22 files changed, 884 insertions, 482 deletions

diff --git a/arch/ia64/kernel/acpi.c b/arch/ia64/kernel/acpi.c
index 7e926471e4ec..9ad94ddf6687 100644
--- a/arch/ia64/kernel/acpi.c
+++ b/arch/ia64/kernel/acpi.c
@@ -838,7 +838,7 @@ EXPORT_SYMBOL(acpi_unmap_lsapic);
 #endif                          /* CONFIG_ACPI_HOTPLUG_CPU */
 
 #ifdef CONFIG_ACPI_NUMA
-acpi_status __devinit
+static acpi_status __devinit
 acpi_map_iosapic(acpi_handle handle, u32 depth, void *context, void **ret)
 {
         struct acpi_buffer buffer = { ACPI_ALLOCATE_BUFFER, NULL };
@@ -890,7 +890,16 @@ acpi_map_iosapic(acpi_handle handle, u32 depth, void *context, void **ret)
         map_iosapic_to_node(gsi_base, node);
         return AE_OK;
 }
-#endif                          /* CONFIG_NUMA */
+
+static int __init
+acpi_map_iosapics (void)
+{
+        acpi_get_devices(NULL, acpi_map_iosapic, NULL, NULL);
+        return 0;
+}
+
+fs_initcall(acpi_map_iosapics);
+#endif                          /* CONFIG_ACPI_NUMA */
 
 int acpi_register_ioapic(acpi_handle handle, u64 phys_addr, u32 gsi_base)
 {
diff --git a/arch/ia64/kernel/cyclone.c b/arch/ia64/kernel/cyclone.c
index 768c7e46957c..6ade3790ce07 100644
--- a/arch/ia64/kernel/cyclone.c
+++ b/arch/ia64/kernel/cyclone.c
@@ -2,6 +2,7 @@
 #include <linux/smp.h>
 #include <linux/time.h>
 #include <linux/errno.h>
+#include <linux/timex.h>
 #include <asm/io.h>
 
 /* IBM Summit (EXA) Cyclone counter code*/
diff --git a/arch/ia64/kernel/efi.c b/arch/ia64/kernel/efi.c
index 179f230816ed..a3aa45cbcfa0 100644
--- a/arch/ia64/kernel/efi.c
+++ b/arch/ia64/kernel/efi.c
@@ -239,57 +239,30 @@ is_available_memory (efi_memory_desc_t *md)
         return 0;
 }
 
-/*
- * Trim descriptor MD so its starts at address START_ADDR.  If the descriptor covers
- * memory that is normally available to the kernel, issue a warning that some memory
- * is being ignored.
- */
-static void
-trim_bottom (efi_memory_desc_t *md, u64 start_addr)
-{
-        u64 num_skipped_pages;
+typedef struct kern_memdesc {
+        u64 attribute;
+        u64 start;
+        u64 num_pages;
+} kern_memdesc_t;
 
-        if (md->phys_addr >= start_addr || !md->num_pages)
-                return;
-
-        num_skipped_pages = (start_addr - md->phys_addr) >> EFI_PAGE_SHIFT;
-        if (num_skipped_pages > md->num_pages)
-                num_skipped_pages = md->num_pages;
-
-        if (is_available_memory(md))
-                printk(KERN_NOTICE "efi.%s: ignoring %luKB of memory at 0x%lx due to granule hole "
-                       "at 0x%lx\n", __FUNCTION__,
-                       (num_skipped_pages << EFI_PAGE_SHIFT) >> 10,
-                       md->phys_addr, start_addr - IA64_GRANULE_SIZE);
-        /*
-         * NOTE: Don't set md->phys_addr to START_ADDR because that could cause the memory
-         * descriptor list to become unsorted.  In such a case, md->num_pages will be
-         * zero, so the Right Thing will happen.
-         */
-        md->phys_addr += num_skipped_pages << EFI_PAGE_SHIFT;
-        md->num_pages -= num_skipped_pages;
-}
+static kern_memdesc_t *kern_memmap;
 
 static void
-trim_top (efi_memory_desc_t *md, u64 end_addr)
+walk (efi_freemem_callback_t callback, void *arg, u64 attr)
 {
-        u64 num_dropped_pages, md_end_addr;
-
-        md_end_addr = md->phys_addr + (md->num_pages << EFI_PAGE_SHIFT);
-
-        if (md_end_addr <= end_addr || !md->num_pages)
-                return;
+        kern_memdesc_t *k;
+        u64 start, end, voff;
 
-        num_dropped_pages = (md_end_addr - end_addr) >> EFI_PAGE_SHIFT;
-        if (num_dropped_pages > md->num_pages)
-                num_dropped_pages = md->num_pages;
-
-        if (is_available_memory(md))
-                printk(KERN_NOTICE "efi.%s: ignoring %luKB of memory at 0x%lx due to granule hole "
-                       "at 0x%lx\n", __FUNCTION__,
-                       (num_dropped_pages << EFI_PAGE_SHIFT) >> 10,
-                       md->phys_addr, end_addr);
-        md->num_pages -= num_dropped_pages;
+        voff = (attr == EFI_MEMORY_WB) ? PAGE_OFFSET : __IA64_UNCACHED_OFFSET;
+        for (k = kern_memmap; k->start != ~0UL; k++) {
+                if (k->attribute != attr)
+                        continue;
+                start = PAGE_ALIGN(k->start);
+                end = (k->start + (k->num_pages << EFI_PAGE_SHIFT)) & PAGE_MASK;
+                if (start < end)
+                        if ((*callback)(start + voff, end + voff, arg) < 0)
+                                return;
+        }
 }
 
 /*
@@ -299,148 +272,19 @@ trim_top (efi_memory_desc_t *md, u64 end_addr)
 void
 efi_memmap_walk (efi_freemem_callback_t callback, void *arg)
 {
-        int prev_valid = 0;
-        struct range {
-                u64 start;
-                u64 end;
-        } prev, curr;
-        void *efi_map_start, *efi_map_end, *p, *q;
-        efi_memory_desc_t *md, *check_md;
-        u64 efi_desc_size, start, end, granule_addr, last_granule_addr, first_non_wb_addr = 0;
-        unsigned long total_mem = 0;
-
-        efi_map_start = __va(ia64_boot_param->efi_memmap);
-        efi_map_end   = efi_map_start + ia64_boot_param->efi_memmap_size;
-        efi_desc_size = ia64_boot_param->efi_memdesc_size;
-
-        for (p = efi_map_start; p < efi_map_end; p += efi_desc_size) {
-                md = p;
-
-                /* skip over non-WB memory descriptors; that's all we're interested in... */
-                if (!(md->attribute & EFI_MEMORY_WB))
-                        continue;
-
-                /*
-                 * granule_addr is the base of md's first granule.
-                 * [granule_addr - first_non_wb_addr) is guaranteed to
-                 * be contiguous WB memory.
-                 */
-                granule_addr = GRANULEROUNDDOWN(md->phys_addr);
-                first_non_wb_addr = max(first_non_wb_addr, granule_addr);
-
-                if (first_non_wb_addr < md->phys_addr) {
-                        trim_bottom(md, granule_addr + IA64_GRANULE_SIZE);
-                        granule_addr = GRANULEROUNDDOWN(md->phys_addr);
-                        first_non_wb_addr = max(first_non_wb_addr, granule_addr);
-                }
-
-                for (q = p; q < efi_map_end; q += efi_desc_size) {
-                        check_md = q;
-
-                        if ((check_md->attribute & EFI_MEMORY_WB) &&
-                            (check_md->phys_addr == first_non_wb_addr))
-                                first_non_wb_addr += check_md->num_pages << EFI_PAGE_SHIFT;
-                        else
-                                break;          /* non-WB or hole */
-                }
-
-                last_granule_addr = GRANULEROUNDDOWN(first_non_wb_addr);
-                if (last_granule_addr < md->phys_addr + (md->num_pages << EFI_PAGE_SHIFT))
-                        trim_top(md, last_granule_addr);
-
-                if (is_available_memory(md)) {
-                        if (md->phys_addr + (md->num_pages << EFI_PAGE_SHIFT) >= max_addr) {
-                                if (md->phys_addr >= max_addr)
-                                        continue;
-                                md->num_pages = (max_addr - md->phys_addr) >> EFI_PAGE_SHIFT;
-                                first_non_wb_addr = max_addr;
-                        }
-
-                        if (total_mem >= mem_limit)
-                                continue;
-
-                        if (total_mem + (md->num_pages << EFI_PAGE_SHIFT) > mem_limit) {
-                                unsigned long limit_addr = md->phys_addr;
-
-                                limit_addr += mem_limit - total_mem;
-                                limit_addr = GRANULEROUNDDOWN(limit_addr);
-
-                                if (md->phys_addr > limit_addr)
-                                        continue;
-
-                                md->num_pages = (limit_addr - md->phys_addr) >>
-                                                EFI_PAGE_SHIFT;
-                                first_non_wb_addr = max_addr = md->phys_addr +
-                                              (md->num_pages << EFI_PAGE_SHIFT);
-                        }
-                        total_mem += (md->num_pages << EFI_PAGE_SHIFT);
-
-                        if (md->num_pages == 0)
-                                continue;
-
-                        curr.start = PAGE_OFFSET + md->phys_addr;
-                        curr.end   = curr.start + (md->num_pages << EFI_PAGE_SHIFT);
-
-                        if (!prev_valid) {
-                                prev = curr;
-                                prev_valid = 1;
-                        } else {
-                                if (curr.start < prev.start)
-                                        printk(KERN_ERR "Oops: EFI memory table not ordered!\n");
-
-                                if (prev.end == curr.start) {
-                                        /* merge two consecutive memory ranges */
-                                        prev.end = curr.end;
-                                } else {
-                                        start = PAGE_ALIGN(prev.start);
-                                        end = prev.end & PAGE_MASK;
-                                        if ((end > start) && (*callback)(start, end, arg) < 0)
-                                                return;
-                                        prev = curr;
-                                }
-                        }
-                }
-        }
-        if (prev_valid) {
-                start = PAGE_ALIGN(prev.start);
-                end = prev.end & PAGE_MASK;
-                if (end > start)
-                        (*callback)(start, end, arg);
-        }
+        walk(callback, arg, EFI_MEMORY_WB);
 }
 
 /*
- * Walk the EFI memory map to pull out leftover pages in the lower
- * memory regions which do not end up in the regular memory map and
- * stick them into the uncached allocator
- *
- * The regular walk function is significantly more complex than the
- * uncached walk which means it really doesn't make sense to try and
- * marge the two.
+ * Walks the EFI memory map and calls CALLBACK once for each EFI memory descriptor that
+ * has memory that is available for uncached allocator.
  */
-void __init
-efi_memmap_walk_uc (efi_freemem_callback_t callback)
+void
+efi_memmap_walk_uc (efi_freemem_callback_t callback, void *arg)
 {
-        void *efi_map_start, *efi_map_end, *p;
-        efi_memory_desc_t *md;
-        u64 efi_desc_size, start, end;
-
-        efi_map_start = __va(ia64_boot_param->efi_memmap);
-        efi_map_end = efi_map_start + ia64_boot_param->efi_memmap_size;
-        efi_desc_size = ia64_boot_param->efi_memdesc_size;
-
-        for (p = efi_map_start; p < efi_map_end; p += efi_desc_size) {
-                md = p;
-                if (md->attribute == EFI_MEMORY_UC) {
-                        start = PAGE_ALIGN(md->phys_addr);
-                        end = PAGE_ALIGN((md->phys_addr+(md->num_pages << EFI_PAGE_SHIFT)) & PAGE_MASK);
-                        if ((*callback)(start, end, NULL) < 0)
-                                return;
-                }
-        }
+        walk(callback, arg, EFI_MEMORY_UC);
 }
 
