6 files changed, 306 insertions, 226 deletions

diff --git a/arch/x86_64/mm/fault.c b/arch/x86_64/mm/fault.c
index 6ada7231f3ab..de99dba2c515 100644
--- a/arch/x86_64/mm/fault.c
+++ b/arch/x86_64/mm/fault.c
@@ -585,7 +585,7 @@ do_sigbus:
 }
 
 DEFINE_SPINLOCK(pgd_lock);
-struct page *pgd_list;
+LIST_HEAD(pgd_list);
 
 void vmalloc_sync_all(void)
 {
@@ -605,8 +605,7 @@ void vmalloc_sync_all(void)
                         if (pgd_none(*pgd_ref))
                                 continue;
                         spin_lock(&pgd_lock);
-                        for (page = pgd_list; page;
-                             page = (struct page *)page->index) {
+                        list_for_each_entry(page, &pgd_list, lru) {
                                 pgd_t *pgd;
                                 pgd = (pgd_t *)page_address(page) + pgd_index(address);
                                 if (pgd_none(*pgd))
diff --git a/arch/x86_64/mm/init.c b/arch/x86_64/mm/init.c
index ec31534eb104..282b0a8f00ad 100644
--- a/arch/x86_64/mm/init.c
+++ b/arch/x86_64/mm/init.c
@@ -22,10 +22,12 @@
 #include <linux/bootmem.h>
 #include <linux/proc_fs.h>
 #include <linux/pci.h>
+#include <linux/pfn.h>
 #include <linux/poison.h>
 #include <linux/dma-mapping.h>
 #include <linux/module.h>
 #include <linux/memory_hotplug.h>
+#include <linux/nmi.h>
 
 #include <asm/processor.h>
 #include <asm/system.h>
@@ -46,7 +48,7 @@
 #define Dprintk(x...)
 #endif
 
-struct dma_mapping_ops* dma_ops;
+const struct dma_mapping_ops* dma_ops;
 EXPORT_SYMBOL(dma_ops);
 
 static unsigned long dma_reserve __initdata;
@@ -72,6 +74,11 @@ void show_mem(void)
 
         for_each_online_pgdat(pgdat) {
                for (i = 0; i < pgdat->node_spanned_pages; ++i) {
+                        /* this loop can take a while with 256 GB and 4k pages
+                           so update the NMI watchdog */
+                        if (unlikely(i % MAX_ORDER_NR_PAGES == 0)) {
+                                touch_nmi_watchdog();
+                        }
                         page = pfn_to_page(pgdat->node_start_pfn + i);
                         total++;
                         if (PageReserved(page))
@@ -167,23 +174,9 @@ __set_fixmap (enum fixed_addresses idx, unsigned long phys, pgprot_t prot)
 
 unsigned long __initdata table_start, table_end; 
 
-extern pmd_t temp_boot_pmds[]; 
-
-static  struct temp_map { 
-        pmd_t *pmd;
-        void  *address; 
-        int    allocated; 
-} temp_mappings[] __initdata = { 
-        { &temp_boot_pmds[0], (void *)(40UL * 1024 * 1024) },
-        { &temp_boot_pmds[1], (void *)(42UL * 1024 * 1024) }, 
-        {}
-}; 
-
-static __meminit void *alloc_low_page(int *index, unsigned long *phys)
+static __meminit void *alloc_low_page(unsigned long *phys)
 { 
-        struct temp_map *ti;
-        int i; 
-        unsigned long pfn = table_end++, paddr; 
+        unsigned long pfn = table_end++;
         void *adr;
 
         if (after_bootmem) {
@@ -194,57 +187,63 @@ static __meminit void *alloc_low_page(int *index, unsigned long *phys)
 
         if (pfn >= end_pfn) 
                 panic("alloc_low_page: ran out of memory"); 
-        for (i = 0; temp_mappings[i].allocated; i++) {
-                if (!temp_mappings[i].pmd) 
-                        panic("alloc_low_page: ran out of temp mappings"); 
-        } 
-        ti = &temp_mappings[i];
-        paddr = (pfn << PAGE_SHIFT) & PMD_MASK; 
-        set_pmd(ti->pmd, __pmd(paddr | _KERNPG_TABLE | _PAGE_PSE)); 
-        ti->allocated = 1; 
-        __flush_tlb();         
-        adr = ti->address + ((pfn << PAGE_SHIFT) & ~PMD_MASK); 
+
+        adr = early_ioremap(pfn * PAGE_SIZE, PAGE_SIZE);
         memset(adr, 0, PAGE_SIZE);
-        *index = i; 
-        *phys  = pfn * PAGE_SIZE;  
-        return adr; 
-} 
+        *phys  = pfn * PAGE_SIZE;
+        return adr;
+}
 
