3 files changed, 126 insertions, 101 deletions

diff --git a/arch/ia64/mm/contig.c b/arch/ia64/mm/contig.c
index 1e79551231b9..44ce5ed9444c 100644
--- a/arch/ia64/mm/contig.c
+++ b/arch/ia64/mm/contig.c
@@ -30,71 +30,73 @@ static unsigned long max_gap;
 #endif
 
 /**
- * show_mem - display a memory statistics summary
+ * show_mem - give short summary of memory stats
  *
- * Just walks the pages in the system and describes where they're allocated.
+ * Shows a simple page count of reserved and used pages in the system.
+ * For discontig machines, it does this on a per-pgdat basis.
  */
-void
-show_mem (void)
+void show_mem(void)
 {
-        int i, total = 0, reserved = 0;
-        int shared = 0, cached = 0;
+        int i, total_reserved = 0;
+        int total_shared = 0, total_cached = 0;
+        unsigned long total_present = 0;
+        pg_data_t *pgdat;
 
         printk(KERN_INFO "Mem-info:\n");
         show_free_areas();
-
         printk(KERN_INFO "Free swap:       %6ldkB\n",
                nr_swap_pages<<(PAGE_SHIFT-10));
-        i = max_mapnr;
-        for (i = 0; i < max_mapnr; i++) {
-                if (!pfn_valid(i)) {
+        printk(KERN_INFO "Node memory in pages:\n");
+        for_each_online_pgdat(pgdat) {
+                unsigned long present;
+                unsigned long flags;
+                int shared = 0, cached = 0, reserved = 0;
+
+                pgdat_resize_lock(pgdat, &flags);
+                present = pgdat->node_present_pages;
+                for(i = 0; i < pgdat->node_spanned_pages; i++) {
+                        struct page *page;
+                        if (pfn_valid(pgdat->node_start_pfn + i))
+                                page = pfn_to_page(pgdat->node_start_pfn + i);
+                        else {
 #ifdef CONFIG_VIRTUAL_MEM_MAP
-                        if (max_gap < LARGE_GAP)
-                                continue;
-                        i = vmemmap_find_next_valid_pfn(0, i) - 1;
+                                if (max_gap < LARGE_GAP)
+                                        continue;
 #endif
-                        continue;
+                                i = vmemmap_find_next_valid_pfn(pgdat->node_id,
+                                         i) - 1;
+                                continue;
+                        }
+                        if (PageReserved(page))
+                                reserved++;
+                        else if (PageSwapCache(page))
+                                cached++;
+                        else if (page_count(page))
+                                shared += page_count(page)-1;
                 }
-                total++;
-                if (PageReserved(mem_map+i))
-                        reserved++;
-                else if (PageSwapCache(mem_map+i))
-                        cached++;
-                else if (page_count(mem_map + i))
-                        shared += page_count(mem_map + i) - 1;
+                pgdat_resize_unlock(pgdat, &flags);
+                total_present += present;
+                total_reserved += reserved;
+                total_cached += cached;
+                total_shared += shared;
+                printk(KERN_INFO "Node %4d:  RAM: %11ld, rsvd: %8d, "
+                       "shrd: %10d, swpd: %10d\n", pgdat->node_id,
+                       present, reserved, shared, cached);
         }
-        printk(KERN_INFO "%d pages of RAM\n", total);
-        printk(KERN_INFO "%d reserved pages\n", reserved);
-        printk(KERN_INFO "%d pages shared\n", shared);
-        printk(KERN_INFO "%d pages swap cached\n", cached);
-        printk(KERN_INFO "%ld pages in page table cache\n",
+        printk(KERN_INFO "%ld pages of RAM\n", total_present);
+        printk(KERN_INFO "%d reserved pages\n", total_reserved);
+        printk(KERN_INFO "%d pages shared\n", total_shared);
+        printk(KERN_INFO "%d pages swap cached\n", total_cached);
+        printk(KERN_INFO "Total of %ld pages in page table cache\n",
                pgtable_quicklist_total_size());
+        printk(KERN_INFO "%d free buffer pages\n", nr_free_buffer_pages());
 }
 
+
 /* physical address where the bootmem map is located */
 unsigned long bootmap_start;
 