-
 /*
  * Look for the PAL_CODE region reported by EFI and maps it using an
  * ITR to enable safe PAL calls in virtual mode.  See IA-64 Processor
@@ -862,3 +706,307 @@ efi_uart_console_only(void)
         printk(KERN_ERR "Malformed %s value\n", name);
         return 0;
 }
+
+#define efi_md_size(md) (md->num_pages << EFI_PAGE_SHIFT)
+
+static inline u64
+kmd_end(kern_memdesc_t *kmd)
+{
+        return (kmd->start + (kmd->num_pages << EFI_PAGE_SHIFT));
+}
+
+static inline u64
+efi_md_end(efi_memory_desc_t *md)
+{
+        return (md->phys_addr + efi_md_size(md));
+}
+
+static inline int
+efi_wb(efi_memory_desc_t *md)
+{
+        return (md->attribute & EFI_MEMORY_WB);
+}
+
+static inline int
+efi_uc(efi_memory_desc_t *md)
+{
+        return (md->attribute & EFI_MEMORY_UC);
+}
+
+/*
+ * Look for the first granule aligned memory descriptor memory
+ * that is big enough to hold EFI memory map. Make sure this
+ * descriptor is atleast granule sized so it does not get trimmed
+ */
+struct kern_memdesc *
+find_memmap_space (void)
+{
+        u64     contig_low=0, contig_high=0;
+        u64     as = 0, ae;
+        void *efi_map_start, *efi_map_end, *p, *q;
+        efi_memory_desc_t *md, *pmd = NULL, *check_md;
+        u64     space_needed, efi_desc_size;
+        unsigned long total_mem = 0;
+
+        efi_map_start = __va(ia64_boot_param->efi_memmap);
+        efi_map_end   = efi_map_start + ia64_boot_param->efi_memmap_size;
+        efi_desc_size = ia64_boot_param->efi_memdesc_size;
+
+        /*
+         * Worst case: we need 3 kernel descriptors for each efi descriptor
+         * (if every entry has a WB part in the middle, and UC head and tail),
+         * plus one for the end marker.
+         */
+        space_needed = sizeof(kern_memdesc_t) *
+                (3 * (ia64_boot_param->efi_memmap_size/efi_desc_size) + 1);
+
+        for (p = efi_map_start; p < efi_map_end; pmd = md, p += efi_desc_size) {
+                md = p;
+                if (!efi_wb(md)) {
+                        continue;
+                }
+                if (pmd == NULL || !efi_wb(pmd) || efi_md_end(pmd) != md->phys_addr) {
+                        contig_low = GRANULEROUNDUP(md->phys_addr);
+                        contig_high = efi_md_end(md);
+                        for (q = p + efi_desc_size; q < efi_map_end; q += efi_desc_size) {
+                                check_md = q;
+                                if (!efi_wb(check_md))
+                                        break;
+                                if (contig_high != check_md->phys_addr)
+                                        break;
+                                contig_high = efi_md_end(check_md);
+                        }
+                        contig_high = GRANULEROUNDDOWN(contig_high);
+                }
+                if (!is_available_memory(md) || md->type == EFI_LOADER_DATA)
+                        continue;
+
+                /* Round ends inward to granule boundaries */
+                as = max(contig_low, md->phys_addr);
+                ae = min(contig_high, efi_md_end(md));
+
+                /* keep within max_addr= command line arg */
+                ae = min(ae, max_addr);
+                if (ae <= as)
+                        continue;
+
+                /* avoid going over mem= command line arg */
+                if (total_mem + (ae - as) > mem_limit)
+                        ae -= total_mem + (ae - as) - mem_limit;
+
+                if (ae <= as)
+                        continue;
+
+                if (ae - as > space_needed)
+                        break;
+        }
+        if (p >= efi_map_end)
+                panic("Can't allocate space for kernel memory descriptors");
+
+        return __va(as);
+}
+
+/*
+ * Walk the EFI memory map and gather all memory available for kernel
+ * to use.  We can allocate partial granules only if the unavailable
+ * parts exist, and are WB.
+ */
+void
+efi_memmap_init(unsigned long *s, unsigned long *e)
+{
+        struct kern_memdesc *k, *prev = 0;
+        u64     contig_low=0, contig_high=0;
+        u64     as, ae, lim;
+        void *efi_map_start, *efi_map_end, *p, *q;
+        efi_memory_desc_t *md, *pmd = NULL, *check_md;
+        u64     efi_desc_size;
+        unsigned long total_mem = 0;
+
+        k = kern_memmap = find_memmap_space();
+
+        efi_map_start = __va(ia64_boot_param->efi_memmap);
+        efi_map_end   = efi_map_start + ia64_boot_param->efi_memmap_size;
+        efi_desc_size = ia64_boot_param->efi_memdesc_size;
+
+        for (p = efi_map_start; p < efi_map_end; pmd = md, p += efi_desc_size) {
+                md = p;
+                if (!efi_wb(md)) {
+                        if (efi_uc(md) && (md->type == EFI_CONVENTIONAL_MEMORY ||
+                                           md->type == EFI_BOOT_SERVICES_DATA)) {
+                                k->attribute = EFI_MEMORY_UC;
+                                k->start = md->phys_addr;
+                                k->num_pages = md->num_pages;
+                                k++;
+                        }
+                        continue;
+                }
+                if (pmd == NULL || !efi_wb(pmd) || efi_md_end(pmd) != md->phys_addr) {
+                        contig_low = GRANULEROUNDUP(md->phys_addr);
+                        contig_high = efi_md_end(md);
+                        for (q = p + efi_desc_size; q < efi_map_end; q += efi_desc_size) {
+                                check_md = q;
+                                if (!efi_wb(check_md))
+                                        break;
+                                if (contig_high != check_md->phys_addr)
+                                        break;
+                                contig_high = efi_md_end(check_md);
+                        }
+                        contig_high = GRANULEROUNDDOWN(contig_high);
+                }
+                if (!is_available_memory(md))
+                        continue;
+
+                /*
+                 * Round ends inward to granule boundaries
+                 * Give trimmings to uncached allocator
+                 */
+                if (md->phys_addr < contig_low) {
+                        lim = min(efi_md_end(md), contig_low);
+                        if (efi_uc(md)) {
+                                if (k > kern_memmap && (k-1)->attribute == EFI_MEMORY_UC &&
+                                    kmd_end(k-1) == md->phys_addr) {
+                                        (k-1)->num_pages += (lim - md->phys_addr) >> EFI_PAGE_SHIFT;
+                                } else {
+                                        k->attribute = EFI_MEMORY_UC;
+                                        k->start = md->phys_addr;
+                                        k->num_pages = (lim - md->phys_addr) >> EFI_PAGE_SHIFT;
+                                        k++;
+                                }
+                        }
+                        as = contig_low;
+                } else
+                        as = md->phys_addr;
+
+                if (efi_md_end(md) > contig_high) {
+                        lim = max(md->phys_addr, contig_high);
+                        if (efi_uc(md)) {
+                                if (lim == md->phys_addr && k > kern_memmap &&
+                                    (k-1)->attribute == EFI_MEMORY_UC &&
+                                    kmd_end(k-1) == md->phys_addr) {
+                                        (k-1)->num_pages += md->num_pages;
+                                } else {
+                                        k->attribute = EFI_MEMORY_UC;
+                                        k->start = lim;
+                                        k->num_pages = (efi_md_end(md) - lim) >> EFI_PAGE_SHIFT;
+                                        k++;
+                                }
+                        }
+                        ae = contig_high;
+                } else
+                        ae = efi_md_end(md);
+
+                /* keep within max_addr= command line arg */
+                ae = min(ae, max_addr);
+                if (ae <= as)
+                        continue;
+
+                /* avoid going over mem= command line arg */
+                if (total_mem + (ae - as) > mem_limit)
+                        ae -= total_mem + (ae - as) - mem_limit;
+
+                if (ae <= as)
+                        continue;
+                if (prev && kmd_end(prev) == md->phys_addr) {
+                        prev->num_pages += (ae - as) >> EFI_PAGE_SHIFT;
+                        total_mem += ae - as;
+                        continue;
+                }
+                k->attribute = EFI_MEMORY_WB;
+                k->start = as;
+                k->num_pages = (ae - as) >> EFI_PAGE_SHIFT;
+                total_mem += ae - as;
+                prev = k++;
+        }
+        k->start = ~0L; /* end-marker */
+
+        /* reserve the memory we are using for kern_memmap */
+        *s = (u64)kern_memmap;
+        *e = (u64)++k;
+}
+
+void
+efi_initialize_iomem_resources(struct resource *code_resource,
+                               struct resource *data_resource)
+{
+        struct resource *res;
+        void *efi_map_start, *efi_map_end, *p;
+        efi_memory_desc_t *md;
+        u64 efi_desc_size;
+        char *name;
+        unsigned long flags;
+
+        efi_map_start = __va(ia64_boot_param->efi_memmap);
+        efi_map_end   = efi_map_start + ia64_boot_param->efi_memmap_size;
+        efi_desc_size = ia64_boot_param->efi_memdesc_size;
+
+        res = NULL;
+
+        for (p = efi_map_start; p < efi_map_end; p += efi_desc_size) {
+                md = p;
+
+                if (md->num_pages == 0) /* should not happen */
+                        continue;
+
+                flags = IORESOURCE_MEM;
+                switch (md->type) {
+
+                        case EFI_MEMORY_MAPPED_IO:
+                        case EFI_MEMORY_MAPPED_IO_PORT_SPACE:
+                                continue;
+
+                        case EFI_LOADER_CODE:
+                        case EFI_LOADER_DATA:
+                        case EFI_BOOT_SERVICES_DATA:
+                        case EFI_BOOT_SERVICES_CODE:
+                        case EFI_CONVENTIONAL_MEMORY:
+                                if (md->attribute & EFI_MEMORY_WP) {
+                                        name = "System ROM";
+                                        flags |= IORESOURCE_READONLY;
+                                } else {
+                                        name = "System RAM";
+                                }
+                                break;
+
+                        case EFI_ACPI_MEMORY_NVS:
+                                name = "ACPI Non-volatile Storage";
+                                flags |= IORESOURCE_BUSY;
+                                break;
+
+                        case EFI_UNUSABLE_MEMORY:
+                                name = "reserved";
+                                flags |= IORESOURCE_BUSY | IORESOURCE_DISABLED;
+                                break;
+
+                        case EFI_RESERVED_TYPE:
+                        case EFI_RUNTIME_SERVICES_CODE:
+                        case EFI_RUNTIME_SERVICES_DATA:
+                        case EFI_ACPI_RECLAIM_MEMORY:
+                        default:
+                                name = "reserved";
+                                flags |= IORESOURCE_BUSY;
+                                break;
+                }
+
+                if ((res = kzalloc(sizeof(struct resource), GFP_KERNEL)) == NULL) {
+                        printk(KERN_ERR "failed to alocate resource for iomem\n");
+                        return;
+                }
+
+                res->name = name;
+                res->start = md->phys_addr;
+                res->end = md->phys_addr + (md->num_pages << EFI_PAGE_SHIFT) - 1;
+                res->flags = flags;
+
+                if (insert_resource(&iomem_resource, res) < 0)
+                        kfree(res);
+                else {
+                        /*
+                         * We don't know which region contains
+                         * kernel data so we try it repeatedly and
+                         * let the resource manager test it.
+                         */
+                        insert_resource(res, code_resource);
+                        insert_resource(res, data_resource);
+                }
+        }
+}
diff --git a/arch/ia64/kernel/ia64_ksyms.c b/arch/ia64/kernel/ia64_ksyms.c
index 01572814abe4..5db9d3bcbbcb 100644
--- a/arch/ia64/kernel/ia64_ksyms.c
+++ b/arch/ia64/kernel/ia64_ksyms.c
@@ -42,6 +42,7 @@ EXPORT_SYMBOL(clear_page);
 
 #ifdef CONFIG_VIRTUAL_MEM_MAP
 #include <linux/bootmem.h>
+EXPORT_SYMBOL(min_low_pfn);     /* defined by bootmem.c, but not exported by generic code */
 EXPORT_SYMBOL(max_low_pfn);     /* defined by bootmem.c, but not exported by generic code */
 #endif
 
diff --git a/arch/ia64/kernel/irq.c b/arch/ia64/kernel/irq.c
index 205d98028261..d33244c32759 100644
--- a/arch/ia64/kernel/irq.c
+++ b/arch/ia64/kernel/irq.c
@@ -57,9 +57,9 @@ int show_interrupts(struct seq_file *p, void *v)
 
         if (i == 0) {
                 seq_printf(p, "           ");
-                for (j=0; j<NR_CPUS; j++)
-                        if (cpu_online(j))
-                                seq_printf(p, "CPU%d       ",j);
+                for_each_online_cpu(j) {
+                        seq_printf(p, "CPU%d       ",j);
+                }
                 seq_putc(p, '\n');
         }
 
