generic changes for memblock

index db59349..afd6494 100644
@@ -77,8 +77,8 @@ void __init setup_memory(void)
 
 	/* Find main memory where is the kernel */
 	for (i = 0; i < memblock.memory.cnt; i++) {
-		memory_start = (u32) memblock.memory.region[i].base;
-		memory_end = (u32) memblock.memory.region[i].base
+		memory_start = (u32) memblock.memory.regions[i].base;
+		memory_end = (u32) memblock.memory.regions[i].base
 				+ (u32) memblock.memory.region[i].size;
 		if ((memory_start <= (u32)_text) &&
 					((u32)_text <= memory_end)) {

index 98f262d..dbaacb7 100644
@@ -660,7 +660,7 @@ static void __init htab_initialize(void)
 
 	/* create bolted the linear mapping in the hash table */
 	for (i=0; i < memblock.memory.cnt; i++) {
-		base = (unsigned long)__va(memblock.memory.region[i].base);
+		base = (unsigned long)__va(memblock.memory.regions[i].base);
 		size = memblock.memory.region[i].size;
 
 		DBG("creating mapping for region: %lx..%lx (prot: %lx)\n",

index 1a84a8d..a33f5c1 100644
@@ -86,10 +86,10 @@ int page_is_ram(unsigned long pfn)
 	for (i=0; i < memblock.memory.cnt; i++) {
 		unsigned long base;
 
-		base = memblock.memory.region[i].base;
+		base = memblock.memory.regions[i].base;
 
 		if ((paddr >= base) &&
-			(paddr < (base + memblock.memory.region[i].size))) {
+			(paddr < (base + memblock.memory.regions[i].size))) {
 			return 1;
 		}
 	}

@@ -149,7 +149,7 @@ int
 walk_system_ram_range(unsigned long start_pfn, unsigned long nr_pages,
 		void *arg, int (*func)(unsigned long, unsigned long, void *))
 {
-	struct memblock_property res;
+	struct memblock_region res;
 	unsigned long pfn, len;
 	u64 end;
 	int ret = -1;

@@ -206,7 +206,7 @@ void __init do_init_bootmem(void)
 	/* Add active regions with valid PFNs */
 	for (i = 0; i < memblock.memory.cnt; i++) {
 		unsigned long start_pfn, end_pfn;
-		start_pfn = memblock.memory.region[i].base >> PAGE_SHIFT;
+		start_pfn = memblock.memory.regions[i].base >> PAGE_SHIFT;
 		end_pfn = start_pfn + memblock_size_pages(&memblock.memory, i);
 		add_active_range(0, start_pfn, end_pfn);
 	}

@@ -219,16 +219,16 @@ void __init do_init_bootmem(void)
 
 	/* reserve the sections we're already using */
 	for (i = 0; i < memblock.reserved.cnt; i++) {
-		unsigned long addr = memblock.reserved.region[i].base +
+		unsigned long addr = memblock.reserved.regions[i].base +
 				     memblock_size_bytes(&memblock.reserved, i) - 1;
 		if (addr < lowmem_end_addr)
-			reserve_bootmem(memblock.reserved.region[i].base,
+			reserve_bootmem(memblock.reserved.regions[i].base,
 					memblock_size_bytes(&memblock.reserved, i),
 					BOOTMEM_DEFAULT);
-		else if (memblock.reserved.region[i].base < lowmem_end_addr) {
+		else if (memblock.reserved.regions[i].base < lowmem_end_addr) {
 			unsigned long adjusted_size = lowmem_end_addr -
-				      memblock.reserved.region[i].base;
-			reserve_bootmem(memblock.reserved.region[i].base,
+				      memblock.reserved.regions[i].base;
+			reserve_bootmem(memblock.reserved.regions[i].base,
 					adjusted_size, BOOTMEM_DEFAULT);
 		}
 	}

@@ -237,7 +237,7 @@ void __init do_init_bootmem(void)
 
 	/* reserve the sections we're already using */
 	for (i = 0; i < memblock.reserved.cnt; i++)
-		reserve_bootmem(memblock.reserved.region[i].base,
+		reserve_bootmem(memblock.reserved.regions[i].base,
 				memblock_size_bytes(&memblock.reserved, i),
 				BOOTMEM_DEFAULT);
 

@@ -257,10 +257,10 @@ static int __init mark_nonram_nosave(void)
 
 	for (i = 0; i < memblock.memory.cnt - 1; i++) {
 		memblock_region_max_pfn =
-			(memblock.memory.region[i].base >> PAGE_SHIFT) +
-			(memblock.memory.region[i].size >> PAGE_SHIFT);
+			(memblock.memory.regions[i].base >> PAGE_SHIFT) +
+			(memblock.memory.regions[i].size >> PAGE_SHIFT);
 		memblock_next_region_start_pfn =
-			memblock.memory.region[i+1].base >> PAGE_SHIFT;
+			memblock.memory.regions[i+1].base >> PAGE_SHIFT;
 
 		if (memblock_region_max_pfn < memblock_next_region_start_pfn)
 			register_nosave_region(memblock_region_max_pfn,

index 5cdcc7c..8450c29 100644
@@ -65,7 +65,7 @@ static int __init page_aligned(unsigned long x)
 
 void __init wii_memory_fixups(void)
 {
-	struct memblock_property *p = memblock.memory.region;
+	struct memblock_region *p = memblock.memory.region;
 
 	/*
 	 * This is part of a workaround to allow the use of two

index f043451..16d8bee 100644
@@ -978,7 +978,7 @@ static void __init add_node_ranges(void)
 		unsigned long size = memblock_size_bytes(&memblock.memory, i);
 		unsigned long start, end;
 
-		start = memblock.memory.region[i].base;
+		start = memblock.memory.regions[i].base;
 		end = start + size;
 		while (start < end) {
 			unsigned long this_end;

@@ -1299,7 +1299,7 @@ static void __init bootmem_init_nonnuma(void)
 		if (!size)
 			continue;
 
-		start_pfn = memblock.memory.region[i].base >> PAGE_SHIFT;
+		start_pfn = memblock.memory.regions[i].base >> PAGE_SHIFT;
 		end_pfn = start_pfn + memblock_size_pages(&memblock.memory, i);
 		add_active_range(0, start_pfn, end_pfn);
 	}

@@ -1339,7 +1339,7 @@ static void __init trim_reserved_in_node(int nid)
 	numadbg("  trim_reserved_in_node(%d)\n", nid);
 
 	for (i = 0; i < memblock.reserved.cnt; i++) {
-		unsigned long start = memblock.reserved.region[i].base;
+		unsigned long start = memblock.reserved.regions[i].base;
 		unsigned long size = memblock_size_bytes(&memblock.reserved, i);
 		unsigned long end = start + size;
 

index a59faf2..86e7daf 100644
@@ -18,22 +18,22 @@
 
 #define MAX_MEMBLOCK_REGIONS 128
 
-struct memblock_property {
+struct memblock_region {
 	u64 base;
 	u64 size;
 };
 
-struct memblock_region {
+struct memblock_type {
 	unsigned long cnt;
 	u64 size;
-	struct memblock_property region[MAX_MEMBLOCK_REGIONS+1];
+	struct memblock_region regions[MAX_MEMBLOCK_REGIONS+1];
 };
 
 struct memblock {
 	unsigned long debug;
 	u64 rmo_size;
-	struct memblock_region memory;
-	struct memblock_region reserved;
+	struct memblock_type memory;
+	struct memblock_type reserved;
 };
 
 extern struct memblock memblock;

@@ -56,27 +56,27 @@ extern u64 memblock_end_of_DRAM(void);
 extern void __init memblock_enforce_memory_limit(u64 memory_limit);
 extern int __init memblock_is_reserved(u64 addr);
 extern int memblock_is_region_reserved(u64 base, u64 size);
-extern int memblock_find(struct memblock_property *res);
+extern int memblock_find(struct memblock_region *res);
 
 extern void memblock_dump_all(void);
 
 static inline u64
-memblock_size_bytes(struct memblock_region *type, unsigned long region_nr)
+memblock_size_bytes(struct memblock_type *type, unsigned long region_nr)
 {
-	return type->region[region_nr].size;
+	return type->regions[region_nr].size;
 }
 static inline u64
-memblock_size_pages(struct memblock_region *type, unsigned long region_nr)
+memblock_size_pages(struct memblock_type *type, unsigned long region_nr)
 {
 	return memblock_size_bytes(type, region_nr) >> PAGE_SHIFT;
 }
 static inline u64
-memblock_start_pfn(struct memblock_region *type, unsigned long region_nr)
+memblock_start_pfn(struct memblock_type *type, unsigned long region_nr)
 {
-	return type->region[region_nr].base >> PAGE_SHIFT;
+	return type->regions[region_nr].base >> PAGE_SHIFT;
 }
 static inline u64
-memblock_end_pfn(struct memblock_region *type, unsigned long region_nr)
+memblock_end_pfn(struct memblock_type *type, unsigned long region_nr)
 {
 	return memblock_start_pfn(type, region_nr) +
 	       memblock_size_pages(type, region_nr);

402 lines not on this page · raw message

index 86e7daf..4b69313 100644
@@ -16,6 +16,8 @@
 #include <linux/init.h>
 #include <linux/mm.h>
 
+#include <asm/memblock.h>
+
 #define MAX_MEMBLOCK_REGIONS 128
 
 struct memblock_region {

@@ -82,8 +84,6 @@ memblock_end_pfn(struct memblock_type *type, unsigned long region_nr)
 	       memblock_size_pages(type, region_nr);
 }
 
-#include <asm/memblock.h>
-
 #endif /* __KERNEL__ */
 
 #endif /* _LINUX_MEMBLOCK_H */

index afd6494..8f45b41 100644
@@ -70,16 +70,16 @@ static void __init paging_init(void)
 
 void __init setup_memory(void)
 {
-	int i;
 	unsigned long map_size;
+	struct memblock_region *reg;
+
 #ifndef CONFIG_MMU
 	u32 kernel_align_start, kernel_align_size;
 
 	/* Find main memory where is the kernel */
-	for (i = 0; i < memblock.memory.cnt; i++) {
-		memory_start = (u32) memblock.memory.regions[i].base;
-		memory_end = (u32) memblock.memory.regions[i].base
-				+ (u32) memblock.memory.region[i].size;
+	for_each_memblock(memory, reg) {
+		memory_start = (u32)reg->base;
+		memory_end = (u32) reg->base + reg->size;
 		if ((memory_start <= (u32)_text) &&
 					((u32)_text <= memory_end)) {
 			memory_size = memory_end - memory_start;

@@ -147,12 +147,10 @@ void __init setup_memory(void)
 	free_bootmem(memory_start, memory_size);
 
 	/* reserve allocate blocks */
-	for (i = 0; i < memblock.reserved.cnt; i++) {
+	for_each_memblock(reserved, reg) {
 		pr_debug("reserved %d - 0x%08x-0x%08x\n", i,
-			(u32) memblock.reserved.region[i].base,
-			(u32) memblock_size_bytes(&memblock.reserved, i));
-		reserve_bootmem(memblock.reserved.region[i].base,
-			memblock_size_bytes(&memblock.reserved, i) - 1, BOOTMEM_DEFAULT);
+			 (u32) reg->base, (u32) reg->size);
+		reserve_bootmem(reg->base, reg->size, BOOTMEM_DEFAULT);
 	}
 #ifdef CONFIG_MMU
 	init_bootmem_done = 1;

index dbaacb7..2b0a807 100644
@@ -588,7 +588,7 @@ static void __init htab_initialize(void)
 	unsigned long pteg_count;
 	unsigned long prot;
 	unsigned long base = 0, size = 0, limit;
-	int i;
+	struct memblock_region *reg;
 
 	DBG(" -> htab_initialize()\n");
 

@@ -659,9 +659,9 @@ static void __init htab_initialize(void)
 	 */
 
 	/* create bolted the linear mapping in the hash table */
-	for (i=0; i < memblock.memory.cnt; i++) {
-		base = (unsigned long)__va(memblock.memory.regions[i].base);
-		size = memblock.memory.region[i].size;
+	for_each_memblock(memory, reg) {
+		base = (unsigned long)__va(reg->base);
+		size = reg->size;
 
 		DBG("creating mapping for region: %lx..%lx (prot: %lx)\n",
 		    base, size, prot);

144 lines not on this page · raw message

index f473645..9eaaf22 100644
@@ -746,16 +746,17 @@ static void __init setup_nonnuma(void)
 	unsigned long top_of_ram = memblock_end_of_DRAM();
 	unsigned long total_ram = memblock_phys_mem_size();
 	unsigned long start_pfn, end_pfn;
-	unsigned int i, nid = 0;
+	unsigned int nid = 0;
+	struct memblock_region *reg;
 
 	printk(KERN_DEBUG "Top of RAM: 0x%lx, Total RAM: 0x%lx\n",
 	       top_of_ram, total_ram);
 	printk(KERN_DEBUG "Memory hole size: %ldMB\n",
 	       (top_of_ram - total_ram) >> 20);
 
-	for (i = 0; i < memblock.memory.cnt; ++i) {
-		start_pfn = memblock.memory.region[i].base >> PAGE_SHIFT;
-		end_pfn = start_pfn + memblock_size_pages(&memblock.memory, i);
+	for_each_memblock(memory, reg) {
+		start_pfn = memblock_region_base_pfn(reg);
+		end_pfn = memblock_region_end_pfn(reg);
 
 		fake_numa_create_new_node(end_pfn, &nid);
 		add_active_range(nid, start_pfn, end_pfn);

@@ -891,11 +892,11 @@ static struct notifier_block __cpuinitdata ppc64_numa_nb = {
 static void mark_reserved_regions_for_nid(int nid)
 {
 	struct pglist_data *node = NODE_DATA(nid);
-	int i;
+	struct memblock_region *reg;
 
