29 files changed, 431 insertions, 118 deletions

diff --git a/include/acpi/acpiosxf.h b/include/acpi/acpiosxf.h
index a62720a7edc0..ab0b85cf21f3 100644
--- a/include/acpi/acpiosxf.h
+++ b/include/acpi/acpiosxf.h
@@ -144,6 +144,7 @@ void __iomem *acpi_os_map_memory(acpi_physical_address where,
                                 acpi_size length);
 
 void acpi_os_unmap_memory(void __iomem * logical_address, acpi_size size);
+void early_acpi_os_unmap_memory(void __iomem * virt, acpi_size size);
 
 #ifdef ACPI_FUTURE_USAGE
 acpi_status
diff --git a/include/acpi/acpixf.h b/include/acpi/acpixf.h
index c8e8cf45830f..cc40102fe2f3 100644
--- a/include/acpi/acpixf.h
+++ b/include/acpi/acpixf.h
@@ -130,6 +130,10 @@ acpi_get_table_header(acpi_string signature,
                       struct acpi_table_header *out_table_header);
 
 acpi_status
+acpi_get_table_with_size(acpi_string signature,
+               u32 instance, struct acpi_table_header **out_table,
+               acpi_size *tbl_size);
+acpi_status
 acpi_get_table(acpi_string signature,
                u32 instance, struct acpi_table_header **out_table);
 
diff --git a/include/asm-frv/swab.h b/include/asm-frv/swab.h
index afb3396ba5ed..f305834b4799 100644
--- a/include/asm-frv/swab.h
+++ b/include/asm-frv/swab.h
@@ -1,7 +1,7 @@
 #ifndef _ASM_SWAB_H
 #define _ASM_SWAB_H
 
-#include <asm/types.h>
+#include <linux/types.h>
 
 #if defined(__GNUC__) && !defined(__STRICT_ANSI__) || defined(__KERNEL__)
 #  define __SWAB_64_THRU_32__
diff --git a/include/asm-generic/percpu.h b/include/asm-generic/percpu.h
index b0e63c672ebd..00f45ff081a6 100644
--- a/include/asm-generic/percpu.h
+++ b/include/asm-generic/percpu.h
@@ -80,4 +80,56 @@ extern void setup_per_cpu_areas(void);
 #define DECLARE_PER_CPU(type, name) extern PER_CPU_ATTRIBUTES \
                                         __typeof__(type) per_cpu_var(name)
 
+/*
+ * Optional methods for optimized non-lvalue per-cpu variable access.
+ *
+ * @var can be a percpu variable or a field of it and its size should
+ * equal char, int or long.  percpu_read() evaluates to a lvalue and
+ * all others to void.
+ *
+ * These operations are guaranteed to be atomic w.r.t. preemption.
+ * The generic versions use plain get/put_cpu_var().  Archs are
+ * encouraged to implement single-instruction alternatives which don't
+ * require preemption protection.
+ */
+#ifndef percpu_read
+# define percpu_read(var)                                               \
+  ({                                                                    \
+        typeof(per_cpu_var(var)) __tmp_var__;                           \
+        __tmp_var__ = get_cpu_var(var);                                 \
+        put_cpu_var(var);                                               \
+        __tmp_var__;                                                    \
+  })
+#endif
+
+#define __percpu_generic_to_op(var, val, op)                            \
+do {                                                                    \
+        get_cpu_var(var) op val;                                        \
+        put_cpu_var(var);                                               \
+} while (0)
+
+#ifndef percpu_write
+# define percpu_write(var, val)         __percpu_generic_to_op(var, (val), =)
+#endif
+
+#ifndef percpu_add
+# define percpu_add(var, val)           __percpu_generic_to_op(var, (val), +=)
+#endif
+
+#ifndef percpu_sub
+# define percpu_sub(var, val)           __percpu_generic_to_op(var, (val), -=)
+#endif
+
+#ifndef percpu_and
+# define percpu_and(var, val)           __percpu_generic_to_op(var, (val), &=)
+#endif
+
+#ifndef percpu_or
+# define percpu_or(var, val)            __percpu_generic_to_op(var, (val), |=)
+#endif
+
+#ifndef percpu_xor
+# define percpu_xor(var, val)           __percpu_generic_to_op(var, (val), ^=)
+#endif
+
 #endif /* _ASM_GENERIC_PERCPU_H_ */
diff --git a/include/asm-generic/sections.h b/include/asm-generic/sections.h
index 79a7ff925bf8..4ce48e878530 100644
--- a/include/asm-generic/sections.h
+++ b/include/asm-generic/sections.h
@@ -9,7 +9,7 @@ extern char __bss_start[], __bss_stop[];
 extern char __init_begin[], __init_end[];
 extern char _sinittext[], _einittext[];
 extern char _end[];
-extern char __per_cpu_start[], __per_cpu_end[];
+extern char __per_cpu_load[], __per_cpu_start[], __per_cpu_end[];
 extern char __kprobes_text_start[], __kprobes_text_end[];
 extern char __initdata_begin[], __initdata_end[];
 extern char __start_rodata[], __end_rodata[];
diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
index c61fab1dd2f8..5406e70aba86 100644
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@@ -430,12 +430,59 @@
         *(.initcall7.init)                                              \
         *(.initcall7s.init)
 
