Merge branch 'x86-bootmem-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip

* 'x86-bootmem-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: (30 commits)
  early_res: Need to save the allocation name in drop_range_partial()
  sparsemem: Fix compilation on PowerPC
  early_res: Add free_early_partial()
  x86: Fix non-bootmem compilation on PowerPC
  core: Move early_res from arch/x86 to kernel/
  x86: Add find_fw_memmap_area
  Move round_up/down to kernel.h
  x86: Make 32bit support NO_BOOTMEM
  early_res: Enhance check_and_double_early_res
  x86: Move back find_e820_area to e820.c
  x86: Add find_early_area_size
  x86: Separate early_res related code from e820.c
  x86: Move bios page reserve early to head32/64.c
  sparsemem: Put mem map for one node together.
  sparsemem: Put usemap for one node together
  x86: Make 64 bit use early_res instead of bootmem before slab
  x86: Only call dma32_reserve_bootmem 64bit !CONFIG_NUMA
  x86: Make early_node_mem get mem > 4 GB if possible
  x86: Dynamically increase early_res array size
  x86: Introduce max_early_res and early_res_count
  ...

4 files changed, 64 insertions, 52 deletions

diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c
index 2226f2c70ea..5cb3f0f54f4 100644
--- a/arch/x86/mm/init_32.c
+++ b/arch/x86/mm/init_32.c
@@ -750,6 +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,
@@ -766,13 +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;
         /*
@@ -784,11 +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;
 
@@ -806,6 +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 69ddfbd9113..e9b040e1cde 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -572,6 +572,7 @@ 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 +580,15 @@ 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 +977,7 @@ 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/numa_32.c b/arch/x86/mm/numa_32.c
index b20760ca724..809baaaf48b 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 3307ea8bd43..8948f47fde0 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);
 }
@@ -709,6 +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;
 }