-static __meminit void unmap_low_page(int i)
+static __meminit void unmap_low_page(void *adr)
 { 
-        struct temp_map *ti;
 
         if (after_bootmem)
                 return;
 
-        ti = &temp_mappings[i];
-        set_pmd(ti->pmd, __pmd(0));
-        ti->allocated = 0; 
+        early_iounmap(adr, PAGE_SIZE);
 } 
 
 /* Must run before zap_low_mappings */
 __init void *early_ioremap(unsigned long addr, unsigned long size)
 {
-        unsigned long map = round_down(addr, LARGE_PAGE_SIZE); 
-
-        /* actually usually some more */
-        if (size >= LARGE_PAGE_SIZE) { 
-                return NULL;
+        unsigned long vaddr;
+        pmd_t *pmd, *last_pmd;
+        int i, pmds;
+
+        pmds = ((addr & ~PMD_MASK) + size + ~PMD_MASK) / PMD_SIZE;
+        vaddr = __START_KERNEL_map;
+        pmd = level2_kernel_pgt;
+        last_pmd = level2_kernel_pgt + PTRS_PER_PMD - 1;
+        for (; pmd <= last_pmd; pmd++, vaddr += PMD_SIZE) {
+                for (i = 0; i < pmds; i++) {
+                        if (pmd_present(pmd[i]))
+                                goto next;
+                }
+                vaddr += addr & ~PMD_MASK;
+                addr &= PMD_MASK;
+                for (i = 0; i < pmds; i++, addr += PMD_SIZE)
+                        set_pmd(pmd + i,__pmd(addr | _KERNPG_TABLE | _PAGE_PSE));
+                __flush_tlb();
+                return (void *)vaddr;
+        next:
+                ;
         }
-        set_pmd(temp_mappings[0].pmd,  __pmd(map | _KERNPG_TABLE | _PAGE_PSE));
-        map += LARGE_PAGE_SIZE;
-        set_pmd(temp_mappings[1].pmd,  __pmd(map | _KERNPG_TABLE | _PAGE_PSE));
-        __flush_tlb();
-        return temp_mappings[0].address + (addr & (LARGE_PAGE_SIZE-1));
+        printk("early_ioremap(0x%lx, %lu) failed\n", addr, size);
+        return NULL;
 }
 
 /* To avoid virtual aliases later */
 __init void early_iounmap(void *addr, unsigned long size)
 {
-        if ((void *)round_down((unsigned long)addr, LARGE_PAGE_SIZE) != temp_mappings[0].address)
-                printk("early_iounmap: bad address %p\n", addr);
-        set_pmd(temp_mappings[0].pmd, __pmd(0));
-        set_pmd(temp_mappings[1].pmd, __pmd(0));
+        unsigned long vaddr;
+        pmd_t *pmd;
+        int i, pmds;
+
+        vaddr = (unsigned long)addr;
+        pmds = ((vaddr & ~PMD_MASK) + size + ~PMD_MASK) / PMD_SIZE;
+        pmd = level2_kernel_pgt + pmd_index(vaddr);
+        for (i = 0; i < pmds; i++)
+                pmd_clear(pmd + i);
         __flush_tlb();
 }
 
@@ -289,7 +288,6 @@ static void __meminit phys_pud_init(pud_t *pud_page, unsigned long addr, unsigne
 
 
         for (; i < PTRS_PER_PUD; i++, addr = (addr & PUD_MASK) + PUD_SIZE ) {
-                int map; 
                 unsigned long pmd_phys;
                 pud_t *pud = pud_page + pud_index(addr);
                 pmd_t *pmd;
@@ -307,12 +305,12 @@ static void __meminit phys_pud_init(pud_t *pud_page, unsigned long addr, unsigne
                         continue;
                 }
 
-                pmd = alloc_low_page(&map, &pmd_phys);
+                pmd = alloc_low_page(&pmd_phys);
                 spin_lock(&init_mm.page_table_lock);
                 set_pud(pud, __pud(pmd_phys | _KERNPG_TABLE));
                 phys_pmd_init(pmd, addr, end);
                 spin_unlock(&init_mm.page_table_lock);
-                unmap_low_page(map);
+                unmap_low_page(pmd);
         }
         __flush_tlb();
 } 
@@ -364,7 +362,6 @@ void __meminit init_memory_mapping(unsigned long start, unsigned long end)
         end = (unsigned long)__va(end);
 
         for (; start < end; start = next) {
-                int map;
                 unsigned long pud_phys; 
                 pgd_t *pgd = pgd_offset_k(start);
                 pud_t *pud;
@@ -372,7 +369,7 @@ void __meminit init_memory_mapping(unsigned long start, unsigned long end)
                 if (after_bootmem)
                         pud = pud_offset(pgd, start & PGDIR_MASK);
                 else
-                        pud = alloc_low_page(&map, &pud_phys);
+                        pud = alloc_low_page(&pud_phys);
 
