Merge ../linus

52 files changed, 1880 insertions, 476 deletions

diff --git a/arch/powerpc/platforms/83xx/mpc834x_sys.c b/arch/powerpc/platforms/83xx/mpc834x_sys.c
index 7c18b4cd5db..7e789d2420b 100644
--- a/arch/powerpc/platforms/83xx/mpc834x_sys.c
+++ b/arch/powerpc/platforms/83xx/mpc834x_sys.c
@@ -158,25 +158,25 @@ static int __init mpc834x_rtc_hookup(void)
 late_initcall(mpc834x_rtc_hookup);
 #endif
 
-void __init platform_init(void)
+/*
+ * Called very early, MMU is off, device-tree isn't unflattened
+ */
+static int __init mpc834x_sys_probe(void)
 {
-	/* setup the PowerPC module struct */
-	ppc_md.setup_arch = mpc834x_sys_setup_arch;
-
-	ppc_md.init_IRQ = mpc834x_sys_init_IRQ;
-	ppc_md.get_irq = ipic_get_irq;
-
-	ppc_md.restart = mpc83xx_restart;
-
-	ppc_md.time_init = mpc83xx_time_init;
-	ppc_md.set_rtc_time = NULL;
-	ppc_md.get_rtc_time = NULL;
-	ppc_md.calibrate_decr = generic_calibrate_decr;
-
-	ppc_md.progress = udbg_progress;
-
-	if (ppc_md.progress)
-		ppc_md.progress("mpc834x_sys_init(): exit", 0);
-
-	return;
+	/* We always match for now, eventually we should look at the flat
+	   dev tree to ensure this is the board we are suppose to run on
+	*/
+	return 1;
 }
+
+define_machine(mpc834x_sys) {
+	.name			= "MPC834x SYS",
+	.probe			= mpc834x_sys_probe,
+	.setup_arch		= mpc834x_sys_setup_arch,
+	.init_IRQ		= mpc834x_sys_init_IRQ,
+	.get_irq		= ipic_get_irq,
+	.restart		= mpc83xx_restart,
+	.time_init		= mpc83xx_time_init,
+	.calibrate_decr		= generic_calibrate_decr,
+	.progress		= udbg_progress,
+};
diff --git a/arch/powerpc/platforms/85xx/Kconfig b/arch/powerpc/platforms/85xx/Kconfig
index d3d0ff745e8..06e371282f5 100644
--- a/arch/powerpc/platforms/85xx/Kconfig
+++ b/arch/powerpc/platforms/85xx/Kconfig
@@ -7,6 +7,7 @@ choice
 
 config MPC8540_ADS
 	bool "Freescale MPC8540 ADS"
+	select DEFAULT_UIMAGE
 	help
 	  This option enables support for the MPC 8540 ADS board
 
diff --git a/arch/powerpc/platforms/85xx/mpc85xx_ads.c b/arch/powerpc/platforms/85xx/mpc85xx_ads.c
index b7821dbae00..5eeff370f5f 100644
--- a/arch/powerpc/platforms/85xx/mpc85xx_ads.c
+++ b/arch/powerpc/platforms/85xx/mpc85xx_ads.c
@@ -220,25 +220,25 @@ void mpc85xx_ads_show_cpuinfo(struct seq_file *m)
 	seq_printf(m, "Memory\t\t: %d MB\n", memsize / (1024 * 1024));
 }
 
-void __init platform_init(void)
+/*
+ * Called very early, device-tree isn't unflattened
+ */
+static int __init mpc85xx_ads_probe(void)
 {
-	ppc_md.setup_arch = mpc85xx_ads_setup_arch;
-	ppc_md.show_cpuinfo = mpc85xx_ads_show_cpuinfo;
-
-	ppc_md.init_IRQ = mpc85xx_ads_pic_init;
-	ppc_md.get_irq = mpic_get_irq;
-
-	ppc_md.restart = mpc85xx_restart;
-	ppc_md.power_off = NULL;
-	ppc_md.halt = NULL;
-
-	ppc_md.time_init = NULL;
-	ppc_md.set_rtc_time = NULL;
-	ppc_md.get_rtc_time = NULL;
-	ppc_md.calibrate_decr = generic_calibrate_decr;
-
-	ppc_md.progress = udbg_progress;
-
-	if (ppc_md.progress)
-		ppc_md.progress("mpc85xx_ads platform_init(): exit", 0);
+	/* We always match for now, eventually we should look at the flat
+	   dev tree to ensure this is the board we are suppose to run on
+	*/
+	return 1;
 }
+
+define_machine(mpc85xx_ads) {
+	.name			= "MPC85xx ADS",
+	.probe			= mpc85xx_ads_probe,
+	.setup_arch		= mpc85xx_ads_setup_arch,
+	.init_IRQ		= mpc85xx_ads_pic_init,
+	.show_cpuinfo		= mpc85xx_ads_show_cpuinfo,
+	.get_irq		= mpic_get_irq,
+	.restart		= mpc85xx_restart,
+	.calibrate_decr		= generic_calibrate_decr,
+	.progress		= udbg_progress,
+};
diff --git a/arch/powerpc/platforms/cell/Kconfig b/arch/powerpc/platforms/cell/Kconfig
index 3157071e241..c2a3db8edb0 100644
--- a/arch/powerpc/platforms/cell/Kconfig
+++ b/arch/powerpc/platforms/cell/Kconfig
@@ -10,4 +10,9 @@ config SPU_FS
 	  Units on machines implementing the Broadband Processor
 	  Architecture.
 
+config SPUFS_MMAP
+	bool
+	depends on SPU_FS && SPARSEMEM && !PPC_64K_PAGES
+	default y
+
 endmenu
diff --git a/arch/powerpc/platforms/cell/Makefile b/arch/powerpc/platforms/cell/Makefile
index 3b998a393e3..e570bad0639 100644
--- a/arch/powerpc/platforms/cell/Makefile
+++ b/arch/powerpc/platforms/cell/Makefile
@@ -6,5 +6,11 @@ obj-$(CONFIG_SPU_FS)	+= spu-base.o spufs/
 
 spu-base-y		+= spu_base.o spu_priv1.o
 
-builtin-spufs-$(CONFIG_SPU_FS)	+= spu_syscalls.o
-obj-y			+= $(builtin-spufs-m)
+# needed only when building loadable spufs.ko
+spufs-modular-$(CONFIG_SPU_FS) += spu_syscalls.o
+obj-y			+= $(spufs-modular-m)
+
+# always needed in kernel
+spufs-builtin-$(CONFIG_SPU_FS) += spu_callbacks.o
+obj-y			+= $(spufs-builtin-y) $(spufs-builtin-m)
+
diff --git a/arch/powerpc/platforms/cell/interrupt.c b/arch/powerpc/platforms/cell/interrupt.c
index 63aa52acf44..978be1c30c1 100644
--- a/arch/powerpc/platforms/cell/interrupt.c
+++ b/arch/powerpc/platforms/cell/interrupt.c
@@ -63,7 +63,24 @@ static DEFINE_PER_CPU(struct iic, iic);
 
 void iic_local_enable(void)
 {
-	out_be64(&__get_cpu_var(iic).regs->prio, 0xff);
+	struct iic *iic = &__get_cpu_var(iic);
+	u64 tmp;
+
+	/*
+	 * There seems to be a bug that is present in DD2.x CPUs
+	 * and still only partially fixed in DD3.1.
+	 * This bug causes a value written to the priority register
+	 * not to make it there, resulting in a system hang unless we
+	 * write it again.
+	 * Masking with 0xf0 is done because the Cell BE does not
+	 * implement the lower four bits of the interrupt priority,
+	 * they always read back as zeroes, although future CPUs
+	 * might implement different bits.
+	 */
+	do {
+		out_be64(&iic->regs->prio, 0xff);
+		tmp = in_be64(&iic->regs->prio);
+	} while ((tmp & 0xf0) != 0xf0);
 }
 
 void iic_local_disable(void)
@@ -123,7 +140,7 @@ static int iic_external_get_irq(struct iic_pending_bits pending)
 		    pending.class != 2)
 			break;
 		irq = IIC_EXT_OFFSET
-			+ spider_get_irq(pending.prio + node * IIC_NODE_STRIDE)
+			+ spider_get_irq(node)
 			+ node * IIC_NODE_STRIDE;
 		break;
 	case 0x01 ... 0x04:
@@ -174,38 +191,98 @@ int iic_get_irq(struct pt_regs *regs)
 	return irq;
 }
 
-static int setup_iic(int cpu, struct iic *iic)
+/* hardcoded part to be compatible with older firmware */
+
+static int setup_iic_hardcoded(void)
 {
 	struct device_node *np;
-	int nodeid = cpu / 2;
+	int nodeid, cpu;
 	unsigned long regs;
+	struct iic *iic;
 
-	for (np = of_find_node_by_type(NULL, "cpu");
-	     np;
-	     np = of_find_node_by_type(np, "cpu")) {
-		if (nodeid == *(int *)get_property(np, "node-id", NULL))
-			break;
+	for_each_cpu(cpu) {
+		iic = &per_cpu(iic, cpu);
+		nodeid = cpu/2;
+
+		for (np = of_find_node_by_type(NULL, "cpu");
+		     np;
+		     np = of_find_node_by_type(np, "cpu")) {
+			if (nodeid == *(int *)get_property(np, "node-id", NULL))
+				break;
+			}
+
+		if (!np) {
+			printk(KERN_WARNING "IIC: CPU %d not found\n", cpu);
+			iic->regs = NULL;
+			iic->target_id = 0xff;
+			return -ENODEV;
+			}
+
+		regs = *(long *)get_property(np, "iic", NULL);
+
+		/* hack until we have decided on the devtree info */
+		regs += 0x400;
+		if (cpu & 1)
+			regs += 0x20;
+
+		printk(KERN_INFO "IIC for CPU %d at %lx\n", cpu, regs);
+		iic->regs = ioremap(regs, sizeof(struct iic_regs));
+		iic->target_id = (nodeid << 4) + ((cpu & 1) ? 0xf : 0xe);
 	}
 
-	if (!np) {
-		printk(KERN_WARNING "IIC: CPU %d not found\n", cpu);
-		iic->regs = NULL;
-		iic->target_id = 0xff;
-		return -ENODEV;
-	}
+	return 0;
+}
 
-	regs = *(long *)get_property(np, "iic", NULL);
+static int setup_iic(void)
+{
+	struct device_node *dn;
+	unsigned long *regs;
+	char *compatible;
+ 	unsigned *np, found = 0;
+	struct iic *iic = NULL;
+
+	for (dn = NULL; (dn = of_find_node_by_name(dn, "interrupt-controller"));) {
+		compatible = (char *)get_property(dn, "compatible", NULL);
+
+		if (!compatible) {
+			printk(KERN_WARNING "no compatible property found !\n");
+			continue;
+		}
 
-	/* hack until we have decided on the devtree info */
-	regs += 0x400;
-	if (cpu & 1)
-		regs += 0x20;
+ 		if (strstr(compatible, "IBM,CBEA-Internal-Interrupt-Controller"))
+ 			regs = (unsigned long *)get_property(dn,"reg", NULL);
+ 		else
+			continue;
 
-	printk(KERN_DEBUG "IIC for CPU %d at %lx\n", cpu, regs);
-	iic->regs = __ioremap(regs, sizeof(struct iic_regs),
-					 _PAGE_NO_CACHE);
-	iic->target_id = (nodeid << 4) + ((cpu & 1) ? 0xf : 0xe);
-	return 0;
+ 		if (!regs)
+ 			printk(KERN_WARNING "IIC: no reg property\n");
+
+ 		np = (unsigned int *)get_property(dn, "ibm,interrupt-server-ranges", NULL);
+
+ 		if (!np) {
+			printk(KERN_WARNING "IIC: CPU association not found\n");
+			iic->regs = NULL;
+			iic->target_id = 0xff;
+			return -ENODEV;
+		}
+
+ 		iic = &per_cpu(iic, np[0]);
+ 		iic->regs = ioremap(regs[0], sizeof(struct iic_regs));
+		iic->target_id = ((np[0] & 2) << 3) + ((np[0] & 1) ? 0xf : 0xe);
+ 		printk("IIC for CPU %d at %lx mapped to %p\n", np[0], regs[0], iic->regs);
+
+ 		iic = &per_cpu(iic, np[1]);
+ 		iic->regs = ioremap(regs[2], sizeof(struct iic_regs));
+		iic->target_id = ((np[1] & 2) << 3) + ((np[1] & 1) ? 0xf : 0xe);
+ 		printk("IIC for CPU %d at %lx mapped to %p\n", np[1], regs[2], iic->regs);
+
+		found++;
+  	}
+
+	if (found)
+		return 0;
+	else
+		return -ENODEV;
 }
 
 #ifdef CONFIG_SMP
@@ -283,10 +360,12 @@ void iic_init_IRQ(void)
 	int cpu, irq_offset;
 	struct iic *iic;
 
+	if (setup_iic() < 0)
+		setup_iic_hardcoded();
+
 	irq_offset = 0;
-	for_each_cpu(cpu) {
+	for_each_possible_cpu(cpu) {
 		iic = &per_cpu(iic, cpu);
-		setup_iic(cpu, iic);
 		if (iic->regs)
 			out_be64(&iic->regs->prio, 0xff);
 	}
diff --git a/arch/powerpc/platforms/cell/interrupt.h b/arch/powerpc/platforms/cell/interrupt.h
index a14bd38791c..799f77d98f9 100644
--- a/arch/powerpc/platforms/cell/interrupt.h
+++ b/arch/powerpc/platforms/cell/interrupt.h
@@ -57,7 +57,7 @@ extern void iic_local_disable(void);
 extern u8 iic_get_target_id(int cpu);
 
 extern void spider_init_IRQ(void);
-extern int spider_get_irq(unsigned long int_pending);
+extern int spider_get_irq(int node);
 
 #endif
 #endif /* ASM_CELL_PIC_H */
diff --git a/arch/powerpc/platforms/cell/iommu.c b/arch/powerpc/platforms/cell/iommu.c
index 46e7cb9c3e6..a49ceb799a8 100644
--- a/arch/powerpc/platforms/cell/iommu.c
+++ b/arch/powerpc/platforms/cell/iommu.c
@@ -289,7 +289,7 @@ static void cell_do_map_iommu(struct cell_iommu *iommu,
 	ioc_base = iommu->mapped_base;
 	ioc_mmio_base = iommu->mapped_mmio_base;
 
-	for (real_address = 0, io_address = 0;
+	for (real_address = 0, io_address = map_start;
 	     io_address <= map_start + map_size;
 	     real_address += io_page_size, io_address += io_page_size) {
 		ioste = get_iost_entry(fake_iopt, io_address, io_page_size);
@@ -302,7 +302,7 @@ static void cell_do_map_iommu(struct cell_iommu *iommu,
 		set_iopt_cache(ioc_mmio_base,
 			get_ioc_hash_1way(ioste, io_address),
 			get_ioc_tag(ioste, io_address),
-			get_iopt_entry(real_address-map_start, ioid, IOPT_PROT_RW));
+			get_iopt_entry(real_address, ioid, IOPT_PROT_RW));
 	}
 }
 
@@ -344,8 +344,8 @@ static int cell_map_iommu_hardcoded(int num_nodes)
 
 	/* node 0 */
 	iommu = &cell_iommus[0];
-	iommu->mapped_base = __ioremap(0x20000511000, 0x1000, _PAGE_NO_CACHE);
-	iommu->mapped_mmio_base = __ioremap(0x20000510000, 0x1000, _PAGE_NO_CACHE);
+	iommu->mapped_base = ioremap(0x20000511000, 0x1000);
+	iommu->mapped_mmio_base = ioremap(0x20000510000, 0x1000);
 
 	enable_mapping(iommu->mapped_base, iommu->mapped_mmio_base);
 
@@ -357,8 +357,8 @@ static int cell_map_iommu_hardcoded(int num_nodes)
 
 	/* node 1 */
 	iommu = &cell_iommus[1];
-	iommu->mapped_base = __ioremap(0x30000511000, 0x1000, _PAGE_NO_CACHE);
-	iommu->mapped_mmio_base = __ioremap(0x30000510000, 0x1000, _PAGE_NO_CACHE);
+	iommu->mapped_base = ioremap(0x30000511000, 0x1000);
+	iommu->mapped_mmio_base = ioremap(0x30000510000, 0x1000);
 
 	enable_mapping(iommu->mapped_base, iommu->mapped_mmio_base);
 
@@ -407,8 +407,8 @@ static int cell_map_iommu(void)
 		iommu->base = *base;
 		iommu->mmio_base = *mmio_base;
 
-		iommu->mapped_base = __ioremap(*base, 0x1000, _PAGE_NO_CACHE);
-		iommu->mapped_mmio_base = __ioremap(*mmio_base, 0x1000, _PAGE_NO_CACHE);
+		iommu->mapped_base = ioremap(*base, 0x1000);
+		iommu->mapped_mmio_base = ioremap(*mmio_base, 0x1000);
 
 		enable_mapping(iommu->mapped_base,
 			       iommu->mapped_mmio_base);
diff --git a/arch/powerpc/platforms/cell/pervasive.c b/arch/powerpc/platforms/cell/pervasive.c
index e0e051c675d..7eed8c62451 100644
--- a/arch/powerpc/platforms/cell/pervasive.c
+++ b/arch/powerpc/platforms/cell/pervasive.c
@@ -203,7 +203,7 @@ found:
 
 	pr_debug("pervasive area for CPU %d at %lx, size %x\n",
 			cpu, real_address, size);
-	p->regs = __ioremap(real_address, size, _PAGE_NO_CACHE);
+	p->regs = ioremap(real_address, size);
 	p->thread = thread;
 	return 0;
 }
@@ -217,7 +217,7 @@ void __init cell_pervasive_init(void)
 	if (!cpu_has_feature(CPU_FTR_PAUSE_ZERO))
 		return;
 
-	for_each_cpu(cpu) {
+	for_each_possible_cpu(cpu) {
 		p = &cbe_pervasive[cpu];
 		ret = cbe_find_pmd_mmio(cpu, p);
 		if (ret)
diff --git a/arch/powerpc/platforms/cell/setup.c b/arch/powerpc/platforms/cell/setup.c
index fec8e65b36e..dac5d0365fd 100644
--- a/arch/powerpc/platforms/cell/setup.c
+++ b/arch/powerpc/platforms/cell/setup.c
@@ -195,9 +195,13 @@ static void __init cell_init_early(void)
 }
 
 
-static int __init cell_probe(int platform)
+static int __init cell_probe(void)
 {
-	if (platform != PLATFORM_CELL)
+	/* XXX This is temporary, the Cell maintainer will come up with
+	 * more appropriate detection logic
+	 */
+	unsigned long root = of_get_flat_dt_root();
+	if (!of_flat_dt_is_compatible(root, "IBM,CPBW-1.0"))
 		return 0;
 
 	return 1;
@@ -212,7 +216,8 @@ static int cell_check_legacy_ioport(unsigned int baseport)
 	return -ENODEV;
 }
 
-struct machdep_calls __initdata cell_md = {
+define_machine(cell) {
+	.name			= "Cell",
 	.probe			= cell_probe,
 	.setup_arch		= cell_setup_arch,
 	.init_early		= cell_init_early,
diff --git a/arch/powerpc/platforms/cell/spider-pic.c b/arch/powerpc/platforms/cell/spider-pic.c
index e74132188bd..55cbdd77a62 100644
--- a/arch/powerpc/platforms/cell/spider-pic.c
+++ b/arch/powerpc/platforms/cell/spider-pic.c
@@ -84,10 +84,11 @@ static void __iomem *spider_get_irq_config(int irq)
 
 static void spider_enable_irq(unsigned int irq)
 {
+	int nodeid = (irq / IIC_NODE_STRIDE) * 0x10;
 	void __iomem *cfg = spider_get_irq_config(irq);
 	irq = spider_get_nr(irq);
 
-	out_be32(cfg, in_be32(cfg) | 0x3107000eu);
+	out_be32(cfg, (in_be32(cfg) & ~0xf0)| 0x3107000eu | nodeid);
 	out_be32(cfg + 4, in_be32(cfg + 4) | 0x00020000u | irq);
 }
 
@@ -131,61 +132,108 @@ static struct hw_interrupt_type spider_pic = {
 	.end = spider_end_irq,
 };
 
