19 files changed, 346 insertions, 261 deletions

diff --git a/arch/x86/mm/hugetlbpage.c b/arch/x86/mm/hugetlbpage.c
index f46c340727b8..069ce7c37c01 100644
--- a/arch/x86/mm/hugetlbpage.c
+++ b/arch/x86/mm/hugetlbpage.c
@@ -9,7 +9,6 @@
 #include <linux/mm.h>
 #include <linux/hugetlb.h>
 #include <linux/pagemap.h>
-#include <linux/slab.h>
 #include <linux/err.h>
 #include <linux/sysctl.h>
 #include <asm/mman.h>
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index d406c5239019..b278535b14aa 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -1,3 +1,4 @@
+#include <linux/gfp.h>
 #include <linux/initrd.h>
 #include <linux/ioport.h>
 #include <linux/swap.h>
@@ -266,16 +267,9 @@ unsigned long __init_refok init_memory_mapping(unsigned long start,
         if (!after_bootmem)
                 find_early_table_space(end, use_pse, use_gbpages);
 
-#ifdef CONFIG_X86_32
-        for (i = 0; i < nr_range; i++)
-                kernel_physical_mapping_init(mr[i].start, mr[i].end,
-                                             mr[i].page_size_mask);
-        ret = end;
-#else /* CONFIG_X86_64 */
         for (i = 0; i < nr_range; i++)
                 ret = kernel_physical_mapping_init(mr[i].start, mr[i].end,
                                                    mr[i].page_size_mask);
-#endif
 
 #ifdef CONFIG_X86_32
         early_ioremap_page_table_range_init();
@@ -338,11 +332,23 @@ int devmem_is_allowed(unsigned long pagenr)
 
 void free_init_pages(char *what, unsigned long begin, unsigned long end)
 {
-        unsigned long addr = begin;
+        unsigned long addr;
+        unsigned long begin_aligned, end_aligned;
+
+        /* Make sure boundaries are page aligned */
+        begin_aligned = PAGE_ALIGN(begin);
+        end_aligned   = end & PAGE_MASK;
 
-        if (addr >= end)
+        if (WARN_ON(begin_aligned != begin || end_aligned != end)) {
+                begin = begin_aligned;
+                end   = end_aligned;
+        }
+
+        if (begin >= end)
                 return;
 
+        addr = begin;
+
         /*
          * If debugging page accesses then do not free this memory but
          * mark them not present - any buggy init-section access will
@@ -350,7 +356,7 @@ void free_init_pages(char *what, unsigned long begin, unsigned long end)
          */
 #ifdef CONFIG_DEBUG_PAGEALLOC
         printk(KERN_INFO "debug: unmapping init memory %08lx..%08lx\n",
-                begin, PAGE_ALIGN(end));
+                begin, end);
         set_memory_np(begin, (end - begin) >> PAGE_SHIFT);
 #else
         /*
@@ -365,8 +371,7 @@ void free_init_pages(char *what, unsigned long begin, unsigned long end)
         for (; 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);
+                memset((void *)addr, POISON_FREE_INITMEM, PAGE_SIZE);
                 free_page(addr);
                 totalram_pages++;
         }
@@ -383,6 +388,15 @@ void free_initmem(void)
 #ifdef CONFIG_BLK_DEV_INITRD
 void free_initrd_mem(unsigned long start, unsigned long end)
 {
-        free_init_pages("initrd memory", start, end);
+        /*
+         * end could be not aligned, and We can not align that,
+         * decompresser could be confused by aligned initrd_end
+         * We already reserve the end partial page before in
+         *   - i386_start_kernel()
+         *   - x86_64_start_kernel()
+         *   - relocate_initrd()
+         * So here We can do PAGE_ALIGN() safely to get partial page to be freed
+         */
+        free_init_pages("initrd memory", start, PAGE_ALIGN(end));
 }
 #endif
diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c
index 9a0c258a86be..bca79091b9d6 100644
--- a/arch/x86/mm/init_32.c
+++ b/arch/x86/mm/init_32.c
@@ -25,11 +25,11 @@
 #include <linux/pfn.h>
 #include <linux/poison.h>
 #include <linux/bootmem.h>
-#include <linux/slab.h>
 #include <linux/proc_fs.h>
 #include <linux/memory_hotplug.h>
 #include <linux/initrd.h>
 #include <linux/cpumask.h>
+#include <linux/gfp.h>
 
 #include <asm/asm.h>
 #include <asm/bios_ebda.h>
@@ -241,6 +241,7 @@ kernel_physical_mapping_init(unsigned long start,
                              unsigned long page_size_mask)
 {
         int use_pse = page_size_mask == (1<<PG_LEVEL_2M);
+        unsigned long last_map_addr = end;
         unsigned long start_pfn, end_pfn;
         pgd_t *pgd_base = swapper_pg_dir;
         int pgd_idx, pmd_idx, pte_ofs;
@@ -341,9 +342,10 @@ repeat:
                                         prot = PAGE_KERNEL_EXEC;
 
                                 pages_4k++;
-                                if (mapping_iter == 1)
+                                if (mapping_iter == 1) {
                                         set_pte(pte, pfn_pte(pfn, init_prot));
-                                else
+                                        last_map_addr = (pfn << PAGE_SHIFT) + PAGE_SIZE;
+                                } else
                                         set_pte(pte, pfn_pte(pfn, prot));
                         }
                 }
@@ -368,7 +370,7 @@ repeat:
                 mapping_iter = 2;
                 goto repeat;
         }
-        return 0;
+        return last_map_addr;
 }
 
 pte_t *kmap_pte;
@@ -748,6 +750,7 @@ static void __init zone_sizes_init(void)
         free_area_init_nodes(max_zone_pfns);
 }
 
