Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/x86/linux-2.6-x86-bigbox-bootmem-v3

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/x86/linux-2.6-x86-bigbox-bootmem-v3:
  x86_64/mm: check and print vmemmap allocation continuous
  x86_64: fix setup_node_bootmem to support big mem excluding with memmap
  x86_64: make reserve_bootmem_generic() use new reserve_bootmem()
  mm: allow reserve_bootmem() cross nodes
  mm: offset align in alloc_bootmem()
  mm: fix alloc_bootmem_core to use fast searching for all nodes
  mm: make mem_map allocation continuous

4 files changed, 80 insertions, 16 deletions

diff --git a/arch/x86/kernel/e820_64.c b/arch/x86/kernel/e820_64.c
index 79f0d52fa99..645ee5e32a2 100644
--- a/arch/x86/kernel/e820_64.c
+++ b/arch/x86/kernel/e820_64.c
@@ -106,14 +106,19 @@ void __init free_early(unsigned long start, unsigned long end)
 	early_res[j - 1].end = 0;
 }
 
-void __init early_res_to_bootmem(void)
+void __init early_res_to_bootmem(unsigned long start, unsigned long end)
 {
 	int i;
+	unsigned long final_start, final_end;
 	for (i = 0; i < MAX_EARLY_RES && early_res[i].end; i++) {
 		struct early_res *r = &early_res[i];
-		printk(KERN_INFO "early res: %d [%lx-%lx] %s\n", i,
-			r->start, r->end - 1, r->name);
-		reserve_bootmem_generic(r->start, r->end - r->start);
+		final_start = max(start, r->start);
+		final_end = min(end, r->end);
+		if (final_start >= final_end)
+			continue;
+		printk(KERN_INFO "  early res: %d [%lx-%lx] %s\n", i,
+			final_start, final_end - 1, r->name);
+		reserve_bootmem_generic(final_start, final_end - final_start);
 	}
 }
 
diff --git a/arch/x86/kernel/setup_64.c b/arch/x86/kernel/setup_64.c
index b04e2c011e1..60e64c8eee9 100644
--- a/arch/x86/kernel/setup_64.c
+++ b/arch/x86/kernel/setup_64.c
@@ -190,6 +190,7 @@ contig_initmem_init(unsigned long start_pfn, unsigned long end_pfn)
 	bootmap_size = init_bootmem(bootmap >> PAGE_SHIFT, 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);
 }
 #endif
@@ -421,8 +422,6 @@ void __init setup_arch(char **cmdline_p)
 	contig_initmem_init(0, end_pfn);
 #endif
 
-	early_res_to_bootmem();
-
 	dma32_reserve_bootmem();
 
 #ifdef CONFIG_ACPI_SLEEP
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index 0cca6266303..5fbb8652cf5 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -810,7 +810,7 @@ void free_initrd_mem(unsigned long start, unsigned long end)
 void __init reserve_bootmem_generic(unsigned long phys, unsigned len)
 {
 #ifdef CONFIG_NUMA
-	int nid = phys_to_nid(phys);
+	int nid, next_nid;
 #endif
 	unsigned long pfn = phys >> PAGE_SHIFT;
 
@@ -829,10 +829,16 @@ void __init reserve_bootmem_generic(unsigned long phys, unsigned len)
 
 	/* Should check here against the e820 map to avoid double free */
 #ifdef CONFIG_NUMA
-	reserve_bootmem_node(NODE_DATA(nid), phys, len, BOOTMEM_DEFAULT);
+	nid = phys_to_nid(phys);
+	next_nid = phys_to_nid(phys + len - 1);
+	if (nid == next_nid)
+		reserve_bootmem_node(NODE_DATA(nid), phys, len, BOOTMEM_DEFAULT);
+	else
+		reserve_bootmem(phys, len, BOOTMEM_DEFAULT);
 #else
 	reserve_bootmem(phys, len, BOOTMEM_DEFAULT);
 #endif
+
 	if (phys+len <= MAX_DMA_PFN*PAGE_SIZE) {
 		dma_reserve += len / PAGE_SIZE;
 		set_dma_reserve(dma_reserve);
@@ -926,6 +932,10 @@ const char *arch_vma_name(struct vm_area_struct *vma)
 /*
  * Initialise the sparsemem vmemmap using huge-pages at the PMD level.
  */
+static long __meminitdata addr_start, addr_end;
+static void __meminitdata *p_start, *p_end;
+static int __meminitdata node_start;
+
 int __meminit
 vmemmap_populate(struct page *start_page, unsigned long size, int node)
 {
@@ -960,12 +970,32 @@ vmemmap_populate(struct page *start_page, unsigned long size, int node)
 							PAGE_KERNEL_LARGE);
 			set_pmd(pmd, __pmd(pte_val(entry)));
 