-
-int spider_get_irq(unsigned long int_pending)
+int spider_get_irq(int node)
 {
-	void __iomem *regs = spider_get_pic(int_pending);
 	unsigned long cs;
-	int irq;
-
-	cs = in_be32(regs + TIR_CS);
+	void __iomem *regs = spider_pics[node];
 
-	irq = cs >> 24;
-	if (irq != 63)
-		return irq;
+	cs = in_be32(regs + TIR_CS) >> 24;
 
-	return -1;
+	if (cs == 63)
+		return -1;
+	else
+		return cs;
 }
- 
-void spider_init_IRQ(void)
+
+/* hardcoded part to be compatible with older firmware */
+
+void spider_init_IRQ_hardcoded(void)
 {
 	int node;
-	struct device_node *dn;
-	unsigned int *property;
 	long spiderpic;
+	long pics[] = { 0x24000008000, 0x34000008000 };
 	int n;
 
-/* FIXME: detect multiple PICs as soon as the device tree has them */
-	for (node = 0; node < 1; node++) {
-		dn = of_find_node_by_path("/");
-		n = prom_n_addr_cells(dn);
-		property = (unsigned int *) get_property(dn,
-				"platform-spider-pic", NULL);
+	pr_debug("%s(%d): Using hardcoded defaults\n", __FUNCTION__, __LINE__);
 
-		if (!property)
-			continue;
-		for (spiderpic = 0; n > 0; --n)
-			spiderpic = (spiderpic << 32) + *property++;
+	for (node = 0; node < num_present_cpus()/2; node++) {
+		spiderpic = pics[node];
 		printk(KERN_DEBUG "SPIDER addr: %lx\n", spiderpic);
-		spider_pics[node] = __ioremap(spiderpic, 0x800, _PAGE_NO_CACHE);
+		spider_pics[node] = ioremap(spiderpic, 0x800);
 		for (n = 0; n < IIC_NUM_EXT; n++) {
 			int irq = n + IIC_EXT_OFFSET + node * IIC_NODE_STRIDE;
 			get_irq_desc(irq)->handler = &spider_pic;
+		}
 
  		/* do not mask any interrupts because of level */
  		out_be32(spider_pics[node] + TIR_MSK, 0x0);
- 		
+
  		/* disable edge detection clear */
  		/* out_be32(spider_pics[node] + TIR_EDC, 0x0); */
- 		
+
  		/* enable interrupt packets to be output */
  		out_be32(spider_pics[node] + TIR_PIEN,
 			in_be32(spider_pics[node] + TIR_PIEN) | 0x1);
- 		
+
  		/* Enable the interrupt detection enable bit. Do this last! */
  		out_be32(spider_pics[node] + TIR_DEN,
-			in_be32(spider_pics[node] +TIR_DEN) | 0x1);
+			in_be32(spider_pics[node] + TIR_DEN) | 0x1);
+	}
+}
+
+void spider_init_IRQ(void)
+{
+	long spider_reg;
+	struct device_node *dn;
+	char *compatible;
+	int n, node = 0;
+
+	for (dn = NULL; (dn = of_find_node_by_name(dn, "interrupt-controller"));) {
+		compatible = (char *)get_property(dn, "compatible", NULL);
 
+		if (!compatible)
+			continue;
+
+		if (strstr(compatible, "CBEA,platform-spider-pic"))
+			spider_reg = *(long *)get_property(dn,"reg", NULL);
+		else if (strstr(compatible, "sti,platform-spider-pic")) {
+			spider_init_IRQ_hardcoded();
+			return;
+		} else
+			continue;
+
+		if (!spider_reg)
+			printk("interrupt controller does not have reg property !\n");
+
+		n = prom_n_addr_cells(dn);
+
+		if ( n != 2)
+			printk("reg property with invalid number of elements \n");
+
+		spider_pics[node] = ioremap(spider_reg, 0x800);
+
+		printk("SPIDER addr: %lx with %i addr_cells mapped to %p\n",
+		       spider_reg, n, spider_pics[node]);
+
+		for (n = 0; n < IIC_NUM_EXT; n++) {
+			int irq = n + IIC_EXT_OFFSET + node * IIC_NODE_STRIDE;
+			get_irq_desc(irq)->handler = &spider_pic;
 		}
+
+		/* do not mask any interrupts because of level */
+		out_be32(spider_pics[node] + TIR_MSK, 0x0);
+
+		/* disable edge detection clear */
+		/* out_be32(spider_pics[node] + TIR_EDC, 0x0); */
+
+		/* enable interrupt packets to be output */
+		out_be32(spider_pics[node] + TIR_PIEN,
+			in_be32(spider_pics[node] + TIR_PIEN) | 0x1);
+
+		/* Enable the interrupt detection enable bit. Do this last! */
+		out_be32(spider_pics[node] + TIR_DEN,
+			in_be32(spider_pics[node] + TIR_DEN) | 0x1);
+
+		node++;
 	}
 }
diff --git a/arch/powerpc/platforms/cell/spu_base.c b/arch/powerpc/platforms/cell/spu_base.c
index a8fa1eeeb17..269dda4fd0b 100644
--- a/arch/powerpc/platforms/cell/spu_base.c
+++ b/arch/powerpc/platforms/cell/spu_base.c
@@ -111,7 +111,7 @@ static int __spu_trap_data_seg(struct spu *spu, unsigned long ea)
 extern int hash_page(unsigned long ea, unsigned long access, unsigned long trap); //XXX
 static int __spu_trap_data_map(struct spu *spu, unsigned long ea, u64 dsisr)
 {
-	pr_debug("%s\n", __FUNCTION__);
+	pr_debug("%s, %lx, %lx\n", __FUNCTION__, dsisr, ea);
 
 	/* Handle kernel space hash faults immediately.
 	   User hash faults need to be deferred to process context. */
@@ -168,7 +168,7 @@ static int __spu_trap_halt(struct spu *spu)
 static int __spu_trap_tag_group(struct spu *spu)
 {
 	pr_debug("%s\n", __FUNCTION__);
-	/* wake_up(&spu->dma_wq); */
+	spu->mfc_callback(spu);
 	return 0;
 }
 
@@ -242,6 +242,8 @@ spu_irq_class_1(int irq, void *data, struct pt_regs *regs)
 		spu_mfc_dsisr_set(spu, 0ul);
 	spu_int_stat_clear(spu, 1, stat);
 	spin_unlock(&spu->register_lock);
+	pr_debug("%s: %lx %lx %lx %lx\n", __FUNCTION__, mask, stat,
+			dar, dsisr);
 
 	if (stat & 1) /* segment fault */
 		__spu_trap_data_seg(spu, dar);
@@ -484,14 +486,13 @@ int spu_irq_class_1_bottom(struct spu *spu)
 
 	ea = spu->dar;
 	dsisr = spu->dsisr;
-	if (dsisr & MFC_DSISR_PTE_NOT_FOUND) {
+	if (dsisr & (MFC_DSISR_PTE_NOT_FOUND | MFC_DSISR_ACCESS_DENIED)) {
 		access = (_PAGE_PRESENT | _PAGE_USER);
 		access |= (dsisr & MFC_DSISR_ACCESS_PUT) ? _PAGE_RW : 0UL;
 		if (hash_page(ea, access, 0x300) != 0)
 			error |= CLASS1_ENABLE_STORAGE_FAULT_INTR;
 	}
-	if ((error & CLASS1_ENABLE_STORAGE_FAULT_INTR) ||
-	    (dsisr & MFC_DSISR_ACCESS_DENIED)) {
+	if (error & CLASS1_ENABLE_STORAGE_FAULT_INTR) {
 		if ((ret = spu_handle_mm_fault(spu)) != 0)
 			error |= CLASS1_ENABLE_STORAGE_FAULT_INTR;
 		else
@@ -568,6 +569,11 @@ static int __init spu_map_device(struct spu *spu, struct device_node *spe)
 	if (!spu->local_store)
 		goto out;
 
+	prop = get_property(spe, "problem", NULL);
+	if (!prop)
+		goto out_unmap;
+	spu->problem_phys = *(unsigned long *)prop;
+
 	spu->problem= map_spe_prop(spe, "problem");
 	if (!spu->problem)
 		goto out_unmap;
@@ -632,6 +638,7 @@ static int __init create_spu(struct device_node *spe)
 	spu->ibox_callback = NULL;
 	spu->wbox_callback = NULL;
 	spu->stop_callback = NULL;
+	spu->mfc_callback = NULL;
 
 	mutex_lock(&spu_mutex);
 	spu->number = number++;
diff --git a/arch/powerpc/platforms/cell/spu_callbacks.c b/arch/powerpc/platforms/cell/spu_callbacks.c
new file mode 100644
index 00000000000..6594bec7388
--- /dev/null
+++ b/arch/powerpc/platforms/cell/spu_callbacks.c
@@ -0,0 +1,346 @@
+/*
+ * System call callback functions for SPUs
+ */
+
+#define DEBUG
+
+#include <linux/kallsyms.h>
+#include <linux/module.h>
+#include <linux/syscalls.h>
+
+#include <asm/spu.h>
+#include <asm/syscalls.h>
+#include <asm/unistd.h>
+
+/*
+ * This table defines the system calls that an SPU can call.
+ * It is currently a subset of the 64 bit powerpc system calls,
+ * with the exact semantics.
+ *
+ * The reasons for disabling some of the system calls are:
+ * 1. They interact with the way SPU syscalls are handled
+ *    and we can't let them execute ever:
+ *	restart_syscall, exit, for, execve, ptrace, ...
+ * 2. They are deprecated and replaced by other means:
+ *	uselib, pciconfig_*, sysfs, ...
+ * 3. They are somewhat interacting with the system in a way
+ *    we don't want an SPU to:
+ *	reboot, init_module, mount, kexec_load
+ * 4. They are optional and we can't rely on them being
+ *    linked into the kernel. Unfortunately, the cond_syscall
+ *    helper does not work here as it does not add the necessary
+ *    opd symbols:
+ *	mbind, mq_open, ipc, ...
+ */
+
+void *spu_syscall_table[] = {
+	[__NR_restart_syscall]		sys_ni_syscall, /* sys_restart_syscall */
+	[__NR_exit]			sys_ni_syscall, /* sys_exit */
+	[__NR_fork]			sys_ni_syscall, /* ppc_fork */
+	[__NR_read]			sys_read,
+	[__NR_write]			sys_write,
+	[__NR_open]			sys_open,
+	[__NR_close]			sys_close,
+	[__NR_waitpid]			sys_waitpid,
+	[__NR_creat]			sys_creat,
+	[__NR_link]			sys_link,
+	[__NR_unlink]			sys_unlink,
+	[__NR_execve]			sys_ni_syscall, /* sys_execve */
+	[__NR_chdir]			sys_chdir,
+	[__NR_time]			sys_time,
+	[__NR_mknod]			sys_mknod,
+	[__NR_chmod]			sys_chmod,
+	[__NR_lchown]			sys_lchown,
+	[__NR_break]			sys_ni_syscall,
+	[__NR_oldstat]			sys_ni_syscall,
+	[__NR_lseek]			sys_lseek,
+	[__NR_getpid]			sys_getpid,
+	[__NR_mount]			sys_ni_syscall, /* sys_mount */
+	[__NR_umount]			sys_ni_syscall,
+	[__NR_setuid]			sys_setuid,
+	[__NR_getuid]			sys_getuid,
+	[__NR_stime]			sys_stime,
+	[__NR_ptrace]			sys_ni_syscall, /* sys_ptrace */
+	[__NR_alarm]			sys_alarm,
+	[__NR_oldfstat]			sys_ni_syscall,
+	[__NR_pause]			sys_ni_syscall, /* sys_pause */
+	[__NR_utime]			sys_ni_syscall, /* sys_utime */
+	[__NR_stty]			sys_ni_syscall,
+	[__NR_gtty]			sys_ni_syscall,
+	[__NR_access]			sys_access,
+	[__NR_nice]			sys_nice,
+	[__NR_ftime]			sys_ni_syscall,
+	[__NR_sync]			sys_sync,
+	[__NR_kill]			sys_kill,
+	[__NR_rename]			sys_rename,
+	[__NR_mkdir]			sys_mkdir,
+	[__NR_rmdir]			sys_rmdir,
+	[__NR_dup]			sys_dup,
+	[__NR_pipe]			sys_pipe,
+	[__NR_times]			sys_times,
+	[__NR_prof]			sys_ni_syscall,
+	[__NR_brk]			sys_brk,
+	[__NR_setgid]			sys_setgid,
+	[__NR_getgid]			sys_getgid,
+	[__NR_signal]			sys_ni_syscall, /* sys_signal */
+	[__NR_geteuid]			sys_geteuid,
+	[__NR_getegid]			sys_getegid,
+	[__NR_acct]			sys_ni_syscall, /* sys_acct */
+	[__NR_umount2]			sys_ni_syscall, /* sys_umount */
+	[__NR_lock]			sys_ni_syscall,
+	[__NR_ioctl]			sys_ioctl,
+	[__NR_fcntl]			sys_fcntl,
+	[__NR_mpx]			sys_ni_syscall,
+	[__NR_setpgid]			sys_setpgid,
+	[__NR_ulimit]			sys_ni_syscall,
+	[__NR_oldolduname]		sys_ni_syscall,
+	[__NR_umask]			sys_umask,
+	[__NR_chroot]			sys_chroot,
+	[__NR_ustat]			sys_ni_syscall, /* sys_ustat */
+	[__NR_dup2]			sys_dup2,
+	[__NR_getppid]			sys_getppid,
+	[__NR_getpgrp]			sys_getpgrp,
+	[__NR_setsid]			sys_setsid,
+	[__NR_sigaction]		sys_ni_syscall,
+	[__NR_sgetmask]			sys_sgetmask,
+	[__NR_ssetmask]			sys_ssetmask,
+	[__NR_setreuid]			sys_setreuid,
+	[__NR_setregid]			sys_setregid,
+	[__NR_sigsuspend]		sys_ni_syscall,
+	[__NR_sigpending]		sys_ni_syscall,
+	[__NR_sethostname]		sys_sethostname,
+	[__NR_setrlimit]		sys_setrlimit,
+	[__NR_getrlimit]		sys_ni_syscall,
+	[__NR_getrusage]		sys_getrusage,
+	[__NR_gettimeofday]		sys_gettimeofday,
+	[__NR_settimeofday]		sys_settimeofday,
+	[__NR_getgroups]		sys_getgroups,
+	[__NR_setgroups]		sys_setgroups,
+	[__NR_select]			sys_ni_syscall,
+	[__NR_symlink]			sys_symlink,
+	[__NR_oldlstat]			sys_ni_syscall,
+	[__NR_readlink]			sys_readlink,
+	[__NR_uselib]			sys_ni_syscall, /* sys_uselib */
+	[__NR_swapon]			sys_ni_syscall, /* sys_swapon */
+	[__NR_reboot]			sys_ni_syscall, /* sys_reboot */
+	[__NR_readdir]			sys_ni_syscall,
+	[__NR_mmap]			sys_mmap,
+	[__NR_munmap]			sys_munmap,
+	[__NR_truncate]			sys_truncate,
+	[__NR_ftruncate]		sys_ftruncate,
+	[__NR_fchmod]			sys_fchmod,
+	[__NR_fchown]			sys_fchown,
+	[__NR_getpriority]		sys_getpriority,
+	[__NR_setpriority]		sys_setpriority,
+	[__NR_profil]			sys_ni_syscall,
+	[__NR_statfs]			sys_ni_syscall, /* sys_statfs */
+	[__NR_fstatfs]			sys_ni_syscall, /* sys_fstatfs */
+	[__NR_ioperm]			sys_ni_syscall,
+	[__NR_socketcall]		sys_socketcall,
+	[__NR_syslog]			sys_syslog,
+	[__NR_setitimer]		sys_setitimer,
+	[__NR_getitimer]		sys_getitimer,
+	[__NR_stat]			sys_newstat,
+	[__NR_lstat]			sys_newlstat,
+	[__NR_fstat]			sys_newfstat,
+	[__NR_olduname]			sys_ni_syscall,
+	[__NR_iopl]			sys_ni_syscall,
+	[__NR_vhangup]			sys_vhangup,
+	[__NR_idle]			sys_ni_syscall,
+	[__NR_vm86]			sys_ni_syscall,
+	[__NR_wait4]			sys_wait4,
+	[__NR_swapoff]			sys_ni_syscall, /* sys_swapoff */
+	[__NR_sysinfo]			sys_sysinfo,
+	[__NR_ipc]			sys_ni_syscall, /* sys_ipc */
+	[__NR_fsync]			sys_fsync,
+	[__NR_sigreturn]		sys_ni_syscall,
+	[__NR_clone]			sys_ni_syscall, /* ppc_clone */
+	[__NR_setdomainname]		sys_setdomainname,
+	[__NR_uname]			ppc_newuname,
+	[__NR_modify_ldt]		sys_ni_syscall,
+	[__NR_adjtimex]			sys_adjtimex,
+	[__NR_mprotect]			sys_mprotect,
+	[__NR_sigprocmask]		sys_ni_syscall,
+	[__NR_create_module]		sys_ni_syscall,
+	[__NR_init_module]		sys_ni_syscall, /* sys_init_module */
+	[__NR_delete_module]		sys_ni_syscall, /* sys_delete_module */
+	[__NR_get_kernel_syms]		sys_ni_syscall,
+	[__NR_quotactl]			sys_ni_syscall, /* sys_quotactl */
+	[__NR_getpgid]			sys_getpgid,
+	[__NR_fchdir]			sys_fchdir,
+	[__NR_bdflush]			sys_bdflush,
+	[__NR_sysfs]			sys_ni_syscall, /* sys_sysfs */
+	[__NR_personality]		ppc64_personality,
+	[__NR_afs_syscall]		sys_ni_syscall,
+	[__NR_setfsuid]			sys_setfsuid,
+	[__NR_setfsgid]			sys_setfsgid,
+	[__NR__llseek]			sys_llseek,
+	[__NR_getdents]			sys_getdents,
+	[__NR__newselect]		sys_select,
+	[__NR_flock]			sys_flock,
+	[__NR_msync]			sys_msync,
+	[__NR_readv]			sys_readv,
+	[__NR_writev]			sys_writev,
+	[__NR_getsid]			sys_getsid,
+	[__NR_fdatasync]		sys_fdatasync,
+	[__NR__sysctl]			sys_ni_syscall, /* sys_sysctl */
+	[__NR_mlock]			sys_mlock,
+	[__NR_munlock]			sys_munlock,
+	[__NR_mlockall]			sys_mlockall,
+	[__NR_munlockall]		sys_munlockall,
+	[__NR_sched_setparam]		sys_sched_setparam,
+	[__NR_sched_getparam]		sys_sched_getparam,
+	[__NR_sched_setscheduler]	sys_sched_setscheduler,
+	[__NR_sched_getscheduler]	sys_sched_getscheduler,
+	[__NR_sched_yield]		sys_sched_yield,
+	[__NR_sched_get_priority_max]	sys_sched_get_priority_max,
+	[__NR_sched_get_priority_min]	sys_sched_get_priority_min,
+	[__NR_sched_rr_get_interval]	sys_sched_rr_get_interval,
+	[__NR_nanosleep]		sys_nanosleep,
+	[__NR_mremap]			sys_mremap,
+	[__NR_setresuid]		sys_setresuid,
+	[__NR_getresuid]		sys_getresuid,
+	[__NR_query_module]		sys_ni_syscall,
+	[__NR_poll]			sys_poll,
+	[__NR_nfsservctl]		sys_ni_syscall, /* sys_nfsservctl */
+	[__NR_setresgid]		sys_setresgid,
+	[__NR_getresgid]		sys_getresgid,
+	[__NR_prctl]			sys_prctl,
+	[__NR_rt_sigreturn]		sys_ni_syscall, /* ppc64_rt_sigreturn */
+	[__NR_rt_sigaction]		sys_ni_syscall, /* sys_rt_sigaction */
+	[__NR_rt_sigprocmask]		sys_ni_syscall, /* sys_rt_sigprocmask */
+	[__NR_rt_sigpending]		sys_ni_syscall, /* sys_rt_sigpending */
+	[__NR_rt_sigtimedwait]		sys_ni_syscall, /* sys_rt_sigtimedwait */
+	[__NR_rt_sigqueueinfo]		sys_ni_syscall, /* sys_rt_sigqueueinfo */
+	[__NR_rt_sigsuspend]		sys_ni_syscall, /* sys_rt_sigsuspend */
+	[__NR_pread64]			sys_pread64,
+	[__NR_pwrite64]			sys_pwrite64,
+	[__NR_chown]			sys_chown,
+	[__NR_getcwd]			sys_getcwd,
+	[__NR_capget]			sys_capget,
+	[__NR_capset]			sys_capset,
+	[__NR_sigaltstack]		sys_ni_syscall, /* sys_sigaltstack */
+	[__NR_sendfile]			sys_sendfile64,
+	[__NR_getpmsg]			sys_ni_syscall,
+	[__NR_putpmsg]			sys_ni_syscall,
+	[__NR_vfork]			sys_ni_syscall, /* ppc_vfork */
+	[__NR_ugetrlimit]		sys_getrlimit,
+	[__NR_readahead]		sys_readahead,
+	[192]				sys_ni_syscall,
+	[193]				sys_ni_syscall,
+	[194]				sys_ni_syscall,
+	[195]				sys_ni_syscall,
+	[196]				sys_ni_syscall,
+	[197]				sys_ni_syscall,
+	[__NR_pciconfig_read]		sys_ni_syscall, /* sys_pciconfig_read */
+	[__NR_pciconfig_write]		sys_ni_syscall, /* sys_pciconfig_write */
+	[__NR_pciconfig_iobase]		sys_ni_syscall, /* sys_pciconfig_iobase */
+	[__NR_multiplexer]		sys_ni_syscall,
+	[__NR_getdents64]		sys_getdents64,
+	[__NR_pivot_root]		sys_pivot_root,
+	[204]				sys_ni_syscall,
+	[__NR_madvise]			sys_madvise,
+	[__NR_mincore]			sys_mincore,
+	[__NR_gettid]			sys_gettid,
+	[__NR_tkill]			sys_tkill,
+	[__NR_setxattr]			sys_setxattr,
+	[__NR_lsetxattr]		sys_lsetxattr,
+	[__NR_fsetxattr]		sys_fsetxattr,
+	[__NR_getxattr]			sys_getxattr,
+	[__NR_lgetxattr]		sys_lgetxattr,
+	[__NR_fgetxattr]		sys_fgetxattr,
+	[__NR_listxattr]		sys_listxattr,
+	[__NR_llistxattr]		sys_llistxattr,
+	[__NR_flistxattr]		sys_flistxattr,
+	[__NR_removexattr]		sys_removexattr,
+	[__NR_lremovexattr]		sys_lremovexattr,
+	[__NR_fremovexattr]		sys_fremovexattr,
+	[__NR_futex]			sys_futex,
+	[__NR_sched_setaffinity]	sys_sched_setaffinity,
+	[__NR_sched_getaffinity]	sys_sched_getaffinity,
+	[__NR_tuxcall]			sys_ni_syscall,
+	[226]				sys_ni_syscall,
+	[__NR_io_setup]			sys_io_setup,
+	[__NR_io_destroy]		sys_io_destroy,
+	[__NR_io_getevents]		sys_io_getevents,
+	[__NR_io_submit]		sys_io_submit,
+	[__NR_io_cancel]		sys_io_cancel,
+	[__NR_set_tid_address]		sys_ni_syscall, /* sys_set_tid_address */
+	[__NR_fadvise64]		sys_fadvise64,
+	[__NR_exit_group]		sys_ni_syscall, /* sys_exit_group */
+	[__NR_lookup_dcookie]		sys_ni_syscall, /* sys_lookup_dcookie */
+	[__NR_epoll_create]		sys_epoll_create,
+	[__NR_epoll_ctl]		sys_epoll_ctl,
+	[__NR_epoll_wait]		sys_epoll_wait,
+	[__NR_remap_file_pages]		sys_remap_file_pages,
+	[__NR_timer_create]		sys_timer_create,
+	[__NR_timer_settime]		sys_timer_settime,
+	[__NR_timer_gettime]		sys_timer_gettime,
+	[__NR_timer_getoverrun]		sys_timer_getoverrun,
+	[__NR_timer_delete]		sys_timer_delete,
+	[__NR_clock_settime]		sys_clock_settime,
+	[__NR_clock_gettime]		sys_clock_gettime,
+	[__NR_clock_getres]		sys_clock_getres,
+	[__NR_clock_nanosleep]		sys_clock_nanosleep,
+	[__NR_swapcontext]		sys_ni_syscall, /* ppc64_swapcontext */
+	[__NR_tgkill]			sys_tgkill,
+	[__NR_utimes]			sys_utimes,
+	[__NR_statfs64]			sys_statfs64,
+	[__NR_fstatfs64]		sys_fstatfs64,
+	[254]				sys_ni_syscall,
+	[__NR_rtas]			ppc_rtas,
+	[256]				sys_ni_syscall,
+	[257]				sys_ni_syscall,
+	[258]				sys_ni_syscall,
+	[__NR_mbind]			sys_ni_syscall, /* sys_mbind */
+	[__NR_get_mempolicy]		sys_ni_syscall, /* sys_get_mempolicy */
+	[__NR_set_mempolicy]		sys_ni_syscall, /* sys_set_mempolicy */
+	[__NR_mq_open]			sys_ni_syscall, /* sys_mq_open */
+	[__NR_mq_unlink]		sys_ni_syscall, /* sys_mq_unlink */
+	[__NR_mq_timedsend]		sys_ni_syscall, /* sys_mq_timedsend */
+	[__NR_mq_timedreceive]		sys_ni_syscall, /* sys_mq_timedreceive */
+	[__NR_mq_notify]		sys_ni_syscall, /* sys_mq_notify */
+	[__NR_mq_getsetattr]		sys_ni_syscall, /* sys_mq_getsetattr */
+	[__NR_kexec_load]		sys_ni_syscall, /* sys_kexec_load */
+	[__NR_add_key]			sys_ni_syscall, /* sys_add_key */
+	[__NR_request_key]		sys_ni_syscall, /* sys_request_key */
+	[__NR_keyctl]			sys_ni_syscall, /* sys_keyctl */
+	[__NR_waitid]			sys_ni_syscall, /* sys_waitid */
+	[__NR_ioprio_set]		sys_ni_syscall, /* sys_ioprio_set */
+	[__NR_ioprio_get]		sys_ni_syscall, /* sys_ioprio_get */
+	[__NR_inotify_init]		sys_ni_syscall, /* sys_inotify_init */
+	[__NR_inotify_add_watch]	sys_ni_syscall, /* sys_inotify_add_watch */
+	[__NR_inotify_rm_watch]		sys_ni_syscall, /* sys_inotify_rm_watch */
+	[__NR_spu_run]			sys_ni_syscall, /* sys_spu_run */
+	[__NR_spu_create]		sys_ni_syscall, /* sys_spu_create */
+	[__NR_pselect6]			sys_ni_syscall, /* sys_pselect */
+	[__NR_ppoll]			sys_ni_syscall, /* sys_ppoll */
+	[__NR_unshare]			sys_unshare,
+	[__NR_splice]			sys_splice,
+};
+
+long spu_sys_callback(struct spu_syscall_block *s)
+{
+	long (*syscall)(u64 a1, u64 a2, u64 a3, u64 a4, u64 a5, u64 a6);
+
+	BUILD_BUG_ON(ARRAY_SIZE(spu_syscall_table) != __NR_syscalls);
+
+	syscall = spu_syscall_table[s->nr_ret];
+
+	if (s->nr_ret >= __NR_syscalls) {
+		pr_debug("%s: invalid syscall #%ld", __FUNCTION__, s->nr_ret);
+		return -ENOSYS;
+	}
+
+#ifdef DEBUG
+	print_symbol(KERN_DEBUG "SPU-syscall %s:", (unsigned long)syscall);
+	printk("syscall%ld(%lx, %lx, %lx, %lx, %lx, %lx)\n",
+			s->nr_ret,
+			s->parm[0], s->parm[1], s->parm[2],
+			s->parm[3], s->parm[4], s->parm[5]);
+#endif
+
+	return syscall(s->parm[0], s->parm[1], s->parm[2],
+		       s->parm[3], s->parm[4], s->parm[5]);
+}
+EXPORT_SYMBOL_GPL(spu_sys_callback);
diff --git a/arch/powerpc/platforms/cell/spufs/backing_ops.c b/arch/powerpc/platforms/cell/spufs/backing_ops.c
index a5c489a53c6..f1d35ddc9df 100644
--- a/arch/powerpc/platforms/cell/spufs/backing_ops.c
+++ b/arch/powerpc/platforms/cell/spufs/backing_ops.c
@@ -285,6 +285,49 @@ static void spu_backing_runcntl_stop(struct spu_context *ctx)
 	spu_backing_runcntl_write(ctx, SPU_RUNCNTL_STOP);
 }
 