+#ifndef CONFIG_NO_BOOTMEM
 static unsigned long __init setup_node_bootmem(int nodeid,
                                  unsigned long start_pfn,
                                  unsigned long end_pfn,
@@ -764,13 +767,14 @@ static unsigned long __init setup_node_bootmem(int nodeid,
         printk(KERN_INFO "  node %d bootmap %08lx - %08lx\n",
                  nodeid, bootmap, bootmap + bootmap_size);
         free_bootmem_with_active_regions(nodeid, end_pfn);
-        early_res_to_bootmem(start_pfn<<PAGE_SHIFT, end_pfn<<PAGE_SHIFT);
 
         return bootmap + bootmap_size;
 }
+#endif
 
 void __init setup_bootmem_allocator(void)
 {
+#ifndef CONFIG_NO_BOOTMEM
         int nodeid;
         unsigned long bootmap_size, bootmap;
         /*
@@ -782,11 +786,13 @@ void __init setup_bootmem_allocator(void)
         if (bootmap == -1L)
                 panic("Cannot find bootmem map of size %ld\n", bootmap_size);
         reserve_early(bootmap, bootmap + bootmap_size, "BOOTMAP");
+#endif
 
         printk(KERN_INFO "  mapped low ram: 0 - %08lx\n",
                  max_pfn_mapped<<PAGE_SHIFT);
         printk(KERN_INFO "  low ram: 0 - %08lx\n", max_low_pfn<<PAGE_SHIFT);
 
+#ifndef CONFIG_NO_BOOTMEM
         for_each_online_node(nodeid) {
                  unsigned long start_pfn, end_pfn;
 
@@ -804,6 +810,7 @@ void __init setup_bootmem_allocator(void)
                 bootmap = setup_node_bootmem(nodeid, start_pfn, end_pfn,
                                                  bootmap);
         }
+#endif
 
         after_bootmem = 1;
 }
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index 69ddfbd91135..ee41bba315d1 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -29,6 +29,7 @@
 #include <linux/module.h>
 #include <linux/memory_hotplug.h>
 #include <linux/nmi.h>
+#include <linux/gfp.h>
 
 #include <asm/processor.h>
 #include <asm/bios_ebda.h>
@@ -572,6 +573,7 @@ kernel_physical_mapping_init(unsigned long start,
 void __init initmem_init(unsigned long start_pfn, unsigned long end_pfn,
                                 int acpi, int k8)
 {
+#ifndef CONFIG_NO_BOOTMEM
         unsigned long bootmap_size, bootmap;
 
         bootmap_size = bootmem_bootmap_pages(end_pfn)<<PAGE_SHIFT;
@@ -579,13 +581,15 @@ void __init initmem_init(unsigned long start_pfn, unsigned long end_pfn,
                                  PAGE_SIZE);
         if (bootmap == -1L)
                 panic("Cannot find bootmem map of size %ld\n", bootmap_size);
+        reserve_early(bootmap, bootmap + bootmap_size, "BOOTMAP");
         /* don't touch min_low_pfn */
         bootmap_size = init_bootmem_node(NODE_DATA(0), bootmap >> PAGE_SHIFT,
                                          0, end_pfn);
         e820_register_active_regions(0, start_pfn, end_pfn);
         free_bootmem_with_active_regions(0, end_pfn);
-        early_res_to_bootmem(0, end_pfn<<PAGE_SHIFT);
-        reserve_bootmem(bootmap, bootmap_size, BOOTMEM_DEFAULT);
+#else
+        e820_register_active_regions(0, start_pfn, end_pfn);
+#endif
 }
 #endif
 
@@ -974,7 +978,7 @@ vmemmap_populate(struct page *start_page, unsigned long size, int node)
                         if (pmd_none(*pmd)) {
                                 pte_t entry;
 
-                                p = vmemmap_alloc_block(PMD_SIZE, node);
+                                p = vmemmap_alloc_block_buf(PMD_SIZE, node);
                                 if (!p)
                                         return -ENOMEM;
 
diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c
index c246d259822d..12e4d2d3c110 100644
--- a/arch/x86/mm/ioremap.c
+++ b/arch/x86/mm/ioremap.c
@@ -24,43 +24,6 @@
 
 #include "physaddr.h"
 
-int page_is_ram(unsigned long pagenr)
-{
-        resource_size_t addr, end;
-        int i;
-
-        /*
-         * A special case is the first 4Kb of memory;
-         * This is a BIOS owned area, not kernel ram, but generally
-         * not listed as such in the E820 table.
-         */
-        if (pagenr == 0)
-                return 0;
-
-        /*
-         * Second special case: Some BIOSen report the PC BIOS
-         * area (640->1Mb) as ram even though it is not.
-         */
-        if (pagenr >= (BIOS_BEGIN >> PAGE_SHIFT) &&
-                    pagenr < (BIOS_END >> PAGE_SHIFT))
-                return 0;
-
-        for (i = 0; i < e820.nr_map; i++) {
-                /*
-                 * Not usable memory:
-                 */
-                if (e820.map[i].type != E820_RAM)
-                        continue;
-                addr = (e820.map[i].addr + PAGE_SIZE-1) >> PAGE_SHIFT;
-                end = (e820.map[i].addr + e820.map[i].size) >> PAGE_SHIFT;
-
-
-                if ((pagenr >= addr) && (pagenr < end))
-                        return 1;
-        }
-        return 0;
-}
-
 /*
  * Fix up the linear direct mapping of the kernel to avoid cache attribute
  * conflicts.
@@ -422,6 +385,10 @@ void __init early_ioremap_init(void)
          * The boot-ioremap range spans multiple pmds, for which
          * we are not prepared:
          */
+#define __FIXADDR_TOP (-PAGE_SIZE)
+        BUILD_BUG_ON((__fix_to_virt(FIX_BTMAP_BEGIN) >> PMD_SHIFT)
+                     != (__fix_to_virt(FIX_BTMAP_END) >> PMD_SHIFT));
+#undef __FIXADDR_TOP
         if (pmd != early_ioremap_pmd(fix_to_virt(FIX_BTMAP_END))) {
                 WARN_ON(1);
                 printk(KERN_WARNING "pmd %p != %p\n",
@@ -481,6 +448,20 @@ static inline void __init early_clear_fixmap(enum fixed_addresses idx)
 static void __iomem *prev_map[FIX_BTMAPS_SLOTS] __initdata;
 static unsigned long prev_size[FIX_BTMAPS_SLOTS] __initdata;
 
