[PATCH -v4 00/08] use lmb with x86

[PATCH -v4 00/08] use lmb with x86

[Yinghai Lu]

new early_res is lmb extension. and it could be used to replace bootmem.

even could share some code before bootmem, like register_active_region, and
lm_reserved_to_bootmem

add test version for powerpc

Thanks

Yinghai

[PATCH 1/8] x86: do not free zero sized per cpu areas

[Yinghai Lu]

From: Ian Campbell <ian.campbell@citrix.com>

This avoids an infinite loop in free_early_partial().

Add a warning to free_early_partial to catch future problems.

-v5: put back start > end back into WARN_ONCE()
-v6: use one line for if according to linus

Signed-off-by: Ian Campbell <ian.campbell@citrix.com>
Signed-off-by: Yinghai Lu <yinghai@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ingo Molnar <mingo@elte.hu>
---
 kernel/early_res.c |    6 ++++++
 1 files changed, 6 insertions(+), 0 deletions(-)

diff --git a/kernel/early_res.c b/kernel/early_res.c
index 3cb2c66..69bed5b 100644
--- a/kernel/early_res.c
+++ b/kernel/early_res.c
@@ -333,6 +333,12 @@ void __init free_early_partial(u64 start, u64 end)
 	struct early_res *r;
 	int i;
 
+	if (start == end)
+		return;
+
+	if (WARN_ONCE(start > end, "free_early_partial: wrong range [%#llx, %#llx]\n", start, end))
+		return;
+
 try_next:
 	i = find_overlapped_early(start, end);
 	if (i >= max_early_res)
-- 
1.6.4.2

[PATCH 2/8] x86: add find_e820_area_node

[Yinghai Lu]

David Miller pointed out that early_res have problem to find node data on correct node
when we have
node0: [0, 2g), [4g, 6g), [10g, 14g)
node1: [6g, 10g), [14g, 18g)
the cross node case

the problem is there for x86 bits even before we are using early_res for bootmem replacement.
after early_res for bootmem replacement, alloc_bootmem_node still can get range on correct node

this patch is fixing problem before bootmem or early_res replacement for bootmem.

now only user is for x86 64bit numa to find node data.

the point is use early_node_map with find_e820_area_node()

Signed-off-by: Yinghai Lu <yinghai@kernel.org>
---
 arch/x86/include/asm/e820.h |    1 +
 arch/x86/kernel/e820.c      |   15 +++++++++++++++
 arch/x86/mm/numa_64.c       |    4 ++--
 include/linux/mm.h          |    2 ++
 mm/page_alloc.c             |   37 +++++++++++++++++++++++--------------
 5 files changed, 43 insertions(+), 16 deletions(-)

diff --git a/arch/x86/include/asm/e820.h b/arch/x86/include/asm/e820.h
index ec8a52d..41553af 100644
--- a/arch/x86/include/asm/e820.h
+++ b/arch/x86/include/asm/e820.h
@@ -116,6 +116,7 @@ extern unsigned long end_user_pfn;
 
 extern u64 find_e820_area(u64 start, u64 end, u64 size, u64 align);
 extern u64 find_e820_area_size(u64 start, u64 *sizep, u64 align);
+u64 find_e820_area_node(int nid, u64 start, u64 end, u64 size, u64 align);
 extern u64 early_reserve_e820(u64 startt, u64 sizet, u64 align);
 #include <linux/early_res.h>
 
diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c
index 740b440..05ee724 100644
--- a/arch/x86/kernel/e820.c
+++ b/arch/x86/kernel/e820.c
@@ -787,6 +787,21 @@ u64 __init find_e820_area_size(u64 start, u64 *sizep, u64 align)
 	return -1ULL;
 }
 
+u64 __init find_e820_area_node(int nid, u64 start, u64 end, u64 size, u64 align)
+{
+	u64 addr;
+	/*
+	 * need to call this function after e820_register_active_regions
+	 * so early_node_map[] is set
+	 */
+	addr = find_memory_core_early(nid, size, align, start, end);
+	if (addr != -1ULL)
+		return addr;
+
+	/* fallback, should already have start end in the node range */
+	return find_e820_area(start, end, size, align);
+}
+
 /*
  * pre allocated 4k and reserved it in e820
  */
diff --git a/arch/x86/mm/numa_64.c b/arch/x86/mm/numa_64.c
index 8948f47..ffc5ad5 100644
--- a/arch/x86/mm/numa_64.c
+++ b/arch/x86/mm/numa_64.c
@@ -174,7 +174,7 @@ static void * __init early_node_mem(int nodeid, unsigned long start,
 	if (start < (MAX_DMA32_PFN<<PAGE_SHIFT) &&
 	    end > (MAX_DMA32_PFN<<PAGE_SHIFT))
 		start = MAX_DMA32_PFN<<PAGE_SHIFT;
-	mem = find_e820_area(start, end, size, align);
+	mem = find_e820_area_node(nodeid, start, end, size, align);
 	if (mem != -1L)
 		return __va(mem);
 
@@ -184,7 +184,7 @@ static void * __init early_node_mem(int nodeid, unsigned long start,
 		start = MAX_DMA32_PFN<<PAGE_SHIFT;
 	else
 		start = MAX_DMA_PFN<<PAGE_SHIFT;
-	mem = find_e820_area(start, end, size, align);
+	mem = find_e820_area_node(nodeid, start, end, size, align);
 	if (mem != -1L)
 		return __va(mem);
 
diff --git a/include/linux/mm.h b/include/linux/mm.h
index e70f21b..5c2d17e 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1160,6 +1160,8 @@ extern void free_bootmem_with_active_regions(int nid,
 						unsigned long max_low_pfn);
 int add_from_early_node_map(struct range *range, int az,
 				   int nr_range, int nid);
+u64 __init find_memory_core_early(int nid, u64 size, u64 align,
+					u64 goal, u64 limit);
 void *__alloc_memory_core_early(int nodeid, u64 size, u64 align,
 				 u64 goal, u64 limit);
 typedef int (*work_fn_t)(unsigned long, unsigned long, void *);
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index d03c946..eef3757 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -3408,12 +3408,11 @@ int __init add_from_early_node_map(struct range *range, int az,
 	return nr_range;
 }
 
-#ifdef CONFIG_NO_BOOTMEM
-void * __init __alloc_memory_core_early(int nid, u64 size, u64 align,
+#ifdef CONFIG_HAVE_EARLY_RES
+u64 __init find_memory_core_early(int nid, u64 size, u64 align,
 					u64 goal, u64 limit)
 {
 	int i;
-	void *ptr;
 
 	/* need to go over early_node_map to find out good range for node */
 	for_each_active_range_index_in_nid(i, nid) {
@@ -3430,20 +3429,30 @@ void * __init __alloc_memory_core_early(int nid, u64 size, u64 align,
 		if (addr == -1ULL)
 			continue;
 
-#if 0
-		printk(KERN_DEBUG "alloc (nid=%d %llx - %llx) (%llx - %llx) %llx %llx => %llx\n",
-				nid,
-				ei_start, ei_last, goal, limit, size,
-				align, addr);
+		return addr;
+	}
+
+	return -1ULL;
+}
 #endif
 
-		ptr = phys_to_virt(addr);
-		memset(ptr, 0, size);
-		reserve_early_without_check(addr, addr + size, "BOOTMEM");
-		return ptr;
-	}
+#ifdef CONFIG_NO_BOOTMEM
+void * __init __alloc_memory_core_early(int nid, u64 size, u64 align,
+					u64 goal, u64 limit)
+{
+	void *ptr;
 
-	return NULL;
+	u64 addr;
+
+	addr = find_memory_core_early(nid, size, align, goal, limit);
+
+	if (addr == -1ULL)
+		return NULL;
+
+	ptr = phys_to_virt(addr);
+	memset(ptr, 0, size);
+	reserve_early_without_check(addr, addr + size, "BOOTMEM");
+	return ptr;
 }
 #endif
 
-- 
1.6.4.2

[PATCH 3/8] x86: add sanitize_e820_map

[Yinghai Lu]

so we could not take e820.map directly.

and could change e820_saved to initdata

Signed-off-by: Yinghai Lu <yinghai@kernel.org>
---
 arch/x86/include/asm/e820.h |    5 ++---
 arch/x86/kernel/e820.c      |   26 ++++++++++++++++++--------
 arch/x86/kernel/efi.c       |    2 +-
 arch/x86/kernel/setup.c     |   10 +++++-----
 arch/x86/xen/setup.c        |    4 +---
 5 files changed, 27 insertions(+), 20 deletions(-)

diff --git a/arch/x86/include/asm/e820.h b/arch/x86/include/asm/e820.h
index 41553af..01bc987 100644
--- a/arch/x86/include/asm/e820.h
+++ b/arch/x86/include/asm/e820.h
@@ -75,15 +75,14 @@ struct e820map {
 #ifdef __KERNEL__
 /* see comment in arch/x86/kernel/e820.c */
 extern struct e820map e820;
-extern struct e820map e820_saved;
 
 extern unsigned long pci_mem_start;
 extern int e820_any_mapped(u64 start, u64 end, unsigned type);
 extern int e820_all_mapped(u64 start, u64 end, unsigned type);
 extern void e820_add_region(u64 start, u64 size, int type);
 extern void e820_print_map(char *who);
-extern int
-sanitize_e820_map(struct e820entry *biosmap, int max_nr_map, u32 *pnr_map);
+int sanitize_e820_map(void);
+void save_e820_map(void);
 extern u64 e820_update_range(u64 start, u64 size, unsigned old_type,
 			       unsigned new_type);
 extern u64 e820_remove_range(u64 start, u64 size, unsigned old_type,
diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c
index 05ee724..0c7143b 100644
--- a/arch/x86/kernel/e820.c
+++ b/arch/x86/kernel/e820.c
@@ -35,7 +35,7 @@
  * next kernel with full memory.
  */
 struct e820map e820;
-struct e820map e820_saved;
+static struct e820map __initdata e820_saved;
 
 /* For PCI or other memory-mapped resources */
 unsigned long pci_mem_start = 0xaeedbabe;
@@ -224,7 +224,7 @@ void __init e820_print_map(char *who)
  *	   ______________________4_
  */
 
-int __init sanitize_e820_map(struct e820entry *biosmap, int max_nr_map,
+static int __init __sanitize_e820_map(struct e820entry *biosmap, int max_nr_map,
 			     u32 *pnr_map)
 {
 	struct change_member {
@@ -383,6 +383,11 @@ int __init sanitize_e820_map(struct e820entry *biosmap, int max_nr_map,
 	return 0;
 }
 
+int __init sanitize_e820_map(void)
+{
+	return __sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &e820.nr_map);
+}
+
 static int __init __append_e820_map(struct e820entry *biosmap, int nr_map)
 {
 	while (nr_map) {
@@ -555,7 +560,7 @@ void __init update_e820(void)
 	u32 nr_map;
 
 	nr_map = e820.nr_map;
-	if (sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &nr_map))
+	if (__sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &nr_map))
 		return;
 	e820.nr_map = nr_map;
 	printk(KERN_INFO "modified physical RAM map:\n");
@@ -566,7 +571,7 @@ static void __init update_e820_saved(void)
 	u32 nr_map;
 
 	nr_map = e820_saved.nr_map;
-	if (sanitize_e820_map(e820_saved.map, ARRAY_SIZE(e820_saved.map), &nr_map))
+	if (__sanitize_e820_map(e820_saved.map, ARRAY_SIZE(e820_saved.map), &nr_map))
 		return;
 	e820_saved.nr_map = nr_map;
 }
@@ -661,7 +666,7 @@ void __init parse_e820_ext(struct setup_data *sdata, unsigned long pa_data)
 		sdata = early_ioremap(pa_data, map_len);
 	extmap = (struct e820entry *)(sdata->data);
 	__append_e820_map(extmap, entries);
-	sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &e820.nr_map);
+	sanitize_e820_map();
 	if (map_len > PAGE_SIZE)
 		early_iounmap(sdata, map_len);
 	printk(KERN_INFO "extended physical RAM map:\n");
@@ -1043,7 +1048,7 @@ void __init finish_e820_parsing(void)
 	if (userdef) {
 		u32 nr = e820.nr_map;
 
-		if (sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &nr) < 0)
+		if (__sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &nr) < 0)
 			early_panic("Invalid user supplied memory map");
 		e820.nr_map = nr;
 
@@ -1173,7 +1178,7 @@ char *__init default_machine_specific_memory_setup(void)
 	 * the next section from 1mb->appropriate_mem_k
 	 */
 	new_nr = boot_params.e820_entries;
-	sanitize_e820_map(boot_params.e820_map,
+	__sanitize_e820_map(boot_params.e820_map,
 			ARRAY_SIZE(boot_params.e820_map),
 			&new_nr);
 	boot_params.e820_entries = new_nr;
@@ -1200,12 +1205,17 @@ char *__init default_machine_specific_memory_setup(void)
 	return who;
 }
 
+void __init save_e820_map(void)
+{
+	memcpy(&e820_saved, &e820, sizeof(struct e820map));
+}
+
 void __init setup_memory_map(void)
 {
 	char *who;
 
 	who = x86_init.resources.memory_setup();
-	memcpy(&e820_saved, &e820, sizeof(struct e820map));
+	save_e820_map();
 	printk(KERN_INFO "BIOS-provided physical RAM map:\n");
 	e820_print_map(who);
 }
diff --git a/arch/x86/kernel/efi.c b/arch/x86/kernel/efi.c
index c2fa9b8..299f03f 100644
--- a/arch/x86/kernel/efi.c
+++ b/arch/x86/kernel/efi.c
@@ -272,7 +272,7 @@ static void __init do_add_efi_memmap(void)
 		}
 		e820_add_region(start, size, e820_type);
 	}
-	sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &e820.nr_map);
+	sanitize_e820_map();
 }
 
 void __init efi_reserve_early(void)
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 5d7ba1a..3787a82 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -461,8 +461,8 @@ static void __init e820_reserve_setup_data(void)
 	if (!found)
 		return;
 