+static int spu_backing_set_mfc_query(struct spu_context * ctx, u32 mask,
+					u32 mode)
+{
+	struct spu_problem_collapsed *prob = &ctx->csa.prob;
+	int ret;
+
+	spin_lock(&ctx->csa.register_lock);
+	ret = -EAGAIN;
+	if (prob->dma_querytype_RW)
+		goto out;
+	ret = 0;
+	/* FIXME: what are the side-effects of this? */
+	prob->dma_querymask_RW = mask;
+	prob->dma_querytype_RW = mode;
+out:
+	spin_unlock(&ctx->csa.register_lock);
+
+	return ret;
+}
+
+static u32 spu_backing_read_mfc_tagstatus(struct spu_context * ctx)
+{
+	return ctx->csa.prob.dma_tagstatus_R;
+}
+
+static u32 spu_backing_get_mfc_free_elements(struct spu_context *ctx)
+{
+	return ctx->csa.prob.dma_qstatus_R;
+}
+
+static int spu_backing_send_mfc_command(struct spu_context *ctx,
+					struct mfc_dma_command *cmd)
+{
+	int ret;
+
+	spin_lock(&ctx->csa.register_lock);
+	ret = -EAGAIN;
+	/* FIXME: set up priv2->puq */
+	spin_unlock(&ctx->csa.register_lock);
+
+	return ret;
+}
+
 struct spu_context_ops spu_backing_ops = {
 	.mbox_read = spu_backing_mbox_read,
 	.mbox_stat_read = spu_backing_mbox_stat_read,
@@ -305,4 +348,8 @@ struct spu_context_ops spu_backing_ops = {
 	.get_ls = spu_backing_get_ls,
 	.runcntl_write = spu_backing_runcntl_write,
 	.runcntl_stop = spu_backing_runcntl_stop,
+	.set_mfc_query = spu_backing_set_mfc_query,
+	.read_mfc_tagstatus = spu_backing_read_mfc_tagstatus,
+	.get_mfc_free_elements = spu_backing_get_mfc_free_elements,
+	.send_mfc_command = spu_backing_send_mfc_command,
 };
diff --git a/arch/powerpc/platforms/cell/spufs/context.c b/arch/powerpc/platforms/cell/spufs/context.c
index 336f238102f..8bb33abfad1 100644
--- a/arch/powerpc/platforms/cell/spufs/context.c
+++ b/arch/powerpc/platforms/cell/spufs/context.c
@@ -27,7 +27,7 @@
 #include <asm/spu_csa.h>
 #include "spufs.h"
 
-struct spu_context *alloc_spu_context(struct address_space *local_store)
+struct spu_context *alloc_spu_context(void)
 {
 	struct spu_context *ctx;
 	ctx = kmalloc(sizeof *ctx, GFP_KERNEL);
@@ -47,10 +47,17 @@ struct spu_context *alloc_spu_context(struct address_space *local_store)
 	init_waitqueue_head(&ctx->ibox_wq);
 	init_waitqueue_head(&ctx->wbox_wq);
 	init_waitqueue_head(&ctx->stop_wq);
+	init_waitqueue_head(&ctx->mfc_wq);
 	ctx->ibox_fasync = NULL;
 	ctx->wbox_fasync = NULL;
+	ctx->mfc_fasync = NULL;
+	ctx->mfc = NULL;
+	ctx->tagwait = 0;
 	ctx->state = SPU_STATE_SAVED;
-	ctx->local_store = local_store;
+	ctx->local_store = NULL;
+	ctx->cntl = NULL;
+	ctx->signal1 = NULL;
+	ctx->signal2 = NULL;
 	ctx->spu = NULL;
 	ctx->ops = &spu_backing_ops;
 	ctx->owner = get_task_mm(current);
@@ -68,8 +75,6 @@ void destroy_spu_context(struct kref *kref)
 	ctx = container_of(kref, struct spu_context, kref);
 	down_write(&ctx->state_sema);
 	spu_deactivate(ctx);
-	ctx->ibox_fasync = NULL;
-	ctx->wbox_fasync = NULL;
 	up_write(&ctx->state_sema);
 	spu_fini_csa(&ctx->csa);
 	kfree(ctx);
@@ -109,7 +114,16 @@ void spu_release(struct spu_context *ctx)
 
 void spu_unmap_mappings(struct spu_context *ctx)
 {
-	unmap_mapping_range(ctx->local_store, 0, LS_SIZE, 1);
+	if (ctx->local_store)
+		unmap_mapping_range(ctx->local_store, 0, LS_SIZE, 1);
+	if (ctx->mfc)
+		unmap_mapping_range(ctx->mfc, 0, 0x4000, 1);
+	if (ctx->cntl)
+		unmap_mapping_range(ctx->cntl, 0, 0x4000, 1);
+	if (ctx->signal1)
+		unmap_mapping_range(ctx->signal1, 0, 0x4000, 1);
+	if (ctx->signal2)
+		unmap_mapping_range(ctx->signal2, 0, 0x4000, 1);
 }
 
 int spu_acquire_runnable(struct spu_context *ctx)
diff --git a/arch/powerpc/platforms/cell/spufs/file.c b/arch/powerpc/platforms/cell/spufs/file.c
index dfa649c9b95..366185e9266 100644
--- a/arch/powerpc/platforms/cell/spufs/file.c
+++ b/arch/powerpc/platforms/cell/spufs/file.c
@@ -20,6 +20,8 @@
  * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 
+#undef DEBUG
+
 #include <linux/fs.h>
 #include <linux/ioctl.h>
 #include <linux/module.h>
@@ -39,8 +41,10 @@ static int
 spufs_mem_open(struct inode *inode, struct file *file)
 {
 	struct spufs_inode_info *i = SPUFS_I(inode);
-	file->private_data = i->i_ctx;
-	file->f_mapping = i->i_ctx->local_store;
+	struct spu_context *ctx = i->i_ctx;
+	file->private_data = ctx;
+	file->f_mapping = inode->i_mapping;
+	ctx->local_store = inode->i_mapping;
 	return 0;
 }
 
@@ -84,7 +88,7 @@ spufs_mem_write(struct file *file, const char __user *buffer,
 	return ret;
 }
 
-#ifdef CONFIG_SPARSEMEM
+#ifdef CONFIG_SPUFS_MMAP
 static struct page *
 spufs_mem_mmap_nopage(struct vm_area_struct *vma,
 		      unsigned long address, int *type)
@@ -136,11 +140,113 @@ static struct file_operations spufs_mem_fops = {
 	.read    = spufs_mem_read,
 	.write   = spufs_mem_write,
 	.llseek  = generic_file_llseek,
-#ifdef CONFIG_SPARSEMEM
+#ifdef CONFIG_SPUFS_MMAP
 	.mmap    = spufs_mem_mmap,
 #endif
 };
 
+#ifdef CONFIG_SPUFS_MMAP
+static struct page *spufs_ps_nopage(struct vm_area_struct *vma,
+				    unsigned long address,
+				    int *type, unsigned long ps_offs)
+{
+	struct page *page = NOPAGE_SIGBUS;
+	int fault_type = VM_FAULT_SIGBUS;
+	struct spu_context *ctx = vma->vm_file->private_data;
+	unsigned long offset = address - vma->vm_start;
+	unsigned long area;
+	int ret;
+
+	offset += vma->vm_pgoff << PAGE_SHIFT;
+	if (offset >= 0x4000)
+		goto out;
+
+	ret = spu_acquire_runnable(ctx);
+	if (ret)
+		goto out;
+
+	area = ctx->spu->problem_phys + ps_offs;
+	page = pfn_to_page((area + offset) >> PAGE_SHIFT);
+	fault_type = VM_FAULT_MINOR;
+	page_cache_get(page);
+
+	spu_release(ctx);
+
+      out:
+	if (type)
+		*type = fault_type;
+
+	return page;
+}
+
+static struct page *spufs_cntl_mmap_nopage(struct vm_area_struct *vma,
+					   unsigned long address, int *type)
+{
+	return spufs_ps_nopage(vma, address, type, 0x4000);
+}
+
+static struct vm_operations_struct spufs_cntl_mmap_vmops = {
+	.nopage = spufs_cntl_mmap_nopage,
+};
+
+/*
+ * mmap support for problem state control area [0x4000 - 0x4fff].
+ * Mapping this area requires that the application have CAP_SYS_RAWIO,
+ * as these registers require special care when read/writing.
+ */
+static int spufs_cntl_mmap(struct file *file, struct vm_area_struct *vma)
+{
+	if (!(vma->vm_flags & VM_SHARED))
+		return -EINVAL;
+
+	if (!capable(CAP_SYS_RAWIO))
+		return -EPERM;
+
+	vma->vm_flags |= VM_RESERVED;
+	vma->vm_page_prot = __pgprot(pgprot_val(vma->vm_page_prot)
+				     | _PAGE_NO_CACHE);
+
+	vma->vm_ops = &spufs_cntl_mmap_vmops;
+	return 0;
+}
+#endif
+
+static int spufs_cntl_open(struct inode *inode, struct file *file)
+{
+	struct spufs_inode_info *i = SPUFS_I(inode);
+	struct spu_context *ctx = i->i_ctx;
+
+	file->private_data = ctx;
+	file->f_mapping = inode->i_mapping;
+	ctx->cntl = inode->i_mapping;
+	return 0;
+}
+
+static ssize_t
+spufs_cntl_read(struct file *file, char __user *buffer,
+		size_t size, loff_t *pos)
+{
+	/* FIXME: read from spu status */
+	return -EINVAL;
+}
+
+static ssize_t
+spufs_cntl_write(struct file *file, const char __user *buffer,
+		 size_t size, loff_t *pos)
+{
+	/* FIXME: write to runctl bit */
+	return -EINVAL;
+}
+
+static struct file_operations spufs_cntl_fops = {
+	.open = spufs_cntl_open,
+	.read = spufs_cntl_read,
+	.write = spufs_cntl_write,
+#ifdef CONFIG_SPUFS_MMAP
+	.mmap = spufs_cntl_mmap,
+#endif
+};
+
 static int
 spufs_regs_open(struct inode *inode, struct file *file)
 {
@@ -501,6 +607,16 @@ static struct file_operations spufs_wbox_stat_fops = {
 	.read	= spufs_wbox_stat_read,
 };
 
+static int spufs_signal1_open(struct inode *inode, struct file *file)
+{
+	struct spufs_inode_info *i = SPUFS_I(inode);
+	struct spu_context *ctx = i->i_ctx;
+	file->private_data = ctx;
+	file->f_mapping = inode->i_mapping;
+	ctx->signal1 = inode->i_mapping;
+	return nonseekable_open(inode, file);
+}
+
 static ssize_t spufs_signal1_read(struct file *file, char __user *buf,
 			size_t len, loff_t *pos)
 {
@@ -541,12 +657,50 @@ static ssize_t spufs_signal1_write(struct file *file, const char __user *buf,
 	return 4;
 }
 
+#ifdef CONFIG_SPUFS_MMAP
+static struct page *spufs_signal1_mmap_nopage(struct vm_area_struct *vma,
+					      unsigned long address, int *type)
+{
+	return spufs_ps_nopage(vma, address, type, 0x14000);
+}
+
+static struct vm_operations_struct spufs_signal1_mmap_vmops = {
+	.nopage = spufs_signal1_mmap_nopage,
+};
+
+static int spufs_signal1_mmap(struct file *file, struct vm_area_struct *vma)
+{
+	if (!(vma->vm_flags & VM_SHARED))
+		return -EINVAL;
+
+	vma->vm_flags |= VM_RESERVED;
+	vma->vm_page_prot = __pgprot(pgprot_val(vma->vm_page_prot)
+				     | _PAGE_NO_CACHE);
+
+	vma->vm_ops = &spufs_signal1_mmap_vmops;
+	return 0;
+}
+#endif
+
 static struct file_operations spufs_signal1_fops = {
-	.open = spufs_pipe_open,
+	.open = spufs_signal1_open,
 	.read = spufs_signal1_read,
 	.write = spufs_signal1_write,
+#ifdef CONFIG_SPUFS_MMAP
+	.mmap = spufs_signal1_mmap,
+#endif
 };
 
