[PATCH -v8 00/24] use lmb with x86

[PATCH -v8 00/24] use lmb with x86

[Yinghai Lu]

the new lmb could be used to early_res in x86.

Suggested by: David, Ben, and Thomas

First three patches should go into 2.6.34

-v6: change sequence as requested by Thomas
-v7: seperate them to more patches
-v8: add boundary checking to make sure not free partial page.

Please check them.

Thanks

Yinghai

[PATCH 01/24] x86: Make smp_locks end with page alignment

[Yinghai Lu]

Try to fix
------------[ cut here ]------------
WARNING: at arch/x86/mm/init.c:342 free_init_pages+0x4c/0xfa()
free_init_pages: range [0x40daf000, 0x40db5c24] is not aligned
Modules linked in:
Pid: 0, comm: swapper Not tainted 2.6.34-rc2-tip-03946-g4f16b23-dirty #50
Call Trace:
 [<40232e9f>] warn_slowpath_common+0x65/0x7c
 [<4021c9f0>] ? free_init_pages+0x4c/0xfa
 [<40881434>] ? _etext+0x0/0x24
 [<40232eea>] warn_slowpath_fmt+0x24/0x27
 [<4021c9f0>] free_init_pages+0x4c/0xfa
 [<40881434>] ? _etext+0x0/0x24
 [<40d3f4bd>] alternative_instructions+0xf6/0x100
 [<40d3fe4f>] check_bugs+0xbd/0xbf
 [<40d398a7>] start_kernel+0x2d5/0x2e4
 [<40d390ce>] i386_start_kernel+0xce/0xd5
---[ end trace 4eaa2a86a8e2da22 ]---

Comments in vmlinux.lds.S already said:
|        /*
|         * smp_locks might be freed after init
|         * start/end must be page aligned
|         */

Signed-off-by: Yinghai Lu <yinghai@kernel.org>
---
 arch/x86/kernel/vmlinux.lds.S |    2 +-
 1 files changed, 1 insertions(+), 1 deletions(-)

diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S
index 44879df..2cc2497 100644
--- a/arch/x86/kernel/vmlinux.lds.S
+++ b/arch/x86/kernel/vmlinux.lds.S
@@ -291,8 +291,8 @@ SECTIONS
 	.smp_locks : AT(ADDR(.smp_locks) - LOAD_OFFSET) {
 		__smp_locks = .;
 		*(.smp_locks)
-		__smp_locks_end = .;
 		. = ALIGN(PAGE_SIZE);
+		__smp_locks_end = .;
 	}
 
 #ifdef CONFIG_X86_64
-- 
1.6.4.2

[PATCH 02/24] x86: Make sure free_init_pages() free pages in boundary

[Yinghai Lu]

When CONFIG_NO_BOOTMEM, it could use memory more effient, or more compact.

Example is:
Allocated new RAMDISK: 00ec2000 - 0248ce57
Move RAMDISK from 000000002ea04000 - 000000002ffcee56 to 00ec2000 - 0248ce56

The new RAMDISK's end is not page aligned.
Last page could use shared with other user.

When free_init_pages are called for initrd or .init, the page could be freed
could have chance to corrupt other data.

code segment in free_init_pages()
|        for (; addr < end; addr += PAGE_SIZE) {
|                ClearPageReserved(virt_to_page(addr));
|                init_page_count(virt_to_page(addr));
|                memset((void *)(addr & ~(PAGE_SIZE-1)),
|                        POISON_FREE_INITMEM, PAGE_SIZE);
|                free_page(addr);
|                totalram_pages++;
|        }
last half page could be used as one whole free page.

Try to make the boundaries to be page aligned.

-v2: make the original initramdisk to be aligned, according to Johannes.
     otherwise we have chance to lose one page.
     we still need to keep initrd_end not aligned, otherwise it could
     confuse decompresser.

Reported-by: Stanislaw Gruszka <sgruszka@redhat.com>
Signed-off-by: Yinghai Lu <yinghai@kernel.org>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Tested-by: Stanislaw Gruszka <sgruszka@redhat.com>
---
 arch/x86/kernel/head32.c |    1 +
 arch/x86/kernel/head64.c |    1 +
 arch/x86/kernel/setup.c  |   40 +++++++++++++++++++++++-----------------
 arch/x86/mm/init.c       |   24 +++++++++++++++++++++++-
 4 files changed, 48 insertions(+), 18 deletions(-)

diff --git a/arch/x86/kernel/head32.c b/arch/x86/kernel/head32.c
index adedeef..fe3d953 100644
--- a/arch/x86/kernel/head32.c
+++ b/arch/x86/kernel/head32.c
@@ -47,6 +47,7 @@ void __init i386_start_kernel(void)
 		u64 ramdisk_image = boot_params.hdr.ramdisk_image;
 		u64 ramdisk_size  = boot_params.hdr.ramdisk_size;
 		u64 ramdisk_end   = ramdisk_image + ramdisk_size;
+		ramdisk_end = PFN_UP(ramdisk_end) << PAGE_SHIFT;
 		reserve_early(ramdisk_image, ramdisk_end, "RAMDISK");
 	}
 #endif
diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c
index b5a9896..fafba92 100644
--- a/arch/x86/kernel/head64.c
+++ b/arch/x86/kernel/head64.c
@@ -106,6 +106,7 @@ void __init x86_64_start_reservations(char *real_mode_data)
 		unsigned long ramdisk_image = boot_params.hdr.ramdisk_image;
 		unsigned long ramdisk_size  = boot_params.hdr.ramdisk_size;
 		unsigned long ramdisk_end   = ramdisk_image + ramdisk_size;
+		ramdisk_end = PFN_UP(ramdisk_end) << PAGE_SHIFT;
 		reserve_early(ramdisk_image, ramdisk_end, "RAMDISK");
 	}
 #endif
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 5d7ba1a..2a1b9d4 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -317,57 +317,61 @@ static void __init relocate_initrd(void)
 
 	u64 ramdisk_image = boot_params.hdr.ramdisk_image;
 	u64 ramdisk_size  = boot_params.hdr.ramdisk_size;
+	u64 ramdisk_end   = ramdisk_image + ramdisk_size;
 	u64 end_of_lowmem = max_low_pfn_mapped << PAGE_SHIFT;
+	u64 image, size_aligned;
 	u64 ramdisk_here;
 	unsigned long slop, clen, mapaddr;
 	char *p, *q;
 
+	ramdisk_end = PFN_UP(ramdisk_end) << PAGE_SHIFT;
+	size_aligned = ramdisk_end - ramdisk_image;
+
 	/* We need to move the initrd down into lowmem */
-	ramdisk_here = find_e820_area(0, end_of_lowmem, ramdisk_size,
+	ramdisk_here = find_e820_area(0, end_of_lowmem, size_aligned,
 					 PAGE_SIZE);
 
 	if (ramdisk_here == -1ULL)
 		panic("Cannot find place for new RAMDISK of size %lld\n",
-			 ramdisk_size);
+			 size_aligned);
 
 	/* Note: this includes all the lowmem currently occupied by
 	   the initrd, we rely on that fact to keep the data intact. */
-	reserve_early(ramdisk_here, ramdisk_here + ramdisk_size,
+	reserve_early(ramdisk_here, ramdisk_here + size_aligned,
 			 "NEW RAMDISK");
 	initrd_start = ramdisk_here + PAGE_OFFSET;
 	initrd_end   = initrd_start + ramdisk_size;
 	printk(KERN_INFO "Allocated new RAMDISK: %08llx - %08llx\n",
-			 ramdisk_here, ramdisk_here + ramdisk_size);
+			 ramdisk_here, ramdisk_here + size_aligned);
 
 	q = (char *)initrd_start;
 
 	/* Copy any lowmem portion of the initrd */
-	if (ramdisk_image < end_of_lowmem) {
-		clen = end_of_lowmem - ramdisk_image;
-		p = (char *)__va(ramdisk_image);
+	image = ramdisk_image;
+	if (image < end_of_lowmem) {
+		clen = end_of_lowmem - image;
+		p = (char *)__va(image);
 		memcpy(q, p, clen);
 		q += clen;
-		ramdisk_image += clen;
-		ramdisk_size  -= clen;
+		image += clen;
+		size_aligned  -= clen;
 	}
 
 	/* Copy the highmem portion of the initrd */
-	while (ramdisk_size) {
-		slop = ramdisk_image & ~PAGE_MASK;
-		clen = ramdisk_size;
+	while (size_aligned) {
+		slop = image & ~PAGE_MASK;
+		clen = size_aligned;
 		if (clen > MAX_MAP_CHUNK-slop)
 			clen = MAX_MAP_CHUNK-slop;
-		mapaddr = ramdisk_image & PAGE_MASK;
+		mapaddr = image & PAGE_MASK;
 		p = early_memremap(mapaddr, clen+slop);
 		memcpy(q, p+slop, clen);
 		early_iounmap(p, clen+slop);
 		q += clen;
-		ramdisk_image += clen;
-		ramdisk_size  -= clen;
+		image += clen;
+		size_aligned  -= clen;
 	}
 	/* high pages is not converted by early_res_to_bootmem */
-	ramdisk_image = boot_params.hdr.ramdisk_image;
-	ramdisk_size  = boot_params.hdr.ramdisk_size;
 	printk(KERN_INFO "Move RAMDISK from %016llx - %016llx to"
 		" %08llx - %08llx\n",
 		ramdisk_image, ramdisk_image + ramdisk_size - 1,
@@ -385,6 +389,8 @@ static void __init reserve_initrd(void)
 	    !ramdisk_image || !ramdisk_size)
 		return;		/* No initrd provided by bootloader */
 
+	ramdisk_end = PFN_UP(ramdisk_end) << PAGE_SHIFT;
+
 	initrd_start = 0;
 
 	if (ramdisk_size >= (end_of_lowmem>>1)) {
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index e71c5cb..727d6b0 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -332,6 +332,16 @@ int devmem_is_allowed(unsigned long pagenr)
 void free_init_pages(char *what, unsigned long begin, unsigned long end)
 {
 	unsigned long addr = begin;
+	unsigned long addr_aligned, end_aligned;
+
+	/* Make sure boundaries are page aligned */
+	addr_aligned = PFN_UP(addr) << PAGE_SHIFT;
+	end_aligned = PFN_DOWN(end) << PAGE_SHIFT;
+
+	if (WARN(addr_aligned != addr || end_aligned != end, "free_init_pages: range [%#lx, %#lx] is not aligned\n", addr, end)) {
+		addr = addr_aligned;
+		end = end_aligned;
+	}
 
 	if (addr >= end)
 		return;
@@ -376,6 +386,18 @@ void free_initmem(void)
 #ifdef CONFIG_BLK_DEV_INITRD
 void free_initrd_mem(unsigned long start, unsigned long end)
 {
-	free_init_pages("initrd memory", start, end);
+	unsigned long end_aligned;
+
+	/*
+	 * end could be not aligned, and We can not align that,
+	 * decompresser could be confused by aligned initrd_end
+	 * We already reserve the end partial page before in
+	 *   - i386_start_kernel()
+	 *   - x86_64_start_kernel()
+	 *   - relocate_initrd()
+	 * So here we can do PFN_UP() safely to get partial page to be freed
+	 */
+	end_aligned = PFN_UP(end) << PAGE_SHIFT;
+	free_init_pages("initrd memory", start, end_aligned);
 }
 #endif
-- 
1.6.4.2

[PATCH 03/24] 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 warning according to linus
-v7: more test by

Signed-off-by: Ian Campbell <ian.campbell@citrix.com>
Signed-off-by: Yinghai Lu <yinghai@kernel.org>
Tested-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Tested-by: Joel Becker <joel.becker@oracle.com>
Tested-by: Stanislaw Gruszka <sgruszka@redhat.com>
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 04/24] lmb: Move lmb.c to mm/

[Yinghai Lu]

that is memory related, so move to mm/ according to Ingo

Signed-off-by: Yinghai Lu <yinghai@kernel.org>
---
 lib/Makefile      |    2 --
 mm/Makefile       |    2 ++
 {lib => mm}/lmb.c |    0
 3 files changed, 2 insertions(+), 2 deletions(-)
 rename {lib => mm}/lmb.c (100%)

diff --git a/lib/Makefile b/lib/Makefile
index 2e152ae..a463a4d 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -85,8 +85,6 @@ obj-$(CONFIG_FAULT_INJECTION) += fault-inject.o
 
 lib-$(CONFIG_GENERIC_BUG) += bug.o
 
-obj-$(CONFIG_HAVE_LMB) += lmb.o
-
 obj-$(CONFIG_HAVE_ARCH_TRACEHOOK) += syscall.o
 
 obj-$(CONFIG_DYNAMIC_DEBUG) += dynamic_debug.o
diff --git a/mm/Makefile b/mm/Makefile
index 7a68d2a..df22fd1 100644
--- a/mm/Makefile
+++ b/mm/Makefile
@@ -15,6 +15,8 @@ obj-y			:= bootmem.o filemap.o mempool.o oom_kill.o fadvise.o \
 			   $(mmu-y)
 obj-y += init-mm.o
 
+obj-$(CONFIG_HAVE_LMB) += lmb.o
+
 obj-$(CONFIG_BOUNCE)	+= bounce.o
 obj-$(CONFIG_SWAP)	+= page_io.o swap_state.o swapfile.o thrash.o
 obj-$(CONFIG_HAS_DMA)	+= dmapool.o
diff --git a/lib/lmb.c b/mm/lmb.c
similarity index 100%
rename from lib/lmb.c
rename to mm/lmb.c
-- 
1.6.4.2

[PATCH 05/24] lmb: Seperate region array from lmb_region struct

[Yinghai Lu]

lmb_init() will connect them back.

Add nr_regions in struct lmb_region to track region array size.

Signed-off-by: Yinghai Lu <yinghai@kernel.org>
---
 include/linux/lmb.h |    3 ++-
 mm/lmb.c            |    9 ++++++++-
 2 files changed, 10 insertions(+), 2 deletions(-)

diff --git a/include/linux/lmb.h b/include/linux/lmb.h
index f3d1433..e14ea8d 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 {
diff --git a/mm/lmb.c b/mm/lmb.c
index b1fc526..65b62dc 100644
--- a/mm/lmb.c
+++ b/mm/lmb.c
@@ -18,6 +18,8 @@
 #define LMB_ALLOC_ANYWHERE	0
 
 struct lmb lmb;
+static struct lmb_property lmb_memory_region[MAX_LMB_REGIONS + 1];
+static 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 06/24] lmb: Add find_lmb_area()

[Yinghai Lu]

It will try find area according with size/align in specified range (start, end).

Need use it find correct buffer for new lmb.reserved.region.

also make it more easy for x86 to use lmb.
x86 early_res is using find/reserve pattern instead of alloc.

find_lmb_area() will hohor goal

When we need temperary buff for range array etc for range work, if We are using
lmb_alloc(), We will need to add some post fix code for buffer that is used
by range array, because it is in the lmb.reserved already.