+void __init fixup_early_ioremap(void)
+{
+        int i;
+
+        for (i = 0; i < FIX_BTMAPS_SLOTS; i++) {
+                if (prev_map[i]) {
+                        WARN_ON(1);
+                        break;
+                }
+        }
+
+        early_ioremap_init();
+}
+
 static int __init check_early_ioremap_leak(void)
 {
         int count = 0;
diff --git a/arch/x86/mm/kmemcheck/kmemcheck.c b/arch/x86/mm/kmemcheck/kmemcheck.c
index 8cc183344140..b3b531a4f8e5 100644
--- a/arch/x86/mm/kmemcheck/kmemcheck.c
+++ b/arch/x86/mm/kmemcheck/kmemcheck.c
@@ -337,7 +337,7 @@ bool kmemcheck_is_obj_initialized(unsigned long addr, size_t size)
         if (!shadow)
                 return true;
 
-        status = kmemcheck_shadow_test(shadow, size);
+        status = kmemcheck_shadow_test_all(shadow, size);
 
         return status == KMEMCHECK_SHADOW_INITIALIZED;
 }
diff --git a/arch/x86/mm/kmemcheck/shadow.c b/arch/x86/mm/kmemcheck/shadow.c
index 3f66b82076a3..aec124214d97 100644
--- a/arch/x86/mm/kmemcheck/shadow.c
+++ b/arch/x86/mm/kmemcheck/shadow.c
@@ -125,12 +125,12 @@ void kmemcheck_mark_initialized_pages(struct page *p, unsigned int n)
 
 enum kmemcheck_shadow kmemcheck_shadow_test(void *shadow, unsigned int size)
 {
+#ifdef CONFIG_KMEMCHECK_PARTIAL_OK
         uint8_t *x;
         unsigned int i;
 
         x = shadow;
 
-#ifdef CONFIG_KMEMCHECK_PARTIAL_OK
         /*
          * Make sure _some_ bytes are initialized. Gcc frequently generates
          * code to access neighboring bytes.
@@ -139,13 +139,25 @@ enum kmemcheck_shadow kmemcheck_shadow_test(void *shadow, unsigned int size)
                 if (x[i] == KMEMCHECK_SHADOW_INITIALIZED)
                         return x[i];
         }
+
+        return x[0];
 #else
+        return kmemcheck_shadow_test_all(shadow, size);
+#endif
+}
+
+enum kmemcheck_shadow kmemcheck_shadow_test_all(void *shadow, unsigned int size)
+{
+        uint8_t *x;
+        unsigned int i;
+
+        x = shadow;
+
         /* All bytes must be initialized. */
         for (i = 0; i < size; ++i) {
                 if (x[i] != KMEMCHECK_SHADOW_INITIALIZED)
                         return x[i];
         }
-#endif
 
         return x[0];
 }
diff --git a/arch/x86/mm/kmemcheck/shadow.h b/arch/x86/mm/kmemcheck/shadow.h
index af46d9ab9d86..ff0b2f70fbcb 100644
--- a/arch/x86/mm/kmemcheck/shadow.h
+++ b/arch/x86/mm/kmemcheck/shadow.h
@@ -11,6 +11,8 @@ enum kmemcheck_shadow {
 void *kmemcheck_shadow_lookup(unsigned long address);
 
 enum kmemcheck_shadow kmemcheck_shadow_test(void *shadow, unsigned int size);
+enum kmemcheck_shadow kmemcheck_shadow_test_all(void *shadow,
+                                                unsigned int size);
 void kmemcheck_shadow_set(void *shadow, unsigned int size);
 
 #endif
diff --git a/arch/x86/mm/kmmio.c b/arch/x86/mm/kmmio.c
index 536fb6823366..5d0e67fff1a6 100644
--- a/arch/x86/mm/kmmio.c
+++ b/arch/x86/mm/kmmio.c
@@ -21,6 +21,7 @@
 #include <linux/kdebug.h>
 #include <linux/mutex.h>
 #include <linux/io.h>
+#include <linux/slab.h>
 #include <asm/cacheflush.h>
 #include <asm/tlbflush.h>
 #include <linux/errno.h>
diff --git a/arch/x86/mm/mmap.c b/arch/x86/mm/mmap.c
index c8191defc38a..1dab5194fd9d 100644
--- a/arch/x86/mm/mmap.c
+++ b/arch/x86/mm/mmap.c
@@ -71,7 +71,7 @@ static int mmap_is_legacy(void)
         if (current->personality & ADDR_COMPAT_LAYOUT)
                 return 1;
 
-        if (current->signal->rlim[RLIMIT_STACK].rlim_cur == RLIM_INFINITY)
+        if (rlimit(RLIMIT_STACK) == RLIM_INFINITY)
                 return 1;
 
         return sysctl_legacy_va_layout;
@@ -96,7 +96,7 @@ static unsigned long mmap_rnd(void)
 
 static unsigned long mmap_base(void)
 {
-        unsigned long gap = current->signal->rlim[RLIMIT_STACK].rlim_cur;
+        unsigned long gap = rlimit(RLIMIT_STACK);
 
         if (gap < MIN_GAP)
                 gap = MIN_GAP;
diff --git a/arch/x86/mm/mmio-mod.c b/arch/x86/mm/mmio-mod.c
index 34a3291ca103..3adff7dcc148 100644
--- a/arch/x86/mm/mmio-mod.c
+++ b/arch/x86/mm/mmio-mod.c
@@ -26,6 +26,7 @@
 