+static int spufs_signal2_open(struct inode *inode, struct file *file)
+{
+	struct spufs_inode_info *i = SPUFS_I(inode);
+	struct spu_context *ctx = i->i_ctx;
+	file->private_data = ctx;
+	file->f_mapping = inode->i_mapping;
+	ctx->signal2 = inode->i_mapping;
+	return nonseekable_open(inode, file);
+}
+
 static ssize_t spufs_signal2_read(struct file *file, char __user *buf,
 			size_t len, loff_t *pos)
 {
@@ -589,10 +743,39 @@ static ssize_t spufs_signal2_write(struct file *file, const char __user *buf,
 	return 4;
 }
 
+#ifdef CONFIG_SPUFS_MMAP
+static struct page *spufs_signal2_mmap_nopage(struct vm_area_struct *vma,
+					      unsigned long address, int *type)
+{
+	return spufs_ps_nopage(vma, address, type, 0x1c000);
+}
+
+static struct vm_operations_struct spufs_signal2_mmap_vmops = {
+	.nopage = spufs_signal2_mmap_nopage,
+};
+
+static int spufs_signal2_mmap(struct file *file, struct vm_area_struct *vma)
+{
+	if (!(vma->vm_flags & VM_SHARED))
+		return -EINVAL;
+
+	/* FIXME: */
+	vma->vm_flags |= VM_RESERVED;
+	vma->vm_page_prot = __pgprot(pgprot_val(vma->vm_page_prot)
+				     | _PAGE_NO_CACHE);
+
+	vma->vm_ops = &spufs_signal2_mmap_vmops;
+	return 0;
+}
+#endif
+
 static struct file_operations spufs_signal2_fops = {
-	.open = spufs_pipe_open,
+	.open = spufs_signal2_open,
 	.read = spufs_signal2_read,
 	.write = spufs_signal2_write,
+#ifdef CONFIG_SPUFS_MMAP
+	.mmap = spufs_signal2_mmap,
+#endif
 };
 
 static void spufs_signal1_type_set(void *data, u64 val)
@@ -641,6 +824,332 @@ static u64 spufs_signal2_type_get(void *data)
 DEFINE_SIMPLE_ATTRIBUTE(spufs_signal2_type, spufs_signal2_type_get,
 					spufs_signal2_type_set, "%llu");
 
+#ifdef CONFIG_SPUFS_MMAP
+static struct page *spufs_mfc_mmap_nopage(struct vm_area_struct *vma,
+					   unsigned long address, int *type)
+{
+	return spufs_ps_nopage(vma, address, type, 0x3000);
+}
+
+static struct vm_operations_struct spufs_mfc_mmap_vmops = {
+	.nopage = spufs_mfc_mmap_nopage,
+};
+
+/*
+ * mmap support for problem state MFC DMA area [0x0000 - 0x0fff].
+ * Mapping this area requires that the application have CAP_SYS_RAWIO,
+ * as these registers require special care when read/writing.
+ */
+static int spufs_mfc_mmap(struct file *file, struct vm_area_struct *vma)
+{
+	if (!(vma->vm_flags & VM_SHARED))
+		return -EINVAL;
+
+	if (!capable(CAP_SYS_RAWIO))
+		return -EPERM;
+
+	vma->vm_flags |= VM_RESERVED;
+	vma->vm_page_prot = __pgprot(pgprot_val(vma->vm_page_prot)
+				     | _PAGE_NO_CACHE);
+
+	vma->vm_ops = &spufs_mfc_mmap_vmops;
+	return 0;
+}
+#endif
+
+static int spufs_mfc_open(struct inode *inode, struct file *file)
+{
+	struct spufs_inode_info *i = SPUFS_I(inode);
+	struct spu_context *ctx = i->i_ctx;
+
+	/* we don't want to deal with DMA into other processes */
+	if (ctx->owner != current->mm)
+		return -EINVAL;
+
+	if (atomic_read(&inode->i_count) != 1)
+		return -EBUSY;
+
+	file->private_data = ctx;
+	return nonseekable_open(inode, file);
+}
+
+/* interrupt-level mfc callback function. */
+void spufs_mfc_callback(struct spu *spu)
+{
+	struct spu_context *ctx = spu->ctx;
+
+	wake_up_all(&ctx->mfc_wq);
+
+	pr_debug("%s %s\n", __FUNCTION__, spu->name);
+	if (ctx->mfc_fasync) {
+		u32 free_elements, tagstatus;
+		unsigned int mask;
+
+		/* no need for spu_acquire in interrupt context */
+		free_elements = ctx->ops->get_mfc_free_elements(ctx);
+		tagstatus = ctx->ops->read_mfc_tagstatus(ctx);
+
+		mask = 0;
+		if (free_elements & 0xffff)
+			mask |= POLLOUT;
+		if (tagstatus & ctx->tagwait)
+			mask |= POLLIN;
+
+		kill_fasync(&ctx->mfc_fasync, SIGIO, mask);
+	}
+}
+
+static int spufs_read_mfc_tagstatus(struct spu_context *ctx, u32 *status)
+{
+	/* See if there is one tag group is complete */
+	/* FIXME we need locking around tagwait */
+	*status = ctx->ops->read_mfc_tagstatus(ctx) & ctx->tagwait;
+	ctx->tagwait &= ~*status;
+	if (*status)
+		return 1;
+
+	/* enable interrupt waiting for any tag group,
+	   may silently fail if interrupts are already enabled */
+	ctx->ops->set_mfc_query(ctx, ctx->tagwait, 1);
+	return 0;
+}
+
+static ssize_t spufs_mfc_read(struct file *file, char __user *buffer,
+			size_t size, loff_t *pos)
+{
+	struct spu_context *ctx = file->private_data;
+	int ret = -EINVAL;
+	u32 status;
+
+	if (size != 4)
+		goto out;
+
+	spu_acquire(ctx);
+	if (file->f_flags & O_NONBLOCK) {
+		status = ctx->ops->read_mfc_tagstatus(ctx);
+		if (!(status & ctx->tagwait))
+			ret = -EAGAIN;
+		else
+			ctx->tagwait &= ~status;
+	} else {
+		ret = spufs_wait(ctx->mfc_wq,
+			   spufs_read_mfc_tagstatus(ctx, &status));
+	}
+	spu_release(ctx);
+
+	if (ret)
+		goto out;
+
+	ret = 4;
+	if (copy_to_user(buffer, &status, 4))
+		ret = -EFAULT;
+
+out:
+	return ret;
+}
+
+static int spufs_check_valid_dma(struct mfc_dma_command *cmd)
+{
+	pr_debug("queueing DMA %x %lx %x %x %x\n", cmd->lsa,
+		 cmd->ea, cmd->size, cmd->tag, cmd->cmd);
+
+	switch (cmd->cmd) {
+	case MFC_PUT_CMD:
+	case MFC_PUTF_CMD:
+	case MFC_PUTB_CMD:
+	case MFC_GET_CMD:
+	case MFC_GETF_CMD:
+	case MFC_GETB_CMD:
+		break;
+	default:
+		pr_debug("invalid DMA opcode %x\n", cmd->cmd);
+		return -EIO;
+	}
+
+	if ((cmd->lsa & 0xf) != (cmd->ea &0xf)) {
+		pr_debug("invalid DMA alignment, ea %lx lsa %x\n",
+				cmd->ea, cmd->lsa);
+		return -EIO;
+	}
+
+	switch (cmd->size & 0xf) {
+	case 1:
+		break;
+	case 2:
+		if (cmd->lsa & 1)
+			goto error;
+		break;
+	case 4:
+		if (cmd->lsa & 3)
+			goto error;
+		break;
+	case 8:
+		if (cmd->lsa & 7)
+			goto error;
+		break;
+	case 0:
+		if (cmd->lsa & 15)
+			goto error;
+		break;
+	error:
+	default:
+		pr_debug("invalid DMA alignment %x for size %x\n",
+			cmd->lsa & 0xf, cmd->size);
+		return -EIO;
+	}
+
+	if (cmd->size > 16 * 1024) {
+		pr_debug("invalid DMA size %x\n", cmd->size);
+		return -EIO;
+	}
+
+	if (cmd->tag & 0xfff0) {
+		/* we reserve the higher tag numbers for kernel use */
+		pr_debug("invalid DMA tag\n");
+		return -EIO;
+	}
+
+	if (cmd->class) {
+		/* not supported in this version */
+		pr_debug("invalid DMA class\n");
+		return -EIO;
+	}
+
+	return 0;
+}
+
+static int spu_send_mfc_command(struct spu_context *ctx,
+				struct mfc_dma_command cmd,
+				int *error)
+{
+	*error = ctx->ops->send_mfc_command(ctx, &cmd);
+	if (*error == -EAGAIN) {
+		/* wait for any tag group to complete
+		   so we have space for the new command */
+		ctx->ops->set_mfc_query(ctx, ctx->tagwait, 1);
+		/* try again, because the queue might be
+		   empty again */
+		*error = ctx->ops->send_mfc_command(ctx, &cmd);
+		if (*error == -EAGAIN)
+			return 0;
+	}
+	return 1;
+}
+
+static ssize_t spufs_mfc_write(struct file *file, const char __user *buffer,
+			size_t size, loff_t *pos)
+{
+	struct spu_context *ctx = file->private_data;
+	struct mfc_dma_command cmd;
+	int ret = -EINVAL;
+
+	if (size != sizeof cmd)
+		goto out;
+
+	ret = -EFAULT;
+	if (copy_from_user(&cmd, buffer, sizeof cmd))
+		goto out;
+
+	ret = spufs_check_valid_dma(&cmd);
+	if (ret)
+		goto out;
+
+	spu_acquire_runnable(ctx);
+	if (file->f_flags & O_NONBLOCK) {
+		ret = ctx->ops->send_mfc_command(ctx, &cmd);
+	} else {
+		int status;
+		ret = spufs_wait(ctx->mfc_wq,
+				 spu_send_mfc_command(ctx, cmd, &status));
+		if (status)
+			ret = status;
+	}
+	spu_release(ctx);
+
+	if (ret)
+		goto out;
+
+	ctx->tagwait |= 1 << cmd.tag;
+
+out:
+	return ret;
+}
+
+static unsigned int spufs_mfc_poll(struct file *file,poll_table *wait)
+{
+	struct spu_context *ctx = file->private_data;
+	u32 free_elements, tagstatus;
+	unsigned int mask;
+
+	spu_acquire(ctx);
+	ctx->ops->set_mfc_query(ctx, ctx->tagwait, 2);
+	free_elements = ctx->ops->get_mfc_free_elements(ctx);
+	tagstatus = ctx->ops->read_mfc_tagstatus(ctx);
+	spu_release(ctx);
+
+	poll_wait(file, &ctx->mfc_wq, wait);
+
+	mask = 0;
+	if (free_elements & 0xffff)
+		mask |= POLLOUT | POLLWRNORM;
+	if (tagstatus & ctx->tagwait)
+		mask |= POLLIN | POLLRDNORM;
+
+	pr_debug("%s: free %d tagstatus %d tagwait %d\n", __FUNCTION__,
+		free_elements, tagstatus, ctx->tagwait);
+
+	return mask;
+}
+
+static int spufs_mfc_flush(struct file *file)
+{
+	struct spu_context *ctx = file->private_data;
+	int ret;
+
+	spu_acquire(ctx);
+#if 0
+/* this currently hangs */
+	ret = spufs_wait(ctx->mfc_wq,
+			 ctx->ops->set_mfc_query(ctx, ctx->tagwait, 2));
+	if (ret)
+		goto out;
+	ret = spufs_wait(ctx->mfc_wq,
+			 ctx->ops->read_mfc_tagstatus(ctx) == ctx->tagwait);
+out:
+#else
+	ret = 0;
+#endif
+	spu_release(ctx);
+
+	return ret;
+}
+
+static int spufs_mfc_fsync(struct file *file, struct dentry *dentry,
+			   int datasync)
+{
+	return spufs_mfc_flush(file);
+}
+
+static int spufs_mfc_fasync(int fd, struct file *file, int on)
+{
+	struct spu_context *ctx = file->private_data;
+
+	return fasync_helper(fd, file, on, &ctx->mfc_fasync);
+}
+
+static struct file_operations spufs_mfc_fops = {
+	.open	 = spufs_mfc_open,
+	.read	 = spufs_mfc_read,
+	.write	 = spufs_mfc_write,
+	.poll	 = spufs_mfc_poll,
+	.flush	 = spufs_mfc_flush,
+	.fsync	 = spufs_mfc_fsync,
+	.fasync	 = spufs_mfc_fasync,
+#ifdef CONFIG_SPUFS_MMAP
+	.mmap	 = spufs_mfc_mmap,
+#endif
+};
+
 static void spufs_npc_set(void *data, u64 val)
 {
 	struct spu_context *ctx = data;
@@ -783,6 +1292,8 @@ struct tree_descr spufs_dir_contents[] = {
 	{ "signal2", &spufs_signal2_fops, 0666, },
 	{ "signal1_type", &spufs_signal1_type, 0666, },
 	{ "signal2_type", &spufs_signal2_type, 0666, },
+	{ "mfc", &spufs_mfc_fops, 0666, },
+	{ "cntl", &spufs_cntl_fops,  0666, },
 	{ "npc", &spufs_npc_ops, 0666, },
 	{ "fpcr", &spufs_fpcr_fops, 0666, },
 	{ "decr", &spufs_decr_ops, 0666, },
diff --git a/arch/powerpc/platforms/cell/spufs/hw_ops.c b/arch/powerpc/platforms/cell/spufs/hw_ops.c
index 5445719bff7..a13a8b5a014 100644
--- a/arch/powerpc/platforms/cell/spufs/hw_ops.c
+++ b/arch/powerpc/platforms/cell/spufs/hw_ops.c
@@ -232,6 +232,59 @@ static void spu_hw_runcntl_stop(struct spu_context *ctx)
 	spin_unlock_irq(&ctx->spu->register_lock);
 }
 
+static int spu_hw_set_mfc_query(struct spu_context * ctx, u32 mask, u32 mode)
+{
+	struct spu_problem *prob = ctx->spu->problem;
+	int ret;
+
+	spin_lock_irq(&ctx->spu->register_lock);
+	ret = -EAGAIN;
+	if (in_be32(&prob->dma_querytype_RW))
+		goto out;
+	ret = 0;
+	out_be32(&prob->dma_querymask_RW, mask);
+	out_be32(&prob->dma_querytype_RW, mode);
+out:
+	spin_unlock_irq(&ctx->spu->register_lock);
+	return ret;
+}
+
+static u32 spu_hw_read_mfc_tagstatus(struct spu_context * ctx)
+{
+	return in_be32(&ctx->spu->problem->dma_tagstatus_R);
+}
+
+static u32 spu_hw_get_mfc_free_elements(struct spu_context *ctx)
+{
+	return in_be32(&ctx->spu->problem->dma_qstatus_R);
+}
+
+static int spu_hw_send_mfc_command(struct spu_context *ctx,
+					struct mfc_dma_command *cmd)
+{
+	u32 status;
+	struct spu_problem *prob = ctx->spu->problem;
+
+	spin_lock_irq(&ctx->spu->register_lock);
+	out_be32(&prob->mfc_lsa_W, cmd->lsa);
+	out_be64(&prob->mfc_ea_W, cmd->ea);
+	out_be32(&prob->mfc_union_W.by32.mfc_size_tag32,
+				cmd->size << 16 | cmd->tag);
+	out_be32(&prob->mfc_union_W.by32.mfc_class_cmd32,
+				cmd->class << 16 | cmd->cmd);
+	status = in_be32(&prob->mfc_union_W.by32.mfc_class_cmd32);
+	spin_unlock_irq(&ctx->spu->register_lock);
+
+	switch (status & 0xffff) {
+	case 0:
+		return 0;
+	case 2:
+		return -EAGAIN;
+	default:
+		return -EINVAL;
+	}
+}
+
 struct spu_context_ops spu_hw_ops = {
 	.mbox_read = spu_hw_mbox_read,
 	.mbox_stat_read = spu_hw_mbox_stat_read,
@@ -252,4 +305,8 @@ struct spu_context_ops spu_hw_ops = {
 	.get_ls = spu_hw_get_ls,
 	.runcntl_write = spu_hw_runcntl_write,
 	.runcntl_stop = spu_hw_runcntl_stop,
+	.set_mfc_query = spu_hw_set_mfc_query,
+	.read_mfc_tagstatus = spu_hw_read_mfc_tagstatus,
+	.get_mfc_free_elements = spu_hw_get_mfc_free_elements,
+	.send_mfc_command = spu_hw_send_mfc_command,
 };
diff --git a/arch/powerpc/platforms/cell/spufs/inode.c b/arch/powerpc/platforms/cell/spufs/inode.c
index 5be40aa483f..d9554199afa 100644
--- a/arch/powerpc/platforms/cell/spufs/inode.c
+++ b/arch/powerpc/platforms/cell/spufs/inode.c
@@ -241,7 +241,7 @@ spufs_mkdir(struct inode *dir, struct dentry *dentry, int mode)
 		inode->i_gid = dir->i_gid;
 		inode->i_mode &= S_ISGID;
 	}
-	ctx = alloc_spu_context(inode->i_mapping);
+	ctx = alloc_spu_context();
 	SPUFS_I(inode)->i_ctx = ctx;
 	if (!ctx)
 		goto out_iput;
@@ -442,7 +442,7 @@ static struct file_system_type spufs_type = {
 	.kill_sb = kill_litter_super,
 };
 
-static int spufs_init(void)
+static int __init spufs_init(void)
 {
 	int ret;
 	ret = -ENOMEM;
@@ -472,7 +472,7 @@ out:
 }
 module_init(spufs_init);
 
-static void spufs_exit(void)
+static void __exit spufs_exit(void)
 {
 	spu_sched_exit();
 	unregister_spu_syscalls(&spufs_calls);
diff --git a/arch/powerpc/platforms/cell/spufs/run.c b/arch/powerpc/platforms/cell/spufs/run.c
index 18ea8866c61..483c8b76232 100644
--- a/arch/powerpc/platforms/cell/spufs/run.c
+++ b/arch/powerpc/platforms/cell/spufs/run.c
@@ -2,6 +2,7 @@
 #include <linux/ptrace.h>
 
 #include <asm/spu.h>
+#include <asm/unistd.h>
 
 #include "spufs.h"
 
@@ -76,6 +77,90 @@ static inline int spu_reacquire_runnable(struct spu_context *ctx, u32 *npc,
 	return 0;
 }
 