-	sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &e820.nr_map);
-	memcpy(&e820_saved, &e820, sizeof(struct e820map));
+	sanitize_e820_map();
+	save_e820_map();
 	printk(KERN_INFO "extended physical RAM map:\n");
 	e820_print_map("reserve setup_data");
 }
@@ -614,7 +614,7 @@ static int __init dmi_low_memory_corruption(const struct dmi_system_id *d)
 		d->ident);
 
 	e820_update_range(0, 0x10000, E820_RAM, E820_RESERVED);
-	sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &e820.nr_map);
+	sanitize_e820_map();
 
 	return 0;
 }
@@ -683,7 +683,7 @@ static void __init trim_bios_range(void)
 	 * take them out.
 	 */
 	e820_remove_range(BIOS_BEGIN, BIOS_END - BIOS_BEGIN, E820_RAM, 1);
-	sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &e820.nr_map);
+	sanitize_e820_map();
 }
 
 /*
@@ -854,7 +854,7 @@ void __init setup_arch(char **cmdline_p)
 	if (ppro_with_ram_bug()) {
 		e820_update_range(0x70000000ULL, 0x40000ULL, E820_RAM,
 				  E820_RESERVED);
-		sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &e820.nr_map);
+		sanitize_e820_map();
 		printk(KERN_INFO "fixed physical RAM map:\n");
 		e820_print_map("bad_ppro");
 	}
diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c
index ad0047f..3f2c411 100644
--- a/arch/x86/xen/setup.c
+++ b/arch/x86/xen/setup.c
@@ -43,8 +43,6 @@ char * __init xen_memory_setup(void)
 
 	max_pfn = min(MAX_DOMAIN_PAGES, max_pfn);
 
-	e820.nr_map = 0;
-
 	e820_add_region(0, PFN_PHYS((u64)max_pfn), E820_RAM);
 
 	/*
@@ -65,7 +63,7 @@ char * __init xen_memory_setup(void)
 		      __pa(xen_start_info->pt_base),
 			"XEN START INFO");
 
-	sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &e820.nr_map);
+	sanitize_e820_map();
 
 	return "Xen";
 }
-- 
1.6.4.2

[PATCH 4/8] lmb: seperate region array from lmb_region struct

[Yinghai Lu]

lmb_init() connect them back.

also add nr_regions in lmb_region to tack the region array size.

-v3: seperate lmb core change to seperated patch
-v4: according to Ingo, change >= x -1 to > x
     change region_array_size to nr_regions

Signed-off-by: Yinghai Lu <yinghai@kernel.org>
---
 include/linux/lmb.h |    5 ++++-
 lib/lmb.c           |    9 ++++++++-
 2 files changed, 12 insertions(+), 2 deletions(-)

diff --git a/include/linux/lmb.h b/include/linux/lmb.h
index f3d1433..37fd29e 100644
--- a/include/linux/lmb.h
+++ b/include/linux/lmb.h
@@ -26,7 +26,8 @@ struct lmb_property {
 struct lmb_region {
 	unsigned long cnt;
 	u64 size;
-	struct lmb_property region[MAX_LMB_REGIONS+1];
+	struct lmb_property *region;
+	unsigned long nr_regions;
 };
 
 struct lmb {
@@ -37,6 +38,8 @@ struct lmb {
 };
 
 extern struct lmb lmb;
+extern struct lmb_property lmb_memory_region[MAX_LMB_REGIONS + 1];
+extern struct lmb_property lmb_reserved_region[MAX_LMB_REGIONS + 1];
 
 extern void __init lmb_init(void);
 extern void __init lmb_analyze(void);
diff --git a/lib/lmb.c b/lib/lmb.c
index b1fc526..ed4e433 100644
--- a/lib/lmb.c
+++ b/lib/lmb.c
@@ -18,6 +18,8 @@
 #define LMB_ALLOC_ANYWHERE	0
 
 struct lmb lmb;
+struct lmb_property lmb_memory_region[MAX_LMB_REGIONS + 1];
+struct lmb_property lmb_reserved_region[MAX_LMB_REGIONS + 1];
 
 static int lmb_debug;
 
@@ -106,6 +108,11 @@ static void lmb_coalesce_regions(struct lmb_region *rgn,
 
 void __init lmb_init(void)
 {
+	lmb.memory.region   = lmb_memory_region;
+	lmb.reserved.region = lmb_reserved_region;
+	lmb.memory.nr_regions   = ARRAY_SIZE(lmb_memory_region);
+	lmb.reserved.nr_regions = ARRAY_SIZE(lmb_reserved_region);
+
 	/* Create a dummy zero size LMB which will get coalesced away later.
 	 * This simplifies the lmb_add() code below...
 	 */
@@ -169,7 +176,7 @@ static long lmb_add_region(struct lmb_region *rgn, u64 base, u64 size)
 
 	if (coalesced)
 		return coalesced;
-	if (rgn->cnt >= MAX_LMB_REGIONS)
+	if (rgn->cnt > rgn->nr_regions)
 		return -1;
 
 	/* Couldn't coalesce the LMB, so add it to the sorted table. */
-- 
1.6.4.2

[PATCH 5/8] x86: use lmb to replace early_res

[Yinghai Lu]

still keep kernel/early_res.c for the extension.

should move those file to lib/lmb.c later?

in early_res.c
1. change find_e820_area_xxx, to find_lmb_area_xxx
2. e820_register_active_regions to lmb_register_active_regions.
3. reserve_early will call lmb_reserve directly.
4. free_early will call lmb_free directly.
5. remove functions that are used by old reserve_early and free_early
6. get_free_all_memory_range use lmb.reserved.
7. early_res_to_bootmem use lmb.reserved
8. add fill_lmb_memory() to fill lmb.memory according e820 RAM entries

-v2: fix NO_BOOTMEM hang with printk
-v4: add add_lmb_memory that could increase lmb.memory.region size
     change region_array_size to nr_regions
     make sure some find_lmb_area<_size> are called after fill_lmb_memory

todo:
1. make early_memtest to depend on early_res. and move it to mm/
2. make all lmb user to use extend early_res/nobootmem
3. merge lmb.c and early_res.c, move it to mm/
4. make other platform to use lmb/early_res/nobootmem
5. remove BOOTMEM related code

Signed-off-by: Yinghai Lu <yinghai@kernel.org>
---
 arch/x86/Kconfig               |    1 +
 arch/x86/include/asm/e820.h    |   38 ++-
 arch/x86/include/asm/lmb.h     |    8 +
 arch/x86/kernel/check.c        |   14 +-
 arch/x86/kernel/e820.c         |  171 ++---------
 arch/x86/kernel/head.c         |    2 +-
 arch/x86/kernel/head32.c       |    5 +-
 arch/x86/kernel/head64.c       |    2 +
 arch/x86/kernel/setup.c        |    9 +-
 arch/x86/kernel/setup_percpu.c |    6 -
 arch/x86/mm/memtest.c          |    5 +-
 arch/x86/mm/numa_64.c          |    4 +-
 include/linux/early_res.h      |   19 +-
 kernel/early_res.c             |  631 ++++++++++++++++------------------------
 mm/page_alloc.c                |    2 +-
 mm/sparse-vmemmap.c            |   11 -
 16 files changed, 344 insertions(+), 584 deletions(-)
 create mode 100644 arch/x86/include/asm/lmb.h

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 6a80bce..585f611 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -27,6 +27,7 @@ config X86
 	select HAVE_PERF_EVENTS if (!M386 && !M486)
 	select HAVE_IOREMAP_PROT
 	select HAVE_KPROBES
+	select HAVE_LMB
 	select ARCH_WANT_OPTIONAL_GPIOLIB
 	select ARCH_WANT_FRAME_POINTERS
 	select HAVE_DMA_ATTRS
diff --git a/arch/x86/include/asm/e820.h b/arch/x86/include/asm/e820.h
index 01bc987..e957101 100644
--- a/arch/x86/include/asm/e820.h
+++ b/arch/x86/include/asm/e820.h
@@ -111,24 +111,30 @@ static inline void early_memtest(unsigned long start, unsigned long end)
 }
 #endif
 
-extern unsigned long end_user_pfn;
-
-extern u64 find_e820_area(u64 start, u64 end, u64 size, u64 align);
-extern u64 find_e820_area_size(u64 start, u64 *sizep, u64 align);
-u64 find_e820_area_node(int nid, u64 start, u64 end, u64 size, u64 align);
-extern u64 early_reserve_e820(u64 startt, u64 sizet, u64 align);
-#include <linux/early_res.h>
-
 extern unsigned long e820_end_of_ram_pfn(void);
 extern unsigned long e820_end_of_low_ram_pfn(void);
-extern int e820_find_active_region(const struct e820entry *ei,
-				  unsigned long start_pfn,
-				  unsigned long last_pfn,
-				  unsigned long *ei_startpfn,
-				  unsigned long *ei_endpfn);
-extern void e820_register_active_regions(int nid, unsigned long start_pfn,
-					 unsigned long end_pfn);
-extern u64 e820_hole_size(u64 start, u64 end);
+#include <linux/early_res.h>
+extern u64 early_reserve_e820(u64 startt, u64 sizet, u64 align);
+
+/*
+ * next three functions will be removed, esp find_e820_area()
+ * can not be used before fill_lmb_memory()
+ */
+static inline u64 find_e820_area(u64 start, u64 end, u64 size, u64 align)
+{
+	return find_lmb_area(start, end, size, align);
+}
+static inline void e820_register_active_regions(int nid, unsigned long start_pfn, unsigned long end_pfn)
+{
+	lmb_register_active_regions(nid, start_pfn, end_pfn);
+}
+static inline u64 e820_hole_size(u64 start, u64 end)
+{
+	return lmb_hole_size(start, end);
+}
+
+void init_lmb_memory(void);
+void fill_lmb_memory(void);
 extern void finish_e820_parsing(void);
 extern void e820_reserve_resources(void);
 extern void e820_reserve_resources_late(void);
diff --git a/arch/x86/include/asm/lmb.h b/arch/x86/include/asm/lmb.h
new file mode 100644
index 0000000..d8fbdbd
--- /dev/null
+++ b/arch/x86/include/asm/lmb.h
@@ -0,0 +1,8 @@
+#ifndef _X86_LMB_H
+#define _X86_LMB_H
+
+#define LMB_DBG(fmt...) printk(fmt)
+
+#define LMB_REAL_LIMIT	0
+
+#endif
diff --git a/arch/x86/kernel/check.c b/arch/x86/kernel/check.c
index fc999e6..e16952b 100644
--- a/arch/x86/kernel/check.c
+++ b/arch/x86/kernel/check.c
@@ -2,7 +2,8 @@
 #include <linux/sched.h>
 #include <linux/kthread.h>
 #include <linux/workqueue.h>
-#include <asm/e820.h>
+#include <linux/early_res.h>
+
 #include <asm/proto.h>
 
 /*
@@ -18,10 +19,12 @@ static int __read_mostly memory_corruption_check = -1;
 static unsigned __read_mostly corruption_check_size = 64*1024;
 static unsigned __read_mostly corruption_check_period = 60; /* seconds */
 
-static struct e820entry scan_areas[MAX_SCAN_AREAS];
+static struct scan_area {
+	u64 addr;
+	u64 size;
+} scan_areas[MAX_SCAN_AREAS];
 static int num_scan_areas;
 
-
 static __init int set_corruption_check(char *arg)
 {
 	char *end;
@@ -81,7 +84,7 @@ void __init setup_bios_corruption_check(void)
 
 	while (addr < corruption_check_size && num_scan_areas < MAX_SCAN_AREAS) {
 		u64 size;
-		addr = find_e820_area_size(addr, &size, PAGE_SIZE);
+		addr = find_lmb_area_size(addr, &size, PAGE_SIZE);
 
 		if (!(addr + 1))
 			break;
@@ -92,7 +95,7 @@ void __init setup_bios_corruption_check(void)
 		if ((addr + size) > corruption_check_size)
 			size = corruption_check_size - addr;
 
-		e820_update_range(addr, size, E820_RAM, E820_RESERVED);
+		reserve_early(addr, addr + size, "SCAN RAM");
 		scan_areas[num_scan_areas].addr = addr;
 		scan_areas[num_scan_areas].size = size;
 		num_scan_areas++;
@@ -105,7 +108,6 @@ void __init setup_bios_corruption_check(void)
 
 	printk(KERN_INFO "Scanning %d areas for low memory corruption\n",
 	       num_scan_areas);
-	update_e820();
 }
 
 
diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c
index 0c7143b..8381b1b 100644
--- a/arch/x86/kernel/e820.c
+++ b/arch/x86/kernel/e820.c
@@ -15,6 +15,7 @@
 #include <linux/pfn.h>
 #include <linux/suspend.h>
 #include <linux/firmware-map.h>
+#include <linux/lmb.h>
 
 #include <asm/e820.h>
 #include <asm/proto.h>
@@ -726,37 +727,6 @@ static int __init e820_mark_nvs_memory(void)
 core_initcall(e820_mark_nvs_memory);
 #endif
 