                 next = start + PGDIR_SIZE;
                 if (next > end) 
@@ -380,7 +377,7 @@ void __meminit init_memory_mapping(unsigned long start, unsigned long end)
                 phys_pud_init(pud, __pa(start), __pa(next));
                 if (!after_bootmem)
                         set_pgd(pgd_offset_k(start), mk_kernel_pgd(pud_phys));
-                unmap_low_page(map);   
+                unmap_low_page(pud);
         } 
 
         if (!after_bootmem)
@@ -388,21 +385,6 @@ void __meminit init_memory_mapping(unsigned long start, unsigned long end)
         __flush_tlb_all();
 }
 
-void __cpuinit zap_low_mappings(int cpu)
-{
-        if (cpu == 0) {
-                pgd_t *pgd = pgd_offset_k(0UL);
-                pgd_clear(pgd);
-        } else {
-                /*
-                 * For AP's, zap the low identity mappings by changing the cr3
-                 * to init_level4_pgt and doing local flush tlb all
-                 */
-                asm volatile("movq %0,%%cr3" :: "r" (__pa_symbol(&init_level4_pgt)));
-        }
-        __flush_tlb_all();
-}
-
 #ifndef CONFIG_NUMA
 void __init paging_init(void)
 {
@@ -579,15 +561,6 @@ void __init mem_init(void)
                 reservedpages << (PAGE_SHIFT-10),
                 datasize >> 10,
                 initsize >> 10);
-
-#ifdef CONFIG_SMP
-        /*
-         * Sync boot_level4_pgt mappings with the init_level4_pgt
-         * except for the low identity mappings which are already zapped
-         * in init_level4_pgt. This sync-up is essential for AP's bringup
-         */
-        memcpy(boot_level4_pgt+1, init_level4_pgt+1, (PTRS_PER_PGD-1)*sizeof(pgd_t));
-#endif
 }
 
 void free_init_pages(char *what, unsigned long begin, unsigned long end)
@@ -597,37 +570,44 @@ void free_init_pages(char *what, unsigned long begin, unsigned long end)
         if (begin >= end)
                 return;
 
-        printk(KERN_INFO "Freeing %s: %ldk freed\n", what, (end - begin) >> 10);
+        printk(KERN_INFO "Freeing %s: %luk freed\n", what, (end - begin) >> 10);
         for (addr = begin; addr < end; addr += PAGE_SIZE) {
-                ClearPageReserved(virt_to_page(addr));
-                init_page_count(virt_to_page(addr));
-                memset((void *)(addr & ~(PAGE_SIZE-1)),
-                        POISON_FREE_INITMEM, PAGE_SIZE);
-                free_page(addr);
+                struct page *page = pfn_to_page(addr >> PAGE_SHIFT);
+                ClearPageReserved(page);
+                init_page_count(page);
+                memset(page_address(page), POISON_FREE_INITMEM, PAGE_SIZE);
+                if (addr >= __START_KERNEL_map)
+                        change_page_attr_addr(addr, 1, __pgprot(0));
+                __free_page(page);
                 totalram_pages++;
         }
+        if (addr > __START_KERNEL_map)
+                global_flush_tlb();
 }
 
 void free_initmem(void)
 {
-        memset(__initdata_begin, POISON_FREE_INITDATA,
-                __initdata_end - __initdata_begin);
         free_init_pages("unused kernel memory",
-                        (unsigned long)(&__init_begin),
-                        (unsigned long)(&__init_end));
+                        __pa_symbol(&__init_begin),
+                        __pa_symbol(&__init_end));
 }
 
 #ifdef CONFIG_DEBUG_RODATA
 
 void mark_rodata_ro(void)
 {
-        unsigned long addr = (unsigned long)__start_rodata;
+        unsigned long start = PFN_ALIGN(__va(__pa_symbol(&_stext))), size;
 
-        for (; addr < (unsigned long)__end_rodata; addr += PAGE_SIZE)
-                change_page_attr_addr(addr, 1, PAGE_KERNEL_RO);
+#ifdef CONFIG_HOTPLUG_CPU
+        /* It must still be possible to apply SMP alternatives. */
+        if (num_possible_cpus() > 1)
+                start = PFN_ALIGN(__va(__pa_symbol(&_etext)));
+#endif
+        size = (unsigned long)__va(__pa_symbol(&__end_rodata)) - start;
+        change_page_attr_addr(start, size >> PAGE_SHIFT, PAGE_KERNEL_RO);
 