+/**
+ * PERCPU_VADDR - define output section for percpu area
+ * @vaddr: explicit base address (optional)
+ * @phdr: destination PHDR (optional)
+ *
+ * Macro which expands to output section for percpu area.  If @vaddr
+ * is not blank, it specifies explicit base address and all percpu
+ * symbols will be offset from the given address.  If blank, @vaddr
+ * always equals @laddr + LOAD_OFFSET.
+ *
+ * @phdr defines the output PHDR to use if not blank.  Be warned that
+ * output PHDR is sticky.  If @phdr is specified, the next output
+ * section in the linker script will go there too.  @phdr should have
+ * a leading colon.
+ *
+ * Note that this macros defines __per_cpu_load as an absolute symbol.
+ * If there is no need to put the percpu section at a predetermined
+ * address, use PERCPU().
+ */
+#define PERCPU_VADDR(vaddr, phdr)                                       \
+        VMLINUX_SYMBOL(__per_cpu_load) = .;                             \
+        .data.percpu vaddr : AT(VMLINUX_SYMBOL(__per_cpu_load)          \
+                                - LOAD_OFFSET) {                        \
+                VMLINUX_SYMBOL(__per_cpu_start) = .;                    \
+                *(.data.percpu.first)                                   \
+                *(.data.percpu.page_aligned)                            \
+                *(.data.percpu)                                         \
+                *(.data.percpu.shared_aligned)                          \
+                VMLINUX_SYMBOL(__per_cpu_end) = .;                      \
+        } phdr                                                          \
+        . = VMLINUX_SYMBOL(__per_cpu_load) + SIZEOF(.data.percpu);
+
+/**
+ * PERCPU - define output section for percpu area, simple version
+ * @align: required alignment
+ *
+ * Align to @align and outputs output section for percpu area.  This
+ * macro doesn't maniuplate @vaddr or @phdr and __per_cpu_load and
+ * __per_cpu_start will be identical.
+ *
+ * This macro is equivalent to ALIGN(align); PERCPU_VADDR( , ) except
+ * that __per_cpu_load is defined as a relative symbol against
+ * .data.percpu which is required for relocatable x86_32
+ * configuration.
+ */
 #define PERCPU(align)                                                   \
         . = ALIGN(align);                                               \
-        VMLINUX_SYMBOL(__per_cpu_start) = .;                            \
-        .data.percpu  : AT(ADDR(.data.percpu) - LOAD_OFFSET) {          \
+        .data.percpu    : AT(ADDR(.data.percpu) - LOAD_OFFSET) {        \
+                VMLINUX_SYMBOL(__per_cpu_load) = .;                     \
+                VMLINUX_SYMBOL(__per_cpu_start) = .;                    \
+                *(.data.percpu.first)                                   \
                 *(.data.percpu.page_aligned)                            \
                 *(.data.percpu)                                         \
                 *(.data.percpu.shared_aligned)                          \
-        }                                                               \
-        VMLINUX_SYMBOL(__per_cpu_end) = .;
+                VMLINUX_SYMBOL(__per_cpu_end) = .;                      \
+        }
diff --git a/include/asm-m32r/swab.h b/include/asm-m32r/swab.h
index 97973e101825..54dab001d6d1 100644
--- a/include/asm-m32r/swab.h
+++ b/include/asm-m32r/swab.h
@@ -1,7 +1,7 @@
 #ifndef _ASM_M32R_SWAB_H
 #define _ASM_M32R_SWAB_H
 
-#include <asm/types.h>
+#include <linux/types.h>
 
 #if !defined(__STRICT_ANSI__) || defined(__KERNEL__)
 #  define __SWAB_64_THRU_32__
diff --git a/include/asm-mn10300/swab.h b/include/asm-mn10300/swab.h
index 4504d1b4b477..bd818a820ca8 100644
--- a/include/asm-mn10300/swab.h
+++ b/include/asm-mn10300/swab.h
@@ -11,7 +11,7 @@
 #ifndef _ASM_SWAB_H
 #define _ASM_SWAB_H
 
-#include <asm/types.h>
+#include <linux/types.h>
 
 #ifdef __GNUC__
 
diff --git a/include/linux/acpi.h b/include/linux/acpi.h
index 6fce2fc2d124..78199151c00b 100644
--- a/include/linux/acpi.h
+++ b/include/linux/acpi.h
@@ -79,6 +79,7 @@ typedef int (*acpi_table_handler) (struct acpi_table_header *table);
 typedef int (*acpi_table_entry_handler) (struct acpi_subtable_header *header, const unsigned long end);
 
 char * __acpi_map_table (unsigned long phys_addr, unsigned long size);
+void __acpi_unmap_table(char *map, unsigned long size);
 int early_acpi_boot_init(void);
 int acpi_boot_init (void);
 int acpi_boot_table_init (void);
diff --git a/include/linux/coda_psdev.h b/include/linux/coda_psdev.h
index 07ae8f846055..5b5d4731f956 100644
--- a/include/linux/coda_psdev.h
+++ b/include/linux/coda_psdev.h
@@ -6,6 +6,7 @@
 #define CODA_PSDEV_MAJOR 67
 #define MAX_CODADEVS  5    /* how many do we allow */
 
+#ifdef __KERNEL__
 struct kstatfs;
 
 /* communication pending/processing queues */
@@ -24,7 +25,6 @@ static inline struct venus_comm *coda_vcp(struct super_block *sb)
         return (struct venus_comm *)((sb)->s_fs_info);
 }
 
-
 /* upcalls */
 int venus_rootfid(struct super_block *sb, struct CodaFid *fidp);
 int venus_getattr(struct super_block *sb, struct CodaFid *fid,
@@ -64,6 +64,12 @@ int coda_downcall(int opcode, union outputArgs *out, struct super_block *sb);
 int venus_fsync(struct super_block *sb, struct CodaFid *fid);
 int venus_statfs(struct dentry *dentry, struct kstatfs *sfs);
 