-/*
- * Find a free area with specified alignment in a specific range.
- */
-u64 __init find_e820_area(u64 start, u64 end, u64 size, u64 align)
-{
-	int i;
-
-	for (i = 0; i < e820.nr_map; i++) {
-		struct e820entry *ei = &e820.map[i];
-		u64 addr;
-		u64 ei_start, ei_last;
-
-		if (ei->type != E820_RAM)
-			continue;
-
-		ei_last = ei->addr + ei->size;
-		ei_start = ei->addr;
-		addr = find_early_area(ei_start, ei_last, start, end,
-					 size, align);
-
-		if (addr != -1ULL)
-			return addr;
-	}
-	return -1ULL;
-}
-
-u64 __init find_fw_memmap_area(u64 start, u64 end, u64 size, u64 align)
-{
-	return find_e820_area(start, end, size, align);
-}
-
 u64 __init get_max_mapped(void)
 {
 	u64 end = max_pfn_mapped;
@@ -765,50 +735,9 @@ u64 __init get_max_mapped(void)
 
 	return end;
 }
-/*
- * Find next free range after *start
- */
-u64 __init find_e820_area_size(u64 start, u64 *sizep, u64 align)
-{
-	int i;
-
-	for (i = 0; i < e820.nr_map; i++) {
-		struct e820entry *ei = &e820.map[i];
-		u64 addr;
-		u64 ei_start, ei_last;
-
-		if (ei->type != E820_RAM)
-			continue;
-
-		ei_last = ei->addr + ei->size;
-		ei_start = ei->addr;
-		addr = find_early_area_size(ei_start, ei_last, start,
-					 sizep, align);
-
-		if (addr != -1ULL)
-			return addr;
-	}
-
-	return -1ULL;
-}
-
-u64 __init find_e820_area_node(int nid, u64 start, u64 end, u64 size, u64 align)
-{
-	u64 addr;
-	/*
-	 * need to call this function after e820_register_active_regions
-	 * so early_node_map[] is set
-	 */
-	addr = find_memory_core_early(nid, size, align, start, end);
-	if (addr != -1ULL)
-		return addr;
-
-	/* fallback, should already have start end in the node range */
-	return find_e820_area(start, end, size, align);
-}
 
 /*
- * pre allocated 4k and reserved it in e820
+ * pre allocated 4k and reserved it in lmb and e820_saved
  */
 u64 __init early_reserve_e820(u64 startt, u64 sizet, u64 align)
 {
@@ -817,7 +746,7 @@ u64 __init early_reserve_e820(u64 startt, u64 sizet, u64 align)
 	u64 start;
 
 	for (start = startt; ; start += size) {
-		start = find_e820_area_size(start, &size, align);
+		start = find_lmb_area_size(start, &size, align);
 		if (!(start + 1))
 			return 0;
 		if (size >= sizet)
@@ -834,10 +763,9 @@ u64 __init early_reserve_e820(u64 startt, u64 sizet, u64 align)
 	addr = round_down(start + size - sizet, align);
 	if (addr < start)
 		return 0;
-	e820_update_range(addr, sizet, E820_RAM, E820_RESERVED);
+	reserve_early(addr, addr + sizet, "new next");
 	e820_update_range_saved(addr, sizet, E820_RAM, E820_RESERVED);
-	printk(KERN_INFO "update e820 for early_reserve_e820\n");
-	update_e820();
+	printk(KERN_INFO "update e820_saved for early_reserve_e820\n");
 	update_e820_saved();
 
 	return addr;
@@ -899,74 +827,6 @@ unsigned long __init e820_end_of_low_ram_pfn(void)
 {
 	return e820_end_pfn(1UL<<(32 - PAGE_SHIFT), E820_RAM);
 }
-/*
- * Finds an active region in the address range from start_pfn to last_pfn and
- * returns its range in ei_startpfn and ei_endpfn for the e820 entry.
- */
-int __init e820_find_active_region(const struct e820entry *ei,
-				  unsigned long start_pfn,
-				  unsigned long last_pfn,
-				  unsigned long *ei_startpfn,
-				  unsigned long *ei_endpfn)
-{
-	u64 align = PAGE_SIZE;
-
-	*ei_startpfn = round_up(ei->addr, align) >> PAGE_SHIFT;
-	*ei_endpfn = round_down(ei->addr + ei->size, align) >> PAGE_SHIFT;
-
-	/* Skip map entries smaller than a page */
-	if (*ei_startpfn >= *ei_endpfn)
-		return 0;
-
-	/* Skip if map is outside the node */
-	if (ei->type != E820_RAM || *ei_endpfn <= start_pfn ||
-				    *ei_startpfn >= last_pfn)
-		return 0;
-
-	/* Check for overlaps */
-	if (*ei_startpfn < start_pfn)
-		*ei_startpfn = start_pfn;
-	if (*ei_endpfn > last_pfn)
-		*ei_endpfn = last_pfn;
-
-	return 1;
-}
-
-/* Walk the e820 map and register active regions within a node */
-void __init e820_register_active_regions(int nid, unsigned long start_pfn,
-					 unsigned long last_pfn)
-{
-	unsigned long ei_startpfn;
-	unsigned long ei_endpfn;
-	int i;
-
-	for (i = 0; i < e820.nr_map; i++)
-		if (e820_find_active_region(&e820.map[i],
-					    start_pfn, last_pfn,
-					    &ei_startpfn, &ei_endpfn))
-			add_active_range(nid, ei_startpfn, ei_endpfn);
-}
-
-/*
- * Find the hole size (in bytes) in the memory range.
- * @start: starting address of the memory range to scan
- * @end: ending address of the memory range to scan
- */
-u64 __init e820_hole_size(u64 start, u64 end)
-{
-	unsigned long start_pfn = start >> PAGE_SHIFT;
-	unsigned long last_pfn = end >> PAGE_SHIFT;
-	unsigned long ei_startpfn, ei_endpfn, ram = 0;
-	int i;
-
-	for (i = 0; i < e820.nr_map; i++) {
-		if (e820_find_active_region(&e820.map[i],
-					    start_pfn, last_pfn,
-					    &ei_startpfn, &ei_endpfn))
-			ram += ei_endpfn - ei_startpfn;
-	}
-	return end - start - ((u64)ram << PAGE_SHIFT);
-}
 
 static void early_panic(char *msg)
 {
@@ -1219,3 +1079,24 @@ void __init setup_memory_map(void)
 	printk(KERN_INFO "BIOS-provided physical RAM map:\n");
 	e820_print_map(who);
 }
+
+void __init init_lmb_memory(void)
+{
+	lmb_init();
+}
+
+void __init fill_lmb_memory(void)
+{
+	int i;
+
+	for (i = 0; i < e820.nr_map; i++) {
+		struct e820entry *ei = &e820.map[i];
+
+		if (ei->type != E820_RAM)
+			continue;
+		add_lmb_memory(ei->addr, ei->addr + ei->size);
+	}
+
+	lmb_analyze();
+	lmb_dump_all();
+}
diff --git a/arch/x86/kernel/head.c b/arch/x86/kernel/head.c
index 3e66bd3..e0d0ce5 100644
--- a/arch/x86/kernel/head.c
+++ b/arch/x86/kernel/head.c
@@ -51,5 +51,5 @@ void __init reserve_ebda_region(void)
 		lowmem = 0x9f000;
 
 	/* reserve all memory between lowmem and the 1MB mark */
-	reserve_early_overlap_ok(lowmem, 0x100000, "BIOS reserved");
+	reserve_early(lowmem, 0x100000, "BIOS reserved");
 }
diff --git a/arch/x86/kernel/head32.c b/arch/x86/kernel/head32.c
index adedeef..8983422 100644
--- a/arch/x86/kernel/head32.c
+++ b/arch/x86/kernel/head32.c
@@ -29,14 +29,15 @@ static void __init i386_default_early_setup(void)
 
 void __init i386_start_kernel(void)
 {
+	init_lmb_memory();
+
 #ifdef CONFIG_X86_TRAMPOLINE
 	/*
 	 * But first pinch a few for the stack/trampoline stuff
 	 * FIXME: Don't need the extra page at 4K, but need to fix
 	 * trampoline before removing it. (see the GDT stuff)
 	 */
-	reserve_early_overlap_ok(PAGE_SIZE, PAGE_SIZE + PAGE_SIZE,
-					 "EX TRAMPOLINE");
+	reserve_early(PAGE_SIZE, PAGE_SIZE + PAGE_SIZE, "EX TRAMPOLINE");
 #endif
 
 	reserve_early(__pa_symbol(&_text), __pa_symbol(&__bss_stop), "TEXT DATA BSS");
diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c
index b5a9896..86e6a9b 100644
--- a/arch/x86/kernel/head64.c
+++ b/arch/x86/kernel/head64.c
@@ -96,6 +96,8 @@ void __init x86_64_start_kernel(char * real_mode_data)
 
 void __init x86_64_start_reservations(char *real_mode_data)
 {
+	init_lmb_memory();
+
 	copy_bootdata(__va(real_mode_data));
 
 	reserve_early(__pa_symbol(&_text), __pa_symbol(&__bss_stop), "TEXT DATA BSS");
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 3787a82..a9e99e6 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -868,8 +868,6 @@ void __init setup_arch(char **cmdline_p)
 	 */
 	max_pfn = e820_end_of_ram_pfn();
 
-	/* preallocate 4k for mptable mpc */
-	early_reserve_e820_mpc_new();
 	/* update e820 for memory not covered by WB MTRRs */
 	mtrr_bp_init();
 	if (mtrr_trim_uncached_memory(max_pfn))
@@ -894,6 +892,11 @@ void __init setup_arch(char **cmdline_p)
 	max_pfn_mapped = KERNEL_IMAGE_SIZE >> PAGE_SHIFT;
 #endif
 
+	fill_lmb_memory();
+
+	/* preallocate 4k for mptable mpc */
+	early_reserve_e820_mpc_new();
+
 #ifdef CONFIG_X86_CHECK_BIOS_CORRUPTION
 	setup_bios_corruption_check();
 #endif
@@ -970,7 +973,7 @@ void __init setup_arch(char **cmdline_p)
 
 	initmem_init(0, max_pfn, acpi, k8);
 #ifndef CONFIG_NO_BOOTMEM
-	early_res_to_bootmem(0, max_low_pfn<<PAGE_SHIFT);
+	lmb_reserved_to_bootmem(0, max_low_pfn<<PAGE_SHIFT);
 #endif
 
 	dma32_reserve_bootmem();
diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c
index ef6370b..35abcb8 100644
--- a/arch/x86/kernel/setup_percpu.c
+++ b/arch/x86/kernel/setup_percpu.c
@@ -137,13 +137,7 @@ static void * __init pcpu_fc_alloc(unsigned int cpu, size_t size, size_t align)
 
 static void __init pcpu_fc_free(void *ptr, size_t size)
 {
-#ifdef CONFIG_NO_BOOTMEM
-	u64 start = __pa(ptr);
-	u64 end = start + size;
-	free_early_partial(start, end);
-#else
 	free_bootmem(__pa(ptr), size);
-#endif
 }
 
 static int __init pcpu_cpu_distance(unsigned int from, unsigned int to)
diff --git a/arch/x86/mm/memtest.c b/arch/x86/mm/memtest.c
index 18d244f..216f832 100644
--- a/arch/x86/mm/memtest.c
+++ b/arch/x86/mm/memtest.c
@@ -6,8 +6,7 @@
 #include <linux/smp.h>
 #include <linux/init.h>
 #include <linux/pfn.h>
-
-#include <asm/e820.h>
+#include <linux/early_res.h>
 
 static u64 patterns[] __initdata = {
 	0,
@@ -74,7 +73,7 @@ static void __init do_one_pass(u64 pattern, u64 start, u64 end)
 	u64 size = 0;
 
 	while (start < end) {
-		start = find_e820_area_size(start, &size, 1);
+		start = find_lmb_area_size(start, &size, 1);
 
 		/* done ? */
 		if (start >= end)
diff --git a/arch/x86/mm/numa_64.c b/arch/x86/mm/numa_64.c
index ffc5ad5..45ac950 100644
--- a/arch/x86/mm/numa_64.c
+++ b/arch/x86/mm/numa_64.c
@@ -174,7 +174,7 @@ static void * __init early_node_mem(int nodeid, unsigned long start,
 	if (start < (MAX_DMA32_PFN<<PAGE_SHIFT) &&
 	    end > (MAX_DMA32_PFN<<PAGE_SHIFT))
 		start = MAX_DMA32_PFN<<PAGE_SHIFT;
-	mem = find_e820_area_node(nodeid, start, end, size, align);
+	mem = find_lmb_area_node(nodeid, start, end, size, align);
 	if (mem != -1L)
 		return __va(mem);
 
@@ -184,7 +184,7 @@ static void * __init early_node_mem(int nodeid, unsigned long start,
 		start = MAX_DMA32_PFN<<PAGE_SHIFT;
 	else
 		start = MAX_DMA_PFN<<PAGE_SHIFT;
-	mem = find_e820_area_node(nodeid, start, end, size, align);
+	mem = find_lmb_area_node(nodeid, start, end, size, align);
 	if (mem != -1L)
 		return __va(mem);
 
diff --git a/include/linux/early_res.h b/include/linux/early_res.h
index 29c09f5..4fac619 100644
--- a/include/linux/early_res.h
+++ b/include/linux/early_res.h
@@ -3,19 +3,22 @@
 #ifdef __KERNEL__
 
 extern void reserve_early(u64 start, u64 end, char *name);
-extern void reserve_early_overlap_ok(u64 start, u64 end, char *name);
 extern void free_early(u64 start, u64 end);
-void free_early_partial(u64 start, u64 end);
-extern void early_res_to_bootmem(u64 start, u64 end);
+void lmb_reserved_to_bootmem(u64 start, u64 end);
 
-void reserve_early_without_check(u64 start, u64 end, char *name);
 u64 find_early_area(u64 ei_start, u64 ei_last, u64 start, u64 end,
 			 u64 size, u64 align);
-u64 find_early_area_size(u64 ei_start, u64 ei_last, u64 start,
-			 u64 *sizep, u64 align);
-u64 find_fw_memmap_area(u64 start, u64 end, u64 size, u64 align);
+
+void add_lmb_memory(u64 start, u64 end);
+
+u64 find_lmb_area(u64 start, u64 end, u64 size, u64 align);
+u64 find_lmb_area_size(u64 start, u64 *sizep, u64 align);
+u64 find_lmb_area_node(int nid, u64 start, u64 end, u64 size, u64 align);
+void lmb_register_active_regions(int nid, unsigned long start_pfn,
+					 unsigned long last_pfn);
+u64 lmb_hole_size(u64 start, u64 end);
 u64 get_max_mapped(void);
-#include <linux/range.h>
+struct range;
 int get_free_all_memory_range(struct range **rangep, int nodeid);
 