-	for (i = 0; i < memblock.reserved.cnt; i++) {
-		unsigned long physbase = memblock.reserved.region[i].base;
-		unsigned long size = memblock.reserved.region[i].size;
+	for_each_memblock(reserved, reg) {
+		unsigned long physbase = reg->base;
+		unsigned long size = reg->size;
 		unsigned long start_pfn = physbase >> PAGE_SHIFT;
 		unsigned long end_pfn = PFN_UP(physbase + size);
 		struct node_active_region node_ar;

index d0e2491..da1605a 100644
@@ -226,11 +226,12 @@ static void __init bootmem_init_one_node(unsigned int nid)
 	 * reservations in other nodes.
 	 */
 	if (nid == 0) {
+		struct memblock_region *reg;
+
 		/* Reserve the sections we're already using. */
-		for (i = 0; i < memblock.reserved.cnt; i++)
-			reserve_bootmem(memblock.reserved.region[i].base,
-					memblock_size_bytes(&memblock.reserved, i),
-					BOOTMEM_DEFAULT);
+		for_each_memblock(reserved, reg) {
+			reserve_bootmem(reg->base, reg->size, BOOTMEM_DEFAULT);
+		}
 	}
 
 	sparse_memory_present_with_active_regions(nid);

@@ -238,13 +239,14 @@ static void __init bootmem_init_one_node(unsigned int nid)
 
 static void __init do_init_bootmem(void)
 {
+	struct memblock_region *reg;
 	int i;
 
 	/* Add active regions with valid PFNs. */
-	for (i = 0; i < memblock.memory.cnt; i++) {
+	for_each_memblock(memory, reg) {
 		unsigned long start_pfn, end_pfn;
-		start_pfn = memblock.memory.region[i].base >> PAGE_SHIFT;
-		end_pfn = start_pfn + memblock_size_pages(&memblock.memory, i);
+		start_pfn = memblock_region_base_pfn(reg);
+		end_pfn = memblock_region_end_pfn(reg);
 		__add_active_range(0, start_pfn, end_pfn);
 	}
 

index 16d8bee..dd68025 100644
@@ -972,13 +972,13 @@ int of_node_to_nid(struct device_node *dp)
 
 static void __init add_node_ranges(void)
 {
-	int i;
+	struct memblock_region *reg;
 
-	for (i = 0; i < memblock.memory.cnt; i++) {
-		unsigned long size = memblock_size_bytes(&memblock.memory, i);
+	for_each_memblock(memory, reg) {
+		unsigned long size = reg->size;
 		unsigned long start, end;
 
-		start = memblock.memory.regions[i].base;
+		start = reg->base;
 		end = start + size;
 		while (start < end) {
 			unsigned long this_end;

@@ -1281,7 +1281,7 @@ static void __init bootmem_init_nonnuma(void)
 {
 	unsigned long top_of_ram = memblock_end_of_DRAM();
 	unsigned long total_ram = memblock_phys_mem_size();
-	unsigned int i;
+	struct memblock_region *reg;
 
 	numadbg("bootmem_init_nonnuma()\n");
 

@@ -1292,15 +1292,14 @@ static void __init bootmem_init_nonnuma(void)
 
 	init_node_masks_nonnuma();
 
-	for (i = 0; i < memblock.memory.cnt; i++) {
-		unsigned long size = memblock_size_bytes(&memblock.memory, i);
+	for_each_memblock(memory, reg) {
 		unsigned long start_pfn, end_pfn;
 
-		if (!size)
+		if (!reg->size)
 			continue;
 
-		start_pfn = memblock.memory.regions[i].base >> PAGE_SHIFT;
-		end_pfn = start_pfn + memblock_size_pages(&memblock.memory, i);
+		start_pfn = memblock_region_base_pfn(reg);
+		end_pfn = memblock_region_end_pfn(reg);
 		add_active_range(0, start_pfn, end_pfn);
 	}
 

@@ -1334,17 +1333,12 @@ static void __init reserve_range_in_node(int nid, unsigned long start,
 
 static void __init trim_reserved_in_node(int nid)
 {
-	int i;
+	struct memblock_region *reg;
 
 	numadbg("  trim_reserved_in_node(%d)\n", nid);
 
-	for (i = 0; i < memblock.reserved.cnt; i++) {
-		unsigned long start = memblock.reserved.regions[i].base;
-		unsigned long size = memblock_size_bytes(&memblock.reserved, i);
-		unsigned long end = start + size;
-
-		reserve_range_in_node(nid, start, end);
-	}
+	for_each_memblock(reserved, reg)
+		reserve_range_in_node(nid, reg->base, reg->base + reg->size);
 }
 
 static void __init bootmem_init_one_node(int nid)

74 lines not on this page · raw message

index 13d4a57..5df1400 100644
@@ -505,35 +505,3 @@ int memblock_is_region_reserved(u64 base, u64 size)
 	return memblock_overlaps_region(&memblock.reserved, base, size);
 }
 
-/*
- * Given a <base, len>, find which memory regions belong to this range.
- * Adjust the request and return a contiguous chunk.
- */
-int memblock_find(struct memblock_region *res)
-{
-	int i;
-	u64 rstart, rend;
-
-	rstart = res->base;
-	rend = rstart + res->size - 1;
-
-	for (i = 0; i < memblock.memory.cnt; i++) {
-		u64 start = memblock.memory.regions[i].base;
-		u64 end = start + memblock.memory.regions[i].size - 1;
-
-		if (start > rend)
-			return -1;
-
-		if ((end >= rstart) && (start < rend)) {
-			/* adjust the request */
-			if (rstart < start)
-				rstart = start;
-			if (rend > end)
-				rend = end;
-			res->base = rstart;
-			res->size = rend - rstart + 1;
-			return 0;
-		}
-	}
-	return -1;
-}

index dd68025..0883113 100644
@@ -785,8 +785,7 @@ static int find_node(unsigned long addr)
 	return -1;
 }
 
-static unsigned long long nid_range(unsigned long long start,
-				    unsigned long long end, int *nid)
+u64 memblock_nid_range(u64 start, u64 end, int *nid)
 {
 	*nid = find_node(start);
 	start += PAGE_SIZE;

@@ -804,8 +803,7 @@ static unsigned long long nid_range(unsigned long long start,
 	return start;
 }
 #else
-static unsigned long long nid_range(unsigned long long start,
-				    unsigned long long end, int *nid)
+u64 memblock_nid_range(u64 start, u64 end, int *nid)
 {
 	*nid = 0;
 	return end;

@@ -822,8 +820,7 @@ static void __init allocate_node_data(int nid)
 	struct pglist_data *p;
 
 #ifdef CONFIG_NEED_MULTIPLE_NODES
-	paddr = memblock_alloc_nid(sizeof(struct pglist_data),
-			      SMP_CACHE_BYTES, nid, nid_range);
+	paddr = memblock_alloc_nid(sizeof(struct pglist_data), SMP_CACHE_BYTES, nid);
 	if (!paddr) {
 		prom_printf("Cannot allocate pglist_data for nid[%d]\n", nid);
 		prom_halt();

@@ -843,8 +840,7 @@ static void __init allocate_node_data(int nid)
 	if (p->node_spanned_pages) {
 		num_pages = bootmem_bootmap_pages(p->node_spanned_pages);
 
-		paddr = memblock_alloc_nid(num_pages << PAGE_SHIFT, PAGE_SIZE, nid,
-				      nid_range);
+		paddr = memblock_alloc_nid(num_pages << PAGE_SHIFT, PAGE_SIZE, nid);
 		if (!paddr) {
 			prom_printf("Cannot allocate bootmap for nid[%d]\n",
 				  nid);

@@ -984,7 +980,7 @@ static void __init add_node_ranges(void)
 			unsigned long this_end;
 			int nid;
 
-			this_end = nid_range(start, end, &nid);
+			this_end = memblock_nid_range(start, end, &nid);
 
 			numadbg("Adding active range nid[%d] "
 				"start[%lx] end[%lx]\n",

@@ -1317,7 +1313,7 @@ static void __init reserve_range_in_node(int nid, unsigned long start,
 		unsigned long this_end;
 		int n;
 
-		this_end = nid_range(start, end, &n);
+		this_end = memblock_nid_range(start, end, &n);
 		if (n == nid) {
 			numadbg("      MATCH reserving range [%lx:%lx]\n",
 				start, this_end);

index d948857..3e4a52f 100644
@@ -46,8 +46,7 @@ extern long memblock_add(u64 base, u64 size);
 extern long memblock_remove(u64 base, u64 size);
 extern long __init memblock_free(u64 base, u64 size);
 extern long __init memblock_reserve(u64 base, u64 size);
-extern u64 __init memblock_alloc_nid(u64 size, u64 align, int nid,
-				u64 (*nid_range)(u64, u64, int *));
+extern u64 __init memblock_alloc_nid(u64 size, u64 align, int nid);
 extern u64 __init memblock_alloc(u64 size, u64 align);
 extern u64 __init memblock_alloc_base(u64 size,
 		u64, u64 max_addr);

@@ -61,6 +60,10 @@ extern int memblock_is_region_reserved(u64 base, u64 size);
 
 extern void memblock_dump_all(void);
 
+/* Provided by the architecture */
+extern u64 memblock_nid_range(u64 start, u64 end, int *nid);
+
+
 /*
  * pfn conversion functions
  *

index 5df1400..83643f3 100644
@@ -319,7 +319,6 @@ static u64 __init memblock_alloc_nid_unreserved(u64 start, u64 end,
 }
 
 static u64 __init memblock_alloc_nid_region(struct memblock_region *mp,
-				       u64 (*nid_range)(u64, u64, int *),
 				       u64 size, u64 align, int nid)
 {
 	u64 start, end;

@@ -332,7 +331,7 @@ static u64 __init memblock_alloc_nid_region(struct memblock_region *mp,
 		u64 this_end;
 		int this_nid;
 
-		this_end = nid_range(start, end, &this_nid);
+		this_end = memblock_nid_range(start, end, &this_nid);
 		if (this_nid == nid) {
 			u64 ret = memblock_alloc_nid_unreserved(start, this_end,
 							   size, align);

@@ -345,8 +344,7 @@ static u64 __init memblock_alloc_nid_region(struct memblock_region *mp,
 	return ~(u64)0;
 }
 
-u64 __init memblock_alloc_nid(u64 size, u64 align, int nid,
-			 u64 (*nid_range)(u64 start, u64 end, int *nid))
+u64 __init memblock_alloc_nid(u64 size, u64 align, int nid)
 {
 	struct memblock_type *mem = &memblock.memory;
 	int i;

@@ -357,7 +355,6 @@ u64 __init memblock_alloc_nid(u64 size, u64 align, int nid,
 
 	for (i = 0; i < mem->cnt; i++) {
 		u64 ret = memblock_alloc_nid_region(&mem->regions[i],
-					       nid_range,
 					       size, align, nid);
 		if (ret != ~(u64)0)
 			return ret;

@@ -505,3 +502,9 @@ int memblock_is_region_reserved(u64 base, u64 size)
 	return memblock_overlaps_region(&memblock.reserved, base, size);
 }
 
+u64 __weak memblock_nid_range(u64 start, u64 end, int *nid)
+{
+	*nid = 0;
+
+	return end;
+}

index 83643f3..9b71de0 100644
@@ -294,8 +294,8 @@ static u64 memblock_align_up(u64 addr, u64 size)
 	return (addr + (size - 1)) & ~(size - 1);
 }
 
-static u64 __init memblock_alloc_nid_unreserved(u64 start, u64 end,
-					   u64 size, u64 align)
+static u64 __init memblock_alloc_region(u64 start, u64 end,
+				   u64 size, u64 align)
 {
 	u64 base, res_base;
 	long j;

@@ -318,6 +318,13 @@ static u64 __init memblock_alloc_nid_unreserved(u64 start, u64 end,
 	return ~(u64)0;
 }
 
+u64 __weak __init memblock_nid_range(u64 start, u64 end, int *nid)
+{
+	*nid = 0;
+
+	return end;
+}
+
 static u64 __init memblock_alloc_nid_region(struct memblock_region *mp,
 				       u64 size, u64 align, int nid)
 {

@@ -333,8 +340,7 @@ static u64 __init memblock_alloc_nid_region(struct memblock_region *mp,
 
 		this_end = memblock_nid_range(start, end, &this_nid);
 		if (this_nid == nid) {
-			u64 ret = memblock_alloc_nid_unreserved(start, this_end,
-							   size, align);
+			u64 ret = memblock_alloc_region(start, this_end, size, align);
 			if (ret != ~(u64)0)
 				return ret;
 		}

@@ -351,6 +357,10 @@ u64 __init memblock_alloc_nid(u64 size, u64 align, int nid)
 
 	BUG_ON(0 == size);
 
+	/* We do a bottom-up search for a region with the right
+	 * nid since that's easier considering how memblock_nid_range()
+	 * works
+	 */
 	size = memblock_align_up(size, align);
 
 	for (i = 0; i < mem->cnt; i++) {

@@ -383,7 +393,7 @@ u64 __init memblock_alloc_base(u64 size, u64 align, u64 max_addr)
 
 u64 __init __memblock_alloc_base(u64 size, u64 align, u64 max_addr)
 {
-	long i, j;
+	long i;
 	u64 base = 0;
 	u64 res_base;
 

@@ -396,33 +406,24 @@ u64 __init __memblock_alloc_base(u64 size, u64 align, u64 max_addr)
 	if (max_addr == MEMBLOCK_ALLOC_ANYWHERE)
 		max_addr = MEMBLOCK_REAL_LIMIT;
 
+	/* Pump up max_addr */
+	if (max_addr == MEMBLOCK_ALLOC_ANYWHERE)
+		max_addr = ~(u64)0;
+
+	/* We do a top-down search, this tends to limit memory
+	 * fragmentation by keeping early boot allocs near the
+	 * top of memory
+	 */
 	for (i = memblock.memory.cnt - 1; i >= 0; i--) {
 		u64 memblockbase = memblock.memory.regions[i].base;
 		u64 memblocksize = memblock.memory.regions[i].size;
 
 		if (memblocksize < size)
 			continue;
-		if (max_addr == MEMBLOCK_ALLOC_ANYWHERE)
-			base = memblock_align_down(memblockbase + memblocksize - size, align);
-		else if (memblockbase < max_addr) {
-			base = min(memblockbase + memblocksize, max_addr);
-			base = memblock_align_down(base - size, align);
-		} else
-			continue;
-
-		while (base && memblockbase <= base) {
-			j = memblock_overlaps_region(&memblock.reserved, base, size);
-			if (j < 0) {
-				/* this area isn't reserved, take it */
-				if (memblock_add_region(&memblock.reserved, base, size) < 0)
-					return 0;
-				return base;
-			}
-			res_base = memblock.reserved.regions[j].base;
-			if (res_base < size)
-				break;
-			base = memblock_align_down(res_base - size, align);
-		}
+		base = min(memblockbase + memblocksize, max_addr);
+		res_base = memblock_alloc_region(memblockbase, base, size, align);
+		if (res_base != ~(u64)0)
+			return res_base;
 	}
 	return 0;
 }