+/*
+ * Statistics
+ */
+
+extern struct venus_comm coda_comms[];
+#endif /* __KERNEL__ */
 
 /* messages between coda filesystem in kernel and Venus */
 struct upc_req {
@@ -82,11 +88,4 @@ struct upc_req {
 #define REQ_WRITE  0x4
 #define REQ_ABORT  0x8
 
-
-/*
- * Statistics
- */
-
-extern struct venus_comm coda_comms[];
-
 #endif
diff --git a/include/linux/elfcore.h b/include/linux/elfcore.h
index 5ca54d77079f..7605c5e9589f 100644
--- a/include/linux/elfcore.h
+++ b/include/linux/elfcore.h
@@ -111,6 +111,15 @@ static inline void elf_core_copy_regs(elf_gregset_t *elfregs, struct pt_regs *re
 #endif
 }
 
+static inline void elf_core_copy_kernel_regs(elf_gregset_t *elfregs, struct pt_regs *regs)
+{
+#ifdef ELF_CORE_COPY_KERNEL_REGS
+        ELF_CORE_COPY_KERNEL_REGS((*elfregs), regs);
+#else
+        elf_core_copy_regs(elfregs, regs);
+#endif
+}
+
 static inline int elf_core_copy_task_regs(struct task_struct *t, elf_gregset_t* elfregs)
 {
 #ifdef ELF_CORE_COPY_TASK_REGS
diff --git a/include/linux/in6.h b/include/linux/in6.h
index bc492048c349..718bf21c5754 100644
--- a/include/linux/in6.h
+++ b/include/linux/in6.h
@@ -44,11 +44,11 @@ struct in6_addr
  * NOTE: Be aware the IN6ADDR_* constants and in6addr_* externals are defined
  * in network byte order, not in host byte order as are the IPv4 equivalents
  */
+#ifdef __KERNEL__
 extern const struct in6_addr in6addr_any;
 #define IN6ADDR_ANY_INIT { { { 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0 } } }
 extern const struct in6_addr in6addr_loopback;
 #define IN6ADDR_LOOPBACK_INIT { { { 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,1 } } }
-#ifdef __KERNEL__
 extern const struct in6_addr in6addr_linklocal_allnodes;
 #define IN6ADDR_LINKLOCAL_ALLNODES_INIT \
                 { { { 0xff,2,0,0,0,0,0,0,0,0,0,0,0,0,0,1 } } }
diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h
index 9127f6b51a39..472f11765f60 100644
--- a/include/linux/interrupt.h
+++ b/include/linux/interrupt.h
@@ -467,6 +467,7 @@ int show_interrupts(struct seq_file *p, void *v);
 struct irq_desc;
 
 extern int early_irq_init(void);
+extern int arch_probe_nr_irqs(void);
 extern int arch_early_irq_init(void);
 extern int arch_init_chip_data(struct irq_desc *desc, int cpu);
 
diff --git a/include/linux/io-mapping.h b/include/linux/io-mapping.h
index 82df31726a54..f1ed66c43787 100644
--- a/include/linux/io-mapping.h
+++ b/include/linux/io-mapping.h
@@ -30,11 +30,14 @@
  * See Documentation/io_mapping.txt
  */
 
-/* this struct isn't actually defined anywhere */
-struct io_mapping;
-
 #ifdef CONFIG_HAVE_ATOMIC_IOMAP
 
+struct io_mapping {
+        resource_size_t base;
+        unsigned long size;
+        pgprot_t prot;
+};
+
 /*
  * For small address space machines, mapping large objects
  * into the kernel virtual space isn't practical. Where
@@ -43,23 +46,42 @@ struct io_mapping;
  */
 
 static inline struct io_mapping *
-io_mapping_create_wc(unsigned long base, unsigned long size)
+io_mapping_create_wc(resource_size_t base, unsigned long size)
 {
-        return (struct io_mapping *) base;
+        struct io_mapping *iomap;
+        pgprot_t prot;
+
+        if (!reserve_io_memtype_wc(base, size, &prot))
+                return NULL;
+
+        iomap = kmalloc(sizeof(*iomap), GFP_KERNEL);
+        if (!iomap)
+                return NULL;
+
+        iomap->base = base;
+        iomap->size = size;
+        iomap->prot = prot;
+        return iomap;
 }
 
 static inline void
 io_mapping_free(struct io_mapping *mapping)
 {
+        free_io_memtype(mapping->base, mapping->size);
+        kfree(mapping);
 }
 
 /* Atomic map/unmap */
 static inline void *
 io_mapping_map_atomic_wc(struct io_mapping *mapping, unsigned long offset)
 {
-        offset += (unsigned long) mapping;
-        return iomap_atomic_prot_pfn(offset >> PAGE_SHIFT, KM_USER0,
-                                     __pgprot(__PAGE_KERNEL_WC));
+        resource_size_t phys_addr;
+        unsigned long pfn;
+
+        BUG_ON(offset >= mapping->size);
+        phys_addr = mapping->base + offset;
+        pfn = (unsigned long) (phys_addr >> PAGE_SHIFT);
+        return iomap_atomic_prot_pfn(pfn, KM_USER0, mapping->prot);
 }
 
 static inline void
@@ -71,8 +93,9 @@ io_mapping_unmap_atomic(void *vaddr)
 static inline void *
 io_mapping_map_wc(struct io_mapping *mapping, unsigned long offset)
 {
-        offset += (unsigned long) mapping;
-        return ioremap_wc(offset, PAGE_SIZE);
+        BUG_ON(offset >= mapping->size);
+        resource_size_t phys_addr = mapping->base + offset;
+        return ioremap_wc(phys_addr, PAGE_SIZE);
 }
 
 static inline void
@@ -83,9 +106,12 @@ io_mapping_unmap(void *vaddr)
 