@@ -72,9 +72,9 @@ int show_interrupts(struct seq_file *p, void *v)
 #ifndef CONFIG_SMP
                 seq_printf(p, "%10u ", kstat_irqs(i));
 #else
-                for (j = 0; j < NR_CPUS; j++)
-                        if (cpu_online(j))
-                                seq_printf(p, "%10u ", kstat_cpu(j).irqs[i]);
+                for_each_online_cpu(j) {
+                        seq_printf(p, "%10u ", kstat_cpu(j).irqs[i]);
+                }
 #endif
                 seq_printf(p, " %14s", irq_desc[i].handler->typename);
                 seq_printf(p, "  %s", action->name);
diff --git a/arch/ia64/kernel/ivt.S b/arch/ia64/kernel/ivt.S
index c13ca0d49c4a..301f2e9d262e 100644
--- a/arch/ia64/kernel/ivt.S
+++ b/arch/ia64/kernel/ivt.S
@@ -91,16 +91,17 @@ ENTRY(vhpt_miss)
          * (the "original") TLB miss, which may either be caused by an instruction
          * fetch or a data access (or non-access).
          *
-         * What we do here is normal TLB miss handing for the _original_ miss, followed
-         * by inserting the TLB entry for the virtual page table page that the VHPT
-         * walker was attempting to access.  The latter gets inserted as long
-         * as both L1 and L2 have valid mappings for the faulting address.
-         * The TLB entry for the original miss gets inserted only if
-         * the L3 entry indicates that the page is present.
+         * What we do here is normal TLB miss handing for the _original_ miss,
+         * followed by inserting the TLB entry for the virtual page table page
+         * that the VHPT walker was attempting to access.  The latter gets
+         * inserted as long as page table entry above pte level have valid
+         * mappings for the faulting address.  The TLB entry for the original
+         * miss gets inserted only if the pte entry indicates that the page is
+         * present.
          *
          * do_page_fault gets invoked in the following cases:
          *      - the faulting virtual address uses unimplemented address bits
-         *      - the faulting virtual address has no L1, L2, or L3 mapping
+         *      - the faulting virtual address has no valid page table mapping
          */
         mov r16=cr.ifa                          // get address that caused the TLB miss
 #ifdef CONFIG_HUGETLB_PAGE
@@ -114,7 +115,7 @@ ENTRY(vhpt_miss)
         shl r21=r16,3                           // shift bit 60 into sign bit
         shr.u r17=r16,61                        // get the region number into r17
         ;;
-        shr r22=r21,3
+        shr.u r22=r21,3
 #ifdef CONFIG_HUGETLB_PAGE
         extr.u r26=r25,2,6
         ;;
@@ -126,7 +127,7 @@ ENTRY(vhpt_miss)
 #endif
         ;;
         cmp.eq p6,p7=5,r17                      // is IFA pointing into to region 5?
-        shr.u r18=r22,PGDIR_SHIFT               // get bits 33-63 of the faulting address
+        shr.u r18=r22,PGDIR_SHIFT               // get bottom portion of pgd index bit
         ;;
 (p7)    dep r17=r17,r19,(PAGE_SHIFT-3),3        // put region number bits in place
 
@@ -137,24 +138,38 @@ ENTRY(vhpt_miss)
 (p6)    shr.u r21=r21,PGDIR_SHIFT+PAGE_SHIFT
 (p7)    shr.u r21=r21,PGDIR_SHIFT+PAGE_SHIFT-3
         ;;
-(p6)    dep r17=r18,r19,3,(PAGE_SHIFT-3)        // r17=PTA + IFA(33,42)*8
-(p7)    dep r17=r18,r17,3,(PAGE_SHIFT-6)        // r17=PTA + (((IFA(61,63) << 7) | IFA(33,39))*8)
+(p6)    dep r17=r18,r19,3,(PAGE_SHIFT-3)        // r17=pgd_offset for region 5
+(p7)    dep r17=r18,r17,3,(PAGE_SHIFT-6)        // r17=pgd_offset for region[0-4]
         cmp.eq p7,p6=0,r21                      // unused address bits all zeroes?
-        shr.u r18=r22,PMD_SHIFT                 // shift L2 index into position
+#ifdef CONFIG_PGTABLE_4
+        shr.u r28=r22,PUD_SHIFT                 // shift pud index into position
+#else
+        shr.u r18=r22,PMD_SHIFT                 // shift pmd index into position
+#endif
+        ;;
+        ld8 r17=[r17]                           // get *pgd (may be 0)
+        ;;
+(p7)    cmp.eq p6,p7=r17,r0                     // was pgd_present(*pgd) == NULL?
+#ifdef CONFIG_PGTABLE_4
+        dep r28=r28,r17,3,(PAGE_SHIFT-3)        // r28=pud_offset(pgd,addr)
         ;;
-        ld8 r17=[r17]                           // fetch the L1 entry (may be 0)
+        shr.u r18=r22,PMD_SHIFT                 // shift pmd index into position
+(p7)    ld8 r29=[r28]                           // get *pud (may be 0)
         ;;
-(p7)    cmp.eq p6,p7=r17,r0                     // was L1 entry NULL?
-        dep r17=r18,r17,3,(PAGE_SHIFT-3)        // compute address of L2 page table entry
+(p7)    cmp.eq.or.andcm p6,p7=r29,r0            // was pud_present(*pud) == NULL?
+        dep r17=r18,r29,3,(PAGE_SHIFT-3)        // r17=pmd_offset(pud,addr)
+#else
+        dep r17=r18,r17,3,(PAGE_SHIFT-3)        // r17=pmd_offset(pgd,addr)
+#endif
         ;;
-(p7)    ld8 r20=[r17]                           // fetch the L2 entry (may be 0)
-        shr.u r19=r22,PAGE_SHIFT                // shift L3 index into position
+(p7)    ld8 r20=[r17]                           // get *pmd (may be 0)
+        shr.u r19=r22,PAGE_SHIFT                // shift pte index into position
         ;;
-(p7)    cmp.eq.or.andcm p6,p7=r20,r0            // was L2 entry NULL?
-        dep r21=r19,r20,3,(PAGE_SHIFT-3)        // compute address of L3 page table entry
+(p7)    cmp.eq.or.andcm p6,p7=r20,r0            // was pmd_present(*pmd) == NULL?
+        dep r21=r19,r20,3,(PAGE_SHIFT-3)        // r21=pte_offset(pmd,addr)
         ;;
-(p7)    ld8 r18=[r21]                           // read the L3 PTE
-        mov r19=cr.isr                          // cr.isr bit 0 tells us if this is an insn miss
+(p7)    ld8 r18=[r21]                           // read *pte
+        mov r19=cr.isr                          // cr.isr bit 32 tells us if this is an insn miss
         ;;
 (p7)    tbit.z p6,p7=r18,_PAGE_P_BIT            // page present bit cleared?
         mov r22=cr.iha                          // get the VHPT address that caused the TLB miss
@@ -188,18 +203,33 @@ ENTRY(vhpt_miss)
         dv_serialize_data
 
         /*
-         * Re-check L2 and L3 pagetable.  If they changed, we may have received a ptc.g
+         * Re-check pagetable entry.  If they changed, we may have received a ptc.g
          * between reading the pagetable and the "itc".  If so, flush the entry we
-         * inserted and retry.
+         * inserted and retry.  At this point, we have:
+         *
+         * r28 = equivalent of pud_offset(pgd, ifa)
+         * r17 = equivalent of pmd_offset(pud, ifa)
+         * r21 = equivalent of pte_offset(pmd, ifa)
+         *
+         * r29 = *pud
+         * r20 = *pmd
+         * r18 = *pte
          */
-        ld8 r25=[r21]                           // read L3 PTE again
-        ld8 r26=[r17]                           // read L2 entry again
+        ld8 r25=[r21]                           // read *pte again
+        ld8 r26=[r17]                           // read *pmd again
+#ifdef CONFIG_PGTABLE_4
+        ld8 r19=[r28]                           // read *pud again
+#endif
+        cmp.ne p6,p7=r0,r0
         ;;
-        cmp.ne p6,p7=r26,r20                    // did L2 entry change
+        cmp.ne.or.andcm p6,p7=r26,r20           // did *pmd change
+#ifdef CONFIG_PGTABLE_4
+        cmp.ne.or.andcm p6,p7=r19,r29           // did *pud change
+#endif
         mov r27=PAGE_SHIFT<<2
         ;;
 (p6)    ptc.l r22,r27                           // purge PTE page translation
-(p7)    cmp.ne.or.andcm p6,p7=r25,r18           // did L3 PTE change
+(p7)    cmp.ne.or.andcm p6,p7=r25,r18           // did *pte change
         ;;
 (p6)    ptc.l r16,r27                           // purge translation
 #endif
@@ -214,19 +244,19 @@ END(vhpt_miss)
 ENTRY(itlb_miss)
         DBG_FAULT(1)
         /*
-         * The ITLB handler accesses the L3 PTE via the virtually mapped linear
+         * The ITLB handler accesses the PTE via the virtually mapped linear
          * page table.  If a nested TLB miss occurs, we switch into physical
-         * mode, walk the page table, and then re-execute the L3 PTE read
-         * and go on normally after that.
+         * mode, walk the page table, and then re-execute the PTE read and
+         * go on normally after that.
          */
         mov r16=cr.ifa                          // get virtual address
         mov r29=b0                              // save b0
         mov r31=pr                              // save predicates
 .itlb_fault:
-        mov r17=cr.iha                          // get virtual address of L3 PTE
+        mov r17=cr.iha                          // get virtual address of PTE
         movl r30=1f                             // load nested fault continuation point
         ;;
-1:      ld8 r18=[r17]                           // read L3 PTE
+1:      ld8 r18=[r17]                           // read *pte
         ;;
         mov b0=r29
         tbit.z p6,p0=r18,_PAGE_P_BIT            // page present bit cleared?
@@ -241,7 +271,7 @@ ENTRY(itlb_miss)
          */
         dv_serialize_data
 
-        ld8 r19=[r17]                           // read L3 PTE again and see if same
+        ld8 r19=[r17]                           // read *pte again and see if same
         mov r20=PAGE_SHIFT<<2                   // setup page size for purge
         ;;
         cmp.ne p7,p0=r18,r19
@@ -258,19 +288,19 @@ END(itlb_miss)
 ENTRY(dtlb_miss)
         DBG_FAULT(2)
         /*
-         * The DTLB handler accesses the L3 PTE via the virtually mapped linear
+         * The DTLB handler accesses the PTE via the virtually mapped linear
          * page table.  If a nested TLB miss occurs, we switch into physical
-         * mode, walk the page table, and then re-execute the L3 PTE read
-         * and go on normally after that.
+         * mode, walk the page table, and then re-execute the PTE read and
+         * go on normally after that.
          */
         mov r16=cr.ifa                          // get virtual address
         mov r29=b0                              // save b0
         mov r31=pr                              // save predicates
 dtlb_fault:
-        mov r17=cr.iha                          // get virtual address of L3 PTE
+        mov r17=cr.iha                          // get virtual address of PTE
         movl r30=1f                             // load nested fault continuation point
         ;;
-1:      ld8 r18=[r17]                           // read L3 PTE
+1:      ld8 r18=[r17]                           // read *pte
         ;;
         mov b0=r29
         tbit.z p6,p0=r18,_PAGE_P_BIT            // page present bit cleared?
@@ -285,7 +315,7 @@ dtlb_fault:
          */
         dv_serialize_data
 
-        ld8 r19=[r17]                           // read L3 PTE again and see if same
+        ld8 r19=[r17]                           // read *pte again and see if same
         mov r20=PAGE_SHIFT<<2                   // setup page size for purge
         ;;
         cmp.ne p7,p0=r18,r19
@@ -399,7 +429,7 @@ ENTRY(nested_dtlb_miss)
          *              r30:    continuation address
          *              r31:    saved pr
          *
-         * Output:      r17:    physical address of L3 PTE of faulting address
+         * Output:      r17:    physical address of PTE of faulting address
          *              r29:    saved b0
          *              r30:    continuation address
          *              r31:    saved pr
@@ -429,21 +459,33 @@ ENTRY(nested_dtlb_miss)
 (p6)    shr.u r21=r21,PGDIR_SHIFT+PAGE_SHIFT
 (p7)    shr.u r21=r21,PGDIR_SHIFT+PAGE_SHIFT-3
         ;;
-(p6)    dep r17=r18,r19,3,(PAGE_SHIFT-3)        // r17=PTA + IFA(33,42)*8
-(p7)    dep r17=r18,r17,3,(PAGE_SHIFT-6)        // r17=PTA + (((IFA(61,63) << 7) | IFA(33,39))*8)
+(p6)    dep r17=r18,r19,3,(PAGE_SHIFT-3)        // r17=pgd_offset for region 5
+(p7)    dep r17=r18,r17,3,(PAGE_SHIFT-6)        // r17=pgd_offset for region[0-4]
         cmp.eq p7,p6=0,r21                      // unused address bits all zeroes?
-        shr.u r18=r22,PMD_SHIFT                 // shift L2 index into position
+#ifdef CONFIG_PGTABLE_4
+        shr.u r18=r22,PUD_SHIFT                 // shift pud index into position
+#else
+        shr.u r18=r22,PMD_SHIFT                 // shift pmd index into position
+#endif
         ;;
-        ld8 r17=[r17]                           // fetch the L1 entry (may be 0)
+        ld8 r17=[r17]                           // get *pgd (may be 0)
         ;;
-(p7)    cmp.eq p6,p7=r17,r0                     // was L1 entry NULL?
-        dep r17=r18,r17,3,(PAGE_SHIFT-3)        // compute address of L2 page table entry
+(p7)    cmp.eq p6,p7=r17,r0                     // was pgd_present(*pgd) == NULL?
+        dep r17=r18,r17,3,(PAGE_SHIFT-3)        // r17=p[u|m]d_offset(pgd,addr)
         ;;
-(p7)    ld8 r17=[r17]                           // fetch the L2 entry (may be 0)
-        shr.u r19=r22,PAGE_SHIFT                // shift L3 index into position
+#ifdef CONFIG_PGTABLE_4
+(p7)    ld8 r17=[r17]                           // get *pud (may be 0)
+        shr.u r18=r22,PMD_SHIFT                 // shift pmd index into position
+        ;;
+(p7)    cmp.eq.or.andcm p6,p7=r17,r0            // was pud_present(*pud) == NULL?
+        dep r17=r18,r17,3,(PAGE_SHIFT-3)        // r17=pmd_offset(pud,addr)
+        ;;
+#endif
+(p7)    ld8 r17=[r17]                           // get *pmd (may be 0)
+        shr.u r19=r22,PAGE_SHIFT                // shift pte index into position
         ;;
-(p7)    cmp.eq.or.andcm p6,p7=r17,r0            // was L2 entry NULL?
-        dep r17=r19,r17,3,(PAGE_SHIFT-3)        // compute address of L3 page table entry
+(p7)    cmp.eq.or.andcm p6,p7=r17,r0            // was pmd_present(*pmd) == NULL?
+        dep r17=r19,r17,3,(PAGE_SHIFT-3)        // r17=pte_offset(pmd,addr);
 (p6)    br.cond.spnt page_fault
         mov b0=r30
         br.sptk.many b0                         // return to continuation point
diff --git a/arch/ia64/kernel/kprobes.c b/arch/ia64/kernel/kprobes.c
index 471086b808a4..2895d6e6062f 100644
--- a/arch/ia64/kernel/kprobes.c
+++ b/arch/ia64/kernel/kprobes.c
@@ -26,7 +26,6 @@
 #include <linux/config.h>
 #include <linux/kprobes.h>
 #include <linux/ptrace.h>
-#include <linux/spinlock.h>
 #include <linux/string.h>
 #include <linux/slab.h>
 #include <linux/preempt.h>
@@ -38,13 +37,8 @@
 