 /**
- * find_max_pfn - adjust the maximum page number callback
- * @start: start of range
- * @end: end of range
- * @arg: address of pointer to global max_pfn variable
- *
- * Passed as a callback function to efi_memmap_walk() to determine the highest
- * available page frame number in the system.
- */
-int
-find_max_pfn (unsigned long start, unsigned long end, void *arg)
-{
-        unsigned long *max_pfnp = arg, pfn;
-
-        pfn = (PAGE_ALIGN(end - 1) - PAGE_OFFSET) >> PAGE_SHIFT;
-        if (pfn > *max_pfnp)
-                *max_pfnp = pfn;
-        return 0;
-}
-
-/**
  * find_bootmap_location - callback to find a memory area for the bootmap
  * @start: start of region
  * @end: end of region
@@ -155,9 +157,10 @@ find_memory (void)
         reserve_memory();
 
         /* first find highest page frame number */
-        max_pfn = 0;
-        efi_memmap_walk(find_max_pfn, &max_pfn);
-
+        min_low_pfn = ~0UL;
+        max_low_pfn = 0;
+        efi_memmap_walk(find_max_min_low_pfn, NULL);
+        max_pfn = max_low_pfn;
         /* how many bytes to cover all the pages */
         bootmap_size = bootmem_bootmap_pages(max_pfn) << PAGE_SHIFT;
 
@@ -167,7 +170,8 @@ find_memory (void)
         if (bootmap_start == ~0UL)
                 panic("Cannot find %ld bytes for bootmap\n", bootmap_size);
 
-        bootmap_size = init_bootmem(bootmap_start >> PAGE_SHIFT, max_pfn);
+        bootmap_size = init_bootmem_node(NODE_DATA(0),
+                        (bootmap_start >> PAGE_SHIFT), 0, max_pfn);
 
         /* Free all available memory, then mark bootmem-map as being in use. */
         efi_memmap_walk(filter_rsvd_memory, free_bootmem);
@@ -175,11 +179,6 @@ find_memory (void)
 
         find_initrd();
 
-#ifdef CONFIG_CRASH_DUMP
-        /* If we are doing a crash dump, we still need to know the real mem
-         * size before original memory map is * reset. */
-        saved_max_pfn = max_pfn;
-#endif
 }
 
 #ifdef CONFIG_SMP
@@ -237,9 +236,11 @@ paging_init (void)
         num_physpages = 0;
         efi_memmap_walk(count_pages, &num_physpages);
 
-        max_dma = virt_to_phys((void *) MAX_DMA_ADDRESS) >> PAGE_SHIFT;
         memset(max_zone_pfns, 0, sizeof(max_zone_pfns));
+#ifdef CONFIG_ZONE_DMA
+        max_dma = virt_to_phys((void *) MAX_DMA_ADDRESS) >> PAGE_SHIFT;
         max_zone_pfns[ZONE_DMA] = max_dma;
+#endif
         max_zone_pfns[ZONE_NORMAL] = max_low_pfn;
 
 #ifdef CONFIG_VIRTUAL_MEM_MAP
diff --git a/arch/ia64/mm/discontig.c b/arch/ia64/mm/discontig.c
index 96722cb1b49d..872da7a2accd 100644
--- a/arch/ia64/mm/discontig.c
+++ b/arch/ia64/mm/discontig.c
@@ -37,7 +37,9 @@ struct early_node_data {
         unsigned long pernode_size;
         struct bootmem_data bootmem_data;
         unsigned long num_physpages;
+#ifdef CONFIG_ZONE_DMA
         unsigned long num_dma_physpages;
+#endif
         unsigned long min_pfn;
         unsigned long max_pfn;
 };
@@ -86,9 +88,6 @@ static int __init build_node_maps(unsigned long start, unsigned long len,
                 bdp->node_low_pfn = max(epfn, bdp->node_low_pfn);
         }
 
-        min_low_pfn = min(min_low_pfn, bdp->node_boot_start>>PAGE_SHIFT);
-        max_low_pfn = max(max_low_pfn, bdp->node_low_pfn);
-
         return 0;
 }
 
@@ -412,37 +411,6 @@ static void __init memory_less_nodes(void)
         return;
 }
 