 #endif /* __KERNEL__ */
diff --git a/kernel/early_res.c b/kernel/early_res.c
index 69bed5b..a793393 100644
--- a/kernel/early_res.c
+++ b/kernel/early_res.c
@@ -6,404 +6,140 @@
 #include <linux/init.h>
 #include <linux/bootmem.h>
 #include <linux/mm.h>
+#include <linux/lmb.h>
+#include <linux/range.h>
 #include <linux/early_res.h>
 
 /*
  * Early reserved memory areas.
  */
-/*
- * need to make sure this one is bigger enough before
- * find_fw_memmap_area could be used
- */
-#define MAX_EARLY_RES_X 32
-
-struct early_res {
-	u64 start, end;
-	char name[15];
-	char overlap_ok;
-};
-static struct early_res early_res_x[MAX_EARLY_RES_X] __initdata;
-
-static int max_early_res __initdata = MAX_EARLY_RES_X;
-static struct early_res *early_res __initdata = &early_res_x[0];
-static int early_res_count __initdata;
-
-static int __init find_overlapped_early(u64 start, u64 end)
-{
-	int i;
-	struct early_res *r;
-
-	for (i = 0; i < max_early_res && early_res[i].end; i++) {
-		r = &early_res[i];
-		if (end > r->start && start < r->end)
-			break;
-	}
 
-	return i;
-}
-
-/*
- * Drop the i-th range from the early reservation map,
- * by copying any higher ranges down one over it, and
- * clearing what had been the last slot.
- */
-static void __init drop_range(int i)
-{
-	int j;
-
-	for (j = i + 1; j < max_early_res && early_res[j].end; j++)
-		;
-
-	memmove(&early_res[i], &early_res[i + 1],
-	       (j - 1 - i) * sizeof(struct early_res));
-
-	early_res[j - 1].end = 0;
-	early_res_count--;
-}
-
-static void __init drop_range_partial(int i, u64 start, u64 end)
-{
-	u64 common_start, common_end;
-	u64 old_start, old_end;
-
-	old_start = early_res[i].start;
-	old_end = early_res[i].end;
-	common_start = max(old_start, start);
-	common_end = min(old_end, end);
-
-	/* no overlap ? */
-	if (common_start >= common_end)
-		return;
-
-	if (old_start < common_start) {
-		/* make head segment */
-		early_res[i].end = common_start;
-		if (old_end > common_end) {
-			char name[15];
-
-			/*
-			 * Save a local copy of the name, since the
-			 * early_res array could get resized inside
-			 * reserve_early_without_check() ->
-			 * __check_and_double_early_res(), which would
-			 * make the current name pointer invalid.
-			 */
-			strncpy(name, early_res[i].name,
-					 sizeof(early_res[i].name) - 1);
-			/* add another for left over on tail */
-			reserve_early_without_check(common_end, old_end, name);
-		}
-		return;
-	} else {
-		if (old_end > common_end) {
-			/* reuse the entry for tail left */
-			early_res[i].start = common_end;
-			return;
-		}
-		/* all covered */
-		drop_range(i);
-	}
-}
-
-/*
- * Split any existing ranges that:
- *  1) are marked 'overlap_ok', and
- *  2) overlap with the stated range [start, end)
- * into whatever portion (if any) of the existing range is entirely
- * below or entirely above the stated range.  Drop the portion
- * of the existing range that overlaps with the stated range,
- * which will allow the caller of this routine to then add that
- * stated range without conflicting with any existing range.
- */
-static void __init drop_overlaps_that_are_ok(u64 start, u64 end)
-{
-	int i;
-	struct early_res *r;
-	u64 lower_start, lower_end;
-	u64 upper_start, upper_end;
-	char name[15];
-
-	for (i = 0; i < max_early_res && early_res[i].end; i++) {
-		r = &early_res[i];
-
-		/* Continue past non-overlapping ranges */
-		if (end <= r->start || start >= r->end)
-			continue;
-
-		/*
-		 * Leave non-ok overlaps as is; let caller
-		 * panic "Overlapping early reservations"
-		 * when it hits this overlap.
-		 */
-		if (!r->overlap_ok)
-			return;
-
-		/*
-		 * We have an ok overlap.  We will drop it from the early
-		 * reservation map, and add back in any non-overlapping
-		 * portions (lower or upper) as separate, overlap_ok,
-		 * non-overlapping ranges.
-		 */
-
-		/* 1. Note any non-overlapping (lower or upper) ranges. */
-		strncpy(name, r->name, sizeof(name) - 1);
-
-		lower_start = lower_end = 0;
-		upper_start = upper_end = 0;
-		if (r->start < start) {
-			lower_start = r->start;
-			lower_end = start;
-		}
-		if (r->end > end) {
-			upper_start = end;
-			upper_end = r->end;
-		}
-
-		/* 2. Drop the original ok overlapping range */
-		drop_range(i);
-
-		i--;		/* resume for-loop on copied down entry */
-
-		/* 3. Add back in any non-overlapping ranges. */
-		if (lower_end)
-			reserve_early_overlap_ok(lower_start, lower_end, name);
-		if (upper_end)
-			reserve_early_overlap_ok(upper_start, upper_end, name);
-	}
-}
-
-static void __init __reserve_early(u64 start, u64 end, char *name,
-						int overlap_ok)
-{
-	int i;
-	struct early_res *r;
-
-	i = find_overlapped_early(start, end);
-	if (i >= max_early_res)
-		panic("Too many early reservations");
-	r = &early_res[i];
-	if (r->end)
-		panic("Overlapping early reservations "
-		      "%llx-%llx %s to %llx-%llx %s\n",
-		      start, end - 1, name ? name : "", r->start,
-		      r->end - 1, r->name);
-	r->start = start;
-	r->end = end;
-	r->overlap_ok = overlap_ok;
-	if (name)
-		strncpy(r->name, name, sizeof(r->name) - 1);
-	early_res_count++;
-}
-
-/*
- * A few early reservtations come here.
- *
- * The 'overlap_ok' in the name of this routine does -not- mean it
- * is ok for these reservations to overlap an earlier reservation.
- * Rather it means that it is ok for subsequent reservations to
- * overlap this one.
- *
- * Use this entry point to reserve early ranges when you are doing
- * so out of "Paranoia", reserving perhaps more memory than you need,
- * just in case, and don't mind a subsequent overlapping reservation
- * that is known to be needed.
- *
- * The drop_overlaps_that_are_ok() call here isn't really needed.
- * It would be needed if we had two colliding 'overlap_ok'
- * reservations, so that the second such would not panic on the
- * overlap with the first.  We don't have any such as of this
- * writing, but might as well tolerate such if it happens in
- * the future.
- */
-void __init reserve_early_overlap_ok(u64 start, u64 end, char *name)
-{
-	drop_overlaps_that_are_ok(start, end);
-	__reserve_early(start, end, name, 1);
-}
-
-static void __init __check_and_double_early_res(u64 ex_start, u64 ex_end)
+static void __init __check_and_double_region_array(struct lmb_region *type,
+			 struct lmb_property *static_region,
+			 u64 ex_start, u64 ex_end)
 {
 	u64 start, end, size, mem;
-	struct early_res *new;
+	struct lmb_property *new, *old;
+	unsigned long rgnsz = type->nr_regions;
 
 	/* do we have enough slots left ? */
-	if ((max_early_res - early_res_count) > max(max_early_res/8, 2))
+	if ((rgnsz - type->cnt) > max_t(unsigned long, rgnsz/8, 2))
 		return;
 
+	old = type->region;
 	/* double it */
 	mem = -1ULL;
-	size = sizeof(struct early_res) * max_early_res * 2;
-	if (early_res == early_res_x)
+	size = sizeof(struct lmb_property) * rgnsz * 2;
+	if (old == static_region)
 		start = 0;
 	else
-		start = early_res[0].end;
+		start = __pa(old) + sizeof(struct lmb_property) * rgnsz;
 	end = ex_start;
 	if (start + size < end)
-		mem = find_fw_memmap_area(start, end, size,
-					 sizeof(struct early_res));
+		mem = find_lmb_area(start, end, size,
+					 sizeof(struct lmb_property));
 	if (mem == -1ULL) {
 		start = ex_end;
 		end = get_max_mapped();
 		if (start + size < end)
-			mem = find_fw_memmap_area(start, end, size,
-						 sizeof(struct early_res));
+			mem = find_lmb_area(start, end, size, sizeof(struct lmb_property));
 	}
 	if (mem == -1ULL)
-		panic("can not find more space for early_res array");
+		panic("can not find more space for lmb.reserved.region array");
 
 	new = __va(mem);
-	/* save the first one for own */
-	new[0].start = mem;
-	new[0].end = mem + size;
-	new[0].overlap_ok = 0;
 	/* copy old to new */
-	if (early_res == early_res_x) {
-		memcpy(&new[1], &early_res[0],
-			 sizeof(struct early_res) * max_early_res);
-		memset(&new[max_early_res+1], 0,
-			 sizeof(struct early_res) * (max_early_res - 1));
-		early_res_count++;
-	} else {
-		memcpy(&new[1], &early_res[1],
-			 sizeof(struct early_res) * (max_early_res - 1));
-		memset(&new[max_early_res], 0,
-			 sizeof(struct early_res) * max_early_res);
-	}
-	memset(&early_res[0], 0, sizeof(struct early_res) * max_early_res);
-	early_res = new;
-	max_early_res *= 2;
-	printk(KERN_DEBUG "early_res array is doubled to %d at [%llx - %llx]\n",
-		max_early_res, mem, mem + size - 1);
+	memcpy(&new[0], &old[0], sizeof(struct lmb_property) * rgnsz);
+	memset(&new[rgnsz], 0, sizeof(struct lmb_property) * rgnsz);
+
+	memset(&old[0], 0, sizeof(struct lmb_property) * rgnsz);
+	type->region = new;
+	type->nr_regions = rgnsz * 2;
+	printk(KERN_DEBUG "lmb.reserved.region array is doubled to %ld at [%llx - %llx]\n",
+		type->nr_regions, mem, mem + size - 1);
+
+	/* reserve new array and free old one */
+	lmb_reserve(mem, sizeof(struct lmb_property) * rgnsz * 2);
+	if (old != static_region)
+		lmb_free(__pa(old), sizeof(struct lmb_property) * rgnsz);
 }
 
-/*
- * Most early reservations come here.
- *
- * We first have drop_overlaps_that_are_ok() drop any pre-existing
- * 'overlap_ok' ranges, so that we can then reserve this memory
- * range without risk of panic'ing on an overlapping overlap_ok
- * early reservation.
- */
-void __init reserve_early(u64 start, u64 end, char *name)
+void __init add_lmb_memory(u64 start, u64 end)
 {
-	if (start >= end)
-		return;
-
-	__check_and_double_early_res(start, end);
-
-	drop_overlaps_that_are_ok(start, end);
-	__reserve_early(start, end, name, 0);
+	__check_and_double_region_array(&lmb.memory, &lmb_memory_region[0], start, end);
+	lmb_add(start, end - start);
 }
 
-void __init reserve_early_without_check(u64 start, u64 end, char *name)
+void __init reserve_early(u64 start, u64 end, char *name)
 {
-	struct early_res *r;
-
-	if (start >= end)
+	if (start == end)
 		return;
 
-	__check_and_double_early_res(start, end);
-
-	r = &early_res[early_res_count];
+	if (WARN_ONCE(start > end, "reserve_early: wrong range [%#llx, %#llx]\n", start, end))
+		return;
 
-	r->start = start;
-	r->end = end;
-	r->overlap_ok = 0;
-	if (name)
-		strncpy(r->name, name, sizeof(r->name) - 1);
-	early_res_count++;
+	__check_and_double_region_array(&lmb.reserved, &lmb_reserved_region[0], start, end);
+	lmb_reserve(start, end - start);
 }
 
 void __init free_early(u64 start, u64 end)
 {
-	struct early_res *r;
-	int i;
-
-	i = find_overlapped_early(start, end);
-	r = &early_res[i];
-	if (i >= max_early_res || r->end != end || r->start != start)
-		panic("free_early on not reserved area: %llx-%llx!",
-			 start, end - 1);
-
-	drop_range(i);
-}
-
-void __init free_early_partial(u64 start, u64 end)
-{
-	struct early_res *r;
-	int i;
-
 	if (start == end)
 		return;
 
-	if (WARN_ONCE(start > end, "free_early_partial: wrong range [%#llx, %#llx]\n", start, end))
-		return;
-
-try_next:
-	i = find_overlapped_early(start, end);
-	if (i >= max_early_res)
-		return;
-
-	r = &early_res[i];
-	/* hole ? */
-	if (r->end >= end && r->start <= start) {
-		drop_range_partial(i, start, end);
+	if (WARN_ONCE(start > end, "free_early: wrong range [%#llx, %#llx]\n", start, end))
 		return;
-	}
 
-	drop_range_partial(i, start, end);
-	goto try_next;
+	/* keep punching hole, could run out of slots too */
+	__check_and_double_region_array(&lmb.reserved, &lmb_reserved_region[0], start, end);
+	lmb_free(start, end - start);
 }
 
 #ifdef CONFIG_NO_BOOTMEM
-static void __init subtract_early_res(struct range *range, int az)
+static void __init subtract_lmb_reserved(struct range *range, int az)
 {
 	int i, count;
 	u64 final_start, final_end;
-	int idx = 0;
 