 #else
 
+/* this struct isn't actually defined anywhere */
+struct io_mapping;
+
 /* Create the io_mapping object*/
 static inline struct io_mapping *
-io_mapping_create_wc(unsigned long base, unsigned long size)
+io_mapping_create_wc(resource_size_t base, unsigned long size)
 {
         return (struct io_mapping *) ioremap_wc(base, size);
 }
diff --git a/include/linux/irq.h b/include/linux/irq.h
index f899b502f186..27a67536511e 100644
--- a/include/linux/irq.h
+++ b/include/linux/irq.h
@@ -182,11 +182,11 @@ struct irq_desc {
         unsigned int            irqs_unhandled;
         spinlock_t              lock;
 #ifdef CONFIG_SMP
-        cpumask_t               affinity;
+        cpumask_var_t           affinity;
         unsigned int            cpu;
-#endif
 #ifdef CONFIG_GENERIC_PENDING_IRQ
-        cpumask_t               pending_mask;
+        cpumask_var_t           pending_mask;
+#endif
 #endif
 #ifdef CONFIG_PROC_FS
         struct proc_dir_entry   *dir;
@@ -422,4 +422,84 @@ extern int set_irq_msi(unsigned int irq, struct msi_desc *entry);
 
 #endif /* !CONFIG_S390 */
 
+#ifdef CONFIG_SMP
+/**
+ * init_alloc_desc_masks - allocate cpumasks for irq_desc
+ * @desc:       pointer to irq_desc struct
+ * @cpu:        cpu which will be handling the cpumasks
+ * @boot:       true if need bootmem
+ *
+ * Allocates affinity and pending_mask cpumask if required.
+ * Returns true if successful (or not required).
+ * Side effect: affinity has all bits set, pending_mask has all bits clear.
+ */
+static inline bool init_alloc_desc_masks(struct irq_desc *desc, int cpu,
+                                                                bool boot)
+{
+        int node;
+
+        if (boot) {
+                alloc_bootmem_cpumask_var(&desc->affinity);
+                cpumask_setall(desc->affinity);
+
+#ifdef CONFIG_GENERIC_PENDING_IRQ
+                alloc_bootmem_cpumask_var(&desc->pending_mask);
+                cpumask_clear(desc->pending_mask);
+#endif
+                return true;
+        }
+
+        node = cpu_to_node(cpu);
+
+        if (!alloc_cpumask_var_node(&desc->affinity, GFP_ATOMIC, node))
+                return false;
+        cpumask_setall(desc->affinity);
+
+#ifdef CONFIG_GENERIC_PENDING_IRQ
+        if (!alloc_cpumask_var_node(&desc->pending_mask, GFP_ATOMIC, node)) {
+                free_cpumask_var(desc->affinity);
+                return false;
+        }
+        cpumask_clear(desc->pending_mask);
+#endif
+        return true;
+}
+
+/**
+ * init_copy_desc_masks - copy cpumasks for irq_desc
+ * @old_desc:   pointer to old irq_desc struct
+ * @new_desc:   pointer to new irq_desc struct
+ *
+ * Insures affinity and pending_masks are copied to new irq_desc.
+ * If !CONFIG_CPUMASKS_OFFSTACK the cpumasks are embedded in the
+ * irq_desc struct so the copy is redundant.
+ */
+
+static inline void init_copy_desc_masks(struct irq_desc *old_desc,
+                                        struct irq_desc *new_desc)
+{
+#ifdef CONFIG_CPUMASKS_OFFSTACK
+        cpumask_copy(new_desc->affinity, old_desc->affinity);
+
+#ifdef CONFIG_GENERIC_PENDING_IRQ
+        cpumask_copy(new_desc->pending_mask, old_desc->pending_mask);
+#endif
+#endif
+}
+
+#else /* !CONFIG_SMP */
+
+static inline bool init_alloc_desc_masks(struct irq_desc *desc, int cpu,
+                                                                bool boot)
+{
+        return true;
+}
+
+static inline void init_copy_desc_masks(struct irq_desc *old_desc,
+                                        struct irq_desc *new_desc)
+{
+}
+
+#endif  /* CONFIG_SMP */
+
 #endif /* _LINUX_IRQ_H */
diff --git a/include/linux/irqnr.h b/include/linux/irqnr.h
index 86af92e9e84c..887477bc2ab0 100644
--- a/include/linux/irqnr.h
+++ b/include/linux/irqnr.h
@@ -20,6 +20,7 @@
 
 # define for_each_irq_desc_reverse(irq, desc)                          \
         for (irq = nr_irqs - 1; irq >= 0; irq--)
+
 #else /* CONFIG_GENERIC_HARDIRQS */
 
 extern int nr_irqs;
diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h
index 32851eef48f0..2ec6cc14a114 100644
--- a/include/linux/kprobes.h
+++ b/include/linux/kprobes.h
@@ -182,6 +182,14 @@ struct kprobe_blackpoint {
 DECLARE_PER_CPU(struct kprobe *, current_kprobe);
 DECLARE_PER_CPU(struct kprobe_ctlblk, kprobe_ctlblk);
 
