Merge branch 'master' of git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux-2.6

29 files changed, 355 insertions, 113 deletions

diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 4fd479059d65..10a0a5488a44 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -385,9 +385,15 @@ config NUMA
 
 config NODES_SHIFT
 	int
+	default "8" if PPC64
 	default "4"
 	depends on NEED_MULTIPLE_NODES
 
+config MAX_ACTIVE_REGIONS
+	int
+	default "256" if PPC64
+	default "32"
+
 config ARCH_SELECT_MEMORY_MODEL
 	def_bool y
 	depends on PPC64
diff --git a/arch/powerpc/Makefile b/arch/powerpc/Makefile
index aacf629c1a9f..1a54a3b3a3fa 100644
--- a/arch/powerpc/Makefile
+++ b/arch/powerpc/Makefile
@@ -164,6 +164,17 @@ PHONY += $(BOOT_TARGETS)
 
 boot := arch/$(ARCH)/boot
 
+ifeq ($(CONFIG_RELOCATABLE),y)
+quiet_cmd_relocs_check = CALL    $<
+      cmd_relocs_check = perl $< "$(OBJDUMP)" "$(obj)/vmlinux"
+
+PHONY += relocs_check
+relocs_check: arch/powerpc/relocs_check.pl vmlinux
+	$(call cmd,relocs_check)
+
+zImage: relocs_check
+endif
+
 $(BOOT_TARGETS): vmlinux
 	$(Q)$(MAKE) ARCH=ppc64 $(build)=$(boot) $(patsubst %,$(boot)/%,$@)
 
diff --git a/arch/powerpc/include/asm/device.h b/arch/powerpc/include/asm/device.h
index 9dade15d1ab4..6d94d27ed850 100644
--- a/arch/powerpc/include/asm/device.h
+++ b/arch/powerpc/include/asm/device.h
@@ -15,7 +15,16 @@ struct dev_archdata {
 
 	/* DMA operations on that device */
 	struct dma_map_ops	*dma_ops;
-	void			*dma_data;
+
+	/*
+	 * When an iommu is in use, dma_data is used as a ptr to the base of the
+	 * iommu_table.  Otherwise, it is a simple numerical offset.
+	 */
+	union {
+		dma_addr_t	dma_offset;
+		void		*iommu_table_base;
+	} dma_data;
+
 #ifdef CONFIG_SWIOTLB
 	dma_addr_t		max_direct_dma_addr;
 #endif
diff --git a/arch/powerpc/include/asm/dma-mapping.h b/arch/powerpc/include/asm/dma-mapping.h
index cb2ca41dd526..e281daebddca 100644
--- a/arch/powerpc/include/asm/dma-mapping.h
+++ b/arch/powerpc/include/asm/dma-mapping.h
@@ -26,7 +26,6 @@ extern void *dma_direct_alloc_coherent(struct device *dev, size_t size,
 extern void dma_direct_free_coherent(struct device *dev, size_t size,
 				     void *vaddr, dma_addr_t dma_handle);
 
-extern unsigned long get_dma_direct_offset(struct device *dev);
 
 #ifdef CONFIG_NOT_COHERENT_CACHE
 /*
@@ -90,6 +89,28 @@ static inline void set_dma_ops(struct device *dev, struct dma_map_ops *ops)
 	dev->archdata.dma_ops = ops;
 }
 
+/*
+ * get_dma_offset()
+ *
+ * Get the dma offset on configurations where the dma address can be determined
+ * from the physical address by looking at a simple offset.  Direct dma and
+ * swiotlb use this function, but it is typically not used by implementations
+ * with an iommu.
+ */
+static inline dma_addr_t get_dma_offset(struct device *dev)
+{
+	if (dev)
+		return dev->archdata.dma_data.dma_offset;
+
+	return PCI_DRAM_OFFSET;
+}
+
+static inline void set_dma_offset(struct device *dev, dma_addr_t off)
+{
+	if (dev)
+		dev->archdata.dma_data.dma_offset = off;
+}
+
 /* this will be removed soon */
 #define flush_write_buffers()
 
@@ -181,12 +202,12 @@ static inline bool dma_capable(struct device *dev, dma_addr_t addr, size_t size)
 
 static inline dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr)
 {
-	return paddr + get_dma_direct_offset(dev);
+	return paddr + get_dma_offset(dev);
 }
 
 static inline phys_addr_t dma_to_phys(struct device *dev, dma_addr_t daddr)
 {
-	return daddr - get_dma_direct_offset(dev);
+	return daddr - get_dma_offset(dev);
 }
 