+/*
+ * SPU syscall restarting is tricky because we violate the basic
+ * assumption that the signal handler is running on the interrupted
+ * thread. Here instead, the handler runs on PowerPC user space code,
+ * while the syscall was called from the SPU.
+ * This means we can only do a very rough approximation of POSIX
+ * signal semantics.
+ */
+int spu_handle_restartsys(struct spu_context *ctx, long *spu_ret,
+			  unsigned int *npc)
+{
+	int ret;
+
+	switch (*spu_ret) {
+	case -ERESTARTSYS:
+	case -ERESTARTNOINTR:
+		/*
+		 * Enter the regular syscall restarting for
+		 * sys_spu_run, then restart the SPU syscall
+		 * callback.
+		 */
+		*npc -= 8;
+		ret = -ERESTARTSYS;
+		break;
+	case -ERESTARTNOHAND:
+	case -ERESTART_RESTARTBLOCK:
+		/*
+		 * Restart block is too hard for now, just return -EINTR
+		 * to the SPU.
+		 * ERESTARTNOHAND comes from sys_pause, we also return
+		 * -EINTR from there.
+		 * Assume that we need to be restarted ourselves though.
+		 */
+		*spu_ret = -EINTR;
+		ret = -ERESTARTSYS;
+		break;
+	default:
+		printk(KERN_WARNING "%s: unexpected return code %ld\n",
+			__FUNCTION__, *spu_ret);
+		ret = 0;
+	}
+	return ret;
+}
+
+int spu_process_callback(struct spu_context *ctx)
+{
+	struct spu_syscall_block s;
+	u32 ls_pointer, npc;
+	char *ls;
+	long spu_ret;
+	int ret;
+
+	/* get syscall block from local store */
+	npc = ctx->ops->npc_read(ctx);
+	ls = ctx->ops->get_ls(ctx);
+	ls_pointer = *(u32*)(ls + npc);
+	if (ls_pointer > (LS_SIZE - sizeof(s)))
+		return -EFAULT;
+	memcpy(&s, ls + ls_pointer, sizeof (s));
+
+	/* do actual syscall without pinning the spu */
+	ret = 0;
+	spu_ret = -ENOSYS;
+	npc += 4;
+
+	if (s.nr_ret < __NR_syscalls) {
+		spu_release(ctx);
+		/* do actual system call from here */
+		spu_ret = spu_sys_callback(&s);
+		if (spu_ret <= -ERESTARTSYS) {
+			ret = spu_handle_restartsys(ctx, &spu_ret, &npc);
+		}
+		spu_acquire(ctx);
+		if (ret == -ERESTARTSYS)
+			return ret;
+	}
+
+	/* write result, jump over indirect pointer */
+	memcpy(ls + ls_pointer, &spu_ret, sizeof (spu_ret));
+	ctx->ops->npc_write(ctx, npc);
+	ctx->ops->runcntl_write(ctx, SPU_RUNCNTL_RUNNABLE);
+	return ret;
+}
+
 static inline int spu_process_events(struct spu_context *ctx)
 {
 	struct spu *spu = ctx->spu;
@@ -107,6 +192,13 @@ long spufs_run_spu(struct file *file, struct spu_context *ctx,
 		ret = spufs_wait(ctx->stop_wq, spu_stopped(ctx, status));
 		if (unlikely(ret))
 			break;
+		if ((*status & SPU_STATUS_STOPPED_BY_STOP) &&
+		    (*status >> SPU_STOP_STATUS_SHIFT == 0x2104)) {
+			ret = spu_process_callback(ctx);
+			if (ret)
+				break;
+			*status &= ~SPU_STATUS_STOPPED_BY_STOP;
+		}
 		if (unlikely(ctx->state != SPU_STATE_RUNNABLE)) {
 			ret = spu_reacquire_runnable(ctx, npc, status);
 			if (ret)
diff --git a/arch/powerpc/platforms/cell/spufs/sched.c b/arch/powerpc/platforms/cell/spufs/sched.c
index 963182fbd1a..bf652cd7700 100644
--- a/arch/powerpc/platforms/cell/spufs/sched.c
+++ b/arch/powerpc/platforms/cell/spufs/sched.c
@@ -180,6 +180,7 @@ static inline void bind_context(struct spu *spu, struct spu_context *ctx)
 	spu->ibox_callback = spufs_ibox_callback;
 	spu->wbox_callback = spufs_wbox_callback;
 	spu->stop_callback = spufs_stop_callback;
+	spu->mfc_callback = spufs_mfc_callback;
 	mb();
 	spu_unmap_mappings(ctx);
 	spu_restore(&ctx->csa, spu);
@@ -197,6 +198,7 @@ static inline void unbind_context(struct spu *spu, struct spu_context *ctx)
 	spu->ibox_callback = NULL;
 	spu->wbox_callback = NULL;
 	spu->stop_callback = NULL;
+	spu->mfc_callback = NULL;
 	spu->mm = NULL;
 	spu->pid = 0;
 	spu->prio = MAX_PRIO;
diff --git a/arch/powerpc/platforms/cell/spufs/spufs.h b/arch/powerpc/platforms/cell/spufs/spufs.h
index db2601f0abd..4485738e210 100644
--- a/arch/powerpc/platforms/cell/spufs/spufs.h
+++ b/arch/powerpc/platforms/cell/spufs/spufs.h
@@ -43,7 +43,11 @@ struct spu_context {
 	struct spu *spu;		  /* pointer to a physical SPU */
 	struct spu_state csa;		  /* SPU context save area. */
 	spinlock_t mmio_lock;		  /* protects mmio access */
-	struct address_space *local_store;/* local store backing store */
+	struct address_space *local_store; /* local store mapping.  */
+	struct address_space *mfc;	   /* 'mfc' area mappings. */
+	struct address_space *cntl; 	   /* 'control' area mappings. */
+	struct address_space *signal1; 	   /* 'signal1' area mappings. */
+	struct address_space *signal2; 	   /* 'signal2' area mappings. */
 
 	enum { SPU_STATE_RUNNABLE, SPU_STATE_SAVED } state;
 	struct rw_semaphore state_sema;
@@ -55,13 +59,27 @@ struct spu_context {
 	wait_queue_head_t ibox_wq;
 	wait_queue_head_t wbox_wq;
 	wait_queue_head_t stop_wq;
+	wait_queue_head_t mfc_wq;
 	struct fasync_struct *ibox_fasync;
 	struct fasync_struct *wbox_fasync;
+	struct fasync_struct *mfc_fasync;
+	u32 tagwait;
 	struct spu_context_ops *ops;
 	struct work_struct reap_work;
 	u64 flags;
 };
 
+struct mfc_dma_command {
+	int32_t pad;	/* reserved */
+	uint32_t lsa;	/* local storage address */
+	uint64_t ea;	/* effective address */
+	uint16_t size;	/* transfer size */
+	uint16_t tag;	/* command tag */
+	uint16_t class;	/* class ID */
+	uint16_t cmd;	/* command opcode */
+};
+
+
 /* SPU context query/set operations. */
 struct spu_context_ops {
 	int (*mbox_read) (struct spu_context * ctx, u32 * data);
@@ -84,6 +102,11 @@ struct spu_context_ops {
 	char*(*get_ls) (struct spu_context * ctx);
 	void (*runcntl_write) (struct spu_context * ctx, u32 data);
 	void (*runcntl_stop) (struct spu_context * ctx);
+	int (*set_mfc_query)(struct spu_context * ctx, u32 mask, u32 mode);
+	u32 (*read_mfc_tagstatus)(struct spu_context * ctx);
+	u32 (*get_mfc_free_elements)(struct spu_context *ctx);
+	int (*send_mfc_command)(struct spu_context *ctx,
+					struct mfc_dma_command *cmd);
 };
 
 extern struct spu_context_ops spu_hw_ops;
@@ -106,7 +129,7 @@ long spufs_create_thread(struct nameidata *nd,
 extern struct file_operations spufs_context_fops;
 
 /* context management */
-struct spu_context * alloc_spu_context(struct address_space *local_store);
+struct spu_context * alloc_spu_context(void);
 void destroy_spu_context(struct kref *kref);
 struct spu_context * get_spu_context(struct spu_context *ctx);
 int put_spu_context(struct spu_context *ctx);
@@ -159,5 +182,6 @@ size_t spu_ibox_read(struct spu_context *ctx, u32 *data);
 void spufs_ibox_callback(struct spu *spu);
 void spufs_wbox_callback(struct spu *spu);
 void spufs_stop_callback(struct spu *spu);
+void spufs_mfc_callback(struct spu *spu);
 
 #endif
diff --git a/arch/powerpc/platforms/cell/spufs/switch.c b/arch/powerpc/platforms/cell/spufs/switch.c
index 212db28531f..1726bfe38ee 100644
--- a/arch/powerpc/platforms/cell/spufs/switch.c
+++ b/arch/powerpc/platforms/cell/spufs/switch.c
@@ -1297,7 +1297,7 @@ static inline void setup_decr(struct spu_state *csa, struct spu *spu)
 		cycles_t resume_time = get_cycles();
 		cycles_t delta_time = resume_time - csa->suspend_time;
 
-		csa->lscsa->decr.slot[0] = delta_time;
+		csa->lscsa->decr.slot[0] -= delta_time;
 	}
 }
 
@@ -2145,7 +2145,8 @@ static void init_priv1(struct spu_state *csa)
 	csa->priv1.int_mask_class1_RW = CLASS1_ENABLE_SEGMENT_FAULT_INTR |
 	    CLASS1_ENABLE_STORAGE_FAULT_INTR;
 	csa->priv1.int_mask_class2_RW = CLASS2_ENABLE_SPU_STOP_INTR |
-	    CLASS2_ENABLE_SPU_HALT_INTR;
+	    CLASS2_ENABLE_SPU_HALT_INTR |
+	    CLASS2_ENABLE_SPU_DMA_TAG_GROUP_COMPLETE_INTR;
 }
 
 static void init_priv2(struct spu_state *csa)
diff --git a/arch/powerpc/platforms/chrp/chrp.h b/arch/powerpc/platforms/chrp/chrp.h
index 814f54742e0..996c28744e9 100644
--- a/arch/powerpc/platforms/chrp/chrp.h
+++ b/arch/powerpc/platforms/chrp/chrp.h
@@ -8,4 +8,5 @@ extern int chrp_set_rtc_time(struct rtc_time *);
 extern long chrp_time_init(void);
 
 extern void chrp_find_bridges(void);
-extern void chrp_event_scan(void);
+extern void chrp_event_scan(unsigned long);
+extern void chrp_pcibios_fixup(void);
diff --git a/arch/powerpc/platforms/chrp/pci.c b/arch/powerpc/platforms/chrp/pci.c
index 8ef279ad36a..ac224876ce5 100644
--- a/arch/powerpc/platforms/chrp/pci.c
+++ b/arch/powerpc/platforms/chrp/pci.c
@@ -23,6 +23,8 @@
 #include <asm/grackle.h>
 #include <asm/rtas.h>
 
+#include "chrp.h"
+
 /* LongTrail */
 void __iomem *gg2_pci_config_base;
 
@@ -314,6 +316,6 @@ chrp_find_bridges(void)
 	}
 
 	/* Do not fixup interrupts from OF tree on pegasos */
-	if (is_pegasos == 0)
-		ppc_md.pcibios_fixup = chrp_pcibios_fixup;
+	if (is_pegasos)
+		ppc_md.pcibios_fixup = NULL;
 }
diff --git a/arch/powerpc/platforms/chrp/setup.c b/arch/powerpc/platforms/chrp/setup.c
index 8bf4307e323..18d89f38796 100644
--- a/arch/powerpc/platforms/chrp/setup.c
+++ b/arch/powerpc/platforms/chrp/setup.c
@@ -35,6 +35,7 @@
 #include <linux/root_dev.h>
 #include <linux/initrd.h>
 #include <linux/module.h>
+#include <linux/timer.h>
 
 #include <asm/io.h>
 #include <asm/pgtable.h>
@@ -61,6 +62,10 @@ EXPORT_SYMBOL(_chrp_type);
 
 struct mpic *chrp_mpic;
 
+/* Used for doing CHRP event-scans */
+DEFINE_PER_CPU(struct timer_list, heartbeat_timer);
+unsigned long event_scan_interval;
+
 /*
  * XXX this should be in xmon.h, but putting it there means xmon.h
  * has to include <linux/interrupt.h> (to get irqreturn_t), which
@@ -229,8 +234,6 @@ void __init chrp_setup_arch(void)
 {
 	struct device_node *root = find_path_device ("/");
 	char *machine = NULL;
-	struct device_node *device;
-	unsigned int *p = NULL;
 
 	/* init to some ~sane value until calibrate_delay() runs */
 	loops_per_jiffy = 50000000/HZ;
@@ -287,23 +290,12 @@ void __init chrp_setup_arch(void)
 	 */
 	sio_init();
 
-	/* Get the event scan rate for the rtas so we know how
-	 * often it expects a heartbeat. -- Cort
-	 */
-	device = find_devices("rtas");
-	if (device)
-		p = (unsigned int *) get_property
-			(device, "rtas-event-scan-rate", NULL);
-	if (p && *p) {
-		ppc_md.heartbeat = chrp_event_scan;
-		ppc_md.heartbeat_reset = HZ / (*p * 30) - 1;
-		ppc_md.heartbeat_count = 1;
-		printk("RTAS Event Scan Rate: %u (%lu jiffies)\n",
-		       *p, ppc_md.heartbeat_reset);
-	}
-
 	pci_create_OF_bus_map();
 
+#ifdef CONFIG_SMP
+	smp_ops = &chrp_smp_ops;
+#endif /* CONFIG_SMP */
+
 	/*
 	 * Print the banner, then scroll down so boot progress
 	 * can be printed.  -- Cort
@@ -312,7 +304,7 @@ void __init chrp_setup_arch(void)
 }
 
 void
-chrp_event_scan(void)
+chrp_event_scan(unsigned long unused)
 {
 	unsigned char log[1024];
 	int ret = 0;
@@ -320,7 +312,8 @@ chrp_event_scan(void)
 	/* XXX: we should loop until the hardware says no more error logs -- Cort */
 	rtas_call(rtas_token("event-scan"), 4, 1, &ret, 0xffffffff, 0,
 		  __pa(log), 1024);
-	ppc_md.heartbeat_count = ppc_md.heartbeat_reset;
+	mod_timer(&__get_cpu_var(heartbeat_timer),
+		  jiffies + event_scan_interval);
 }
 
 /*
@@ -447,8 +440,6 @@ void __init chrp_init_IRQ(void)
 
 	if (_chrp_type == _CHRP_Pegasos)
 		ppc_md.get_irq        = i8259_irq;
-	else
-		ppc_md.get_irq        = mpic_get_irq;
 
 #if defined(CONFIG_VT) && defined(CONFIG_INPUT_ADBHID) && defined(XMON)
 	/* see if there is a keyboard in the device tree
@@ -465,6 +456,9 @@ void __init chrp_init_IRQ(void)
 void __init
 chrp_init2(void)
 {
+	struct device_node *device;
+	unsigned int *p = NULL;
+
 #ifdef CONFIG_NVRAM
 	chrp_nvram_init();
 #endif
@@ -476,12 +470,53 @@ chrp_init2(void)
 	request_region(0x80,0x10,"dma page reg");
 	request_region(0xc0,0x20,"dma2");
 
+	/* Get the event scan rate for the rtas so we know how
+	 * often it expects a heartbeat. -- Cort
+	 */
+	device = find_devices("rtas");
+	if (device)
+		p = (unsigned int *) get_property
+			(device, "rtas-event-scan-rate", NULL);
+	if (p && *p) {
+		/*
+		 * Arrange to call chrp_event_scan at least *p times
+		 * per minute.  We use 59 rather than 60 here so that
+		 * the rate will be slightly higher than the minimum.
+		 * This all assumes we don't do hotplug CPU on any
+		 * machine that needs the event scans done.
+		 */
+		unsigned long interval, offset;
+		int cpu, ncpus;
+		struct timer_list *timer;
+
+		interval = HZ * 59 / *p;
+		offset = HZ;
+		ncpus = num_online_cpus();
+		event_scan_interval = ncpus * interval;
+		for (cpu = 0; cpu < ncpus; ++cpu) {
+			timer = &per_cpu(heartbeat_timer, cpu);
+			setup_timer(timer, chrp_event_scan, 0);
+			timer->expires = jiffies + offset;
+			add_timer_on(timer, cpu);
+			offset += interval;
+		}
+		printk("RTAS Event Scan Rate: %u (%lu jiffies)\n",
+		       *p, interval);
+	}
+
 	if (ppc_md.progress)
 		ppc_md.progress("  Have fun!    ", 0x7777);
 }
 
-void __init chrp_init(void)
+static int __init chrp_probe(void)
 {
+ 	char *dtype = of_get_flat_dt_prop(of_get_flat_dt_root(),
+ 					  "device_type", NULL);
+ 	if (dtype == NULL)
+ 		return 0;
+ 	if (strcmp(dtype, "chrp"))
+		return 0;
+
 	ISA_DMA_THRESHOLD = ~0L;
 	DMA_MODE_READ = 0x44;
 	DMA_MODE_WRITE = 0x48;
@@ -491,26 +526,24 @@ void __init chrp_init(void)
 	/* Assume we have an 8259... */
 	__irq_offset_value = NUM_ISA_INTERRUPTS;
 
-	ppc_md.setup_arch     = chrp_setup_arch;
-	ppc_md.show_cpuinfo   = chrp_show_cpuinfo;
-
-	ppc_md.init_IRQ       = chrp_init_IRQ;
-	ppc_md.init           = chrp_init2;
-
-	ppc_md.phys_mem_access_prot = pci_phys_mem_access_prot;
-
-	ppc_md.restart        = rtas_restart;
-	ppc_md.power_off      = rtas_power_off;
-	ppc_md.halt           = rtas_halt;
-
-	ppc_md.time_init      = chrp_time_init;
-	ppc_md.calibrate_decr = generic_calibrate_decr;
-
-	/* this may get overridden with rtas routines later... */
-	ppc_md.set_rtc_time   = chrp_set_rtc_time;
-	ppc_md.get_rtc_time   = chrp_get_rtc_time;
-
-#ifdef CONFIG_SMP
-	smp_ops = &chrp_smp_ops;
-#endif /* CONFIG_SMP */
+	return 1;
 }
+
+define_machine(chrp) {
+	.name			= "CHRP",
+	.probe			= chrp_probe,
+	.setup_arch		= chrp_setup_arch,
+	.init			= chrp_init2,
+	.show_cpuinfo		= chrp_show_cpuinfo,
+	.init_IRQ		= chrp_init_IRQ,
+	.get_irq		= mpic_get_irq,
+	.pcibios_fixup		= chrp_pcibios_fixup,
+	.restart		= rtas_restart,
+	.power_off		= rtas_power_off,
+	.halt			= rtas_halt,
+	.time_init		= chrp_time_init,
+	.set_rtc_time		= chrp_set_rtc_time,
+	.get_rtc_time		= chrp_get_rtc_time,
+	.calibrate_decr		= generic_calibrate_decr,
+	.phys_mem_access_prot	= pci_phys_mem_access_prot,
+};
diff --git a/arch/powerpc/platforms/iseries/setup.c b/arch/powerpc/platforms/iseries/setup.c
index fa4550611c1..a6fd9bedb07 100644
--- a/arch/powerpc/platforms/iseries/setup.c
+++ b/arch/powerpc/platforms/iseries/setup.c
@@ -54,6 +54,7 @@
 #include <asm/iseries/hv_lp_event.h>
 #include <asm/iseries/lpar_map.h>
 #include <asm/udbg.h>
+#include <asm/irq.h>
 
 #include "naca.h"
 #include "setup.h"
@@ -675,18 +676,26 @@ static void iseries_dedicated_idle(void)
 void __init iSeries_init_IRQ(void) { }
 #endif
 
-static int __init iseries_probe(int platform)
+static int __init iseries_probe(void)
 {
-	if (PLATFORM_ISERIES_LPAR != platform)
+	unsigned long root = of_get_flat_dt_root();
+	if (!of_flat_dt_is_compatible(root, "IBM,iSeries"))
 		return 0;
 
-	ppc64_firmware_features |= FW_FEATURE_ISERIES;
-	ppc64_firmware_features |= FW_FEATURE_LPAR;
+	powerpc_firmware_features |= FW_FEATURE_ISERIES;
+	powerpc_firmware_features |= FW_FEATURE_LPAR;
+
+	/*
+	 * The Hypervisor only allows us up to 256 interrupt
+	 * sources (the irq number is passed in a u8).
+	 */
+	virt_irq_max = 255;
 
 	return 1;
 }
 
-struct machdep_calls __initdata iseries_md = {
+define_machine(iseries) {
+	.name		= "iSeries",
 	.setup_arch	= iSeries_setup_arch,
 	.show_cpuinfo	= iSeries_show_cpuinfo,
 	.init_IRQ	= iSeries_init_IRQ,
@@ -930,7 +939,6 @@ void build_flat_dt(struct iseries_flat_dt *dt, unsigned long phys_mem_size)
 
 	/* /chosen */
 	dt_start_node(dt, "chosen");
-	dt_prop_u32(dt, "linux,platform", PLATFORM_ISERIES_LPAR);
 	dt_prop_str(dt, "bootargs", cmd_line);
 	if (cmd_mem_limit)
 		dt_prop_u64(dt, "linux,memory-limit", cmd_mem_limit);
diff --git a/arch/powerpc/platforms/maple/setup.c b/arch/powerpc/platforms/maple/setup.c
index ec5c1e10c40..24c0aef4ea3 100644
--- a/arch/powerpc/platforms/maple/setup.c
+++ b/arch/powerpc/platforms/maple/setup.c
@@ -259,9 +259,10 @@ static void __init maple_progress(char *s, unsigned short hex)
 /*
  * Called very early, MMU is off, device-tree isn't unflattened
  */
-static int __init maple_probe(int platform)
+static int __init maple_probe(void)
 {
-	if (platform != PLATFORM_MAPLE)
+	unsigned long root = of_get_flat_dt_root();
+	if (!of_flat_dt_is_compatible(root, "Momentum,Maple"))
 		return 0;
 	/*
 	 * On U3, the DART (iommu) must be allocated now since it
@@ -274,7 +275,8 @@ static int __init maple_probe(int platform)
 	return 1;
 }
 