 #include <linux/module.h>
 #include <linux/debugfs.h>
+#include <linux/slab.h>
 #include <linux/uaccess.h>
 #include <linux/io.h>
 #include <linux/version.h>
diff --git a/arch/x86/mm/numa_32.c b/arch/x86/mm/numa_32.c
index b20760ca7244..809baaaf48b1 100644
--- a/arch/x86/mm/numa_32.c
+++ b/arch/x86/mm/numa_32.c
@@ -418,7 +418,10 @@ void __init initmem_init(unsigned long start_pfn, unsigned long end_pfn,
 
         for_each_online_node(nid) {
                 memset(NODE_DATA(nid), 0, sizeof(struct pglist_data));
+                NODE_DATA(nid)->node_id = nid;
+#ifndef CONFIG_NO_BOOTMEM
                 NODE_DATA(nid)->bdata = &bootmem_node_data[nid];
+#endif
         }
 
         setup_bootmem_allocator();
diff --git a/arch/x86/mm/numa_64.c b/arch/x86/mm/numa_64.c
index 83bbc70d11bb..8948f47fde05 100644
--- a/arch/x86/mm/numa_64.c
+++ b/arch/x86/mm/numa_64.c
@@ -163,30 +163,48 @@ static void * __init early_node_mem(int nodeid, unsigned long start,
                                     unsigned long end, unsigned long size,
                                     unsigned long align)
 {
-        unsigned long mem = find_e820_area(start, end, size, align);
-        void *ptr;
+        unsigned long mem;
 
+        /*
+         * put it on high as possible
+         * something will go with NODE_DATA
+         */
+        if (start < (MAX_DMA_PFN<<PAGE_SHIFT))
+                start = MAX_DMA_PFN<<PAGE_SHIFT;
+        if (start < (MAX_DMA32_PFN<<PAGE_SHIFT) &&
+            end > (MAX_DMA32_PFN<<PAGE_SHIFT))
+                start = MAX_DMA32_PFN<<PAGE_SHIFT;
+        mem = find_e820_area(start, end, size, align);
+        if (mem != -1L)
+                return __va(mem);
+
+        /* extend the search scope */
+        end = max_pfn_mapped << PAGE_SHIFT;
+        if (end > (MAX_DMA32_PFN<<PAGE_SHIFT))
+                start = MAX_DMA32_PFN<<PAGE_SHIFT;
+        else
+                start = MAX_DMA_PFN<<PAGE_SHIFT;
+        mem = find_e820_area(start, end, size, align);
         if (mem != -1L)
                 return __va(mem);
 
-        ptr = __alloc_bootmem_nopanic(size, align, __pa(MAX_DMA_ADDRESS));
-        if (ptr == NULL) {
-                printk(KERN_ERR "Cannot find %lu bytes in node %d\n",
+        printk(KERN_ERR "Cannot find %lu bytes in node %d\n",
                        size, nodeid);
-                return NULL;
-        }
-        return ptr;
+
+        return NULL;
 }
 
 /* Initialize bootmem allocator for a node */
 void __init
 setup_node_bootmem(int nodeid, unsigned long start, unsigned long end)
 {
-        unsigned long start_pfn, last_pfn, bootmap_pages, bootmap_size;
+        unsigned long start_pfn, last_pfn, nodedata_phys;
         const int pgdat_size = roundup(sizeof(pg_data_t), PAGE_SIZE);
-        unsigned long bootmap_start, nodedata_phys;
-        void *bootmap;
         int nid;
+#ifndef CONFIG_NO_BOOTMEM
+        unsigned long bootmap_start, bootmap_pages, bootmap_size;
+        void *bootmap;
+#endif
 
         if (!end)
                 return;
@@ -200,7 +218,7 @@ setup_node_bootmem(int nodeid, unsigned long start, unsigned long end)
 
         start = roundup(start, ZONE_ALIGN);
 
-        printk(KERN_INFO "Bootmem setup node %d %016lx-%016lx\n", nodeid,
+        printk(KERN_INFO "Initmem setup node %d %016lx-%016lx\n", nodeid,
                start, end);
 
         start_pfn = start >> PAGE_SHIFT;
@@ -211,14 +229,21 @@ setup_node_bootmem(int nodeid, unsigned long start, unsigned long end)
         if (node_data[nodeid] == NULL)
                 return;
         nodedata_phys = __pa(node_data[nodeid]);
+        reserve_early(nodedata_phys, nodedata_phys + pgdat_size, "NODE_DATA");
         printk(KERN_INFO "  NODE_DATA [%016lx - %016lx]\n", nodedata_phys,
                 nodedata_phys + pgdat_size - 1);
+        nid = phys_to_nid(nodedata_phys);
+        if (nid != nodeid)
+                printk(KERN_INFO "    NODE_DATA(%d) on node %d\n", nodeid, nid);
 
         memset(NODE_DATA(nodeid), 0, sizeof(pg_data_t));
-        NODE_DATA(nodeid)->bdata = &bootmem_node_data[nodeid];
+        NODE_DATA(nodeid)->node_id = nodeid;
         NODE_DATA(nodeid)->node_start_pfn = start_pfn;
         NODE_DATA(nodeid)->node_spanned_pages = last_pfn - start_pfn;
 