 #define dma_alloc_noncoherent(d, s, h, f) dma_alloc_coherent(d, s, h, f)
diff --git a/arch/powerpc/include/asm/fsldma.h b/arch/powerpc/include/asm/fsldma.h
new file mode 100644
index 000000000000..a67aeed17d40
--- /dev/null
+++ b/arch/powerpc/include/asm/fsldma.h
@@ -0,0 +1,136 @@
+/*
+ * Freescale MPC83XX / MPC85XX DMA Controller
+ *
+ * Copyright (c) 2009 Ira W. Snyder <iws@ovro.caltech.edu>
+ *
+ * This file is licensed under the terms of the GNU General Public License
+ * version 2. This program is licensed "as is" without any warranty of any
+ * kind, whether express or implied.
+ */
+
+#ifndef __ARCH_POWERPC_ASM_FSLDMA_H__
+#define __ARCH_POWERPC_ASM_FSLDMA_H__
+
+#include <linux/dmaengine.h>
+
+/*
+ * Definitions for the Freescale DMA controller's DMA_SLAVE implemention
+ *
+ * The Freescale DMA_SLAVE implementation was designed to handle many-to-many
+ * transfers. An example usage would be an accelerated copy between two
+ * scatterlists. Another example use would be an accelerated copy from
+ * multiple non-contiguous device buffers into a single scatterlist.
+ *
+ * A DMA_SLAVE transaction is defined by a struct fsl_dma_slave. This
+ * structure contains a list of hardware addresses that should be copied
+ * to/from the scatterlist passed into device_prep_slave_sg(). The structure
+ * also has some fields to enable hardware-specific features.
+ */
+
+/**
+ * struct fsl_dma_hw_addr
+ * @entry: linked list entry
+ * @address: the hardware address
+ * @length: length to transfer
+ *
+ * Holds a single physical hardware address / length pair for use
+ * with the DMAEngine DMA_SLAVE API.
+ */
+struct fsl_dma_hw_addr {
+	struct list_head entry;
+
+	dma_addr_t address;
+	size_t length;
+};
+
+/**
+ * struct fsl_dma_slave
+ * @addresses: a linked list of struct fsl_dma_hw_addr structures
+ * @request_count: value for DMA request count
+ * @src_loop_size: setup and enable constant source-address DMA transfers
+ * @dst_loop_size: setup and enable constant destination address DMA transfers
+ * @external_start: enable externally started DMA transfers
+ * @external_pause: enable externally paused DMA transfers
+ *
+ * Holds a list of address / length pairs for use with the DMAEngine
+ * DMA_SLAVE API implementation for the Freescale DMA controller.
+ */
+struct fsl_dma_slave {
+
+	/* List of hardware address/length pairs */
+	struct list_head addresses;
+
+	/* Support for extra controller features */
+	unsigned int request_count;
+	unsigned int src_loop_size;
+	unsigned int dst_loop_size;
+	bool external_start;
+	bool external_pause;
+};
+
+/**
+ * fsl_dma_slave_append - add an address/length pair to a struct fsl_dma_slave
+ * @slave: the &struct fsl_dma_slave to add to
+ * @address: the hardware address to add
+ * @length: the length of bytes to transfer from @address
+ *
+ * Add a hardware address/length pair to a struct fsl_dma_slave. Returns 0 on
+ * success, -ERRNO otherwise.
+ */
+static inline int fsl_dma_slave_append(struct fsl_dma_slave *slave,
+				       dma_addr_t address, size_t length)
+{
+	struct fsl_dma_hw_addr *addr;
+
+	addr = kzalloc(sizeof(*addr), GFP_ATOMIC);
+	if (!addr)
+		return -ENOMEM;
+
+	INIT_LIST_HEAD(&addr->entry);
+	addr->address = address;
+	addr->length = length;
+
+	list_add_tail(&addr->entry, &slave->addresses);
+	return 0;
+}
+
+/**
+ * fsl_dma_slave_free - free a struct fsl_dma_slave
+ * @slave: the struct fsl_dma_slave to free
+ *
+ * Free a struct fsl_dma_slave and all associated address/length pairs
+ */
+static inline void fsl_dma_slave_free(struct fsl_dma_slave *slave)
+{
+	struct fsl_dma_hw_addr *addr, *tmp;
+
+	if (slave) {
+		list_for_each_entry_safe(addr, tmp, &slave->addresses, entry) {
+			list_del(&addr->entry);
+			kfree(addr);
+		}
+
+		kfree(slave);
+	}
+}
+
+/**
+ * fsl_dma_slave_alloc - allocate a struct fsl_dma_slave
+ * @gfp: the flags to pass to kmalloc when allocating this structure
+ *
+ * Allocate a struct fsl_dma_slave for use by the DMA_SLAVE API. Returns a new
+ * struct fsl_dma_slave on success, or NULL on failure.
+ */
+static inline struct fsl_dma_slave *fsl_dma_slave_alloc(gfp_t gfp)
+{
+	struct fsl_dma_slave *slave;
+
+	slave = kzalloc(sizeof(*slave), gfp);
+	if (!slave)
+		return NULL;
+
+	INIT_LIST_HEAD(&slave->addresses);
+	return slave;
+}
+
+#endif /* __ARCH_POWERPC_ASM_FSLDMA_H__ */
diff --git a/arch/powerpc/include/asm/iommu.h b/arch/powerpc/include/asm/iommu.h
index 7464c0daddd1..edfc9803ec91 100644
--- a/arch/powerpc/include/asm/iommu.h
+++ b/arch/powerpc/include/asm/iommu.h
@@ -70,6 +70,16 @@ struct iommu_table {
 
 struct scatterlist;
 
+static inline void set_iommu_table_base(struct device *dev, void *base)
+{
+	dev->archdata.dma_data.iommu_table_base = base;
+}
+
+static inline void *get_iommu_table_base(struct device *dev)
+{
+	return dev->archdata.dma_data.iommu_table_base;
+}
+
 /* Frees table for an individual device node */
 extern void iommu_free_table(struct iommu_table *tbl, const char *node_name);
 
diff --git a/arch/powerpc/include/asm/pmc.h b/arch/powerpc/include/asm/pmc.h
index ccc68b50d05d..5a9ede4962cb 100644
--- a/arch/powerpc/include/asm/pmc.h
+++ b/arch/powerpc/include/asm/pmc.h
@@ -29,7 +29,7 @@ int reserve_pmc_hardware(perf_irq_t new_perf_irq);
 void release_pmc_hardware(void);
 void ppc_enable_pmcs(void);
 