+/*
+ * For #ifdef avoidance:
+ */
+static inline int kprobes_built_in(void)
+{
+        return 1;
+}
+
 #ifdef CONFIG_KRETPROBES
 extern void arch_prepare_kretprobe(struct kretprobe_instance *ri,
                                    struct pt_regs *regs);
@@ -271,8 +279,16 @@ void unregister_kretprobes(struct kretprobe **rps, int num);
 void kprobe_flush_task(struct task_struct *tk);
 void recycle_rp_inst(struct kretprobe_instance *ri, struct hlist_head *head);
 
-#else /* CONFIG_KPROBES */
+#else /* !CONFIG_KPROBES: */
 
+static inline int kprobes_built_in(void)
+{
+        return 0;
+}
+static inline int kprobe_fault_handler(struct pt_regs *regs, int trapnr)
+{
+        return 0;
+}
 static inline struct kprobe *get_kprobe(void *addr)
 {
         return NULL;
@@ -329,5 +345,5 @@ static inline void unregister_kretprobes(struct kretprobe **rps, int num)
 static inline void kprobe_flush_task(struct task_struct *tk)
 {
 }
-#endif                          /* CONFIG_KPROBES */
-#endif                          /* _LINUX_KPROBES_H */
+#endif /* CONFIG_KPROBES */
+#endif /* _LINUX_KPROBES_H */
diff --git a/include/linux/magic.h b/include/linux/magic.h
index 0b4df7eba852..5b4e28bcb788 100644
--- a/include/linux/magic.h
+++ b/include/linux/magic.h
@@ -49,4 +49,5 @@
 #define FUTEXFS_SUPER_MAGIC     0xBAD1DEA
 #define INOTIFYFS_SUPER_MAGIC   0x2BAD1DEA
 
+#define STACK_END_MAGIC         0x57AC6E9D
 #endif /* __LINUX_MAGIC_H__ */
diff --git a/include/linux/mmiotrace.h b/include/linux/mmiotrace.h
index 139d7c88d9c9..3d1b7bde1283 100644
--- a/include/linux/mmiotrace.h
+++ b/include/linux/mmiotrace.h
@@ -1,5 +1,5 @@
-#ifndef MMIOTRACE_H
-#define MMIOTRACE_H
+#ifndef _LINUX_MMIOTRACE_H
+#define _LINUX_MMIOTRACE_H
 
 #include <linux/types.h>
 #include <linux/list.h>
@@ -13,28 +13,34 @@ typedef void (*kmmio_post_handler_t)(struct kmmio_probe *,
                                 unsigned long condition, struct pt_regs *);
 
 struct kmmio_probe {
-        struct list_head list; /* kmmio internal list */
-        unsigned long addr; /* start location of the probe point */
-        unsigned long len; /* length of the probe region */
-        kmmio_pre_handler_t pre_handler; /* Called before addr is executed. */
-        kmmio_post_handler_t post_handler; /* Called after addr is executed */
-        void *private;
+        /* kmmio internal list: */
+        struct list_head        list;
+        /* start location of the probe point: */
+        unsigned long           addr;
+        /* length of the probe region: */
+        unsigned long           len;
+        /* Called before addr is executed: */
+        kmmio_pre_handler_t     pre_handler;
+        /* Called after addr is executed: */
+        kmmio_post_handler_t    post_handler;
+        void                    *private;
 };
 
+extern unsigned int kmmio_count;
+
+extern int register_kmmio_probe(struct kmmio_probe *p);
+extern void unregister_kmmio_probe(struct kmmio_probe *p);
+
+#ifdef CONFIG_MMIOTRACE
 /* kmmio is active by some kmmio_probes? */
 static inline int is_kmmio_active(void)
 {
-        extern unsigned int kmmio_count;
         return kmmio_count;
 }
 
-extern int register_kmmio_probe(struct kmmio_probe *p);
-extern void unregister_kmmio_probe(struct kmmio_probe *p);
-
 /* Called from page fault handler. */
 extern int kmmio_handler(struct pt_regs *regs, unsigned long addr);
 
-#ifdef CONFIG_MMIOTRACE
 /* Called from ioremap.c */
 extern void mmiotrace_ioremap(resource_size_t offset, unsigned long size,
                                                         void __iomem *addr);
@@ -43,7 +49,17 @@ extern void mmiotrace_iounmap(volatile void __iomem *addr);
 /* For anyone to insert markers. Remember trailing newline. */
 extern int mmiotrace_printk(const char *fmt, ...)
                                 __attribute__ ((format (printf, 1, 2)));
-#else
+#else /* !CONFIG_MMIOTRACE: */
+static inline int is_kmmio_active(void)
+{
+        return 0;
+}
+
+static inline int kmmio_handler(struct pt_regs *regs, unsigned long addr)
+{
+        return 0;
+}
+
 static inline void mmiotrace_ioremap(resource_size_t offset,
                                         unsigned long size, void __iomem *addr)
 {
@@ -63,28 +79,28 @@ static inline int mmiotrace_printk(const char *fmt, ...)
 #endif /* CONFIG_MMIOTRACE */
 
 enum mm_io_opcode {
-        MMIO_READ = 0x1,     /* struct mmiotrace_rw */
-        MMIO_WRITE = 0x2,    /* struct mmiotrace_rw */
-        MMIO_PROBE = 0x3,    /* struct mmiotrace_map */
-        MMIO_UNPROBE = 0x4,  /* struct mmiotrace_map */
-        MMIO_UNKNOWN_OP = 0x5, /* struct mmiotrace_rw */
+        MMIO_READ       = 0x1,  /* struct mmiotrace_rw */
+        MMIO_WRITE      = 0x2,  /* struct mmiotrace_rw */
+        MMIO_PROBE      = 0x3,  /* struct mmiotrace_map */
+        MMIO_UNPROBE    = 0x4,  /* struct mmiotrace_map */
+        MMIO_UNKNOWN_OP = 0x5,  /* struct mmiotrace_rw */
 };
 
