (ctx) {
+					get_spu_context(ctx);
 					mutex_unlock(mtx);
 					spusched_tick(ctx);
 					mutex_lock(mtx);
+					put_spu_context(ctx);
 				}
 			}
 			mutex_unlock(mtx);
@@ -993,6 +1029,7 @@ void spuctx_switch_state(struct spu_context *ctx,
 	struct timespec ts;
 	struct spu *spu;
 	enum spu_utilization_state old_state;
+	int node;
 
 	ktime_get_ts(&ts);
 	curtime = timespec_to_ns(&ts);
@@ -1014,6 +1051,11 @@ void spuctx_switch_state(struct spu_context *ctx,
 		spu->stats.times[old_state] += delta;
 		spu->stats.util_state = new_state;
 		spu->stats.tstamp = curtime;
+		node = spu->node;
+		if (old_state == SPU_UTIL_USER)
+			atomic_dec(&cbe_spu_info[node].busy_spus);
+		if (new_state == SPU_UTIL_USER)
+			atomic_inc(&cbe_spu_info[node].busy_spus);
 	}
 }
 
diff --git a/arch/powerpc/platforms/cell/spufs/spufs.h b/arch/powerpc/platforms/cell/spufs/spufs.h
index 454c277c1457..8ae8ef9dfc22 100644
--- a/arch/powerpc/platforms/cell/spufs/spufs.h
+++ b/arch/powerpc/platforms/cell/spufs/spufs.h
@@ -32,6 +32,13 @@
 #include <asm/spu_csa.h>
 #include <asm/spu_info.h>
 
+#define SPUFS_PS_MAP_SIZE	0x20000
+#define SPUFS_MFC_MAP_SIZE	0x1000
+#define SPUFS_CNTL_MAP_SIZE	0x1000
+#define SPUFS_CNTL_MAP_SIZE	0x1000
+#define SPUFS_SIGNAL_MAP_SIZE	PAGE_SIZE
+#define SPUFS_MSS_MAP_SIZE	0x1000
+
 /* The magic number for our file system */
 enum {
 	SPUFS_MAGIC = 0x23c9b64e,
@@ -228,8 +235,16 @@ struct spufs_inode_info {
 #define SPUFS_I(inode) \
 	container_of(inode, struct spufs_inode_info, vfs_inode)
 
-extern struct tree_descr spufs_dir_contents[];
-extern struct tree_descr spufs_dir_nosched_contents[];
+struct spufs_tree_descr {
+	const char *name;
+	const struct file_operations *ops;
+	int mode;
+	size_t size;
+};
+
+extern struct spufs_tree_descr spufs_dir_contents[];
+extern struct spufs_tree_descr spufs_dir_nosched_contents[];
+extern struct spufs_tree_descr spufs_dir_debug_contents[];
 
 /* system call implementation */
 extern struct spufs_calls spufs_calls;
diff --git a/arch/powerpc/platforms/cell/spufs/sputrace.c b/arch/powerpc/platforms/cell/spufs/sputrace.c
index 53202422ba72..92d20e993ede 100644
--- a/arch/powerpc/platforms/cell/spufs/sputrace.c
+++ b/arch/powerpc/platforms/cell/spufs/sputrace.c
@@ -182,10 +182,10 @@ struct spu_probe spu_probes[] = {
 	{ "spu_yield__enter", "ctx %p", spu_context_nospu_event },
 	{ "spu_deactivate__enter", "ctx %p", spu_context_nospu_event },
 	{ "__spu_deactivate__unload", "ctx %p spu %p", spu_context_event },
-	{ "spufs_ps_nopfn__enter", "ctx %p", spu_context_nospu_event },
-	{ "spufs_ps_nopfn__sleep", "ctx %p", spu_context_nospu_event },
-	{ "spufs_ps_nopfn__wake", "ctx %p spu %p", spu_context_event },
-	{ "spufs_ps_nopfn__insert", "ctx %p spu %p", spu_context_event },
+	{ "spufs_ps_fault__enter", "ctx %p", spu_context_nospu_event },
+	{ "spufs_ps_fault__sleep", "ctx %p", spu_context_nospu_event },
+	{ "spufs_ps_fault__wake", "ctx %p spu %p", spu_context_event },
+	{ "spufs_ps_fault__insert", "ctx %p spu %p", spu_context_event },
 	{ "spu_acquire_saved__enter", "ctx %p", spu_context_nospu_event },
 	{ "destroy_spu_context__enter", "ctx %p", spu_context_nospu_event },
 	{ "spufs_stop_callback__enter", "ctx %p spu %p", spu_context_event },
@@ -196,8 +196,7 @@ static int __init sputrace_init(void)
 	struct proc_dir_entry *entry;
 	int i, error = -ENOMEM;
 
-	sputrace_log = kcalloc(sizeof(struct sputrace),
-				bufsize, GFP_KERNEL);
+	sputrace_log = kcalloc(bufsize, sizeof(struct sputrace), GFP_KERNEL);
 	if (!sputrace_log)
 		goto out;