-#ifdef CONFIG_PPC64
+#ifdef CONFIG_PPC_BOOK3S_64
 #include <asm/lppaca.h>
 
 static inline void ppc_set_pmu_inuse(int inuse)
diff --git a/arch/powerpc/include/asm/pte-40x.h b/arch/powerpc/include/asm/pte-40x.h
index 6c3e1f4378d4..ec0b0b0d1df9 100644
--- a/arch/powerpc/include/asm/pte-40x.h
+++ b/arch/powerpc/include/asm/pte-40x.h
@@ -43,6 +43,7 @@
 #define	_PAGE_NO_CACHE	0x004	/* I: caching is inhibited */
 #define	_PAGE_WRITETHRU	0x008	/* W: caching is write-through */
 #define	_PAGE_USER	0x010	/* matches one of the zone permission bits */
+#define	_PAGE_SPECIAL	0x020	/* software: Special page */
 #define	_PAGE_RW	0x040	/* software: Writes permitted */
 #define	_PAGE_DIRTY	0x080	/* software: dirty page */
 #define _PAGE_HWWRITE	0x100	/* hardware: Dirty & RW, set in exception */
diff --git a/arch/powerpc/include/asm/pte-8xx.h b/arch/powerpc/include/asm/pte-8xx.h
index 94e979718dcf..dd5ea95fe61e 100644
--- a/arch/powerpc/include/asm/pte-8xx.h
+++ b/arch/powerpc/include/asm/pte-8xx.h
@@ -32,6 +32,7 @@
 #define _PAGE_FILE	0x0002	/* when !present: nonlinear file mapping */
 #define _PAGE_NO_CACHE	0x0002	/* I: cache inhibit */
 #define _PAGE_SHARED	0x0004	/* No ASID (context) compare */
+#define _PAGE_SPECIAL	0x0008	/* SW entry, forced to 0 by the TLB miss */
 
 /* These five software bits must be masked out when the entry is loaded
  * into the TLB.
diff --git a/arch/powerpc/include/asm/pte-common.h b/arch/powerpc/include/asm/pte-common.h
index c3b65076a263..f2b370180a09 100644
--- a/arch/powerpc/include/asm/pte-common.h
+++ b/arch/powerpc/include/asm/pte-common.h
@@ -25,9 +25,6 @@
 #ifndef _PAGE_WRITETHRU
 #define _PAGE_WRITETHRU	0
 #endif
-#ifndef _PAGE_SPECIAL
-#define _PAGE_SPECIAL	0
-#endif
 #ifndef _PAGE_4K_PFN
 #define _PAGE_4K_PFN		0
 #endif
@@ -179,7 +176,5 @@ extern unsigned long bad_call_to_PMD_PAGE_SIZE(void);
 #define HAVE_PAGE_AGP
 
 /* Advertise support for _PAGE_SPECIAL */
-#ifdef _PAGE_SPECIAL
 #define __HAVE_ARCH_PTE_SPECIAL
-#endif
 
diff --git a/arch/powerpc/kernel/dma-iommu.c b/arch/powerpc/kernel/dma-iommu.c
index 87ddb3fb948c..37771a518119 100644
--- a/arch/powerpc/kernel/dma-iommu.c
+++ b/arch/powerpc/kernel/dma-iommu.c
@@ -18,7 +18,7 @@
 static void *dma_iommu_alloc_coherent(struct device *dev, size_t size,
 				      dma_addr_t *dma_handle, gfp_t flag)
 {
-	return iommu_alloc_coherent(dev, dev->archdata.dma_data, size,
+	return iommu_alloc_coherent(dev, get_iommu_table_base(dev), size,
 				    dma_handle, device_to_mask(dev), flag,
 				    dev_to_node(dev));
 }
@@ -26,7 +26,7 @@ static void *dma_iommu_alloc_coherent(struct device *dev, size_t size,
 static void dma_iommu_free_coherent(struct device *dev, size_t size,
 				    void *vaddr, dma_addr_t dma_handle)
 {
-	iommu_free_coherent(dev->archdata.dma_data, size, vaddr, dma_handle);
+	iommu_free_coherent(get_iommu_table_base(dev), size, vaddr, dma_handle);
 }
 
 /* Creates TCEs for a user provided buffer.  The user buffer must be
@@ -39,8 +39,8 @@ static dma_addr_t dma_iommu_map_page(struct device *dev, struct page *page,
 				     enum dma_data_direction direction,
 				     struct dma_attrs *attrs)
 {
-	return iommu_map_page(dev, dev->archdata.dma_data, page, offset, size,
-			      device_to_mask(dev), direction, attrs);
+	return iommu_map_page(dev, get_iommu_table_base(dev), page, offset,
+			      size, device_to_mask(dev), direction, attrs);
 }
 
 
@@ -48,7 +48,7 @@ static void dma_iommu_unmap_page(struct device *dev, dma_addr_t dma_handle,
 				 size_t size, enum dma_data_direction direction,
 				 struct dma_attrs *attrs)
 {
-	iommu_unmap_page(dev->archdata.dma_data, dma_handle, size, direction,
+	iommu_unmap_page(get_iommu_table_base(dev), dma_handle, size, direction,
 			 attrs);
 }
 
@@ -57,7 +57,7 @@ static int dma_iommu_map_sg(struct device *dev, struct scatterlist *sglist,
 			    int nelems, enum dma_data_direction direction,
 			    struct dma_attrs *attrs)
 {
-	return iommu_map_sg(dev, dev->archdata.dma_data, sglist, nelems,
+	return iommu_map_sg(dev, get_iommu_table_base(dev), sglist, nelems,
 			    device_to_mask(dev), direction, attrs);
 }
 
@@ -65,14 +65,14 @@ static void dma_iommu_unmap_sg(struct device *dev, struct scatterlist *sglist,
 		int nelems, enum dma_data_direction direction,
 		struct dma_attrs *attrs)
 {
-	iommu_unmap_sg(dev->archdata.dma_data, sglist, nelems, direction,
+	iommu_unmap_sg(get_iommu_table_base(dev), sglist, nelems, direction,
 		       attrs);
 }
 
