3 files changed, 90 insertions, 50 deletions

diff --git a/arch/powerpc/mm/40x_mmu.c b/arch/powerpc/mm/40x_mmu.c
index cecbbc76f624..29954dc28942 100644
--- a/arch/powerpc/mm/40x_mmu.c
+++ b/arch/powerpc/mm/40x_mmu.c
@@ -93,7 +93,7 @@ void __init MMU_init_hw(void)
 
 unsigned long __init mmu_mapin_ram(void)
 {
-	unsigned long v, s;
+	unsigned long v, s, mapped;
 	phys_addr_t p;
 
 	v = KERNELBASE;
@@ -130,5 +130,17 @@ unsigned long __init mmu_mapin_ram(void)
 		s -= LARGE_PAGE_SIZE_4M;
 	}
 
-	return total_lowmem - s;
+	mapped = total_lowmem - s;
+
+	/* If the size of RAM is not an exact power of two, we may not
+	 * have covered RAM in its entirety with 16 and 4 MiB
+	 * pages. Consequently, restrict the top end of RAM currently
+	 * allocable so that calls to the LMB to allocate PTEs for "tail"
+	 * coverage with normal-sized pages (or other reasons) do not
+	 * attempt to allocate outside the allowed range.
+	 */
+
+	__initial_memory_limit_addr = memstart_addr + mapped;
+
+	return mapped;
 }
diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c
index a117024ab8cd..7bbf4e4ed430 100644
--- a/arch/powerpc/mm/hugetlbpage.c
+++ b/arch/powerpc/mm/hugetlbpage.c
@@ -677,7 +677,7 @@ repeat:
 	return err;
 }
 
-void set_huge_psize(int psize)
+static void __init set_huge_psize(int psize)
 {
 	/* Check that it is a page size supported by the hardware and
 	 * that it fits within pagetable limits. */
diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c
index eb505ad34a85..a8397bbad3d4 100644
--- a/arch/powerpc/mm/numa.c
+++ b/arch/powerpc/mm/numa.c
@@ -865,6 +865,67 @@ static struct notifier_block __cpuinitdata ppc64_numa_nb = {
 	.priority = 1 /* Must run before sched domains notifier. */
 };
 
+static void mark_reserved_regions_for_nid(int nid)
+{
+	struct pglist_data *node = NODE_DATA(nid);
+	int i;
+
+	for (i = 0; i < lmb.reserved.cnt; i++) {
+		unsigned long physbase = lmb.reserved.region[i].base;
+		unsigned long size = lmb.reserved.region[i].size;
+		unsigned long start_pfn = physbase >> PAGE_SHIFT;
+		unsigned long end_pfn = ((physbase + size) >> PAGE_SHIFT);
+		struct node_active_region node_ar;
+		unsigned long node_end_pfn = node->node_start_pfn +
+					     node->node_spanned_pages;
+
+		/*
+		 * Check to make sure that this lmb.reserved area is
+		 * within the bounds of the node that we care about.
+		 * Checking the nid of the start and end points is not
+		 * sufficient because the reserved area could span the
+		 * entire node.
+		 */
+		if (end_pfn <= node->node_start_pfn ||
+		    start_pfn >= node_end_pfn)
+			continue;
+
+		get_node_active_region(start_pfn, &node_ar);
+		while (start_pfn < end_pfn &&
+			node_ar.start_pfn < node_ar.end_pfn) {
+			unsigned long reserve_size = size;
+			/*
+			 * if reserved region extends past active region
+			 * then trim size to active region
+			 */
+			if (end_pfn > node_ar.end_pfn)
+				reserve_size = (node_ar.end_pfn << PAGE_SHIFT)
+					- (start_pfn << PAGE_SHIFT);
+			dbg("reserve_bootmem %lx %lx nid=%d\n", physbase,
+				reserve_size, node_ar.nid);
+			reserve_bootmem_node(NODE_DATA(node_ar.nid), physbase,
+						reserve_size, BOOTMEM_DEFAULT);
+			/*
+			 * if reserved region is contained in the active region
+			 * then done.
+			 */
+			if (end_pfn <= node_ar.end_pfn)
+				break;
+
+			/*
+			 * reserved region extends past the active region
+			 *   get next active region that contains this
+			 *   reserved region
+			 */
+			start_pfn = node_ar.end_pfn;
+			physbase = start_pfn << PAGE_SHIFT;
+			size = size - reserve_size;
+			get_node_active_region(start_pfn, &node_ar);
+		}
+	}
+}
+
+
 void __init do_init_bootmem(void)
 {
 	int nid;
@@ -890,7 +951,13 @@ void __init do_init_bootmem(void)
 
 		get_pfn_range_for_nid(nid, &start_pfn, &end_pfn);
 
-		/* Allocate the node structure node local if possible */
+		/*
+		 * Allocate the node structure node local if possible
+		 *
+		 * Be careful moving this around, as it relies on all
+		 * previous nodes' bootmem to be initialized and have
+		 * all reserved areas marked.
+		 */
 		NODE_DATA(nid) = careful_allocation(nid,
 					sizeof(struct pglist_data),
 					SMP_CACHE_BYTES, end_pfn);
@@ -922,53 +989,14 @@ void __init do_init_bootmem(void)
 				  start_pfn, end_pfn);
 
 		free_bootmem_with_active_regions(nid, end_pfn);
-	}
-
-	/* Mark reserved regions */
-	for (i = 0; i < lmb.reserved.cnt; i++) {
-		unsigned long physbase = lmb.reserved.region[i].base;
-		unsigned long size = lmb.reserved.region[i].size;
-		unsigned long start_pfn = physbase >> PAGE_SHIFT;
-		unsigned long end_pfn = ((physbase + size) >> PAGE_SHIFT);
-		struct node_active_region node_ar;
-
-		get_node_active_region(start_pfn, &node_ar);
-		while (start_pfn < end_pfn &&
-			node_ar.start_pfn < node_ar.end_pfn) {
-			unsigned long reserve_size = size;
-			/*
-			 * if reserved region extends past active region
-			 * then trim size to active region
-			 */
-			if (end_pfn > node_ar.end_pfn)
-				reserve_size = (node_ar.end_pfn << PAGE_SHIFT)
-					- (start_pfn << PAGE_SHIFT);
-			dbg("reserve_bootmem %lx %lx nid=%d\n", physbase,
-				reserve_size, node_ar.nid);
-			reserve_bootmem_node(NODE_DATA(node_ar.nid), physbase,
-						reserve_size, BOOTMEM_DEFAULT);
-			/*
-			 * if reserved region is contained in the active region
-			 * then done.
-			 */
-			if (end_pfn <= node_ar.end_pfn)
-				break;
-
-			/*
-			 * reserved region extends past the active region
-			 *   get next active region that contains this
-			 *   reserved region
-			 */
-			start_pfn = node_ar.end_pfn;
-			physbase = start_pfn << PAGE_SHIFT;
-			size = size - reserve_size;
-			get_node_active_region(start_pfn, &node_ar);
-		}
-
-	}
-
-	for_each_online_node(nid)
+		/*
+		 * Be very careful about moving this around.  Future
+		 * calls to careful_allocation() depend on this getting
+		 * done correctly.
+		 */
+		mark_reserved_regions_for_nid(nid);
 		sparse_memory_present_with_active_regions(nid);
+	}
 }
 
 void __init paging_init(void)