-        printk ("Write protecting the kernel read-only data: %luk\n",
-                        (__end_rodata - __start_rodata) >> 10);
+        printk(KERN_INFO "Write protecting the kernel read-only data: %luk\n",
+               size >> 10);
 
         /*
          * change_page_attr_addr() requires a global_flush_tlb() call after it.
@@ -642,7 +622,7 @@ void mark_rodata_ro(void)
 #ifdef CONFIG_BLK_DEV_INITRD
 void free_initrd_mem(unsigned long start, unsigned long end)
 {
-        free_init_pages("initrd memory", start, end);
+        free_init_pages("initrd memory", __pa(start), __pa(end));
 }
 #endif
 
diff --git a/arch/x86_64/mm/k8topology.c b/arch/x86_64/mm/k8topology.c
index b5b8dba28b4e..f983c75825d0 100644
--- a/arch/x86_64/mm/k8topology.c
+++ b/arch/x86_64/mm/k8topology.c
@@ -49,11 +49,8 @@ int __init k8_scan_nodes(unsigned long start, unsigned long end)
         int found = 0;
         u32 reg;
         unsigned numnodes;
-        nodemask_t nodes_parsed;
         unsigned dualcore = 0;
 
-        nodes_clear(nodes_parsed);
-
         if (!early_pci_allowed())
                 return -1;
 
@@ -65,6 +62,8 @@ int __init k8_scan_nodes(unsigned long start, unsigned long end)
 
         reg = read_pci_config(0, nb, 0, 0x60); 
         numnodes = ((reg >> 4) & 0xF) + 1;
+        if (numnodes <= 1)
+                return -1;
 
         printk(KERN_INFO "Number of nodes %d\n", numnodes);
 
@@ -102,7 +101,7 @@ int __init k8_scan_nodes(unsigned long start, unsigned long end)
                                nodeid, (base>>8)&3, (limit>>8) & 3); 
                         return -1; 
                 }       
-                if (node_isset(nodeid, nodes_parsed)) { 
+                if (node_isset(nodeid, node_possible_map)) {
                         printk(KERN_INFO "Node %d already present. Skipping\n", 
                                nodeid);
                         continue;
@@ -155,7 +154,7 @@ int __init k8_scan_nodes(unsigned long start, unsigned long end)
 
                 prevbase = base;
 
-                node_set(nodeid, nodes_parsed);
+                node_set(nodeid, node_possible_map);
         } 
 
         if (!found)
diff --git a/arch/x86_64/mm/numa.c b/arch/x86_64/mm/numa.c
index 41b8fb069924..51548947ad3b 100644
--- a/arch/x86_64/mm/numa.c
+++ b/arch/x86_64/mm/numa.c
@@ -273,125 +273,213 @@ void __init numa_init_array(void)
 
 #ifdef CONFIG_NUMA_EMU
 /* Numa emulation */
-int numa_fake __initdata = 0;
+#define E820_ADDR_HOLE_SIZE(start, end)                                 \
+        (e820_hole_size((start) >> PAGE_SHIFT, (end) >> PAGE_SHIFT) <<  \
+        PAGE_SHIFT)
+char *cmdline __initdata;
 
 /*
- * This function is used to find out if the start and end correspond to
- * different zones.
+ * Setups up nid to range from addr to addr + size.  If the end boundary is
+ * greater than max_addr, then max_addr is used instead.  The return value is 0
+ * if there is additional memory left for allocation past addr and -1 otherwise.
+ * addr is adjusted to be at the end of the node.
  */
-int zone_cross_over(unsigned long start, unsigned long end)
+static int __init setup_node_range(int nid, struct bootnode *nodes, u64 *addr,
+                                   u64 size, u64 max_addr)
 {
-        if ((start < (MAX_DMA32_PFN << PAGE_SHIFT)) &&
-                        (end >= (MAX_DMA32_PFN << PAGE_SHIFT)))
-                return 1;
-        return 0;
+        int ret = 0;
+        nodes[nid].start = *addr;
+        *addr += size;
+        if (*addr >= max_addr) {
+                *addr = max_addr;
+                ret = -1;
+        }
+        nodes[nid].end = *addr;
+        node_set(nid, node_possible_map);
+        printk(KERN_INFO "Faking node %d at %016Lx-%016Lx (%LuMB)\n", nid,
+               nodes[nid].start, nodes[nid].end,
+               (nodes[nid].end - nodes[nid].start) >> 20);
+        return ret;
 }
 