 /* We support DMA to/from any memory page via the iommu */
 static int dma_iommu_dma_supported(struct device *dev, u64 mask)
 {
-	struct iommu_table *tbl = dev->archdata.dma_data;
+	struct iommu_table *tbl = get_iommu_table_base(dev);
 
 	if (!tbl || tbl->it_offset > mask) {
 		printk(KERN_INFO
diff --git a/arch/powerpc/kernel/dma.c b/arch/powerpc/kernel/dma.c
index 21b784d7e7d0..6215062caf8c 100644
--- a/arch/powerpc/kernel/dma.c
+++ b/arch/powerpc/kernel/dma.c
@@ -21,13 +21,6 @@
  * default the offset is PCI_DRAM_OFFSET.
  */
 
-unsigned long get_dma_direct_offset(struct device *dev)
-{
-	if (dev)
-		return (unsigned long)dev->archdata.dma_data;
-
-	return PCI_DRAM_OFFSET;
-}
 
 void *dma_direct_alloc_coherent(struct device *dev, size_t size,
 				dma_addr_t *dma_handle, gfp_t flag)
@@ -37,7 +30,7 @@ void *dma_direct_alloc_coherent(struct device *dev, size_t size,
 	ret = __dma_alloc_coherent(dev, size, dma_handle, flag);
 	if (ret == NULL)
 		return NULL;
-	*dma_handle += get_dma_direct_offset(dev);
+	*dma_handle += get_dma_offset(dev);
 	return ret;
 #else
 	struct page *page;
@@ -51,7 +44,7 @@ void *dma_direct_alloc_coherent(struct device *dev, size_t size,
 		return NULL;
 	ret = page_address(page);
 	memset(ret, 0, size);
-	*dma_handle = virt_to_abs(ret) + get_dma_direct_offset(dev);
+	*dma_handle = virt_to_abs(ret) + get_dma_offset(dev);
 
 	return ret;
 #endif
@@ -75,7 +68,7 @@ static int dma_direct_map_sg(struct device *dev, struct scatterlist *sgl,
 	int i;
 
 	for_each_sg(sgl, sg, nents, i) {
-		sg->dma_address = sg_phys(sg) + get_dma_direct_offset(dev);
+		sg->dma_address = sg_phys(sg) + get_dma_offset(dev);
 		sg->dma_length = sg->length;
 		__dma_sync_page(sg_page(sg), sg->offset, sg->length, direction);
 	}
@@ -110,7 +103,7 @@ static inline dma_addr_t dma_direct_map_page(struct device *dev,
 {
 	BUG_ON(dir == DMA_NONE);
 	__dma_sync_page(page, offset, size, dir);
-	return page_to_phys(page) + offset + get_dma_direct_offset(dev);
+	return page_to_phys(page) + offset + get_dma_offset(dev);
 }
 
 static inline void dma_direct_unmap_page(struct device *dev,
diff --git a/arch/powerpc/kernel/exceptions-64e.S b/arch/powerpc/kernel/exceptions-64e.S
index 9048f96237f6..24dcc0ecf246 100644
--- a/arch/powerpc/kernel/exceptions-64e.S
+++ b/arch/powerpc/kernel/exceptions-64e.S
@@ -17,7 +17,6 @@
 #include <asm/cputable.h>
 #include <asm/setup.h>
 #include <asm/thread_info.h>
-#include <asm/reg.h>
 #include <asm/exception-64e.h>
 #include <asm/bug.h>
 #include <asm/irqflags.h>
diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c
index e9f4840096b3..bb8209e34931 100644
--- a/arch/powerpc/kernel/pci-common.c
+++ b/arch/powerpc/kernel/pci-common.c
@@ -1117,7 +1117,7 @@ void __devinit pcibios_setup_bus_devices(struct pci_bus *bus)
 
 		/* Hook up default DMA ops */
 		sd->dma_ops = pci_dma_ops;
-		sd->dma_data = (void *)PCI_DRAM_OFFSET;
+		set_dma_offset(&dev->dev, PCI_DRAM_OFFSET);
 
 		/* Additional platform DMA/iommu setup */
 		if (ppc_md.pci_dma_dev_setup)
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index 0a3216433051..1168c5f440ab 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -1165,7 +1165,22 @@ static inline unsigned long brk_rnd(void)
 
 unsigned long arch_randomize_brk(struct mm_struct *mm)
 {
-	unsigned long ret = PAGE_ALIGN(mm->brk + brk_rnd());
+	unsigned long base = mm->brk;
+	unsigned long ret;
+
+#ifdef CONFIG_PPC64
+	/*
+	 * If we are using 1TB segments and we are allowed to randomise
+	 * the heap, we can put it above 1TB so it is backed by a 1TB
+	 * segment. Otherwise the heap will be in the bottom 1TB
+	 * which always uses 256MB segments and this may result in a
+	 * performance penalty.
+	 */
+	if (!is_32bit_task() && (mmu_highuser_ssize == MMU_SEGSIZE_1T))
+		base = max_t(unsigned long, mm->brk, 1UL << SID_SHIFT_1T);
+#endif
+
+	ret = PAGE_ALIGN(base + brk_rnd());
 
 	if (ret < mm->brk)
 		return mm->brk;
diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c
index 864334b337a3..bafac2e41ae1 100644
--- a/arch/powerpc/kernel/prom_init.c
+++ b/arch/powerpc/kernel/prom_init.c
@@ -800,7 +800,7 @@ static void __init prom_send_capabilities(void)
 	root = call_prom("open", 1, 1, ADDR("/"));
 	if (root != 0) {
 		/* try calling the ibm,client-architecture-support method */
-		prom_printf("Calling ibm,client-architecture...");
+		prom_printf("Calling ibm,client-architecture-support...");
 		if (call_prom_ret("call-method", 3, 2, &ret,
 				  ADDR("ibm,client-architecture-support"),
 				  root,
@@ -814,6 +814,7 @@ static void __init prom_send_capabilities(void)
 			return;
 		}
 		call_prom("close", 1, 0, root);
+		prom_printf(" not implemented\n");
 	}
 