 struct mmiotrace_rw {
-        resource_size_t phys;   /* PCI address of register */
-        unsigned long value;
-        unsigned long pc;       /* optional program counter */
-        int map_id;
-        unsigned char opcode;   /* one of MMIO_{READ,WRITE,UNKNOWN_OP} */
-        unsigned char width;    /* size of register access in bytes */
+        resource_size_t phys;   /* PCI address of register */
+        unsigned long   value;
+        unsigned long   pc;     /* optional program counter */
+        int             map_id;
+        unsigned char   opcode; /* one of MMIO_{READ,WRITE,UNKNOWN_OP} */
+        unsigned char   width;  /* size of register access in bytes */
 };
 
 struct mmiotrace_map {
-        resource_size_t phys;   /* base address in PCI space */
-        unsigned long virt;     /* base virtual address */
-        unsigned long len;      /* mapping size */
-        int map_id;
-        unsigned char opcode;   /* MMIO_PROBE or MMIO_UNPROBE */
+        resource_size_t phys;   /* base address in PCI space */
+        unsigned long   virt;   /* base virtual address */
+        unsigned long   len;    /* mapping size */
+        int             map_id;
+        unsigned char   opcode; /* MMIO_PROBE or MMIO_UNPROBE */
 };
 
 /* in kernel/trace/trace_mmiotrace.c */
@@ -94,4 +110,4 @@ extern void mmio_trace_rw(struct mmiotrace_rw *rw);
 extern void mmio_trace_mapping(struct mmiotrace_map *map);
 extern int mmio_trace_printk(const char *fmt, va_list args);
 
-#endif /* MMIOTRACE_H */
+#endif /* _LINUX_MMIOTRACE_H */
diff --git a/include/linux/nubus.h b/include/linux/nubus.h
index 7382af374731..e137b3c486a7 100644
--- a/include/linux/nubus.h
+++ b/include/linux/nubus.h
@@ -237,6 +237,7 @@ struct nubus_dirent
         int mask;
 };
 
+#ifdef __KERNEL__
 struct nubus_board {
         struct nubus_board* next;
         struct nubus_dev* first_dev;
@@ -351,6 +352,7 @@ void nubus_get_rsrc_mem(void* dest,
 void nubus_get_rsrc_str(void* dest,
                         const struct nubus_dirent *dirent,
                         int maxlen);
+#endif /* __KERNEL__ */
 
 /* We'd like to get rid of this eventually.  Only daynaport.c uses it now. */
 static inline void *nubus_slot_addr(int slot)
diff --git a/include/linux/percpu.h b/include/linux/percpu.h
index 9f2a3751873a..3577ffd90d45 100644
--- a/include/linux/percpu.h
+++ b/include/linux/percpu.h
@@ -8,35 +8,46 @@
 
 #include <asm/percpu.h>
 
+#ifndef PER_CPU_BASE_SECTION
+#ifdef CONFIG_SMP
+#define PER_CPU_BASE_SECTION ".data.percpu"
+#else
+#define PER_CPU_BASE_SECTION ".data"
+#endif
+#endif
+
 #ifdef CONFIG_SMP
-#define DEFINE_PER_CPU(type, name)                                      \
-        __attribute__((__section__(".data.percpu")))                    \
-        PER_CPU_ATTRIBUTES __typeof__(type) per_cpu__##name
 
 #ifdef MODULE
-#define SHARED_ALIGNED_SECTION ".data.percpu"
+#define PER_CPU_SHARED_ALIGNED_SECTION ""
 #else
-#define SHARED_ALIGNED_SECTION ".data.percpu.shared_aligned"
+#define PER_CPU_SHARED_ALIGNED_SECTION ".shared_aligned"
 #endif
+#define PER_CPU_FIRST_SECTION ".first"
 
-#define DEFINE_PER_CPU_SHARED_ALIGNED(type, name)                       \
-        __attribute__((__section__(SHARED_ALIGNED_SECTION)))            \
-        PER_CPU_ATTRIBUTES __typeof__(type) per_cpu__##name             \
-        ____cacheline_aligned_in_smp
+#else
 
-#define DEFINE_PER_CPU_PAGE_ALIGNED(type, name)                 \
-        __attribute__((__section__(".data.percpu.page_aligned")))       \
+#define PER_CPU_SHARED_ALIGNED_SECTION ""
+#define PER_CPU_FIRST_SECTION ""
+
+#endif
+
+#define DEFINE_PER_CPU_SECTION(type, name, section)                     \
+        __attribute__((__section__(PER_CPU_BASE_SECTION section)))      \
         PER_CPU_ATTRIBUTES __typeof__(type) per_cpu__##name
-#else
+
 #define DEFINE_PER_CPU(type, name)                                      \
-        PER_CPU_ATTRIBUTES __typeof__(type) per_cpu__##name
+        DEFINE_PER_CPU_SECTION(type, name, "")
 
-#define DEFINE_PER_CPU_SHARED_ALIGNED(type, name)                     \
-        DEFINE_PER_CPU(type, name)
+#define DEFINE_PER_CPU_SHARED_ALIGNED(type, name)                       \
+        DEFINE_PER_CPU_SECTION(type, name, PER_CPU_SHARED_ALIGNED_SECTION) \
+        ____cacheline_aligned_in_smp
 