 extern void jprobe_inst_return(void);
 
-/* kprobe_status settings */
-#define KPROBE_HIT_ACTIVE       0x00000001
-#define KPROBE_HIT_SS           0x00000002
-
-static struct kprobe *current_kprobe, *kprobe_prev;
-static unsigned long kprobe_status, kprobe_status_prev;
-static struct pt_regs jprobe_saved_regs;
+DEFINE_PER_CPU(struct kprobe *, current_kprobe) = NULL;
+DEFINE_PER_CPU(struct kprobe_ctlblk, kprobe_ctlblk);
 
 enum instruction_type {A, I, M, F, B, L, X, u};
 static enum instruction_type bundle_encoding[32][3] = {
@@ -313,21 +307,22 @@ static int __kprobes valid_kprobe_addr(int template, int slot,
         return 0;
 }
 
-static inline void save_previous_kprobe(void)
+static inline void save_previous_kprobe(struct kprobe_ctlblk *kcb)
 {
-        kprobe_prev = current_kprobe;
-        kprobe_status_prev = kprobe_status;
+        kcb->prev_kprobe.kp = kprobe_running();
+        kcb->prev_kprobe.status = kcb->kprobe_status;
 }
 
-static inline void restore_previous_kprobe(void)
+static inline void restore_previous_kprobe(struct kprobe_ctlblk *kcb)
 {
-        current_kprobe = kprobe_prev;
-        kprobe_status = kprobe_status_prev;
+        __get_cpu_var(current_kprobe) = kcb->prev_kprobe.kp;
+        kcb->kprobe_status = kcb->prev_kprobe.status;
 }
 
-static inline void set_current_kprobe(struct kprobe *p)
+static inline void set_current_kprobe(struct kprobe *p,
+                        struct kprobe_ctlblk *kcb)
 {
-        current_kprobe = p;
+        __get_cpu_var(current_kprobe) = p;
 }
 
 static void kretprobe_trampoline(void)
@@ -347,11 +342,12 @@ int __kprobes trampoline_probe_handler(struct kprobe *p, struct pt_regs *regs)
         struct kretprobe_instance *ri = NULL;
         struct hlist_head *head;
         struct hlist_node *node, *tmp;
-        unsigned long orig_ret_address = 0;
+        unsigned long flags, orig_ret_address = 0;
         unsigned long trampoline_address =
                 ((struct fnptr *)kretprobe_trampoline)->ip;
 
-        head = kretprobe_inst_table_head(current);
+        spin_lock_irqsave(&kretprobe_lock, flags);
+        head = kretprobe_inst_table_head(current);
 
         /*
          * It is possible to have multiple instances associated with a given
@@ -367,9 +363,9 @@ int __kprobes trampoline_probe_handler(struct kprobe *p, struct pt_regs *regs)
          *       kretprobe_trampoline
          */
         hlist_for_each_entry_safe(ri, node, tmp, head, hlist) {
-                if (ri->task != current)
+                if (ri->task != current)
                         /* another task is sharing our hash bucket */
-                        continue;
+                        continue;
 
                 if (ri->rp && ri->rp->handler)
                         ri->rp->handler(ri, regs);
@@ -389,17 +385,19 @@ int __kprobes trampoline_probe_handler(struct kprobe *p, struct pt_regs *regs)
         BUG_ON(!orig_ret_address || (orig_ret_address == trampoline_address));
         regs->cr_iip = orig_ret_address;
 
-        unlock_kprobes();
+        reset_current_kprobe();
+        spin_unlock_irqrestore(&kretprobe_lock, flags);
         preempt_enable_no_resched();
 
-        /*
-         * By returning a non-zero value, we are telling
-         * kprobe_handler() that we have handled unlocking
-         * and re-enabling preemption.
-         */
-        return 1;
+        /*
+         * By returning a non-zero value, we are telling
+         * kprobe_handler() that we don't want the post_handler
+         * to run (and have re-enabled preemption)
+         */
+        return 1;
 }
 
+/* Called with kretprobe_lock held */
 void __kprobes arch_prepare_kretprobe(struct kretprobe *rp,
                                       struct pt_regs *regs)
 {
@@ -606,17 +604,22 @@ static int __kprobes pre_kprobes_handler(struct die_args *args)
         int ret = 0;
         struct pt_regs *regs = args->regs;
         kprobe_opcode_t *addr = (kprobe_opcode_t *)instruction_pointer(regs);
+        struct kprobe_ctlblk *kcb;
 
+        /*
+         * We don't want to be preempted for the entire
+         * duration of kprobe processing
+         */
         preempt_disable();
+        kcb = get_kprobe_ctlblk();
 
         /* Handle recursion cases */
         if (kprobe_running()) {
                 p = get_kprobe(addr);
                 if (p) {
-                        if ( (kprobe_status == KPROBE_HIT_SS) &&
+                        if ((kcb->kprobe_status == KPROBE_HIT_SS) &&
                              (p->ainsn.inst_flag == INST_FLAG_BREAK_INST)) {
                                 ia64_psr(regs)->ss = 0;
-                                unlock_kprobes();
                                 goto no_kprobe;
                         }
                         /* We have reentered the pre_kprobe_handler(), since
@@ -625,17 +628,17 @@ static int __kprobes pre_kprobes_handler(struct die_args *args)
                          * just single step on the instruction of the new probe
                          * without calling any user handlers.
                          */
-                        save_previous_kprobe();
-                        set_current_kprobe(p);
+                        save_previous_kprobe(kcb);
+                        set_current_kprobe(p, kcb);
                         p->nmissed++;
                         prepare_ss(p, regs);
-                        kprobe_status = KPROBE_REENTER;
+                        kcb->kprobe_status = KPROBE_REENTER;
                         return 1;
                 } else if (args->err == __IA64_BREAK_JPROBE) {
                         /*
                          * jprobe instrumented function just completed
                          */
-                        p = current_kprobe;
+                        p = __get_cpu_var(current_kprobe);
                         if (p->break_handler && p->break_handler(p, regs)) {
                                 goto ss_probe;
                         }
@@ -645,10 +648,8 @@ static int __kprobes pre_kprobes_handler(struct die_args *args)
                 }
         }
 
-        lock_kprobes();
         p = get_kprobe(addr);
         if (!p) {
-                unlock_kprobes();
                 if (!is_ia64_break_inst(regs)) {
                         /*
                          * The breakpoint instruction was removed right
@@ -665,8 +666,8 @@ static int __kprobes pre_kprobes_handler(struct die_args *args)
                 goto no_kprobe;
         }
 
-        kprobe_status = KPROBE_HIT_ACTIVE;
-        set_current_kprobe(p);
+        set_current_kprobe(p, kcb);
+        kcb->kprobe_status = KPROBE_HIT_ACTIVE;
 
         if (p->pre_handler && p->pre_handler(p, regs))
                 /*
@@ -678,7 +679,7 @@ static int __kprobes pre_kprobes_handler(struct die_args *args)
 
 ss_probe:
         prepare_ss(p, regs);
-        kprobe_status = KPROBE_HIT_SS;
+        kcb->kprobe_status = KPROBE_HIT_SS;
         return 1;
 
 no_kprobe:
@@ -688,23 +689,25 @@ no_kprobe:
 
 static int __kprobes post_kprobes_handler(struct pt_regs *regs)
 {
-        if (!kprobe_running())
+        struct kprobe *cur = kprobe_running();
+        struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
+
+        if (!cur)
                 return 0;
 
-        if ((kprobe_status != KPROBE_REENTER) && current_kprobe->post_handler) {
-                kprobe_status = KPROBE_HIT_SSDONE;
-                current_kprobe->post_handler(current_kprobe, regs, 0);
+        if ((kcb->kprobe_status != KPROBE_REENTER) && cur->post_handler) {
+                kcb->kprobe_status = KPROBE_HIT_SSDONE;
+                cur->post_handler(cur, regs, 0);
         }
 
-        resume_execution(current_kprobe, regs);
+        resume_execution(cur, regs);
 
         /*Restore back the original saved kprobes variables and continue. */
-        if (kprobe_status == KPROBE_REENTER) {
-                restore_previous_kprobe();
+        if (kcb->kprobe_status == KPROBE_REENTER) {
+                restore_previous_kprobe(kcb);
                 goto out;
         }
-
-        unlock_kprobes();
+        reset_current_kprobe();
 
 out:
         preempt_enable_no_resched();
@@ -713,16 +716,15 @@ out:
 
 static int __kprobes kprobes_fault_handler(struct pt_regs *regs, int trapnr)
 {
-        if (!kprobe_running())
-                return 0;
+        struct kprobe *cur = kprobe_running();
+        struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
 
-        if (current_kprobe->fault_handler &&
-            current_kprobe->fault_handler(current_kprobe, regs, trapnr))
+        if (cur->fault_handler && cur->fault_handler(cur, regs, trapnr))
                 return 1;
 
-        if (kprobe_status & KPROBE_HIT_SS) {
-                resume_execution(current_kprobe, regs);
-                unlock_kprobes();
+        if (kcb->kprobe_status & KPROBE_HIT_SS) {
+                resume_execution(cur, regs);
+                reset_current_kprobe();
                 preempt_enable_no_resched();
         }
 
@@ -733,31 +735,42 @@ int __kprobes kprobe_exceptions_notify(struct notifier_block *self,
                                        unsigned long val, void *data)
 {
         struct die_args *args = (struct die_args *)data;
+        int ret = NOTIFY_DONE;
+
         switch(val) {
         case DIE_BREAK:
-                if (pre_kprobes_handler(args))
-                        return NOTIFY_STOP;
+                /* err is break number from ia64_bad_break() */
+                if (args->err == 0x80200 || args->err == 0x80300 || args->err == 0)
+                        if (pre_kprobes_handler(args))
+                                ret = NOTIFY_STOP;
                 break;
-        case DIE_SS:
-                if (post_kprobes_handler(args->regs))
-                        return NOTIFY_STOP;
+        case DIE_FAULT:
+                /* err is vector number from ia64_fault() */
+                if (args->err == 36)
+                        if (post_kprobes_handler(args->regs))
+                                ret = NOTIFY_STOP;
                 break;
         case DIE_PAGE_FAULT:
-                if (kprobes_fault_handler(args->regs, args->trapnr))
-                        return NOTIFY_STOP;
+                /* kprobe_running() needs smp_processor_id() */
+                preempt_disable();
+                if (kprobe_running() &&
+                        kprobes_fault_handler(args->regs, args->trapnr))
+                        ret = NOTIFY_STOP;
+                preempt_enable();
         default:
                 break;
         }
-        return NOTIFY_DONE;
+        return ret;
 }
 
 int __kprobes setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs)
 {
         struct jprobe *jp = container_of(p, struct jprobe, kp);
         unsigned long addr = ((struct fnptr *)(jp->entry))->ip;
+        struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
 