@@ -502,9 +503,3 @@ int memblock_is_region_reserved(u64 base, u64 size)
 	return memblock_overlaps_region(&memblock.reserved, base, size);
 }
 
-u64 __weak memblock_nid_range(u64 start, u64 end, int *nid)
-{
-	*nid = 0;
-
-	return end;
-}

index 2b0a807..c630b4f 100644
@@ -625,7 +625,7 @@ static void __init htab_initialize(void)
 		if (machine_is(cell))
 			limit = 0x80000000;
 		else
-			limit = 0;
+			limit = MEMBLOCK_ALLOC_ANYWHERE;
 
 		table = memblock_alloc_base(htab_size_bytes, htab_size_bytes, limit);
 

index 3e4a52f..5853752 100644
@@ -50,6 +50,7 @@ extern u64 __init memblock_alloc_nid(u64 size, u64 align, int nid);
 extern u64 __init memblock_alloc(u64 size, u64 align);
 extern u64 __init memblock_alloc_base(u64 size,
 		u64, u64 max_addr);
+#define MEMBLOCK_ALLOC_ANYWHERE	0
 extern u64 __init __memblock_alloc_base(u64 size,
 		u64 align, u64 max_addr);
 extern u64 __init memblock_phys_mem_size(void);

index 9b71de0..0ad7626 100644
@@ -15,8 +15,6 @@
 #include <linux/bitops.h>
 #include <linux/memblock.h>
 
-#define MEMBLOCK_ALLOC_ANYWHERE	0
-
 struct memblock memblock;
 
 static int memblock_debug;

index f9c2fa3..20a8e25 100644
@@ -9,9 +9,6 @@
 #ifndef _ASM_MICROBLAZE_MEMBLOCK_H
 #define _ASM_MICROBLAZE_MEMBLOCK_H
 
-/* MEMBLOCK limit is OFF */
-#define MEMBLOCK_REAL_LIMIT	0xFFFFFFFF
-
 #endif /* _ASM_MICROBLAZE_MEMBLOCK_H */
 
 

index 3c29728..43efc34 100644
@@ -5,11 +5,4 @@
 
 #define MEMBLOCK_DBG(fmt...) udbg_printf(fmt)
 
-#ifdef CONFIG_PPC32
-extern phys_addr_t lowmem_end_addr;
-#define MEMBLOCK_REAL_LIMIT	lowmem_end_addr
-#else
-#define MEMBLOCK_REAL_LIMIT	0
-#endif
-
 #endif /* _ASM_POWERPC_MEMBLOCK_H */

index 9d39539..f665d1b 100644
@@ -98,7 +98,7 @@ static void __init move_device_tree(void)
 
 	if ((memory_limit && (start + size) > memory_limit) ||
 			overlaps_crashkernel(start, size)) {
-		p = __va(memblock_alloc_base(size, PAGE_SIZE, memblock.rmo_size));
+		p = __va(memblock_alloc(size, PAGE_SIZE));
 		memcpy(p, initial_boot_params, size);
 		initial_boot_params = (struct boot_param_header *)p;
 		DBG("Moved device tree to 0x%p\n", p);

@@ -655,6 +655,21 @@ static void __init phyp_dump_reserve_mem(void)
 static inline void __init phyp_dump_reserve_mem(void) {}
 #endif /* CONFIG_PHYP_DUMP  && CONFIG_PPC_RTAS */
 
+static void set_boot_memory_limit(void)
+{
+#ifdef CONFIG_PPC32
+	/* 601 can only access 16MB at the moment */
+	if (PVR_VER(mfspr(SPRN_PVR)) == 1)
+		memblock_set_current_limit(0x01000000);
+	/* 8xx can only access 8MB at the moment */
+	else if (PVR_VER(mfspr(SPRN_PVR)) == 0x50)
+		memblock_set_current_limit(0x00800000);
+	else
+		memblock_set_current_limit(0x10000000);
+#else
+	memblock_set_current_limit(memblock.rmo_size);
+#endif
+}
 
 void __init early_init_devtree(void *params)
 {

@@ -683,6 +698,7 @@ void __init early_init_devtree(void *params)
 
 	/* Scan memory nodes and rebuild MEMBLOCKs */
 	memblock_init();
+
 	of_scan_flat_dt(early_init_dt_scan_root, NULL);
 	of_scan_flat_dt(early_init_dt_scan_memory_ppc, NULL);
 

@@ -718,6 +734,8 @@ void __init early_init_devtree(void *params)
 
 	DBG("Phys. mem: %llx\n", memblock_phys_mem_size());
 
+	set_boot_memory_limit();
+
 	/* We may need to relocate the flat tree, do it now.
 	 * FIXME .. and the initrd too? */
 	move_device_tree();

index a10ffc8..b7eb1de 100644
@@ -246,7 +246,7 @@ static void __init irqstack_early_init(void)
 	unsigned int i;
 
 	/* interrupt stacks must be in lowmem, we get that for free on ppc32
-	 * as the memblock is limited to lowmem by MEMBLOCK_REAL_LIMIT */
+	 * as the memblock is limited to lowmem by default */
 	for_each_possible_cpu(i) {
 		softirq_ctx[i] = (struct thread_info *)
 			__va(memblock_alloc(THREAD_SIZE, THREAD_SIZE));

index 1dc2fa5..58969b5 100644
@@ -35,6 +35,7 @@
 #include <linux/init.h>
 #include <linux/delay.h>
 #include <linux/highmem.h>
+#include <linux/memblock.h>
 
 #include <asm/pgalloc.h>
 #include <asm/prom.h>

@@ -47,6 +48,7 @@
 #include <asm/bootx.h>
 #include <asm/machdep.h>
 #include <asm/setup.h>
+
 #include "mmu_decl.h"
 
 extern int __map_without_ltlbs;

@@ -139,8 +141,7 @@ unsigned long __init mmu_mapin_ram(unsigned long top)
 	 * coverage with normal-sized pages (or other reasons) do not
 	 * attempt to allocate outside the allowed range.
 	 */
-
-	__initial_memory_limit_addr = memstart_addr + mapped;
+	memblock_set_current_limit(memstart_addr + mapped);
 
 	return mapped;
 }

index cdc7526..e525f86 100644
@@ -40,6 +40,7 @@
 #include <linux/init.h>
 #include <linux/delay.h>
 #include <linux/highmem.h>
+#include <linux/memblock.h>
 
 #include <asm/pgalloc.h>
 #include <asm/prom.h>

@@ -212,5 +213,5 @@ void __init adjust_total_lowmem(void)
 	pr_cont("%lu Mb, residual: %dMb\n", tlbcam_sz(tlbcam_index - 1) >> 20,
 	        (unsigned int)((total_lowmem - __max_low_memory) >> 20));
 
-	__initial_memory_limit_addr = memstart_addr + __max_low_memory;
+	memblock_set_current_limit(memstart_addr + __max_low_memory);
 }

index c630b4f..79f9445 100644
@@ -696,7 +696,8 @@ static void __init htab_initialize(void)
 #endif /* CONFIG_U3_DART */
 		BUG_ON(htab_bolt_mapping(base, base + size, __pa(base),
 				prot, mmu_linear_psize, mmu_kernel_ssize));
-       }
+	}
+	memblock_set_current_limit(MEMBLOCK_ALLOC_ANYWHERE);
 
 	/*
 	 * If we have a memory_limit and we've allocated TCEs then we need to

index 6a6975d..59b208b 100644
@@ -92,12 +92,6 @@ int __allow_ioremap_reserved;
 unsigned long __max_low_memory = MAX_LOW_MEM;
 
 /*
- * address of the limit of what is accessible with initial MMU setup -
- * 256MB usually, but only 16MB on 601.
- */
-phys_addr_t __initial_memory_limit_addr = (phys_addr_t)0x10000000;
-
-/*
  * Check for command-line options that affect what MMU_init will do.
  */
 void MMU_setup(void)

@@ -126,13 +120,6 @@ void __init MMU_init(void)
 	if (ppc_md.progress)
 		ppc_md.progress("MMU:enter", 0x111);
 
-	/* 601 can only access 16MB at the moment */
-	if (PVR_VER(mfspr(SPRN_PVR)) == 1)
-		__initial_memory_limit_addr = 0x01000000;
-	/* 8xx can only access 8MB at the moment */
-	if (PVR_VER(mfspr(SPRN_PVR)) == 0x50)
-		__initial_memory_limit_addr = 0x00800000;
-
 	/* parse args from command line */
 	MMU_setup();
 

@@ -190,20 +177,18 @@ void __init MMU_init(void)
 #ifdef CONFIG_BOOTX_TEXT
 	btext_unmap();
 #endif
+
+	/* Shortly after that, the entire linear mapping will be available */
+	memblock_set_current_limit(lowmem_end_addr);
 }
 
 /* This is only called until mem_init is done. */
 void __init *early_get_page(void)
 {
-	void *p;
-
-	if (init_bootmem_done) {
-		p = alloc_bootmem_pages(PAGE_SIZE);
-	} else {
-		p = __va(memblock_alloc_base(PAGE_SIZE, PAGE_SIZE,
-					__initial_memory_limit_addr));
-	}
-	return p;
+	if (init_bootmem_done)
+		return alloc_bootmem_pages(PAGE_SIZE);
+	else
+		return __va(memblock_alloc(PAGE_SIZE, PAGE_SIZE));
 }
 
 /* Free up now-unused memory */

index f8a0182..7d34e17 100644
@@ -223,8 +223,7 @@ void __init MMU_init_hw(void)
 	 * Find some memory for the hash table.
 	 */
 	if ( ppc_md.progress ) ppc_md.progress("hash:find piece", 0x322);
-	Hash = __va(memblock_alloc_base(Hash_size, Hash_size,
-				   __initial_memory_limit_addr));
+	Hash = __va(memblock_alloc(Hash_size, Hash_size));
 	cacheable_memzero(Hash, Hash_size);
 	_SDR1 = __pa(Hash) | SDR1_LOW_BITS;
 

index d8695b0..7ba32e7 100644
@@ -432,6 +432,8 @@ static void __early_init_mmu(int boot_cpu)
 	 * the MMU configuration
 	 */
 	mb();
+
+	memblock_set_current_limit(linear_map_top);
 }
 
 void __init early_init_mmu(void)

index dfe683b..e87063f 100644
@@ -1,6 +1,4 @@
 #ifndef __ASM_SH_MEMBLOCK_H
 #define __ASM_SH_MEMBLOCK_H
 
-#define MEMBLOCK_REAL_LIMIT	0
-
 #endif /* __ASM_SH_MEMBLOCK_H */

index f12af88..c67b047 100644
@@ -5,6 +5,4 @@
 
 #define MEMBLOCK_DBG(fmt...) prom_printf(fmt)
 
-#define MEMBLOCK_REAL_LIMIT	0
-
 #endif /* !(_SPARC64_MEMBLOCK_H) */

index 5853752..aabdcdd 100644
@@ -34,6 +34,7 @@ struct memblock_type {
 struct memblock {
 	unsigned long debug;
 	u64 rmo_size;
+	u64 current_limit;
 	struct memblock_type memory;
 	struct memblock_type reserved;
 };

@@ -46,11 +47,16 @@ extern long memblock_add(u64 base, u64 size);
 extern long memblock_remove(u64 base, u64 size);
 extern long __init memblock_free(u64 base, u64 size);
 extern long __init memblock_reserve(u64 base, u64 size);
+
 extern u64 __init memblock_alloc_nid(u64 size, u64 align, int nid);
 extern u64 __init memblock_alloc(u64 size, u64 align);
+
+/* Flags for memblock_alloc_base() amd __memblock_alloc_base() */
+#define MEMBLOCK_ALLOC_ANYWHERE	(~(u64)0)
+#define MEMBLOCK_ALLOC_ACCESSIBLE	0
+
 extern u64 __init memblock_alloc_base(u64 size,
 		u64, u64 max_addr);
-#define MEMBLOCK_ALLOC_ANYWHERE	0
 extern u64 __init __memblock_alloc_base(u64 size,
 		u64 align, u64 max_addr);
 extern u64 __init memblock_phys_mem_size(void);

@@ -64,6 +70,14 @@ extern void memblock_dump_all(void);
 /* Provided by the architecture */
 extern u64 memblock_nid_range(u64 start, u64 end, int *nid);
 
+/**
+ * memblock_set_current_limit - Set the current allocation limit to allow
+ *                         limiting allocations to what is currently
+ *                         accessible during boot
+ * @limit: New limit value (physical address)
+ */
+extern void memblock_set_current_limit(u64 limit);
+
 
 /*
  * pfn conversion functions

index 0ad7626..cdb35ba 100644
@@ -115,6 +115,8 @@ void __init memblock_init(void)
 	memblock.reserved.regions[0].base = 0;
 	memblock.reserved.regions[0].size = 0;
 	memblock.reserved.cnt = 1;
+
+	memblock.current_limit = MEMBLOCK_ALLOC_ANYWHERE;
 }
 
 void __init memblock_analyze(void)

@@ -373,7 +375,7 @@ u64 __init memblock_alloc_nid(u64 size, u64 align, int nid)
 
 u64 __init memblock_alloc(u64 size, u64 align)
 {
-	return memblock_alloc_base(size, align, MEMBLOCK_ALLOC_ANYWHERE);
+	return memblock_alloc_base(size, align, MEMBLOCK_ALLOC_ACCESSIBLE);
 }
 
 u64 __init memblock_alloc_base(u64 size, u64 align, u64 max_addr)

@@ -399,14 +401,9 @@ u64 __init __memblock_alloc_base(u64 size, u64 align, u64 max_addr)
 
 	size = memblock_align_up(size, align);
 
-	/* On some platforms, make sure we allocate lowmem */
-	/* Note that MEMBLOCK_REAL_LIMIT may be MEMBLOCK_ALLOC_ANYWHERE */
-	if (max_addr == MEMBLOCK_ALLOC_ANYWHERE)
-		max_addr = MEMBLOCK_REAL_LIMIT;
-
 	/* Pump up max_addr */
-	if (max_addr == MEMBLOCK_ALLOC_ANYWHERE)
-		max_addr = ~(u64)0;
+	if (max_addr == MEMBLOCK_ALLOC_ACCESSIBLE)
+		max_addr = memblock.current_limit;
 
