12 files changed, 88 insertions, 109 deletions

diff --git a/arch/ia64/Kconfig b/arch/ia64/Kconfig
index 9ed69e79dd1d..0b7f701d5cf7 100644
--- a/arch/ia64/Kconfig
+++ b/arch/ia64/Kconfig
@@ -66,15 +66,6 @@ config IA64_UNCACHED_ALLOCATOR
         bool
         select GENERIC_ALLOCATOR
 
-config DMA_IS_DMA32
-        bool
-        default y
-
-config DMA_IS_NORMAL
-        bool
-        depends on IA64_SGI_SN2
-        default y
-
 config AUDIT_ARCH
         bool
         default y
@@ -365,6 +356,9 @@ config NODES_SHIFT
           MAX_NUMNODES will be 2^(This value).
           If in doubt, use the default.
 
+config ARCH_POPULATES_NODE_MAP
+        def_bool y
+
 # VIRTUAL_MEM_MAP and FLAT_NODE_MEM_MAP are functionally equivalent.
 # VIRTUAL_MEM_MAP has been retained for historical reasons.
 config VIRTUAL_MEM_MAP
diff --git a/arch/ia64/ia32/sys_ia32.c b/arch/ia64/ia32/sys_ia32.c
index 6aa3c51619ca..bddbd22706ed 100644
--- a/arch/ia64/ia32/sys_ia32.c
+++ b/arch/ia64/ia32/sys_ia32.c
@@ -1942,7 +1942,7 @@ struct sysctl32 {
         unsigned int    __unused[4];
 };
 
-#ifdef CONFIG_SYSCTL
+#ifdef CONFIG_SYSCTL_SYSCALL
 asmlinkage long
 sys32_sysctl (struct sysctl32 __user *args)
 {
diff --git a/arch/ia64/kernel/acpi.c b/arch/ia64/kernel/acpi.c
index 0176556aeecc..32c3abededc6 100644
--- a/arch/ia64/kernel/acpi.c
+++ b/arch/ia64/kernel/acpi.c
@@ -771,16 +771,19 @@ int acpi_map_cpu2node(acpi_handle handle, int cpu, long physid)
 {
 #ifdef CONFIG_ACPI_NUMA
         int pxm_id;
+        int nid;
 
         pxm_id = acpi_get_pxm(handle);
-
         /*
-         * Assuming that the container driver would have set the proximity
-         * domain and would have initialized pxm_to_node(pxm_id) && pxm_flag
+         * We don't have cpu-only-node hotadd. But if the system equips
+         * SRAT table, pxm is already found and node is ready.
+         * So, just pxm_to_nid(pxm) is OK.
+         * This code here is for the system which doesn't have full SRAT
+         * table for possible cpus.
          */
-        node_cpuid[cpu].nid = (pxm_id < 0) ? 0 : pxm_to_node(pxm_id);
-
+        nid = acpi_map_pxm_to_node(pxm_id);
         node_cpuid[cpu].phys_id = physid;
+        node_cpuid[cpu].nid = nid;
 #endif
         return (0);
 }
diff --git a/arch/ia64/kernel/numa.c b/arch/ia64/kernel/numa.c
index 1cc360c83e7a..20340631179f 100644
--- a/arch/ia64/kernel/numa.c
+++ b/arch/ia64/kernel/numa.c
@@ -29,6 +29,36 @@ EXPORT_SYMBOL(cpu_to_node_map);
 
 cpumask_t node_to_cpu_mask[MAX_NUMNODES] __cacheline_aligned;
 