-	count  = 0;
-	for (i = 0; i < max_early_res && early_res[i].end; i++)
-		count++;
+	/*take out region array at first*/
+	if (lmb.reserved.region != lmb_reserved_region)
+		lmb_free(__pa(lmb.reserved.region), sizeof(struct lmb_property) * lmb.reserved.nr_regions);
 
-	/* need to skip first one ?*/
-	if (early_res != early_res_x)
-		idx = 1;
+	count  = lmb.reserved.cnt;
 
 #define DEBUG_PRINT_EARLY_RES 1
 
 #if DEBUG_PRINT_EARLY_RES
 	printk(KERN_INFO "Subtract (%d early reservations)\n", count);
 #endif
-	for (i = idx; i < count; i++) {
-		struct early_res *r = &early_res[i];
+
+	for (i = 0; i < count; i++) {
+		struct lmb_property *r = &lmb.reserved.region[i];
 #if DEBUG_PRINT_EARLY_RES
-		printk(KERN_INFO "  #%d [%010llx - %010llx] %15s\n", i,
-			r->start, r->end, r->name);
+		printk(KERN_INFO "  #%d [%010llx - %010llx]\n", i,
+			r->base, r->base + r->size);
 #endif
-		final_start = PFN_DOWN(r->start);
-		final_end = PFN_UP(r->end);
+		final_start = PFN_DOWN(r->base);
+		final_end = PFN_UP(r->base + r->size);
 		if (final_start >= final_end)
 			continue;
 		subtract_range(range, az, final_start, final_end);
 	}
-
+	/* put region array back */
+	if (lmb.reserved.region != lmb_reserved_region)
+		lmb_reserve(__pa(lmb.reserved.region), sizeof(struct lmb_property) * lmb.reserved.nr_regions);
 }
 
 int __init get_free_all_memory_range(struct range **rangep, int nodeid)
 {
-	int i, count;
+	int count;
 	u64 start = 0, end;
 	u64 size;
 	u64 mem;
 	struct range *range;
 	int nr_range;
 
-	count  = 0;
-	for (i = 0; i < max_early_res && early_res[i].end; i++)
-		count++;
-
-	count *= 2;
+	count = lmb.reserved.cnt * 2;
 
 	size = sizeof(struct range) * count;
 	end = get_max_mapped();
@@ -411,12 +147,15 @@ int __init get_free_all_memory_range(struct range **rangep, int nodeid)
 	if (end > (MAX_DMA32_PFN << PAGE_SHIFT))
 		start = MAX_DMA32_PFN << PAGE_SHIFT;
 #endif
-	mem = find_fw_memmap_area(start, end, size, sizeof(struct range));
+	mem = find_lmb_area(start, end, size, sizeof(struct range));
 	if (mem == -1ULL)
 		panic("can not find more space for range free");
 
 	range = __va(mem);
-	/* use early_node_map[] and early_res to get range array at first */
+	/*
+	 * use early_node_map[] and lmb.reserved.region to get range array
+	 * at first
+	 */
 	memset(range, 0, size);
 	nr_range = 0;
 
@@ -425,43 +164,39 @@ int __init get_free_all_memory_range(struct range **rangep, int nodeid)
 #ifdef CONFIG_X86_32
 	subtract_range(range, count, max_low_pfn, -1ULL);
 #endif
-	subtract_early_res(range, count);
+	subtract_lmb_reserved(range, count);
 	nr_range = clean_sort_range(range, count);
 
 	/* need to clear it ? */
 	if (nodeid == MAX_NUMNODES) {
-		memset(&early_res[0], 0,
-			 sizeof(struct early_res) * max_early_res);
-		early_res = NULL;
-		max_early_res = 0;
+		memset(&lmb.reserved.region[0], 0, sizeof(struct lmb_property) * lmb.reserved.nr_regions);
+		lmb.reserved.region = NULL;
+		lmb.reserved.nr_regions = 0;
+		lmb.reserved.cnt = 0;
 	}
 
 	*rangep = range;
 	return nr_range;
 }
 #else
-void __init early_res_to_bootmem(u64 start, u64 end)
+void __init lmb_reserved_to_bootmem(u64 start, u64 end)
 {
 	int i, count;
 	u64 final_start, final_end;
-	int idx = 0;
-
-	count  = 0;
-	for (i = 0; i < max_early_res && early_res[i].end; i++)
-		count++;
-
-	/* need to skip first one ?*/
-	if (early_res != early_res_x)
-		idx = 1;
-
-	printk(KERN_INFO "(%d/%d early reservations) ==> bootmem [%010llx - %010llx]\n",
-			 count - idx, max_early_res, start, end);
-	for (i = idx; i < count; i++) {
-		struct early_res *r = &early_res[i];
-		printk(KERN_INFO "  #%d [%010llx - %010llx] %16s", i,
-			r->start, r->end, r->name);
-		final_start = max(start, r->start);
-		final_end = min(end, r->end);
+
+	/*take out region array */
+	if (lmb.reserved.region != lmb_reserved_region)
+		lmb_free(__pa(lmb.reserved.region), sizeof(struct lmb_property) * lmb.reserved.nr_regions);
+
+	count  = lmb.reserved.cnt;
+	printk(KERN_INFO "(%d early reservations) ==> bootmem [%010llx - %010llx]\n",
+			 count, start, end);
+	for (i = 0; i < count; i++) {
+		struct lmb_property *r = &lmb.reserved.region[i];
+		printk(KERN_INFO "  #%d [%010llx - %010llx] ", i,
+			r->base, r->base + r->size);
+		final_start = max(start, r->base);
+		final_end = min(end, r->base + r->size);
 		if (final_start >= final_end) {
 			printk(KERN_CONT "\n");
 			continue;
@@ -471,57 +206,71 @@ void __init early_res_to_bootmem(u64 start, u64 end)
 		reserve_bootmem_generic(final_start, final_end - final_start,
 				BOOTMEM_DEFAULT);
 	}
-	/* clear them */
-	memset(&early_res[0], 0, sizeof(struct early_res) * max_early_res);
-	early_res = NULL;
-	max_early_res = 0;
-	early_res_count = 0;
+	/* clear them to avoid misuse */
+	memset(&lmb.reserved.region[0], 0, sizeof(struct lmb_property) * lmb.reserved.nr_regions);
+	lmb.reserved.region = NULL;
+	lmb.reserved.nr_regions = 0;
+	lmb.reserved.cnt = 0;
 }
 #endif
 
+static int __init find_overlapped_early(u64 start, u64 end)
+{
+	int i;
+	struct lmb_property *r;
+
+	for (i = 0; i < lmb.reserved.cnt && lmb.reserved.region[i].size; i++) {
+		r = &lmb.reserved.region[i];
+		if (end > r->base && start < (r->base + r->size))
+			break;
+	}
+
+	return i;
+}
+
 /* Check for already reserved areas */
-static inline int __init bad_addr(u64 *addrp, u64 size, u64 align)
+static inline bool __init bad_addr(u64 *addrp, u64 size, u64 align)
 {
 	int i;
 	u64 addr = *addrp;
-	int changed = 0;
-	struct early_res *r;
+	bool changed = false;
+	struct lmb_property *r;
 again:
 	i = find_overlapped_early(addr, addr + size);
-	r = &early_res[i];
-	if (i < max_early_res && r->end) {
-		*addrp = addr = round_up(r->end, align);
-		changed = 1;
+	r = &lmb.reserved.region[i];
+	if (i < lmb.reserved.cnt && r->size) {
+		*addrp = addr = round_up(r->base + r->size, align);
+		changed = true;
 		goto again;
 	}
 	return changed;
 }
 
 /* Check for already reserved areas */
-static inline int __init bad_addr_size(u64 *addrp, u64 *sizep, u64 align)
+static inline bool __init bad_addr_size(u64 *addrp, u64 *sizep, u64 align)
 {
 	int i;
 	u64 addr = *addrp, last;
 	u64 size = *sizep;
-	int changed = 0;
+	bool changed = false;
 again:
 	last = addr + size;
-	for (i = 0; i < max_early_res && early_res[i].end; i++) {
-		struct early_res *r = &early_res[i];
-		if (last > r->start && addr < r->start) {
-			size = r->start - addr;
-			changed = 1;
+	for (i = 0; i < lmb.reserved.cnt && lmb.reserved.region[i].size; i++) {
+		struct lmb_property *r = &lmb.reserved.region[i];
+		if (last > r->base && addr < r->base) {
+			size = r->base - addr;
+			changed = true;
 			goto again;
 		}
-		if (last > r->end && addr < r->end) {
-			addr = round_up(r->end, align);
+		if (last > (r->base + r->size) && addr < (r->base + r->size)) {
+			addr = round_up(r->base + r->size, align);
 			size = last - addr;
-			changed = 1;
+			changed = true;
 			goto again;
 		}
-		if (last <= r->end && addr >= r->start) {
+		if (last <= (r->base + r->size) && addr >= r->base) {
 			(*sizep)++;
-			return 0;
+			return false;
 		}
 	}
 	if (changed) {
@@ -531,13 +280,8 @@ again:
 	return changed;
 }
 
-/*
- * Find a free area with specified alignment in a specific range.
- * only with the area.between start to end is active range from early_node_map
- * so they are good as RAM
- */
 u64 __init find_early_area(u64 ei_start, u64 ei_last, u64 start, u64 end,
-			 u64 size, u64 align)
+				 u64 size, u64 align)
 {
 	u64 addr, last;
 
@@ -560,7 +304,7 @@ out:
 	return -1ULL;
 }
 
-u64 __init find_early_area_size(u64 ei_start, u64 ei_last, u64 start,
+static u64 __init find_early_area_size(u64 ei_start, u64 ei_last, u64 start,
 			 u64 *sizep, u64 align)
 {
 	u64 addr, last;
@@ -582,3 +326,130 @@ u64 __init find_early_area_size(u64 ei_start, u64 ei_last, u64 start,
 out:
 	return -1ULL;
 }
+
+/*
+ * Find a free area with specified alignment in a specific range.
+ */
+u64 __init find_lmb_area(u64 start, u64 end, u64 size, u64 align)
+{
+	int i;
+
+	for (i = 0; i < lmb.memory.cnt; i++) {
+		u64 ei_start = lmb.memory.region[i].base;
+		u64 ei_last = ei_start + lmb.memory.region[i].size;
+		u64 addr;
+
+		addr = find_early_area(ei_start, ei_last, start, end,
+					 size, align);
+
+		if (addr != -1ULL)
+			return addr;
+	}
+	return -1ULL;
+}
+
+/*
+ * Find next free range after *start
+ */
+u64 __init find_lmb_area_size(u64 start, u64 *sizep, u64 align)
+{
+	int i;
+
+	for (i = 0; i < lmb.memory.cnt; i++) {
+		u64 ei_start = lmb.memory.region[i].base;
+		u64 ei_last = ei_start + lmb.memory.region[i].size;
+		u64 addr;
+
+		addr = find_early_area_size(ei_start, ei_last, start,
+					 sizep, align);
+
+		if (addr != -1ULL)
+			return addr;
+	}
+
+	return -1ULL;
+}
+
+u64 __init find_lmb_area_node(int nid, u64 start, u64 end, u64 size, u64 align)
+{
+	u64 addr;
+	/*
+	 * need to call this function after lmb_register_active_regions
+	 * so early_node_map[] is set
+	 */
+	addr = find_memory_core_early(nid, size, align, start, end);
+	if (addr != -1ULL)
+		return addr;
+
+	/* fallback, should already have start end in the node range */
+	return find_lmb_area(start, end, size, align);
+}
+
+/*
+ * Finds an active region in the address range from start_pfn to last_pfn and
+ * returns its range in ei_startpfn and ei_endpfn for the lmb entry.
+ */
+static int __init lmb_find_active_region(const struct lmb_property *ei,
+				  unsigned long start_pfn,
+				  unsigned long last_pfn,
+				  unsigned long *ei_startpfn,
+				  unsigned long *ei_endpfn)
+{
+	u64 align = PAGE_SIZE;
+
+	*ei_startpfn = round_up(ei->base, align) >> PAGE_SHIFT;
+	*ei_endpfn = round_down(ei->base + ei->size, align) >> PAGE_SHIFT;
+
+	/* Skip map entries smaller than a page */
+	if (*ei_startpfn >= *ei_endpfn)
+		return 0;
+
+	/* Skip if map is outside the node */
+	if (*ei_endpfn <= start_pfn || *ei_startpfn >= last_pfn)
+		return 0;
+
+	/* Check for overlaps */
+	if (*ei_startpfn < start_pfn)
+		*ei_startpfn = start_pfn;
+	if (*ei_endpfn > last_pfn)
+		*ei_endpfn = last_pfn;
+
+	return 1;
+}
+
+/* Walk the lmb.memory map and register active regions within a node */
+void __init lmb_register_active_regions(int nid, unsigned long start_pfn,
+					 unsigned long last_pfn)
+{
+	unsigned long ei_startpfn;
+	unsigned long ei_endpfn;
+	int i;
+
+	for (i = 0; i < lmb.memory.cnt; i++)
+		if (lmb_find_active_region(&lmb.memory.region[i],
+					    start_pfn, last_pfn,
+					    &ei_startpfn, &ei_endpfn))
+			add_active_range(nid, ei_startpfn, ei_endpfn);
+}
+
+/*
+ * Find the hole size (in bytes) in the memory range.
+ * @start: starting address of the memory range to scan
+ * @end: ending address of the memory range to scan
+ */
+u64 __init lmb_hole_size(u64 start, u64 end)
+{
+	unsigned long start_pfn = start >> PAGE_SHIFT;
+	unsigned long last_pfn = end >> PAGE_SHIFT;
+	unsigned long ei_startpfn, ei_endpfn, ram = 0;
+	int i;
+
+	for (i = 0; i < lmb.memory.cnt; i++) {
+		if (lmb_find_active_region(&lmb.memory.region[i],
+					    start_pfn, last_pfn,
+					    &ei_startpfn, &ei_endpfn))
+			ram += ei_endpfn - ei_startpfn;
+	}
+	return end - start - ((u64)ram << PAGE_SHIFT);
+}
+
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index eef3757..04c241a 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -3451,7 +3451,7 @@ void * __init __alloc_memory_core_early(int nid, u64 size, u64 align,
 
 	ptr = phys_to_virt(addr);
 	memset(ptr, 0, size);
-	reserve_early_without_check(addr, addr + size, "BOOTMEM");
+	reserve_early(addr, addr + size, "BOOTMEM");
 	return ptr;
 }
 #endif
diff --git a/mm/sparse-vmemmap.c b/mm/sparse-vmemmap.c
index 392b9bb..cb917d5 100644
--- a/mm/sparse-vmemmap.c
+++ b/mm/sparse-vmemmap.c
@@ -219,18 +219,7 @@ void __init sparse_mem_maps_populate_node(struct page **map_map,
 
 	if (vmemmap_buf_start) {
 		/* need to free left buf */
-#ifdef CONFIG_NO_BOOTMEM
-		free_early(__pa(vmemmap_buf_start), __pa(vmemmap_buf_end));
-		if (vmemmap_buf_start < vmemmap_buf) {
-			char name[15];
-
-			snprintf(name, sizeof(name), "MEMMAP %d", nodeid);
-			reserve_early_without_check(__pa(vmemmap_buf_start),
-						    __pa(vmemmap_buf), name);
-		}
-#else
 		free_bootmem(__pa(vmemmap_buf), vmemmap_buf_end - vmemmap_buf);
-#endif
 		vmemmap_buf = NULL;
 		vmemmap_buf_end = NULL;
 	}
-- 
1.6.4.2