 	/* We do a top-down search, this tends to limit memory
 	 * fragmentation by keeping early boot allocs near the

@@ -501,3 +498,9 @@ int memblock_is_region_reserved(u64 base, u64 size)
 	return memblock_overlaps_region(&memblock.reserved, base, size);
 }
 
+
+void __init memblock_set_current_limit(u64 limit)
+{
+	memblock.current_limit = limit;
+}
+

index 7ebf42e..bb40a06 100644
@@ -2,6 +2,8 @@
 #define _ASM_POWERPC_MMU_H_
 #ifdef __KERNEL__
 
+#include <linux/types.h>
+
 #include <asm/asm-compat.h>
 #include <asm/feature-fixups.h>
 

@@ -82,6 +84,16 @@ extern unsigned int __start___mmu_ftr_fixup, __stop___mmu_ftr_fixup;
 extern void early_init_mmu(void);
 extern void early_init_mmu_secondary(void);
 
+extern void setup_initial_memory_limit(phys_addr_t first_memblock_base,
+				       phys_addr_t first_memblock_size);
+
+#ifdef CONFIG_PPC64
+/* This is our real memory area size on ppc64 server, on embedded, we
+ * make it match the size our of bolted TLB area
+ */
+extern u64 ppc64_rma_size;
+#endif /* CONFIG_PPC64 */
+
 #endif /* !__ASSEMBLY__ */
 
 /* The kernel use the constants below to index in the page sizes array.

index 139a773..b9ffd7d 100644
@@ -117,7 +117,7 @@ void __init allocate_pacas(void)
 	 * the first segment. On iSeries they must be within the area mapped
 	 * by the HV, which is HvPagesToMap * HVPAGESIZE bytes.
 	 */
-	limit = min(0x10000000ULL, memblock.rmo_size);
+	limit = min(0x10000000ULL, ppc64_rma_size);
 	if (firmware_has_feature(FW_FEATURE_ISERIES))
 		limit = min(limit, HvPagesToMap * HVPAGESIZE);
 

index f665d1b..f12b193 100644
@@ -66,6 +66,7 @@
 int __initdata iommu_is_off;
 int __initdata iommu_force_on;
 unsigned long tce_alloc_start, tce_alloc_end;
+u64 ppc64_rma_size;
 #endif
 
 static int __init early_parse_mem(char *p)

@@ -492,7 +493,7 @@ static int __init early_init_dt_scan_memory_ppc(unsigned long node,
 
 void __init early_init_dt_add_memory_arch(u64 base, u64 size)
 {
-#if defined(CONFIG_PPC64)
+#ifdef CONFIG_PPC64
 	if (iommu_is_off) {
 		if (base >= 0x80000000ul)
 			return;

@@ -501,9 +502,13 @@ void __init early_init_dt_add_memory_arch(u64 base, u64 size)
 	}
 #endif
 
-	memblock_add(base, size);
-
+	/* First MEMBLOCK added, do some special initializations */
+	if (memstart_addr == ~(phys_addr_t)0)
+		setup_initial_memory_limit(base, size);
 	memstart_addr = min((u64)memstart_addr, base);
+
+	/* Add the chunk to the MEMBLOCK list */
+	memblock_add(base, size);
 }
 
 u64 __init early_init_dt_alloc_memory_arch(u64 size, u64 align)

@@ -655,22 +660,6 @@ static void __init phyp_dump_reserve_mem(void)
 static inline void __init phyp_dump_reserve_mem(void) {}
 #endif /* CONFIG_PHYP_DUMP  && CONFIG_PPC_RTAS */
 
-static void set_boot_memory_limit(void)
-{
-#ifdef CONFIG_PPC32
-	/* 601 can only access 16MB at the moment */
-	if (PVR_VER(mfspr(SPRN_PVR)) == 1)
-		memblock_set_current_limit(0x01000000);
-	/* 8xx can only access 8MB at the moment */
-	else if (PVR_VER(mfspr(SPRN_PVR)) == 0x50)
-		memblock_set_current_limit(0x00800000);
-	else
-		memblock_set_current_limit(0x10000000);
-#else
-	memblock_set_current_limit(memblock.rmo_size);
-#endif
-}
-
 void __init early_init_devtree(void *params)
 {
 	phys_addr_t limit;

@@ -734,8 +723,6 @@ void __init early_init_devtree(void *params)
 
 	DBG("Phys. mem: %llx\n", memblock_phys_mem_size());
 
-	set_boot_memory_limit();
-
 	/* We may need to relocate the flat tree, do it now.
 	 * FIXME .. and the initrd too? */
 	move_device_tree();

index d0516db..1662777 100644
@@ -934,7 +934,7 @@ void __init rtas_initialize(void)
 	 */
 #ifdef CONFIG_PPC64
 	if (machine_is(pseries) && firmware_has_feature(FW_FEATURE_LPAR)) {
-		rtas_region = min(memblock.rmo_size, RTAS_INSTANTIATE_MAX);
+		rtas_region = min(ppc64_rma_size, RTAS_INSTANTIATE_MAX);
 		ibm_suspend_me_token = rtas_token("ibm,suspend-me");
 	}
 #endif

index d135f93..4360944 100644
@@ -487,7 +487,7 @@ static void __init emergency_stack_init(void)
 	 * bringup, we need to get at them in real mode. This means they
 	 * must also be within the RMO region.
 	 */
-	limit = min(slb0_limit(), memblock.rmo_size);
+	limit = min(slb0_limit(), ppc64_rma_size);
 
 	for_each_possible_cpu(i) {
 		unsigned long sp;

index 58969b5..5810967 100644
@@ -141,7 +141,19 @@ unsigned long __init mmu_mapin_ram(unsigned long top)
 	 * coverage with normal-sized pages (or other reasons) do not
 	 * attempt to allocate outside the allowed range.
 	 */
-	memblock_set_current_limit(memstart_addr + mapped);
+	memblock_set_current_limit(mapped);
 
 	return mapped;
 }
+
+void setup_initial_memory_limit(phys_addr_t first_memblock_base,
+				phys_addr_t first_memblock_size)
+{
+	/* We don't currently support the first MEMBLOCK not mapping 0
+	 * physical on those processors
+	 */
+	BUG_ON(first_memblock_base != 0);
+
+	/* 40x can only access 16MB at the moment (see head_40x.S) */
+	memblock_set_current_limit(min_t(u64, first_memblock_size, 0x00800000));
+}

index d8c6efb..024acab 100644
@@ -24,6 +24,8 @@
  */
 
 #include <linux/init.h>
+#include <linux/memblock.h>
+
 #include <asm/mmu.h>
 #include <asm/system.h>
 #include <asm/page.h>

@@ -213,6 +215,18 @@ unsigned long __init mmu_mapin_ram(unsigned long top)
 	return total_lowmem;
 }
 
+void setup_initial_memory_limit(phys_addr_t first_memblock_base,
+				phys_addr_t first_memblock_size)
+{
+	/* We don't currently support the first MEMBLOCK not mapping 0
+	 * physical on those processors
+	 */
+	BUG_ON(first_memblock_base != 0);
+
+	/* 44x has a 256M TLB entry pinned at boot */
+	memblock_set_current_limit(min_t(u64, first_memblock_size, PPC_PIN_SIZE));
+}
+
 #ifdef CONFIG_SMP
 void __cpuinit mmu_init_secondary(int cpu)
 {

index e525f86..0be8fe2 100644
@@ -215,3 +215,12 @@ void __init adjust_total_lowmem(void)
 
 	memblock_set_current_limit(memstart_addr + __max_low_memory);
 }
+
+void setup_initial_memory_limit(phys_addr_t first_memblock_base,
+				phys_addr_t first_memblock_size)
+{
+	phys_addr_t limit = first_memblock_base + first_memblock_size;
+
+	/* 64M mapped initially according to head_fsl_booke.S */
+	memblock_set_current_limit(min_t(u64, limit, 0x04000000));
+}

index 79f9445..327a3cd 100644
@@ -649,7 +649,7 @@ static void __init htab_initialize(void)
 #ifdef CONFIG_DEBUG_PAGEALLOC
 	linear_map_hash_count = memblock_end_of_DRAM() >> PAGE_SHIFT;
 	linear_map_hash_slots = __va(memblock_alloc_base(linear_map_hash_count,
-						    1, memblock.rmo_size));
+						    1, ppc64_rma_size));
 	memset(linear_map_hash_slots, 0, linear_map_hash_count);
 #endif /* CONFIG_DEBUG_PAGEALLOC */
 

@@ -1221,3 +1221,23 @@ void kernel_map_pages(struct page *page, int numpages, int enable)
 	local_irq_restore(flags);
 }
 #endif /* CONFIG_DEBUG_PAGEALLOC */
+
+void setup_initial_memory_limit(phys_addr_t first_memblock_base,
+				phys_addr_t first_memblock_size)
+{
+	/* We don't currently support the first MEMBLOCK not mapping 0
+	 * physical on those processors
+	 */
+	BUG_ON(first_memblock_base != 0);
+
+	/* On LPAR systems, the first entry is our RMA region,
+	 * non-LPAR 64-bit hash MMU systems don't have a limitation
+	 * on real mode access, but using the first entry works well
+	 * enough. We also clamp it to 1G to avoid some funky things
+	 * such as RTAS bugs etc...
+	 */
+	ppc64_rma_size = min_t(u64, first_memblock_size, 0x40000000);
+
+	/* Finally limit subsequent allocations */
+	memblock_set_current_limit(ppc64_rma_size);
+}

index 59b208b..742da43 100644
@@ -237,3 +237,17 @@ void free_initrd_mem(unsigned long start, unsigned long end)
 }
 #endif
 
+
+#ifdef CONFIG_8xx /* No 8xx specific .c file to put that in ... */
+void setup_initial_memory_limit(phys_addr_t first_memblock_base,
+				phys_addr_t first_memblock_size)
+{
+	/* We don't currently support the first MEMBLOCK not mapping 0
+	 * physical on those processors
+	 */
+	BUG_ON(first_memblock_base != 0);
+
+	/* 8xx can only access 8MB at the moment */
+	memblock_set_current_limit(min_t(u64, first_memblock_size, 0x00800000));
+}
+#endif /* CONFIG_8xx */

index 71f1415..9e081ff 100644
@@ -328,3 +328,4 @@ int __meminit vmemmap_populate(struct page *start_page,
 	return 0;
 }
 #endif /* CONFIG_SPARSEMEM_VMEMMAP */
+

index 7d34e17..11571e1 100644
@@ -271,3 +271,18 @@ void __init MMU_init_hw(void)
 
 	if ( ppc_md.progress ) ppc_md.progress("hash:done", 0x205);
 }
+
+void setup_initial_memory_limit(phys_addr_t first_memblock_base,
+				phys_addr_t first_memblock_size)
+{
+	/* We don't currently support the first MEMBLOCK not mapping 0
+	 * physical on those processors
+	 */
+	BUG_ON(first_memblock_base != 0);
+
+	/* 601 can only access 16MB at the moment */
+	if (PVR_VER(mfspr(SPRN_PVR)) == 1)
+		memblock_set_current_limit(min_t(u64, first_memblock_size, 0x01000000));
+	else /* Anything else has 256M mapped */
+		memblock_set_current_limit(min_t(u64, first_memblock_size, 0x10000000));
+}

index 7ba32e7..a086ed5 100644
@@ -446,4 +446,18 @@ void __cpuinit early_init_mmu_secondary(void)
 	__early_init_mmu(0);
 }
 
+void setup_initial_memory_limit(phys_addr_t first_memblock_base,
+				phys_addr_t first_memblock_size)
+{
+	/* On Embedded 64-bit, we adjust the RMA size to match
+	 * the bolted TLB entry. We know for now that only 1G
+	 * entries are supported though that may eventually
+	 * change. We crop it to the size of the first MEMBLOCK to
+	 * avoid going over total available memory just in case...
+	 */
+	ppc64_rma_size = min_t(u64, first_memblock_size, 0x40000000);
+
+	/* Finally limit subsequent allocations */
+	memblock_set_current_limit(ppc64_memblock_base + ppc64_rma_size);
+}
 #endif /* CONFIG_PPC64 */

index aabdcdd..767c198 100644
@@ -33,7 +33,6 @@ struct memblock_type {
 
 struct memblock {
 	unsigned long debug;
-	u64 rmo_size;
 	u64 current_limit;
 	struct memblock_type memory;
 	struct memblock_type reserved;

index cdb35ba..43fa162 100644
@@ -49,7 +49,6 @@ void memblock_dump_all(void)
 		return;
 
 	pr_info("MEMBLOCK configuration:\n");
-	pr_info(" rmo_size    = 0x%llx\n", (unsigned long long)memblock.rmo_size);
 	pr_info(" memory.size = 0x%llx\n", (unsigned long long)memblock.memory.size);
 
 	memblock_dump(&memblock.memory, "memory");

@@ -195,10 +194,6 @@ static long memblock_add_region(struct memblock_type *type, u64 base, u64 size)
 
 long memblock_add(u64 base, u64 size)
 {
-	/* On pSeries LPAR systems, the first MEMBLOCK is our RMO region. */
-	if (base == 0)
-		memblock.rmo_size = size;
-
 	return memblock_add_region(&memblock.memory, base, size);
 
 }

@@ -459,9 +454,6 @@ void __init memblock_enforce_memory_limit(u64 memory_limit)
 		break;
 	}
 
-	if (memblock.memory.regions[0].size < memblock.rmo_size)
-		memblock.rmo_size = memblock.memory.regions[0].size;
-
 	memory_limit = memblock_end_of_DRAM();
 
 	/* And truncate any reserves above the limit also. */

index 767c198..3b41f61 100644
@@ -21,19 +21,19 @@
 #define MAX_MEMBLOCK_REGIONS 128
 
 struct memblock_region {
-	u64 base;
-	u64 size;
+	phys_addr_t base;
+	phys_addr_t size;
 };
 
 struct memblock_type {
 	unsigned long cnt;
-	u64 size;
+	phys_addr_t size;
 	struct memblock_region regions[MAX_MEMBLOCK_REGIONS+1];
 };
 
 struct memblock {
 	unsigned long debug;
-	u64 current_limit;
+	phys_addr_t current_limit;
 	struct memblock_type memory;
 	struct memblock_type reserved;
 };