+void __cpuinit map_cpu_to_node(int cpu, int nid)
+{
+        int oldnid;
+        if (nid < 0) { /* just initialize by zero */
+                cpu_to_node_map[cpu] = 0;
+                return;
+        }
+        /* sanity check first */
+        oldnid = cpu_to_node_map[cpu];
+        if (cpu_isset(cpu, node_to_cpu_mask[oldnid])) {
+                return; /* nothing to do */
+        }
+        /* we don't have cpu-driven node hot add yet...
+           In usual case, node is created from SRAT at boot time. */
+        if (!node_online(nid))
+                nid = first_online_node;
+        cpu_to_node_map[cpu] = nid;
+        cpu_set(cpu, node_to_cpu_mask[nid]);
+        return;
+}
+
+void __cpuinit unmap_cpu_from_node(int cpu, int nid)
+{
+        WARN_ON(!cpu_isset(cpu, node_to_cpu_mask[nid]));
+        WARN_ON(cpu_to_node_map[cpu] != nid);
+        cpu_to_node_map[cpu] = 0;
+        cpu_clear(cpu, node_to_cpu_mask[nid]);
+}
+
+
 /**
  * build_cpu_to_node_map - setup cpu to node and node to cpumask arrays
  *
@@ -49,8 +79,6 @@ void __init build_cpu_to_node_map(void)
                                 node = node_cpuid[i].nid;
                                 break;
                         }
-                cpu_to_node_map[cpu] = (node >= 0) ? node : 0;
-                if (node >= 0)
-                        cpu_set(cpu, node_to_cpu_mask[node]);
+                map_cpu_to_node(cpu, node);
         }
 }
diff --git a/arch/ia64/kernel/perfmon.c b/arch/ia64/kernel/perfmon.c
index 45000d5d0cfa..281004ff7b00 100644
--- a/arch/ia64/kernel/perfmon.c
+++ b/arch/ia64/kernel/perfmon.c
@@ -34,6 +34,7 @@
 #include <linux/file.h>
 #include <linux/poll.h>
 #include <linux/vfs.h>
+#include <linux/smp.h>
 #include <linux/pagemap.h>
 #include <linux/mount.h>
 #include <linux/bitops.h>
diff --git a/arch/ia64/kernel/topology.c b/arch/ia64/kernel/topology.c
index f648c610b10c..5629b45e89c6 100644
--- a/arch/ia64/kernel/topology.c
+++ b/arch/ia64/kernel/topology.c
@@ -36,6 +36,7 @@ int arch_register_cpu(int num)
          */
         if (!can_cpei_retarget() && is_cpu_cpei_target(num))
                 sysfs_cpus[num].cpu.no_control = 1;
+        map_cpu_to_node(num, node_cpuid[num].nid);
 #endif
 
         return register_cpu(&sysfs_cpus[num].cpu, num);
@@ -45,7 +46,8 @@ int arch_register_cpu(int num)
 
 void arch_unregister_cpu(int num)
 {
-        return unregister_cpu(&sysfs_cpus[num].cpu);
+        unregister_cpu(&sysfs_cpus[num].cpu);
+        unmap_cpu_from_node(num, cpu_to_node(num));
 }
 EXPORT_SYMBOL(arch_register_cpu);
 EXPORT_SYMBOL(arch_unregister_cpu);
diff --git a/arch/ia64/kernel/uncached.c b/arch/ia64/kernel/uncached.c
index 4c73a6763669..c58e933694d5 100644
--- a/arch/ia64/kernel/uncached.c
+++ b/arch/ia64/kernel/uncached.c
@@ -98,7 +98,7 @@ static int uncached_add_chunk(struct uncached_pool *uc_pool, int nid)
 
         /* attempt to allocate a granule's worth of cached memory pages */
 
-        page = alloc_pages_node(nid, GFP_KERNEL | __GFP_ZERO,
+        page = alloc_pages_node(nid, GFP_KERNEL | __GFP_ZERO | GFP_THISNODE,
                                 IA64_GRANULE_SHIFT-PAGE_SHIFT);
         if (!page) {
                 mutex_unlock(&uc_pool->add_chunk_mutex);
diff --git a/arch/ia64/mm/contig.c b/arch/ia64/mm/contig.c
index 537c2f3833ee..daf977ff2920 100644
--- a/arch/ia64/mm/contig.c
+++ b/arch/ia64/mm/contig.c
@@ -26,7 +26,6 @@
 #include <asm/mca.h>
 
 #ifdef CONFIG_VIRTUAL_MEM_MAP
-static unsigned long num_dma_physpages;
 static unsigned long max_gap;
 #endif
 
@@ -219,18 +218,6 @@ count_pages (u64 start, u64 end, void *arg)
         return 0;
 }
 
-#ifdef CONFIG_VIRTUAL_MEM_MAP
-static int
-count_dma_pages (u64 start, u64 end, void *arg)
-{
-        unsigned long *count = arg;
-
-        if (start < MAX_DMA_ADDRESS)
-                *count += (min(end, MAX_DMA_ADDRESS) - start) >> PAGE_SHIFT;
-        return 0;
-}
-#endif
-
 /*
  * Set up the page tables.
  */
@@ -239,45 +226,22 @@ void __init
 paging_init (void)
 {
         unsigned long max_dma;
-        unsigned long zones_size[MAX_NR_ZONES];
-#ifdef CONFIG_VIRTUAL_MEM_MAP
-        unsigned long zholes_size[MAX_NR_ZONES];
-#endif
-
-        /* initialize mem_map[] */
-
-        memset(zones_size, 0, sizeof(zones_size));
+        unsigned long nid = 0;
+        unsigned long max_zone_pfns[MAX_NR_ZONES];
 
         num_physpages = 0;
         efi_memmap_walk(count_pages, &num_physpages);
 
         max_dma = virt_to_phys((void *) MAX_DMA_ADDRESS) >> PAGE_SHIFT;
+        max_zone_pfns[ZONE_DMA] = max_dma;
+        max_zone_pfns[ZONE_NORMAL] = max_low_pfn;
 