Signed-off-by: Yinghai Lu <yinghai@kernel.org>
---
 include/linux/lmb.h |    4 ++
 mm/lmb.c            |   81 +++++++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 85 insertions(+), 0 deletions(-)

diff --git a/include/linux/lmb.h b/include/linux/lmb.h
index e14ea8d..05234bd 100644
--- a/include/linux/lmb.h
+++ b/include/linux/lmb.h
@@ -83,6 +83,10 @@ lmb_end_pfn(struct lmb_region *type, unsigned long region_nr)
 	       lmb_size_pages(type, region_nr);
 }
 
+u64 __find_lmb_area(u64 ei_start, u64 ei_last, u64 start, u64 end,
+			 u64 size, u64 align);
+u64 find_lmb_area(u64 start, u64 end, u64 size, u64 align);
+
 #include <asm/lmb.h>
 
 #endif /* __KERNEL__ */
diff --git a/mm/lmb.c b/mm/lmb.c
index 65b62dc..d5d5dc4 100644
--- a/mm/lmb.c
+++ b/mm/lmb.c
@@ -11,9 +11,13 @@
  */
 
 #include <linux/kernel.h>
+#include <linux/types.h>
 #include <linux/init.h>
 #include <linux/bitops.h>
 #include <linux/lmb.h>
+#include <linux/bootmem.h>
+#include <linux/mm.h>
+#include <linux/range.h>
 
 #define LMB_ALLOC_ANYWHERE	0
 
@@ -546,3 +550,80 @@ int lmb_find(struct lmb_property *res)
 	}
 	return -1;
 }
+
+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 bool __init bad_addr(u64 *addrp, u64 size, u64 align)
+{
+	int i;
+	u64 addr = *addrp;
+	bool changed = false;
+	struct lmb_property *r;
+again:
+	i = find_overlapped_early(addr, addr + size);
+	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;
+}
+
+u64 __init __find_lmb_area(u64 ei_start, u64 ei_last, u64 start, u64 end,
+				 u64 size, u64 align)
+{
+	u64 addr, last;
+
+	addr = round_up(ei_start, align);
+	if (addr < start)
+		addr = round_up(start, align);
+	if (addr >= ei_last)
+		goto out;
+	while (bad_addr(&addr, size, align) && addr+size <= ei_last)
+		;
+	last = addr + size;
+	if (last > ei_last)
+		goto out;
+	if (last > end)
+		goto out;
+
+	return addr;
+
+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_lmb_area(ei_start, ei_last, start, end,
+					 size, align);
+
+		if (addr != -1ULL)
+			return addr;
+	}
+	return -1ULL;
+}
-- 
1.6.4.2

[PATCH 07/24] lmb: Add reserve_lmb/free_lmb

[Yinghai Lu]

They will check if the region array is big enough.

__check_and_double_region_array will try to double the region if that array spare
slots if not big enough.
find_lmb_area() is used to find good postion for new region array.
Old array will be copied to new array.

Arch code should provide to get_max_mapped, so the new array have accessiable
address

Signed-off-by: Yinghai Lu <yinghai@kernel.org>
---
 include/linux/lmb.h |    4 ++
 mm/lmb.c            |   89 +++++++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 93 insertions(+), 0 deletions(-)

diff --git a/include/linux/lmb.h b/include/linux/lmb.h
index 05234bd..95ae3f4 100644
--- a/include/linux/lmb.h
+++ b/include/linux/lmb.h
@@ -83,9 +83,13 @@ lmb_end_pfn(struct lmb_region *type, unsigned long region_nr)
 	       lmb_size_pages(type, region_nr);
 }
 
+void reserve_lmb(u64 start, u64 end, char *name);
+void free_lmb(u64 start, u64 end);
+void add_lmb_memory(u64 start, u64 end);
 u64 __find_lmb_area(u64 ei_start, u64 ei_last, u64 start, u64 end,
 			 u64 size, u64 align);
 u64 find_lmb_area(u64 start, u64 end, u64 size, u64 align);
+u64 get_max_mapped(void);
 
 #include <asm/lmb.h>
 
diff --git a/mm/lmb.c b/mm/lmb.c
index d5d5dc4..9798458 100644
--- a/mm/lmb.c
+++ b/mm/lmb.c
@@ -551,6 +551,95 @@ int lmb_find(struct lmb_property *res)
 	return -1;
 }
 
+u64 __weak __init get_max_mapped(void)
+{
+	u64 end = max_low_pfn;
+
+	end <<= PAGE_SHIFT;
+
+	return 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 lmb_property *new, *old;
+	unsigned long rgnsz = type->nr_regions;
+
+	/* Do we have enough slots left ? */
+	if ((rgnsz - type->cnt) > max_t(unsigned long, rgnsz/8, 2))
+		return;
+
+	old = type->region;
+	/* Double the array size */
+	size = sizeof(struct lmb_property) * rgnsz * 2;
+	if (old == static_region)
+		start = 0;
+	else
+		start = __pa(old) + sizeof(struct lmb_property) * rgnsz;
+	end = ex_start;
+	mem = -1ULL;
+	if (start + size < end)
+		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_lmb_area(start, end, size, sizeof(struct lmb_property));
+	}
+	if (mem == -1ULL)
+		panic("can not find more space for lmb.reserved.region array");
+
+	new = __va(mem);
+	/* Copy old to new */
+	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);
+}
+
+void __init add_lmb_memory(u64 start, u64 end)
+{
+	__check_and_double_region_array(&lmb.memory, &lmb_memory_region[0], start, end);
+	lmb_add(start, end - start);
+}
+
+void __init reserve_lmb(u64 start, u64 end, char *name)
+{
+	if (start == end)
+		return;
+
+	if (WARN_ONCE(start > end, "reserve_lmb: wrong range [%#llx, %#llx]\n", start, end))
+		return;
+
+	__check_and_double_region_array(&lmb.reserved, &lmb_reserved_region[0], start, end);
+	lmb_reserve(start, end - start);
+}
+
+void __init free_lmb(u64 start, u64 end)
+{
+	if (start == end)
+		return;
+
+	if (WARN_ONCE(start > end, "free_lmb: wrong range [%#llx, %#llx]\n", start, end))
+		return;
+
+	/* 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);
+}
+
 static int __init find_overlapped_early(u64 start, u64 end)
 {
 	int i;
-- 
1.6.4.2

[PATCH 08/24] lmb: Add find_lmb_area_size()

[Yinghai Lu]

The same as find_lmb_area(), but size is returned according free range.

Will be used to find free ranges for early_memtest and memory corruption check

Signed-off-by: Yinghai Lu <yinghai@kernel.org>
---
 include/linux/lmb.h |    1 +
 mm/lmb.c            |   80 +++++++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 81 insertions(+), 0 deletions(-)

diff --git a/include/linux/lmb.h b/include/linux/lmb.h
index 95ae3f4..7301072 100644
--- a/include/linux/lmb.h
+++ b/include/linux/lmb.h
@@ -89,6 +89,7 @@ void add_lmb_memory(u64 start, u64 end);
 u64 __find_lmb_area(u64 ei_start, u64 ei_last, u64 start, u64 end,
 			 u64 size, u64 align);
 u64 find_lmb_area(u64 start, u64 end, u64 size, u64 align);
+u64 find_lmb_area_size(u64 start, u64 *sizep, u64 align);
 u64 get_max_mapped(void);
 
 #include <asm/lmb.h>
diff --git a/mm/lmb.c b/mm/lmb.c
index 9798458..a91f48d 100644
--- a/mm/lmb.c
+++ b/mm/lmb.c
@@ -672,6 +672,40 @@ again:
 	return changed;
 }
 
+/* Check for already reserved areas */
+static inline bool __init bad_addr_size(u64 *addrp, u64 *sizep, u64 align)
+{
+	int i;
+	u64 addr = *addrp, last;
+	u64 size = *sizep;
+	bool changed = false;
+again:
+	last = addr + size;
+	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->base + r->size) && addr < (r->base + r->size)) {
+			addr = round_up(r->base + r->size, align);
+			size = last - addr;
+			changed = true;
+			goto again;
+		}
+		if (last <= (r->base + r->size) && addr >= r->base) {
+			(*sizep)++;
+			return false;
+		}
+	}
+	if (changed) {
+		*addrp = addr;
+		*sizep = size;
+	}
+	return changed;
+}
+
 u64 __init __find_lmb_area(u64 ei_start, u64 ei_last, u64 start, u64 end,
 				 u64 size, u64 align)
 {
@@ -696,6 +730,29 @@ out:
 	return -1ULL;
 }
 
+static u64 __init __find_lmb_area_size(u64 ei_start, u64 ei_last, u64 start,
+			 u64 *sizep, u64 align)
+{
+	u64 addr, last;
+
+	addr = round_up(ei_start, align);
+	if (addr < start)
+		addr = round_up(start, align);
+	if (addr >= ei_last)
+		goto out;
+	*sizep = ei_last - addr;
+	while (bad_addr_size(&addr, sizep, align) && addr + *sizep <= ei_last)
+		;
+	last = addr + *sizep;
+	if (last > ei_last)
+		goto out;
+
+	return addr;
+
+out:
+	return -1ULL;
+}
+
 /*
  * Find a free area with specified alignment in a specific range.
  */
@@ -716,3 +773,26 @@ u64 __init find_lmb_area(u64 start, u64 end, u64 size, u64 align)
 	}
 	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_lmb_area_size(ei_start, ei_last, start,
+					 sizep, align);
+
+		if (addr != -1ULL)
+			return addr;
+	}
+
+	return -1ULL;
+}
+
-- 
1.6.4.2

[PATCH 09/24] bootmem, x86: Add weak version of reserve_bootmem_generic

[Yinghai Lu]

It will be used lmb_to_bootmem converting

It is an wrapper for reserve_bootmem, and x86 64bit is using special one.

Also clean up that version for x86_64. We don't need to take care of numa
path for that, bootmem can handle it how

Signed-off-by: Yinghai Lu <yinghai@kernel.org>
---
 arch/x86/mm/init_32.c |    6 ------
 arch/x86/mm/init_64.c |   20 ++------------------
 mm/bootmem.c          |    6 ++++++
 3 files changed, 8 insertions(+), 24 deletions(-)

diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c
index 5cb3f0f..804bbe9 100644
--- a/arch/x86/mm/init_32.c
+++ b/arch/x86/mm/init_32.c
@@ -1069,9 +1069,3 @@ void mark_rodata_ro(void)
 #endif
 }
 #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 e9b040e..5ba6b0e 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -798,13 +798,10 @@ void mark_rodata_ro(void)
 
 #endif
 
+#ifndef CONFIG_NO_BOOTMEM
 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 +817,7 @@ 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;
@@ -843,6 +826,7 @@ int __init reserve_bootmem_generic(unsigned long phys, unsigned long len,
 
 	return 0;
 }
+#endif
 
 int kern_addr_valid(unsigned long addr)
 {
diff --git a/mm/bootmem.c b/mm/bootmem.c
index 9b13446..fadbc3b 100644
--- a/mm/bootmem.c
+++ b/mm/bootmem.c
@@ -512,6 +512,12 @@ 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)
 {
-- 
1.6.4.2

[PATCH 10/24] lmb: Add lmb_to_bootmem()

[Yinghai Lu]

lmb_to_bootmem() will reserve lmb.reserved.region in bootmem

We can use it to with all arches that support lmb.

Signed-off-by: Yinghai Lu <yinghai@kernel.org>
---
 include/linux/lmb.h |    2 ++
 mm/lmb.c            |   32 ++++++++++++++++++++++++++++++++
 2 files changed, 34 insertions(+), 0 deletions(-)

diff --git a/include/linux/lmb.h b/include/linux/lmb.h
index 7301072..f5071e1 100644
--- a/include/linux/lmb.h
+++ b/include/linux/lmb.h
@@ -92,6 +92,8 @@ u64 find_lmb_area(u64 start, u64 end, u64 size, u64 align);
 u64 find_lmb_area_size(u64 start, u64 *sizep, u64 align);
 u64 get_max_mapped(void);
 
+void lmb_to_bootmem(u64 start, u64 end);
+
 #include <asm/lmb.h>
 
 #endif /* __KERNEL__ */
diff --git a/mm/lmb.c b/mm/lmb.c
index a91f48d..7a34f4a 100644
--- a/mm/lmb.c
+++ b/mm/lmb.c
@@ -640,6 +640,38 @@ void __init free_lmb(u64 start, u64 end)
 	lmb_free(start, end - start);
 }
 
+#ifndef CONFIG_NO_BOOTMEM
+void __init lmb_to_bootmem(u64 start, u64 end)
+{
+	int i, count;
+	u64 final_start, final_end;
+
+	/* Take out region array itself */
+	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;
+	pr_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];
+		pr_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) {
+			pr_cont("\n");
+			continue;
+		}
+		pr_cont(" ==> [%010llx - %010llx]\n", final_start, final_end);
+		reserve_bootmem_generic(final_start, final_end - final_start, BOOTMEM_DEFAULT);
+	}
+	/* Clear them to avoid misusing ? */
+	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;
-- 
1.6.4.2

[PATCH 11/24] lmb: Add get_free_all_memory_range()

[Yinghai Lu]

get_free_all_memory_range is for CONFIG_NO_BOOTMEM, and will be called by
free_all_memory_core_early().

It will use early_node_map aka active ranges subtract lmb.reserved to
get all free range.

-v2: Update with Jan Beulich's patch "fix allocation done in get_free_all_memory_range()", that one is for early_res.

Signed-off-by: Yinghai Lu <yinghai@kernel.org>
Cc: Jan Beulich <jbeulich@novell.com>
---
 include/linux/lmb.h |    2 +
 mm/lmb.c            |   86 ++++++++++++++++++++++++++++++++++++++++++++++++++-
 2 files changed, 87 insertions(+), 1 deletions(-)

diff --git a/include/linux/lmb.h b/include/linux/lmb.h
index f5071e1..9e2dcf5 100644
--- a/include/linux/lmb.h
+++ b/include/linux/lmb.h
@@ -93,6 +93,8 @@ u64 find_lmb_area_size(u64 start, u64 *sizep, u64 align);
 u64 get_max_mapped(void);
 
 void lmb_to_bootmem(u64 start, u64 end);
+struct range;
+int get_free_all_memory_range(struct range **rangep, int nodeid);
 
 #include <asm/lmb.h>
 
diff --git a/mm/lmb.c b/mm/lmb.c
index 7a34f4a..f687a42 100644
--- a/mm/lmb.c
+++ b/mm/lmb.c
@@ -640,7 +640,91 @@ void __init free_lmb(u64 start, u64 end)
 	lmb_free(start, end - start);
 }
 
-#ifndef CONFIG_NO_BOOTMEM
+static __init struct range *find_range_array(int count)
+{
+	u64 end, size, mem = -1ULL;
+	struct range *range;
+
+	size = sizeof(struct range) * count;
+	end = get_max_mapped();
+#ifdef MAX_DMA32_PFN
+	if (end > (MAX_DMA32_PFN << PAGE_SHIFT))
+		mem = find_lmb_area(MAX_DMA32_PFN << PAGE_SHIFT, end,
+					 size, sizeof(struct range));
+#endif
+	if (mem == -1ULL)
+		mem = find_lmb_area(0, end, size, sizeof(struct range));
+	if (mem == -1ULL)
+		panic("can not find more space for range free");
+
+	range = __va(mem);
+	memset(range, 0, size);
+
+	return range;
+}
+
+#ifdef CONFIG_NO_BOOTMEM
+static void __init subtract_lmb_reserved(struct range *range, int az)
+{
+	int i, count;
+	u64 final_start, final_end;
+
+	/* Take out region array itself at first*/
+	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;
+
+	pr_info("Subtract (%d early reservations)\n", count);
+
+	for (i = 0; i < count; i++) {
+		struct lmb_property *r = &lmb.reserved.region[i];
+		pr_info("  #%d [%010llx - %010llx]\n", i, r->base, r->base + r->size);
+		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 count;
+	struct range *range;
+	int nr_range;
+
+	count = lmb.reserved.cnt * 2;
+
+	range = find_range_array(count);
+	nr_range = 0;
+
+	/*
+	 * Use early_node_map[] and lmb.reserved.region to get range array
+	 * at first
+	 */
+	nr_range = add_from_early_node_map(range, count, nr_range, nodeid);
+#ifdef CONFIG_X86_32
+	subtract_range(range, count, max_low_pfn, -1ULL);
+#endif
+	subtract_lmb_reserved(range, count);
+	nr_range = clean_sort_range(range, count);
+
+	/* Need to clear it ? */
+	if (nodeid == MAX_NUMNODES) {
+		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 lmb_to_bootmem(u64 start, u64 end)
 {
 	int i, count;
-- 
1.6.4.2

[PATCH 12/24] lmb: Add lmb_register_active_regions() and lmb_hole_size()

[Yinghai Lu]

lmb_register_active_regions() will be used to fill early_node_map,
the result will be lmb.memory.region AND numa data

lmb_hole_size will be used to find hole size on lmb.memory.region
with specified range.