@@ -42,32 +42,32 @@ extern struct memblock memblock;
 
 extern void __init memblock_init(void);
 extern void __init memblock_analyze(void);
-extern long memblock_add(u64 base, u64 size);
-extern long memblock_remove(u64 base, u64 size);
-extern long __init memblock_free(u64 base, u64 size);
-extern long __init memblock_reserve(u64 base, u64 size);
+extern long memblock_add(phys_addr_t base, phys_addr_t size);
+extern long memblock_remove(phys_addr_t base, phys_addr_t size);
+extern long __init memblock_free(phys_addr_t base, phys_addr_t size);
+extern long __init memblock_reserve(phys_addr_t base, phys_addr_t size);
 
-extern u64 __init memblock_alloc_nid(u64 size, u64 align, int nid);
-extern u64 __init memblock_alloc(u64 size, u64 align);
+extern phys_addr_t __init memblock_alloc_nid(phys_addr_t size, phys_addr_t align, int nid);
+extern phys_addr_t __init memblock_alloc(phys_addr_t size, phys_addr_t align);
 
 /* Flags for memblock_alloc_base() amd __memblock_alloc_base() */
-#define MEMBLOCK_ALLOC_ANYWHERE	(~(u64)0)
+#define MEMBLOCK_ALLOC_ANYWHERE	(~(phys_addr_t)0)
 #define MEMBLOCK_ALLOC_ACCESSIBLE	0
 
-extern u64 __init memblock_alloc_base(u64 size,
-		u64, u64 max_addr);
-extern u64 __init __memblock_alloc_base(u64 size,
-		u64 align, u64 max_addr);
-extern u64 __init memblock_phys_mem_size(void);
-extern u64 memblock_end_of_DRAM(void);
-extern void __init memblock_enforce_memory_limit(u64 memory_limit);
-extern int __init memblock_is_reserved(u64 addr);
-extern int memblock_is_region_reserved(u64 base, u64 size);
+extern phys_addr_t __init memblock_alloc_base(phys_addr_t size,
+		phys_addr_t, phys_addr_t max_addr);
+extern phys_addr_t __init __memblock_alloc_base(phys_addr_t size,
+		phys_addr_t align, phys_addr_t max_addr);
+extern phys_addr_t __init memblock_phys_mem_size(void);
+extern phys_addr_t memblock_end_of_DRAM(void);
+extern void __init memblock_enforce_memory_limit(phys_addr_t memory_limit);
+extern int __init memblock_is_reserved(phys_addr_t addr);
+extern int memblock_is_region_reserved(phys_addr_t base, phys_addr_t size);
 
 extern void memblock_dump_all(void);
 
 /* Provided by the architecture */
-extern u64 memblock_nid_range(u64 start, u64 end, int *nid);
+extern phys_addr_t memblock_nid_range(phys_addr_t start, phys_addr_t end, int *nid);
 
 /**
  * memblock_set_current_limit - Set the current allocation limit to allow

@@ -75,7 +75,7 @@ extern u64 memblock_nid_range(u64 start, u64 end, int *nid);
  *                         accessible during boot
  * @limit: New limit value (physical address)
  */
-extern void memblock_set_current_limit(u64 limit);
+extern void memblock_set_current_limit(phys_addr_t limit);
 
 
 /*

308 lines not on this page · raw message

index 3b41f61..5abb06b 100644
@@ -32,7 +32,6 @@ struct memblock_type {
 };
 
 struct memblock {
-	unsigned long debug;
 	phys_addr_t current_limit;
 	struct memblock_type memory;
 	struct memblock_type reserved;

@@ -55,9 +54,11 @@ extern phys_addr_t __init memblock_alloc(phys_addr_t size, phys_addr_t align);
 #define MEMBLOCK_ALLOC_ACCESSIBLE	0
 
 extern phys_addr_t __init memblock_alloc_base(phys_addr_t size,
-		phys_addr_t, phys_addr_t max_addr);
+					 phys_addr_t align,
+					 phys_addr_t max_addr);
 extern phys_addr_t __init __memblock_alloc_base(phys_addr_t size,
-		phys_addr_t align, phys_addr_t max_addr);
+					   phys_addr_t align,
+					   phys_addr_t max_addr);
 extern phys_addr_t __init memblock_phys_mem_size(void);
 extern phys_addr_t memblock_end_of_DRAM(void);
 extern void __init memblock_enforce_memory_limit(phys_addr_t memory_limit);

index 52df542..f661f6c 100644
@@ -301,7 +301,7 @@ void __init mem_init(void)
 		swiotlb_init(1);
 #endif
 
-	num_physpages = memblock.memory.size >> PAGE_SHIFT;
+	num_physpages = memblock_phys_mem_size() >> PAGE_SHIFT;
 	high_memory = (void *) __va(max_low_pfn * PAGE_SIZE);
 
 #ifdef CONFIG_NEED_MULTIPLE_NODES

index 5abb06b..e849d31 100644
@@ -27,12 +27,12 @@ struct memblock_region {
 
 struct memblock_type {
 	unsigned long cnt;
-	phys_addr_t size;
 	struct memblock_region regions[MAX_MEMBLOCK_REGIONS+1];
 };
 
 struct memblock {
 	phys_addr_t current_limit;
+	phys_addr_t memory_size;	/* Updated by memblock_analyze() */
 	struct memblock_type memory;
 	struct memblock_type reserved;
 };

index 0c0f787..78c2394 100644
@@ -49,7 +49,7 @@ void memblock_dump_all(void)
 		return;
 
 	pr_info("MEMBLOCK configuration:\n");
-	pr_info(" memory.size = 0x%llx\n", (unsigned long long)memblock.memory.size);
+	pr_info(" memory size = 0x%llx\n", (unsigned long long)memblock.memory_size);
 
 	memblock_dump(&memblock.memory, "memory");
 	memblock_dump(&memblock.reserved, "reserved");

@@ -123,10 +123,10 @@ void __init memblock_analyze(void)
 {
 	int i;
 
-	memblock.memory.size = 0;
+	memblock.memory_size = 0;
 
 	for (i = 0; i < memblock.memory.cnt; i++)
-		memblock.memory.size += memblock.memory.regions[i].size;
+		memblock.memory_size += memblock.memory.regions[i].size;
 }
 
 static long memblock_add_region(struct memblock_type *type, phys_addr_t base, phys_addr_t size)

@@ -423,7 +423,7 @@ phys_addr_t __init __memblock_alloc_base(phys_addr_t size, phys_addr_t align, ph
 /* You must call memblock_analyze() before this. */
 phys_addr_t __init memblock_phys_mem_size(void)
 {
-	return memblock.memory.size;
+	return memblock.memory_size;
 }
 
 phys_addr_t memblock_end_of_DRAM(void)

index e849d31..b839053 100644
@@ -18,7 +18,7 @@
 
 #include <asm/memblock.h>
 
-#define MAX_MEMBLOCK_REGIONS 128
+#define INIT_MEMBLOCK_REGIONS 128
 
 struct memblock_region {
 	phys_addr_t base;

@@ -26,8 +26,9 @@ struct memblock_region {
 };
 
 struct memblock_type {
-	unsigned long cnt;
-	struct memblock_region regions[MAX_MEMBLOCK_REGIONS+1];
+	unsigned long cnt;	/* number of regions */
+	unsigned long max;	/* size of the allocated array */
+	struct memblock_region *regions;
 };
 
 struct memblock {

index 78c2394..e1c5ce3 100644
@@ -18,6 +18,8 @@
 struct memblock memblock;
 
 static int memblock_debug;
+static struct memblock_region memblock_memory_init_regions[INIT_MEMBLOCK_REGIONS + 1];
+static struct memblock_region memblock_reserved_init_regions[INIT_MEMBLOCK_REGIONS + 1];
 
 static int __init early_memblock(char *p)
 {

@@ -104,6 +106,12 @@ static void memblock_coalesce_regions(struct memblock_type *type,
 
 void __init memblock_init(void)
 {
+	/* Hookup the initial arrays */
+	memblock.memory.regions	= memblock_memory_init_regions;
+	memblock.memory.max		= INIT_MEMBLOCK_REGIONS;
+	memblock.reserved.regions	= memblock_reserved_init_regions;
+	memblock.reserved.max	= INIT_MEMBLOCK_REGIONS;
+
 	/* Create a dummy zero size MEMBLOCK which will get coalesced away later.
 	 * This simplifies the memblock_add() code below...
 	 */

@@ -169,7 +177,7 @@ static long memblock_add_region(struct memblock_type *type, phys_addr_t base, ph
 
 	if (coalesced)
 		return coalesced;
-	if (type->cnt >= MAX_MEMBLOCK_REGIONS)
+	if (type->cnt >= type->max)
 		return -1;
 
 	/* Couldn't coalesce the MEMBLOCK, so add it to the sorted table. */

index e1c5ce3..21ba089 100644
@@ -13,6 +13,7 @@
 #include <linux/kernel.h>
 #include <linux/init.h>
 #include <linux/bitops.h>
+#include <linux/poison.h>
 #include <linux/memblock.h>
 
 struct memblock memblock;

@@ -112,6 +113,10 @@ void __init memblock_init(void)
 	memblock.reserved.regions	= memblock_reserved_init_regions;
 	memblock.reserved.max	= INIT_MEMBLOCK_REGIONS;
 
+	/* Write a marker in the unused last array entry */
+	memblock.memory.regions[INIT_MEMBLOCK_REGIONS].base = (phys_addr_t)RED_INACTIVE;
+	memblock.reserved.regions[INIT_MEMBLOCK_REGIONS].base = (phys_addr_t)RED_INACTIVE;
+
 	/* Create a dummy zero size MEMBLOCK which will get coalesced away later.
 	 * This simplifies the memblock_add() code below...
 	 */

@@ -131,6 +136,12 @@ void __init memblock_analyze(void)
 {
 	int i;
 
+	/* Check marker in the unused last array entry */
+	WARN_ON(memblock_memory_init_regions[INIT_MEMBLOCK_REGIONS].base
+		!= (phys_addr_t)RED_INACTIVE);
+	WARN_ON(memblock_reserved_init_regions[INIT_MEMBLOCK_REGIONS].base
+		!= (phys_addr_t)RED_INACTIVE);
+
 	memblock.memory_size = 0;
 
 	for (i = 0; i < memblock.memory.cnt; i++)

index 21ba089..eae3dc0 100644
@@ -309,8 +309,8 @@ static phys_addr_t memblock_align_up(phys_addr_t addr, phys_addr_t size)
 	return (addr + (size - 1)) & ~(size - 1);
 }
 
-static phys_addr_t __init memblock_alloc_region(phys_addr_t start, phys_addr_t end,
-					   phys_addr_t size, phys_addr_t align)
+static phys_addr_t __init memblock_find_region(phys_addr_t start, phys_addr_t end,
+					  phys_addr_t size, phys_addr_t align)
 {
 	phys_addr_t base, res_base;
 	long j;

@@ -318,12 +318,8 @@ static phys_addr_t __init memblock_alloc_region(phys_addr_t start, phys_addr_t e
 	base = memblock_align_down((end - size), align);
 	while (start <= base) {
 		j = memblock_overlaps_region(&memblock.reserved, base, size);
-		if (j < 0) {
-			/* this area isn't reserved, take it */
-			if (memblock_add_region(&memblock.reserved, base, size) < 0)
-				base = ~(phys_addr_t)0;
+		if (j < 0)
 			return base;
-		}
 		res_base = memblock.reserved.regions[j].base;
 		if (res_base < size)
 			break;

@@ -356,8 +352,9 @@ static phys_addr_t __init memblock_alloc_nid_region(struct memblock_region *mp,
 
 		this_end = memblock_nid_range(start, end, &this_nid);
 		if (this_nid == nid) {
-			phys_addr_t ret = memblock_alloc_region(start, this_end, size, align);
-			if (ret != ~(phys_addr_t)0)
+			phys_addr_t ret = memblock_find_region(start, this_end, size, align);
+			if (ret != ~(phys_addr_t)0 &&
+			    memblock_add_region(&memblock.reserved, ret, size) >= 0)
 				return ret;
 		}
 		start = this_end;

@@ -432,8 +429,9 @@ phys_addr_t __init __memblock_alloc_base(phys_addr_t size, phys_addr_t align, ph
 		if (memblocksize < size)
 			continue;
 		base = min(memblockbase + memblocksize, max_addr);
-		res_base = memblock_alloc_region(memblockbase, base, size, align);
-		if (res_base != ~(phys_addr_t)0)
+		res_base = memblock_find_region(memblockbase, base, size, align);
+		if (res_base != ~(phys_addr_t)0 &&
+		    memblock_add_region(&memblock.reserved, res_base, size) >= 0)
 			return res_base;
 	}
 	return 0;

index eae3dc0..5743417 100644
@@ -22,6 +22,8 @@ static int memblock_debug;
 static struct memblock_region memblock_memory_init_regions[INIT_MEMBLOCK_REGIONS + 1];
 static struct memblock_region memblock_reserved_init_regions[INIT_MEMBLOCK_REGIONS + 1];
 
+#define MEMBLOCK_ERROR	(~(phys_addr_t)0)
+
 static int __init early_memblock(char *p)
 {
 	if (p && strstr(p, "debug"))

@@ -326,7 +328,7 @@ static phys_addr_t __init memblock_find_region(phys_addr_t start, phys_addr_t en
 		base = memblock_align_down(res_base - size, align);
 	}
 
-	return ~(phys_addr_t)0;
+	return MEMBLOCK_ERROR;
 }
 
 phys_addr_t __weak __init memblock_nid_range(phys_addr_t start, phys_addr_t end, int *nid)

@@ -353,14 +355,14 @@ static phys_addr_t __init memblock_alloc_nid_region(struct memblock_region *mp,
 		this_end = memblock_nid_range(start, end, &this_nid);
 		if (this_nid == nid) {
 			phys_addr_t ret = memblock_find_region(start, this_end, size, align);
-			if (ret != ~(phys_addr_t)0 &&
+			if (ret != MEMBLOCK_ERROR &&
 			    memblock_add_region(&memblock.reserved, ret, size) >= 0)
 				return ret;
 		}
 		start = this_end;
 	}
 