 	/* no ibm,client-architecture-support call, try the old way */
diff --git a/arch/powerpc/kernel/vdso.c b/arch/powerpc/kernel/vdso.c
index 3faaf29bdb29..94e2df3cae07 100644
--- a/arch/powerpc/kernel/vdso.c
+++ b/arch/powerpc/kernel/vdso.c
@@ -241,6 +241,13 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
 	}
 
 	/*
+	 * Put vDSO base into mm struct. We need to do this before calling
+	 * install_special_mapping or the perf counter mmap tracking code
+	 * will fail to recognise it as a vDSO (since arch_vma_name fails).
+	 */
+	current->mm->context.vdso_base = vdso_base;
+
+	/*
 	 * our vma flags don't have VM_WRITE so by default, the process isn't
 	 * allowed to write those pages.
 	 * gdb can break that with ptrace interface, and thus trigger COW on
@@ -260,11 +267,10 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
 				     VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC|
 				     VM_ALWAYSDUMP,
 				     vdso_pagelist);
-	if (rc)
+	if (rc) {
+		current->mm->context.vdso_base = 0;
 		goto fail_mmapsem;
-
-	/* Put vDSO base into mm struct */
-	current->mm->context.vdso_base = vdso_base;
+	}
 
 	up_write(&mm->mmap_sem);
 	return 0;
diff --git a/arch/powerpc/kernel/vio.c b/arch/powerpc/kernel/vio.c
index bc7b41edbdfc..77f64218abf3 100644
--- a/arch/powerpc/kernel/vio.c
+++ b/arch/powerpc/kernel/vio.c
@@ -1054,6 +1054,8 @@ static struct iommu_table *vio_build_iommu_table(struct vio_dev *dev)
 		return NULL;
 
 	tbl = kmalloc(sizeof(*tbl), GFP_KERNEL);
+	if (tbl == NULL)
+		return NULL;
 
 	of_parse_dma_window(dev->dev.archdata.of_node, dma_window,
 			    &tbl->it_index, &offset, &size);
@@ -1233,7 +1235,7 @@ struct vio_dev *vio_register_device_node(struct device_node *of_node)
 		vio_cmo_set_dma_ops(viodev);
 	else
 		viodev->dev.archdata.dma_ops = &dma_iommu_ops;
-	viodev->dev.archdata.dma_data = vio_build_iommu_table(viodev);
+	set_iommu_table_base(&viodev->dev, vio_build_iommu_table(viodev));
 	set_dev_node(&viodev->dev, of_node_to_nid(of_node));
 
 	/* init generic 'struct device' fields: */
diff --git a/arch/powerpc/kernel/vmlinux.lds.S b/arch/powerpc/kernel/vmlinux.lds.S
index 58da4070723d..f56429362a12 100644
--- a/arch/powerpc/kernel/vmlinux.lds.S
+++ b/arch/powerpc/kernel/vmlinux.lds.S
@@ -6,6 +6,7 @@
 #include <asm/page.h>
 #include <asm-generic/vmlinux.lds.h>
 #include <asm/cache.h>
+#include <asm/thread_info.h>
 
 ENTRY(_stext)
 
@@ -71,12 +72,7 @@ SECTIONS
 	/* Read-only data */
 	RODATA
 
-	/* Exception & bug tables */
-	__ex_table : AT(ADDR(__ex_table) - LOAD_OFFSET) {
-		__start___ex_table = .;
-		*(__ex_table)
-		__stop___ex_table = .;
-	}
+	EXCEPTION_TABLE(0)
 
 	NOTES :kernel :notes
 
@@ -93,12 +89,7 @@ SECTIONS
  */
 	. = ALIGN(PAGE_SIZE);
 	__init_begin = .;
-
-	.init.text : AT(ADDR(.init.text) - LOAD_OFFSET) {
-		_sinittext = .;
-		INIT_TEXT
-		_einittext = .;
-	} :kernel
+	INIT_TEXT_SECTION(PAGE_SIZE) :kernel
 
 	/* .exit.text is discarded at runtime, not link time,
 	 * to deal with references from __bug_table
@@ -122,23 +113,16 @@ SECTIONS
 #endif
 	}
 
-	. = ALIGN(16);
 	.init.setup : AT(ADDR(.init.setup) - LOAD_OFFSET) {
-		__setup_start = .;
-		*(.init.setup)
-		__setup_end = .;
+		INIT_SETUP(16)
 	}
 
 	.initcall.init : AT(ADDR(.initcall.init) - LOAD_OFFSET) {
-		__initcall_start = .;
-		INITCALLS
-		__initcall_end = .;
-		}
+		INIT_CALLS
+	}
 
 	.con_initcall.init : AT(ADDR(.con_initcall.init) - LOAD_OFFSET) {
-		__con_initcall_start = .;
-		*(.con_initcall.init)
-		__con_initcall_end = .;
+		CON_INITCALL
 	}
 