Signed-off-by: Yinghai Lu <yinghai@kernel.org>
---
 include/linux/lmb.h |    4 +++
 mm/lmb.c            |   68 +++++++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 72 insertions(+), 0 deletions(-)

diff --git a/include/linux/lmb.h b/include/linux/lmb.h
index 9e2dcf5..6568e9d 100644
--- a/include/linux/lmb.h
+++ b/include/linux/lmb.h
@@ -96,6 +96,10 @@ void lmb_to_bootmem(u64 start, u64 end);
 struct range;
 int get_free_all_memory_range(struct range **rangep, int nodeid);
 
+void lmb_register_active_regions(int nid, unsigned long start_pfn,
+					 unsigned long last_pfn);
+u64 lmb_hole_size(u64 start, u64 end);
+
 #include <asm/lmb.h>
 
 #endif /* __KERNEL__ */
diff --git a/mm/lmb.c b/mm/lmb.c
index f687a42..05d3244 100644
--- a/mm/lmb.c
+++ b/mm/lmb.c
@@ -912,3 +912,71 @@ u64 __init find_lmb_area_size(u64 start, u64 *sizep, u64 align)
 	return -1ULL;
 }
 
+/*
+ * 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);
+}
+
-- 
1.6.4.2

[PATCH 13/24] lmb: Prepare to include linux/lmb.h in core file

[Yinghai Lu]

Need to add protection in linux/lmb.h, to prepare to include it in mm/page_alloc.c
and mm/bootmem.c etc.

Signed-off-by: Yinghai Lu <yinghai@kernel.org>
---
 include/linux/lmb.h |    3 +++
 1 files changed, 3 insertions(+), 0 deletions(-)

diff --git a/include/linux/lmb.h b/include/linux/lmb.h
index 6568e9d..143f97d 100644
--- a/include/linux/lmb.h
+++ b/include/linux/lmb.h
@@ -2,6 +2,7 @@
 #define _LINUX_LMB_H
 #ifdef __KERNEL__
 
+#ifdef CONFIG_HAVE_LMB
 /*
  * Logical memory blocks.
  *
@@ -102,6 +103,8 @@ u64 lmb_hole_size(u64 start, u64 end);
 
 #include <asm/lmb.h>
 
+#endif /* CONFIG_HAVE_LMB */
+
 #endif /* __KERNEL__ */
 
 #endif /* _LINUX_LMB_H */
-- 
1.6.4.2

[PATCH 14/24] lmb: Add find_memory_core_early()

[Yinghai Lu]

According to node range in early_node_map[] with __find_lmb_area
to find free range.

Will be used by find_lmb_area_node()

find_lmb_area_node will be used to find right buffer for NODE_DATA

Signed-off-by: Yinghai Lu <yinghai@kernel.org>
---
 include/linux/mm.h |    2 ++
 mm/page_alloc.c    |   29 +++++++++++++++++++++++++++++
 2 files changed, 31 insertions(+), 0 deletions(-)

diff --git a/include/linux/mm.h b/include/linux/mm.h
index c8442b6..8070bd8 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1159,6 +1159,8 @@ 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..faae23a 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/lmb.h>
 #include <linux/compiler.h>
 #include <linux/kernel.h>
 #include <linux/kmemcheck.h>
@@ -3393,6 +3394,34 @@ void __init free_bootmem_with_active_regions(int nid,
 	}
 }
 
+#ifdef CONFIG_HAVE_LMB
+u64 __init find_memory_core_early(int nid, u64 size, u64 align,
+					u64 goal, u64 limit)
+{
+	int i;
+
+	/* Need to go over early_node_map to find out good range for node */
+	for_each_active_range_index_in_nid(i, nid) {
+		u64 addr;
+		u64 ei_start, ei_last;
+
+		ei_last = early_node_map[i].end_pfn;
+		ei_last <<= PAGE_SHIFT;
+		ei_start = early_node_map[i].start_pfn;
+		ei_start <<= PAGE_SHIFT;
+		addr = __find_lmb_area(ei_start, ei_last,
+					 goal, limit, size, align);
+
+		if (addr == -1ULL)
+			continue;
+
+		return addr;
+	}
+
+	return -1ULL;
+}
+#endif
+
 int __init add_from_early_node_map(struct range *range, int az,
 				   int nr_range, int nid)
 {
-- 
1.6.4.2

[PATCH 15/24] lmb: Add find_lmb_area_node()

[Yinghai Lu]

It can be used to find NODE_DATA for numa.

Need to make sure early_node_map[] is filled before it is called

Signed-off-by: Yinghai Lu <yinghai@kernel.org>
---
 include/linux/lmb.h |    1 +
 mm/lmb.c            |   15 +++++++++++++++
 2 files changed, 16 insertions(+), 0 deletions(-)

diff --git a/include/linux/lmb.h b/include/linux/lmb.h
index 143f97d..019520a 100644
--- a/include/linux/lmb.h
+++ b/include/linux/lmb.h
@@ -91,6 +91,7 @@ u64 __find_lmb_area(u64 ei_start, u64 ei_last, u64 start, u64 end,
 			 u64 size, u64 align);
 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);
 u64 get_max_mapped(void);
 
 void lmb_to_bootmem(u64 start, u64 end);
diff --git a/mm/lmb.c b/mm/lmb.c
index 05d3244..6f794ed 100644
--- a/mm/lmb.c
+++ b/mm/lmb.c
@@ -913,6 +913,21 @@ u64 __init find_lmb_area_size(u64 start, u64 *sizep, u64 align)
 }
 
 /*
+ * Need to call this function after lmb_register_active_regions,
+ * so early_node_map[] is filled already.
+ */
+u64 __init find_lmb_area_node(int nid, u64 start, u64 end, u64 size, u64 align)
+{
+	u64 addr;
+	addr = find_memory_core_early(nid, size, align, start, end);
+	if (addr != -1ULL)
+		return addr;
+
+	/* Fallback, should already have start end within 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.
  */
-- 
1.6.4.2

[PATCH 16/24] lmb: Add lmb_free_memory_size()

[Yinghai Lu]

It will return free memory size in specified range.

We can not use memory_size - reserved_size here, because some reserved area
may not be in the scope of lmb.memory.region.

Use lmb.memory.region subtracting lmb.reserved.region to get free range array.
then count size of all free ranges.

Signed-off-by: Yinghai Lu <yinghai@kernel.org>
---
 include/linux/lmb.h |    1 +
 mm/lmb.c            |   51 +++++++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 52 insertions(+), 0 deletions(-)

diff --git a/include/linux/lmb.h b/include/linux/lmb.h
index 019520a..51a8653 100644
--- a/include/linux/lmb.h
+++ b/include/linux/lmb.h
@@ -101,6 +101,7 @@ int get_free_all_memory_range(struct range **rangep, int nodeid);
 void lmb_register_active_regions(int nid, unsigned long start_pfn,
 					 unsigned long last_pfn);
 u64 lmb_hole_size(u64 start, u64 end);
+u64 lmb_free_memory_size(u64 addr, u64 limit);
 
 #include <asm/lmb.h>
 
diff --git a/mm/lmb.c b/mm/lmb.c
index 6f794ed..a98ab51 100644
--- a/mm/lmb.c
+++ b/mm/lmb.c
@@ -756,6 +756,57 @@ void __init lmb_to_bootmem(u64 start, u64 end)
 }
 #endif
 
+u64 __init lmb_free_memory_size(u64 addr, u64 limit)
+{
+	int i, count;
+	struct range *range;
+	int nr_range;
+	u64 final_start, final_end;
+	u64 free_size;
+
+	count = lmb.reserved.cnt * 2;
+
+	range = find_range_array(count);
+	nr_range = 0;
+
+	addr = PFN_UP(addr);
+	limit = PFN_DOWN(limit);
+
+	for (i = 0; i < lmb.memory.cnt; i++) {
+		struct lmb_property *r = &lmb.memory.region[i];
+
+		final_start = PFN_UP(r->base);
+		final_end = PFN_DOWN(r->base + r->size);
+		if (final_start >= final_end)
+			continue;
+		if (final_start >= limit || final_end <= addr)
+			continue;
+
+		nr_range = add_range(range, count, nr_range, final_start, final_end);
+	}
+	subtract_range(range, count, 0, addr);
+	subtract_range(range, count, limit, -1ULL);
+	for (i = 0; i < lmb.reserved.cnt; i++) {
+		struct lmb_property *r = &lmb.reserved.region[i];
+
+		final_start = PFN_DOWN(r->base);
+		final_end = PFN_UP(r->base + r->size);
+		if (final_start >= final_end)
+			continue;
+		if (final_start >= limit || final_end <= addr)
+			continue;
+
+		subtract_range(range, count, final_start, final_end);
+	}
+	nr_range = clean_sort_range(range, count);
+
+	free_size = 0;
+	for (i = 0; i < nr_range; i++)
+		free_size += range[i].end - range[i].start;
+
+	return free_size << PAGE_SHIFT;
+}
+
 static int __init find_overlapped_early(u64 start, u64 end)
 {
 	int i;
-- 
1.6.4.2

[PATCH 17/24] lmb: Add lmb_memory_size()

[Yinghai Lu]

It will return memory size in specified range according to lmb.memory.region

Try to share some code with lmb_free_memory_size() by passing get_free to
__lmb_memory_size().

Signed-off-by: Yinghai Lu <yinghai@kernel.org>
---
 include/linux/lmb.h |    1 +
 mm/lmb.c            |   18 +++++++++++++++++-
 2 files changed, 18 insertions(+), 1 deletions(-)

diff --git a/include/linux/lmb.h b/include/linux/lmb.h
index 51a8653..285f287 100644
--- a/include/linux/lmb.h
+++ b/include/linux/lmb.h
@@ -102,6 +102,7 @@ void lmb_register_active_regions(int nid, unsigned long start_pfn,
 					 unsigned long last_pfn);
 u64 lmb_hole_size(u64 start, u64 end);
 u64 lmb_free_memory_size(u64 addr, u64 limit);
+u64 lmb_memory_size(u64 addr, u64 limit);
 
 #include <asm/lmb.h>
 
diff --git a/mm/lmb.c b/mm/lmb.c
index a98ab51..0dab3b6 100644
--- a/mm/lmb.c
+++ b/mm/lmb.c
@@ -756,7 +756,7 @@ void __init lmb_to_bootmem(u64 start, u64 end)
 }
 #endif
 
-u64 __init lmb_free_memory_size(u64 addr, u64 limit)
+static u64 __init __lmb_memory_size(u64 addr, u64 limit, bool get_free)
 {
 	int i, count;
 	struct range *range;
@@ -786,6 +786,10 @@ u64 __init lmb_free_memory_size(u64 addr, u64 limit)
 	}
 	subtract_range(range, count, 0, addr);
 	subtract_range(range, count, limit, -1ULL);
+
+	/* Subtract lmb.reserved.region in range ? */
+	if (!get_free)
+		goto sort_and_count_them;
 	for (i = 0; i < lmb.reserved.cnt; i++) {
 		struct lmb_property *r = &lmb.reserved.region[i];
 
@@ -798,6 +802,8 @@ u64 __init lmb_free_memory_size(u64 addr, u64 limit)
 
 		subtract_range(range, count, final_start, final_end);
 	}
+
+sort_and_count_them:
 	nr_range = clean_sort_range(range, count);
 
 	free_size = 0;
@@ -807,6 +813,16 @@ u64 __init lmb_free_memory_size(u64 addr, u64 limit)
 	return free_size << PAGE_SHIFT;
 }
 
+u64 __init lmb_free_memory_size(u64 addr, u64 limit)
+{
+	return __lmb_memory_size(addr, limit, true);
+}
+
+u64 __init lmb_memory_size(u64 addr, u64 limit)
+{
+	return __lmb_memory_size(addr, limit, false);
+}
+
 static int __init find_overlapped_early(u64 start, u64 end)
 {
 	int i;
-- 
1.6.4.2

[PATCH 18/24] lmb: Add reserve_lmb_overlap_ok()

[Yinghai Lu]

Some areas from firmware could be reserved several times from different callers.

If these area are overlapped, We may have overlapped entries in lmb.reserved.

Try to free the area at first, before rerserve them again.

Signed-off-by: Yinghai Lu <yinghai@kernel.org>
---
 include/linux/lmb.h |    1 +
 mm/lmb.c            |   27 +++++++++++++++++++++++++--
 2 files changed, 26 insertions(+), 2 deletions(-)

diff --git a/include/linux/lmb.h b/include/linux/lmb.h
index 285f287..1e11fe0 100644
--- a/include/linux/lmb.h
+++ b/include/linux/lmb.h
@@ -85,6 +85,7 @@ lmb_end_pfn(struct lmb_region *type, unsigned long region_nr)
 }
 
 void reserve_lmb(u64 start, u64 end, char *name);
+void reserve_lmb_overlap_ok(u64 start, u64 end, char *name);
 void free_lmb(u64 start, u64 end);
 void add_lmb_memory(u64 start, u64 end);
 u64 __find_lmb_area(u64 ei_start, u64 ei_last, u64 start, u64 end,
diff --git a/mm/lmb.c b/mm/lmb.c
index 0dab3b6..20ab927 100644
--- a/mm/lmb.c
+++ b/mm/lmb.c
@@ -615,6 +615,12 @@ void __init add_lmb_memory(u64 start, u64 end)
 	lmb_add(start, end - start);
 }
 
+static void __init __reserve_lmb(u64 start, u64 end, char *name)
+{
+	__check_and_double_region_array(&lmb.reserved, &lmb_reserved_region[0], start, end);
+	lmb_reserve(start, end - start);
+}
+
 void __init reserve_lmb(u64 start, u64 end, char *name)
 {
 	if (start == end)
@@ -623,8 +629,25 @@ void __init reserve_lmb(u64 start, u64 end, char *name)
 	if (WARN_ONCE(start > end, "reserve_lmb: wrong range [%#llx, %#llx]\n", start, end))
 		return;
 
-	__check_and_double_region_array(&lmb.reserved, &lmb_reserved_region[0], start, end);
-	lmb_reserve(start, end - start);
+	__reserve_lmb(start, end, name);
+}
+
+/*
+ * Could be used to avoid having overlap entries in lmb.reserved.region.
+ *  Don't need to use it with area that is from find_lmb_area()
+ *  Only use it for the area that fw hidden area.
+ */
+void __init reserve_lmb_overlap_ok(u64 start, u64 end, char *name)
+{
+	if (start == end)
+		return;
+
+	if (WARN_ONCE(start > end, "reserve_lmb_overlap_ok: wrong range [%#llx, %#llx]\n", start, end))
+		return;
+
+	/* Free that region at first */
+	lmb_free(start, end - start);
+	__reserve_lmb(start, end, name);
 }
 
 void __init free_lmb(u64 start, u64 end)
-- 
1.6.4.2

[PATCH 19/24] x86: Add sanitize_e820_map()

[Yinghai Lu]

So We don't need to take e820.map with it.

Also change e820_saved to initdata to get some bytes memory back.