-	return ~(phys_addr_t)0;
+	return MEMBLOCK_ERROR;
 }
 
 phys_addr_t __init memblock_alloc_nid(phys_addr_t size, phys_addr_t align, int nid)

@@ -379,7 +381,7 @@ phys_addr_t __init memblock_alloc_nid(phys_addr_t size, phys_addr_t align, int n
 	for (i = 0; i < mem->cnt; i++) {
 		phys_addr_t ret = memblock_alloc_nid_region(&mem->regions[i],
 					       size, align, nid);
-		if (ret != ~(phys_addr_t)0)
+		if (ret != MEMBLOCK_ERROR)
 			return ret;
 	}
 

@@ -430,7 +432,7 @@ phys_addr_t __init __memblock_alloc_base(phys_addr_t size, phys_addr_t align, ph
 			continue;
 		base = min(memblockbase + memblocksize, max_addr);
 		res_base = memblock_find_region(memblockbase, base, size, align);
-		if (res_base != ~(phys_addr_t)0 &&
+		if (res_base != MEMBLOCK_ERROR &&
 		    memblock_add_region(&memblock.reserved, res_base, size) >= 0)
 			return res_base;
 	}

index 5743417..1283893 100644
@@ -107,33 +107,6 @@ static void memblock_coalesce_regions(struct memblock_type *type,
 	memblock_remove_region(type, r2);
 }
 
-void __init memblock_init(void)
-{
-	/* Hookup the initial arrays */
-	memblock.memory.regions	= memblock_memory_init_regions;
-	memblock.memory.max		= INIT_MEMBLOCK_REGIONS;
-	memblock.reserved.regions	= memblock_reserved_init_regions;
-	memblock.reserved.max	= INIT_MEMBLOCK_REGIONS;
-
-	/* Write a marker in the unused last array entry */
-	memblock.memory.regions[INIT_MEMBLOCK_REGIONS].base = (phys_addr_t)RED_INACTIVE;
-	memblock.reserved.regions[INIT_MEMBLOCK_REGIONS].base = (phys_addr_t)RED_INACTIVE;
-
-	/* Create a dummy zero size MEMBLOCK which will get coalesced away later.
-	 * This simplifies the memblock_add() code below...
-	 */
-	memblock.memory.regions[0].base = 0;
-	memblock.memory.regions[0].size = 0;
-	memblock.memory.cnt = 1;
-
-	/* Ditto. */
-	memblock.reserved.regions[0].base = 0;
-	memblock.reserved.regions[0].size = 0;
-	memblock.reserved.cnt = 1;
-
-	memblock.current_limit = MEMBLOCK_ALLOC_ANYWHERE;
-}
-
 void __init memblock_analyze(void)
 {
 	int i;

@@ -517,3 +490,30 @@ void __init memblock_set_current_limit(phys_addr_t limit)
 	memblock.current_limit = limit;
 }
 
+void __init memblock_init(void)
+{
+	/* Hookup the initial arrays */
+	memblock.memory.regions	= memblock_memory_init_regions;
+	memblock.memory.max		= INIT_MEMBLOCK_REGIONS;
+	memblock.reserved.regions	= memblock_reserved_init_regions;
+	memblock.reserved.max	= INIT_MEMBLOCK_REGIONS;
+
+	/* Write a marker in the unused last array entry */
+	memblock.memory.regions[INIT_MEMBLOCK_REGIONS].base = (phys_addr_t)RED_INACTIVE;
+	memblock.reserved.regions[INIT_MEMBLOCK_REGIONS].base = (phys_addr_t)RED_INACTIVE;
+
+	/* Create a dummy zero size MEMBLOCK which will get coalesced away later.
+	 * This simplifies the memblock_add() code below...
+	 */
+	memblock.memory.regions[0].base = 0;
+	memblock.memory.regions[0].size = 0;
+	memblock.memory.cnt = 1;
+
+	/* Ditto. */
+	memblock.reserved.regions[0].base = 0;
+	memblock.reserved.regions[0].size = 0;
+	memblock.reserved.cnt = 1;
+
+	memblock.current_limit = MEMBLOCK_ALLOC_ANYWHERE;
+}
+

index 1283893..17403e6 100644
@@ -345,12 +345,15 @@ phys_addr_t __init memblock_alloc_nid(phys_addr_t size, phys_addr_t align, int n
 
 	BUG_ON(0 == size);
 
+	/* We align the size to limit fragmentation. Without this, a lot of
+	 * small allocs quickly eat up the whole reserve array on sparc
+	 */
+	size = memblock_align_up(size, align);
+
 	/* We do a bottom-up search for a region with the right
 	 * nid since that's easier considering how memblock_nid_range()
 	 * works
 	 */
-	size = memblock_align_up(size, align);
-
 	for (i = 0; i < mem->cnt; i++) {
 		phys_addr_t ret = memblock_alloc_nid_region(&mem->regions[i],
 					       size, align, nid);

@@ -366,20 +369,7 @@ phys_addr_t __init memblock_alloc(phys_addr_t size, phys_addr_t align)
 	return memblock_alloc_base(size, align, MEMBLOCK_ALLOC_ACCESSIBLE);
 }
 
-phys_addr_t __init memblock_alloc_base(phys_addr_t size, phys_addr_t align, phys_addr_t max_addr)
-{
-	phys_addr_t alloc;
-
-	alloc = __memblock_alloc_base(size, align, max_addr);
-
-	if (alloc == 0)
-		panic("ERROR: Failed to allocate 0x%llx bytes below 0x%llx.\n",
-		      (unsigned long long) size, (unsigned long long) max_addr);
-
-	return alloc;
-}
-
-phys_addr_t __init __memblock_alloc_base(phys_addr_t size, phys_addr_t align, phys_addr_t max_addr)
+static phys_addr_t __init memblock_find_base(phys_addr_t size, phys_addr_t align, phys_addr_t max_addr)
 {
 	long i;
 	phys_addr_t base = 0;

@@ -387,8 +377,6 @@ phys_addr_t __init __memblock_alloc_base(phys_addr_t size, phys_addr_t align, ph
 
 	BUG_ON(0 == size);
 
-	size = memblock_align_up(size, align);
-
 	/* Pump up max_addr */
 	if (max_addr == MEMBLOCK_ALLOC_ACCESSIBLE)
 		max_addr = memblock.current_limit;

@@ -405,13 +393,43 @@ phys_addr_t __init __memblock_alloc_base(phys_addr_t size, phys_addr_t align, ph
 			continue;
 		base = min(memblockbase + memblocksize, max_addr);
 		res_base = memblock_find_region(memblockbase, base, size, align);
-		if (res_base != MEMBLOCK_ERROR &&
-		    memblock_add_region(&memblock.reserved, res_base, size) >= 0)
+		if (res_base != MEMBLOCK_ERROR)
 			return res_base;
 	}
+	return MEMBLOCK_ERROR;
+}
+
+phys_addr_t __init __memblock_alloc_base(phys_addr_t size, phys_addr_t align, phys_addr_t max_addr)
+{	
+	phys_addr_t found;
+
+	/* We align the size to limit fragmentation. Without this, a lot of
+	 * small allocs quickly eat up the whole reserve array on sparc
+	 */
+	size = memblock_align_up(size, align);
+
+	found = memblock_find_base(size, align, max_addr);
+	if (found != MEMBLOCK_ERROR &&
+	    memblock_add_region(&memblock.reserved, found, size) >= 0)
+		return found;
+
 	return 0;
 }
 
+phys_addr_t __init memblock_alloc_base(phys_addr_t size, phys_addr_t align, phys_addr_t max_addr)
+{
+	phys_addr_t alloc;
+
+	alloc = __memblock_alloc_base(size, align, max_addr);
+
+	if (alloc == 0)
+		panic("ERROR: Failed to allocate 0x%llx bytes below 0x%llx.\n",
+		      (unsigned long long) size, (unsigned long long) max_addr);
+
+	return alloc;
+}
+
+
 /* You must call memblock_analyze() before this. */
 phys_addr_t __init memblock_phys_mem_size(void)
 {

index 17403e6..80d8b85 100644
@@ -24,40 +24,18 @@ static struct memblock_region memblock_reserved_init_regions[INIT_MEMBLOCK_REGIO
 
 #define MEMBLOCK_ERROR	(~(phys_addr_t)0)
 
-static int __init early_memblock(char *p)
-{
-	if (p && strstr(p, "debug"))
-		memblock_debug = 1;
-	return 0;
-}
-early_param("memblock", early_memblock);
+/*
+ * Address comparison utilities
+ */
 
-static void memblock_dump(struct memblock_type *region, char *name)
+static phys_addr_t memblock_align_down(phys_addr_t addr, phys_addr_t size)
 {
-	unsigned long long base, size;
-	int i;
-
-	pr_info(" %s.cnt  = 0x%lx\n", name, region->cnt);
-
-	for (i = 0; i < region->cnt; i++) {
-		base = region->regions[i].base;
-		size = region->regions[i].size;
-
-		pr_info(" %s[0x%x]\t0x%016llx - 0x%016llx, 0x%llx bytes\n",
-		    name, i, base, base + size - 1, size);
-	}
+	return addr & ~(size - 1);
 }
 
-void memblock_dump_all(void)
+static phys_addr_t memblock_align_up(phys_addr_t addr, phys_addr_t size)
 {
-	if (!memblock_debug)
-		return;
-
-	pr_info("MEMBLOCK configuration:\n");
-	pr_info(" memory size = 0x%llx\n", (unsigned long long)memblock.memory_size);
-
-	memblock_dump(&memblock.memory, "memory");
-	memblock_dump(&memblock.reserved, "reserved");
+	return (addr + (size - 1)) & ~(size - 1);
 }
 
 static unsigned long memblock_addrs_overlap(phys_addr_t base1, phys_addr_t size1,

@@ -88,6 +66,77 @@ static long memblock_regions_adjacent(struct memblock_type *type,
 	return memblock_addrs_adjacent(base1, size1, base2, size2);
 }
 
+long memblock_overlaps_region(struct memblock_type *type, phys_addr_t base, phys_addr_t size)
+{
+	unsigned long i;
+
+	for (i = 0; i < type->cnt; i++) {
+		phys_addr_t rgnbase = type->regions[i].base;
+		phys_addr_t rgnsize = type->regions[i].size;
+		if (memblock_addrs_overlap(base, size, rgnbase, rgnsize))
+			break;
+	}
+
+	return (i < type->cnt) ? i : -1;
+}
+
+/*
+ * Find, allocate, deallocate or reserve unreserved regions. All allocations
+ * are top-down.
+ */
+
+static phys_addr_t __init memblock_find_region(phys_addr_t start, phys_addr_t end,
+					  phys_addr_t size, phys_addr_t align)
+{
+	phys_addr_t base, res_base;
+	long j;
+
+	base = memblock_align_down((end - size), align);
+	while (start <= base) {
+		j = memblock_overlaps_region(&memblock.reserved, base, size);
+		if (j < 0)
+			return base;
+		res_base = memblock.reserved.regions[j].base;
+		if (res_base < size)
+			break;
+		base = memblock_align_down(res_base - size, align);
+	}
+
+	return MEMBLOCK_ERROR;
+}
+
+static phys_addr_t __init memblock_find_base(phys_addr_t size, phys_addr_t align, phys_addr_t max_addr)
+{
+	long i;
+	phys_addr_t base = 0;
+	phys_addr_t res_base;
+
+	BUG_ON(0 == size);
+
+	size = memblock_align_up(size, align);
+
+	/* Pump up max_addr */
+	if (max_addr == MEMBLOCK_ALLOC_ACCESSIBLE)
+		max_addr = memblock.current_limit;
+
+	/* We do a top-down search, this tends to limit memory
+	 * fragmentation by keeping early boot allocs near the
+	 * top of memory
+	 */
+	for (i = memblock.memory.cnt - 1; i >= 0; i--) {
+		phys_addr_t memblockbase = memblock.memory.regions[i].base;
+		phys_addr_t memblocksize = memblock.memory.regions[i].size;
+
+		if (memblocksize < size)
+			continue;
+		base = min(memblockbase + memblocksize, max_addr);
+		res_base = memblock_find_region(memblockbase, base, size, align);
+		if (res_base != MEMBLOCK_ERROR)
+			return res_base;
+	}
+	return MEMBLOCK_ERROR;
+}
+
 static void memblock_remove_region(struct memblock_type *type, unsigned long r)
 {
 	unsigned long i;

@@ -107,22 +156,6 @@ static void memblock_coalesce_regions(struct memblock_type *type,
 	memblock_remove_region(type, r2);
 }
 
-void __init memblock_analyze(void)
-{
-	int i;
-
-	/* Check marker in the unused last array entry */
-	WARN_ON(memblock_memory_init_regions[INIT_MEMBLOCK_REGIONS].base
-		!= (phys_addr_t)RED_INACTIVE);
-	WARN_ON(memblock_reserved_init_regions[INIT_MEMBLOCK_REGIONS].base
-		!= (phys_addr_t)RED_INACTIVE);
-
-	memblock.memory_size = 0;
-
-	for (i = 0; i < memblock.memory.cnt; i++)
-		memblock.memory_size += memblock.memory.regions[i].size;
-}
-
 static long memblock_add_region(struct memblock_type *type, phys_addr_t base, phys_addr_t size)
 {
 	unsigned long coalesced = 0;

@@ -260,49 +293,47 @@ long __init memblock_reserve(phys_addr_t base, phys_addr_t size)
 	return memblock_add_region(_rgn, base, size);
 }
 
-long memblock_overlaps_region(struct memblock_type *type, phys_addr_t base, phys_addr_t size)
+phys_addr_t __init __memblock_alloc_base(phys_addr_t size, phys_addr_t align, phys_addr_t max_addr)
 {
-	unsigned long i;
+	phys_addr_t found;
 
-	for (i = 0; i < type->cnt; i++) {
-		phys_addr_t rgnbase = type->regions[i].base;
-		phys_addr_t rgnsize = type->regions[i].size;
-		if (memblock_addrs_overlap(base, size, rgnbase, rgnsize))
-			break;
-	}
+	/* We align the size to limit fragmentation. Without this, a lot of
+	 * small allocs quickly eat up the whole reserve array on sparc
+	 */
+	size = memblock_align_up(size, align);
 
-	return (i < type->cnt) ? i : -1;
-}
+	found = memblock_find_base(size, align, max_addr);
+	if (found != MEMBLOCK_ERROR &&
+	    memblock_add_region(&memblock.reserved, found, size) >= 0)
+		return found;
 