-			printk(KERN_DEBUG " [%lx-%lx] PMD ->%p on node %d\n",
-				addr, addr + PMD_SIZE - 1, p, node);
+			/* check to see if we have contiguous blocks */
+			if (p_end != p || node_start != node) {
+				if (p_start)
+					printk(KERN_DEBUG " [%lx-%lx] PMD -> [%p-%p] on node %d\n",
+						addr_start, addr_end-1, p_start, p_end-1, node_start);
+				addr_start = addr;
+				node_start = node;
+				p_start = p;
+			}
+			addr_end = addr + PMD_SIZE;
+			p_end = p + PMD_SIZE;
 		} else {
 			vmemmap_verify((pte_t *)pmd, node, addr, next);
 		}
 	}
 	return 0;
 }
+
+void __meminit vmemmap_populate_print_last(void)
+{
+	if (p_start) {
+		printk(KERN_DEBUG " [%lx-%lx] PMD -> [%p-%p] on node %d\n",
+			addr_start, addr_end-1, p_start, p_end-1, node_start);
+		p_start = NULL;
+		p_end = NULL;
+		node_start = 0;
+	}
+}
 #endif
diff --git a/arch/x86/mm/numa_64.c b/arch/x86/mm/numa_64.c
index 9a6892200b2..c5066d519e5 100644
--- a/arch/x86/mm/numa_64.c
+++ b/arch/x86/mm/numa_64.c
@@ -196,6 +196,7 @@ void __init setup_node_bootmem(int nodeid, unsigned long start,
 	unsigned long bootmap_start, nodedata_phys;
 	void *bootmap;
 	const int pgdat_size = round_up(sizeof(pg_data_t), PAGE_SIZE);
+	int nid;
 
 	start = round_up(start, ZONE_ALIGN);
 
@@ -218,9 +219,19 @@ void __init setup_node_bootmem(int nodeid, unsigned long start,
 	NODE_DATA(nodeid)->node_start_pfn = start_pfn;
 	NODE_DATA(nodeid)->node_spanned_pages = end_pfn - start_pfn;
 
-	/* Find a place for the bootmem map */
+	/*
+	 * Find a place for the bootmem map
+	 * nodedata_phys could be on other nodes by alloc_bootmem,
+	 * so need to sure bootmap_start not to be small, otherwise
+	 * early_node_mem will get that with find_e820_area instead
+	 * of alloc_bootmem, that could clash with reserved range
+	 */
 	bootmap_pages = bootmem_bootmap_pages(end_pfn - start_pfn);
-	bootmap_start = round_up(nodedata_phys + pgdat_size, PAGE_SIZE);
+	nid = phys_to_nid(nodedata_phys);
+	if (nid == nodeid)
+		bootmap_start = round_up(nodedata_phys + pgdat_size, PAGE_SIZE);
+	else
+		bootmap_start = round_up(start, PAGE_SIZE);
 	/*
 	 * SMP_CAHCE_BYTES could be enough, but init_bootmem_node like
 	 * to use that to align to PAGE_SIZE
@@ -245,10 +256,29 @@ void __init setup_node_bootmem(int nodeid, unsigned long start,
 
 	free_bootmem_with_active_regions(nodeid, end);
 
-	reserve_bootmem_node(NODE_DATA(nodeid), nodedata_phys, pgdat_size,
-			BOOTMEM_DEFAULT);
-	reserve_bootmem_node(NODE_DATA(nodeid), bootmap_start,
-			bootmap_pages<<PAGE_SHIFT, BOOTMEM_DEFAULT);
+	/*
+	 * 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);
+
 #ifdef CONFIG_ACPI_NUMA
 	srat_reserve_add_area(nodeid);
 #endif