 #ifdef CONFIG_VIRTUAL_MEM_MAP
-        memset(zholes_size, 0, sizeof(zholes_size));
-
-        num_dma_physpages = 0;
-        efi_memmap_walk(count_dma_pages, &num_dma_physpages);
-
-        if (max_low_pfn < max_dma) {
-                zones_size[ZONE_DMA] = max_low_pfn;
-                zholes_size[ZONE_DMA] = max_low_pfn - num_dma_physpages;
-        } else {
-                zones_size[ZONE_DMA] = max_dma;
-                zholes_size[ZONE_DMA] = max_dma - num_dma_physpages;
-                if (num_physpages > num_dma_physpages) {
-                        zones_size[ZONE_NORMAL] = max_low_pfn - max_dma;
-                        zholes_size[ZONE_NORMAL] =
-                                ((max_low_pfn - max_dma) -
-                                 (num_physpages - num_dma_physpages));
-                }
-        }
-
+        efi_memmap_walk(register_active_ranges, &nid);
         efi_memmap_walk(find_largest_hole, (u64 *)&max_gap);
         if (max_gap < LARGE_GAP) {
                 vmem_map = (struct page *) 0;
-                free_area_init_node(0, NODE_DATA(0), zones_size, 0,
-                                    zholes_size);
+                free_area_init_nodes(max_zone_pfns);
         } else {
                 unsigned long map_size;
 
@@ -289,20 +253,19 @@ paging_init (void)
                 vmem_map = (struct page *) vmalloc_end;
                 efi_memmap_walk(create_mem_map_page_table, NULL);
 
-                NODE_DATA(0)->node_mem_map = vmem_map;
-                free_area_init_node(0, NODE_DATA(0), zones_size,
-                                    0, zholes_size);
+                /*
+                 * alloc_node_mem_map makes an adjustment for mem_map
+                 * which isn't compatible with vmem_map.
+                 */
+                NODE_DATA(0)->node_mem_map = vmem_map +
+                        find_min_pfn_with_active_regions();
+                free_area_init_nodes(max_zone_pfns);
 
                 printk("Virtual mem_map starts at 0x%p\n", mem_map);
         }
 #else /* !CONFIG_VIRTUAL_MEM_MAP */
-        if (max_low_pfn < max_dma)
-                zones_size[ZONE_DMA] = max_low_pfn;
-        else {
-                zones_size[ZONE_DMA] = max_dma;
-                zones_size[ZONE_NORMAL] = max_low_pfn - max_dma;
-        }
-        free_area_init(zones_size);
+        add_active_range(0, 0, max_low_pfn);
+        free_area_init_nodes(max_zone_pfns);
 #endif /* !CONFIG_VIRTUAL_MEM_MAP */
         zero_page_memmap_ptr = virt_to_page(ia64_imva(empty_zero_page));
 }
diff --git a/arch/ia64/mm/discontig.c b/arch/ia64/mm/discontig.c
index 6ea279766334..d497b6b0f5b2 100644
--- a/arch/ia64/mm/discontig.c
+++ b/arch/ia64/mm/discontig.c
@@ -654,6 +654,7 @@ static __init int count_node_pages(unsigned long start, unsigned long len, int n
 {
         unsigned long end = start + len;
 
+        add_active_range(node, start >> PAGE_SHIFT, end >> PAGE_SHIFT);
         mem_data[node].num_physpages += len >> PAGE_SHIFT;
         if (start <= __pa(MAX_DMA_ADDRESS))
                 mem_data[node].num_dma_physpages +=
@@ -678,10 +679,10 @@ static __init int count_node_pages(unsigned long start, unsigned long len, int n
 void __init paging_init(void)
 {
         unsigned long max_dma;
-        unsigned long zones_size[MAX_NR_ZONES];
-        unsigned long zholes_size[MAX_NR_ZONES];
         unsigned long pfn_offset = 0;
+        unsigned long max_pfn = 0;
         int node;
+        unsigned long max_zone_pfns[MAX_NR_ZONES];
 
         max_dma = virt_to_phys((void *) MAX_DMA_ADDRESS) >> PAGE_SHIFT;
 