         /* save architectural state */
-        jprobe_saved_regs = *regs;
+        kcb->jprobe_saved_regs = *regs;
 
         /* after rfi, execute the jprobe instrumented function */
         regs->cr_iip = addr & ~0xFULL;
@@ -775,7 +788,10 @@ int __kprobes setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs)
 
 int __kprobes longjmp_break_handler(struct kprobe *p, struct pt_regs *regs)
 {
-        *regs = jprobe_saved_regs;
+        struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
+
+        *regs = kcb->jprobe_saved_regs;
+        preempt_enable_no_resched();
         return 1;
 }
 
diff --git a/arch/ia64/kernel/mca.c b/arch/ia64/kernel/mca.c
index 6dc726ad7137..355af15287c7 100644
--- a/arch/ia64/kernel/mca.c
+++ b/arch/ia64/kernel/mca.c
@@ -51,6 +51,9 @@
  *
  * 2005-08-12 Keith Owens <kaos@sgi.com>
  *            Convert MCA/INIT handlers to use per event stacks and SAL/OS state.
+ *
+ * 2005-10-07 Keith Owens <kaos@sgi.com>
+ *            Add notify_die() hooks.
  */
 #include <linux/config.h>
 #include <linux/types.h>
@@ -58,7 +61,6 @@
 #include <linux/sched.h>
 #include <linux/interrupt.h>
 #include <linux/irq.h>
-#include <linux/kallsyms.h>
 #include <linux/smp_lock.h>
 #include <linux/bootmem.h>
 #include <linux/acpi.h>
@@ -69,6 +71,7 @@
 #include <linux/workqueue.h>
 
 #include <asm/delay.h>
+#include <asm/kdebug.h>
 #include <asm/machvec.h>
 #include <asm/meminit.h>
 #include <asm/page.h>
@@ -132,6 +135,14 @@ extern void salinfo_log_wakeup(int type, u8 *buffer, u64 size, int irqsafe);
 
 static int mca_init;
 
+
+static void inline
+ia64_mca_spin(const char *func)
+{
+        printk(KERN_EMERG "%s: spinning here, not returning to SAL\n", func);
+        while (1)
+                cpu_relax();
+}
 /*
  * IA64_MCA log support
  */
@@ -508,9 +519,7 @@ ia64_mca_wakeup_all(void)
         int cpu;
 
         /* Clear the Rendez checkin flag for all cpus */
-        for(cpu = 0; cpu < NR_CPUS; cpu++) {
-                if (!cpu_online(cpu))
-                        continue;
+        for_each_online_cpu(cpu) {
                 if (ia64_mc_info.imi_rendez_checkin[cpu] == IA64_MCA_RENDEZ_CHECKIN_DONE)
                         ia64_mca_wakeup(cpu);
         }
@@ -528,13 +537,16 @@ ia64_mca_wakeup_all(void)
  *  Outputs :   None
  */
 static irqreturn_t
-ia64_mca_rendez_int_handler(int rendez_irq, void *arg, struct pt_regs *ptregs)
+ia64_mca_rendez_int_handler(int rendez_irq, void *arg, struct pt_regs *regs)
 {
         unsigned long flags;
         int cpu = smp_processor_id();
 
         /* Mask all interrupts */
         local_irq_save(flags);
+        if (notify_die(DIE_MCA_RENDZVOUS_ENTER, "MCA", regs, 0, 0, 0)
+                        == NOTIFY_STOP)
+                ia64_mca_spin(__FUNCTION__);
 
         ia64_mc_info.imi_rendez_checkin[cpu] = IA64_MCA_RENDEZ_CHECKIN_DONE;
         /* Register with the SAL monarch that the slave has
@@ -542,10 +554,18 @@ ia64_mca_rendez_int_handler(int rendez_irq, void *arg, struct pt_regs *ptregs)
          */
         ia64_sal_mc_rendez();
 
+        if (notify_die(DIE_MCA_RENDZVOUS_PROCESS, "MCA", regs, 0, 0, 0)
+                        == NOTIFY_STOP)
+                ia64_mca_spin(__FUNCTION__);
+
         /* Wait for the monarch cpu to exit. */
         while (monarch_cpu != -1)
                cpu_relax();     /* spin until monarch leaves */
 
+        if (notify_die(DIE_MCA_RENDZVOUS_LEAVE, "MCA", regs, 0, 0, 0)
+                        == NOTIFY_STOP)
+                ia64_mca_spin(__FUNCTION__);
+
         /* Enable all interrupts */
         local_irq_restore(flags);
         return IRQ_HANDLED;
@@ -935,6 +955,9 @@ ia64_mca_handler(struct pt_regs *regs, struct switch_stack *sw,
         oops_in_progress = 1;   /* FIXME: make printk NMI/MCA/INIT safe */
         previous_current = ia64_mca_modify_original_stack(regs, sw, sos, "MCA");
         monarch_cpu = cpu;
+        if (notify_die(DIE_MCA_MONARCH_ENTER, "MCA", regs, 0, 0, 0)
+                        == NOTIFY_STOP)
+                ia64_mca_spin(__FUNCTION__);
         ia64_wait_for_slaves(cpu);
 
         /* Wakeup all the processors which are spinning in the rendezvous loop.
@@ -944,6 +967,9 @@ ia64_mca_handler(struct pt_regs *regs, struct switch_stack *sw,
          * spinning in SAL does not work.
          */
         ia64_mca_wakeup_all();
+        if (notify_die(DIE_MCA_MONARCH_PROCESS, "MCA", regs, 0, 0, 0)
+                        == NOTIFY_STOP)
+                ia64_mca_spin(__FUNCTION__);
 
         /* Get the MCA error record and log it */
         ia64_mca_log_sal_error_record(SAL_INFO_TYPE_MCA);
@@ -962,6 +988,9 @@ ia64_mca_handler(struct pt_regs *regs, struct switch_stack *sw,
                 ia64_sal_clear_state_info(SAL_INFO_TYPE_MCA);
                 sos->os_status = IA64_MCA_CORRECTED;
         }
+        if (notify_die(DIE_MCA_MONARCH_LEAVE, "MCA", regs, 0, 0, recover)
+                        == NOTIFY_STOP)
+                ia64_mca_spin(__FUNCTION__);
 
         set_curr_task(cpu, previous_current);
         monarch_cpu = -1;
@@ -1016,6 +1045,11 @@ ia64_mca_cmc_int_handler(int cmc_irq, void *arg, struct pt_regs *ptregs)
 
                         cmc_polling_enabled = 1;
                         spin_unlock(&cmc_history_lock);
+                        /* If we're being hit with CMC interrupts, we won't
+                         * ever execute the schedule_work() below.  Need to
+                         * disable CMC interrupts on this processor now.
+                         */
+                        ia64_mca_cmc_vector_disable(NULL);
                         schedule_work(&cmc_disable_work);
 
                         /*
@@ -1185,6 +1219,37 @@ ia64_mca_cpe_poll (unsigned long dummy)
 
 #endif /* CONFIG_ACPI */
 
+static int
+default_monarch_init_process(struct notifier_block *self, unsigned long val, void *data)
+{
+        int c;
+        struct task_struct *g, *t;
+        if (val != DIE_INIT_MONARCH_PROCESS)
+                return NOTIFY_DONE;
+        printk(KERN_ERR "Processes interrupted by INIT -");
+        for_each_online_cpu(c) {
+                struct ia64_sal_os_state *s;
+                t = __va(__per_cpu_mca[c] + IA64_MCA_CPU_INIT_STACK_OFFSET);
+                s = (struct ia64_sal_os_state *)((char *)t + MCA_SOS_OFFSET);
+                g = s->prev_task;
+                if (g) {
+                        if (g->pid)
+                                printk(" %d", g->pid);
+                        else
+                                printk(" %d (cpu %d task 0x%p)", g->pid, task_cpu(g), g);
+                }
+        }
+        printk("\n\n");
+        if (read_trylock(&tasklist_lock)) {
+                do_each_thread (g, t) {
+                        printk("\nBacktrace of pid %d (%s)\n", t->pid, t->comm);
+                        show_stack(t, NULL);
+                } while_each_thread (g, t);
+                read_unlock(&tasklist_lock);
+        }
+        return NOTIFY_DONE;
+}
+
 /*
  * C portion of the OS INIT handler
  *
@@ -1209,8 +1274,7 @@ ia64_init_handler(struct pt_regs *regs, struct switch_stack *sw,
         static atomic_t slaves;
         static atomic_t monarchs;
         task_t *previous_current;
-        int cpu = smp_processor_id(), c;
-        struct task_struct *g, *t;
+        int cpu = smp_processor_id();
 
         oops_in_progress = 1;   /* FIXME: make printk NMI/MCA/INIT safe */
         console_loglevel = 15;  /* make sure printks make it to console */
@@ -1250,8 +1314,17 @@ ia64_init_handler(struct pt_regs *regs, struct switch_stack *sw,
                 ia64_mc_info.imi_rendez_checkin[cpu] = IA64_MCA_RENDEZ_CHECKIN_INIT;
                 while (monarch_cpu == -1)
                        cpu_relax();     /* spin until monarch enters */
+                if (notify_die(DIE_INIT_SLAVE_ENTER, "INIT", regs, 0, 0, 0)
+                                == NOTIFY_STOP)
+                        ia64_mca_spin(__FUNCTION__);
+                if (notify_die(DIE_INIT_SLAVE_PROCESS, "INIT", regs, 0, 0, 0)
+                                == NOTIFY_STOP)
+                        ia64_mca_spin(__FUNCTION__);
                 while (monarch_cpu != -1)
                        cpu_relax();     /* spin until monarch leaves */
+                if (notify_die(DIE_INIT_SLAVE_LEAVE, "INIT", regs, 0, 0, 0)
+                                == NOTIFY_STOP)
+                        ia64_mca_spin(__FUNCTION__);
                 printk("Slave on cpu %d returning to normal service.\n", cpu);
                 set_curr_task(cpu, previous_current);
                 ia64_mc_info.imi_rendez_checkin[cpu] = IA64_MCA_RENDEZ_CHECKIN_NOTDONE;
@@ -1260,6 +1333,9 @@ ia64_init_handler(struct pt_regs *regs, struct switch_stack *sw,
         }
 
         monarch_cpu = cpu;
+        if (notify_die(DIE_INIT_MONARCH_ENTER, "INIT", regs, 0, 0, 0)
+                        == NOTIFY_STOP)
+                ia64_mca_spin(__FUNCTION__);
 
         /*
          * Wait for a bit.  On some machines (e.g., HP's zx2000 and zx6000, INIT can be
@@ -1270,27 +1346,16 @@ ia64_init_handler(struct pt_regs *regs, struct switch_stack *sw,
         printk("Delaying for 5 seconds...\n");
         udelay(5*1000000);
         ia64_wait_for_slaves(cpu);
-        printk(KERN_ERR "Processes interrupted by INIT -");
-        for_each_online_cpu(c) {
-                struct ia64_sal_os_state *s;
-                t = __va(__per_cpu_mca[c] + IA64_MCA_CPU_INIT_STACK_OFFSET);
-                s = (struct ia64_sal_os_state *)((char *)t + MCA_SOS_OFFSET);
-                g = s->prev_task;
-                if (g) {
-                        if (g->pid)
-                                printk(" %d", g->pid);
-                        else
-                                printk(" %d (cpu %d task 0x%p)", g->pid, task_cpu(g), g);
-                }
-        }
-        printk("\n\n");
-        if (read_trylock(&tasklist_lock)) {
-                do_each_thread (g, t) {
-                        printk("\nBacktrace of pid %d (%s)\n", t->pid, t->comm);
-                        show_stack(t, NULL);
-                } while_each_thread (g, t);
-                read_unlock(&tasklist_lock);
-        }
+        /* If nobody intercepts DIE_INIT_MONARCH_PROCESS then we drop through
+         * to default_monarch_init_process() above and just print all the
+         * tasks.
+         */
+        if (notify_die(DIE_INIT_MONARCH_PROCESS, "INIT", regs, 0, 0, 0)
+                        == NOTIFY_STOP)
+                ia64_mca_spin(__FUNCTION__);
+        if (notify_die(DIE_INIT_MONARCH_LEAVE, "INIT", regs, 0, 0, 0)
+                        == NOTIFY_STOP)
+                ia64_mca_spin(__FUNCTION__);
         printk("\nINIT dump complete.  Monarch on cpu %d returning to normal service.\n", cpu);
         atomic_dec(&monarchs);
         set_curr_task(cpu, previous_current);
@@ -1459,6 +1524,10 @@ ia64_mca_init(void)
         s64 rc;
         struct ia64_sal_retval isrv;
         u64 timeout = IA64_MCA_RENDEZ_TIMEOUT;  /* platform specific */
+        static struct notifier_block default_init_monarch_nb = {
+                .notifier_call = default_monarch_init_process,
+                .priority = 0/* we need to notified last */
+        };
 