+#ifndef CONFIG_NO_BOOTMEM
+        NODE_DATA(nodeid)->bdata = &bootmem_node_data[nodeid];
+
         /*
          * Find a place for the bootmem map
          * nodedata_phys could be on other nodes by alloc_bootmem,
@@ -227,11 +252,7 @@ setup_node_bootmem(int nodeid, unsigned long start, unsigned long end)
          * of alloc_bootmem, that could clash with reserved range
          */
         bootmap_pages = bootmem_bootmap_pages(last_pfn - start_pfn);
-        nid = phys_to_nid(nodedata_phys);
-        if (nid == nodeid)
-                bootmap_start = roundup(nodedata_phys + pgdat_size, PAGE_SIZE);
-        else
-                bootmap_start = roundup(start, PAGE_SIZE);
+        bootmap_start = roundup(nodedata_phys + pgdat_size, PAGE_SIZE);
         /*
          * SMP_CACHE_BYTES could be enough, but init_bootmem_node like
          * to use that to align to PAGE_SIZE
@@ -239,18 +260,13 @@ setup_node_bootmem(int nodeid, unsigned long start, unsigned long end)
         bootmap = early_node_mem(nodeid, bootmap_start, end,
                                  bootmap_pages<<PAGE_SHIFT, PAGE_SIZE);
         if (bootmap == NULL)  {
-                if (nodedata_phys < start || nodedata_phys >= end) {
-                        /*
-                         * only need to free it if it is from other node
-                         * bootmem
-                         */
-                        if (nid != nodeid)
-                                free_bootmem(nodedata_phys, pgdat_size);
-                }
+                free_early(nodedata_phys, nodedata_phys + pgdat_size);
                 node_data[nodeid] = NULL;
                 return;
         }
         bootmap_start = __pa(bootmap);
+        reserve_early(bootmap_start, bootmap_start+(bootmap_pages<<PAGE_SHIFT),
+                        "BOOTMAP");
 
         bootmap_size = init_bootmem_node(NODE_DATA(nodeid),
                                          bootmap_start >> PAGE_SHIFT,
@@ -259,31 +275,12 @@ setup_node_bootmem(int nodeid, unsigned long start, unsigned long end)
         printk(KERN_INFO "  bootmap [%016lx -  %016lx] pages %lx\n",
                  bootmap_start, bootmap_start + bootmap_size - 1,
                  bootmap_pages);
-
-        free_bootmem_with_active_regions(nodeid, end);
-
-        /*
-         * convert early reserve to bootmem reserve earlier
-         * otherwise early_node_mem could use early reserved mem
-         * on previous node
-         */
-        early_res_to_bootmem(start, end);
-
-        /*
-         * in some case early_node_mem could use alloc_bootmem
-         * to get range on other node, don't reserve that again
-         */
-        if (nid != nodeid)
-                printk(KERN_INFO "    NODE_DATA(%d) on node %d\n", nodeid, nid);
-        else
-                reserve_bootmem_node(NODE_DATA(nodeid), nodedata_phys,
-                                        pgdat_size, BOOTMEM_DEFAULT);
         nid = phys_to_nid(bootmap_start);
         if (nid != nodeid)
                 printk(KERN_INFO "    bootmap(%d) on node %d\n", nodeid, nid);
-        else
-                reserve_bootmem_node(NODE_DATA(nodeid), bootmap_start,
-                                 bootmap_pages<<PAGE_SHIFT, BOOTMEM_DEFAULT);
+
+        free_bootmem_with_active_regions(nodeid, end);
+#endif
 
         node_set_online(nodeid);
 }
@@ -427,7 +424,7 @@ static int __init split_nodes_interleave(u64 addr, u64 max_addr,
          * Calculate the number of big nodes that can be allocated as a result
          * of consolidating the remainder.
          */
-        big = ((size & ~FAKE_NODE_MIN_HASH_MASK) & nr_nodes) /
+        big = ((size & ~FAKE_NODE_MIN_HASH_MASK) * nr_nodes) /
                 FAKE_NODE_MIN_SIZE;
 
         size &= FAKE_NODE_MIN_HASH_MASK;
@@ -502,77 +499,99 @@ static int __init split_nodes_interleave(u64 addr, u64 max_addr,
 }
 
 /*
- * 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.
+ * Returns the end address of a node so that there is at least `size' amount of
+ * non-reserved memory or `max_addr' is reached.
  */
-static int __init split_nodes_equally(u64 *addr, u64 max_addr, int node_start,
-                                      int num_nodes)
+static u64 __init find_end_of_node(u64 start, u64 max_addr, u64 size)
 {
-        unsigned int big;
-        u64 size;
-        int i;
+        u64 end = start + size;
 
-        if (num_nodes <= 0)
-                return -1;
-        if (num_nodes > MAX_NUMNODES)
-                num_nodes = MAX_NUMNODES;
-        size = (max_addr - *addr - e820_hole_size(*addr, max_addr)) /
-               num_nodes;
-        /*
-         * Calculate the number of big nodes that can be allocated as a result
-         * of consolidating the leftovers.
-         */
-        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;
-        }
-
-        for (i = node_start; i < num_nodes + node_start; i++) {
-                u64 end = *addr + size;
-
-                if (i < big)
-                        end += FAKE_NODE_MIN_SIZE;
-                /*
-                 * The final node can have the remaining system RAM.  Other
-                 * nodes receive roughly the same amount of available pages.
-                 */
-                if (i == num_nodes + node_start - 1)
+        while (end - start - e820_hole_size(start, end) < size) {
+                end += FAKE_NODE_MIN_SIZE;
+                if (end > max_addr) {
                         end = max_addr;
-                else
-                        while (end - *addr - e820_hole_size(*addr, end) <
-                               size) {
-                                end += FAKE_NODE_MIN_SIZE;
-                                if (end > max_addr) {
-                                        end = max_addr;
-                                        break;
-                                }
-                        }
-                if (setup_node_range(i, addr, end - *addr, max_addr) < 0)
                         break;
+                }
         }
-        return i - node_start + 1;
+        return end;
 }
 