-static phys_addr_t memblock_align_down(phys_addr_t addr, phys_addr_t size)
-{
-	return addr & ~(size - 1);
+	return 0;
 }
 
-static phys_addr_t memblock_align_up(phys_addr_t addr, phys_addr_t size)
+phys_addr_t __init memblock_alloc_base(phys_addr_t size, phys_addr_t align, phys_addr_t max_addr)
 {
-	return (addr + (size - 1)) & ~(size - 1);
+	phys_addr_t alloc;
+
+	alloc = __memblock_alloc_base(size, align, max_addr);
+
+	if (alloc == 0)
+		panic("ERROR: Failed to allocate 0x%llx bytes below 0x%llx.\n",
+		      (unsigned long long) size, (unsigned long long) max_addr);
+
+	return alloc;
 }
 
-static phys_addr_t __init memblock_find_region(phys_addr_t start, phys_addr_t end,
-					  phys_addr_t size, phys_addr_t align)
+phys_addr_t __init memblock_alloc(phys_addr_t size, phys_addr_t align)
 {
-	phys_addr_t base, res_base;
-	long j;
+	return memblock_alloc_base(size, align, MEMBLOCK_ALLOC_ACCESSIBLE);
+}
 
-	base = memblock_align_down((end - size), align);
-	while (start <= base) {
-		j = memblock_overlaps_region(&memblock.reserved, base, size);
-		if (j < 0)
-			return base;
-		res_base = memblock.reserved.regions[j].base;
-		if (res_base < size)
-			break;
-		base = memblock_align_down(res_base - size, align);
-	}
 
-	return MEMBLOCK_ERROR;
-}
+/*
+ * Additional node-local allocators. Search for node memory is bottom up
+ * and walks memblock regions within that node bottom-up as well, but allocation
+ * within an memblock region is top-down.
+ */
 
 phys_addr_t __weak __init memblock_nid_range(phys_addr_t start, phys_addr_t end, int *nid)
 {

@@ -364,72 +395,6 @@ phys_addr_t __init memblock_alloc_nid(phys_addr_t size, phys_addr_t align, int n
 	return memblock_alloc(size, align);
 }
 
-phys_addr_t __init memblock_alloc(phys_addr_t size, phys_addr_t align)
-{
-	return memblock_alloc_base(size, align, MEMBLOCK_ALLOC_ACCESSIBLE);
-}
-
-static phys_addr_t __init memblock_find_base(phys_addr_t size, phys_addr_t align, phys_addr_t max_addr)
-{
-	long i;
-	phys_addr_t base = 0;
-	phys_addr_t res_base;
-
-	BUG_ON(0 == size);
-
-	/* Pump up max_addr */
-	if (max_addr == MEMBLOCK_ALLOC_ACCESSIBLE)
-		max_addr = memblock.current_limit;
-
-	/* We do a top-down search, this tends to limit memory
-	 * fragmentation by keeping early boot allocs near the
-	 * top of memory
-	 */
-	for (i = memblock.memory.cnt - 1; i >= 0; i--) {
-		phys_addr_t memblockbase = memblock.memory.regions[i].base;
-		phys_addr_t memblocksize = memblock.memory.regions[i].size;
-
-		if (memblocksize < size)
-			continue;
-		base = min(memblockbase + memblocksize, max_addr);
-		res_base = memblock_find_region(memblockbase, base, size, align);
-		if (res_base != MEMBLOCK_ERROR)
-			return res_base;
-	}
-	return MEMBLOCK_ERROR;
-}
-
-phys_addr_t __init __memblock_alloc_base(phys_addr_t size, phys_addr_t align, phys_addr_t max_addr)
-{	
-	phys_addr_t found;
-
-	/* We align the size to limit fragmentation. Without this, a lot of
-	 * small allocs quickly eat up the whole reserve array on sparc
-	 */
-	size = memblock_align_up(size, align);
-
-	found = memblock_find_base(size, align, max_addr);
-	if (found != MEMBLOCK_ERROR &&
-	    memblock_add_region(&memblock.reserved, found, size) >= 0)
-		return found;
-
-	return 0;
-}
-
-phys_addr_t __init memblock_alloc_base(phys_addr_t size, phys_addr_t align, phys_addr_t max_addr)
-{
-	phys_addr_t alloc;
-
-	alloc = __memblock_alloc_base(size, align, max_addr);
-
-	if (alloc == 0)
-		panic("ERROR: Failed to allocate 0x%llx bytes below 0x%llx.\n",
-		      (unsigned long long) size, (unsigned long long) max_addr);
-
-	return alloc;
-}
-
-
 /* You must call memblock_analyze() before this. */
 phys_addr_t __init memblock_phys_mem_size(void)
 {

@@ -508,6 +473,50 @@ void __init memblock_set_current_limit(phys_addr_t limit)
 	memblock.current_limit = limit;
 }
 
+static void memblock_dump(struct memblock_type *region, char *name)
+{
+	unsigned long long base, size;
+	int i;
+
+	pr_info(" %s.cnt  = 0x%lx\n", name, region->cnt);
+
+	for (i = 0; i < region->cnt; i++) {
+		base = region->regions[i].base;
+		size = region->regions[i].size;
+
+		pr_info(" %s[0x%x]\t0x%016llx - 0x%016llx, 0x%llx bytes\n",
+		    name, i, base, base + size - 1, size);
+	}
+}
+
+void memblock_dump_all(void)
+{
+	if (!memblock_debug)
+		return;
+
+	pr_info("MEMBLOCK configuration:\n");
+	pr_info(" memory size = 0x%llx\n", (unsigned long long)memblock.memory_size);
+
+	memblock_dump(&memblock.memory, "memory");
+	memblock_dump(&memblock.reserved, "reserved");
+}
+
+void __init memblock_analyze(void)
+{
+	int i;
+
+	/* Check marker in the unused last array entry */
+	WARN_ON(memblock_memory_init_regions[INIT_MEMBLOCK_REGIONS].base
+		!= (phys_addr_t)RED_INACTIVE);
+	WARN_ON(memblock_reserved_init_regions[INIT_MEMBLOCK_REGIONS].base
+		!= (phys_addr_t)RED_INACTIVE);
+
+	memblock.memory_size = 0;
+
+	for (i = 0; i < memblock.memory.cnt; i++)
+		memblock.memory_size += memblock.memory.regions[i].size;
+}
+
 void __init memblock_init(void)
 {
 	/* Hookup the initial arrays */

@@ -535,3 +544,11 @@ void __init memblock_init(void)
 	memblock.current_limit = MEMBLOCK_ALLOC_ANYWHERE;
 }
 
+static int __init early_memblock(char *p)
+{
+	if (p && strstr(p, "debug"))
+		memblock_debug = 1;
+	return 0;
+}
+early_param("memblock", early_memblock);
+

index 80d8b85..8197f37 100644
@@ -11,6 +11,7 @@
  */
 
 #include <linux/kernel.h>
+#include <linux/slab.h>
 #include <linux/init.h>
 #include <linux/bitops.h>
 #include <linux/poison.h>

@@ -18,12 +19,23 @@
 
 struct memblock memblock;
 
-static int memblock_debug;
+static int memblock_debug, memblock_can_resize;
 static struct memblock_region memblock_memory_init_regions[INIT_MEMBLOCK_REGIONS + 1];
 static struct memblock_region memblock_reserved_init_regions[INIT_MEMBLOCK_REGIONS + 1];
 
 #define MEMBLOCK_ERROR	(~(phys_addr_t)0)
 
+/* inline so we don't get a warning when pr_debug is compiled out */
+static inline const char *memblock_type_name(struct memblock_type *type)
+{
+	if (type == &memblock.memory)
+		return "memory";
+	else if (type == &memblock.reserved)
+		return "reserved";
+	else
+		return "unknown";
+}
+
 /*
  * Address comparison utilities
  */

@@ -156,6 +168,79 @@ static void memblock_coalesce_regions(struct memblock_type *type,
 	memblock_remove_region(type, r2);
 }
 
+/* Defined below but needed now */
+static long memblock_add_region(struct memblock_type *type, phys_addr_t base, phys_addr_t size);
+
+static int memblock_double_array(struct memblock_type *type)
+{
+	struct memblock_region *new_array, *old_array;
+	phys_addr_t old_size, new_size, addr;
+	int use_slab = slab_is_available();
+
+	/* We don't allow resizing until we know about the reserved regions
+	 * of memory that aren't suitable for allocation
+	 */
+	if (!memblock_can_resize)
+		return -1;
+
+	pr_debug("memblock: %s array full, doubling...", memblock_type_name(type));
+
+	/* Calculate new doubled size */
+	old_size = type->max * sizeof(struct memblock_region);
+	new_size = old_size << 1;
+
+	/* Try to find some space for it.
+	 *
+	 * WARNING: We assume that either slab_is_available() and we use it or
+	 * we use MEMBLOCK for allocations. That means that this is unsafe to use
+	 * when bootmem is currently active (unless bootmem itself is implemented
+	 * on top of MEMBLOCK which isn't the case yet)
+	 *
+	 * This should however not be an issue for now, as we currently only
+	 * call into MEMBLOCK while it's still active, or much later when slab is
+	 * active for memory hotplug operations
+	 */
+	if (use_slab) {
+		new_array = kmalloc(new_size, GFP_KERNEL);
+		addr = new_array == NULL ? MEMBLOCK_ERROR : __pa(new_array);
+	} else
+		addr = memblock_find_base(new_size, sizeof(phys_addr_t), MEMBLOCK_ALLOC_ACCESSIBLE);
+	if (addr == MEMBLOCK_ERROR) {
+		pr_err("memblock: Failed to double %s array from %ld to %ld entries !\n",
+		       memblock_type_name(type), type->max, type->max * 2);
+		return -1;
+	}
+	new_array = __va(addr);
+
+	/* Found space, we now need to move the array over before
+	 * we add the reserved region since it may be our reserved
+	 * array itself that is full.
+	 */
+	memcpy(new_array, type->regions, old_size);
+	memset(new_array + type->max, 0, old_size);
+	old_array = type->regions;
+	type->regions = new_array;
+	type->max <<= 1;
+
+	/* If we use SLAB that's it, we are done */
+	if (use_slab)
+		return 0;
+
+	/* Add the new reserved region now. Should not fail ! */
+	BUG_ON(memblock_add_region(&memblock.reserved, addr, new_size) < 0);
+
+	/* If the array wasn't our static init one, then free it. We only do
+	 * that before SLAB is available as later on, we don't know whether
+	 * to use kfree or free_bootmem_pages(). Shouldn't be a big deal
+	 * anyways
+	 */
+	if (old_array != memblock_memory_init_regions &&
+	    old_array != memblock_reserved_init_regions)
+		memblock_free(__pa(old_array), old_size);
+
+	return 0;
+}
+
 static long memblock_add_region(struct memblock_type *type, phys_addr_t base, phys_addr_t size)
 {
 	unsigned long coalesced = 0;

@@ -196,7 +281,11 @@ static long memblock_add_region(struct memblock_type *type, phys_addr_t base, ph
 
 	if (coalesced)
 		return coalesced;
-	if (type->cnt >= type->max)
+
+	/* If we are out of space, we fail. It's too late to resize the array
+	 * but then this shouldn't have happened in the first place.
+	 */
+	if (WARN_ON(type->cnt >= type->max))
 		return -1;
 
 	/* Couldn't coalesce the MEMBLOCK, so add it to the sorted table. */

@@ -217,6 +306,14 @@ static long memblock_add_region(struct memblock_type *type, phys_addr_t base, ph
 	}
 	type->cnt++;
 
+	/* The array is full ? Try to resize it. If that fails, we undo
+	 * our allocation and return an error
+	 */
+	if (type->cnt == type->max && memblock_double_array(type)) {
+		type->cnt--;
+		return -1;
+	}
+
 	return 0;
 }
 

@@ -515,6 +612,9 @@ void __init memblock_analyze(void)
 
 	for (i = 0; i < memblock.memory.cnt; i++)
 		memblock.memory_size += memblock.memory.regions[i].size;
+
+	/* We allow resizing from there */
+	memblock_can_resize = 1;
 }
 
 void __init memblock_init(void)

index b839053..15da7d9 100644
@@ -70,6 +70,8 @@ extern void memblock_dump_all(void);
 
 /* Provided by the architecture */
 extern phys_addr_t memblock_nid_range(phys_addr_t start, phys_addr_t end, int *nid);
+extern int memblock_memory_can_coalesce(phys_addr_t addr1, phys_addr_t size1,
+				   phys_addr_t addr2, phys_addr_t size2);
 
 /**
  * memblock_set_current_limit - Set the current allocation limit to allow

index 8197f37..f793d9f 100644
@@ -241,6 +241,12 @@ static int memblock_double_array(struct memblock_type *type)
 	return 0;
 }
 
+extern int __weak memblock_memory_can_coalesce(phys_addr_t addr1, phys_addr_t size1,
+					  phys_addr_t addr2, phys_addr_t size2)
+{
+	return 1;
+}
+
 static long memblock_add_region(struct memblock_type *type, phys_addr_t base, phys_addr_t size)
 {
 	unsigned long coalesced = 0;

@@ -262,6 +268,10 @@ static long memblock_add_region(struct memblock_type *type, phys_addr_t base, ph
 			return 0;
 
 		adjacent = memblock_addrs_adjacent(base, size, rgnbase, rgnsize);
+		/* Check if arch allows coalescing */
+		if (adjacent != 0 && type == &memblock.memory &&
+		    !memblock_memory_can_coalesce(base, size, rgnbase, rgnsize))
+			break;
 		if (adjacent > 0) {
 			type->regions[i].base -= size;
 			type->regions[i].size += size;

@@ -274,7 +284,14 @@ static long memblock_add_region(struct memblock_type *type, phys_addr_t base, ph
 		}
 	}
 
-	if ((i < type->cnt - 1) && memblock_regions_adjacent(type, i, i+1)) {
+	/* If we plugged a hole, we may want to also coalesce with the
+	 * next region
+	 */
+	if ((i < type->cnt - 1) && memblock_regions_adjacent(type, i, i+1) &&
+	    ((type != &memblock.memory || memblock_memory_can_coalesce(type->regions[i].base,
+							     type->regions[i].size,
+							     type->regions[i+1].base,
+							     type->regions[i+1].size)))) {
 		memblock_coalesce_regions(type, i, i+1);
 		coalesced++;
 	}

index f793d9f..b4870cf 100644
@@ -117,19 +117,18 @@ static phys_addr_t __init memblock_find_region(phys_addr_t start, phys_addr_t en
 	return MEMBLOCK_ERROR;
 }
 