 	SECURITY_INIT
@@ -169,14 +153,10 @@ SECTIONS
 		__stop___fw_ftr_fixup = .;
 	}
 #endif
-#ifdef CONFIG_BLK_DEV_INITRD
-	. = ALIGN(PAGE_SIZE);
 	.init.ramfs : AT(ADDR(.init.ramfs) - LOAD_OFFSET) {
-		__initramfs_start = .;
-		*(.init.ramfs)
-		__initramfs_end = .;
+		INIT_RAM_FS
 	}
-#endif
+
 	PERCPU(PAGE_SIZE)
 
 	. = ALIGN(8);
@@ -240,36 +220,24 @@ SECTIONS
 #endif
 
 	/* The initial task and kernel stack */
-#ifdef CONFIG_PPC32
-	. = ALIGN(8192);
-#else
-	. = ALIGN(16384);
-#endif
 	.data.init_task : AT(ADDR(.data.init_task) - LOAD_OFFSET) {
-		*(.data.init_task)
+		INIT_TASK_DATA(THREAD_SIZE)
 	}
 
-	. = ALIGN(PAGE_SIZE);
 	.data.page_aligned : AT(ADDR(.data.page_aligned) - LOAD_OFFSET) {
-		*(.data.page_aligned)
+		PAGE_ALIGNED_DATA(PAGE_SIZE)
 	}
 
-	. = ALIGN(L1_CACHE_BYTES);
 	.data.cacheline_aligned : AT(ADDR(.data.cacheline_aligned) - LOAD_OFFSET) {
-		*(.data.cacheline_aligned)
+		CACHELINE_ALIGNED_DATA(L1_CACHE_BYTES)
 	}
 
-	. = ALIGN(L1_CACHE_BYTES);
 	.data.read_mostly : AT(ADDR(.data.read_mostly) - LOAD_OFFSET) {
-		*(.data.read_mostly)
+		READ_MOSTLY_DATA(L1_CACHE_BYTES)
 	}
 
-	. = ALIGN(PAGE_SIZE);
 	.data_nosave : AT(ADDR(.data_nosave) - LOAD_OFFSET) {
-		__nosave_begin = .;
-		*(.data.nosave)
-		. = ALIGN(PAGE_SIZE);
-		__nosave_end = .;
+		NOSAVE_DATA
 	}
 
 	. = ALIGN(PAGE_SIZE);
@@ -280,14 +248,7 @@ SECTIONS
  * And finally the bss
  */
 
-	.bss : AT(ADDR(.bss) - LOAD_OFFSET) {
-		__bss_start = .;
-		*(.sbss) *(.scommon)
-		*(.dynbss)
-		*(.bss)
-		*(COMMON)
-		__bss_stop = .;
-	}
+	BSS_SECTION(0, 0, 0)
 
 	. = ALIGN(PAGE_SIZE);
 	_end = . ;
diff --git a/arch/powerpc/mm/pgtable.c b/arch/powerpc/mm/pgtable.c
index 83f1551ec2c9..53040931de32 100644
--- a/arch/powerpc/mm/pgtable.c
+++ b/arch/powerpc/mm/pgtable.c
@@ -30,6 +30,8 @@
 #include <asm/tlbflush.h>
 #include <asm/tlb.h>
 
+#include "mmu_decl.h"
+
 DEFINE_PER_CPU(struct mmu_gather, mmu_gathers);
 
 #ifdef CONFIG_SMP
@@ -166,7 +168,7 @@ struct page * maybe_pte_to_page(pte_t pte)
  * support falls into the same category.
  */
 
-static pte_t set_pte_filter(pte_t pte)
+static pte_t set_pte_filter(pte_t pte, unsigned long addr)
 {
 	pte = __pte(pte_val(pte) & ~_PAGE_HPTEFLAGS);
 	if (pte_looks_normal(pte) && !(cpu_has_feature(CPU_FTR_COHERENT_ICACHE) ||
@@ -175,6 +177,17 @@ static pte_t set_pte_filter(pte_t pte)
 		if (!pg)
 			return pte;
 		if (!test_bit(PG_arch_1, &pg->flags)) {
+#ifdef CONFIG_8xx
+			/* On 8xx, cache control instructions (particularly
+			 * "dcbst" from flush_dcache_icache) fault as write
+			 * operation if there is an unpopulated TLB entry
+			 * for the address in question. To workaround that,
+			 * we invalidate the TLB here, thus avoiding dcbst
+			 * misbehaviour.
+			 */
+			/* 8xx doesn't care about PID, size or ind args */
+			_tlbil_va(addr, 0, 0, 0);
+#endif /* CONFIG_8xx */
 			flush_dcache_icache_page(pg);
 			set_bit(PG_arch_1, &pg->flags);
 		}
@@ -194,7 +207,7 @@ static pte_t set_access_flags_filter(pte_t pte, struct vm_area_struct *vma,
  * as we don't have two bits to spare for _PAGE_EXEC and _PAGE_HWEXEC so
  * instead we "filter out" the exec permission for non clean pages.
  */
-static pte_t set_pte_filter(pte_t pte)
+static pte_t set_pte_filter(pte_t pte, unsigned long addr)
 {
 	struct page *pg;
 
@@ -276,7 +289,7 @@ void set_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep,
 	 * this context might not have been activated yet when this
 	 * is called.
 	 */
-	pte = set_pte_filter(pte);
+	pte = set_pte_filter(pte, addr);
 