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 ec8a52d..0457c49 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 740b440..0eb9830 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");
@@ -1028,7 +1033,7 @@ 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;
 
@@ -1158,7 +1163,7 @@ 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;
@@ -1185,12 +1190,17 @@ 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 2a1b9d4..d83fb6e 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -467,8 +467,8 @@ 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");
 }
@@ -620,7 +620,7 @@ 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;
 }
@@ -689,7 +689,7 @@ 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();
 }
 
 /*
@@ -860,7 +860,7 @@ 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 20/24] x86: Use lmb to replace early_res

[Yinghai Lu]

1. replace find_e820_area with find_lmb_area
2. replace reserve_early with reserve_lmb
3. replace free_early with free_lmb.
4. NO_BOOTMEM will switch to use lmb too.
5. use _e820, _early wrap in the patch, in following patch, will
   replace them all
6. because free_lmb support partial free, we can remove some special care
7. Need to make sure that find_lmb_area() is called after fill_lmb_memory()
   so adjust some calling later in setup.c::setup_arch()
   -- corruption_check and mptable_update

Suggested-by: David S. Miller <davem@davemloft.net>
Suggested-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Suggested-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Yinghai Lu <yinghai@kernel.org>

---
 arch/x86/Kconfig               |    9 +--
 arch/x86/include/asm/e820.h    |   15 +++--
 arch/x86/include/asm/lmb.h     |    8 ++
 arch/x86/kernel/check.c        |   14 ++--
 arch/x86/kernel/e820.c         |  139 +++++++++++-----------------------------
 arch/x86/kernel/head.c         |    3 +-
 arch/x86/kernel/head32.c       |    6 +-
 arch/x86/kernel/head64.c       |    3 +
 arch/x86/kernel/mpparse.c      |    5 +-
 arch/x86/kernel/setup.c        |   10 ++-
 arch/x86/kernel/setup_percpu.c |    6 --
 arch/x86/mm/numa_64.c          |    5 +-
 kernel/Makefile                |    1 -
 mm/bootmem.c                   |    1 +
 mm/page_alloc.c                |   35 ++--------
 mm/sparse-vmemmap.c            |   11 ---
 16 files changed, 97 insertions(+), 174 deletions(-)
 create mode 100644 arch/x86/include/asm/lmb.h

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 6a80bce..3117de5 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
@@ -192,9 +193,6 @@ config ARCH_SUPPORTS_OPTIMIZED_INLINING
 config ARCH_SUPPORTS_DEBUG_PAGEALLOC
 	def_bool y
 
-config HAVE_EARLY_RES
-	def_bool y
-
 config HAVE_INTEL_TXT
 	def_bool y
 	depends on EXPERIMENTAL && DMAR && ACPI
@@ -589,14 +587,13 @@ config NO_BOOTMEM
 	default y
 	bool "Disable Bootmem code"
 	---help---
-	  Use early_res directly instead of bootmem before slab is ready.
+	  Use lmb directly instead of bootmem before slab is ready.
 		- allocator (buddy) [generic]
 		- early allocator (bootmem) [generic]
-		- very early allocator (reserve_early*()) [x86]
+		- very early allocator (lmb) [some generic]
 		- very very early allocator (early brk model) [x86]
 	  So reduce one layer between early allocator to final allocator
 
-
 config MEMTEST
 	bool "Memtest"
 	---help---
diff --git a/arch/x86/include/asm/e820.h b/arch/x86/include/asm/e820.h
index 0457c49..396c849 100644
--- a/arch/x86/include/asm/e820.h
+++ b/arch/x86/include/asm/e820.h
@@ -116,24 +116,27 @@ 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);
 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);
+
+extern u64 early_reserve_e820(u64 startt, u64 sizet, u64 align);
+
+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);
 extern void setup_memory_map(void);
 extern char *default_machine_specific_memory_setup(void);
 
+void reserve_early(u64 start, u64 end, char *name);
+void free_early(u64 start, u64 end);
+
 /*
  * Returns true iff the specified range [s,e) is completely contained inside
  * the ISA region.
diff --git a/arch/x86/include/asm/lmb.h b/arch/x86/include/asm/lmb.h
new file mode 100644
index 0000000..5764319
--- /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..90236af 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/lmb.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_lmb(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 0eb9830..54d478d 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>
@@ -731,30 +732,7 @@ core_initcall(e820_mark_nvs_memory);
  */
 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);
+	return find_lmb_area(start, end, size, align);
 }
 
 u64 __init get_max_mapped(void)
@@ -770,30 +748,11 @@ u64 __init get_max_mapped(void)
  */
 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;
+	return find_lmb_area_size(start, sizep, 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)
 {
@@ -802,7 +761,7 @@ 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)
@@ -819,10 +778,9 @@ 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_lmb(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;
@@ -884,52 +842,12 @@ 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);
+	lmb_register_active_regions(nid, start_pfn, last_pfn);
 }
 
 /*
@@ -939,18 +857,16 @@ void __init e820_register_active_regions(int nid, unsigned long start_pfn,
  */
 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;
+	return lmb_hole_size(start, end);
+}
 
-	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);
+void reserve_early(u64 start, u64 end, char *name)
+{
+	reserve_lmb(start, end, name);
+}
+void free_early(u64 start, u64 end)
+{
+	free_lmb(start, end);
 }
 
 static void early_panic(char *msg)
@@ -1204,3 +1120,24 @@ 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..0341b09 100644
--- a/arch/x86/kernel/head.c
+++ b/arch/x86/kernel/head.c
@@ -1,5 +1,6 @@
 #include <linux/kernel.h>
 #include <linux/init.h>
+#include <linux/lmb.h>
 
 #include <asm/setup.h>
 #include <asm/bios_ebda.h>
@@ -51,5 +52,5 @@ 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_lmb_overlap_ok(lowmem, 0x100000, "BIOS reserved");
 }
diff --git a/arch/x86/kernel/head32.c b/arch/x86/kernel/head32.c
index fe3d953..5225a00 100644
--- a/arch/x86/kernel/head32.c
+++ b/arch/x86/kernel/head32.c
@@ -7,6 +7,7 @@
 
 #include <linux/init.h>
 #include <linux/start_kernel.h>
+#include <linux/lmb.h>
 
 #include <asm/setup.h>
 #include <asm/sections.h>
@@ -29,14 +30,15 @@ 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_lmb(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 fafba92..30db129 100644
--- a/arch/x86/kernel/head64.c
+++ b/arch/x86/kernel/head64.c
@@ -12,6 +12,7 @@
 #include <linux/percpu.h>
 #include <linux/start_kernel.h>
 #include <linux/io.h>
+#include <linux/lmb.h>
 
 #include <asm/processor.h>
 #include <asm/proto.h>
@@ -96,6 +97,8 @@ 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/mpparse.c b/arch/x86/kernel/mpparse.c
index a2c1edd..5779c27 100644
--- a/arch/x86/kernel/mpparse.c
+++ b/arch/x86/kernel/mpparse.c
@@ -11,6 +11,7 @@
 #include <linux/init.h>
 #include <linux/delay.h>
 #include <linux/bootmem.h>
+#include <linux/lmb.h>
 #include <linux/kernel_stat.h>
 #include <linux/mc146818rtc.h>
 #include <linux/bitops.h>
@@ -664,7 +665,7 @@ static void __init smp_reserve_memory(struct mpf_intel *mpf)
 {
 	unsigned long size = get_mpc_size(mpf->physptr);
 
-	reserve_early(mpf->physptr, mpf->physptr+size, "MP-table mpc");
+	reserve_lmb_overlap_ok(mpf->physptr, mpf->physptr+size, "MP-table mpc");
 }
 
 static int __init smp_scan_config(unsigned long base, unsigned long length)
@@ -693,7 +694,7 @@ static int __init smp_scan_config(unsigned long base, unsigned long length)
 			       mpf, (u64)virt_to_phys(mpf));
 
 			mem = virt_to_phys(mpf);
-			reserve_early(mem, mem + sizeof(*mpf), "MP-table mpf");
+			reserve_lmb_overlap_ok(mem, mem + sizeof(*mpf), "MP-table mpf");
 			if (mpf->physptr)
 				smp_reserve_memory(mpf);
 
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index d83fb6e..9598806 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -31,6 +31,7 @@
 #include <linux/apm_bios.h>
 #include <linux/initrd.h>
 #include <linux/bootmem.h>
+#include <linux/lmb.h>
 #include <linux/seq_file.h>
 #include <linux/console.h>
 #include <linux/mca.h>
@@ -874,8 +875,6 @@ 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))
@@ -900,6 +899,11 @@ 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
@@ -976,7 +980,7 @@ 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_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/numa_64.c b/arch/x86/mm/numa_64.c
index 8948f47..fc9a403 100644
--- a/arch/x86/mm/numa_64.c
+++ b/arch/x86/mm/numa_64.c
@@ -7,6 +7,7 @@
 #include <linux/string.h>
 #include <linux/init.h>
 #include <linux/bootmem.h>
+#include <linux/lmb.h>
 #include <linux/mmzone.h>
 #include <linux/ctype.h>
 #include <linux/module.h>
@@ -174,7 +175,7 @@ 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_lmb_area_node(nodeid, start, end, size, align);
 	if (mem != -1L)
 		return __va(mem);
 
@@ -184,7 +185,7 @@ 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_lmb_area_node(nodeid, start, end, size, align);
 	if (mem != -1L)
 		return __va(mem);
 
diff --git a/kernel/Makefile b/kernel/Makefile
index d5c3006..754bf79 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -11,7 +11,6 @@ obj-y     = sched.o fork.o exec_domain.o panic.o printk.o \
 	    hrtimer.o rwsem.o nsproxy.o srcu.o semaphore.o \
 	    notifier.o ksysfs.o pm_qos_params.o sched_clock.o cred.o \
 	    async.o range.o
-obj-$(CONFIG_HAVE_EARLY_RES) += early_res.o
 obj-y += groups.o
 
 ifdef CONFIG_FUNCTION_TRACER
diff --git a/mm/bootmem.c b/mm/bootmem.c
index fadbc3b..81f9350 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/lmb.h>
 
 #include <asm/bug.h>
 #include <asm/io.h>
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index faae23a..42bc09e 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -3441,38 +3441,19 @@ int __init add_from_early_node_map(struct range *range, int az,
 void * __init __alloc_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) {
-		u64 addr;
-		u64 ei_start, ei_last;
-
-		ei_last = early_node_map[i].end_pfn;
-		ei_last <<= PAGE_SHIFT;
-		ei_start = early_node_map[i].start_pfn;
-		ei_start <<= PAGE_SHIFT;
-		addr = find_early_area(ei_start, ei_last,
-					 goal, limit, size, align);
-
-		if (addr == -1ULL)
-			continue;
+	u64 addr;
 
-#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);
-#endif
+	addr = find_memory_core_early(nid, size, align, goal, limit);
 
-		ptr = phys_to_virt(addr);
-		memset(ptr, 0, size);
-		reserve_early_without_check(addr, addr + size, "BOOTMEM");
-		return ptr;
-	}
+	if (addr == -1ULL)
+		return NULL;
 
-	return NULL;
+	ptr = phys_to_virt(addr);
+	memset(ptr, 0, size);
+	reserve_lmb(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 21/24] x86: Replace e820_/_early string with lmb_

[Yinghai Lu]

1.include linux/lmb.h directly. so later could reduce e820.h reference.
2 this patch is done by sed scripts mainly

Signed-off-by: Yinghai Lu <yinghai@kernel.org>
---
 arch/x86/include/asm/efi.h      |    2 +-
 arch/x86/kernel/acpi/sleep.c    |    5 +++--
 arch/x86/kernel/apic/numaq_32.c |    3 ++-
 arch/x86/kernel/efi.c           |    5 +++--
 arch/x86/kernel/head32.c        |    4 ++--
 arch/x86/kernel/head64.c        |    4 ++--
 arch/x86/kernel/setup.c         |   26 +++++++++++++-------------
 arch/x86/kernel/trampoline.c    |    6 +++---
 arch/x86/mm/init.c              |    5 +++--
 arch/x86/mm/init_32.c           |   10 ++++++----
 arch/x86/mm/init_64.c           |    9 +++++----
 arch/x86/mm/k8topology_64.c     |    4 +++-
 arch/x86/mm/memtest.c           |    7 +++----
 arch/x86/mm/numa_32.c           |   17 +++++++++--------
 arch/x86/mm/numa_64.c           |   32 ++++++++++++++++----------------
 arch/x86/mm/srat_32.c           |    3 ++-
 arch/x86/mm/srat_64.c           |    9 +++++----
 arch/x86/xen/mmu.c              |    5 +++--
 arch/x86/xen/setup.c            |    3 ++-
 mm/bootmem.c                    |    4 ++--
 20 files changed, 88 insertions(+), 75 deletions(-)

diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h
index 8406ed7..f756536 100644
--- a/arch/x86/include/asm/efi.h
+++ b/arch/x86/include/asm/efi.h
@@ -90,7 +90,7 @@ extern void __iomem *efi_ioremap(unsigned long addr, unsigned long size,
 #endif /* CONFIG_X86_32 */
 
 extern int add_efi_memmap;
-extern void efi_reserve_early(void);
+extern void efi_reserve_lmb(void);
 extern void efi_call_phys_prelog(void);
 extern void efi_call_phys_epilog(void);
 
diff --git a/arch/x86/kernel/acpi/sleep.c b/arch/x86/kernel/acpi/sleep.c
index f996103..0cabfaa 100644
--- a/arch/x86/kernel/acpi/sleep.c
+++ b/arch/x86/kernel/acpi/sleep.c
@@ -7,6 +7,7 @@
 
 #include <linux/acpi.h>
 #include <linux/bootmem.h>
+#include <linux/lmb.h>
 #include <linux/dmi.h>
 #include <linux/cpumask.h>
 #include <asm/segment.h>
@@ -133,7 +134,7 @@ 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");
@@ -141,7 +142,7 @@ void __init acpi_reserve_wakeup_memory(void)
 	}
 	acpi_realmode = (unsigned long) phys_to_virt(mem);
 	acpi_wakeup_address = mem;
-	reserve_early(mem, mem + WAKEUP_SIZE, "ACPI WAKEUP");
+	reserve_lmb(mem, mem + WAKEUP_SIZE, "ACPI WAKEUP");
 }
 
 
diff --git a/arch/x86/kernel/apic/numaq_32.c b/arch/x86/kernel/apic/numaq_32.c
index 3e28401..c71e494 100644
--- a/arch/x86/kernel/apic/numaq_32.c
+++ b/arch/x86/kernel/apic/numaq_32.c
@@ -26,6 +26,7 @@
 #include <linux/nodemask.h>
 #include <linux/topology.h>
 #include <linux/bootmem.h>
+#include <linux/lmb.h>
 #include <linux/threads.h>
 #include <linux/cpumask.h>
 #include <linux/kernel.h>
@@ -88,7 +89,7 @@ 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/efi.c b/arch/x86/kernel/efi.c
index 299f03f..35038a7 100644
--- a/arch/x86/kernel/efi.c
+++ b/arch/x86/kernel/efi.c
@@ -30,6 +30,7 @@
 #include <linux/init.h>
 #include <linux/efi.h>
 #include <linux/bootmem.h>
+#include <linux/lmb.h>
 #include <linux/spinlock.h>
 #include <linux/uaccess.h>
 #include <linux/time.h>
@@ -275,7 +276,7 @@ static void __init do_add_efi_memmap(void)
 	sanitize_e820_map();
 }
 
-void __init efi_reserve_early(void)
+void __init efi_reserve_lmb(void)
 {
 	unsigned long pmap;
 
@@ -290,7 +291,7 @@ void __init efi_reserve_early(void)
 		boot_params.efi_info.efi_memdesc_size;
 	memmap.desc_version = boot_params.efi_info.efi_memdesc_version;
 	memmap.desc_size = boot_params.efi_info.efi_memdesc_size;
-	reserve_early(pmap, pmap + memmap.nr_map * memmap.desc_size,
+	reserve_lmb(pmap, pmap + memmap.nr_map * memmap.desc_size,
 		      "EFI memmap");
 }
 
diff --git a/arch/x86/kernel/head32.c b/arch/x86/kernel/head32.c
index 5225a00..62e30c8 100644
--- a/arch/x86/kernel/head32.c
+++ b/arch/x86/kernel/head32.c
@@ -41,7 +41,7 @@ void __init i386_start_kernel(void)
 	reserve_lmb(PAGE_SIZE, PAGE_SIZE + PAGE_SIZE, "EX TRAMPOLINE");
 #endif
 
-	reserve_early(__pa_symbol(&_text), __pa_symbol(&__bss_stop), "TEXT DATA BSS");
+	reserve_lmb(__pa_symbol(&_text), __pa_symbol(&__bss_stop), "TEXT DATA BSS");
 