-#ifdef CONFIG_SPARSEMEM
-/**
- * register_sparse_mem - notify SPARSEMEM that this memory range exists.
- * @start: physical start of range
- * @end: physical end of range
- * @arg: unused
- *
- * Simply calls SPARSEMEM to register memory section(s).
- */
-static int __init register_sparse_mem(unsigned long start, unsigned long end,
-        void *arg)
-{
-        int nid;
-
-        start = __pa(start) >> PAGE_SHIFT;
-        end = __pa(end) >> PAGE_SHIFT;
-        nid = early_pfn_to_nid(start);
-        memory_present(nid, start, end);
-
-        return 0;
-}
-
-static void __init arch_sparse_init(void)
-{
-        efi_memmap_walk(register_sparse_mem, NULL);
-        sparse_init();
-}
-#else
-#define arch_sparse_init() do {} while (0)
-#endif
-
 /**
  * find_memory - walk the EFI memory map and setup the bootmem allocator
  *
@@ -467,12 +435,16 @@ void __init find_memory(void)
         /* These actually end up getting called by call_pernode_memory() */
         efi_memmap_walk(filter_rsvd_memory, build_node_maps);
         efi_memmap_walk(filter_rsvd_memory, find_pernode_space);
+        efi_memmap_walk(find_max_min_low_pfn, NULL);
 
         for_each_online_node(node)
                 if (mem_data[node].bootmem_data.node_low_pfn) {
                         node_clear(node, memory_less_mask);
                         mem_data[node].min_pfn = ~0UL;
                 }
+
+        efi_memmap_walk(register_active_ranges, NULL);
+
         /*
          * Initialize the boot memory maps in reverse order since that's
          * what the bootmem allocator expects
@@ -654,11 +626,12 @@ 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;
+#ifdef CONFIG_ZONE_DMA
         if (start <= __pa(MAX_DMA_ADDRESS))
                 mem_data[node].num_dma_physpages +=
                         (min(end, __pa(MAX_DMA_ADDRESS)) - start) >>PAGE_SHIFT;
+#endif
         start = GRANULEROUNDDOWN(start);
         start = ORDERROUNDDOWN(start);
         end = GRANULEROUNDUP(end);
@@ -686,10 +659,11 @@ void __init paging_init(void)
 
         max_dma = virt_to_phys((void *) MAX_DMA_ADDRESS) >> PAGE_SHIFT;
 
-        arch_sparse_init();
-
         efi_memmap_walk(filter_rsvd_memory, count_node_pages);
 
+        sparse_memory_present_with_active_regions(MAX_NUMNODES);
+        sparse_init();
+
 #ifdef CONFIG_VIRTUAL_MEM_MAP
         vmalloc_end -= PAGE_ALIGN(ALIGN(max_low_pfn, MAX_ORDER_NR_PAGES) *
                 sizeof(struct page));
@@ -710,7 +684,9 @@ void __init paging_init(void)
         }
 
         memset(max_zone_pfns, 0, sizeof(max_zone_pfns));
+#ifdef CONFIG_ZONE_DMA
         max_zone_pfns[ZONE_DMA] = max_dma;
+#endif
         max_zone_pfns[ZONE_NORMAL] = max_pfn;
         free_area_init_nodes(max_zone_pfns);
 
diff --git a/arch/ia64/mm/init.c b/arch/ia64/mm/init.c
index 07d82cd7cbdd..5b70241741b4 100644
--- a/arch/ia64/mm/init.c
+++ b/arch/ia64/mm/init.c
@@ -19,6 +19,7 @@
 #include <linux/swap.h>
 #include <linux/proc_fs.h>
 #include <linux/bitops.h>
+#include <linux/kexec.h>
 
 #include <asm/a.out.h>
 #include <asm/dma.h>
@@ -67,7 +68,7 @@ max_pgt_pages(void)
 #ifndef CONFIG_NUMA
         node_free_pages = nr_free_pages();
 #else
-        node_free_pages = nr_free_pages_pgdat(NODE_DATA(numa_node_id()));
+        node_free_pages = node_page_state(numa_node_id(), NR_FREE_PAGES);
 #endif
         max_pgt_pages = node_free_pages / PGT_FRACTION_OF_NODE_MEM;
         max_pgt_pages = max(max_pgt_pages, MIN_PGT_PAGES);
@@ -128,6 +129,25 @@ lazy_mmu_prot_update (pte_t pte)
         set_bit(PG_arch_1, &page->flags);       /* mark page as clean */
 }
 