 	/* Perform the setting of the PTE */
 	__set_pte_at(mm, addr, ptep, pte, 0);
diff --git a/arch/powerpc/mm/tlb_low_64e.S b/arch/powerpc/mm/tlb_low_64e.S
index ef1cccf71173..f288279e679d 100644
--- a/arch/powerpc/mm/tlb_low_64e.S
+++ b/arch/powerpc/mm/tlb_low_64e.S
@@ -18,7 +18,6 @@
 #include <asm/asm-offsets.h>
 #include <asm/cputable.h>
 #include <asm/pgtable.h>
-#include <asm/reg.h>
 #include <asm/exception-64e.h>
 #include <asm/ppc-opcode.h>
 
diff --git a/arch/powerpc/platforms/cell/beat_iommu.c b/arch/powerpc/platforms/cell/beat_iommu.c
index 93b0efddd658..39d361c5c6d2 100644
--- a/arch/powerpc/platforms/cell/beat_iommu.c
+++ b/arch/powerpc/platforms/cell/beat_iommu.c
@@ -77,7 +77,7 @@ static void __init celleb_init_direct_mapping(void)
 static void celleb_dma_dev_setup(struct device *dev)
 {
 	dev->archdata.dma_ops = get_pci_dma_ops();
-	dev->archdata.dma_data = (void *)celleb_dma_direct_offset;
+	set_dma_offset(dev, celleb_dma_direct_offset);
 }
 
 static void celleb_pci_dma_dev_setup(struct pci_dev *pdev)
diff --git a/arch/powerpc/platforms/cell/iommu.c b/arch/powerpc/platforms/cell/iommu.c
index 416db17eb18f..ca5bfdfe47f2 100644
--- a/arch/powerpc/platforms/cell/iommu.c
+++ b/arch/powerpc/platforms/cell/iommu.c
@@ -657,15 +657,13 @@ static void cell_dma_dev_setup_fixed(struct device *dev);
 
 static void cell_dma_dev_setup(struct device *dev)
 {
-	struct dev_archdata *archdata = &dev->archdata;
-
 	/* Order is important here, these are not mutually exclusive */
 	if (get_dma_ops(dev) == &dma_iommu_fixed_ops)
 		cell_dma_dev_setup_fixed(dev);
 	else if (get_pci_dma_ops() == &dma_iommu_ops)
-		archdata->dma_data = cell_get_iommu_table(dev);
+		set_iommu_table_base(dev, cell_get_iommu_table(dev));
 	else if (get_pci_dma_ops() == &dma_direct_ops)
-		archdata->dma_data = (void *)cell_dma_direct_offset;
+		set_dma_offset(dev, cell_dma_direct_offset);
 	else
 		BUG();
 }
@@ -973,11 +971,10 @@ static int dma_set_mask_and_switch(struct device *dev, u64 dma_mask)
 
 static void cell_dma_dev_setup_fixed(struct device *dev)
 {
-	struct dev_archdata *archdata = &dev->archdata;
 	u64 addr;
 
 	addr = cell_iommu_get_fixed_address(dev) + dma_iommu_fixed_base;
-	archdata->dma_data = (void *)addr;
+	set_dma_offset(dev, addr);
 
 	dev_dbg(dev, "iommu: fixed addr = %llx\n", addr);
 }
diff --git a/arch/powerpc/platforms/iseries/iommu.c b/arch/powerpc/platforms/iseries/iommu.c
index 6c1e1011959e..9d53cb481a7c 100644
--- a/arch/powerpc/platforms/iseries/iommu.c
+++ b/arch/powerpc/platforms/iseries/iommu.c
@@ -193,7 +193,7 @@ static void pci_dma_dev_setup_iseries(struct pci_dev *pdev)
 		pdn->iommu_table = iommu_init_table(tbl, -1);
 	else
 		kfree(tbl);
-	pdev->dev.archdata.dma_data = pdn->iommu_table;
+	set_iommu_table_base(&pdev->dev, pdn->iommu_table);
 }
 #else
 #define pci_dma_dev_setup_iseries	NULL
diff --git a/arch/powerpc/platforms/pasemi/iommu.c b/arch/powerpc/platforms/pasemi/iommu.c
index a0ff03a3d8da..7b1d608ea3c8 100644
--- a/arch/powerpc/platforms/pasemi/iommu.c
+++ b/arch/powerpc/platforms/pasemi/iommu.c
@@ -189,7 +189,7 @@ static void pci_dma_dev_setup_pasemi(struct pci_dev *dev)
 	}
 #endif
 
-	dev->dev.archdata.dma_data = &iommu_table_iobmap;
+	set_iommu_table_base(&dev->dev, &iommu_table_iobmap);
 }
 
 static void pci_dma_bus_setup_null(struct pci_bus *b) { }
diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c
index 661c8e02bcba..1a0000a4b6d6 100644
--- a/arch/powerpc/platforms/pseries/iommu.c
+++ b/arch/powerpc/platforms/pseries/iommu.c
@@ -482,7 +482,7 @@ static void pci_dma_dev_setup_pSeries(struct pci_dev *dev)
 				   phb->node);
 		iommu_table_setparms(phb, dn, tbl);
 		PCI_DN(dn)->iommu_table = iommu_init_table(tbl, phb->node);
-		dev->dev.archdata.dma_data = PCI_DN(dn)->iommu_table;
+		set_iommu_table_base(&dev->dev, PCI_DN(dn)->iommu_table);
 		return;
 	}
 
@@ -494,7 +494,7 @@ static void pci_dma_dev_setup_pSeries(struct pci_dev *dev)
 		dn = dn->parent;
 
 	if (dn && PCI_DN(dn))
-		dev->dev.archdata.dma_data = PCI_DN(dn)->iommu_table;
+		set_iommu_table_base(&dev->dev, PCI_DN(dn)->iommu_table);
 	else
 		printk(KERN_WARNING "iommu: Device %s has no iommu table\n",
 		       pci_name(dev));
@@ -538,7 +538,7 @@ static void pci_dma_dev_setup_pSeriesLP(struct pci_dev *dev)
 	 */
 	if (dma_window == NULL || pdn->parent == NULL) {
 		pr_debug("  no dma window for device, linking to parent\n");
-		dev->dev.archdata.dma_data = PCI_DN(pdn)->iommu_table;
+		set_iommu_table_base(&dev->dev, PCI_DN(pdn)->iommu_table);
 		return;
 	}
 