 /*
- * 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.
+ * Sets up fake nodes of `size' interleaved over physical nodes ranging from
+ * `addr' to `max_addr'.  The return value is the number of nodes allocated.
  */
-static int __init split_nodes_by_size(u64 *addr, u64 max_addr, int node_start,
-                                      u64 size)
+static int __init split_nodes_size_interleave(u64 addr, u64 max_addr, u64 size)
 {
-        int i = node_start;
-        size = (size << 20) & FAKE_NODE_MIN_HASH_MASK;
-        while (!setup_node_range(i++, addr, size, max_addr))
-                ;
-        return i - node_start;
+        nodemask_t physnode_mask = NODE_MASK_NONE;
+        u64 min_size;
+        int ret = 0;
+        int i;
+
+        if (!size)
+                return -1;
+        /*
+         * The limit on emulated nodes is MAX_NUMNODES, so the size per node is
+         * increased accordingly if the requested size is too small.  This
+         * creates a uniform distribution of node sizes across the entire
+         * machine (but not necessarily over physical nodes).
+         */
+        min_size = (max_addr - addr - e820_hole_size(addr, max_addr)) /
+                                                MAX_NUMNODES;
+        min_size = max(min_size, FAKE_NODE_MIN_SIZE);
+        if ((min_size & FAKE_NODE_MIN_HASH_MASK) < min_size)
+                min_size = (min_size + FAKE_NODE_MIN_SIZE) &
+                                                FAKE_NODE_MIN_HASH_MASK;
+        if (size < min_size) {
+                pr_err("Fake node size %LuMB too small, increasing to %LuMB\n",
+                        size >> 20, min_size >> 20);
+                size = min_size;
+        }
+        size &= FAKE_NODE_MIN_HASH_MASK;
+
+        for (i = 0; i < MAX_NUMNODES; i++)
+                if (physnodes[i].start != physnodes[i].end)
+                        node_set(i, physnode_mask);
+        /*
+         * Fill physical nodes with fake nodes of size until there is no memory
+         * left on any of them.
+         */
+        while (nodes_weight(physnode_mask)) {
+                for_each_node_mask(i, physnode_mask) {
+                        u64 dma32_end = MAX_DMA32_PFN << PAGE_SHIFT;
+                        u64 end;
+
+                        end = find_end_of_node(physnodes[i].start,
+                                                physnodes[i].end, size);
+                        /*
+                         * If there won't be at least FAKE_NODE_MIN_SIZE of
+                         * non-reserved memory in ZONE_DMA32 for the next node,
+                         * this one must extend to the boundary.
+                         */
+                        if (end < dma32_end && dma32_end - end -
+                            e820_hole_size(end, dma32_end) < FAKE_NODE_MIN_SIZE)
+                                end = dma32_end;
+
+                        /*
+                         * If there won't be enough non-reserved memory for the
+                         * next node, this one must extend to the end of the
+                         * physical node.
+                         */
+                        if (physnodes[i].end - end -
+                            e820_hole_size(end, physnodes[i].end) < size)
+                                end = physnodes[i].end;
+
+                        /*
+                         * Setup the fake node that will be allocated as bootmem
+                         * later.  If setup_node_range() returns non-zero, there
+                         * is no more memory available on this physical node.
+                         */
+                        if (setup_node_range(ret++, &physnodes[i].start,
+                                                end - physnodes[i].start,
+                                                physnodes[i].end) < 0)
+                                node_clear(i, physnode_mask);
+                }
+        }
+        return ret;
 }
 
 /*
@@ -582,87 +601,32 @@ static int __init split_nodes_by_size(u64 *addr, u64 max_addr, int node_start,
 static int __init numa_emulation(unsigned long start_pfn,
                         unsigned long last_pfn, int acpi, int k8)
 {
-        u64 size, addr = start_pfn << PAGE_SHIFT;
+        u64 addr = start_pfn << PAGE_SHIFT;
         u64 max_addr = last_pfn << PAGE_SHIFT;
-        int num_nodes = 0, num = 0, coeff_flag, coeff = -1, i;
         int num_phys_nodes;
+        int num_nodes;
+        int i;
 
         num_phys_nodes = setup_physnodes(addr, max_addr, acpi, k8);
         /*
-         * If the numa=fake command-line is just a single number N, split the
-         * system RAM into N fake nodes.
+         * If the numa=fake command-line contains a 'M' or 'G', it represents
+         * the fixed node size.  Otherwise, if it is just a single number N,
+         * split the system RAM into N fake nodes.
          */
-        if (!strchr(cmdline, '*') && !strchr(cmdline, ',')) {
-                long n = simple_strtol(cmdline, NULL, 0);
-
-                num_nodes = split_nodes_interleave(addr, max_addr,
-                                                        num_phys_nodes, n);
-                if (num_nodes < 0)
-                        return num_nodes;
-                goto out;
-        }
+        if (strchr(cmdline, 'M') || strchr(cmdline, 'G')) {
+                u64 size;
 