 #ifdef CONFIG_BLK_DEV_INITRD
 	/* Reserve INITRD */
@@ -50,7 +50,7 @@ void __init i386_start_kernel(void)
 		u64 ramdisk_size  = boot_params.hdr.ramdisk_size;
 		u64 ramdisk_end   = ramdisk_image + ramdisk_size;
 		ramdisk_end = PFN_UP(ramdisk_end) << PAGE_SHIFT;
-		reserve_early(ramdisk_image, ramdisk_end, "RAMDISK");
+		reserve_lmb(ramdisk_image, ramdisk_end, "RAMDISK");
 	}
 #endif
 
diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c
index 30db129..1dcae81 100644
--- a/arch/x86/kernel/head64.c
+++ b/arch/x86/kernel/head64.c
@@ -101,7 +101,7 @@ void __init x86_64_start_reservations(char *real_mode_data)
 
 	copy_bootdata(__va(real_mode_data));
 
-	reserve_early(__pa_symbol(&_text), __pa_symbol(&__bss_stop), "TEXT DATA BSS");
+	reserve_lmb(__pa_symbol(&_text), __pa_symbol(&__bss_stop), "TEXT DATA BSS");
 
 #ifdef CONFIG_BLK_DEV_INITRD
 	/* Reserve INITRD */
@@ -110,7 +110,7 @@ void __init x86_64_start_reservations(char *real_mode_data)
 		unsigned long ramdisk_size  = boot_params.hdr.ramdisk_size;
 		unsigned long ramdisk_end   = ramdisk_image + ramdisk_size;
 		ramdisk_end = PFN_UP(ramdisk_end) << PAGE_SHIFT;
-		reserve_early(ramdisk_image, ramdisk_end, "RAMDISK");
+		reserve_lmb(ramdisk_image, ramdisk_end, "RAMDISK");
 	}
 #endif
 
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 9598806..f0a32a4 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -303,7 +303,7 @@ static inline void init_gbpages(void)
 static void __init reserve_brk(void)
 {
 	if (_brk_end > _brk_start)
-		reserve_early(__pa(_brk_start), __pa(_brk_end), "BRK");
+		reserve_lmb(__pa(_brk_start), __pa(_brk_end), "BRK");
 
 	/* Mark brk area as locked down and no longer taking any
 	   new allocations */
@@ -329,7 +329,7 @@ static void __init relocate_initrd(void)
 	size_aligned = ramdisk_end - ramdisk_image;
 
 	/* We need to move the initrd down into lowmem */
-	ramdisk_here = find_e820_area(0, end_of_lowmem, size_aligned,
+	ramdisk_here = find_lmb_area(0, end_of_lowmem, size_aligned,
 					 PAGE_SIZE);
 
 	if (ramdisk_here == -1ULL)
@@ -338,17 +338,17 @@ static void __init relocate_initrd(void)
 
 	/* Note: this includes all the lowmem currently occupied by
 	   the initrd, we rely on that fact to keep the data intact. */
-	reserve_early(ramdisk_here, ramdisk_here + size_aligned,
+	reserve_lmb(ramdisk_here, ramdisk_here + size_aligned,
 			 "NEW RAMDISK");
 	initrd_start = ramdisk_here + PAGE_OFFSET;
 	initrd_end   = initrd_start + ramdisk_size;
 	printk(KERN_INFO "Allocated new RAMDISK: %08llx - %08llx\n",
 			 ramdisk_here, ramdisk_here + size_aligned);
 
+	image = ramdisk_image;
 	q = (char *)initrd_start;
 
 	/* Copy any lowmem portion of the initrd */
-	image = ramdisk_image;
 	if (image < end_of_lowmem) {
 		clen = end_of_lowmem - image;
 		p = (char *)__va(image);
@@ -395,7 +395,7 @@ static void __init reserve_initrd(void)
 	initrd_start = 0;
 
 	if (ramdisk_size >= (end_of_lowmem>>1)) {
-		free_early(ramdisk_image, ramdisk_end);
+		free_lmb(ramdisk_image, ramdisk_end);
 		printk(KERN_ERR "initrd too large to handle, "
 		       "disabling initrd\n");
 		return;
@@ -418,7 +418,7 @@ static void __init reserve_initrd(void)
 
 	relocate_initrd();
 
-	free_early(ramdisk_image, ramdisk_end);
+	free_lmb(ramdisk_image, ramdisk_end);
 }
 #else
 static void __init reserve_initrd(void)
@@ -474,7 +474,7 @@ static void __init e820_reserve_setup_data(void)
 	e820_print_map("reserve setup_data");
 }
 
-static void __init reserve_early_setup_data(void)
+static void __init reserve_lmb_setup_data(void)
 {
 	struct setup_data *data;
 	u64 pa_data;
@@ -486,7 +486,7 @@ static void __init reserve_early_setup_data(void)
 	while (pa_data) {
 		data = early_memremap(pa_data, sizeof(*data));
 		sprintf(buf, "setup data %x", data->type);
-		reserve_early(pa_data, pa_data+sizeof(*data)+data->len, buf);
+		reserve_lmb(pa_data, pa_data+sizeof(*data)+data->len, buf);
 		pa_data = data->next;
 		early_iounmap(data, sizeof(*data));
 	}
@@ -524,7 +524,7 @@ 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");
@@ -533,14 +533,14 @@ 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");
 			return;
 		}
 	}
-	reserve_early(crash_base, crash_base + crash_size, "CRASH KERNEL");
+	reserve_lmb(crash_base, crash_base + crash_size, "CRASH KERNEL");
 
 	printk(KERN_INFO "Reserving %ldMB of memory at %ldMB "
 			"for crashkernel (System RAM: %ldMB)\n",
@@ -760,7 +760,7 @@ void __init setup_arch(char **cmdline_p)
 #endif
 	 4)) {
 		efi_enabled = 1;
-		efi_reserve_early();
+		efi_reserve_lmb();
 	}
 #endif
 
@@ -820,7 +820,7 @@ void __init setup_arch(char **cmdline_p)
 	vmi_activate();
 
 	/* after early param, so could get panic from serial */
-	reserve_early_setup_data();
+	reserve_lmb_setup_data();
 
 	if (acpi_mps_check()) {
 #ifdef CONFIG_X86_LOCAL_APIC
diff --git a/arch/x86/kernel/trampoline.c b/arch/x86/kernel/trampoline.c
index c652ef6..4a634f6 100644
--- a/arch/x86/kernel/trampoline.c
+++ b/arch/x86/kernel/trampoline.c
@@ -1,7 +1,7 @@
 #include <linux/io.h>
+#include <linux/lmb.h>
 
 #include <asm/trampoline.h>
-#include <asm/e820.h>
 
 #if defined(CONFIG_X86_64) && defined(CONFIG_ACPI_SLEEP)
 #define __trampinit
@@ -19,12 +19,12 @@ 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");
 
 	trampoline_base = __va(mem);
-	reserve_early(mem, mem + TRAMPOLINE_SIZE, "TRAMPOLINE");
+	reserve_lmb(mem, mem + TRAMPOLINE_SIZE, "TRAMPOLINE");
 }
 
 /*
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index 727d6b0..4ba3753 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -1,6 +1,7 @@
 #include <linux/initrd.h>
 #include <linux/ioport.h>
 #include <linux/swap.h>
+#include <linux/lmb.h>
 
 #include <asm/cacheflush.h>
 #include <asm/e820.h>
@@ -74,7 +75,7 @@ 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");
@@ -298,7 +299,7 @@ unsigned long __init_refok init_memory_mapping(unsigned long start,
 	__flush_tlb_all();
 
 	if (!after_bootmem && e820_table_end > e820_table_start)
-		reserve_early(e820_table_start << PAGE_SHIFT,
+		reserve_lmb(e820_table_start << PAGE_SHIFT,
 				 e820_table_end << PAGE_SHIFT, "PGTABLE");
 
 	if (!after_bootmem)
diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c
index 804bbe9..26b9ceb 100644
--- a/arch/x86/mm/init_32.c
+++ b/arch/x86/mm/init_32.c
@@ -25,6 +25,7 @@
 #include <linux/pfn.h>
 #include <linux/poison.h>
 #include <linux/bootmem.h>
+#include <linux/lmb.h>
 #include <linux/slab.h>
 #include <linux/proc_fs.h>
 #include <linux/memory_hotplug.h>
@@ -712,14 +713,14 @@ 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;
@@ -781,11 +782,11 @@ 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);
-	reserve_early(bootmap, bootmap + bootmap_size, "BOOTMAP");
+	reserve_lmb(bootmap, bootmap + bootmap_size, "BOOTMAP");
 #endif
 
 	printk(KERN_INFO "  mapped low ram: 0 - %08lx\n",
@@ -1069,3 +1070,4 @@ void mark_rodata_ro(void)
 #endif
 }
 #endif
+
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index 5ba6b0e..b86492e 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -21,6 +21,7 @@
 #include <linux/initrd.h>
 #include <linux/pagemap.h>
 #include <linux/bootmem.h>
+#include <linux/lmb.h>
 #include <linux/proc_fs.h>
 #include <linux/pci.h>
 #include <linux/pfn.h>
@@ -576,18 +577,18 @@ 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);
-	reserve_early(bootmap, bootmap + bootmap_size, "BOOTMAP");
+	reserve_lmb(bootmap, bootmap + bootmap_size, "BOOTMAP");
 	/* don't touch min_low_pfn */
 	bootmap_size = init_bootmem_node(NODE_DATA(0), bootmap >> PAGE_SHIFT,
 					 0, end_pfn);
-	e820_register_active_regions(0, start_pfn, end_pfn);
+	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..d7d031b 100644
--- a/arch/x86/mm/k8topology_64.c
+++ b/arch/x86/mm/k8topology_64.c
@@ -11,6 +11,8 @@
 #include <linux/string.h>
 #include <linux/module.h>
 #include <linux/nodemask.h>
+#include <linux/lmb.h>
+
 #include <asm/io.h>
 #include <linux/pci_ids.h>
 #include <linux/acpi.h>
@@ -222,7 +224,7 @@ 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/memtest.c b/arch/x86/mm/memtest.c
index 18d244f..f889776 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/lmb.h>
 
 static u64 patterns[] __initdata = {
 	0,
@@ -35,7 +34,7 @@ static void __init reserve_bad_mem(u64 pattern, u64 start_bad, u64 end_bad)
 	       (unsigned long long) pattern,
 	       (unsigned long long) start_bad,
 	       (unsigned long long) end_bad);
-	reserve_early(start_bad, end_bad, "BAD RAM");
+	reserve_lmb(start_bad, end_bad, "BAD RAM");
 }
 
 static void __init memtest(u64 pattern, u64 start_phys, u64 size)
@@ -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_32.c b/arch/x86/mm/numa_32.c
index 809baaa..3434a93 100644
--- a/arch/x86/mm/numa_32.c
+++ b/arch/x86/mm/numa_32.c
@@ -24,6 +24,7 @@
 
 #include <linux/mm.h>
 #include <linux/bootmem.h>
+#include <linux/lmb.h>
 #include <linux/mmzone.h>
 #include <linux/highmem.h>
 #include <linux/initrd.h>
@@ -120,7 +121,7 @@ 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);
 
@@ -161,14 +162,14 @@ 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);
 		NODE_DATA(nid) = (pg_data_t *)(pfn_to_kaddr(pgdat_phys>>PAGE_SHIFT));
 		memset(buf, 0, sizeof(buf));
 		sprintf(buf, "NODE_DATA %d",  nid);
-		reserve_early(pgdat_phys, pgdat_phys + sizeof(pg_data_t), buf);
+		reserve_lmb(pgdat_phys, pgdat_phys + sizeof(pg_data_t), buf);
 	}
 	printk(KERN_DEBUG "allocate_pgdat: node %d NODE_DATA %08lx\n",
 		nid, (unsigned long)NODE_DATA(nid));
@@ -291,7 +292,7 @@ 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);
@@ -318,9 +319,9 @@ static __init unsigned long calculate_numa_remap_pages(void)
 		 *  but we could have some hole in high memory, and it will only
 		 *  check page_is_ram(pfn) && !page_is_reserved_early(pfn) to decide
 		 *  to use it as free.
-		 *  So reserve_early here, hope we don't run out of that array
+		 *  So reserve_lmb here, hope we don't run out of that array
 		 */
-		reserve_early(node_kva_final,
+		reserve_lmb(node_kva_final,
 			      node_kva_final+(((u64)size)<<PAGE_SHIFT),
 			      "KVA RAM");
 
@@ -367,7 +368,7 @@ 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;
@@ -382,7 +383,7 @@ void __init initmem_init(unsigned long start_pfn, unsigned long end_pfn,
 	printk(KERN_INFO "max_pfn = %lx\n", max_pfn);
 
 	/* avoid clash with initrd */
-	reserve_early(kva_start_pfn<<PAGE_SHIFT,
+	reserve_lmb(kva_start_pfn<<PAGE_SHIFT,
 		      (kva_start_pfn + kva_pages)<<PAGE_SHIFT,
 		     "KVA PG");
 #ifdef CONFIG_HIGHMEM
diff --git a/arch/x86/mm/numa_64.c b/arch/x86/mm/numa_64.c
index fc9a403..80b568d 100644
--- a/arch/x86/mm/numa_64.c
+++ b/arch/x86/mm/numa_64.c
@@ -90,7 +90,7 @@ 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
@@ -99,7 +99,7 @@ static int __init allocate_cachealigned_memnodemap(void)
 		return -1;
 	}
 	memnodemap = phys_to_virt(nodemap_addr);
-	reserve_early(nodemap_addr, nodemap_addr + nodemap_size, "MEMNODEMAP");
+	reserve_lmb(nodemap_addr, nodemap_addr + nodemap_size, "MEMNODEMAP");
 
 	printk(KERN_DEBUG "NUMA: Allocated memnodemap from %lx - %lx\n",
 	       nodemap_addr, nodemap_addr + nodemap_size);
@@ -230,7 +230,7 @@ setup_node_bootmem(int nodeid, unsigned long start, unsigned long end)
 	if (node_data[nodeid] == NULL)
 		return;
 	nodedata_phys = __pa(node_data[nodeid]);
-	reserve_early(nodedata_phys, nodedata_phys + pgdat_size, "NODE_DATA");
+	reserve_lmb(nodedata_phys, nodedata_phys + pgdat_size, "NODE_DATA");
 	printk(KERN_INFO "  NODE_DATA [%016lx - %016lx]\n", nodedata_phys,
 		nodedata_phys + pgdat_size - 1);
 	nid = phys_to_nid(nodedata_phys);
@@ -249,7 +249,7 @@ 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);
@@ -261,12 +261,12 @@ setup_node_bootmem(int nodeid, unsigned long start, unsigned long end)
 	bootmap = early_node_mem(nodeid, bootmap_start, end,
 				 bootmap_pages<<PAGE_SHIFT, PAGE_SIZE);
 	if (bootmap == NULL)  {
-		free_early(nodedata_phys, nodedata_phys + pgdat_size);
+		free_lmb(nodedata_phys, nodedata_phys + pgdat_size);
 		node_data[nodeid] = NULL;
 		return;
 	}
 	bootmap_start = __pa(bootmap);
-	reserve_early(bootmap_start, bootmap_start+(bootmap_pages<<PAGE_SHIFT),
+	reserve_lmb(bootmap_start, bootmap_start+(bootmap_pages<<PAGE_SHIFT),
 			"BOOTMAP");
 
 	bootmap_size = init_bootmem_node(NODE_DATA(nodeid),
@@ -420,7 +420,7 @@ 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.
@@ -456,7 +456,7 @@ 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;
@@ -470,7 +470,7 @@ 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;
 
 			/*
@@ -479,7 +479,7 @@ 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;
 
 			/*
@@ -507,7 +507,7 @@ 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;
@@ -536,7 +536,7 @@ 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)
@@ -569,7 +569,7 @@ 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;
 