@@ -554,7 +554,7 @@ static void pci_dma_dev_setup_pSeriesLP(struct pci_dev *dev)
 		pr_debug("  found DMA window, table: %p\n", pci->iommu_table);
 	}
 
-	dev->dev.archdata.dma_data = pci->iommu_table;
+	set_iommu_table_base(&dev->dev, pci->iommu_table);
 }
 #else  /* CONFIG_PCI */
 #define pci_dma_bus_setup_pSeries	NULL
diff --git a/arch/powerpc/relocs_check.pl b/arch/powerpc/relocs_check.pl
new file mode 100755
index 000000000000..d2571096c3e9
--- /dev/null
+++ b/arch/powerpc/relocs_check.pl
@@ -0,0 +1,56 @@
+#!/usr/bin/perl
+
+# Copyright © 2009 IBM Corporation
+
+# This program is free software; you can redistribute it and/or
+# modify it under the terms of the GNU General Public License
+# as published by the Free Software Foundation; either version
+# 2 of the License, or (at your option) any later version.
+
+# This script checks the relcoations of a vmlinux for "suspicious"
+# relocations.
+
+use strict;
+use warnings;
+
+if ($#ARGV != 1) {
+	die "$0 [path to objdump] [path to vmlinux]\n";
+}
+
+# Have Kbuild supply the path to objdump so we handle cross compilation.
+my $objdump = shift;
+my $vmlinux = shift;
+my $bad_relocs_count = 0;
+my $bad_relocs = "";
+my $old_binutils = 0;
+
+open(FD, "$objdump -R $vmlinux|") or die;
+while (<FD>) {
+	study $_;
+
+	# Only look at relcoation lines.
+	next if (!/\s+R_/);
+
+	# These relocations are okay
+	next if (/R_PPC64_RELATIVE/ or /R_PPC64_NONE/ or
+	         /R_PPC64_ADDR64\s+mach_/);
+
+	# If we see this type of relcoation it's an idication that
+	# we /may/ be using an old version of binutils.
+	if (/R_PPC64_UADDR64/) {
+		$old_binutils++;
+	}
+
+	$bad_relocs_count++;
+	$bad_relocs .= $_;
+}
+
+if ($bad_relocs_count) {
+	print "WARNING: $bad_relocs_count bad relocations\n";
+	print $bad_relocs;
+}
+
+if ($old_binutils) {
+	print "WARNING: You need at binutils >= 2.19 to build a ".
+	      "CONFIG_RELCOATABLE kernel\n";
+}
diff --git a/arch/powerpc/sysdev/dart_iommu.c b/arch/powerpc/sysdev/dart_iommu.c
index 89639ecbf381..ae3c4db86fe8 100644
--- a/arch/powerpc/sysdev/dart_iommu.c
+++ b/arch/powerpc/sysdev/dart_iommu.c
@@ -297,7 +297,7 @@ static void pci_dma_dev_setup_dart(struct pci_dev *dev)
 	/* We only have one iommu table on the mac for now, which makes
 	 * things simple. Setup all PCI devices to point to this table
 	 */
-	dev->dev.archdata.dma_data = &iommu_table_dart;
+	set_iommu_table_base(&dev->dev, &iommu_table_dart);
 }
 
 static void pci_dma_bus_setup_dart(struct pci_bus *bus)
diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c
index 0e09a45ac79a..c6f0a71b405e 100644
--- a/arch/powerpc/xmon/xmon.c
+++ b/arch/powerpc/xmon/xmon.c
@@ -335,6 +335,16 @@ int cpus_are_in_xmon(void)
 }
 #endif
 
+static inline int unrecoverable_excp(struct pt_regs *regs)
+{
+#ifdef CONFIG_4xx
+	/* We have no MSR_RI bit on 4xx, so we simply return false */
+	return 0;
+#else
+	return ((regs->msr & MSR_RI) == 0);
+#endif
+}
+
 static int xmon_core(struct pt_regs *regs, int fromipi)
 {
 	int cmd = 0;
@@ -388,7 +398,7 @@ static int xmon_core(struct pt_regs *regs, int fromipi)
 	bp = NULL;
 	if ((regs->msr & (MSR_IR|MSR_PR|MSR_SF)) == (MSR_IR|MSR_SF))
 		bp = at_breakpoint(regs->nip);
-	if (bp || (regs->msr & MSR_RI) == 0)
+	if (bp || unrecoverable_excp(regs))
 		fromipi = 0;
 
 	if (!fromipi) {
@@ -399,7 +409,7 @@ static int xmon_core(struct pt_regs *regs, int fromipi)
 			       cpu, BP_NUM(bp));
 			xmon_print_symbol(regs->nip, " ", ")\n");
 		}
-		if ((regs->msr & MSR_RI) == 0)
+		if (unrecoverable_excp(regs))
 			printf("WARNING: exception is not recoverable, "
 			       "can't continue\n");
 		release_output_lock();
@@ -490,7 +500,7 @@ static int xmon_core(struct pt_regs *regs, int fromipi)
 			printf("Stopped at breakpoint %x (", BP_NUM(bp));
 			xmon_print_symbol(regs->nip, " ", ")\n");
 		}
-		if ((regs->msr & MSR_RI) == 0)
+		if (unrecoverable_excp(regs))
 			printf("WARNING: exception is not recoverable, "
 			       "can't continue\n");
 		remove_bpts();