-#define DEFINE_PER_CPU_PAGE_ALIGNED(type, name)               \
-        DEFINE_PER_CPU(type, name)
-#endif
+#define DEFINE_PER_CPU_PAGE_ALIGNED(type, name)                         \
+        DEFINE_PER_CPU_SECTION(type, name, ".page_aligned")
+
+#define DEFINE_PER_CPU_FIRST(type, name)                                \
+        DEFINE_PER_CPU_SECTION(type, name, PER_CPU_FIRST_SECTION)
 
 #define EXPORT_PER_CPU_SYMBOL(var) EXPORT_SYMBOL(per_cpu__##var)
 #define EXPORT_PER_CPU_SYMBOL_GPL(var) EXPORT_SYMBOL_GPL(per_cpu__##var)
diff --git a/include/linux/reiserfs_fs.h b/include/linux/reiserfs_fs.h
index bc5114d35e99..e356c99f0659 100644
--- a/include/linux/reiserfs_fs.h
+++ b/include/linux/reiserfs_fs.h
@@ -28,8 +28,6 @@
 #include <linux/reiserfs_fs_sb.h>
 #endif
 
-struct fid;
-
 /*
  *  include/linux/reiser_fs.h
  *
@@ -37,6 +35,33 @@ struct fid;
  *
  */
 
+/* ioctl's command */
+#define REISERFS_IOC_UNPACK             _IOW(0xCD,1,long)
+/* define following flags to be the same as in ext2, so that chattr(1),
+   lsattr(1) will work with us. */
+#define REISERFS_IOC_GETFLAGS           FS_IOC_GETFLAGS
+#define REISERFS_IOC_SETFLAGS           FS_IOC_SETFLAGS
+#define REISERFS_IOC_GETVERSION         FS_IOC_GETVERSION
+#define REISERFS_IOC_SETVERSION         FS_IOC_SETVERSION
+
+#ifdef __KERNEL__
+/* the 32 bit compat definitions with int argument */
+#define REISERFS_IOC32_UNPACK           _IOW(0xCD, 1, int)
+#define REISERFS_IOC32_GETFLAGS         FS_IOC32_GETFLAGS
+#define REISERFS_IOC32_SETFLAGS         FS_IOC32_SETFLAGS
+#define REISERFS_IOC32_GETVERSION       FS_IOC32_GETVERSION
+#define REISERFS_IOC32_SETVERSION       FS_IOC32_SETVERSION
+
+/* Locking primitives */
+/* Right now we are still falling back to (un)lock_kernel, but eventually that
+   would evolve into real per-fs locks */
+#define reiserfs_write_lock( sb ) lock_kernel()
+#define reiserfs_write_unlock( sb ) unlock_kernel()
+
+/* xattr stuff */
+#define REISERFS_XATTR_DIR_SEM(s) (REISERFS_SB(s)->xattr_dir_sem)
+struct fid;
+
 /* in reading the #defines, it may help to understand that they employ
    the following abbreviations:
 
@@ -698,6 +723,7 @@ static inline void cpu_key_k_offset_dec(struct cpu_key *key)
 /* object identifier for root dir */
 #define REISERFS_ROOT_OBJECTID 2
 #define REISERFS_ROOT_PARENT_OBJECTID 1
+
 extern struct reiserfs_key root_key;
 
 /* 
@@ -1540,7 +1566,6 @@ struct reiserfs_iget_args {
 /*                    FUNCTION DECLARATIONS                                */
 /***************************************************************************/
 
-/*#ifdef __KERNEL__*/
 #define get_journal_desc_magic(bh) (bh->b_data + bh->b_size - 12)
 
 #define journal_trans_half(blocksize) \
@@ -2178,29 +2203,6 @@ long reiserfs_compat_ioctl(struct file *filp,
                    unsigned int cmd, unsigned long arg);
 int reiserfs_unpack(struct inode *inode, struct file *filp);
 
-/* ioctl's command */
-#define REISERFS_IOC_UNPACK             _IOW(0xCD,1,long)
-/* define following flags to be the same as in ext2, so that chattr(1),
-   lsattr(1) will work with us. */
-#define REISERFS_IOC_GETFLAGS           FS_IOC_GETFLAGS
-#define REISERFS_IOC_SETFLAGS           FS_IOC_SETFLAGS
-#define REISERFS_IOC_GETVERSION         FS_IOC_GETVERSION
-#define REISERFS_IOC_SETVERSION         FS_IOC_SETVERSION
-
-/* the 32 bit compat definitions with int argument */
-#define REISERFS_IOC32_UNPACK           _IOW(0xCD, 1, int)
-#define REISERFS_IOC32_GETFLAGS         FS_IOC32_GETFLAGS
-#define REISERFS_IOC32_SETFLAGS         FS_IOC32_SETFLAGS
-#define REISERFS_IOC32_GETVERSION       FS_IOC32_GETVERSION
-#define REISERFS_IOC32_SETVERSION       FS_IOC32_SETVERSION
-
-/* Locking primitives */
-/* Right now we are still falling back to (un)lock_kernel, but eventually that
-   would evolve into real per-fs locks */
-#define reiserfs_write_lock( sb ) lock_kernel()
-#define reiserfs_write_unlock( sb ) unlock_kernel()
-
-/* xattr stuff */
-#define REISERFS_XATTR_DIR_SEM(s) (REISERFS_SB(s)->xattr_dir_sem)
 