[PATCH 6/8] x86: remove find_e820_area

[Yinghai Lu]

and e820_register_active_region, e820_hole_size

Signed-off-by: Yinghai Lu <yinghai@kernel.org>
---
 arch/x86/include/asm/e820.h     |   17 -----------------
 arch/x86/kernel/acpi/sleep.c    |    2 +-
 arch/x86/kernel/apic/numaq_32.c |    2 +-
 arch/x86/kernel/setup.c         |    6 +++---
 arch/x86/kernel/trampoline.c    |    4 ++--
 arch/x86/mm/init.c              |    2 +-
 arch/x86/mm/init_32.c           |    6 +++---
 arch/x86/mm/init_64.c           |    6 +++---
 arch/x86/mm/k8topology_64.c     |    2 +-
 arch/x86/mm/numa_32.c           |    8 ++++----
 arch/x86/mm/numa_64.c           |   24 ++++++++++++------------
 arch/x86/mm/srat_32.c           |    2 +-
 arch/x86/mm/srat_64.c           |    6 +++---
 13 files changed, 35 insertions(+), 52 deletions(-)

diff --git a/arch/x86/include/asm/e820.h b/arch/x86/include/asm/e820.h
index e957101..9234c78 100644
--- a/arch/x86/include/asm/e820.h
+++ b/arch/x86/include/asm/e820.h
@@ -116,23 +116,6 @@ extern unsigned long e820_end_of_low_ram_pfn(void);
 #include <linux/early_res.h>
 extern u64 early_reserve_e820(u64 startt, u64 sizet, u64 align);
 
-/*
- * next three functions will be removed, esp find_e820_area()
- * can not be used before fill_lmb_memory()
- */
-static inline u64 find_e820_area(u64 start, u64 end, u64 size, u64 align)
-{
-	return find_lmb_area(start, end, size, align);
-}
-static inline void e820_register_active_regions(int nid, unsigned long start_pfn, unsigned long end_pfn)
-{
-	lmb_register_active_regions(nid, start_pfn, end_pfn);
-}
-static inline u64 e820_hole_size(u64 start, u64 end)
-{
-	return lmb_hole_size(start, end);
-}
-
 void init_lmb_memory(void);
 void fill_lmb_memory(void);
 extern void finish_e820_parsing(void);
diff --git a/arch/x86/kernel/acpi/sleep.c b/arch/x86/kernel/acpi/sleep.c
index f996103..700a3b7 100644
--- a/arch/x86/kernel/acpi/sleep.c
+++ b/arch/x86/kernel/acpi/sleep.c
@@ -133,7 +133,7 @@ void __init acpi_reserve_wakeup_memory(void)
 		return;
 	}
 
-	mem = find_e820_area(0, 1<<20, WAKEUP_SIZE, PAGE_SIZE);
+	mem = find_lmb_area(0, 1<<20, WAKEUP_SIZE, PAGE_SIZE);
 
 	if (mem == -1L) {
 		printk(KERN_ERR "ACPI: Cannot allocate lowmem, S3 disabled.\n");
diff --git a/arch/x86/kernel/apic/numaq_32.c b/arch/x86/kernel/apic/numaq_32.c
index 3e28401..d021cd4 100644
--- a/arch/x86/kernel/apic/numaq_32.c
+++ b/arch/x86/kernel/apic/numaq_32.c
@@ -88,7 +88,7 @@ static inline void numaq_register_node(int node, struct sys_cfg_data *scd)
 	node_end_pfn[node] =
 		 MB_TO_PAGES(eq->hi_shrd_mem_start + eq->hi_shrd_mem_size);
 
-	e820_register_active_regions(node, node_start_pfn[node],
+	lmb_register_active_regions(node, node_start_pfn[node],
 						node_end_pfn[node]);
 
 	memory_present(node, node_start_pfn[node], node_end_pfn[node]);
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index a9e99e6..b716ea3 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -323,7 +323,7 @@ static void __init relocate_initrd(void)
 	char *p, *q;
 
 	/* We need to move the initrd down into lowmem */
-	ramdisk_here = find_e820_area(0, end_of_lowmem, ramdisk_size,
+	ramdisk_here = find_lmb_area(0, end_of_lowmem, ramdisk_size,
 					 PAGE_SIZE);
 
 	if (ramdisk_here == -1ULL)
@@ -517,7 +517,7 @@ static void __init reserve_crashkernel(void)
 	if (crash_base <= 0) {
 		const unsigned long long alignment = 16<<20;	/* 16M */
 
-		crash_base = find_e820_area(alignment, ULONG_MAX, crash_size,
+		crash_base = find_lmb_area(alignment, ULONG_MAX, crash_size,
 				 alignment);
 		if (crash_base == -1ULL) {
 			pr_info("crashkernel reservation failed - No suitable area found.\n");
@@ -526,7 +526,7 @@ static void __init reserve_crashkernel(void)
 	} else {
 		unsigned long long start;
 
-		start = find_e820_area(crash_base, ULONG_MAX, crash_size,
+		start = find_lmb_area(crash_base, ULONG_MAX, crash_size,
 				 1<<20);
 		if (start != crash_base) {
 			pr_info("crashkernel reservation failed - memory is in use.\n");
diff --git a/arch/x86/kernel/trampoline.c b/arch/x86/kernel/trampoline.c
index c652ef6..2276e8b 100644
--- a/arch/x86/kernel/trampoline.c
+++ b/arch/x86/kernel/trampoline.c
@@ -1,7 +1,7 @@
 #include <linux/io.h>
+#include <linux/early_res.h>
 
 #include <asm/trampoline.h>
-#include <asm/e820.h>
 
 #if defined(CONFIG_X86_64) && defined(CONFIG_ACPI_SLEEP)
 #define __trampinit
@@ -19,7 +19,7 @@ void __init reserve_trampoline_memory(void)
 	unsigned long mem;
 
 	/* Has to be in very low memory so we can execute real-mode AP code. */
-	mem = find_e820_area(0, 1<<20, TRAMPOLINE_SIZE, PAGE_SIZE);
+	mem = find_lmb_area(0, 1<<20, TRAMPOLINE_SIZE, PAGE_SIZE);
 	if (mem == -1L)
 		panic("Cannot allocate trampoline\n");
 
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index e71c5cb..7d40e37 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -74,7 +74,7 @@ static void __init find_early_table_space(unsigned long end, int use_pse,
 #else
 	start = 0x8000;
 #endif
-	e820_table_start = find_e820_area(start, max_pfn_mapped<<PAGE_SHIFT,
+	e820_table_start = find_lmb_area(start, max_pfn_mapped<<PAGE_SHIFT,
 					tables, PAGE_SIZE);
 	if (e820_table_start == -1UL)
 		panic("Cannot find space for the kernel page tables");
diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c
index 5cb3f0f..a7625d5 100644
--- a/arch/x86/mm/init_32.c
+++ b/arch/x86/mm/init_32.c
@@ -712,14 +712,14 @@ void __init initmem_init(unsigned long start_pfn, unsigned long end_pfn,
 	highstart_pfn = highend_pfn = max_pfn;
 	if (max_pfn > max_low_pfn)
 		highstart_pfn = max_low_pfn;
-	e820_register_active_regions(0, 0, highend_pfn);
+	lmb_register_active_regions(0, 0, highend_pfn);
 	sparse_memory_present_with_active_regions(0);
 	printk(KERN_NOTICE "%ldMB HIGHMEM available.\n",
 		pages_to_mb(highend_pfn - highstart_pfn));
 	num_physpages = highend_pfn;
 	high_memory = (void *) __va(highstart_pfn * PAGE_SIZE - 1) + 1;
 #else
-	e820_register_active_regions(0, 0, max_low_pfn);
+	lmb_register_active_regions(0, 0, max_low_pfn);
 	sparse_memory_present_with_active_regions(0);
 	num_physpages = max_low_pfn;
 	high_memory = (void *) __va(max_low_pfn * PAGE_SIZE - 1) + 1;
@@ -781,7 +781,7 @@ void __init setup_bootmem_allocator(void)
 	 * Initialize the boot-time allocator (with low memory only):
 	 */
 	bootmap_size = bootmem_bootmap_pages(max_low_pfn)<<PAGE_SHIFT;
-	bootmap = find_e820_area(0, max_pfn_mapped<<PAGE_SHIFT, bootmap_size,
+	bootmap = find_lmb_area(0, max_pfn_mapped<<PAGE_SHIFT, bootmap_size,
 				 PAGE_SIZE);
 	if (bootmap == -1L)
 		panic("Cannot find bootmem map of size %ld\n", bootmap_size);
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index e9b040e..dd88ef9 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -576,7 +576,7 @@ void __init initmem_init(unsigned long start_pfn, unsigned long end_pfn,
 	unsigned long bootmap_size, bootmap;
 
 	bootmap_size = bootmem_bootmap_pages(end_pfn)<<PAGE_SHIFT;
-	bootmap = find_e820_area(0, end_pfn<<PAGE_SHIFT, bootmap_size,
+	bootmap = find_lmb_area(0, end_pfn<<PAGE_SHIFT, bootmap_size,
 				 PAGE_SIZE);
 	if (bootmap == -1L)
 		panic("Cannot find bootmem map of size %ld\n", bootmap_size);
@@ -584,10 +584,10 @@ void __init initmem_init(unsigned long start_pfn, unsigned long end_pfn,
 	/* don't touch min_low_pfn */
 	bootmap_size = init_bootmem_node(NODE_DATA(0), bootmap >> PAGE_SHIFT,
 					 0, end_pfn);
-	e820_register_active_regions(0, start_pfn, end_pfn);
+	lmb_register_active_regions(0, start_pfn, end_pfn);
 	free_bootmem_with_active_regions(0, end_pfn);
 #else
-	e820_register_active_regions(0, start_pfn, end_pfn);
+	lmb_register_active_regions(0, start_pfn, end_pfn);
 #endif
 }
 #endif
diff --git a/arch/x86/mm/k8topology_64.c b/arch/x86/mm/k8topology_64.c
index 970ed57..1c5b234 100644
--- a/arch/x86/mm/k8topology_64.c
+++ b/arch/x86/mm/k8topology_64.c
@@ -222,7 +222,7 @@ int __init k8_scan_nodes(void)
 	for_each_node_mask(i, node_possible_map) {
 		int j;
 
-		e820_register_active_regions(i,
+		lmb_register_active_regions(i,
 				nodes[i].start >> PAGE_SHIFT,
 				nodes[i].end >> PAGE_SHIFT);
 		for (j = apicid_base; j < cores + apicid_base; j++)
diff --git a/arch/x86/mm/numa_32.c b/arch/x86/mm/numa_32.c
index 809baaa..8780f4d 100644
--- a/arch/x86/mm/numa_32.c
+++ b/arch/x86/mm/numa_32.c
@@ -120,7 +120,7 @@ int __init get_memcfg_numa_flat(void)
 
 	node_start_pfn[0] = 0;
 	node_end_pfn[0] = max_pfn;
-	e820_register_active_regions(0, 0, max_pfn);
+	lmb_register_active_regions(0, 0, max_pfn);
 	memory_present(0, 0, max_pfn);
 	node_remap_size[0] = node_memmap_size_bytes(0, 0, max_pfn);
 