+/*
+ * Since DMA is i-cache coherent, any (complete) pages that were written via
+ * DMA can be marked as "clean" so that lazy_mmu_prot_update() doesn't have to
+ * flush them when they get mapped into an executable vm-area.
+ */
+void
+dma_mark_clean(void *addr, size_t size)
+{
+        unsigned long pg_addr, end;
+
+        pg_addr = PAGE_ALIGN((unsigned long) addr);
+        end = (unsigned long) addr + size;
+        while (pg_addr + PAGE_SIZE <= end) {
+                struct page *page = virt_to_page(pg_addr);
+                set_bit(PG_arch_1, &page->flags);
+                pg_addr += PAGE_SIZE;
+        }
+}
+
 inline void
 ia64_set_rbs_bot (void)
 {
@@ -135,7 +155,7 @@ ia64_set_rbs_bot (void)
 
         if (stack_size > MAX_USER_STACK_SIZE)
                 stack_size = MAX_USER_STACK_SIZE;
-        current->thread.rbs_bot = STACK_TOP - stack_size;
+        current->thread.rbs_bot = PAGE_ALIGN(current->mm->start_stack - stack_size);
 }
 
 /*
@@ -156,9 +176,8 @@ ia64_init_addr_space (void)
          * the problem.  When the process attempts to write to the register backing store
          * for the first time, it will get a SEGFAULT in this case.
          */
-        vma = kmem_cache_alloc(vm_area_cachep, GFP_KERNEL);
+        vma = kmem_cache_zalloc(vm_area_cachep, GFP_KERNEL);
         if (vma) {
-                memset(vma, 0, sizeof(*vma));
                 vma->vm_mm = current->mm;
                 vma->vm_start = current->thread.rbs_bot & PAGE_MASK;
                 vma->vm_end = vma->vm_start + PAGE_SIZE;
@@ -175,9 +194,8 @@ ia64_init_addr_space (void)
 
         /* map NaT-page at address zero to speed up speculative dereferencing of NULL: */
         if (!(current->personality & MMAP_PAGE_ZERO)) {
-                vma = kmem_cache_alloc(vm_area_cachep, GFP_KERNEL);
+                vma = kmem_cache_zalloc(vm_area_cachep, GFP_KERNEL);
                 if (vma) {
-                        memset(vma, 0, sizeof(*vma));
                         vma->vm_mm = current->mm;
                         vma->vm_end = PAGE_SIZE;
                         vma->vm_page_prot = __pgprot(pgprot_val(PAGE_READONLY) | _PAGE_MA_NAT);
@@ -586,13 +604,27 @@ find_largest_hole (u64 start, u64 end, void *arg)
         return 0;
 }
 
+#endif /* CONFIG_VIRTUAL_MEM_MAP */
+
 int __init
 register_active_ranges(u64 start, u64 end, void *arg)
 {
-        add_active_range(0, __pa(start) >> PAGE_SHIFT, __pa(end) >> PAGE_SHIFT);
+        int nid = paddr_to_nid(__pa(start));
+
+        if (nid < 0)
+                nid = 0;
+#ifdef CONFIG_KEXEC
+        if (start > crashk_res.start && start < crashk_res.end)
+                start = crashk_res.end;
+        if (end > crashk_res.start && end < crashk_res.end)
+                end = crashk_res.start;
+#endif
+
+        if (start < end)
+                add_active_range(nid, __pa(start) >> PAGE_SHIFT,
+                        __pa(end) >> PAGE_SHIFT);
         return 0;
 }
-#endif /* CONFIG_VIRTUAL_MEM_MAP */
 
 static int __init
 count_reserved_pages (u64 start, u64 end, void *arg)
@@ -607,6 +639,22 @@ count_reserved_pages (u64 start, u64 end, void *arg)
         return 0;
 }
 
+int
+find_max_min_low_pfn (unsigned long start, unsigned long end, void *arg)
+{
+        unsigned long pfn_start, pfn_end;
+#ifdef CONFIG_FLATMEM
+        pfn_start = (PAGE_ALIGN(__pa(start))) >> PAGE_SHIFT;
+        pfn_end = (PAGE_ALIGN(__pa(end - 1))) >> PAGE_SHIFT;
+#else
+        pfn_start = GRANULEROUNDDOWN(__pa(start)) >> PAGE_SHIFT;
+        pfn_end = GRANULEROUNDUP(__pa(end - 1)) >> PAGE_SHIFT;
+#endif
+        min_low_pfn = min(min_low_pfn, pfn_start);
+        max_low_pfn = max(max_low_pfn, pfn_end);
+        return 0;
+}
+
 /*
  * Boot command-line option "nolwsys" can be used to disable the use of any light-weight
  * system call handler.  When this option is in effect, all fsyscalls will end up bubbling