-        /* Parse the command line. */
-        for (coeff_flag = 0; ; cmdline++) {
-                if (*cmdline && isdigit(*cmdline)) {
-                        num = num * 10 + *cmdline - '0';
-                        continue;
-                }
-                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, &addr,
-                                                size, max_addr) < 0)
-                                                goto done;
-                        if (!*cmdline)
-                                break;
-                        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(&addr, max_addr,
-                                                         num_nodes, num);
-                        goto out;
-                }
-                switch (*(cmdline - 1)) {
-                case '*':
-                        /* Split remaining nodes into coeff chunks */
-                        if (coeff <= 0)
-                                break;
-                        num_nodes += split_nodes_equally(&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, &addr, max_addr - addr,
-                                         max_addr);
-                        num_nodes++;
-                }
+                size = memparse(cmdline, &cmdline);
+                num_nodes = split_nodes_size_interleave(addr, max_addr, size);
+        } else {
+                unsigned long n;
+
+                n = simple_strtoul(cmdline, NULL, 0);
+                num_nodes = split_nodes_interleave(addr, max_addr, num_phys_nodes, n);
         }
-out:
+
+        if (num_nodes < 0)
+                return num_nodes;
         memnode_shift = compute_hash_shift(nodes, num_nodes, NULL);
         if (memnode_shift < 0) {
                 memnode_shift = 0;
@@ -742,6 +706,10 @@ unsigned long __init numa_free_all_bootmem(void)
         for_each_online_node(i)
                 pages += free_all_bootmem_node(NODE_DATA(i));
 
+#ifdef CONFIG_NO_BOOTMEM
+        pages += free_all_memory_core_early(MAX_NUMNODES);
+#endif
+
         return pages;
 }
 
diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c
index 1d4eb93d333c..28195c350b97 100644
--- a/arch/x86/mm/pageattr.c
+++ b/arch/x86/mm/pageattr.c
@@ -6,13 +6,13 @@
 #include <linux/bootmem.h>
 #include <linux/module.h>
 #include <linux/sched.h>
-#include <linux/slab.h>
 #include <linux/mm.h>
 #include <linux/interrupt.h>
 #include <linux/seq_file.h>
 #include <linux/debugfs.h>
 #include <linux/pfn.h>
 #include <linux/percpu.h>
+#include <linux/gfp.h>
 
 #include <asm/e820.h>
 #include <asm/processor.h>
@@ -291,8 +291,29 @@ static inline pgprot_t static_protections(pgprot_t prot, unsigned long address,
          */
         if (kernel_set_to_readonly &&
             within(address, (unsigned long)_text,
-                   (unsigned long)__end_rodata_hpage_align))
-                pgprot_val(forbidden) |= _PAGE_RW;
+                   (unsigned long)__end_rodata_hpage_align)) {
+                unsigned int level;
+
+                /*
+                 * Don't enforce the !RW mapping for the kernel text mapping,
+                 * if the current mapping is already using small page mapping.
+                 * No need to work hard to preserve large page mappings in this
+                 * case.
+                 *
+                 * This also fixes the Linux Xen paravirt guest boot failure
+                 * (because of unexpected read-only mappings for kernel identity
+                 * mappings). In this paravirt guest case, the kernel text
+                 * mapping and the kernel identity mapping share the same
+                 * page-table pages. Thus we can't really use different
+                 * protections for the kernel text and identity mappings. Also,
+                 * these shared mappings are made of small page mappings.
+                 * Thus this don't enforce !RW mapping for small page kernel
+                 * text mapping logic will help Linux Xen parvirt guest boot
+                 * aswell.
+                 */
+                if (lookup_address(address, &level) && (level != PG_LEVEL_4K))
+                        pgprot_val(forbidden) |= _PAGE_RW;
+        }
 #endif
 
         prot = __pgprot(pgprot_val(prot) & ~pgprot_val(forbidden));
diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c
index 501fc60e5e4d..bbe5502ee1cb 100644
--- a/arch/x86/mm/pat.c
+++ b/arch/x86/mm/pat.c
@@ -12,7 +12,7 @@
 #include <linux/debugfs.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
-#include <linux/gfp.h>
+#include <linux/slab.h>
 #include <linux/mm.h>
 #include <linux/fs.h>
 #include <linux/rbtree.h>
diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c
index ed34f5e35999..5c4ee422590e 100644
--- a/arch/x86/mm/pgtable.c
+++ b/arch/x86/mm/pgtable.c
@@ -1,4 +1,5 @@
 #include <linux/mm.h>
+#include <linux/gfp.h>
 #include <asm/pgalloc.h>
 #include <asm/pgtable.h>
 #include <asm/tlb.h>
@@ -6,6 +7,14 @@
 
 #define PGALLOC_GFP GFP_KERNEL | __GFP_NOTRACK | __GFP_REPEAT | __GFP_ZERO
 
+#ifdef CONFIG_HIGHPTE
+#define PGALLOC_USER_GFP __GFP_HIGHMEM
+#else
+#define PGALLOC_USER_GFP 0
+#endif
+
+gfp_t __userpte_alloc_gfp = PGALLOC_GFP | PGALLOC_USER_GFP;
+
 pte_t *pte_alloc_one_kernel(struct mm_struct *mm, unsigned long address)
 {
         return (pte_t *)__get_free_page(PGALLOC_GFP);
@@ -15,16 +24,29 @@ pgtable_t pte_alloc_one(struct mm_struct *mm, unsigned long address)
 {
         struct page *pte;
 
-#ifdef CONFIG_HIGHPTE
-        pte = alloc_pages(PGALLOC_GFP | __GFP_HIGHMEM, 0);
-#else
-        pte = alloc_pages(PGALLOC_GFP, 0);
-#endif
+        pte = alloc_pages(__userpte_alloc_gfp, 0);
         if (pte)
                 pgtable_page_ctor(pte);
         return pte;
 }
 