+#endif /* __KERNEL__ */
 #endif                          /* _LINUX_REISER_FS_H */
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 8981e52c714f..f0a50b20e8a0 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1178,10 +1178,9 @@ struct task_struct {
         pid_t pid;
         pid_t tgid;
 
-#ifdef CONFIG_CC_STACKPROTECTOR
         /* Canary value for the -fstack-protector gcc feature */
         unsigned long stack_canary;
-#endif
+
         /* 
          * pointers to (original) parent process, youngest child, younger sibling,
          * older sibling, respectively.  (p->father can be replaced with 
@@ -2087,6 +2086,19 @@ static inline int object_is_on_stack(void *obj)
 
 extern void thread_info_cache_init(void);
 
+#ifdef CONFIG_DEBUG_STACK_USAGE
+static inline unsigned long stack_not_used(struct task_struct *p)
+{
+        unsigned long *n = end_of_stack(p);
+
+        do {    /* Skip over canary */
+                n++;
+        } while (!*n);
+
+        return (unsigned long)n - (unsigned long)end_of_stack(p);
+}
+#endif
+
 /* set thread flags in other task's structures
  * - see asm/thread_info.h for TIF_xxxx flags available
  */
diff --git a/include/linux/smp.h b/include/linux/smp.h
index 715196b09d67..bbacb7baa446 100644
--- a/include/linux/smp.h
+++ b/include/linux/smp.h
@@ -176,6 +176,12 @@ static inline void init_call_single_data(void)
 #define put_cpu()               preempt_enable()
 #define put_cpu_no_resched()    preempt_enable_no_resched()
 
+/*
+ * Callback to arch code if there's nosmp or maxcpus=0 on the
+ * boot command line:
+ */
+extern void arch_disable_smp_support(void);
+
 void smp_setup_processor_id(void);
 
 #endif /* __LINUX_SMP_H */
diff --git a/include/linux/socket.h b/include/linux/socket.h
index 20fc4bbfca42..afc01909a428 100644
--- a/include/linux/socket.h
+++ b/include/linux/socket.h
@@ -24,10 +24,12 @@ struct __kernel_sockaddr_storage {
 #include <linux/types.h>                /* pid_t                        */
 #include <linux/compiler.h>             /* __user                       */
 
-#ifdef CONFIG_PROC_FS
+#ifdef __KERNEL__
+# ifdef CONFIG_PROC_FS
 struct seq_file;
 extern void socket_seq_show(struct seq_file *seq);
-#endif
+# endif
+#endif /* __KERNEL__ */
 
 typedef unsigned short  sa_family_t;
 
diff --git a/include/linux/stackprotector.h b/include/linux/stackprotector.h
new file mode 100644
index 000000000000..6f3e54c704c0
--- /dev/null
+++ b/include/linux/stackprotector.h
@@ -0,0 +1,16 @@
+#ifndef _LINUX_STACKPROTECTOR_H
+#define _LINUX_STACKPROTECTOR_H 1
+
+#include <linux/compiler.h>
+#include <linux/sched.h>
+#include <linux/random.h>
+
+#ifdef CONFIG_CC_STACKPROTECTOR
+# include <asm/stackprotector.h>
+#else
+static inline void boot_init_stack_canary(void)
+{
+}
+#endif
+
+#endif
diff --git a/include/linux/topology.h b/include/linux/topology.h
index e632d29f0544..a16b9e06f2e5 100644
--- a/include/linux/topology.h
+++ b/include/linux/topology.h
@@ -193,5 +193,11 @@ int arch_update_cpu_topology(void);
 #ifndef topology_core_siblings
 #define topology_core_siblings(cpu)             cpumask_of_cpu(cpu)
 #endif
+#ifndef topology_thread_cpumask
+#define topology_thread_cpumask(cpu)            cpumask_of(cpu)
+#endif
+#ifndef topology_core_cpumask
+#define topology_core_cpumask(cpu)              cpumask_of(cpu)
+#endif
 
 #endif /* _LINUX_TOPOLOGY_H */
diff --git a/include/linux/types.h b/include/linux/types.h
index 712ca53bc348..fca82ed55f49 100644
--- a/include/linux/types.h
+++ b/include/linux/types.h
@@ -1,6 +1,9 @@
 #ifndef _LINUX_TYPES_H
 #define _LINUX_TYPES_H
 
+#include <asm/types.h>
+
+#ifndef __ASSEMBLY__
 #ifdef  __KERNEL__
 
 #define DECLARE_BITMAP(name,bits) \
@@ -9,7 +12,6 @@
 #endif
 
 #include <linux/posix_types.h>
-#include <asm/types.h>
 
 #ifndef __KERNEL_STRICT_NAMES
 
@@ -212,5 +214,5 @@ struct ustat {
 };
 
 #endif  /* __KERNEL__ */
-
+#endif /*  __ASSEMBLY__ */
 #endif /* _LINUX_TYPES_H */
diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h
index 6b58367d145e..6f3c603b0d67 100644
--- a/include/linux/uaccess.h
+++ b/include/linux/uaccess.h
@@ -41,13 +41,13 @@ static inline void pagefault_enable(void)
 #ifndef ARCH_HAS_NOCACHE_UACCESS
 
 static inline unsigned long __copy_from_user_inatomic_nocache(void *to,
-                                const void __user *from, unsigned long n)
+                const void __user *from, unsigned long n, unsigned long total)
 {
         return __copy_from_user_inatomic(to, from, n);
 }
 
 static inline unsigned long __copy_from_user_nocache(void *to,
-                                const void __user *from, unsigned long n)
+                const void __user *from, unsigned long n, unsigned long total)
 {
         return __copy_from_user(to, from, n);
 }