-static int __init numa_emulation(unsigned long start_pfn, unsigned long end_pfn)
+/*
+ * Splits num_nodes nodes up equally starting at node_start.  The return value
+ * is the number of nodes split up and addr is adjusted to be at the end of the
+ * last node allocated.
+ */
+static int __init split_nodes_equally(struct bootnode *nodes, u64 *addr,
+                                      u64 max_addr, int node_start,
+                                      int num_nodes)
 {
-        int i, big;
-        struct bootnode nodes[MAX_NUMNODES];
-        unsigned long sz, old_sz;
-        unsigned long hole_size;
-        unsigned long start, end;
-        unsigned long max_addr = (end_pfn << PAGE_SHIFT);
-
-        start = (start_pfn << PAGE_SHIFT);
-        hole_size = e820_hole_size(start, max_addr);
-        sz = (max_addr - start - hole_size) / numa_fake;
-
-        /* Kludge needed for the hash function */
-
-        old_sz = sz;
-        /*
-         * Round down to the nearest FAKE_NODE_MIN_SIZE.
-         */
-        sz &= FAKE_NODE_MIN_HASH_MASK;
+        unsigned int big;
+        u64 size;
+        int i;
 
+        if (num_nodes <= 0)
+                return -1;
+        if (num_nodes > MAX_NUMNODES)
+                num_nodes = MAX_NUMNODES;
+        size = (max_addr - *addr - E820_ADDR_HOLE_SIZE(*addr, max_addr)) /
+               num_nodes;
         /*
-         * We ensure that each node is at least 64MB big.  Smaller than this
-         * size can cause VM hiccups.
+         * Calculate the number of big nodes that can be allocated as a result
+         * of consolidating the leftovers.
          */
-        if (sz == 0) {
-                printk(KERN_INFO "Not enough memory for %d nodes.  Reducing "
-                                "the number of nodes\n", numa_fake);
-                numa_fake = (max_addr - start - hole_size) / FAKE_NODE_MIN_SIZE;
-                printk(KERN_INFO "Number of fake nodes will be = %d\n",
-                                numa_fake);
-                sz = FAKE_NODE_MIN_SIZE;
+        big = ((size & ~FAKE_NODE_MIN_HASH_MASK) * num_nodes) /
+              FAKE_NODE_MIN_SIZE;
+
+        /* Round down to nearest FAKE_NODE_MIN_SIZE. */
+        size &= FAKE_NODE_MIN_HASH_MASK;
+        if (!size) {
+                printk(KERN_ERR "Not enough memory for each node.  "
+                       "NUMA emulation disabled.\n");
+                return -1;
         }
-        /*
-         * Find out how many nodes can get an extra NODE_MIN_SIZE granule.
-         * This logic ensures the extra memory gets distributed among as many
-         * nodes as possible (as compared to one single node getting all that
-         * extra memory.
-         */
-        big = ((old_sz - sz) * numa_fake) / FAKE_NODE_MIN_SIZE;
-        printk(KERN_INFO "Fake node Size: %luMB hole_size: %luMB big nodes: "
-                        "%d\n",
-                        (sz >> 20), (hole_size >> 20), big);
-        memset(&nodes,0,sizeof(nodes));
-        end = start;
-        for (i = 0; i < numa_fake; i++) {
-                /*
-                 * In case we are not able to allocate enough memory for all
-                 * the nodes, we reduce the number of fake nodes.
-                 */
-                if (end >= max_addr) {
-                        numa_fake = i - 1;
-                        break;
-                }
-                start = nodes[i].start = end;
-                /*
-                 * Final node can have all the remaining memory.
-                 */
-                if (i == numa_fake-1)
-                        sz = max_addr - start;
-                end = nodes[i].start + sz;
-                /*
-                 * Fir "big" number of nodes get extra granule.
-                 */
+
+        for (i = node_start; i < num_nodes + node_start; i++) {
+                u64 end = *addr + size;
                 if (i < big)
                         end += FAKE_NODE_MIN_SIZE;
                 /*
-                 * Iterate over the range to ensure that this node gets at
-                 * least sz amount of RAM (excluding holes)
+                 * The final node can have the remaining system RAM.  Other
+                 * nodes receive roughly the same amount of available pages.
                  */
-                while ((end - start - e820_hole_size(start, end)) < sz) {
-                        end += FAKE_NODE_MIN_SIZE;
-                        if (end >= max_addr)
-                                break;
+                if (i == num_nodes + node_start - 1)
+                        end = max_addr;
+                else
+                        while (end - *addr - E820_ADDR_HOLE_SIZE(*addr, end) <
+                               size) {
+                                end += FAKE_NODE_MIN_SIZE;
+                                if (end > max_addr) {
+                                        end = max_addr;
+                                        break;
+                                }
+                        }
+                if (setup_node_range(i, nodes, addr, end - *addr, max_addr) < 0)
+                        break;
+        }
+        return i - node_start + 1;
+}
+
+/*
+ * Splits the remaining system RAM into chunks of size.  The remaining memory is
+ * always assigned to a final node and can be asymmetric.  Returns the number of
+ * nodes split.
+ */
+static int __init split_nodes_by_size(struct bootnode *nodes, u64 *addr,
+                                      u64 max_addr, int node_start, u64 size)
+{
+        int i = node_start;
+        size = (size << 20) & FAKE_NODE_MIN_HASH_MASK;
+        while (!setup_node_range(i++, nodes, addr, size, max_addr))
+                ;
+        return i - node_start;
+}
+
+/*
+ * Sets up the system RAM area from start_pfn to end_pfn according to the