+static int __init setup_userpte(char *arg)
+{
+        if (!arg)
+                return -EINVAL;
+
+        /*
+         * "userpte=nohigh" disables allocation of user pagetables in
+         * high memory.
+         */
+        if (strcmp(arg, "nohigh") == 0)
+                __userpte_alloc_gfp &= ~__GFP_HIGHMEM;
+        else
+                return -EINVAL;
+        return 0;
+}
+early_param("userpte", setup_userpte);
+
 void ___pte_free_tlb(struct mmu_gather *tlb, struct page *pte)
 {
         pgtable_page_dtor(pte);
diff --git a/arch/x86/mm/pgtable_32.c b/arch/x86/mm/pgtable_32.c
index 46c8834aedc0..792854003ed3 100644
--- a/arch/x86/mm/pgtable_32.c
+++ b/arch/x86/mm/pgtable_32.c
@@ -6,7 +6,6 @@
 #include <linux/swap.h>
 #include <linux/smp.h>
 #include <linux/highmem.h>
-#include <linux/slab.h>
 #include <linux/pagemap.h>
 #include <linux/spinlock.h>
 #include <linux/module.h>
@@ -19,6 +18,7 @@
 #include <asm/e820.h>
 #include <asm/tlb.h>
 #include <asm/tlbflush.h>
+#include <asm/io.h>
 
 unsigned int __VMALLOC_RESERVE = 128 << 20;
 
@@ -129,6 +129,7 @@ static int __init parse_reservetop(char *arg)
 
         address = memparse(arg, &arg);
         reserve_top_address(address);
+        fixup_early_ioremap();
         return 0;
 }
 early_param("reservetop", parse_reservetop);
diff --git a/arch/x86/mm/srat_64.c b/arch/x86/mm/srat_64.c
index 28c68762648f..f9897f7a9ef1 100644
--- a/arch/x86/mm/srat_64.c
+++ b/arch/x86/mm/srat_64.c
@@ -363,6 +363,54 @@ int __init acpi_scan_nodes(unsigned long start, unsigned long end)
         for (i = 0; i < MAX_NUMNODES; i++)
                 cutoff_node(i, start, end);
 
+        /*
+         * Join together blocks on the same node, holes between
+         * which don't overlap with memory on other nodes.
+         */
+        for (i = 0; i < num_node_memblks; ++i) {
+                int j, k;
+
+                for (j = i + 1; j < num_node_memblks; ++j) {
+                        unsigned long start, end;
+
+                        if (memblk_nodeid[i] != memblk_nodeid[j])
+                                continue;
+                        start = min(node_memblk_range[i].end,
+                                    node_memblk_range[j].end);
+                        end = max(node_memblk_range[i].start,
+                                  node_memblk_range[j].start);
+                        for (k = 0; k < num_node_memblks; ++k) {
+                                if (memblk_nodeid[i] == memblk_nodeid[k])
+                                        continue;
+                                if (start < node_memblk_range[k].end &&
+                                    end > node_memblk_range[k].start)
+                                        break;
+                        }
+                        if (k < num_node_memblks)
+                                continue;
+                        start = min(node_memblk_range[i].start,
+                                    node_memblk_range[j].start);
+                        end = max(node_memblk_range[i].end,
+                                  node_memblk_range[j].end);
+                        printk(KERN_INFO "SRAT: Node %d "
+                               "[%Lx,%Lx) + [%Lx,%Lx) -> [%lx,%lx)\n",
+                               memblk_nodeid[i],
+                               node_memblk_range[i].start,
+                               node_memblk_range[i].end,
+                               node_memblk_range[j].start,
+                               node_memblk_range[j].end,
+                               start, end);
+                        node_memblk_range[i].start = start;
+                        node_memblk_range[i].end = end;
+                        k = --num_node_memblks - j;
+                        memmove(memblk_nodeid + j, memblk_nodeid + j+1,
+                                k * sizeof(*memblk_nodeid));
+                        memmove(node_memblk_range + j, node_memblk_range + j+1,
+                                k * sizeof(*node_memblk_range));
+                        --j;
+                }
+        }
+
         memnode_shift = compute_hash_shift(node_memblk_range, num_node_memblks,
                                            memblk_nodeid);
         if (memnode_shift < 0) {
@@ -461,7 +509,8 @@ void __init acpi_fake_nodes(const struct bootnode *fake_nodes, int num_nodes)
                  * node, it must now point to the fake node ID.
                  */
                 for (j = 0; j < MAX_LOCAL_APIC; j++)
-                        if (apicid_to_node[j] == nid)
+                        if (apicid_to_node[j] == nid &&
+                            fake_apicid_to_node[j] == NUMA_NO_NODE)
                                 fake_apicid_to_node[j] = i;
         }
         for (i = 0; i < num_nodes; i++)
diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index 65b58e4b0b8b..426f3a1a64d3 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -41,7 +41,7 @@ union smp_flush_state {
         struct {
                 struct mm_struct *flush_mm;
                 unsigned long flush_va;
-                spinlock_t tlbstate_lock;
+                raw_spinlock_t tlbstate_lock;
                 DECLARE_BITMAP(flush_cpumask, NR_CPUS);
         };
         char pad[INTERNODE_CACHE_BYTES];
@@ -181,7 +181,7 @@ static void flush_tlb_others_ipi(const struct cpumask *cpumask,
          * num_online_cpus() <= NUM_INVALIDATE_TLB_VECTORS, but it is
          * probably not worth checking this for a cache-hot lock.
          */
-        spin_lock(&f->tlbstate_lock);
+        raw_spin_lock(&f->tlbstate_lock);
 
         f->flush_mm = mm;
         f->flush_va = va;
@@ -199,7 +199,7 @@ static void flush_tlb_others_ipi(const struct cpumask *cpumask,
 
         f->flush_mm = NULL;
         f->flush_va = 0;
-        spin_unlock(&f->tlbstate_lock);
+        raw_spin_unlock(&f->tlbstate_lock);
 }
 
 void native_flush_tlb_others(const struct cpumask *cpumask,
@@ -223,7 +223,7 @@ static int __cpuinit init_smp_flush(void)
         int i;
 
         for (i = 0; i < ARRAY_SIZE(flush_state); i++)
-                spin_lock_init(&flush_state[i].tlbstate_lock);
+                raw_spin_lock_init(&flush_state[i].tlbstate_lock);
 
         return 0;
 }