         IA64_MCA_DEBUG("%s: begin\n", __FUNCTION__);
 
@@ -1552,6 +1621,10 @@ ia64_mca_init(void)
                        "(status %ld)\n", rc);
                 return;
         }
+        if (register_die_notifier(&default_init_monarch_nb)) {
+                printk(KERN_ERR "Failed to register default monarch INIT process\n");
+                return;
+        }
 
         IA64_MCA_DEBUG("%s: registered OS INIT handler with SAL\n", __FUNCTION__);
 
diff --git a/arch/ia64/kernel/mca_asm.S b/arch/ia64/kernel/mca_asm.S
index 499a065f4e60..db32fc1d3935 100644
--- a/arch/ia64/kernel/mca_asm.S
+++ b/arch/ia64/kernel/mca_asm.S
@@ -489,24 +489,27 @@ ia64_state_save:
         ;;
         st8 [temp1]=r17,16      // pal_min_state
         st8 [temp2]=r6,16       // prev_IA64_KR_CURRENT
+        mov r6=IA64_KR(CURRENT_STACK)
+        ;;
+        st8 [temp1]=r6,16       // prev_IA64_KR_CURRENT_STACK
+        st8 [temp2]=r0,16       // prev_task, starts off as NULL
         mov r6=cr.ifa
         ;;
-        st8 [temp1]=r0,16       // prev_task, starts off as NULL
-        st8 [temp2]=r12,16      // cr.isr
+        st8 [temp1]=r12,16      // cr.isr
+        st8 [temp2]=r6,16       // cr.ifa
         mov r12=cr.itir
         ;;
-        st8 [temp1]=r6,16       // cr.ifa
-        st8 [temp2]=r12,16      // cr.itir
+        st8 [temp1]=r12,16      // cr.itir
+        st8 [temp2]=r11,16      // cr.iipa
         mov r12=cr.iim
         ;;
-        st8 [temp1]=r11,16      // cr.iipa
-        st8 [temp2]=r12,16      // cr.iim
-        mov r6=cr.iha
+        st8 [temp1]=r12,16      // cr.iim
 (p1)    mov r12=IA64_MCA_COLD_BOOT
 (p2)    mov r12=IA64_INIT_WARM_BOOT
+        mov r6=cr.iha
         ;;
-        st8 [temp1]=r6,16       // cr.iha
-        st8 [temp2]=r12         // os_status, default is cold boot
+        st8 [temp2]=r6,16       // cr.iha
+        st8 [temp1]=r12         // os_status, default is cold boot
         mov r6=IA64_MCA_SAME_CONTEXT
         ;;
         st8 [temp1]=r6          // context, default is same context
@@ -823,9 +826,12 @@ ia64_state_restore:
         ld8 r12=[temp1],16      // sal_ra
         ld8 r9=[temp2],16       // sal_gp
         ;;
-        ld8 r22=[temp1],24      // pal_min_state, virtual.  skip prev_task
+        ld8 r22=[temp1],16      // pal_min_state, virtual
         ld8 r21=[temp2],16      // prev_IA64_KR_CURRENT
         ;;
+        ld8 r16=[temp1],16      // prev_IA64_KR_CURRENT_STACK
+        ld8 r20=[temp2],16      // prev_task
+        ;;
         ld8 temp3=[temp1],16    // cr.isr
         ld8 temp4=[temp2],16    // cr.ifa
         ;;
@@ -846,6 +852,45 @@ ia64_state_restore:
         ld8 r8=[temp1]          // os_status
         ld8 r10=[temp2]         // context
 
+        /* Wire IA64_TR_CURRENT_STACK to the stack that we are resuming to.  To
+         * avoid any dependencies on the algorithm in ia64_switch_to(), just
+         * purge any existing CURRENT_STACK mapping and insert the new one.
+         *
+         * r16 contains prev_IA64_KR_CURRENT_STACK, r21 contains
+         * prev_IA64_KR_CURRENT, these values may have been changed by the C
+         * code.  Do not use r8, r9, r10, r22, they contain values ready for
+         * the return to SAL.
+         */
+
+        mov r15=IA64_KR(CURRENT_STACK)          // physical granule mapped by IA64_TR_CURRENT_STACK
+        ;;
+        shl r15=r15,IA64_GRANULE_SHIFT
+        ;;
+        dep r15=-1,r15,61,3                     // virtual granule
+        mov r18=IA64_GRANULE_SHIFT<<2           // for cr.itir.ps
+        ;;
+        ptr.d r15,r18
+        ;;
+        srlz.d
+
+        extr.u r19=r21,61,3                     // r21 = prev_IA64_KR_CURRENT
+        shl r20=r16,IA64_GRANULE_SHIFT          // r16 = prev_IA64_KR_CURRENT_STACK
+        movl r21=PAGE_KERNEL                    // page properties
+        ;;
+        mov IA64_KR(CURRENT_STACK)=r16
+        cmp.ne p6,p0=RGN_KERNEL,r19             // new stack is in the kernel region?
+        or r21=r20,r21                          // construct PA | page properties
+(p6)    br.spnt 1f                              // the dreaded cpu 0 idle task in region 5:(
+        ;;
+        mov cr.itir=r18
+        mov cr.ifa=r21
+        mov r20=IA64_TR_CURRENT_STACK
+        ;;
+        itr.d dtr[r20]=r21
+        ;;
+        srlz.d
+1:
+
         br.sptk b0
 
 //EndStub//////////////////////////////////////////////////////////////////////
@@ -982,6 +1027,7 @@ ia64_set_kernel_registers:
         add temp4=temp4, temp1  // &struct ia64_sal_os_state.os_gp
         add r12=temp1, temp3    // kernel stack pointer on MCA/INIT stack
         add r13=temp1, r3       // set current to start of MCA/INIT stack
+        add r20=temp1, r3       // physical start of MCA/INIT stack
         ;;
         ld8 r1=[temp4]          // OS GP from SAL OS state
         ;;
@@ -991,7 +1037,35 @@ ia64_set_kernel_registers:
         ;;
         mov IA64_KR(CURRENT)=r13
 
-        // FIXME: do I need to wire IA64_KR_CURRENT_STACK and IA64_TR_CURRENT_STACK?
+        /* Wire IA64_TR_CURRENT_STACK to the MCA/INIT handler stack.  To avoid
+         * any dependencies on the algorithm in ia64_switch_to(), just purge
+         * any existing CURRENT_STACK mapping and insert the new one.
+         */
+
+        mov r16=IA64_KR(CURRENT_STACK)          // physical granule mapped by IA64_TR_CURRENT_STACK
+        ;;
+        shl r16=r16,IA64_GRANULE_SHIFT
+        ;;
+        dep r16=-1,r16,61,3                     // virtual granule
+        mov r18=IA64_GRANULE_SHIFT<<2           // for cr.itir.ps
+        ;;
+        ptr.d r16,r18
+        ;;
+        srlz.d
+
+        shr.u r16=r20,IA64_GRANULE_SHIFT        // r20 = physical start of MCA/INIT stack
+        movl r21=PAGE_KERNEL                    // page properties
+        ;;
+        mov IA64_KR(CURRENT_STACK)=r16
+        or r21=r20,r21                          // construct PA | page properties
+        ;;
+        mov cr.itir=r18
+        mov cr.ifa=r13
+        mov r20=IA64_TR_CURRENT_STACK
+        ;;
+        itr.d dtr[r20]=r21
+        ;;
+        srlz.d
 
         br.sptk b0
 
diff --git a/arch/ia64/kernel/mca_drv.c b/arch/ia64/kernel/mca_drv.c
index 80f83d6cdbfc..3492e3211a44 100644
--- a/arch/ia64/kernel/mca_drv.c
+++ b/arch/ia64/kernel/mca_drv.c
@@ -56,8 +56,9 @@ static struct page *page_isolate[MAX_PAGE_ISOLATE];
 static int num_page_isolate = 0;
 
 typedef enum {
-        ISOLATE_NG = 0,
-        ISOLATE_OK = 1
+        ISOLATE_NG,
+        ISOLATE_OK,
+        ISOLATE_NONE
 } isolate_status_t;
 
 /*
@@ -74,7 +75,7 @@ static struct {
  * @paddr:      poisoned memory location
  *
  * Return value:
- *      ISOLATE_OK / ISOLATE_NG
+ *      one of isolate_status_t, ISOLATE_OK/NG/NONE.
  */
 
 static isolate_status_t
@@ -85,7 +86,10 @@ mca_page_isolate(unsigned long paddr)
 
         /* whether physical address is valid or not */
         if (!ia64_phys_addr_valid(paddr))
-                return ISOLATE_NG;
+                return ISOLATE_NONE;
+
+        if (!pfn_valid(paddr >> PAGE_SHIFT))
+                return ISOLATE_NONE;
 
         /* convert physical address to physical page number */
         p = pfn_to_page(paddr>>PAGE_SHIFT);
@@ -104,6 +108,7 @@ mca_page_isolate(unsigned long paddr)
                 return ISOLATE_NG;
 
         /* add attribute 'Reserved' and register the page */
+        get_page(p);
         SetPageReserved(p);
         page_isolate[num_page_isolate++] = p;
 
@@ -122,10 +127,15 @@ mca_handler_bh(unsigned long paddr)
                 current->pid, current->comm);
 
         spin_lock(&mca_bh_lock);
-        if (mca_page_isolate(paddr) == ISOLATE_OK) {
+        switch (mca_page_isolate(paddr)) {
+        case ISOLATE_OK:
                 printk(KERN_DEBUG "Page isolation: ( %lx ) success.\n", paddr);
-        } else {
+                break;
+        case ISOLATE_NG:
                 printk(KERN_DEBUG "Page isolation: ( %lx ) failure.\n", paddr);
+                break;
+        default:
+                break;
         }
         spin_unlock(&mca_bh_lock);
 
@@ -537,9 +547,20 @@ recover_from_processor_error(int platform, slidx_table_t *slidx,
                 (pal_processor_state_info_t*)peidx_psp(peidx);
 
         /*
-         * We cannot recover errors with other than bus_check.
+         * Processor recovery status must key off of the PAL recovery
+         * status in the Processor State Parameter.
+         */
+
+        /*
+         * The machine check is corrected.
          */
-        if (psp->cc || psp->rc || psp->uc)
+        if (psp->cm == 1)
+                return 1;
+
+        /*
+         * The error was not contained.  Software must be reset.
+         */
+        if (psp->us || psp->ci == 0)
                 return 0;
 
         /*
@@ -560,8 +581,6 @@ recover_from_processor_error(int platform, slidx_table_t *slidx,
                 return 0;
         if (pbci->eb && pbci->bsi > 0)
                 return 0;
-        if (psp->ci == 0)
-                return 0;
 
         /*
          * This is a local MCA and estimated as recoverble external bus error.
diff --git a/arch/ia64/kernel/module.c b/arch/ia64/kernel/module.c
index f1aca7cffd12..7a2f0a798d12 100644
--- a/arch/ia64/kernel/module.c
+++ b/arch/ia64/kernel/module.c
@@ -947,8 +947,8 @@ void
 percpu_modcopy (void *pcpudst, const void *src, unsigned long size)
 {
         unsigned int i;
-        for (i = 0; i < NR_CPUS; i++)
-                if (cpu_possible(i))
-                        memcpy(pcpudst + __per_cpu_offset[i], src, size);
+        for_each_cpu(i) {
+                memcpy(pcpudst + __per_cpu_offset[i], src, size);
+        }
 }
 #endif /* CONFIG_SMP */
diff --git a/arch/ia64/kernel/patch.c b/arch/ia64/kernel/patch.c
index 367804a605fa..6a4ac7d70b35 100644
--- a/arch/ia64/kernel/patch.c
+++ b/arch/ia64/kernel/patch.c
@@ -64,22 +64,30 @@ ia64_patch (u64 insn_addr, u64 mask, u64 val)
 void
 ia64_patch_imm64 (u64 insn_addr, u64 val)
 {
-        ia64_patch(insn_addr,
+        /* The assembler may generate offset pointing to either slot 1
+           or slot 2 for a long (2-slot) instruction, occupying slots 1
+           and 2.  */
+        insn_addr &= -16UL;
+        ia64_patch(insn_addr + 2,
                    0x01fffefe000UL, (  ((val & 0x8000000000000000UL) >> 27) /* bit 63 -> 36 */
                                      | ((val & 0x0000000000200000UL) <<  0) /* bit 21 -> 21 */
                                      | ((val & 0x00000000001f0000UL) <<  6) /* bit 16 -> 22 */
                                      | ((val & 0x000000000000ff80UL) << 20) /* bit  7 -> 27 */
                                      | ((val & 0x000000000000007fUL) << 13) /* bit  0 -> 13 */));
-        ia64_patch(insn_addr - 1, 0x1ffffffffffUL, val >> 22);
+        ia64_patch(insn_addr + 1, 0x1ffffffffffUL, val >> 22);
 }
 
 void
 ia64_patch_imm60 (u64 insn_addr, u64 val)
 {
-        ia64_patch(insn_addr,
+        /* The assembler may generate offset pointing to either slot 1
+           or slot 2 for a long (2-slot) instruction, occupying slots 1
+           and 2.  */
+        insn_addr &= -16UL;
+        ia64_patch(insn_addr + 2,
                    0x011ffffe000UL, (  ((val & 0x0800000000000000UL) >> 23) /* bit 59 -> 36 */
                                      | ((val & 0x00000000000fffffUL) << 13) /* bit  0 -> 13 */));
-        ia64_patch(insn_addr - 1, 0x1fffffffffcUL, val >> 18);
+        ia64_patch(insn_addr + 1, 0x1fffffffffcUL, val >> 18);
 }
 