 			/*
@@ -578,7 +578,7 @@ 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;
 
 			/*
@@ -642,7 +642,7 @@ 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);
 	}
@@ -695,7 +695,7 @@ 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..68dd606 100644
--- a/arch/x86/mm/srat_32.c
+++ b/arch/x86/mm/srat_32.c
@@ -25,6 +25,7 @@
  */
 #include <linux/mm.h>
 #include <linux/bootmem.h>
+#include <linux/lmb.h>
 #include <linux/mmzone.h>
 #include <linux/acpi.h>
 #include <linux/nodemask.h>
@@ -264,7 +265,7 @@ 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..9eca2bc 100644
--- a/arch/x86/mm/srat_64.c
+++ b/arch/x86/mm/srat_64.c
@@ -16,6 +16,7 @@
 #include <linux/module.h>
 #include <linux/topology.h>
 #include <linux/bootmem.h>
+#include <linux/lmb.h>
 #include <linux/mm.h>
 #include <asm/proto.h>
 #include <asm/numa.h>
@@ -98,7 +99,7 @@ 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)
@@ -106,7 +107,7 @@ void __init acpi_numa_slit_init(struct acpi_table_slit *slit)
 
 	acpi_slit = __va(phys);
 	memcpy(acpi_slit, slit, length);
-	reserve_early(phys, phys + length, "ACPI SLIT");
+	reserve_lmb(phys, phys + length, "ACPI SLIT");
 }
 
 /* Callback for Proximity Domain -> x2APIC mapping */
@@ -324,7 +325,7 @@ 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 +374,7 @@ 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();
diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index f9eb7de..e61658e 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -43,6 +43,7 @@
 #include <linux/debugfs.h>
 #include <linux/bug.h>
 #include <linux/module.h>
+#include <linux/lmb.h>
 
 #include <asm/pgtable.h>
 #include <asm/tlbflush.h>
@@ -1734,7 +1735,7 @@ __init pgd_t *xen_setup_kernel_pagetable(pgd_t *pgd,
 	__xen_write_cr3(true, __pa(pgd));
 	xen_mc_issue(PARAVIRT_LAZY_CPU);
 
-	reserve_early(__pa(xen_start_info->pt_base),
+	reserve_lmb(__pa(xen_start_info->pt_base),
 		      __pa(xen_start_info->pt_base +
 			   xen_start_info->nr_pt_frames * PAGE_SIZE),
 		      "XEN PAGETABLES");
@@ -1772,7 +1773,7 @@ __init pgd_t *xen_setup_kernel_pagetable(pgd_t *pgd,
 
 	pin_pagetable_pfn(MMUEXT_PIN_L3_TABLE, PFN_DOWN(__pa(swapper_pg_dir)));
 
-	reserve_early(__pa(xen_start_info->pt_base),
+	reserve_lmb(__pa(xen_start_info->pt_base),
 		      __pa(xen_start_info->pt_base +
 			   xen_start_info->nr_pt_frames * PAGE_SIZE),
 		      "XEN PAGETABLES");
diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c
index 3f2c411..e8b3ca1 100644
--- a/arch/x86/xen/setup.c
+++ b/arch/x86/xen/setup.c
@@ -8,6 +8,7 @@
 #include <linux/sched.h>
 #include <linux/mm.h>
 #include <linux/pm.h>
+#include <linux/lmb.h>
 
 #include <asm/elf.h>
 #include <asm/vdso.h>
@@ -59,7 +60,7 @@ char * __init xen_memory_setup(void)
 	 *  - xen_start_info
 	 * See comment above "struct start_info" in <xen/interface/xen.h>
 	 */
-	reserve_early(__pa(xen_start_info->mfn_list),
+	reserve_lmb(__pa(xen_start_info->mfn_list),
 		      __pa(xen_start_info->pt_base),
 			"XEN START INFO");
 
diff --git a/mm/bootmem.c b/mm/bootmem.c
index 81f9350..7e10d41 100644
--- a/mm/bootmem.c
+++ b/mm/bootmem.c
@@ -421,7 +421,7 @@ void __init free_bootmem_node(pg_data_t *pgdat, unsigned long physaddr,
 			      unsigned long size)
 {
 #ifdef CONFIG_NO_BOOTMEM
-	free_early(physaddr, physaddr + size);
+	free_lmb(physaddr, physaddr + size);
 #else
 	unsigned long start, end;
 
@@ -446,7 +446,7 @@ void __init free_bootmem_node(pg_data_t *pgdat, unsigned long physaddr,
 void __init free_bootmem(unsigned long addr, unsigned long size)
 {
 #ifdef CONFIG_NO_BOOTMEM
-	free_early(addr, addr + size);
+	free_lmb(addr, addr + size);
 #else
 	unsigned long start, end;
 
-- 
1.6.4.2

[PATCH 22/24] x86: Remove not used early_res code

[Yinghai Lu]

and some functions in e820.c that are not used anymore

Signed-off-by: Yinghai Lu <yinghai@kernel.org>
---
 arch/x86/include/asm/e820.h |   14 -
 arch/x86/kernel/e820.c      |   41 ---
 include/linux/early_res.h   |   23 --
 kernel/early_res.c          |  584 -------------------------------------------
 4 files changed, 0 insertions(+), 662 deletions(-)
 delete mode 100644 include/linux/early_res.h
 delete mode 100644 kernel/early_res.c

diff --git a/arch/x86/include/asm/e820.h b/arch/x86/include/asm/e820.h
index 396c849..de6cd06 100644
--- a/arch/x86/include/asm/e820.h
+++ b/arch/x86/include/asm/e820.h
@@ -111,32 +111,18 @@ 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);
-extern u64 early_reserve_e820(u64 startt, u64 sizet, u64 align);
-
 extern unsigned long e820_end_of_ram_pfn(void);
 extern unsigned long e820_end_of_low_ram_pfn(void);
-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);
-
 extern u64 early_reserve_e820(u64 startt, u64 sizet, u64 align);
 
 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);
 extern void setup_memory_map(void);
 extern char *default_machine_specific_memory_setup(void);
 
-void reserve_early(u64 start, u64 end, char *name);
-void free_early(u64 start, u64 end);
-
 /*
  * Returns true iff the specified range [s,e) is completely contained inside
  * the ISA region.
diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c
index 54d478d..78ba396 100644
--- a/arch/x86/kernel/e820.c
+++ b/arch/x86/kernel/e820.c
@@ -727,14 +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)
-{
-	return find_lmb_area(start, end, size, align);
-}
-
 u64 __init get_max_mapped(void)
 {
 	u64 end = max_pfn_mapped;
@@ -743,13 +735,6 @@ 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)
-{
-	return find_lmb_area_size(start, sizep, align);
-}
 
 /*
  * pre allocated 4k and reserved it in lmb and e820_saved
@@ -843,32 +828,6 @@ unsigned long __init e820_end_of_low_ram_pfn(void)
 	return e820_end_pfn(1UL<<(32 - PAGE_SHIFT), E820_RAM);
 }
 
-/* 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)
-{
-	lmb_register_active_regions(nid, start_pfn, last_pfn);
-}
-
-/*
- * 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)
-{
-	return lmb_hole_size(start, end);
-}
-
-void reserve_early(u64 start, u64 end, char *name)
-{
-	reserve_lmb(start, end, name);
-}
-void free_early(u64 start, u64 end)
-{
-	free_lmb(start, end);
-}
-
 static void early_panic(char *msg)
 {
 	early_printk(msg);
diff --git a/include/linux/early_res.h b/include/linux/early_res.h
deleted file mode 100644
index 29c09f5..0000000
--- a/include/linux/early_res.h
+++ /dev/null
@@ -1,23 +0,0 @@
-#ifndef _LINUX_EARLY_RES_H
-#define _LINUX_EARLY_RES_H
-#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 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);
-u64 get_max_mapped(void);
-#include <linux/range.h>
-int get_free_all_memory_range(struct range **rangep, int nodeid);
-
-#endif /* __KERNEL__ */
-
-#endif /* _LINUX_EARLY_RES_H */
diff --git a/kernel/early_res.c b/kernel/early_res.c
deleted file mode 100644
index 69bed5b..0000000
--- a/kernel/early_res.c
+++ /dev/null
@@ -1,584 +0,0 @@
-/*
- * early_res, could be used to replace bootmem
- */
-#include <linux/kernel.h>
-#include <linux/types.h>
-#include <linux/init.h>
-#include <linux/bootmem.h>
-#include <linux/mm.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)
-{
-	u64 start, end, size, mem;
-	struct early_res *new;
-
-	/* do we have enough slots left ? */
-	if ((max_early_res - early_res_count) > max(max_early_res/8, 2))
-		return;
-
-	/* double it */
-	mem = -1ULL;
-	size = sizeof(struct early_res) * max_early_res * 2;
-	if (early_res == early_res_x)
-		start = 0;
-	else
-		start = early_res[0].end;
-	end = ex_start;
-	if (start + size < end)
-		mem = find_fw_memmap_area(start, end, size,
-					 sizeof(struct early_res));
-	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));
-	}
-	if (mem == -1ULL)
-		panic("can not find more space for early_res 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);
-}
-
-/*
- * 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)
-{
-	if (start >= end)
-		return;
-
-	__check_and_double_early_res(start, end);
-
-	drop_overlaps_that_are_ok(start, end);
-	__reserve_early(start, end, name, 0);
-}
-
-void __init reserve_early_without_check(u64 start, u64 end, char *name)
-{
-	struct early_res *r;
-
-	if (start >= end)
-		return;
-
-	__check_and_double_early_res(start, end);
-
-	r = &early_res[early_res_count];
-
-	r->start = start;
-	r->end = end;
-	r->overlap_ok = 0;
-	if (name)
-		strncpy(r->name, name, sizeof(r->name) - 1);
-	early_res_count++;
-}
-
-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);
-		return;
-	}
-
-	drop_range_partial(i, start, end);
-	goto try_next;
-}
-
-#ifdef CONFIG_NO_BOOTMEM
-static void __init subtract_early_res(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++;
-
-	/* need to skip first one ?*/
-	if (early_res != early_res_x)
-		idx = 1;
-
-#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];
-#if DEBUG_PRINT_EARLY_RES
-		printk(KERN_INFO "  #%d [%010llx - %010llx] %15s\n", i,
-			r->start, r->end, r->name);
-#endif
-		final_start = PFN_DOWN(r->start);
-		final_end = PFN_UP(r->end);
-		if (final_start >= final_end)
-			continue;
-		subtract_range(range, az, final_start, final_end);
-	}
-
-}
-
-int __init get_free_all_memory_range(struct range **rangep, int nodeid)
-{
-	int i, 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;
-
-	size = sizeof(struct range) * count;
-	end = get_max_mapped();
-#ifdef MAX_DMA32_PFN
-	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));
-	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 */
-	memset(range, 0, size);
-	nr_range = 0;
-
-	/* need to go over early_node_map to find out good range for node */
-	nr_range = add_from_early_node_map(range, count, nr_range, nodeid);
-#ifdef CONFIG_X86_32
-	subtract_range(range, count, max_low_pfn, -1ULL);
-#endif
-	subtract_early_res(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;
-	}
-
-	*rangep = range;
-	return nr_range;
-}
-#else
-void __init early_res_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);
-		if (final_start >= final_end) {
-			printk(KERN_CONT "\n");
-			continue;
-		}
-		printk(KERN_CONT " ==> [%010llx - %010llx]\n",
-			final_start, final_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;
-}
-#endif
-
-/* Check for already reserved areas */
-static inline int __init bad_addr(u64 *addrp, u64 size, u64 align)
-{
-	int i;
-	u64 addr = *addrp;
-	int changed = 0;
-	struct early_res *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;
-		goto again;
-	}
-	return changed;
-}
-
-/* Check for already reserved areas */
-static inline int __init bad_addr_size(u64 *addrp, u64 *sizep, u64 align)
-{
-	int i;
-	u64 addr = *addrp, last;
-	u64 size = *sizep;
-	int changed = 0;
-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;
-			goto again;
-		}
-		if (last > r->end && addr < r->end) {
-			addr = round_up(r->end, align);
-			size = last - addr;
-			changed = 1;
-			goto again;
-		}
-		if (last <= r->end && addr >= r->start) {
-			(*sizep)++;
-			return 0;
-		}
-	}
-	if (changed) {
-		*addrp = addr;
-		*sizep = size;
-	}
-	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 addr, last;
-
-	addr = round_up(ei_start, align);
-	if (addr < start)
-		addr = round_up(start, align);
-	if (addr >= ei_last)
-		goto out;
-	while (bad_addr(&addr, size, align) && addr+size <= ei_last)
-		;
-	last = addr + size;
-	if (last > ei_last)
-		goto out;
-	if (last > end)
-		goto out;
-
-	return addr;
-
-out:
-	return -1ULL;
-}
-
-u64 __init find_early_area_size(u64 ei_start, u64 ei_last, u64 start,
-			 u64 *sizep, u64 align)
-{
-	u64 addr, last;
-
-	addr = round_up(ei_start, align);
-	if (addr < start)
-		addr = round_up(start, align);
-	if (addr >= ei_last)
-		goto out;
-	*sizep = ei_last - addr;
-	while (bad_addr_size(&addr, sizep, align) && addr + *sizep <= ei_last)
-		;
-	last = addr + *sizep;
-	if (last > ei_last)
-		goto out;
-
-	return addr;
-
-out:
-	return -1ULL;
-}
-- 
1.6.4.2

[PATCH 23/24] x86, lmb: Use lmb_memory_size()/lmb_free_memory_size() to get correct dma_reserve

[Yinghai Lu]

lmb_memory_size() will return memory size in lmb.memory.region.
lmb_free_memory_size() will return free memory size in lmb.memory.region.

So We can get exact reseved size.

Set the size right after initmem_init(), because later bootmem API will
get area from 16M. (except some fallback).

Later after we remove the bootmem, We could call that just before paging_init().

Signed-off-by: Yinghai Lu <yinghai@kernel.org>
---
 arch/x86/include/asm/e820.h |    2 ++
 arch/x86/kernel/e820.c      |   17 +++++++++++++++++
 arch/x86/kernel/setup.c     |    1 +
 arch/x86/mm/init_64.c       |    7 -------
 4 files changed, 20 insertions(+), 7 deletions(-)

diff --git a/arch/x86/include/asm/e820.h b/arch/x86/include/asm/e820.h
index de6cd06..334281f 100644
--- a/arch/x86/include/asm/e820.h
+++ b/arch/x86/include/asm/e820.h
@@ -117,6 +117,8 @@ extern u64 early_reserve_e820(u64 startt, u64 sizet, u64 align);
 
 void init_lmb_memory(void);
 void fill_lmb_memory(void);
+void find_lmb_dma_reserve(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/kernel/e820.c b/arch/x86/kernel/e820.c
index 78ba396..e0257b8 100644
--- a/arch/x86/kernel/e820.c
+++ b/arch/x86/kernel/e820.c
@@ -1100,3 +1100,20 @@ void __init fill_lmb_memory(void)
 	lmb_analyze();
 	lmb_dump_all();
 }
+
+void __init find_lmb_dma_reserve(void)
+{
+#ifdef CONFIG_X86_64
+	u64 free_size_pfn;
+	u64 mem_size_pfn;
+	/*
+	 * need to find out used area below MAX_DMA_PFN
+	 * need to use lmb to get free size in [0, MAX_DMA_PFN]
+	 * at first, and assume boot_mem will not take below MAX_DMA_PFN
+	 */
+	mem_size_pfn = lmb_memory_size(0, MAX_DMA_PFN << PAGE_SHIFT) >> PAGE_SHIFT;
+	free_size_pfn = lmb_free_memory_size(0, MAX_DMA_PFN << PAGE_SHIFT) >> PAGE_SHIFT;
+	set_dma_reserve(mem_size_pfn - free_size_pfn);
+#endif
+}
+
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index f0a32a4..6b62d9b 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -979,6 +979,7 @@ void __init setup_arch(char **cmdline_p)
 #endif
 
 	initmem_init(0, max_pfn, acpi, k8);
+	find_lmb_dma_reserve();
 #ifndef CONFIG_NO_BOOTMEM
 	lmb_to_bootmem(0, max_low_pfn<<PAGE_SHIFT);
 #endif
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index b86492e..f1af41c 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -52,8 +52,6 @@
 #include <asm/init.h>
 #include <linux/bootmem.h>
 
-static unsigned long dma_reserve __initdata;
-
 static int __init parse_direct_gbpages_off(char *arg)
 {
 	direct_gbpages = 0;
@@ -820,11 +818,6 @@ int __init reserve_bootmem_generic(unsigned long phys, unsigned long len,
 
 	reserve_bootmem(phys, len, flags);
 
-	if (phys+len <= MAX_DMA_PFN*PAGE_SIZE) {
-		dma_reserve += len / PAGE_SIZE;
-		set_dma_reserve(dma_reserve);
-	}
-
 	return 0;
 }
 #endif
-- 
1.6.4.2

[PATCH 24/24] x86: Align e820 ram range to page

[Yinghai Lu]

to workaround wrong BIOS map.