+ * numa=fake command-line option.
+ */
+static int __init numa_emulation(unsigned long start_pfn, unsigned long end_pfn)
+{
+        struct bootnode nodes[MAX_NUMNODES];
+        u64 addr = start_pfn << PAGE_SHIFT;
+        u64 max_addr = end_pfn << PAGE_SHIFT;
+        int num_nodes = 0;
+        int coeff_flag;
+        int coeff = -1;
+        int num = 0;
+        u64 size;
+        int i;
+
+        memset(&nodes, 0, sizeof(nodes));
+        /*
+         * If the numa=fake command-line is just a single number N, split the
+         * system RAM into N fake nodes.
+         */
+        if (!strchr(cmdline, '*') && !strchr(cmdline, ',')) {
+                num_nodes = split_nodes_equally(nodes, &addr, max_addr, 0,
+                                                simple_strtol(cmdline, NULL, 0));
+                if (num_nodes < 0)
+                        return num_nodes;
+                goto out;
+        }
+
+        /* Parse the command line. */
+        for (coeff_flag = 0; ; cmdline++) {
+                if (*cmdline && isdigit(*cmdline)) {
+                        num = num * 10 + *cmdline - '0';
+                        continue;
                 }
-                /*
-                 * Look at the next node to make sure there is some real memory
-                 * to map.  Bad things happen when the only memory present
-                 * in a zone on a fake node is IO hole.
-                 */
-                while (e820_hole_size(end, end + FAKE_NODE_MIN_SIZE) > 0) {
-                        if (zone_cross_over(start, end + sz)) {
-                                end = (MAX_DMA32_PFN << PAGE_SHIFT);
+                if (*cmdline == '*') {
+                        if (num > 0)
+                                coeff = num;
+                        coeff_flag = 1;
+                }
+                if (!*cmdline || *cmdline == ',') {
+                        if (!coeff_flag)
+                                coeff = 1;
+                        /*
+                         * Round down to the nearest FAKE_NODE_MIN_SIZE.
+                         * Command-line coefficients are in megabytes.
+                         */
+                        size = ((u64)num << 20) & FAKE_NODE_MIN_HASH_MASK;
+                        if (size)
+                                for (i = 0; i < coeff; i++, num_nodes++)
+                                        if (setup_node_range(num_nodes, nodes,
+                                                &addr, size, max_addr) < 0)
+                                                goto done;
+                        if (!*cmdline)
                                 break;
-                        }
-                        if (end >= max_addr)
+                        coeff_flag = 0;
+                        coeff = -1;
+                }
+                num = 0;
+        }
+done:
+        if (!num_nodes)
+                return -1;
+        /* Fill remainder of system RAM, if appropriate. */
+        if (addr < max_addr) {
+                if (coeff_flag && coeff < 0) {
+                        /* Split remaining nodes into num-sized chunks */
+                        num_nodes += split_nodes_by_size(nodes, &addr, max_addr,
+                                                         num_nodes, num);
+                        goto out;
+                }
+                switch (*(cmdline - 1)) {
+                case '*':
+                        /* Split remaining nodes into coeff chunks */
+                        if (coeff <= 0)
                                 break;
-                        end += FAKE_NODE_MIN_SIZE;
+                        num_nodes += split_nodes_equally(nodes, &addr, max_addr,
+                                                         num_nodes, coeff);
+                        break;
+                case ',':
+                        /* Do not allocate remaining system RAM */
+                        break;
+                default:
+                        /* Give one final node */
+                        setup_node_range(num_nodes, nodes, &addr,
+                                         max_addr - addr, max_addr);
+                        num_nodes++;
                 }
-                if (end > max_addr)
-                        end = max_addr;
-                nodes[i].end = end;
-                printk(KERN_INFO "Faking node %d at %016Lx-%016Lx (%LuMB)\n",
-                       i,
-                       nodes[i].start, nodes[i].end,
-                       (nodes[i].end - nodes[i].start) >> 20);
-                node_set_online(i);
-        }
-        memnode_shift = compute_hash_shift(nodes, numa_fake);
-        if (memnode_shift < 0) {
-                memnode_shift = 0;
-                printk(KERN_ERR "No NUMA hash function found. Emulation disabled.\n");
-                return -1;
-        }
-        for_each_online_node(i) {
+        }
+out:
+        memnode_shift = compute_hash_shift(nodes, num_nodes);
+        if (memnode_shift < 0) {
+                memnode_shift = 0;
+                printk(KERN_ERR "No NUMA hash function found.  NUMA emulation "
+                       "disabled.\n");
+                return -1;
+        }
+
+        /*
+         * We need to vacate all active ranges that may have been registered by
+         * SRAT.
+         */
+        remove_all_active_ranges();
+        for_each_node_mask(i, node_possible_map) {
                 e820_register_active_regions(i, nodes[i].start >> PAGE_SHIFT,
                                                 nodes[i].end >> PAGE_SHIFT);
                 setup_node_bootmem(i, nodes[i].start, nodes[i].end);
@@ -399,26 +487,32 @@ static int __init numa_emulation(unsigned long start_pfn, unsigned long end_pfn)
         numa_init_array();
         return 0;
 }
-#endif
+#undef E820_ADDR_HOLE_SIZE
+#endif /* CONFIG_NUMA_EMU */
 