@@ -161,7 +161,7 @@ static void __init allocate_pgdat(int nid)
 		NODE_DATA(nid) = (pg_data_t *)node_remap_start_vaddr[nid];
 	else {
 		unsigned long pgdat_phys;
-		pgdat_phys = find_e820_area(min_low_pfn<<PAGE_SHIFT,
+		pgdat_phys = find_lmb_area(min_low_pfn<<PAGE_SHIFT,
 				 max_pfn_mapped<<PAGE_SHIFT,
 				 sizeof(pg_data_t),
 				 PAGE_SIZE);
@@ -291,7 +291,7 @@ static __init unsigned long calculate_numa_remap_pages(void)
 						 PTRS_PER_PTE);
 		node_kva_target <<= PAGE_SHIFT;
 		do {
-			node_kva_final = find_e820_area(node_kva_target,
+			node_kva_final = find_lmb_area(node_kva_target,
 					((u64)node_end_pfn[nid])<<PAGE_SHIFT,
 						((u64)size)<<PAGE_SHIFT,
 						LARGE_PAGE_BYTES);
@@ -367,7 +367,7 @@ void __init initmem_init(unsigned long start_pfn, unsigned long end_pfn,
 
 	kva_target_pfn = round_down(max_low_pfn - kva_pages, PTRS_PER_PTE);
 	do {
-		kva_start_pfn = find_e820_area(kva_target_pfn<<PAGE_SHIFT,
+		kva_start_pfn = find_lmb_area(kva_target_pfn<<PAGE_SHIFT,
 					max_low_pfn<<PAGE_SHIFT,
 					kva_pages<<PAGE_SHIFT,
 					PTRS_PER_PTE<<PAGE_SHIFT) >> PAGE_SHIFT;
diff --git a/arch/x86/mm/numa_64.c b/arch/x86/mm/numa_64.c
index 45ac950..12c1268 100644
--- a/arch/x86/mm/numa_64.c
+++ b/arch/x86/mm/numa_64.c
@@ -89,7 +89,7 @@ static int __init allocate_cachealigned_memnodemap(void)
 
 	addr = 0x8000;
 	nodemap_size = roundup(sizeof(s16) * memnodemapsize, L1_CACHE_BYTES);
-	nodemap_addr = find_e820_area(addr, max_pfn<<PAGE_SHIFT,
+	nodemap_addr = find_lmb_area(addr, max_pfn<<PAGE_SHIFT,
 				      nodemap_size, L1_CACHE_BYTES);
 	if (nodemap_addr == -1UL) {
 		printk(KERN_ERR
@@ -248,7 +248,7 @@ setup_node_bootmem(int nodeid, unsigned long start, unsigned long end)
 	 * Find a place for the bootmem map
 	 * nodedata_phys could be on other nodes by alloc_bootmem,
 	 * so need to sure bootmap_start not to be small, otherwise
-	 * early_node_mem will get that with find_e820_area instead
+	 * early_node_mem will get that with find_lmb_area instead
 	 * of alloc_bootmem, that could clash with reserved range
 	 */
 	bootmap_pages = bootmem_bootmap_pages(last_pfn - start_pfn);
@@ -419,7 +419,7 @@ static int __init split_nodes_interleave(u64 addr, u64 max_addr,
 		nr_nodes = MAX_NUMNODES;
 	}
 
-	size = (max_addr - addr - e820_hole_size(addr, max_addr)) / nr_nodes;
+	size = (max_addr - addr - lmb_hole_size(addr, max_addr)) / nr_nodes;
 	/*
 	 * Calculate the number of big nodes that can be allocated as a result
 	 * of consolidating the remainder.
@@ -455,7 +455,7 @@ static int __init split_nodes_interleave(u64 addr, u64 max_addr,
 			 * non-reserved memory is less than the per-node size.
 			 */
 			while (end - physnodes[i].start -
-				e820_hole_size(physnodes[i].start, end) < size) {
+				lmb_hole_size(physnodes[i].start, end) < size) {
 				end += FAKE_NODE_MIN_SIZE;
 				if (end > physnodes[i].end) {
 					end = physnodes[i].end;
@@ -469,7 +469,7 @@ static int __init split_nodes_interleave(u64 addr, u64 max_addr,
 			 * this one must extend to the boundary.
 			 */
 			if (end < dma32_end && dma32_end - end -
-			    e820_hole_size(end, dma32_end) < FAKE_NODE_MIN_SIZE)
+			    lmb_hole_size(end, dma32_end) < FAKE_NODE_MIN_SIZE)
 				end = dma32_end;
 
 			/*
@@ -478,7 +478,7 @@ static int __init split_nodes_interleave(u64 addr, u64 max_addr,
 			 * physical node.
 			 */
 			if (physnodes[i].end - end -
-			    e820_hole_size(end, physnodes[i].end) < size)
+			    lmb_hole_size(end, physnodes[i].end) < size)
 				end = physnodes[i].end;
 
 			/*
@@ -506,7 +506,7 @@ static u64 __init find_end_of_node(u64 start, u64 max_addr, u64 size)
 {
 	u64 end = start + size;
 
-	while (end - start - e820_hole_size(start, end) < size) {
+	while (end - start - lmb_hole_size(start, end) < size) {
 		end += FAKE_NODE_MIN_SIZE;
 		if (end > max_addr) {
 			end = max_addr;
@@ -535,7 +535,7 @@ static int __init split_nodes_size_interleave(u64 addr, u64 max_addr, u64 size)
 	 * creates a uniform distribution of node sizes across the entire
 	 * machine (but not necessarily over physical nodes).
 	 */
-	min_size = (max_addr - addr - e820_hole_size(addr, max_addr)) /
+	min_size = (max_addr - addr - lmb_hole_size(addr, max_addr)) /
 						MAX_NUMNODES;
 	min_size = max(min_size, FAKE_NODE_MIN_SIZE);
 	if ((min_size & FAKE_NODE_MIN_HASH_MASK) < min_size)
@@ -568,7 +568,7 @@ static int __init split_nodes_size_interleave(u64 addr, u64 max_addr, u64 size)
 			 * this one must extend to the boundary.
 			 */
 			if (end < dma32_end && dma32_end - end -
-			    e820_hole_size(end, dma32_end) < FAKE_NODE_MIN_SIZE)
+			    lmb_hole_size(end, dma32_end) < FAKE_NODE_MIN_SIZE)
 				end = dma32_end;
 
 			/*
@@ -577,7 +577,7 @@ static int __init split_nodes_size_interleave(u64 addr, u64 max_addr, u64 size)
 			 * physical node.
 			 */
 			if (physnodes[i].end - end -
-			    e820_hole_size(end, physnodes[i].end) < size)
+			    lmb_hole_size(end, physnodes[i].end) < size)
 				end = physnodes[i].end;
 
 			/*
@@ -641,7 +641,7 @@ static int __init numa_emulation(unsigned long start_pfn,
 	 */
 	remove_all_active_ranges();
 	for_each_node_mask(i, node_possible_map) {
-		e820_register_active_regions(i, nodes[i].start >> PAGE_SHIFT,
+		lmb_register_active_regions(i, nodes[i].start >> PAGE_SHIFT,
 						nodes[i].end >> PAGE_SHIFT);
 		setup_node_bootmem(i, nodes[i].start, nodes[i].end);
 	}
@@ -694,7 +694,7 @@ void __init initmem_init(unsigned long start_pfn, unsigned long last_pfn,
 	node_set(0, node_possible_map);
 	for (i = 0; i < nr_cpu_ids; i++)
 		numa_set_node(i, 0);
-	e820_register_active_regions(0, start_pfn, last_pfn);
+	lmb_register_active_regions(0, start_pfn, last_pfn);
 	setup_node_bootmem(0, start_pfn << PAGE_SHIFT, last_pfn << PAGE_SHIFT);
 }
 
diff --git a/arch/x86/mm/srat_32.c b/arch/x86/mm/srat_32.c
index 9324f13..a97c922 100644
--- a/arch/x86/mm/srat_32.c
+++ b/arch/x86/mm/srat_32.c
@@ -264,7 +264,7 @@ int __init get_memcfg_from_srat(void)
 		if (node_read_chunk(chunk->nid, chunk))
 			continue;
 
-		e820_register_active_regions(chunk->nid, chunk->start_pfn,
+		lmb_register_active_regions(chunk->nid, chunk->start_pfn,
 					     min(chunk->end_pfn, max_pfn));
 	}
 	/* for out of order entries in SRAT */
diff --git a/arch/x86/mm/srat_64.c b/arch/x86/mm/srat_64.c
index 28c6876..634392d 100644
--- a/arch/x86/mm/srat_64.c
+++ b/arch/x86/mm/srat_64.c
@@ -98,7 +98,7 @@ void __init acpi_numa_slit_init(struct acpi_table_slit *slit)
 	unsigned long phys;
 
 	length = slit->header.length;
-	phys = find_e820_area(0, max_pfn_mapped<<PAGE_SHIFT, length,
+	phys = find_lmb_area(0, max_pfn_mapped<<PAGE_SHIFT, length,
 		 PAGE_SIZE);
 
 	if (phys == -1L)
@@ -324,7 +324,7 @@ static int __init nodes_cover_memory(const struct bootnode *nodes)
 			pxmram = 0;
 	}
 
-	e820ram = max_pfn - (e820_hole_size(0, max_pfn<<PAGE_SHIFT)>>PAGE_SHIFT);
+	e820ram = max_pfn - (lmb_hole_size(0, max_pfn<<PAGE_SHIFT)>>PAGE_SHIFT);
 	/* We seem to lose 3 pages somewhere. Allow 1M of slack. */
 	if ((long)(e820ram - pxmram) >= (1<<(20 - PAGE_SHIFT))) {
 		printk(KERN_ERR
@@ -373,7 +373,7 @@ int __init acpi_scan_nodes(unsigned long start, unsigned long end)
 	}
 
 	for_each_node_mask(i, nodes_parsed)
-		e820_register_active_regions(i, nodes[i].start >> PAGE_SHIFT,
+		lmb_register_active_regions(i, nodes[i].start >> PAGE_SHIFT,
 						nodes[i].end >> PAGE_SHIFT);
 	/* for out of order entries in SRAT */
 	sort_node_map();
-- 
1.6.4.2

[PATCH 7/8] early_res: prepare for other platform to use it

[Yinghai Lu]

add weak reserver_bootmem_generic()

also clean up x86 64 bit one.

add include for linux/early_res.h

Signed-off-by: Yinghai Lu <yinghai@kernel.org>
---
 arch/x86/mm/init_32.c |    5 -----
 arch/x86/mm/init_64.c |   18 ------------------
 mm/bootmem.c          |    7 +++++++
 mm/page_alloc.c       |    1 +
 4 files changed, 8 insertions(+), 23 deletions(-)

diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c
index a7625d5..16001e1 100644
--- a/arch/x86/mm/init_32.c
+++ b/arch/x86/mm/init_32.c
@@ -1070,8 +1070,3 @@ void mark_rodata_ro(void)
 }
 #endif
 
-int __init reserve_bootmem_generic(unsigned long phys, unsigned long len,
-				   int flags)
-{
-	return reserve_bootmem(phys, len, flags);
-}
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index dd88ef9..cc3627b 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -801,10 +801,6 @@ void mark_rodata_ro(void)
 int __init reserve_bootmem_generic(unsigned long phys, unsigned long len,
 				   int flags)
 {
-#ifdef CONFIG_NUMA
-	int nid, next_nid;
-	int ret;
-#endif
 	unsigned long pfn = phys >> PAGE_SHIFT;
 
 	if (pfn >= max_pfn) {
@@ -820,21 +816,7 @@ int __init reserve_bootmem_generic(unsigned long phys, unsigned long len,
 		return -EFAULT;
 	}
 
-	/* Should check here against the e820 map to avoid double free */
-#ifdef CONFIG_NUMA
-	nid = phys_to_nid(phys);
-	next_nid = phys_to_nid(phys + len - 1);
-	if (nid == next_nid)
-		ret = reserve_bootmem_node(NODE_DATA(nid), phys, len, flags);
-	else
-		ret = reserve_bootmem(phys, len, flags);
-
-	if (ret != 0)
-		return ret;
-
-#else
 	reserve_bootmem(phys, len, flags);
-#endif
 
 	if (phys+len <= MAX_DMA_PFN*PAGE_SIZE) {
 		dma_reserve += len / PAGE_SIZE;
diff --git a/mm/bootmem.c b/mm/bootmem.c
index d7c791e..760c279 100644
--- a/mm/bootmem.c
+++ b/mm/bootmem.c
@@ -14,6 +14,7 @@
 #include <linux/module.h>
 #include <linux/kmemleak.h>
 #include <linux/range.h>
+#include <linux/early_res.h>
 
 #include <asm/bug.h>
 #include <asm/io.h>
@@ -525,6 +526,12 @@ int __init reserve_bootmem(unsigned long addr, unsigned long size,
 }
 
 #ifndef CONFIG_NO_BOOTMEM
+int __weak __init reserve_bootmem_generic(unsigned long phys, unsigned long len,
+				   int flags)
+{
+	return reserve_bootmem(phys, len, flags);
+}
+
 static unsigned long __init align_idx(struct bootmem_data *bdata,
 				      unsigned long idx, unsigned long step)
 {
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 04c241a..e7b1d72 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -21,6 +21,7 @@
 #include <linux/pagemap.h>
 #include <linux/jiffies.h>
 #include <linux/bootmem.h>
+#include <linux/early_res.h>
 #include <linux/compiler.h>
 #include <linux/kernel.h>
 #include <linux/kmemcheck.h>
-- 
1.6.4.2

[PATCH 8/8] powerpc : use early_res/nobootmem

[Yinghai Lu]

new early_res is extension for lmb, and it could be used to replace bootmem

also even could be used to simplify the bootmem path if needed.