Signed-off-by: Yinghai Lu <yinghai@kernel.org>
---
 arch/x86/kernel/e820.c |   44 ++++++++++++++++++++++++++++++++++++++++++++
 1 files changed, 44 insertions(+), 0 deletions(-)

diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c
index e0257b8..89b8bf9 100644
--- a/arch/x86/kernel/e820.c
+++ b/arch/x86/kernel/e820.c
@@ -903,6 +903,47 @@ static int __init parse_memmap_opt(char *p)
 }
 early_param("memmap", parse_memmap_opt);
 
+static void __init e820_align_ram_page(void)
+{
+	int i;
+	bool changed = false;;
+
+	for (i = 0; i < e820.nr_map; i++) {
+		struct e820entry *entry = &e820.map[i];
+		u64 start, end;
+		u64 start_aligned, end_aligned;
+
+		if (entry->type != E820_RAM)
+			continue;
+
+		start = entry->addr;
+		end = start + entry->size;
+
+		start_aligned = round_up(start, PAGE_SIZE);
+		end_aligned = round_down(end, PAGE_SIZE);
+
+		if (end_aligned <= start_aligned) {
+			e820_update_range(start, end - start, E820_RAM, E820_RESERVED);
+			changed = true;
+			continue;
+		}
+		if (start < start_aligned) {
+			e820_update_range(start, start_aligned - start, E820_RAM, E820_RESERVED);
+			changed = true;
+		}
+		if (end_aligned < end) {
+			e820_update_range(end_aligned, end - end_aligned, E820_RAM, E820_RESERVED);
+			changed = true;
+		}
+	}
+
+	if (changed) {
+		sanitize_e820_map();
+		printk(KERN_INFO "aligned physical RAM map:\n");
+		e820_print_map("aligned");
+	}
+}
+
 void __init finish_e820_parsing(void)
 {
 	if (userdef) {
@@ -915,6 +956,9 @@ void __init finish_e820_parsing(void)
 		printk(KERN_INFO "user-defined physical RAM map:\n");
 		e820_print_map("user");
 	}
+
+	/* In case, We have RAM entres that are not PAGE aligned */
+	e820_align_ram_page();
 }
 
 static inline const char *e820_type_to_string(int e820_type)
-- 
1.6.4.2

Re: [PATCH 02/24] x86: Make sure free_init_pages() free pages in boundary

[Johannes Weiner]

On Fri, Mar 26, 2010 at 03:21:32PM -0700, Yinghai Lu wrote:
> diff --git a/arch/x86/kernel/head32.c b/arch/x86/kernel/head32.c
> index adedeef..fe3d953 100644
> --- a/arch/x86/kernel/head32.c
> +++ b/arch/x86/kernel/head32.c
> @@ -47,6 +47,7 @@ void __init i386_start_kernel(void)
>  		u64 ramdisk_image = boot_params.hdr.ramdisk_image;
>  		u64 ramdisk_size  = boot_params.hdr.ramdisk_size;
>  		u64 ramdisk_end   = ramdisk_image + ramdisk_size;
> +		ramdisk_end = PFN_UP(ramdisk_end) << PAGE_SHIFT;

Why not PAGE_ALIGN()?

>  		reserve_early(ramdisk_image, ramdisk_end, "RAMDISK");
>  	}
>  #endif
> diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c
> index b5a9896..fafba92 100644
> --- a/arch/x86/kernel/head64.c
> +++ b/arch/x86/kernel/head64.c
> @@ -106,6 +106,7 @@ void __init x86_64_start_reservations(char *real_mode_data)
>  		unsigned long ramdisk_image = boot_params.hdr.ramdisk_image;
>  		unsigned long ramdisk_size  = boot_params.hdr.ramdisk_size;
>  		unsigned long ramdisk_end   = ramdisk_image + ramdisk_size;
> +		ramdisk_end = PFN_UP(ramdisk_end) << PAGE_SHIFT;

Dito

>  		reserve_early(ramdisk_image, ramdisk_end, "RAMDISK");
>  	}
>  #endif
> diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
> index 5d7ba1a..2a1b9d4 100644
> --- a/arch/x86/kernel/setup.c
> +++ b/arch/x86/kernel/setup.c
> @@ -317,57 +317,61 @@ static void __init relocate_initrd(void)
>  
>  	u64 ramdisk_image = boot_params.hdr.ramdisk_image;
>  	u64 ramdisk_size  = boot_params.hdr.ramdisk_size;
> +	u64 ramdisk_end   = ramdisk_image + ramdisk_size;
>  	u64 end_of_lowmem = max_low_pfn_mapped << PAGE_SHIFT;
> +	u64 image, size_aligned;
>  	u64 ramdisk_here;
>  	unsigned long slop, clen, mapaddr;
>  	char *p, *q;
>  
> +	ramdisk_end = PFN_UP(ramdisk_end) << PAGE_SHIFT;

Dito

> +	size_aligned = ramdisk_end - ramdisk_image;
> +
>  	/* We need to move the initrd down into lowmem */
> -	ramdisk_here = find_e820_area(0, end_of_lowmem, ramdisk_size,
> +	ramdisk_here = find_e820_area(0, end_of_lowmem, size_aligned,
>  					 PAGE_SIZE);
>  
>  	if (ramdisk_here == -1ULL)
>  		panic("Cannot find place for new RAMDISK of size %lld\n",
> -			 ramdisk_size);
> +			 size_aligned);
>  
>  	/* Note: this includes all the lowmem currently occupied by
>  	   the initrd, we rely on that fact to keep the data intact. */
> -	reserve_early(ramdisk_here, ramdisk_here + ramdisk_size,
> +	reserve_early(ramdisk_here, ramdisk_here + size_aligned,
>  			 "NEW RAMDISK");
>  	initrd_start = ramdisk_here + PAGE_OFFSET;
>  	initrd_end   = initrd_start + ramdisk_size;
>  	printk(KERN_INFO "Allocated new RAMDISK: %08llx - %08llx\n",
> -			 ramdisk_here, ramdisk_here + ramdisk_size);
> +			 ramdisk_here, ramdisk_here + size_aligned);
>  
>  	q = (char *)initrd_start;
>  
>  	/* Copy any lowmem portion of the initrd */
> -	if (ramdisk_image < end_of_lowmem) {
> -		clen = end_of_lowmem - ramdisk_image;
> -		p = (char *)__va(ramdisk_image);
> +	image = ramdisk_image;
> +	if (image < end_of_lowmem) {
> +		clen = end_of_lowmem - image;
> +		p = (char *)__va(image);
>  		memcpy(q, p, clen);
>  		q += clen;
> -		ramdisk_image += clen;
> -		ramdisk_size  -= clen;
> +		image += clen;
> +		size_aligned  -= clen;
>  	}
>  
>  	/* Copy the highmem portion of the initrd */
> -	while (ramdisk_size) {
> -		slop = ramdisk_image & ~PAGE_MASK;
> -		clen = ramdisk_size;
> +	while (size_aligned) {
> +		slop = image & ~PAGE_MASK;
> +		clen = size_aligned;
>  		if (clen > MAX_MAP_CHUNK-slop)
>  			clen = MAX_MAP_CHUNK-slop;
> -		mapaddr = ramdisk_image & PAGE_MASK;
> +		mapaddr = image & PAGE_MASK;
>  		p = early_memremap(mapaddr, clen+slop);
>  		memcpy(q, p+slop, clen);
>  		early_iounmap(p, clen+slop);
>  		q += clen;
> -		ramdisk_image += clen;
> -		ramdisk_size  -= clen;
> +		image += clen;
> +		size_aligned  -= clen;

Those appear to be a lot of spurious changes.  We don't need to
copy the alignment padding as well, so it only matters that the
arguments to find_e820_area() and reserve_early() are aligned, no?

>  	}
>  	/* high pages is not converted by early_res_to_bootmem */
> -	ramdisk_image = boot_params.hdr.ramdisk_image;
> -	ramdisk_size  = boot_params.hdr.ramdisk_size;
>  	printk(KERN_INFO "Move RAMDISK from %016llx - %016llx to"
>  		" %08llx - %08llx\n",
>  		ramdisk_image, ramdisk_image + ramdisk_size - 1,
> @@ -385,6 +389,8 @@ static void __init reserve_initrd(void)
>  	    !ramdisk_image || !ramdisk_size)
>  		return;		/* No initrd provided by bootloader */
>  
> +	ramdisk_end = PFN_UP(ramdisk_end) << PAGE_SHIFT;

Dito

> diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
> index e71c5cb..727d6b0 100644
> --- a/arch/x86/mm/init.c
> +++ b/arch/x86/mm/init.c
> @@ -332,6 +332,16 @@ int devmem_is_allowed(unsigned long pagenr)
>  void free_init_pages(char *what, unsigned long begin, unsigned long end)
>  {
>  	unsigned long addr = begin;
> +	unsigned long addr_aligned, end_aligned;
> +
> +	/* Make sure boundaries are page aligned */
> +	addr_aligned = PFN_UP(addr) << PAGE_SHIFT;
> +	end_aligned = PFN_DOWN(end) << PAGE_SHIFT;
> +
> +	if (WARN(addr_aligned != addr || end_aligned != end, "free_init_pages: range [%#lx, %#lx] is not aligned\n", addr, end)) {
> +		addr = addr_aligned;
> +		end = end_aligned;
> +	}

Maybe realign only for when it is not aligned?  So to keep the fixup
out of line.

I suppose WARN_ON() is enough as it will print a stack trace which
should be enough clue of what went wrong.

>  	if (addr >= end)
>  		return;
> @@ -376,6 +386,18 @@ void free_initmem(void)
>  #ifdef CONFIG_BLK_DEV_INITRD
>  void free_initrd_mem(unsigned long start, unsigned long end)
>  {
> -	free_init_pages("initrd memory", start, end);
> +	unsigned long end_aligned;
> +
> +	/*
> +	 * end could be not aligned, and We can not align that,
> +	 * decompresser could be confused by aligned initrd_end
> +	 * We already reserve the end partial page before in
> +	 *   - i386_start_kernel()
> +	 *   - x86_64_start_kernel()
> +	 *   - relocate_initrd()
> +	 * So here we can do PFN_UP() safely to get partial page to be freed
> +	 */
> +	end_aligned = PFN_UP(end) << PAGE_SHIFT;

PAGE_ALIGN()

> +	free_init_pages("initrd memory", start, end_aligned);
>  }
>  #endif

Re: [PATCH 01/24] x86: Make smp_locks end with page alignment

[Johannes Weiner]

On Fri, Mar 26, 2010 at 03:21:31PM -0700, Yinghai Lu wrote:
> Try to fix
> ------------[ cut here ]------------
> WARNING: at arch/x86/mm/init.c:342 free_init_pages+0x4c/0xfa()
> free_init_pages: range [0x40daf000, 0x40db5c24] is not aligned
> Modules linked in:
> Pid: 0, comm: swapper Not tainted 2.6.34-rc2-tip-03946-g4f16b23-dirty #50
> Call Trace:
>  [<40232e9f>] warn_slowpath_common+0x65/0x7c
>  [<4021c9f0>] ? free_init_pages+0x4c/0xfa
>  [<40881434>] ? _etext+0x0/0x24
>  [<40232eea>] warn_slowpath_fmt+0x24/0x27
>  [<4021c9f0>] free_init_pages+0x4c/0xfa
>  [<40881434>] ? _etext+0x0/0x24
>  [<40d3f4bd>] alternative_instructions+0xf6/0x100
>  [<40d3fe4f>] check_bugs+0xbd/0xbf
>  [<40d398a7>] start_kernel+0x2d5/0x2e4
>  [<40d390ce>] i386_start_kernel+0xce/0xd5
> ---[ end trace 4eaa2a86a8e2da22 ]---
> 
> Comments in vmlinux.lds.S already said:
> |        /*
> |         * smp_locks might be freed after init
> |         * start/end must be page aligned
> |         */
> 
> Signed-off-by: Yinghai Lu <yinghai@kernel.org>

FWIW, Acked-by: Johannes Weiner <hannes@cmpxchg.org>

> ---
>  arch/x86/kernel/vmlinux.lds.S |    2 +-
>  1 files changed, 1 insertions(+), 1 deletions(-)
> 
> diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S
> index 44879df..2cc2497 100644
> --- a/arch/x86/kernel/vmlinux.lds.S
> +++ b/arch/x86/kernel/vmlinux.lds.S
> @@ -291,8 +291,8 @@ SECTIONS
>  	.smp_locks : AT(ADDR(.smp_locks) - LOAD_OFFSET) {
>  		__smp_locks = .;
>  		*(.smp_locks)
> -		__smp_locks_end = .;
>  		. = ALIGN(PAGE_SIZE);
> +		__smp_locks_end = .;
>  	}
>  
>  #ifdef CONFIG_X86_64

Re: [PATCH 03/24] x86: Do not free zero sized per cpu areas

[Johannes Weiner]

On Fri, Mar 26, 2010 at 03:21:33PM -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 warning according to linus
> -v7: more test by
> 
> Signed-off-by: Ian Campbell <ian.campbell@citrix.com>
> Signed-off-by: Yinghai Lu <yinghai@kernel.org>
> Tested-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
> Tested-by: Joel Becker <joel.becker@oracle.com>
> Tested-by: Stanislaw Gruszka <sgruszka@redhat.com>
> 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;

I think you can drop the function name, it will be in the stack dump
anyway.  And that would get the line back into bounds :)

Other than that,
Acked-by: Johannes Weiner <hannes@cmpxchg.org>

Re: [PATCH 02/24] x86: Make sure free_init_pages() free pages in boundary

[Yinghai Lu]

On 03/26/2010 04:06 PM, Johannes Weiner wrote:
> On Fri, Mar 26, 2010 at 03:21:32PM -0700, Yinghai Lu wrote:
>> diff --git a/arch/x86/kernel/head32.c b/arch/x86/kernel/head32.c
>> index adedeef..fe3d953 100644
>> --- a/arch/x86/kernel/head32.c
>> +++ b/arch/x86/kernel/head32.c
>> @@ -47,6 +47,7 @@ void __init i386_start_kernel(void)
>>  		u64 ramdisk_image = boot_params.hdr.ramdisk_image;
>>  		u64 ramdisk_size  = boot_params.hdr.ramdisk_size;
>>  		u64 ramdisk_end   = ramdisk_image + ramdisk_size;
>> +		ramdisk_end = PFN_UP(ramdisk_end) << PAGE_SHIFT;
> 
> Why not PAGE_ALIGN()?

looks like PFN_UP is more clear.