 /*
diff --git a/arch/ia64/kernel/perfmon.c b/arch/ia64/kernel/perfmon.c
index d71731ee5b61..410d4804fa6e 100644
--- a/arch/ia64/kernel/perfmon.c
+++ b/arch/ia64/kernel/perfmon.c
@@ -2352,7 +2352,8 @@ pfm_smpl_buffer_alloc(struct task_struct *task, pfm_context_t *ctx, unsigned lon
         insert_vm_struct(mm, vma);
 
         mm->total_vm  += size >> PAGE_SHIFT;
-        vm_stat_account(vma);
+        vm_stat_account(vma->vm_mm, vma->vm_flags, vma->vm_file,
+                                                        vma_pages(vma));
         up_write(&task->mm->mmap_sem);
 
         /*
@@ -4939,7 +4940,7 @@ abort_locked:
         if (call_made && PFM_CMD_RW_ARG(cmd) && copy_to_user(arg, args_k, base_sz*count)) ret = -EFAULT;
 
 error_args:
-        if (args_k) kfree(args_k);
+        kfree(args_k);
 
         DPRINT(("cmd=%s ret=%ld\n", PFM_CMD_NAME(cmd), ret));
 
diff --git a/arch/ia64/kernel/process.c b/arch/ia64/kernel/process.c
index 051e050359e4..2e33665d9c18 100644
--- a/arch/ia64/kernel/process.c
+++ b/arch/ia64/kernel/process.c
@@ -4,6 +4,9 @@
  * Copyright (C) 1998-2003 Hewlett-Packard Co
  *      David Mosberger-Tang <davidm@hpl.hp.com>
  * 04/11/17 Ashok Raj   <ashok.raj@intel.com> Added CPU Hotplug Support
+ *
+ * 2005-10-07 Keith Owens <kaos@sgi.com>
+ *            Add notify_die() hooks.
  */
 #define __KERNEL_SYSCALLS__     /* see <asm/unistd.h> */
 #include <linux/config.h>
@@ -34,6 +37,7 @@
 #include <asm/elf.h>
 #include <asm/ia32.h>
 #include <asm/irq.h>
+#include <asm/kdebug.h>
 #include <asm/pgalloc.h>
 #include <asm/processor.h>
 #include <asm/sal.h>
@@ -197,11 +201,12 @@ void
 default_idle (void)
 {
         local_irq_enable();
-        while (!need_resched())
+        while (!need_resched()) {
                 if (can_do_pal_halt)
                         safe_halt();
                 else
                         cpu_relax();
+        }
 }
 
 #ifdef CONFIG_HOTPLUG_CPU
@@ -263,16 +268,20 @@ void __attribute__((noreturn))
 cpu_idle (void)
 {
         void (*mark_idle)(int) = ia64_mark_idle;
+        int cpu = smp_processor_id();
 
         /* endless idle loop with no priority at all */
         while (1) {
+                if (can_do_pal_halt)
+                        clear_thread_flag(TIF_POLLING_NRFLAG);
+                else
+                        set_thread_flag(TIF_POLLING_NRFLAG);
+
+                if (!need_resched()) {
+                        void (*idle)(void);
 #ifdef CONFIG_SMP
-                if (!need_resched())
                         min_xtp();
 #endif
-                while (!need_resched()) {
-                        void (*idle)(void);
-
                         if (__get_cpu_var(cpu_idle_state))
                                 __get_cpu_var(cpu_idle_state) = 0;
 
@@ -284,17 +293,17 @@ cpu_idle (void)
                         if (!idle)
                                 idle = default_idle;
                         (*idle)();
-                }
-
-                if (mark_idle)
-                        (*mark_idle)(0);
-
+                        if (mark_idle)
+                                (*mark_idle)(0);
 #ifdef CONFIG_SMP
-                normal_xtp();
+                        normal_xtp();
 #endif
+                }
+                preempt_enable_no_resched();
                 schedule();
+                preempt_disable();
                 check_pgt_cache();
-                if (cpu_is_offline(smp_processor_id()))
+                if (cpu_is_offline(cpu))
                         play_dead();
         }
 }
@@ -709,13 +718,6 @@ kernel_thread_helper (int (*fn)(void *), void *arg)
 void
 flush_thread (void)
 {
-        /*
-         * Remove function-return probe instances associated with this task
-         * and put them back on the free list. Do not insert an exit probe for
-         * this function, it will be disabled by kprobe_flush_task if you do.
-         */
-        kprobe_flush_task(current);
-
         /* drop floating-point and debug-register state if it exists: */
         current->thread.flags &= ~(IA64_THREAD_FPH_VALID | IA64_THREAD_DBG_VALID);
         ia64_drop_fpu(current);
@@ -804,12 +806,14 @@ cpu_halt (void)
 void
 machine_restart (char *restart_cmd)
 {
+        (void) notify_die(DIE_MACHINE_RESTART, restart_cmd, NULL, 0, 0, 0);
         (*efi.reset_system)(EFI_RESET_WARM, 0, 0, NULL);
 }
 
 void
 machine_halt (void)
 {
+        (void) notify_die(DIE_MACHINE_HALT, "", NULL, 0, 0, 0);
         cpu_halt();
 }
 
diff --git a/arch/ia64/kernel/ptrace.c b/arch/ia64/kernel/ptrace.c
index bbb8bc7c0552..4b19d0410632 100644
--- a/arch/ia64/kernel/ptrace.c
+++ b/arch/ia64/kernel/ptrace.c
@@ -587,8 +587,9 @@ thread_matches (struct task_struct *thread, unsigned long addr)
 static struct task_struct *
 find_thread_for_addr (struct task_struct *child, unsigned long addr)
 {
-        struct task_struct *g, *p;
+        struct task_struct *p;
         struct mm_struct *mm;
+        struct list_head *this, *next;
         int mm_users;
 
         if (!(mm = get_task_mm(child)))
@@ -600,28 +601,21 @@ find_thread_for_addr (struct task_struct *child, unsigned long addr)
                 goto out;               /* not multi-threaded */
 
         /*
-         * First, traverse the child's thread-list.  Good for scalability with
-         * NPTL-threads.
+         * Traverse the current process' children list.  Every task that
+         * one attaches to becomes a child.  And it is only attached children
+         * of the debugger that are of interest (ptrace_check_attach checks
+         * for this).
          */
-        p = child;
-        do {
-                if (thread_matches(p, addr)) {
-                        child = p;
-                        goto out;
-                }
-                if (mm_users-- <= 1)
-                        goto out;
-        } while ((p = next_thread(p)) != child);
-
-        do_each_thread(g, p) {
-                if (child->mm != mm)
+        list_for_each_safe(this, next, &current->children) {
+                p = list_entry(this, struct task_struct, sibling);
+                if (p->mm != mm)
                         continue;
-
                 if (thread_matches(p, addr)) {
                         child = p;
                         goto out;
                 }
-        } while_each_thread(g, p);
+        }
+
   out:
         mmput(mm);
         return child;
diff --git a/arch/ia64/kernel/setup.c b/arch/ia64/kernel/setup.c
index 1f5c26dbe705..5add0bcf87a7 100644
--- a/arch/ia64/kernel/setup.c
+++ b/arch/ia64/kernel/setup.c
@@ -78,7 +78,27 @@ struct screen_info screen_info;
 unsigned long vga_console_iobase;
 unsigned long vga_console_membase;
 
+static struct resource data_resource = {
+        .name   = "Kernel data",
+        .flags  = IORESOURCE_BUSY | IORESOURCE_MEM
+};
+
+static struct resource code_resource = {
+        .name   = "Kernel code",
+        .flags  = IORESOURCE_BUSY | IORESOURCE_MEM
+};
+extern void efi_initialize_iomem_resources(struct resource *,
+                struct resource *);
+extern char _text[], _end[], _etext[];
+
 unsigned long ia64_max_cacheline_size;
+
+int dma_get_cache_alignment(void)
+{
+        return ia64_max_cacheline_size;
+}
+EXPORT_SYMBOL(dma_get_cache_alignment);
+
 unsigned long ia64_iobase;      /* virtual address for I/O accesses */
 EXPORT_SYMBOL(ia64_iobase);
 struct io_space io_space[MAX_IO_SPACES];
@@ -171,6 +191,22 @@ sort_regions (struct rsvd_region *rsvd_region, int max)
         }
 }
 
+/*
+ * Request address space for all standard resources
+ */
+static int __init register_memory(void)
+{
+        code_resource.start = ia64_tpa(_text);
+        code_resource.end   = ia64_tpa(_etext) - 1;
+        data_resource.start = ia64_tpa(_etext);
+        data_resource.end   = ia64_tpa(_end) - 1;
+        efi_initialize_iomem_resources(&code_resource, &data_resource);
+
+        return 0;
+}
+
+__initcall(register_memory);
+
 /**
  * reserve_memory - setup reserved memory areas
  *
@@ -211,6 +247,9 @@ reserve_memory (void)
         }
 #endif
 
+        efi_memmap_init(&rsvd_region[n].start, &rsvd_region[n].end);
+        n++;
+
         /* end of memory marker */
         rsvd_region[n].start = ~0UL;
         rsvd_region[n].end   = ~0UL;
@@ -244,28 +283,31 @@ find_initrd (void)
 static void __init
 io_port_init (void)
 {
-        extern unsigned long ia64_iobase;
         unsigned long phys_iobase;
 
         /*
-         *  Set `iobase' to the appropriate address in region 6 (uncached access range).
+         * Set `iobase' based on the EFI memory map or, failing that, the
+         * value firmware left in ar.k0.
          *
-         *  The EFI memory map is the "preferred" location to get the I/O port space base,
-         *  rather the relying on AR.KR0. This should become more clear in future SAL
-         *  specs. We'll fall back to getting it out of AR.KR0 if no appropriate entry is
-         *  found in the memory map.
+         * Note that in ia32 mode, IN/OUT instructions use ar.k0 to compute
+         * the port's virtual address, so ia32_load_state() loads it with a
+         * user virtual address.  But in ia64 mode, glibc uses the
+         * *physical* address in ar.k0 to mmap the appropriate area from
+         * /dev/mem, and the inX()/outX() interfaces use MMIO.  In both
+         * cases, user-mode can only use the legacy 0-64K I/O port space.
+         *
+         * ar.k0 is not involved in kernel I/O port accesses, which can use
+         * any of the I/O port spaces and are done via MMIO using the
+         * virtual mmio_base from the appropriate io_space[].
          */
         phys_iobase = efi_get_iobase();
-        if (phys_iobase)
-                /* set AR.KR0 since this is all we use it for anyway */
-                ia64_set_kr(IA64_KR_IO_BASE, phys_iobase);
-        else {
+        if (!phys_iobase) {
                 phys_iobase = ia64_get_kr(IA64_KR_IO_BASE);
-                printk(KERN_INFO "No I/O port range found in EFI memory map, falling back "
-                       "to AR.KR0\n");
-                printk(KERN_INFO "I/O port base = 0x%lx\n", phys_iobase);
+                printk(KERN_INFO "No I/O port range found in EFI memory map, "
+                        "falling back to AR.KR0 (0x%lx)\n", phys_iobase);
         }
         ia64_iobase = (unsigned long) ioremap(phys_iobase, 0);
+        ia64_set_kr(IA64_KR_IO_BASE, __pa(ia64_iobase));
 
         /* setup legacy IO port space */
         io_space[0].mmio_base = ia64_iobase;
@@ -419,6 +461,7 @@ setup_arch (char **cmdline_p)
 #endif
 
         cpu_init();     /* initialize the bootstrap CPU */
+        mmu_context_init();     /* initialize context_id bitmap */
 