--NOT TESTED--

Signed-off-by: Yinghai Lu <yinghai@kernel.org>
---
 arch/powerpc/Kconfig   |   14 ++++++++++++++
 arch/powerpc/mm/mem.c  |   23 +++++++++++++++++++++--
 arch/powerpc/mm/numa.c |   11 ++++++++++-
 3 files changed, 45 insertions(+), 3 deletions(-)

diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 2e19500..307c3ef 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -52,6 +52,9 @@ config HAVE_SETUP_PER_CPU_AREA
 config NEED_PER_CPU_EMBED_FIRST_CHUNK
 	def_bool PPC64
 
+config HAVE_EARLY_RES
+	def_bool y
+
 config IRQ_PER_CPU
 	bool
 	default y
@@ -443,6 +446,17 @@ config ARCH_SPARSEMEM_DEFAULT
 	def_bool y
 	depends on (SMP && PPC_PSERIES) || PPC_PS3
 
+config NO_BOOTMEM
+	default y
+	bool "Disable Bootmem code"
+	---help---
+	  Use early_res directly instead of bootmem before slab is ready.
+		- allocator (buddy) [generic]
+		- early allocator (bootmem) [generic]
+		- very early allocator (reserve_early*()/lmb)
+	  So reduce one layer between early allocator to final allocator
+
+
 config ARCH_POPULATES_NODE_MAP
 	def_bool y
 
diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c
index 448f972..7004f9e 100644
--- a/arch/powerpc/mm/mem.c
+++ b/arch/powerpc/mm/mem.c
@@ -179,9 +179,11 @@ EXPORT_SYMBOL_GPL(walk_system_ram_range);
 void __init do_init_bootmem(void)
 {
 	unsigned long i;
-	unsigned long start, bootmap_pages;
 	unsigned long total_pages;
+#ifndef CONFIG_NO_BOOTMEM
+	unsigned long start, bootmap_pages;
 	int boot_mapsize;
+#endif
 
 	max_low_pfn = max_pfn = lmb_end_of_DRAM() >> PAGE_SHIFT;
 	total_pages = (lmb_end_of_DRAM() - memstart_addr) >> PAGE_SHIFT;
@@ -189,7 +191,9 @@ void __init do_init_bootmem(void)
 	total_pages = total_lowmem >> PAGE_SHIFT;
 	max_low_pfn = lowmem_end_addr >> PAGE_SHIFT;
 #endif
+	min_low_pfn = MEMORY_START >> PAGE_SHIFT;
 
+#ifndef CONFIG_NO_BOOTMEM
 	/*
 	 * Find an area to use for the bootmem bitmap.  Calculate the size of
 	 * bitmap required as (Total Memory) / PAGE_SIZE / BITS_PER_BYTE.
@@ -199,8 +203,8 @@ void __init do_init_bootmem(void)
 
 	start = lmb_alloc(bootmap_pages << PAGE_SHIFT, PAGE_SIZE);
 
-	min_low_pfn = MEMORY_START >> PAGE_SHIFT;
 	boot_mapsize = init_bootmem_node(NODE_DATA(0), start >> PAGE_SHIFT, min_low_pfn, max_low_pfn);
+#endif
 
 	/* Add active regions with valid PFNs */
 	for (i = 0; i < lmb.memory.cnt; i++) {
@@ -210,6 +214,7 @@ void __init do_init_bootmem(void)
 		add_active_range(0, start_pfn, end_pfn);
 	}
 
+#ifndef CONFIG_NO_BOOTMEM
 	/* Add all physical memory to the bootmem map, mark each area
 	 * present.
 	 */
@@ -241,6 +246,7 @@ void __init do_init_bootmem(void)
 				BOOTMEM_DEFAULT);
 
 #endif
+#endif
 	/* XXX need to clip this if using highmem? */
 	sparse_memory_present_with_active_regions(0);
 
@@ -311,6 +317,16 @@ void __init paging_init(void)
 }
 #endif /* ! CONFIG_NEED_MULTIPLE_NODES */
 
+u64 __init get_max_mapped(void)
+{
+	u64 end = max_low_pfn;
+
+	end <<= PAGE_SHIFT;
+
+	return end;
+}
+
+
 void __init mem_init(void)
 {
 #ifdef CONFIG_NEED_MULTIPLE_NODES
@@ -337,6 +353,9 @@ void __init mem_init(void)
 				free_all_bootmem_node(NODE_DATA(nid));
 		}
 	}
+#ifdef CONFIG_NO_BOOTMEM
+	totalram_pages += free_all_memory_core_early(MAX_NUMNODES);
+#endif
 #else
 	max_mapnr = max_pfn;
 	totalram_pages += free_all_bootmem();
diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c
index 64c0022..024c3ff 100644
--- a/arch/powerpc/mm/numa.c
+++ b/arch/powerpc/mm/numa.c
@@ -90,6 +90,7 @@ static int __cpuinit fake_numa_create_new_node(unsigned long end_pfn,
 	return 0;
 }
 
+#ifndef CONFIG_NO_BOOTMEM
 /*
  * get_active_region_work_fn - A helper function for get_node_active_region
  *	Returns datax set to the start_pfn and end_pfn if they contain
@@ -131,6 +132,7 @@ static void __init get_node_active_region(unsigned long start_pfn,
 	node_ar->end_pfn = start_pfn;
 	work_with_active_regions(nid, get_active_region_work_fn, node_ar);
 }
+#endif
 
 static void __cpuinit map_cpu_to_node(int cpu, int node)
 {
@@ -845,6 +847,7 @@ static struct notifier_block __cpuinitdata ppc64_numa_nb = {
 	.priority = 1 /* Must run before sched domains notifier. */
 };
 
+#ifndef CONFIG_NO_BOOTMEM
 static void mark_reserved_regions_for_nid(int nid)
 {
 	struct pglist_data *node = NODE_DATA(nid);
@@ -911,7 +914,7 @@ static void mark_reserved_regions_for_nid(int nid)
 		}
 	}
 }
-
+#endif
 
 void __init do_init_bootmem(void)
 {
@@ -932,8 +935,10 @@ void __init do_init_bootmem(void)
 
 	for_each_online_node(nid) {
 		unsigned long start_pfn, end_pfn;
+#ifndef CONFIG_NO_BOOTMEM
 		void *bootmem_vaddr;
 		unsigned long bootmap_pages;
+#endif
 
 		get_pfn_range_for_nid(nid, &start_pfn, &end_pfn);
 
@@ -951,7 +956,9 @@ void __init do_init_bootmem(void)
   		dbg("node %d\n", nid);
 		dbg("NODE_DATA() = %p\n", NODE_DATA(nid));
 
+#ifndef CONFIG_NO_BOOTMEM
 		NODE_DATA(nid)->bdata = &bootmem_node_data[nid];
+#endif
 		NODE_DATA(nid)->node_start_pfn = start_pfn;
 		NODE_DATA(nid)->node_spanned_pages = end_pfn - start_pfn;
 
@@ -961,6 +968,7 @@ void __init do_init_bootmem(void)
   		dbg("start_paddr = %lx\n", start_pfn << PAGE_SHIFT);
   		dbg("end_paddr = %lx\n", end_pfn << PAGE_SHIFT);
 
+#ifndef CONFIG_NO_BOOTMEM
 		bootmap_pages = bootmem_bootmap_pages(end_pfn - start_pfn);
 		bootmem_vaddr = careful_zallocation(nid,
 					bootmap_pages << PAGE_SHIFT,
@@ -979,6 +987,7 @@ void __init do_init_bootmem(void)
 		 * done correctly.
 		 */
 		mark_reserved_regions_for_nid(nid);
+#endif
 		sparse_memory_present_with_active_regions(nid);
 	}
 
-- 
1.6.4.2

Re: [PATCH -v4 00/08] use lmb with x86

[Ingo Molnar]

* Yinghai Lu <yinghai@kernel.org> wrote:

> new early_res is lmb extension. and it could be used to replace bootmem.

Why not do what we suggested: extend lmb.c to also offer the 
early_res-equivalent functionality, and remove kernel/early_res.c and move 
lib/lmb.c to mm/lmb.c?

We dont want two facilities (early_res and lmb) really ...

	Ingo

Re: [PATCH -v4 00/08] use lmb with x86

[Michael Ellerman]

[-- Attachment #1: Type: text/plain, Size: 890 bytes --]

On Wed, 2010-03-24 at 11:48 +0100, Ingo Molnar wrote:
> * Yinghai Lu <yinghai@kernel.org> wrote:
> 
> > new early_res is lmb extension. and it could be used to replace bootmem.
> 
> Why not do what we suggested: extend lmb.c to also offer the 
> early_res-equivalent functionality, and remove kernel/early_res.c and move 
> lib/lmb.c to mm/lmb.c?
> 
> We dont want two facilities (early_res and lmb) really ...

Exactly. 

This series seems to leave us with kernel/early_res.c (which should
never have moved out of arch/x86 AFAICS) - as well as using some of
lmb.c.

It doesn't compile on powerpc, because early_res.c is looking for
find_fw_memmap_area() which is still under arch/x86.

And sprinkling CONFIG_NO_BOOTMEM everywhere is getting a bit gross. I
notice that's already happened to mm/(bootmem|page_alloc).c but
propagating it further is not nice.

cheers

[-- Attachment #2: This is a digitally signed message part --]
[-- Type: application/pgp-signature, Size: 197 bytes --]

Re: [PATCH -v4 00/08] use lmb with x86

[Yinghai Lu]

On 03/24/2010 04:41 AM, Michael Ellerman wrote:
> On Wed, 2010-03-24 at 11:48 +0100, Ingo Molnar wrote:
>> * Yinghai Lu <yinghai@kernel.org> wrote:
>>
>>> new early_res is lmb extension. and it could be used to replace bootmem.
>>
>> Why not do what we suggested: extend lmb.c to also offer the 
>> early_res-equivalent functionality, and remove kernel/early_res.c and move 
>> lib/lmb.c to mm/lmb.c?
>>
>> We dont want two facilities (early_res and lmb) really ...
> 
> Exactly. 
> 
> This series seems to leave us with kernel/early_res.c (which should
> never have moved out of arch/x86 AFAICS) - as well as using some of
> lmb.c.
the new version...
http://git.kernel.org/?p=linux/kernel/git/yinghai/linux-2.6-yinghai.git;a=blob;f=kernel/early_res.c;h=a7933939b44ae1ccb72e30203031f5b742c88a3f;hb=c9115b0731084ec0c0e164456b7434ea61c2a67b

should be clean.

> 
> It doesn't compile on powerpc, because early_res.c is looking for
> find_fw_memmap_area() which is still under arch/x86.

it looks that you are looking at old version somehow.

please check
http://git.kernel.org/?p=linux/kernel/git/yinghai/linux-2.6-yinghai.git;a=summary

> 
> And sprinkling CONFIG_NO_BOOTMEM everywhere is getting a bit gross. I
> notice that's already happened to mm/(bootmem|page_alloc).c but
> propagating it further is not nice.

for converting smoothly, before we remove bootmem core, we can keep it. and can compare bootmem and nobootmem side by side.

Thanks

Yinghai

Re: [PATCH -v4 00/08] use lmb with x86

[Yinghai Lu]

On 03/24/2010 03:48 AM, Ingo Molnar wrote:
> 
> * Yinghai Lu <yinghai@kernel.org> wrote:
> 
>> new early_res is lmb extension. and it could be used to replace bootmem.
> 
> Why not do what we suggested: extend lmb.c to also offer the 
> early_res-equivalent functionality, and remove kernel/early_res.c and move 
> lib/lmb.c to mm/lmb.c?
> 
> We dont want two facilities (early_res and lmb) really ...

the new early_res.c is extension to lmb.

it will
1. add find_lmb_area
2. add check_double_region array with find_lmb_area
3. free_early and reserve_early is wrapper for lmb_free, and lmb_reserve with array size checking
4. some other generizing function like lmb_register_active_regions and lmb_hole_size that could be all lmb users.

so it is seperated file at point.

if lmb guys are happy, we can merge early_res.c and lmb.c. just put them in one file.

Thanks

Yinghai

Re: [PATCH 1/8] x86: do not free zero sized per cpu areas

[Joel Becker]

On Wed, Mar 24, 2010 at 03:37:02AM -0700, Yinghai Lu wrote:
> From: Ian Campbell <ian.campbell@citrix.com>
> 
> This avoids an infinite loop in free_early_partial().
> 
> Add a warning to free_early_partial to catch future problems.
> 
> -v5: put back start > end back into WARN_ONCE()
> -v6: use one line for if according to linus
> 
> Signed-off-by: Ian Campbell <ian.campbell@citrix.com>
> Signed-off-by: Yinghai Lu <yinghai@kernel.org>
> Cc: Peter Zijlstra <peterz@infradead.org>
> Cc: Ingo Molnar <mingo@elte.hu>

Tested-by: Joel Becker <joel.becker@oracle.com>

	I ran into this when moving my paravirt_ops PVMs to 2.6.34-rc1.
I turned on CONFIG_NO_BOOTMEM to try it because it was the default.  I
had to put earlyprintk=xen on the command line to debug the problem.
My boots hung after:

...
(early) Local APIC disabled by BIOS -- you can enable it with "lapic"
(early) APIC: disable apic facility
(early) APIC: switched to apic NOOP
(early) Allocating PCI resources starting at 78000000 (gap: 78000000:88000000)
(early) Booting paravirtualized kernel on Xen
(early) Xen version: 3.1.3-rc3
(early) setup_percpu: NR_CPUS:8 nr_cpumask_bits:8 nr_cpu_ids:2 nr_node_ids:1

	Bisecting narrowed the problem to fb90ef [early_res: Add
free_early_partial()].  Turning off CONFIG_NO_BOOTMEM allowed me to
boot.  I then hunted up references to this function, which found me this
patch.
	This patch successfully resolved the problem.

Joel

-- 

"The nice thing about egotists is that they don't talk about other
 people."
         - Lucille S. Harper

Joel Becker
Principal Software Developer
Oracle
E-mail: joel.becker@oracle.com
Phone: (650) 506-8127

[PATCH -v4 00/08] use lmb with x86

[Yinghai Lu]

new early_res is lmb extension. and it could be used to replace bootmem.

even could share some code before bootmem, like register_active_region, and
lm_reserved_to_bootmem

add test version for powerpc

Thanks

Yinghai

[PATCH -v4 00/08] use lmb with x86

[Yinghai Lu]

new early_res is lmb extension. and it could be used to replace bootmem.

even could share some code before bootmem, like register_active_region, and
lm_reserved_to_bootmem

add test version for powerpc

Thanks

Yinghai