-static phys_addr_t __init memblock_find_base(phys_addr_t size, phys_addr_t align, phys_addr_t max_addr)
+static phys_addr_t __init memblock_find_base(phys_addr_t size, phys_addr_t align,
+					phys_addr_t start, phys_addr_t end)
 {
 	long i;
-	phys_addr_t base = 0;
-	phys_addr_t res_base;
 
 	BUG_ON(0 == size);
 
 	size = memblock_align_up(size, align);
 
 	/* Pump up max_addr */
-	if (max_addr == MEMBLOCK_ALLOC_ACCESSIBLE)
-		max_addr = memblock.current_limit;
+	if (end == MEMBLOCK_ALLOC_ACCESSIBLE)
+		end = memblock.current_limit;
 
 	/* We do a top-down search, this tends to limit memory
 	 * fragmentation by keeping early boot allocs near the

@@ -138,13 +137,19 @@ static phys_addr_t __init memblock_find_base(phys_addr_t size, phys_addr_t align
 	for (i = memblock.memory.cnt - 1; i >= 0; i--) {
 		phys_addr_t memblockbase = memblock.memory.regions[i].base;
 		phys_addr_t memblocksize = memblock.memory.regions[i].size;
+		phys_addr_t bottom, top, found;
 
 		if (memblocksize < size)
 			continue;
-		base = min(memblockbase + memblocksize, max_addr);
-		res_base = memblock_find_region(memblockbase, base, size, align);
-		if (res_base != MEMBLOCK_ERROR)
-			return res_base;
+		if ((memblockbase + memblocksize) <= start)
+			break;
+		bottom = max(memblockbase, start);
+		top = min(memblockbase + memblocksize, end);
+		if (bottom >= top)
+			continue;
+		found = memblock_find_region(bottom, top, size, align);
+		if (found != MEMBLOCK_ERROR)
+			return found;
 	}
 	return MEMBLOCK_ERROR;
 }

@@ -204,7 +209,7 @@ static int memblock_double_array(struct memblock_type *type)
 		new_array = kmalloc(new_size, GFP_KERNEL);
 		addr = new_array == NULL ? MEMBLOCK_ERROR : __pa(new_array);
 	} else
-		addr = memblock_find_base(new_size, sizeof(phys_addr_t), MEMBLOCK_ALLOC_ACCESSIBLE);
+		addr = memblock_find_base(new_size, sizeof(phys_addr_t), 0, MEMBLOCK_ALLOC_ACCESSIBLE);
 	if (addr == MEMBLOCK_ERROR) {
 		pr_err("memblock: Failed to double %s array from %ld to %ld entries !\n",
 		       memblock_type_name(type), type->max, type->max * 2);

@@ -416,7 +421,7 @@ phys_addr_t __init __memblock_alloc_base(phys_addr_t size, phys_addr_t align, ph
 	 */
 	size = memblock_align_up(size, align);
 
-	found = memblock_find_base(size, align, max_addr);
+	found = memblock_find_base(size, align, 0, max_addr);
 	if (found != MEMBLOCK_ERROR &&
 	    memblock_add_region(&memblock.reserved, found, size) >= 0)
 		return found;

index 15da7d9..b69c243 100644
@@ -47,6 +47,9 @@ extern long memblock_remove(phys_addr_t base, phys_addr_t size);
 extern long __init memblock_free(phys_addr_t base, phys_addr_t size);
 extern long __init memblock_reserve(phys_addr_t base, phys_addr_t size);
 
+/* The numa aware allocator is only available if
+ * CONFIG_ARCH_POPULATES_NODE_MAP is set
+ */
 extern phys_addr_t __init memblock_alloc_nid(phys_addr_t size, phys_addr_t align, int nid);
 extern phys_addr_t __init memblock_alloc(phys_addr_t size, phys_addr_t align);
 

index b4870cf..a9c15a5 100644
@@ -15,6 +15,7 @@
 #include <linux/init.h>
 #include <linux/bitops.h>
 #include <linux/poison.h>
+#include <linux/pfn.h>
 #include <linux/memblock.h>
 
 struct memblock memblock;

@@ -451,11 +452,36 @@ phys_addr_t __init memblock_alloc(phys_addr_t size, phys_addr_t align)
 /*
  * Additional node-local allocators. Search for node memory is bottom up
  * and walks memblock regions within that node bottom-up as well, but allocation
- * within an memblock region is top-down.
+ * within an memblock region is top-down. XXX I plan to fix that at some stage
+ *
+ * WARNING: Only available after early_node_map[] has been populated,
+ * on some architectures, that is after all the calls to add_active_range()
+ * have been done to populate it.
  */
 
 phys_addr_t __weak __init memblock_nid_range(phys_addr_t start, phys_addr_t end, int *nid)
 {
+#ifdef CONFIG_ARCH_POPULATES_NODE_MAP
+	/*
+	 * This code originates from sparc which really wants use to walk by addresses
+	 * and returns the nid. This is not very convenient for early_pfn_map[] users
+	 * as the map isn't sorted yet, and it really wants to be walked by nid.
+	 *
+	 * For now, I implement the inefficient method below which walks the early
+	 * map multiple times. Eventually we may want to use an ARCH config option
+	 * to implement a completely different method for both case.
+	 */
+	unsigned long start_pfn, end_pfn;
+	int i;
+
+	for (i = 0; i < MAX_NUMNODES; i++) {
+		get_pfn_range_for_nid(i, &start_pfn, &end_pfn);
+		if (start < PFN_PHYS(start_pfn) || start >= PFN_PHYS(end_pfn))
+			continue;
+		*nid = i;
+		return min(end, PFN_PHYS(end_pfn));
+	}
+#endif
 	*nid = 0;
 
 	return end;

index 0883113..dc584d2 100644
@@ -820,7 +820,7 @@ static void __init allocate_node_data(int nid)
 	struct pglist_data *p;
 
 #ifdef CONFIG_NEED_MULTIPLE_NODES
-	paddr = memblock_alloc_nid(sizeof(struct pglist_data), SMP_CACHE_BYTES, nid);
+	paddr = memblock_alloc_try_nid(sizeof(struct pglist_data), SMP_CACHE_BYTES, nid);
 	if (!paddr) {
 		prom_printf("Cannot allocate pglist_data for nid[%d]\n", nid);
 		prom_halt();

@@ -840,7 +840,7 @@ static void __init allocate_node_data(int nid)
 	if (p->node_spanned_pages) {
 		num_pages = bootmem_bootmap_pages(p->node_spanned_pages);
 
-		paddr = memblock_alloc_nid(num_pages << PAGE_SHIFT, PAGE_SIZE, nid);
+		paddr = memblock_alloc_try_nid(num_pages << PAGE_SHIFT, PAGE_SIZE, nid);
 		if (!paddr) {
 			prom_printf("Cannot allocate bootmap for nid[%d]\n",
 				  nid);

index b69c243..08a12cf 100644
@@ -50,7 +50,11 @@ extern long __init memblock_reserve(phys_addr_t base, phys_addr_t size);
 /* The numa aware allocator is only available if
  * CONFIG_ARCH_POPULATES_NODE_MAP is set
  */
-extern phys_addr_t __init memblock_alloc_nid(phys_addr_t size, phys_addr_t align, int nid);
+extern phys_addr_t __init memblock_alloc_nid(phys_addr_t size, phys_addr_t align,
+					int nid);
+extern phys_addr_t __init memblock_alloc_try_nid(phys_addr_t size, phys_addr_t align,
+					    int nid);
+
 extern phys_addr_t __init memblock_alloc(phys_addr_t size, phys_addr_t align);
 
 /* Flags for memblock_alloc_base() amd __memblock_alloc_base() */

index a9c15a5..c3c499e 100644
@@ -537,9 +537,23 @@ phys_addr_t __init memblock_alloc_nid(phys_addr_t size, phys_addr_t align, int n
 			return ret;
 	}
 
+	return 0;
+}
+
+phys_addr_t __init memblock_alloc_try_nid(phys_addr_t size, phys_addr_t align, int nid)
+{
+	phys_addr_t res = memblock_alloc_nid(size, align, nid);
+
+	if (res)
+		return res;
 	return memblock_alloc(size, align);
 }
 
+
+/*
+ * Remaining API functions
+ */
+
 /* You must call memblock_analyze() before this. */
 phys_addr_t __init memblock_phys_mem_size(void)
 {

index c3c499e..424ca11 100644
@@ -546,7 +546,7 @@ phys_addr_t __init memblock_alloc_try_nid(phys_addr_t size, phys_addr_t align, i
 
 	if (res)
 		return res;
-	return memblock_alloc(size, align);
+	return memblock_alloc_base(size, align, MEMBLOCK_ALLOC_ANYWHERE);
 }
 
 

index 424ca11..b5eb901 100644
@@ -16,6 +16,8 @@
 #include <linux/bitops.h>
 #include <linux/poison.h>
 #include <linux/pfn.h>
+#include <linux/debugfs.h>
+#include <linux/seq_file.h>
 #include <linux/memblock.h>
 
 struct memblock memblock;

@@ -714,3 +716,52 @@ static int __init early_memblock(char *p)
 }
 early_param("memblock", early_memblock);
 
+#ifdef CONFIG_DEBUG_FS
+
+static int memblock_debug_show(struct seq_file *m, void *private)
+{
+	struct memblock_type *type = m->private;
+	struct memblock_region *reg;
+	int i;
+
+	for (i = 0; i < type->cnt; i++) {
+		reg = &type->regions[i];
+		seq_printf(m, "%4d: ", i);
+		if (sizeof(phys_addr_t) == 4)
+			seq_printf(m, "0x%08lx..0x%08lx\n",
+				   (unsigned long)reg->base,
+				   (unsigned long)(reg->base + reg->size - 1));
+		else
+			seq_printf(m, "0x%016llx..0x%016llx\n",
+				   (unsigned long long)reg->base,
+				   (unsigned long long)(reg->base + reg->size - 1));
+
+	}
+	return 0;
+}
+
+static int memblock_debug_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, memblock_debug_show, inode->i_private);
+}
+
+static const struct file_operations memblock_debug_fops = {
+	.open = memblock_debug_open,
+	.read = seq_read,
+	.llseek = seq_lseek,
+	.release = single_release,
+};
+
+static int __init memblock_init_debugfs(void)
+{
+	struct dentry *root = debugfs_create_dir("memblock", NULL);
+	if (!root)
+		return -ENXIO;
+	debugfs_create_file("memory", S_IRUGO, root, &memblock.memory, &memblock_debug_fops);
+	debugfs_create_file("reserved", S_IRUGO, root, &memblock.reserved, &memblock_debug_fops);
+
+	return 0;
+}
+__initcall(memblock_init_debugfs);
+
+#endif /* CONFIG_DEBUG_FS */

index 08a12cf..70bc467 100644
@@ -39,6 +39,12 @@ struct memblock {
 };
 
 extern struct memblock memblock;
+extern int memblock_debug;
+extern int memblock_can_resize;
+extern struct memblock_region memblock_reserved_init_regions[];
+
+#define memblock_dbg(fmt, ...) \
+	if (memblock_debug) printk(KERN_INFO pr_fmt(fmt), ##__VA_ARGS__)
 
 extern void __init memblock_init(void);
 extern void __init memblock_analyze(void);

index b5eb901..c16d4c6 100644
@@ -22,9 +22,10 @@
 
 struct memblock memblock;
 
-static int memblock_debug, memblock_can_resize;
+int memblock_debug;
+int memblock_can_resize;
 static struct memblock_region memblock_memory_init_regions[INIT_MEMBLOCK_REGIONS + 1];
-static struct memblock_region memblock_reserved_init_regions[INIT_MEMBLOCK_REGIONS + 1];
+struct memblock_region memblock_reserved_init_regions[INIT_MEMBLOCK_REGIONS + 1];
 
 #define MEMBLOCK_ERROR	(~(phys_addr_t)0)
 

index c16d4c6..796ef8c 100644
@@ -192,8 +192,6 @@ static int memblock_double_array(struct memblock_type *type)
 	if (!memblock_can_resize)
 		return -1;
 
-	pr_debug("memblock: %s array full, doubling...", memblock_type_name(type));
-
 	/* Calculate new doubled size */
 	old_size = type->max * sizeof(struct memblock_region);
 	new_size = old_size << 1;

@@ -221,6 +219,9 @@ static int memblock_double_array(struct memblock_type *type)
 	}
 	new_array = __va(addr);
 
+	memblock_dbg("memblock: %s array is doubled to %ld at [%#010llx-%#010llx]",
+		 memblock_type_name(type), type->max * 2, (u64)addr, (u64)addr + new_size - 1);
+
 	/* Found space, we now need to move the array over before
 	 * we add the reserved region since it may be our reserved
 	 * array itself that is full.

@@ -646,7 +647,7 @@ static void memblock_dump(struct memblock_type *region, char *name)
 		base = region->regions[i].base;
 		size = region->regions[i].size;
 
-		pr_info(" %s[0x%x]\t0x%016llx - 0x%016llx, 0x%llx bytes\n",
+		pr_info(" %s[%#x]\t[%#016llx-%#016llx], %#llx bytes\n",
 		    name, i, base, base + size - 1, size);
 	}
 }

index 70bc467..89749c4 100644
@@ -19,6 +19,7 @@
 #include <asm/memblock.h>
 
 #define INIT_MEMBLOCK_REGIONS 128
+#define MEMBLOCK_ERROR		0
 
 struct memblock_region {
 	phys_addr_t base;

index 796ef8c..3d0a754 100644
@@ -27,8 +27,6 @@ int memblock_can_resize;
 static struct memblock_region memblock_memory_init_regions[INIT_MEMBLOCK_REGIONS + 1];
 struct memblock_region memblock_reserved_init_regions[INIT_MEMBLOCK_REGIONS + 1];
 
-#define MEMBLOCK_ERROR	(~(phys_addr_t)0)
-
 /* inline so we don't get a warning when pr_debug is compiled out */
 static inline const char *memblock_type_name(struct memblock_type *type)
 {