 #ifdef CONFIG_ACPI
         acpi_boot_init();
@@ -526,7 +569,7 @@ show_cpuinfo (struct seq_file *m, void *v)
                    c->itc_freq / 1000000, c->itc_freq % 1000000,
                    lpj*HZ/500000, (lpj*HZ/5000) % 100);
 #ifdef CONFIG_SMP
-        seq_printf(m, "siblings   : %u\n", c->num_log);
+        seq_printf(m, "siblings   : %u\n", cpus_weight(cpu_core_map[cpunum]));
         if (c->threads_per_core > 1 || c->cores_per_socket > 1)
                 seq_printf(m,
                            "physical id: %u\n"
diff --git a/arch/ia64/kernel/signal.c b/arch/ia64/kernel/signal.c
index 774f34b675cf..58ce07efc56e 100644
--- a/arch/ia64/kernel/signal.c
+++ b/arch/ia64/kernel/signal.c
@@ -387,15 +387,14 @@ setup_frame (int sig, struct k_sigaction *ka, siginfo_t *info, sigset_t *set,
              struct sigscratch *scr)
 {
         extern char __kernel_sigtramp[];
-        unsigned long tramp_addr, new_rbs = 0;
+        unsigned long tramp_addr, new_rbs = 0, new_sp;
         struct sigframe __user *frame;
         long err;
 
-        frame = (void __user *) scr->pt.r12;
+        new_sp = scr->pt.r12;
         tramp_addr = (unsigned long) __kernel_sigtramp;
-        if ((ka->sa.sa_flags & SA_ONSTACK) && sas_ss_flags((unsigned long) frame) == 0) {
-                frame = (void __user *) ((current->sas_ss_sp + current->sas_ss_size)
-                                         & ~(STACK_ALIGN - 1));
+        if ((ka->sa.sa_flags & SA_ONSTACK) && sas_ss_flags(new_sp) == 0) {
+                new_sp = current->sas_ss_sp + current->sas_ss_size;
                 /*
                  * We need to check for the register stack being on the signal stack
                  * separately, because it's switched separately (memory stack is switched
@@ -404,7 +403,7 @@ setup_frame (int sig, struct k_sigaction *ka, siginfo_t *info, sigset_t *set,
                 if (!rbs_on_sig_stack(scr->pt.ar_bspstore))
                         new_rbs = (current->sas_ss_sp + sizeof(long) - 1) & ~(sizeof(long) - 1);
         }
-        frame = (void __user *) frame - ((sizeof(*frame) + STACK_ALIGN - 1) & ~(STACK_ALIGN - 1));
+        frame = (void __user *) ((new_sp - sizeof(*frame)) & -STACK_ALIGN);
 
         if (!access_ok(VERIFY_WRITE, frame, sizeof(*frame)))
                 return force_sigsegv_info(sig, frame);
diff --git a/arch/ia64/kernel/smp.c b/arch/ia64/kernel/smp.c
index 0166a9847095..657ac99a451c 100644
--- a/arch/ia64/kernel/smp.c
+++ b/arch/ia64/kernel/smp.c
@@ -185,8 +185,8 @@ send_IPI_allbutself (int op)
 {
         unsigned int i;
 
-        for (i = 0; i < NR_CPUS; i++) {
-                if (cpu_online(i) && i != smp_processor_id())
+        for_each_online_cpu(i) {
+                if (i != smp_processor_id())
                         send_IPI_single(i, op);
         }
 }
@@ -199,9 +199,9 @@ send_IPI_all (int op)
 {
         int i;
 
-        for (i = 0; i < NR_CPUS; i++)
-                if (cpu_online(i))
-                        send_IPI_single(i, op);
+        for_each_online_cpu(i) {
+                send_IPI_single(i, op);
+        }
 }
 
 /*
diff --git a/arch/ia64/kernel/smpboot.c b/arch/ia64/kernel/smpboot.c
index 7d72c0d872b3..8f44e7d2df66 100644
--- a/arch/ia64/kernel/smpboot.c
+++ b/arch/ia64/kernel/smpboot.c
@@ -399,6 +399,7 @@ start_secondary (void *unused)
         Dprintk("start_secondary: starting CPU 0x%x\n", hard_smp_processor_id());
         efi_map_pal_code();
         cpu_init();
+        preempt_disable();
         smp_callin();
 
         cpu_idle();
@@ -694,9 +695,9 @@ smp_cpus_done (unsigned int dummy)
          * Allow the user to impress friends.
          */
 
-        for (cpu = 0; cpu < NR_CPUS; cpu++)
-                if (cpu_online(cpu))
-                        bogosum += cpu_data(cpu)->loops_per_jiffy;
+        for_each_online_cpu(cpu) {
+                bogosum += cpu_data(cpu)->loops_per_jiffy;
+        }
 
         printk(KERN_INFO "Total of %d processors activated (%lu.%02lu BogoMIPS).\n",
                (int)num_online_cpus(), bogosum/(500000/HZ), (bogosum/(5000/HZ))%100);
diff --git a/arch/ia64/kernel/time.c b/arch/ia64/kernel/time.c
index 8b8a5a45b621..5b7e736f3b49 100644
--- a/arch/ia64/kernel/time.c
+++ b/arch/ia64/kernel/time.c
@@ -32,10 +32,6 @@
 
 extern unsigned long wall_jiffies;
 
-u64 jiffies_64 __cacheline_aligned_in_smp = INITIAL_JIFFIES;
-
-EXPORT_SYMBOL(jiffies_64);
-
 #define TIME_KEEPER_ID  0       /* smp_processor_id() of time-keeper */
 
 #ifdef CONFIG_IA64_DEBUG_IRQ
diff --git a/arch/ia64/kernel/traps.c b/arch/ia64/kernel/traps.c
index f970359e7edf..d3e0ecb56d62 100644
--- a/arch/ia64/kernel/traps.c
+++ b/arch/ia64/kernel/traps.c
@@ -30,17 +30,20 @@ fpswa_interface_t *fpswa_interface;
 EXPORT_SYMBOL(fpswa_interface);
 
 struct notifier_block *ia64die_chain;
-static DEFINE_SPINLOCK(die_notifier_lock);
 
-int register_die_notifier(struct notifier_block *nb)
+int
+register_die_notifier(struct notifier_block *nb)
 {
-        int err = 0;
-        unsigned long flags;
-        spin_lock_irqsave(&die_notifier_lock, flags);
-        err = notifier_chain_register(&ia64die_chain, nb);
-        spin_unlock_irqrestore(&die_notifier_lock, flags);
-        return err;
+        return notifier_chain_register(&ia64die_chain, nb);
 }
+EXPORT_SYMBOL_GPL(register_die_notifier);
+
+int
+unregister_die_notifier(struct notifier_block *nb)
+{
+        return notifier_chain_unregister(&ia64die_chain, nb);
+}
+EXPORT_SYMBOL_GPL(unregister_die_notifier);
 
 void __init
 trap_init (void)
@@ -105,6 +108,7 @@ die (const char *str, struct pt_regs *regs, long err)
         if (++die.lock_owner_depth < 3) {
                 printk("%s[%d]: %s %ld [%d]\n",
                         current->comm, current->pid, str, err, ++die_counter);
+                (void) notify_die(DIE_OOPS, (char *)str, regs, err, 255, SIGSEGV);
                 show_regs(regs);
         } else
                 printk(KERN_ERR "Recursive die() failure, output suppressed\n");
@@ -128,24 +132,6 @@ __kprobes ia64_bad_break (unsigned long break_num, struct pt_regs *regs)
         siginfo_t siginfo;
         int sig, code;
 
-        /* break.b always sets cr.iim to 0, which causes problems for
-         * debuggers.  Get the real break number from the original instruction,
-         * but only for kernel code.  User space break.b is left alone, to
-         * preserve the existing behaviour.  All break codings have the same
-         * format, so there is no need to check the slot type.
-         */
-        if (break_num == 0 && !user_mode(regs)) {
-                struct ia64_psr *ipsr = ia64_psr(regs);
-                unsigned long *bundle = (unsigned long *)regs->cr_iip;
-                unsigned long slot;
-                switch (ipsr->ri) {
-                      case 0:  slot = (bundle[0] >>  5); break;
-                      case 1:  slot = (bundle[0] >> 46) | (bundle[1] << 18); break;
-                      default: slot = (bundle[1] >> 23); break;
-                }
-                break_num = ((slot >> 36 & 1) << 20) | (slot >> 6 & 0xfffff);
-        }
-
         /* SIGILL, SIGFPE, SIGSEGV, and SIGBUS want these field initialized: */
         siginfo.si_addr = (void __user *) (regs->cr_iip + ia64_psr(regs)->ri);
         siginfo.si_imm = break_num;
@@ -155,9 +141,8 @@ __kprobes ia64_bad_break (unsigned long break_num, struct pt_regs *regs)
         switch (break_num) {
               case 0: /* unknown error (used by GCC for __builtin_abort()) */
                 if (notify_die(DIE_BREAK, "break 0", regs, break_num, TRAP_BRKPT, SIGTRAP)
-                                == NOTIFY_STOP) {
+                                == NOTIFY_STOP)
                         return;
-                }
                 die_if_kernel("bugcheck!", regs, break_num);
                 sig = SIGILL; code = ILL_ILLOPC;
                 break;
@@ -210,15 +195,6 @@ __kprobes ia64_bad_break (unsigned long break_num, struct pt_regs *regs)
                 sig = SIGILL; code = __ILL_BNDMOD;
                 break;
 
-              case 0x80200:
-              case 0x80300:
-                if (notify_die(DIE_BREAK, "kprobe", regs, break_num, TRAP_BRKPT, SIGTRAP)
-                                == NOTIFY_STOP) {
-                        return;
-                }
-                sig = SIGTRAP; code = TRAP_BRKPT;
-                break;
-
               default:
                 if (break_num < 0x40000 || break_num > 0x100000)
                         die_if_kernel("Bad break", regs, break_num);
@@ -226,6 +202,9 @@ __kprobes ia64_bad_break (unsigned long break_num, struct pt_regs *regs)
                 if (break_num < 0x80000) {
                         sig = SIGILL; code = __ILL_BREAK;
                 } else {
+                        if (notify_die(DIE_BREAK, "bad break", regs, break_num, TRAP_BRKPT, SIGTRAP)
+                                        == NOTIFY_STOP)
+                                return;
                         sig = SIGTRAP; code = TRAP_BRKPT;
                 }
         }
@@ -578,12 +557,11 @@ ia64_fault (unsigned long vector, unsigned long isr, unsigned long ifa,
 #endif
                         break;
                       case 35: siginfo.si_code = TRAP_BRANCH; ifa = 0; break;
-                      case 36:
-                              if (notify_die(DIE_SS, "ss", &regs, vector,
-                                             vector, SIGTRAP) == NOTIFY_STOP)
-                                      return;
-                              siginfo.si_code = TRAP_TRACE; ifa = 0; break;
+                      case 36: siginfo.si_code = TRAP_TRACE; ifa = 0; break;
                 }
+                if (notify_die(DIE_FAULT, "ia64_fault", &regs, vector, siginfo.si_code, SIGTRAP)
+                                == NOTIFY_STOP)
+                        return;
                 siginfo.si_signo = SIGTRAP;
                 siginfo.si_errno = 0;
                 siginfo.si_addr  = (void __user *) ifa;
diff --git a/arch/ia64/kernel/uncached.c b/arch/ia64/kernel/uncached.c
index 4e9d06c48a8b..c6d40446c2c4 100644
--- a/arch/ia64/kernel/uncached.c
+++ b/arch/ia64/kernel/uncached.c
@@ -205,23 +205,18 @@ EXPORT_SYMBOL(uncached_free_page);
 static int __init
 uncached_build_memmap(unsigned long start, unsigned long end, void *arg)
 {
-        long length;
-        unsigned long vstart, vend;
+        long length = end - start;
         int node;
 
-        length = end - start;
-        vstart = start + __IA64_UNCACHED_OFFSET;
-        vend = end + __IA64_UNCACHED_OFFSET;
-
         dprintk(KERN_ERR "uncached_build_memmap(%lx %lx)\n", start, end);
 
-        memset((char *)vstart, 0, length);
+        memset((char *)start, 0, length);
 
-        node = paddr_to_nid(start);
+        node = paddr_to_nid(start - __IA64_UNCACHED_OFFSET);
 
-        for (; vstart < vend ; vstart += PAGE_SIZE) {
-                dprintk(KERN_INFO "sticking %lx into the pool!\n", vstart);
-                gen_pool_free(uncached_pool[node], vstart, PAGE_SIZE);
+        for (; start < end ; start += PAGE_SIZE) {
+                dprintk(KERN_INFO "sticking %lx into the pool!\n", start);
+                gen_pool_free(uncached_pool[node], start, PAGE_SIZE);
         }
 
         return 0;