 void __init numa_initmem_init(unsigned long start_pfn, unsigned long end_pfn)
 { 
         int i;
 
+        nodes_clear(node_possible_map);
+
 #ifdef CONFIG_NUMA_EMU
-        if (numa_fake && !numa_emulation(start_pfn, end_pfn))
+        if (cmdline && !numa_emulation(start_pfn, end_pfn))
                 return;
+        nodes_clear(node_possible_map);
 #endif
 
 #ifdef CONFIG_ACPI_NUMA
         if (!numa_off && !acpi_scan_nodes(start_pfn << PAGE_SHIFT,
                                           end_pfn << PAGE_SHIFT))
                 return;
+        nodes_clear(node_possible_map);
 #endif
 
 #ifdef CONFIG_K8_NUMA
         if (!numa_off && !k8_scan_nodes(start_pfn<<PAGE_SHIFT, end_pfn<<PAGE_SHIFT))
                 return;
+        nodes_clear(node_possible_map);
 #endif
         printk(KERN_INFO "%s\n",
                numa_off ? "NUMA turned off" : "No NUMA configuration found");
@@ -432,6 +526,7 @@ void __init numa_initmem_init(unsigned long start_pfn, unsigned long end_pfn)
         memnodemap[0] = 0;
         nodes_clear(node_online_map);
         node_set_online(0);
+        node_set(0, node_possible_map);
         for (i = 0; i < NR_CPUS; i++)
                 numa_set_node(i, 0);
         node_to_cpumask[0] = cpumask_of_cpu(0);
@@ -486,11 +581,8 @@ static __init int numa_setup(char *opt)
         if (!strncmp(opt,"off",3))
                 numa_off = 1;
 #ifdef CONFIG_NUMA_EMU
-        if(!strncmp(opt, "fake=", 5)) {
-                numa_fake = simple_strtoul(opt+5,NULL,0); ;
-                if (numa_fake >= MAX_NUMNODES)
-                        numa_fake = MAX_NUMNODES;
-        }
+        if (!strncmp(opt, "fake=", 5))
+                cmdline = opt + 5;
 #endif
 #ifdef CONFIG_ACPI_NUMA
         if (!strncmp(opt,"noacpi",6))
diff --git a/arch/x86_64/mm/pageattr.c b/arch/x86_64/mm/pageattr.c
index 081409aa3452..bf4aa8dd4254 100644
--- a/arch/x86_64/mm/pageattr.c
+++ b/arch/x86_64/mm/pageattr.c
@@ -51,7 +51,6 @@ static struct page *split_large_page(unsigned long address, pgprot_t prot,
         SetPagePrivate(base);
         page_private(base) = 0;
 
-        address = __pa(address);
         addr = address & LARGE_PAGE_MASK; 
         pbase = (pte_t *)page_address(base);
         for (i = 0; i < PTRS_PER_PTE; i++, addr += PAGE_SIZE) {
@@ -101,13 +100,12 @@ static inline void save_page(struct page *fpage)
  * No more special protections in this 2/4MB area - revert to a
  * large page again. 
  */
-static void revert_page(unsigned long address, pgprot_t ref_prot)
+static void revert_page(unsigned long address, unsigned long pfn, pgprot_t ref_prot)
 {
         pgd_t *pgd;
         pud_t *pud;
         pmd_t *pmd;
         pte_t large_pte;
-        unsigned long pfn;
 