-struct machdep_calls __initdata maple_md = {
+define_machine(maple_md) {
+	.name			= "Maple",
 	.probe			= maple_probe,
 	.setup_arch		= maple_setup_arch,
 	.init_early		= maple_init_early,
@@ -290,7 +292,7 @@ struct machdep_calls __initdata maple_md = {
        	.get_rtc_time		= maple_get_rtc_time,
       	.calibrate_decr		= generic_calibrate_decr,
 	.progress		= maple_progress,
-	.idle_loop		= native_idle,
+	.power_save		= power4_idle,
 #ifdef CONFIG_KEXEC
 	.machine_kexec		= default_machine_kexec,
 	.machine_kexec_prepare	= default_machine_kexec_prepare,
diff --git a/arch/powerpc/platforms/powermac/bootx_init.c b/arch/powerpc/platforms/powermac/bootx_init.c
index fa8b4d7b5de..eacbfd9beab 100644
--- a/arch/powerpc/platforms/powermac/bootx_init.c
+++ b/arch/powerpc/platforms/powermac/bootx_init.c
@@ -161,9 +161,7 @@ static void __init bootx_dt_add_prop(char *name, void *data, int size,
 static void __init bootx_add_chosen_props(unsigned long base,
 					  unsigned long *mem_end)
 {
-	u32 val = _MACH_Pmac;
-
-	bootx_dt_add_prop("linux,platform", &val, 4, mem_end);
+	u32 val;
 
 	if (bootx_info->kernelParamsOffset) {
 		char *args = (char *)((unsigned long)bootx_info) +
@@ -493,7 +491,7 @@ void __init bootx_init(unsigned long r3, unsigned long r4)
 		    && (strcmp(model, "iMac,1") == 0
 			|| strcmp(model, "PowerMac1,1") == 0)) {
 			bootx_printf("iMac,1 detected, shutting down USB \n");
-			out_le32((unsigned *)0x80880008, 1);	/* XXX */
+			out_le32((unsigned __iomem *)0x80880008, 1);	/* XXX */
 		}
 	}
 
diff --git a/arch/powerpc/platforms/powermac/feature.c b/arch/powerpc/platforms/powermac/feature.c
index e49eddd5042..a5063cd675c 100644
--- a/arch/powerpc/platforms/powermac/feature.c
+++ b/arch/powerpc/platforms/powermac/feature.c
@@ -2951,7 +2951,7 @@ static void *pmac_early_vresume_data;
 
 void pmac_set_early_video_resume(void (*proc)(void *data), void *data)
 {
-	if (_machine != _MACH_Pmac)
+	if (!machine_is(powermac))
 		return;
 	preempt_disable();
 	pmac_early_vresume_proc = proc;
diff --git a/arch/powerpc/platforms/powermac/low_i2c.c b/arch/powerpc/platforms/powermac/low_i2c.c
index 87eb6bb7f0e..e14f9ac55cf 100644
--- a/arch/powerpc/platforms/powermac/low_i2c.c
+++ b/arch/powerpc/platforms/powermac/low_i2c.c
@@ -1457,6 +1457,9 @@ int __init pmac_i2c_init(void)
 		return 0;
 	i2c_inited = 1;
 
+	if (!machine_is(powermac))
+		return 0;
+
 	/* Probe keywest-i2c busses */
 	kw_i2c_probe();
 
diff --git a/arch/powerpc/platforms/powermac/nvram.c b/arch/powerpc/platforms/powermac/nvram.c
index 5fd28995c74..262f967b880 100644
--- a/arch/powerpc/platforms/powermac/nvram.c
+++ b/arch/powerpc/platforms/powermac/nvram.c
@@ -74,7 +74,7 @@ struct core99_header {
  * Read and write the non-volatile RAM on PowerMacs and CHRP machines.
  */
 static int nvram_naddrs;
-static volatile unsigned char *nvram_data;
+static volatile unsigned char __iomem *nvram_data;
 static int is_core_99;
 static int core99_bank = 0;
 static int nvram_partitions[3];
@@ -148,7 +148,7 @@ static ssize_t core99_nvram_size(void)
 }
 
 #ifdef CONFIG_PPC32
-static volatile unsigned char *nvram_addr;
+static volatile unsigned char __iomem *nvram_addr;
 static int nvram_mult;
 
 static unsigned char direct_nvram_read_byte(int addr)
@@ -285,7 +285,7 @@ static int sm_erase_bank(int bank)
 	int stat, i;
 	unsigned long timeout;
 
-	u8* base = (u8 *)nvram_data + core99_bank*NVRAM_SIZE;
+	u8 __iomem *base = (u8 __iomem *)nvram_data + core99_bank*NVRAM_SIZE;
 
        	DBG("nvram: Sharp/Micron Erasing bank %d...\n", bank);
 
@@ -317,7 +317,7 @@ static int sm_write_bank(int bank, u8* datas)
 	int i, stat = 0;
 	unsigned long timeout;
 
-	u8* base = (u8 *)nvram_data + core99_bank*NVRAM_SIZE;
+	u8 __iomem *base = (u8 __iomem *)nvram_data + core99_bank*NVRAM_SIZE;
 
        	DBG("nvram: Sharp/Micron Writing bank %d...\n", bank);
 
@@ -352,7 +352,7 @@ static int amd_erase_bank(int bank)
 	int i, stat = 0;
 	unsigned long timeout;
 
-	u8* base = (u8 *)nvram_data + core99_bank*NVRAM_SIZE;
+	u8 __iomem *base = (u8 __iomem *)nvram_data + core99_bank*NVRAM_SIZE;
 
        	DBG("nvram: AMD Erasing bank %d...\n", bank);
 
@@ -399,7 +399,7 @@ static int amd_write_bank(int bank, u8* datas)
 	int i, stat = 0;
 	unsigned long timeout;
 
-	u8* base = (u8 *)nvram_data + core99_bank*NVRAM_SIZE;
+	u8 __iomem *base = (u8 __iomem *)nvram_data + core99_bank*NVRAM_SIZE;
 
        	DBG("nvram: AMD Writing bank %d...\n", bank);
 
@@ -597,7 +597,7 @@ int __init pmac_nvram_init(void)
 	}
 
 #ifdef CONFIG_PPC32
-	if (_machine == _MACH_chrp && nvram_naddrs == 1) {
+	if (machine_is(chrp) && nvram_naddrs == 1) {
 		nvram_data = ioremap(r1.start, s1);
 		nvram_mult = 1;
 		ppc_md.nvram_read_val	= direct_nvram_read_byte;
diff --git a/arch/powerpc/platforms/powermac/pci.c b/arch/powerpc/platforms/powermac/pci.c
index de3f30e6b33..f5d8d15d74f 100644
--- a/arch/powerpc/platforms/powermac/pci.c
+++ b/arch/powerpc/platforms/powermac/pci.c
@@ -1201,7 +1201,7 @@ void __init pmac_pcibios_after_init(void)
 #ifdef CONFIG_PPC32
 void pmac_pci_fixup_cardbus(struct pci_dev* dev)
 {
-	if (_machine != _MACH_Pmac)
+	if (!machine_is(powermac))
 		return;
 	/*
 	 * Fix the interrupt routing on the various cardbus bridges
@@ -1244,8 +1244,9 @@ void pmac_pci_fixup_pciata(struct pci_dev* dev)
         * On PowerMacs, we try to switch any PCI ATA controller to
 	* fully native mode
         */
-	if (_machine != _MACH_Pmac)
+	if (!machine_is(powermac))
 		return;
+
 	/* Some controllers don't have the class IDE */
 	if (dev->vendor == PCI_VENDOR_ID_PROMISE)
 		switch(dev->device) {
diff --git a/arch/powerpc/platforms/powermac/pfunc_base.c b/arch/powerpc/platforms/powermac/pfunc_base.c
index 9b7150f1041..a3bd3e728fa 100644
--- a/arch/powerpc/platforms/powermac/pfunc_base.c
+++ b/arch/powerpc/platforms/powermac/pfunc_base.c
@@ -336,6 +336,8 @@ int __init pmac_pfunc_base_install(void)
 		return 0;
 	pfbase_inited = 1;
 
+	if (!machine_is(powermac))
+		return 0;
 
 	DBG("Installing base platform functions...\n");
 
diff --git a/arch/powerpc/platforms/powermac/setup.c b/arch/powerpc/platforms/powermac/setup.c
index 385aab90c4d..4d15e396655 100644
--- a/arch/powerpc/platforms/powermac/setup.c
+++ b/arch/powerpc/platforms/powermac/setup.c
@@ -350,6 +350,13 @@ static void __init pmac_setup_arch(void)
 		smp_ops = &psurge_smp_ops;
 #endif
 #endif /* CONFIG_SMP */
+
+#ifdef CONFIG_ADB
+	if (strstr(cmd_line, "adb_sync")) {
+		extern int __adb_probe_sync;
+		__adb_probe_sync = 1;
+	}
+#endif /* CONFIG_ADB */
 }
 
 char *bootpath;
@@ -576,30 +583,6 @@ pmac_halt(void)
 	pmac_power_off();
 }
 
-#ifdef CONFIG_PPC32
-void __init pmac_init(void)
-{
-	/* isa_io_base gets set in pmac_pci_init */
-	isa_mem_base = PMAC_ISA_MEM_BASE;
-	pci_dram_offset = PMAC_PCI_DRAM_OFFSET;
-	ISA_DMA_THRESHOLD = ~0L;
-	DMA_MODE_READ = 1;
-	DMA_MODE_WRITE = 2;
-
-	ppc_md = pmac_md;
-
-#if defined(CONFIG_BLK_DEV_IDE) || defined(CONFIG_BLK_DEV_IDE_MODULE)
-#ifdef CONFIG_BLK_DEV_IDE_PMAC
-        ppc_ide_md.ide_init_hwif	= pmac_ide_init_hwif_ports;
-        ppc_ide_md.default_io_base	= pmac_ide_get_base;
-#endif /* CONFIG_BLK_DEV_IDE_PMAC */
-#endif /* defined(CONFIG_BLK_DEV_IDE) || defined(CONFIG_BLK_DEV_IDE_MODULE) */
-
-	if (ppc_md.progress) ppc_md.progress("pmac_init(): exit", 0);
-
-}
-#endif
-
 /* 
  * Early initialization.
  */
@@ -646,6 +629,12 @@ static int __init pmac_declare_of_platform_devices(void)
 {
 	struct device_node *np;
 
+	if (machine_is(chrp))
+		return -1;
+
+	if (!machine_is(powermac))
+		return 0;
+
 	np = of_find_node_by_name(NULL, "valkyrie");
 	if (np)
 		of_platform_device_create(np, "valkyrie", NULL);
@@ -666,12 +655,15 @@ device_initcall(pmac_declare_of_platform_devices);
 /*
  * Called very early, MMU is off, device-tree isn't unflattened
  */
-static int __init pmac_probe(int platform)
+static int __init pmac_probe(void)
 {
-#ifdef CONFIG_PPC64
-	if (platform != PLATFORM_POWERMAC)
+	unsigned long root = of_get_flat_dt_root();
+
+	if (!of_flat_dt_is_compatible(root, "Power Macintosh") &&
+	    !of_flat_dt_is_compatible(root, "MacRISC"))
 		return 0;
 
+#ifdef CONFIG_PPC64
 	/*
 	 * On U3, the DART (iommu) must be allocated now since it
 	 * has an impact on htab_initialize (due to the large page it
@@ -681,6 +673,23 @@ static int __init pmac_probe(int platform)
 	alloc_dart_table();
 #endif
 
+#ifdef CONFIG_PPC32
+	/* isa_io_base gets set in pmac_pci_init */
+	isa_mem_base = PMAC_ISA_MEM_BASE;
+	pci_dram_offset = PMAC_PCI_DRAM_OFFSET;
+	ISA_DMA_THRESHOLD = ~0L;
+	DMA_MODE_READ = 1;
+	DMA_MODE_WRITE = 2;
+
+#if defined(CONFIG_BLK_DEV_IDE) || defined(CONFIG_BLK_DEV_IDE_MODULE)
+#ifdef CONFIG_BLK_DEV_IDE_PMAC
+        ppc_ide_md.ide_init_hwif	= pmac_ide_init_hwif_ports;
+        ppc_ide_md.default_io_base	= pmac_ide_get_base;
+#endif /* CONFIG_BLK_DEV_IDE_PMAC */
+#endif /* defined(CONFIG_BLK_DEV_IDE) || defined(CONFIG_BLK_DEV_IDE_MODULE) */
+
+#endif /* CONFIG_PPC32 */
+
 #ifdef CONFIG_PMAC_SMU
 	/*
 	 * SMU based G5s need some memory below 2Gb, at least the current
@@ -709,10 +718,8 @@ static int pmac_pci_probe_mode(struct pci_bus *bus)
 }
 #endif
 
-struct machdep_calls __initdata pmac_md = {
-#if defined(CONFIG_HOTPLUG_CPU) && defined(CONFIG_PPC64)
-	.cpu_die		= generic_mach_cpu_die,
-#endif
+define_machine(powermac) {
+	.name			= "PowerMac",
 	.probe			= pmac_probe,
 	.setup_arch		= pmac_setup_arch,
 	.init_early		= pmac_init_early,
@@ -733,7 +740,7 @@ struct machdep_calls __initdata pmac_md = {
 	.progress		= udbg_progress,
 #ifdef CONFIG_PPC64
 	.pci_probe_mode		= pmac_pci_probe_mode,
-	.idle_loop		= native_idle,
+	.power_save		= power4_idle,
 	.enable_pmcs		= power4_enable_pmcs,
 #ifdef CONFIG_KEXEC
 	.machine_kexec		= default_machine_kexec,
@@ -746,4 +753,7 @@ struct machdep_calls __initdata pmac_md = {
 	.pcibios_after_init	= pmac_pcibios_after_init,
 	.phys_mem_access_prot	= pci_phys_mem_access_prot,
 #endif
+#if defined(CONFIG_HOTPLUG_CPU) && defined(CONFIG_PPC64)
+	.cpu_die		= generic_mach_cpu_die,
+#endif
 };
diff --git a/arch/powerpc/platforms/powermac/time.c b/arch/powerpc/platforms/powermac/time.c
index 5d9afa1fa02..890758aa966 100644
--- a/arch/powerpc/platforms/powermac/time.c
+++ b/arch/powerpc/platforms/powermac/time.c
@@ -336,10 +336,10 @@ static struct pmu_sleep_notifier time_sleep_notifier = {
  */
 void __init pmac_calibrate_decr(void)
 {
-#ifdef CONFIG_PM
+#if defined(CONFIG_PM) && defined(CONFIG_ADB_PMU)
 	/* XXX why here? */
 	pmu_register_sleep_notifier(&time_sleep_notifier);
-#endif /* CONFIG_PM */
+#endif
 
 	generic_calibrate_decr();
 
diff --git a/arch/powerpc/platforms/powermac/udbg_scc.c b/arch/powerpc/platforms/powermac/udbg_scc.c
index c4352a8db64..b4fa9f03b46 100644
--- a/arch/powerpc/platforms/powermac/udbg_scc.c
+++ b/arch/powerpc/platforms/powermac/udbg_scc.c
@@ -116,7 +116,7 @@ void udbg_scc_init(int force_scc)
 	/* Setup for 57600 8N1 */
 	if (ch == ch_a)
 		addr += 0x20;
-	sccc = (volatile u8 * __iomem) ioremap(addr & PAGE_MASK, PAGE_SIZE) ;
+	sccc = ioremap(addr & PAGE_MASK, PAGE_SIZE) ;
 	sccc += addr & ~PAGE_MASK;
 	sccd = sccc + 0x10;
 
diff --git a/arch/powerpc/platforms/pseries/eeh.c b/arch/powerpc/platforms/pseries/eeh.c
index 2ab9dcdfb41..32eaddfa547 100644
--- a/arch/powerpc/platforms/pseries/eeh.c
+++ b/arch/powerpc/platforms/pseries/eeh.c
@@ -865,7 +865,7 @@ void __init eeh_init(void)
  * on the CEC architecture, type of the device, on earlier boot
  * command-line arguments & etc.
  */
-void eeh_add_device_early(struct device_node *dn)
+static void eeh_add_device_early(struct device_node *dn)
 {
 	struct pci_controller *phb;
 	struct eeh_early_enable_info info;
@@ -882,7 +882,6 @@ void eeh_add_device_early(struct device_node *dn)
 	info.buid_lo = BUID_LO(phb->buid);
 	early_enable_eeh(dn, &info);
 }
-EXPORT_SYMBOL_GPL(eeh_add_device_early);
 
 void eeh_add_device_tree_early(struct device_node *dn)
 {
@@ -893,20 +892,6 @@ void eeh_add_device_tree_early(struct device_node *dn)
 }
 EXPORT_SYMBOL_GPL(eeh_add_device_tree_early);
 
-void eeh_add_device_tree_late(struct pci_bus *bus)
-{
-	struct pci_dev *dev;
-
-	list_for_each_entry(dev, &bus->devices, bus_list) {
- 		eeh_add_device_late(dev);
- 		if (dev->hdr_type == PCI_HEADER_TYPE_BRIDGE) {
- 			struct pci_bus *subbus = dev->subordinate;
- 			if (subbus)
- 				eeh_add_device_tree_late(subbus);
- 		}
-	}
-}
-
 /**
  * eeh_add_device_late - perform EEH initialization for the indicated pci device
  * @dev: pci device for which to set up EEH
@@ -914,7 +899,7 @@ void eeh_add_device_tree_late(struct pci_bus *bus)
  * This routine must be used to complete EEH initialization for PCI
  * devices that were added after system boot (e.g. hotplug, dlpar).
  */
-void eeh_add_device_late(struct pci_dev *dev)
+static void eeh_add_device_late(struct pci_dev *dev)
 {
 	struct device_node *dn;
 	struct pci_dn *pdn;
@@ -933,16 +918,33 @@ void eeh_add_device_late(struct pci_dev *dev)
 
 	pci_addr_cache_insert_device (dev);
 }
-EXPORT_SYMBOL_GPL(eeh_add_device_late);
+
+void eeh_add_device_tree_late(struct pci_bus *bus)
+{
+	struct pci_dev *dev;
+
+	list_for_each_entry(dev, &bus->devices, bus_list) {
+ 		eeh_add_device_late(dev);
+ 		if (dev->hdr_type == PCI_HEADER_TYPE_BRIDGE) {
+ 			struct pci_bus *subbus = dev->subordinate;
+ 			if (subbus)
+ 				eeh_add_device_tree_late(subbus);
+ 		}
+	}
+}
+EXPORT_SYMBOL_GPL(eeh_add_device_tree_late);
 
 /**
  * eeh_remove_device - undo EEH setup for the indicated pci device
  * @dev: pci device to be removed
  *
- * This routine should be when a device is removed from a running
- * system (e.g. by hotplug or dlpar).
+ * This routine should be called when a device is removed from
+ * a running system (e.g. by hotplug or dlpar).  It unregisters
+ * the PCI device from the EEH subsystem.  I/O errors affecting
+ * this device will no longer be detected after this call; thus,
+ * i/o errors affecting this slot may leave this device unusable.
  */
-void eeh_remove_device(struct pci_dev *dev)
+static void eeh_remove_device(struct pci_dev *dev)
 {
 	struct device_node *dn;
 	if (!dev || !eeh_subsystem_enabled)
@@ -955,24 +957,22 @@ void eeh_remove_device(struct pci_dev *dev)
 	pci_addr_cache_remove_device(dev);
 
 	dn = pci_device_to_OF_node(dev);
-	PCI_DN(dn)->pcidev = NULL;
-	pci_dev_put (dev);
+	if (PCI_DN(dn)->pcidev) {
+		PCI_DN(dn)->pcidev = NULL;
+		pci_dev_put (dev);
+	}
 }
-EXPORT_SYMBOL_GPL(eeh_remove_device);
 
 void eeh_remove_bus_device(struct pci_dev *dev)
 {
+	struct pci_bus *bus = dev->subordinate;
+	struct pci_dev *child, *tmp;
+
 	eeh_remove_device(dev);
-	if (dev->hdr_type == PCI_HEADER_TYPE_BRIDGE) {
-		struct pci_bus *bus = dev->subordinate;
-		struct list_head *ln;
-		if (!bus)
-			return; 
-		for (ln = bus->devices.next; ln != &bus->devices; ln = ln->next) {
-			struct pci_dev *pdev = pci_dev_b(ln);
-			if (pdev)
-				eeh_remove_bus_device(pdev);
-		}
+
+	if (bus && dev->hdr_type == PCI_HEADER_TYPE_BRIDGE) {
+		list_for_each_entry_safe(child, tmp, &bus->devices, bus_list)
+			 eeh_remove_bus_device(child);
 	}
 }
 EXPORT_SYMBOL_GPL(eeh_remove_bus_device);
@@ -1018,7 +1018,7 @@ static int __init eeh_init_proc(void)
 {
 	struct proc_dir_entry *e;
 