@@ -698,47 +699,20 @@ void __init paging_init(void)
 #endif
 
         for_each_online_node(node) {
-                memset(zones_size, 0, sizeof(zones_size));
-                memset(zholes_size, 0, sizeof(zholes_size));
-
                 num_physpages += mem_data[node].num_physpages;
-
-                if (mem_data[node].min_pfn >= max_dma) {
-                        /* All of this node's memory is above ZONE_DMA */
-                        zones_size[ZONE_NORMAL] = mem_data[node].max_pfn -
-                                mem_data[node].min_pfn;
-                        zholes_size[ZONE_NORMAL] = mem_data[node].max_pfn -
-                                mem_data[node].min_pfn -
-                                mem_data[node].num_physpages;
-                } else if (mem_data[node].max_pfn < max_dma) {
-                        /* All of this node's memory is in ZONE_DMA */
-                        zones_size[ZONE_DMA] = mem_data[node].max_pfn -
-                                mem_data[node].min_pfn;
-                        zholes_size[ZONE_DMA] = mem_data[node].max_pfn -
-                                mem_data[node].min_pfn -
-                                mem_data[node].num_dma_physpages;
-                } else {
-                        /* This node has memory in both zones */
-                        zones_size[ZONE_DMA] = max_dma -
-                                mem_data[node].min_pfn;
-                        zholes_size[ZONE_DMA] = zones_size[ZONE_DMA] -
-                                mem_data[node].num_dma_physpages;
-                        zones_size[ZONE_NORMAL] = mem_data[node].max_pfn -
-                                max_dma;
-                        zholes_size[ZONE_NORMAL] = zones_size[ZONE_NORMAL] -
-                                (mem_data[node].num_physpages -
-                                 mem_data[node].num_dma_physpages);
-                }
-
                 pfn_offset = mem_data[node].min_pfn;
 
 #ifdef CONFIG_VIRTUAL_MEM_MAP
                 NODE_DATA(node)->node_mem_map = vmem_map + pfn_offset;
 #endif
-                free_area_init_node(node, NODE_DATA(node), zones_size,
-                                    pfn_offset, zholes_size);
+                if (mem_data[node].max_pfn > max_pfn)
+                        max_pfn = mem_data[node].max_pfn;
         }
 
+        max_zone_pfns[ZONE_DMA] = max_dma;
+        max_zone_pfns[ZONE_NORMAL] = max_pfn;
+        free_area_init_nodes(max_zone_pfns);
+
         zero_page_memmap_ptr = virt_to_page(ia64_imva(empty_zero_page));
 }
 
diff --git a/arch/ia64/mm/init.c b/arch/ia64/mm/init.c
index 30617ccb4f7e..ff87a5cba399 100644
--- a/arch/ia64/mm/init.c
+++ b/arch/ia64/mm/init.c
@@ -593,6 +593,18 @@ find_largest_hole (u64 start, u64 end, void *arg)
         last_end = end;
         return 0;
 }
+
+int __init
+register_active_ranges(u64 start, u64 end, void *nid)
+{
+        BUG_ON(nid == NULL);
+        BUG_ON(*(unsigned long *)nid >= MAX_NUMNODES);
+
+        add_active_range(*(unsigned long *)nid,
+                                __pa(start) >> PAGE_SHIFT,
+                                __pa(end) >> PAGE_SHIFT);
+        return 0;
+}
 #endif /* CONFIG_VIRTUAL_MEM_MAP */
 
 static int __init
diff --git a/arch/ia64/pci/pci.c b/arch/ia64/pci/pci.c
index 60b45e79f080..15c7c670da39 100644
--- a/arch/ia64/pci/pci.c
+++ b/arch/ia64/pci/pci.c
@@ -562,7 +562,8 @@ pcibios_enable_device (struct pci_dev *dev, int mask)
 void
 pcibios_disable_device (struct pci_dev *dev)
 {
-        acpi_pci_irq_disable(dev);
+        if (dev->is_enabled)
+                acpi_pci_irq_disable(dev);
 }
 
 void
diff --git a/arch/ia64/sn/kernel/sn2/sn_hwperf.c b/arch/ia64/sn/kernel/sn2/sn_hwperf.c
index 9a8a29339d2d..b632b9c1e3b3 100644
--- a/arch/ia64/sn/kernel/sn2/sn_hwperf.c
+++ b/arch/ia64/sn/kernel/sn2/sn_hwperf.c
@@ -32,9 +32,10 @@
 #include <linux/cpumask.h>
 #include <linux/smp_lock.h>
 #include <linux/nodemask.h>
+#include <linux/smp.h>
+
 #include <asm/processor.h>
 #include <asm/topology.h>
-#include <asm/smp.h>
 #include <asm/semaphore.h>
 #include <asm/uaccess.h>
 #include <asm/sal.h>