         pgd = pgd_offset_k(address);
         BUG_ON(pgd_none(*pgd));
@@ -115,7 +113,6 @@ static void revert_page(unsigned long address, pgprot_t ref_prot)
         BUG_ON(pud_none(*pud));
         pmd = pmd_offset(pud, address);
         BUG_ON(pmd_val(*pmd) & _PAGE_PSE);
-        pfn = (__pa(address) & LARGE_PAGE_MASK) >> PAGE_SHIFT;
         large_pte = pfn_pte(pfn, ref_prot);
         large_pte = pte_mkhuge(large_pte);
         set_pte((pte_t *)pmd, large_pte);
@@ -141,7 +138,8 @@ __change_page_attr(unsigned long address, unsigned long pfn, pgprot_t prot,
                          */
                         struct page *split;
                         ref_prot2 = pte_pgprot(pte_clrhuge(*kpte));
-                        split = split_large_page(address, prot, ref_prot2);
+                        split = split_large_page(pfn << PAGE_SHIFT, prot,
+                                                        ref_prot2);
                         if (!split)
                                 return -ENOMEM;
                         set_pte(kpte, mk_pte(split, ref_prot2));
@@ -160,7 +158,7 @@ __change_page_attr(unsigned long address, unsigned long pfn, pgprot_t prot,
 
         if (page_private(kpte_page) == 0) {
                 save_page(kpte_page);
-                revert_page(address, ref_prot);
+                revert_page(address, pfn, ref_prot);
         }
         return 0;
 } 
@@ -180,22 +178,32 @@ __change_page_attr(unsigned long address, unsigned long pfn, pgprot_t prot,
  */
 int change_page_attr_addr(unsigned long address, int numpages, pgprot_t prot)
 {
-        int err = 0; 
+        unsigned long phys_base_pfn = __pa_symbol(__START_KERNEL_map) >> PAGE_SHIFT;
+        int err = 0, kernel_map = 0;
         int i; 
 
+        if (address >= __START_KERNEL_map
+            && address < __START_KERNEL_map + KERNEL_TEXT_SIZE) {
+                address = (unsigned long)__va(__pa(address));
+                kernel_map = 1;
+        }
+
         down_write(&init_mm.mmap_sem);
         for (i = 0; i < numpages; i++, address += PAGE_SIZE) {
                 unsigned long pfn = __pa(address) >> PAGE_SHIFT;
 
-                err = __change_page_attr(address, pfn, prot, PAGE_KERNEL);
-                if (err) 
-                        break; 
+                if (!kernel_map || pte_present(pfn_pte(0, prot))) {
+                        err = __change_page_attr(address, pfn, prot, PAGE_KERNEL);
+                        if (err)
+                                break;
+                }
                 /* Handle kernel mapping too which aliases part of the
                  * lowmem */
-                if (__pa(address) < KERNEL_TEXT_SIZE) {
+                if ((pfn >= phys_base_pfn) &&
+                        ((pfn - phys_base_pfn) < (KERNEL_TEXT_SIZE >> PAGE_SHIFT))) {
                         unsigned long addr2;
                         pgprot_t prot2;
-                        addr2 = __START_KERNEL_map + __pa(address);
+                        addr2 = __START_KERNEL_map + ((pfn - phys_base_pfn) << PAGE_SHIFT);
                         /* Make sure the kernel mappings stay executable */
                         prot2 = pte_pgprot(pte_mkexec(pfn_pte(0, prot)));
                         err = __change_page_attr(addr2, pfn, prot2,
diff --git a/arch/x86_64/mm/srat.c b/arch/x86_64/mm/srat.c
index 2efe215fc76a..1e76bb0a7277 100644
--- a/arch/x86_64/mm/srat.c
+++ b/arch/x86_64/mm/srat.c
@@ -419,19 +419,21 @@ int __init acpi_scan_nodes(unsigned long start, unsigned long end)
                 return -1;
         }
 
+        node_possible_map = nodes_parsed;
+
         /* Finally register nodes */
-        for_each_node_mask(i, nodes_parsed)
+        for_each_node_mask(i, node_possible_map)
                 setup_node_bootmem(i, nodes[i].start, nodes[i].end);
         /* Try again in case setup_node_bootmem missed one due
            to missing bootmem */
-        for_each_node_mask(i, nodes_parsed)
+        for_each_node_mask(i, node_possible_map)
                 if (!node_online(i))
                         setup_node_bootmem(i, nodes[i].start, nodes[i].end);
 
         for (i = 0; i < NR_CPUS; i++) {
                 if (cpu_to_node[i] == NUMA_NO_NODE)
                         continue;
-                if (!node_isset(cpu_to_node[i], nodes_parsed))
+                if (!node_isset(cpu_to_node[i], node_possible_map))
                         numa_set_node(i, NUMA_NO_NODE);
         }
         numa_init_array();