-	if (platform_is_pseries()) {
+	if (machine_is(pseries)) {
 		e = create_proc_entry("ppc64/eeh", 0, NULL);
 		if (e)
 			e->proc_fops = &proc_eeh_operations;
diff --git a/arch/powerpc/platforms/pseries/eeh_driver.c b/arch/powerpc/platforms/pseries/eeh_driver.c
index b811d5ff92f..1fba695e32e 100644
--- a/arch/powerpc/platforms/pseries/eeh_driver.c
+++ b/arch/powerpc/platforms/pseries/eeh_driver.c
@@ -257,6 +257,7 @@ void handle_eeh_events (struct eeh_event *event)
 	struct pci_bus *frozen_bus;
 	int rc = 0;
 	enum pci_ers_result result = PCI_ERS_RESULT_NONE;
+	const char *pci_str, *drv_str;
 
 	frozen_dn = find_device_pe(event->dn);
 	frozen_bus = pcibios_find_pci_bus(frozen_dn);
@@ -291,9 +292,17 @@ void handle_eeh_events (struct eeh_event *event)
 
 	frozen_pdn = PCI_DN(frozen_dn);
 	frozen_pdn->eeh_freeze_count++;
+
+	if (frozen_pdn->pcidev) {
+		pci_str = pci_name (frozen_pdn->pcidev);
+		drv_str = pcid_name (frozen_pdn->pcidev);
+	} else {
+		pci_str = pci_name (event->dev);
+		drv_str = pcid_name (event->dev);
+	}
 	
 	if (frozen_pdn->eeh_freeze_count > EEH_MAX_ALLOWED_FREEZES)
-		goto hard_fail;
+		goto excess_failures;
 
 	/* If the reset state is a '5' and the time to reset is 0 (infinity)
 	 * or is more then 15 seconds, then mark this as a permanent failure.
@@ -306,9 +315,7 @@ void handle_eeh_events (struct eeh_event *event)
 	eeh_slot_error_detail(frozen_pdn, 1 /* Temporary Error */);
 	printk(KERN_WARNING
 	   "EEH: This PCI device has failed %d times since last reboot: %s - %s\n",
-		frozen_pdn->eeh_freeze_count,
-		pci_name (frozen_pdn->pcidev), 
-		pcid_name(frozen_pdn->pcidev));
+		frozen_pdn->eeh_freeze_count, drv_str, pci_str);
 
 	/* Walk the various device drivers attached to this slot through
 	 * a reset sequence, giving each an opportunity to do what it needs
@@ -350,7 +357,7 @@ void handle_eeh_events (struct eeh_event *event)
 
 	return;
 	
-hard_fail:
+excess_failures:
 	/*
 	 * About 90% of all real-life EEH failures in the field
 	 * are due to poorly seated PCI cards. Only 10% or so are
@@ -360,10 +367,16 @@ hard_fail:
 	   "EEH: PCI device %s - %s has failed %d times \n"
 	   "and has been permanently disabled.  Please try reseating\n"
 	   "this device or replacing it.\n",
-		pci_name (frozen_pdn->pcidev), 
-		pcid_name(frozen_pdn->pcidev), 
-		frozen_pdn->eeh_freeze_count);
+		drv_str, pci_str, frozen_pdn->eeh_freeze_count);
+	goto perm_error;
+
+hard_fail:
+	printk(KERN_ERR
+	   "EEH: Unable to recover from failure of PCI device %s - %s\n"
+	   "Please try reseating this device or replacing it.\n",
+		drv_str, pci_str);
 
+perm_error:
 	eeh_slot_error_detail(frozen_pdn, 2 /* Permanent Error */);
 
 	/* Notify all devices that they're about to go down. */
diff --git a/arch/powerpc/platforms/pseries/eeh_event.c b/arch/powerpc/platforms/pseries/eeh_event.c
index 9a9961f2748..a1bda6f96fd 100644
--- a/arch/powerpc/platforms/pseries/eeh_event.c
+++ b/arch/powerpc/platforms/pseries/eeh_event.c
@@ -19,7 +19,9 @@
  */
 
 #include <linux/list.h>
+#include <linux/mutex.h>
 #include <linux/pci.h>
+#include <linux/workqueue.h>
 #include <asm/eeh_event.h>
 #include <asm/ppc-pci.h>
 
@@ -37,14 +39,18 @@ LIST_HEAD(eeh_eventlist);
 static void eeh_thread_launcher(void *);
 DECLARE_WORK(eeh_event_wq, eeh_thread_launcher, NULL);
 
+/* Serialize reset sequences for a given pci device */
+DEFINE_MUTEX(eeh_event_mutex);
+
 /**
- * eeh_event_handler - dispatch EEH events.  The detection of a frozen
- * slot can occur inside an interrupt, where it can be hard to do
- * anything about it.  The goal of this routine is to pull these
- * detection events out of the context of the interrupt handler, and
- * re-dispatch them for processing at a later time in a normal context.
- *
+ * eeh_event_handler - dispatch EEH events.
  * @dummy - unused
+ *
+ * The detection of a frozen slot can occur inside an interrupt,
+ * where it can be hard to do anything about it.  The goal of this
+ * routine is to pull these detection events out of the context
+ * of the interrupt handler, and re-dispatch them for processing
+ * at a later time in a normal context.
  */
 static int eeh_event_handler(void * dummy)
 {
@@ -64,23 +70,24 @@ static int eeh_event_handler(void * dummy)
 			event = list_entry(eeh_eventlist.next, struct eeh_event, list);
 			list_del(&event->list);
 		}
-		
-		if (event)
-			eeh_mark_slot(event->dn, EEH_MODE_RECOVERING);
-
 		spin_unlock_irqrestore(&eeh_eventlist_lock, flags);
+
 		if (event == NULL)
 			break;
 
+		/* Serialize processing of EEH events */
+		mutex_lock(&eeh_event_mutex);
+		eeh_mark_slot(event->dn, EEH_MODE_RECOVERING);
+
 		printk(KERN_INFO "EEH: Detected PCI bus error on device %s\n",
 		       pci_name(event->dev));
 
 		handle_eeh_events(event);
 
 		eeh_clear_slot(event->dn, EEH_MODE_RECOVERING);
-
 		pci_dev_put(event->dev);
 		kfree(event);
+		mutex_unlock(&eeh_event_mutex);
 	}
 
 	return 0;
@@ -88,7 +95,6 @@ static int eeh_event_handler(void * dummy)
 
 /**
  * eeh_thread_launcher
- *
  * @dummy - unused
  */
 static void eeh_thread_launcher(void *dummy)
diff --git a/arch/powerpc/platforms/pseries/firmware.c b/arch/powerpc/platforms/pseries/firmware.c
index 989f4bc136c..c01d8f0cbe6 100644
--- a/arch/powerpc/platforms/pseries/firmware.c
+++ b/arch/powerpc/platforms/pseries/firmware.c
@@ -91,7 +91,7 @@ void __init fw_feature_init(void)
 				continue;
 
 			/* we have a match */
-			ppc64_firmware_features |=
+			powerpc_firmware_features |=
 				firmware_features_table[i].val;
 			break;
 		}
diff --git a/arch/powerpc/platforms/pseries/hvCall.S b/arch/powerpc/platforms/pseries/hvCall.S
index db7c19fe929..c9ff547f9d2 100644
--- a/arch/powerpc/platforms/pseries/hvCall.S
+++ b/arch/powerpc/platforms/pseries/hvCall.S
@@ -127,3 +127,103 @@ _GLOBAL(plpar_hcall_4out)
 
 	mtcrf	0xff,r0
 	blr				/* return r3 = status */
+
+/* plpar_hcall_7arg_7ret(unsigned long opcode,		R3
+			 unsigned long arg1,		R4
+			 unsigned long arg2,		R5
+			 unsigned long arg3,		R6
+			 unsigned long arg4,		R7
+			 unsigned long arg5,		R8
+			 unsigned long arg6,		R9
+			 unsigned long arg7,		R10
+			 unsigned long *out1,		112(R1)
+			 unsigned long *out2,		110(R1)
+			 unsigned long *out3,		108(R1)
+			 unsigned long *out4,		106(R1)
+			 unsigned long *out5,		104(R1)
+			 unsigned long *out6,		102(R1)
+			 unsigned long *out7);		100(R1)
+*/
+_GLOBAL(plpar_hcall_7arg_7ret)
+	HMT_MEDIUM
+
+	mfcr	r0
+	stw	r0,8(r1)
+
+	HVSC				/* invoke the hypervisor */
+
+	lwz	r0,8(r1)
+
+	ld	r11,STK_PARM(r11)(r1)	/* Fetch r4 ret arg */
+	std	r4,0(r11)
+	ld	r11,STK_PARM(r12)(r1)	/* Fetch r5 ret arg */
+	std	r5,0(r11)
+	ld	r11,STK_PARM(r13)(r1)	/* Fetch r6 ret arg */
+	std	r6,0(r11)
+	ld	r11,STK_PARM(r14)(r1)	/* Fetch r7 ret arg */
+	std	r7,0(r11)
+	ld	r11,STK_PARM(r15)(r1)	/* Fetch r8 ret arg */
+	std	r8,0(r11)
+	ld	r11,STK_PARM(r16)(r1)	/* Fetch r9 ret arg */
+	std	r9,0(r11)
+	ld	r11,STK_PARM(r17)(r1)	/* Fetch r10 ret arg */
+	std	r10,0(r11)
+
+	mtcrf	0xff,r0
+
+	blr				/* return r3 = status */
+
+/* plpar_hcall_9arg_9ret(unsigned long opcode,		R3
+			 unsigned long arg1,		R4
+			 unsigned long arg2,		R5
+			 unsigned long arg3,		R6
+			 unsigned long arg4,		R7
+			 unsigned long arg5,		R8
+			 unsigned long arg6,		R9
+			 unsigned long arg7,		R10
+			 unsigned long arg8,		112(R1)
+			 unsigned long arg9,		110(R1)
+			 unsigned long *out1,		108(R1)
+			 unsigned long *out2,		106(R1)
+			 unsigned long *out3,		104(R1)
+			 unsigned long *out4,		102(R1)
+			 unsigned long *out5,		100(R1)
+			 unsigned long *out6,		 98(R1)
+			 unsigned long *out7);		 96(R1)
+			 unsigned long *out8,		 94(R1)
+		         unsigned long *out9,            92(R1)
+*/
+_GLOBAL(plpar_hcall_9arg_9ret)
+	HMT_MEDIUM
+
+	mfcr	r0
+	stw	r0,8(r1)
+
+	ld	r11,STK_PARM(r11)(r1)	 /* put arg8 in R11 */
+	ld	r12,STK_PARM(r12)(r1)    /* put arg9 in R12 */
+
+	HVSC				/* invoke the hypervisor */
+
+	ld	r0,STK_PARM(r13)(r1)	/* Fetch r4 ret arg */
+	stdx	r4,r0,r0
+	ld	r0,STK_PARM(r14)(r1)	/* Fetch r5 ret arg */
+	stdx	r5,r0,r0
+	ld	r0,STK_PARM(r15)(r1)	/* Fetch r6 ret arg */
+	stdx	r6,r0,r0
+	ld	r0,STK_PARM(r16)(r1)	/* Fetch r7 ret arg */
+	stdx	r7,r0,r0
+	ld	r0,STK_PARM(r17)(r1)	/* Fetch r8 ret arg */
+	stdx	r8,r0,r0
+	ld	r0,STK_PARM(r18)(r1)	/* Fetch r9 ret arg */
+	stdx	r9,r0,r0
+	ld	r0,STK_PARM(r19)(r1)	/* Fetch r10 ret arg */
+	stdx	r10,r0,r0
+	ld	r0,STK_PARM(r20)(r1)	/* Fetch r11 ret arg */
+	stdx	r11,r0,r0
+	ld	r0,STK_PARM(r21)(r1)	/* Fetch r12 ret arg */
+	stdx	r12,r0,r0
+
+	lwz	r0,8(r1)
+	mtcrf	0xff,r0
+
+	blr				/* return r3 = status */
diff --git a/arch/powerpc/platforms/pseries/hvconsole.c b/arch/powerpc/platforms/pseries/hvconsole.c
index 138e128a388..a72a987f1d4 100644
--- a/arch/powerpc/platforms/pseries/hvconsole.c
+++ b/arch/powerpc/platforms/pseries/hvconsole.c
@@ -41,7 +41,7 @@ int hvc_get_chars(uint32_t vtermno, char *buf, int count)
 	unsigned long got;
 
 	if (plpar_hcall(H_GET_TERM_CHAR, vtermno, 0, 0, 0, &got,
-		(unsigned long *)buf, (unsigned long *)buf+1) == H_Success)
+		(unsigned long *)buf, (unsigned long *)buf+1) == H_SUCCESS)
 		return got;
 	return 0;
 }
@@ -62,11 +62,16 @@ int hvc_put_chars(uint32_t vtermno, const char *buf, int count)
 	unsigned long *lbuf = (unsigned long *) buf;
 	long ret;
 
+
+	/* hcall will ret H_PARAMETER if 'count' exceeds firmware max.*/
+	if (count > MAX_VIO_PUT_CHARS)
+		count = MAX_VIO_PUT_CHARS;
+
 	ret = plpar_hcall_norets(H_PUT_TERM_CHAR, vtermno, count, lbuf[0],
 				 lbuf[1]);
-	if (ret == H_Success)
+	if (ret == H_SUCCESS)
 		return count;
-	if (ret == H_Busy)
+	if (ret == H_BUSY)
 		return 0;
 	return -EIO;
 }
diff --git a/arch/powerpc/platforms/pseries/hvcserver.c b/arch/powerpc/platforms/pseries/hvcserver.c
index 22bfb5c89db..fcf4b4cbeaf 100644
--- a/arch/powerpc/platforms/pseries/hvcserver.c
+++ b/arch/powerpc/platforms/pseries/hvcserver.c
@@ -43,21 +43,21 @@ MODULE_VERSION(HVCS_ARCH_VERSION);
 static int hvcs_convert(long to_convert)
 {
 	switch (to_convert) {
-		case H_Success:
+		case H_SUCCESS:
 			return 0;
-		case H_Parameter:
+		case H_PARAMETER:
 			return -EINVAL;
-		case H_Hardware:
+		case H_HARDWARE:
 			return -EIO;
-		case H_Busy:
-		case H_LongBusyOrder1msec:
-		case H_LongBusyOrder10msec:
-		case H_LongBusyOrder100msec:
-		case H_LongBusyOrder1sec:
-		case H_LongBusyOrder10sec:
-		case H_LongBusyOrder100sec:
+		case H_BUSY:
+		case H_LONG_BUSY_ORDER_1_MSEC:
+		case H_LONG_BUSY_ORDER_10_MSEC:
+		case H_LONG_BUSY_ORDER_100_MSEC:
+		case H_LONG_BUSY_ORDER_1_SEC:
+		case H_LONG_BUSY_ORDER_10_SEC:
+		case H_LONG_BUSY_ORDER_100_SEC:
 			return -EBUSY;
-		case H_Function: /* fall through */
+		case H_FUNCTION: /* fall through */
 		default:
 			return -EPERM;
 	}
diff --git a/arch/powerpc/platforms/pseries/lpar.c b/arch/powerpc/platforms/pseries/lpar.c
index 8952528d31a..634b7d06d3c 100644
--- a/arch/powerpc/platforms/pseries/lpar.c
+++ b/arch/powerpc/platforms/pseries/lpar.c
@@ -54,7 +54,8 @@ EXPORT_SYMBOL(plpar_hcall);
 EXPORT_SYMBOL(plpar_hcall_4out);
 EXPORT_SYMBOL(plpar_hcall_norets);
 EXPORT_SYMBOL(plpar_hcall_8arg_2ret);
-
+EXPORT_SYMBOL(plpar_hcall_7arg_7ret);
+EXPORT_SYMBOL(plpar_hcall_9arg_9ret);
 extern void pSeries_find_serial_port(void);
 
 
@@ -72,7 +73,7 @@ static void udbg_hvsi_putc(char c)
 
 	do {
 		rc = plpar_put_term_char(vtermno, sizeof(packet), packet);
-	} while (rc == H_Busy);
+	} while (rc == H_BUSY);
 }
 
 static long hvsi_udbg_buf_len;
@@ -85,7 +86,7 @@ static int udbg_hvsi_getc_poll(void)
 
 	if (hvsi_udbg_buf_len == 0) {
 		rc = plpar_get_term_char(vtermno, &hvsi_udbg_buf_len, hvsi_udbg_buf);
-		if (rc != H_Success || hvsi_udbg_buf[0] != 0xff) {
+		if (rc != H_SUCCESS || hvsi_udbg_buf[0] != 0xff) {
 			/* bad read or non-data packet */
 			hvsi_udbg_buf_len = 0;
 		} else {
@@ -139,7 +140,7 @@ static void udbg_putcLP(char c)
 	buf[0] = c;
 	do {
 		rc = plpar_put_term_char(vtermno, 1, buf);
-	} while(rc == H_Busy);
+	} while(rc == H_BUSY);
 }
 
 /* Buffered chars getc */
@@ -158,7 +159,7 @@ static int udbg_getc_pollLP(void)
 		/* get some more chars. */
 		inbuflen = 0;
 		rc = plpar_get_term_char(vtermno, &inbuflen, buf);
-		if (rc != H_Success)
+		if (rc != H_SUCCESS)
 			inbuflen = 0;	/* otherwise inbuflen is garbage */
 	}
 	if (inbuflen <= 0 || inbuflen > 16) {
@@ -304,7 +305,7 @@ long pSeries_lpar_hpte_insert(unsigned long hpte_group,
 
 	lpar_rc = plpar_hcall(H_ENTER, flags, hpte_group, hpte_v,
 			      hpte_r, &slot, &dummy0, &dummy1);
-	if (unlikely(lpar_rc == H_PTEG_Full)) {
+	if (unlikely(lpar_rc == H_PTEG_FULL)) {
 		if (!(vflags & HPTE_V_BOLTED))
 			DBG_LOW(" full\n");
 		return -1;
@@ -315,7 +316,7 @@ long pSeries_lpar_hpte_insert(unsigned long hpte_group,
 	 * will fail. However we must catch the failure in hash_page
 	 * or we will loop forever, so return -2 in this case.
 	 */
-	if (unlikely(lpar_rc != H_Success)) {
+	if (unlikely(lpar_rc != H_SUCCESS)) {
 		if (!(vflags & HPTE_V_BOLTED))
 			DBG_LOW(" lpar err %d\n", lpar_rc);
 		return -2;
@@ -346,9 +347,9 @@ static long pSeries_lpar_hpte_remove(unsigned long hpte_group)
 		/* don't remove a bolted entry */
 		lpar_rc = plpar_pte_remove(H_ANDCOND, hpte_group + slot_offset,
 					   (0x1UL << 4), &dummy1, &dummy2);
-		if (lpar_rc == H_Success)
+		if (lpar_rc == H_SUCCESS)
 			return i;
-		BUG_ON(lpar_rc != H_Not_Found);
+		BUG_ON(lpar_rc != H_NOT_FOUND);
 
 		slot_offset++;
 		slot_offset &= 0x7;
@@ -391,14 +392,14 @@ static long pSeries_lpar_hpte_updatepp(unsigned long slot,
 
 	lpar_rc = plpar_pte_protect(flags, slot, want_v & HPTE_V_AVPN);
 
-	if (lpar_rc == H_Not_Found) {
+	if (lpar_rc == H_NOT_FOUND) {
 		DBG_LOW("not found !\n");
 		return -1;
 	}
 
 	DBG_LOW("ok\n");
 
-	BUG_ON(lpar_rc != H_Success);
+	BUG_ON(lpar_rc != H_SUCCESS);
 
 	return 0;
 }
@@ -417,7 +418,7 @@ static unsigned long pSeries_lpar_hpte_getword0(unsigned long slot)
 
 	lpar_rc = plpar_pte_read(flags, slot, &dword0, &dummy_word1);
 
-	BUG_ON(lpar_rc != H_Success);
+	BUG_ON(lpar_rc != H_SUCCESS);
 
 	return dword0;
 }
@@ -468,7 +469,7 @@ static void pSeries_lpar_hpte_updateboltedpp(unsigned long newpp,
 	flags = newpp & 7;
 	lpar_rc = plpar_pte_protect(flags, slot, 0);
 
-	BUG_ON(lpar_rc != H_Success);
+	BUG_ON(lpar_rc != H_SUCCESS);
 }
 
 static void pSeries_lpar_hpte_invalidate(unsigned long slot, unsigned long va,
@@ -484,10 +485,10 @@ static void pSeries_lpar_hpte_invalidate(unsigned long slot, unsigned long va,
 	want_v = hpte_encode_v(va, psize);
 	lpar_rc = plpar_pte_remove(H_AVPN, slot, want_v & HPTE_V_AVPN,
 				   &dummy1, &dummy2);
-	if (lpar_rc == H_Not_Found)
+	if (lpar_rc == H_NOT_FOUND)
 		return;
 
-	BUG_ON(lpar_rc != H_Success);
+	BUG_ON(lpar_rc != H_SUCCESS);
 }
 
 /*
diff --git a/arch/powerpc/platforms/pseries/pci.c b/arch/powerpc/platforms/pseries/pci.c
index 946ad59e335..e97e67f5e07 100644
--- a/arch/powerpc/platforms/pseries/pci.c
+++ b/arch/powerpc/platforms/pseries/pci.c
@@ -120,7 +120,7 @@ static void fixup_winbond_82c105(struct pci_dev* dev)
 	int i;
 	unsigned int reg;
 
-	if (!platform_is_pseries())
+	if (!machine_is(pseries))
 		return;
 
 	printk("Using INTC for W82c105 IDE controller.\n");
diff --git a/arch/powerpc/platforms/pseries/pci_dlpar.c b/arch/powerpc/platforms/pseries/pci_dlpar.c
index 44abdeb9ca0..6bfacc21708 100644
--- a/arch/powerpc/platforms/pseries/pci_dlpar.c
+++ b/arch/powerpc/platforms/pseries/pci_dlpar.c
@@ -28,6 +28,7 @@
 #include <linux/pci.h>
 #include <asm/pci-bridge.h>
 #include <asm/ppc-pci.h>
+#include <asm/firmware.h>
 
 static struct pci_bus *
 find_bus_among_children(struct pci_bus *bus,
@@ -152,20 +153,24 @@ pcibios_pci_config_bridge(struct pci_dev *dev)
 void
 pcibios_add_pci_devices(struct pci_bus * bus)
 {
-	int slotno, num;
+	int slotno, num, mode;
 	struct pci_dev *dev;
 	struct device_node *dn = pci_bus_to_OF_node(bus);
 
 	eeh_add_device_tree_early(dn);
 
-	if (_machine == PLATFORM_PSERIES_LPAR) {
+	mode = PCI_PROBE_NORMAL;
+	if (ppc_md.pci_probe_mode)
+		mode = ppc_md.pci_probe_mode(bus);
+
+	if (mode == PCI_PROBE_DEVTREE) {
 		/* use ofdt-based probe */
 		of_scan_bus(dn, bus);
 		if (!list_empty(&bus->devices)) {
 			pcibios_fixup_new_pci_devices(bus, 0);
 			pci_bus_add_devices(bus);
 		}
-	} else {
+	} else if (mode == PCI_PROBE_NORMAL) {
 		/* use legacy probe */
 		slotno = PCI_SLOT(PCI_DN(dn->child)->devfn);
 		num = pci_scan_slot(bus, PCI_DEVFN(slotno, 0));
diff --git a/arch/powerpc/platforms/pseries/ras.c b/arch/powerpc/platforms/pseries/ras.c
index b046bcf7443..9639c66b453 100644
--- a/arch/powerpc/platforms/pseries/ras.c
+++ b/arch/powerpc/platforms/pseries/ras.c
@@ -132,7 +132,7 @@ static int __init init_ras_IRQ(void)
 		of_node_put(np);
 	}
 
-	return 1;
+	return 0;
 }
 __initcall(init_ras_IRQ);
 
diff --git a/arch/powerpc/platforms/pseries/reconfig.c b/arch/powerpc/platforms/pseries/reconfig.c
index 5ad90676567..1773103354b 100644
--- a/arch/powerpc/platforms/pseries/reconfig.c
+++ b/arch/powerpc/platforms/pseries/reconfig.c
@@ -17,8 +17,9 @@
 #include <linux/proc_fs.h>
 
 #include <asm/prom.h>
-#include <asm/pSeries_reconfig.h>
+#include <asm/machdep.h>
 #include <asm/uaccess.h>
+#include <asm/pSeries_reconfig.h>
 
 
 
@@ -508,7 +509,7 @@ static int proc_ppc64_create_ofdt(void)
 {
 	struct proc_dir_entry *ent;
 
-	if (!platform_is_pseries())
+	if (!machine_is(pseries))
 		return 0;
 
 	ent = create_proc_entry("ppc64/ofdt", S_IWUSR, NULL);
diff --git a/arch/powerpc/platforms/pseries/rtasd.c b/arch/powerpc/platforms/pseries/rtasd.c
index a6f628d4c9d..e0000ce769e 100644
--- a/arch/powerpc/platforms/pseries/rtasd.c
+++ b/arch/powerpc/platforms/pseries/rtasd.c
@@ -27,6 +27,7 @@
 #include <asm/prom.h>
 #include <asm/nvram.h>
 #include <asm/atomic.h>
+#include <asm/machdep.h>
 
 #if 0
 #define DEBUG(A...)	printk(KERN_ERR A)
@@ -481,13 +482,13 @@ static int __init rtas_init(void)
 {
 	struct proc_dir_entry *entry;
 
-	if (!platform_is_pseries())
+	if (!machine_is(pseries))
 		return 0;
 
 	/* No RTAS */
 	if (rtas_token("event-scan") == RTAS_UNKNOWN_SERVICE) {
 		printk(KERN_INFO "rtasd: no event-scan on system\n");
-		return 1;
+		return -ENODEV;
 	}
 
 	entry = create_proc_entry("ppc64/rtas/error_log", S_IRUSR, NULL);
diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c
index 44d5c7fdcd9..5eb55ef1c91 100644
--- a/arch/powerpc/platforms/pseries/setup.c
+++ b/arch/powerpc/platforms/pseries/setup.c
@@ -81,8 +81,8 @@ extern void find_udbg_vterm(void);
 
 int fwnmi_active;  /* TRUE if an FWNMI handler is present */
 
-static void pseries_shared_idle(void);
-static void pseries_dedicated_idle(void);
+static void pseries_shared_idle_sleep(void);
+static void pseries_dedicated_idle_sleep(void);
 
 struct mpic *pSeries_mpic;
 
@@ -236,14 +236,13 @@ static void __init pSeries_setup_arch(void)
 		vpa_init(boot_cpuid);
 		if (get_lppaca()->shared_proc) {
 			printk(KERN_INFO "Using shared processor idle loop\n");
-			ppc_md.idle_loop = pseries_shared_idle;
+			ppc_md.power_save = pseries_shared_idle_sleep;
 		} else {
 			printk(KERN_INFO "Using dedicated idle loop\n");
-			ppc_md.idle_loop = pseries_dedicated_idle;
+			ppc_md.power_save = pseries_dedicated_idle_sleep;
 		}
 	} else {
 		printk(KERN_INFO "Using default idle loop\n");
-		ppc_md.idle_loop = default_idle;
 	}
 
 	if (firmware_has_feature(FW_FEATURE_LPAR))
@@ -373,156 +372,123 @@ static int pSeries_check_legacy_ioport(unsigned int baseport)
 /*
  * Called very early, MMU is off, device-tree isn't unflattened
  */
-extern struct machdep_calls pSeries_md;
 
-static int __init pSeries_probe(int platform)
+static int __init pSeries_probe_hypertas(unsigned long node,
+					 const char *uname, int depth,
+					 void *data)
 {
-	if (platform != PLATFORM_PSERIES &&
-	    platform != PLATFORM_PSERIES_LPAR)
-		return 0;
-
-	/* if we have some ppc_md fixups for LPAR to do, do
-	 * it here ...
-	 */
+	if (depth != 1 ||
+	    (strcmp(uname, "rtas") != 0 && strcmp(uname, "rtas@0") != 0))
+ 		return 0;
 
-	if (platform == PLATFORM_PSERIES_LPAR)
-		ppc64_firmware_features |= FW_FEATURE_LPAR;
+	if (of_get_flat_dt_prop(node, "ibm,hypertas-functions", NULL) != NULL)
+ 		powerpc_firmware_features |= FW_FEATURE_LPAR;
 
-	return 1;
+ 	return 1;
 }
 
-DECLARE_PER_CPU(unsigned long, smt_snooze_delay);
-
-static inline void dedicated_idle_sleep(unsigned int cpu)
+static int __init pSeries_probe(void)
 {
-	struct lppaca *plppaca = &lppaca[cpu ^ 1];
+ 	char *dtype = of_get_flat_dt_prop(of_get_flat_dt_root(),
+ 					  "device_type", NULL);
+ 	if (dtype == NULL)
+ 		return 0;
+ 	if (strcmp(dtype, "chrp"))
+		return 0;
 
-	/* Only sleep if the other thread is not idle */
-	if (!(plppaca->idle)) {
-		local_irq_disable();
+	DBG("pSeries detected, looking for LPAR capability...\n");
 
-		/*
-		 * We are about to sleep the thread and so wont be polling any
-		 * more.
-		 */
-		clear_thread_flag(TIF_POLLING_NRFLAG);
-		smp_mb__after_clear_bit();
-
-		/*
-		 * SMT dynamic mode. Cede will result in this thread going
-		 * dormant, if the partner thread is still doing work.  Thread
-		 * wakes up if partner goes idle, an interrupt is presented, or
-		 * a prod occurs.  Returning from the cede enables external
-		 * interrupts.
-		 */
-		if (!need_resched())
-			cede_processor();
-		else
-			local_irq_enable();
-		set_thread_flag(TIF_POLLING_NRFLAG);
-	} else {
-		/*
-		 * Give the HV an opportunity at the processor, since we are
-		 * not doing any work.
-		 */
-		poll_pending();
-	}
+	/* Now try to figure out if we are running on LPAR */
+	of_scan_flat_dt(pSeries_probe_hypertas, NULL);
+
+	DBG("Machine is%s LPAR !\n",
+	    (powerpc_firmware_features & FW_FEATURE_LPAR) ? "" : " not");
+
+	return 1;
 }
 
-static void pseries_dedicated_idle(void)
+
+DECLARE_PER_CPU(unsigned long, smt_snooze_delay);
+
+static void pseries_dedicated_idle_sleep(void)
 { 
 	unsigned int cpu = smp_processor_id();
 	unsigned long start_snooze;
 	unsigned long *smt_snooze_delay = &__get_cpu_var(smt_snooze_delay);
-	set_thread_flag(TIF_POLLING_NRFLAG);
-
-	while (1) {
-		/*
-		 * Indicate to the HV that we are idle. Now would be
-		 * a good time to find other work to dispatch.
-		 */
-		get_lppaca()->idle = 1;
-
-		if (!need_resched()) {
-			start_snooze = get_tb() +
-				*smt_snooze_delay * tb_ticks_per_usec;
-
-			while (!need_resched() && !cpu_is_offline(cpu)) {
-				ppc64_runlatch_off();
-
-				/*
-				 * Go into low thread priority and possibly
-				 * low power mode.
-				 */
-				HMT_low();
-				HMT_very_low();
-
-				if (*smt_snooze_delay != 0 &&
-				    get_tb() > start_snooze) {
-					HMT_medium();
-					dedicated_idle_sleep(cpu);
-				}
-
-			}
-
-			HMT_medium();
-		}
-
-		get_lppaca()->idle = 0;
-		ppc64_runlatch_on();
 
-		preempt_enable_no_resched();
-		schedule();
-		preempt_disable();
+	/*
+	 * Indicate to the HV that we are idle. Now would be
+	 * a good time to find other work to dispatch.
+	 */
+	get_lppaca()->idle = 1;
 
-		if (cpu_is_offline(cpu) && system_state == SYSTEM_RUNNING)
-			cpu_die();
-	}
-}
+	/*
+	 * We come in with interrupts disabled, and need_resched()
+	 * has been checked recently.  If we should poll for a little
+	 * while, do so.
+	 */
+	if (*smt_snooze_delay) {
+		start_snooze = get_tb() +
+			*smt_snooze_delay * tb_ticks_per_usec;
+		local_irq_enable();
+		set_thread_flag(TIF_POLLING_NRFLAG);
 
-static void pseries_shared_idle(void)
-{
-	unsigned int cpu = smp_processor_id();
+		while (get_tb() < start_snooze) {
+			if (need_resched() || cpu_is_offline(cpu))
+				goto out;
+			ppc64_runlatch_off();
+			HMT_low();
+			HMT_very_low();
+		}
 
-	while (1) {
-		/*
-		 * Indicate to the HV that we are idle. Now would be
-		 * a good time to find other work to dispatch.
-		 */
-		get_lppaca()->idle = 1;
+		HMT_medium();
+		clear_thread_flag(TIF_POLLING_NRFLAG);
+		smp_mb();
+		local_irq_disable();
+		if (need_resched() || cpu_is_offline(cpu))
+			goto out;
+	}
 
-		while (!need_resched() && !cpu_is_offline(cpu)) {
-			local_irq_disable();
-			ppc64_runlatch_off();
+	/*
+	 * Cede if the other thread is not idle, so that it can
+	 * go single-threaded.  If the other thread is idle,
+	 * we ask the hypervisor if it has pending work it
+	 * wants to do and cede if it does.  Otherwise we keep
+	 * polling in order to reduce interrupt latency.
+	 *
+	 * Doing the cede when the other thread is active will
+	 * result in this thread going dormant, meaning the other
+	 * thread gets to run in single-threaded (ST) mode, which
+	 * is slightly faster than SMT mode with this thread at
+	 * very low priority.  The cede enables interrupts, which
+	 * doesn't matter here.
+	 */
+	if (!lppaca[cpu ^ 1].idle || poll_pending() == H_PENDING)
+		cede_processor();
 
-			/*
-			 * Yield the processor to the hypervisor.  We return if
-			 * an external interrupt occurs (which are driven prior
-			 * to returning here) or if a prod occurs from another
-			 * processor. When returning here, external interrupts
-			 * are enabled.
-			 *
-			 * Check need_resched() again with interrupts disabled
-			 * to avoid a race.
-			 */
-			if (!need_resched())
-				cede_processor();
-			else
-				local_irq_enable();
-
-			HMT_medium();
-		}
+out:
+	HMT_medium();
+	get_lppaca()->idle = 0;
+}
 
-		get_lppaca()->idle = 0;
-		ppc64_runlatch_on();
+static void pseries_shared_idle_sleep(void)
+{
+	/*
+	 * Indicate to the HV that we are idle. Now would be
+	 * a good time to find other work to dispatch.
+	 */
+	get_lppaca()->idle = 1;
 
-		preempt_enable_no_resched();
-		schedule();
-		preempt_disable();
+	/*
+	 * Yield the processor to the hypervisor.  We return if
+	 * an external interrupt occurs (which are driven prior
+	 * to returning here) or if a prod occurs from another
+	 * processor. When returning here, external interrupts
+	 * are enabled.
+	 */
+	cede_processor();
 
-		if (cpu_is_offline(cpu) && system_state == SYSTEM_RUNNING)
-			cpu_die();
-	}
+	get_lppaca()->idle = 0;
 }
 
 static int pSeries_pci_probe_mode(struct pci_bus *bus)
@@ -553,7 +519,8 @@ static void pseries_kexec_cpu_down(int crash_shutdown, int secondary)
 }
 #endif
 
-struct machdep_calls __initdata pSeries_md = {
+define_machine(pseries) {
+	.name			= "pSeries",
 	.probe			= pSeries_probe,
 	.setup_arch		= pSeries_setup_arch,
 	.init_early		= pSeries_init_early,
diff --git a/arch/powerpc/platforms/pseries/vio.c b/arch/powerpc/platforms/pseries/vio.c
index 866379b80c0..8e53e04ada8 100644
--- a/arch/powerpc/platforms/pseries/vio.c
+++ b/arch/powerpc/platforms/pseries/vio.c
@@ -258,7 +258,7 @@ EXPORT_SYMBOL(vio_find_node);
 int vio_enable_interrupts(struct vio_dev *dev)
 {
 	int rc = h_vio_signal(dev->unit_address, VIO_IRQ_ENABLE);
-	if (rc != H_Success)
+	if (rc != H_SUCCESS)
 		printk(KERN_ERR "vio: Error 0x%x enabling interrupts\n", rc);
 	return rc;
 }
@@ -267,7 +267,7 @@ EXPORT_SYMBOL(vio_enable_interrupts);
 int vio_disable_interrupts(struct vio_dev *dev)
 {
 	int rc = h_vio_signal(dev->unit_address, VIO_IRQ_DISABLE);
-	if (rc != H_Success)
+	if (rc != H_SUCCESS)
 		printk(KERN_ERR "vio: Error 0x%x disabling interrupts\n", rc);
 	return rc;
 }
diff --git a/arch/powerpc/platforms/pseries/xics.c b/arch/powerpc/platforms/pseries/xics.c
index eb86cdb9b80..2d60ea30fed 100644
--- a/arch/powerpc/platforms/pseries/xics.c
+++ b/arch/powerpc/platforms/pseries/xics.c
@@ -168,7 +168,7 @@ static int pSeriesLP_xirr_info_get(int n_cpu)
 	unsigned long return_value;
 
 	lpar_rc = plpar_xirr(&return_value);
-	if (lpar_rc != H_Success)
+	if (lpar_rc != H_SUCCESS)
 		panic(" bad return code xirr - rc = %lx \n", lpar_rc);
 	return (int)return_value;
 }
@@ -179,7 +179,7 @@ static void pSeriesLP_xirr_info_set(int n_cpu, int value)
 	unsigned long val64 = value & 0xffffffff;
 
 	lpar_rc = plpar_eoi(val64);
-	if (lpar_rc != H_Success)
+	if (lpar_rc != H_SUCCESS)
 		panic("bad return code EOI - rc = %ld, value=%lx\n", lpar_rc,
 		      val64);
 }
@@ -189,7 +189,7 @@ void pSeriesLP_cppr_info(int n_cpu, u8 value)
 	unsigned long lpar_rc;
 
 	lpar_rc = plpar_cppr(value);
-	if (lpar_rc != H_Success)
+	if (lpar_rc != H_SUCCESS)
 		panic("bad return code cppr - rc = %lx\n", lpar_rc);
 }
 
@@ -198,7 +198,7 @@ static void pSeriesLP_qirr_info(int n_cpu , u8 value)
 	unsigned long lpar_rc;
 
 	lpar_rc = plpar_ipi(get_hard_smp_processor_id(n_cpu), value);
-	if (lpar_rc != H_Success)
+	if (lpar_rc != H_SUCCESS)
 		panic("bad return code qirr - rc = %lx\n", lpar_rc);
 }
 
@@ -500,7 +500,7 @@ nextnode:
 	     np;
 	     np = of_find_node_by_type(np, "cpu")) {
 		ireg = (uint *)get_property(np, "reg", &ilen);
-		if (ireg && ireg[0] == boot_cpuid_phys) {
+		if (ireg && ireg[0] == get_hard_smp_processor_id(boot_cpuid)) {
 			ireg = (uint *)get_property(np, "ibm,ppc-interrupt-gserver#s",
 						    &ilen);
 			i = ilen / sizeof(int);
@@ -541,7 +541,7 @@ nextnode:
 		ops = &pSeriesLP_ops;
 	else {
 #ifdef CONFIG_SMP
-		for_each_cpu(i) {
+		for_each_possible_cpu(i) {
 			int hard_id;
 
 			/* FIXME: Do this dynamically! --RR */