>> +	size_aligned = ramdisk_end - ramdisk_image;
>> +
>>  	/* We need to move the initrd down into lowmem */
>> -	ramdisk_here = find_e820_area(0, end_of_lowmem, ramdisk_size,
>> +	ramdisk_here = find_e820_area(0, end_of_lowmem, size_aligned,
>>  					 PAGE_SIZE);
>>  
>>  	if (ramdisk_here == -1ULL)
>>  		panic("Cannot find place for new RAMDISK of size %lld\n",
>> -			 ramdisk_size);
>> +			 size_aligned);
>>  
>>  	/* Note: this includes all the lowmem currently occupied by
>>  	   the initrd, we rely on that fact to keep the data intact. */
>> -	reserve_early(ramdisk_here, ramdisk_here + ramdisk_size,
>> +	reserve_early(ramdisk_here, ramdisk_here + size_aligned,
>>  			 "NEW RAMDISK");
>>  	initrd_start = ramdisk_here + PAGE_OFFSET;
>>  	initrd_end   = initrd_start + ramdisk_size;
>>  	printk(KERN_INFO "Allocated new RAMDISK: %08llx - %08llx\n",
>> -			 ramdisk_here, ramdisk_here + ramdisk_size);
>> +			 ramdisk_here, ramdisk_here + size_aligned);
>>  
>>  	q = (char *)initrd_start;
>>  
>>  	/* Copy any lowmem portion of the initrd */
>> -	if (ramdisk_image < end_of_lowmem) {
>> -		clen = end_of_lowmem - ramdisk_image;
>> -		p = (char *)__va(ramdisk_image);
>> +	image = ramdisk_image;
>> +	if (image < end_of_lowmem) {
>> +		clen = end_of_lowmem - image;
>> +		p = (char *)__va(image);
>>  		memcpy(q, p, clen);
>>  		q += clen;
>> -		ramdisk_image += clen;
>> -		ramdisk_size  -= clen;
>> +		image += clen;
>> +		size_aligned  -= clen;
>>  	}
>>  
>>  	/* Copy the highmem portion of the initrd */
>> -	while (ramdisk_size) {
>> -		slop = ramdisk_image & ~PAGE_MASK;
>> -		clen = ramdisk_size;
>> +	while (size_aligned) {
>> +		slop = image & ~PAGE_MASK;
>> +		clen = size_aligned;
>>  		if (clen > MAX_MAP_CHUNK-slop)
>>  			clen = MAX_MAP_CHUNK-slop;
>> -		mapaddr = ramdisk_image & PAGE_MASK;
>> +		mapaddr = image & PAGE_MASK;
>>  		p = early_memremap(mapaddr, clen+slop);
>>  		memcpy(q, p+slop, clen);
>>  		early_iounmap(p, clen+slop);
>>  		q += clen;
>> -		ramdisk_image += clen;
>> -		ramdisk_size  -= clen;
>> +		image += clen;
>> +		size_aligned  -= clen;
> 
> Those appear to be a lot of spurious changes.  We don't need to
> copy the alignment padding as well, so it only matters that the
> arguments to find_e820_area() and reserve_early() are aligned, no?

we need to reserve that whole page, otherwise other user may use the same page.

then we can not use PFN_UP() later to free the whole page.

>> --- a/arch/x86/mm/init.c
>> +++ b/arch/x86/mm/init.c
>> @@ -332,6 +332,16 @@ int devmem_is_allowed(unsigned long pagenr)
>>  void free_init_pages(char *what, unsigned long begin, unsigned long end)
>>  {
>>  	unsigned long addr = begin;
>> +	unsigned long addr_aligned, end_aligned;
>> +
>> +	/* Make sure boundaries are page aligned */
>> +	addr_aligned = PFN_UP(addr) << PAGE_SHIFT;
>> +	end_aligned = PFN_DOWN(end) << PAGE_SHIFT;
>> +
>> +	if (WARN(addr_aligned != addr || end_aligned != end, "free_init_pages: range [%#lx, %#lx] is not aligned\n", addr, end)) {
>> +		addr = addr_aligned;
>> +		end = end_aligned;
>> +	}
> 
> Maybe realign only for when it is not aligned?  So to keep the fixup
> out of line.
> 
> I suppose WARN_ON() is enough as it will print a stack trace which
> should be enough clue of what went wrong.

we need to PFN_DOWN the end, and don't free the partial page.
otherwise could crash the system.

So just print out the trace, and system still can be used. reporter to get dmesg if
he don't have serial console.

> 
>>  	if (addr >= end)
>>  		return;
>> @@ -376,6 +386,18 @@ void free_initmem(void)
>>  #ifdef CONFIG_BLK_DEV_INITRD
>>  void free_initrd_mem(unsigned long start, unsigned long end)
>>  {
>> -	free_init_pages("initrd memory", start, end);
>> +	unsigned long end_aligned;
>> +
>> +	/*
>> +	 * end could be not aligned, and We can not align that,
>> +	 * decompresser could be confused by aligned initrd_end
>> +	 * We already reserve the end partial page before in
>> +	 *   - i386_start_kernel()
>> +	 *   - x86_64_start_kernel()
>> +	 *   - relocate_initrd()
>> +	 * So here we can do PFN_UP() safely to get partial page to be freed
>> +	 */
>> +	end_aligned = PFN_UP(end) << PAGE_SHIFT;
> 
> PAGE_ALIGN()

no PAGE_ALIGN is bad name, it is not clear UP or DOWN.

Thanks

Yinghai

Re: [PATCH 03/24] x86: Do not free zero sized per cpu areas

[Yinghai Lu]

On 03/26/2010 04:42 PM, Johannes Weiner wrote:
> On Fri, Mar 26, 2010 at 03:21:33PM -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 warning according to linus
>> -v7: more test by
>>
>> Signed-off-by: Ian Campbell <ian.campbell@citrix.com>
>> Signed-off-by: Yinghai Lu <yinghai@kernel.org>
>> Tested-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
>> Tested-by: Joel Becker <joel.becker@oracle.com>
>> Tested-by: Stanislaw Gruszka <sgruszka@redhat.com>
>> 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;
> 
> I think you can drop the function name, it will be in the stack dump
> anyway.  And that would get the line back into bounds :)
> 
> Other than that,
> Acked-by: Johannes Weiner <hannes@cmpxchg.org>

Thanks.

is there any chance that dump stack only print out address instead of function name ?

BTW, kernel/early_res.c will be replaced by lmb.c

Yinghai

Re: [PATCH 03/24] x86: Do not free zero sized per cpu areas

[Johannes Weiner]

On Fri, Mar 26, 2010 at 04:49:10PM -0700, Yinghai Lu wrote:
> On 03/26/2010 04:42 PM, Johannes Weiner wrote:
> > On Fri, Mar 26, 2010 at 03:21:33PM -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 warning according to linus
> >> -v7: more test by
> >>
> >> Signed-off-by: Ian Campbell <ian.campbell@citrix.com>
> >> Signed-off-by: Yinghai Lu <yinghai@kernel.org>
> >> Tested-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
> >> Tested-by: Joel Becker <joel.becker@oracle.com>
> >> Tested-by: Stanislaw Gruszka <sgruszka@redhat.com>
> >> 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;
> > 
> > I think you can drop the function name, it will be in the stack dump
> > anyway.  And that would get the line back into bounds :)
> > 
> > Other than that,
> > Acked-by: Johannes Weiner <hannes@cmpxchg.org>
> 
> Thanks.
> 
> is there any chance that dump stack only print out address instead of function name ?

I suppose so, lacking frame pointers, but you still have
filename + linenumber + 'wrong range'.

Re: [PATCH 03/24] x86: Do not free zero sized per cpu areas

[Yinghai Lu]

On 03/26/2010 04:54 PM, Johannes Weiner wrote:
> On Fri, Mar 26, 2010 at 04:49:10PM -0700, Yinghai Lu wrote:
>>
>> is there any chance that dump stack only print out address instead of function name ?
> 
> I suppose so, lacking frame pointers, but you still have
> filename + linenumber + 'wrong range'.

ok, will remove that function name.

Re: [PATCH 02/24] x86: Make sure free_init_pages() free pages in boundary

[Johannes Weiner]

On Fri, Mar 26, 2010 at 04:45:56PM -0700, Yinghai Lu wrote:
> On 03/26/2010 04:06 PM, Johannes Weiner wrote:
> > On Fri, Mar 26, 2010 at 03:21:32PM -0700, Yinghai Lu wrote:
> >> diff --git a/arch/x86/kernel/head32.c b/arch/x86/kernel/head32.c
> >> index adedeef..fe3d953 100644
> >> --- a/arch/x86/kernel/head32.c
> >> +++ b/arch/x86/kernel/head32.c
> >> @@ -47,6 +47,7 @@ void __init i386_start_kernel(void)
> >>  		u64 ramdisk_image = boot_params.hdr.ramdisk_image;
> >>  		u64 ramdisk_size  = boot_params.hdr.ramdisk_size;
> >>  		u64 ramdisk_end   = ramdisk_image + ramdisk_size;
> >> +		ramdisk_end = PFN_UP(ramdisk_end) << PAGE_SHIFT;
> > 
> > Why not PAGE_ALIGN()?
> 
> looks like PFN_UP is more clear.

Why would you convert to a pfn just to go back to a physical address,
when all you wanted is align at the next page boundary?  It looks
rather clumsy.

PAGE_ALIGN() is pretty wide spread and I think it's clear to most
people what it does.

> >> +	size_aligned = ramdisk_end - ramdisk_image;
> >> +
> >>  	/* We need to move the initrd down into lowmem */
> >> -	ramdisk_here = find_e820_area(0, end_of_lowmem, ramdisk_size,
> >> +	ramdisk_here = find_e820_area(0, end_of_lowmem, size_aligned,
> >>  					 PAGE_SIZE);
> >>  
> >>  	if (ramdisk_here == -1ULL)
> >>  		panic("Cannot find place for new RAMDISK of size %lld\n",
> >> -			 ramdisk_size);
> >> +			 size_aligned);
> >>  
> >>  	/* Note: this includes all the lowmem currently occupied by
> >>  	   the initrd, we rely on that fact to keep the data intact. */
> >> -	reserve_early(ramdisk_here, ramdisk_here + ramdisk_size,
> >> +	reserve_early(ramdisk_here, ramdisk_here + size_aligned,
> >>  			 "NEW RAMDISK");
> >>  	initrd_start = ramdisk_here + PAGE_OFFSET;
> >>  	initrd_end   = initrd_start + ramdisk_size;
> >>  	printk(KERN_INFO "Allocated new RAMDISK: %08llx - %08llx\n",
> >> -			 ramdisk_here, ramdisk_here + ramdisk_size);
> >> +			 ramdisk_here, ramdisk_here + size_aligned);
> >>  
> >>  	q = (char *)initrd_start;
> >>  
> >>  	/* Copy any lowmem portion of the initrd */
> >> -	if (ramdisk_image < end_of_lowmem) {
> >> -		clen = end_of_lowmem - ramdisk_image;
> >> -		p = (char *)__va(ramdisk_image);
> >> +	image = ramdisk_image;
> >> +	if (image < end_of_lowmem) {
> >> +		clen = end_of_lowmem - image;
> >> +		p = (char *)__va(image);
> >>  		memcpy(q, p, clen);
> >>  		q += clen;
> >> -		ramdisk_image += clen;
> >> -		ramdisk_size  -= clen;
> >> +		image += clen;
> >> +		size_aligned  -= clen;
> >>  	}
> >>  
> >>  	/* Copy the highmem portion of the initrd */
> >> -	while (ramdisk_size) {
> >> -		slop = ramdisk_image & ~PAGE_MASK;
> >> -		clen = ramdisk_size;
> >> +	while (size_aligned) {
> >> +		slop = image & ~PAGE_MASK;
> >> +		clen = size_aligned;
> >>  		if (clen > MAX_MAP_CHUNK-slop)
> >>  			clen = MAX_MAP_CHUNK-slop;
> >> -		mapaddr = ramdisk_image & PAGE_MASK;
> >> +		mapaddr = image & PAGE_MASK;
> >>  		p = early_memremap(mapaddr, clen+slop);
> >>  		memcpy(q, p+slop, clen);
> >>  		early_iounmap(p, clen+slop);
> >>  		q += clen;
> >> -		ramdisk_image += clen;
> >> -		ramdisk_size  -= clen;
> >> +		image += clen;
> >> +		size_aligned  -= clen;
> > 
> > Those appear to be a lot of spurious changes.  We don't need to
> > copy the alignment padding as well, so it only matters that the
> > arguments to find_e820_area() and reserve_early() are aligned, no?
> 
> we need to reserve that whole page, otherwise other user may use the same page.

I know that.  And you would know that I know that, if you actually
read what I wrote.

> >> --- a/arch/x86/mm/init.c
> >> +++ b/arch/x86/mm/init.c
> >> @@ -332,6 +332,16 @@ int devmem_is_allowed(unsigned long pagenr)
> >>  void free_init_pages(char *what, unsigned long begin, unsigned long end)
> >>  {
> >>  	unsigned long addr = begin;
> >> +	unsigned long addr_aligned, end_aligned;
> >> +
> >> +	/* Make sure boundaries are page aligned */
> >> +	addr_aligned = PFN_UP(addr) << PAGE_SHIFT;
> >> +	end_aligned = PFN_DOWN(end) << PAGE_SHIFT;
> >> +
> >> +	if (WARN(addr_aligned != addr || end_aligned != end, "free_init_pages: range [%#lx, %#lx] is not aligned\n", addr, end)) {
> >> +		addr = addr_aligned;
> >> +		end = end_aligned;
> >> +	}
> > 
> > Maybe realign only for when it is not aligned?  So to keep the fixup
> > out of line.
> > 
> > I suppose WARN_ON() is enough as it will print a stack trace which
> > should be enough clue of what went wrong.
> 
> we need to PFN_DOWN the end, and don't free the partial page.
> otherwise could crash the system.

Dito.

	if (WARN_ON(not_aligned)) {
		align
	}

is what I meant.

> So just print out the trace, and system still can be used. reporter to get dmesg if
> he don't have serial console.

/me goes arguing with M-x doctor, that thing actually acts on the
supplied input.

Re: [PATCH 02/24] x86: Make sure free_init_pages() free pages in boundary

[Yinghai Lu]

On 03/26/2010 05:07 PM, Johannes Weiner wrote:
> On Fri, Mar 26, 2010 at 04:45:56PM -0700, Yinghai Lu wrote:
>> On 03/26/2010 04:06 PM, Johannes Weiner wrote:
>>> On Fri, Mar 26, 2010 at 03:21:32PM -0700, Yinghai Lu wrote:
>>>> diff --git a/arch/x86/kernel/head32.c b/arch/x86/kernel/head32.c
>>>> index adedeef..fe3d953 100644
>>>> --- a/arch/x86/kernel/head32.c
>>>> +++ b/arch/x86/kernel/head32.c
>>>> @@ -47,6 +47,7 @@ void __init i386_start_kernel(void)
>>>>  		u64 ramdisk_image = boot_params.hdr.ramdisk_image;
>>>>  		u64 ramdisk_size  = boot_params.hdr.ramdisk_size;
>>>>  		u64 ramdisk_end   = ramdisk_image + ramdisk_size;
>>>> +		ramdisk_end = PFN_UP(ramdisk_end) << PAGE_SHIFT;
>>>
>>> Why not PAGE_ALIGN()?
>>
>> looks like PFN_UP is more clear.
> 
> Why would you convert to a pfn just to go back to a physical address,
> when all you wanted is align at the next page boundary?  It looks
> rather clumsy.

reserve_early() will take phys addr

> 
> PAGE_ALIGN() is pretty wide spread and I think it's clear to most
> people what it does.

we may need to clean up all those:
round_up
round_down
roundup
ALIGN
PAGE_ALIGN etc.

> 
...
>>>> --- a/arch/x86/mm/init.c
>>>> +++ b/arch/x86/mm/init.c
>>>> @@ -332,6 +332,16 @@ int devmem_is_allowed(unsigned long pagenr)
>>>>  void free_init_pages(char *what, unsigned long begin, unsigned long end)
>>>>  {
>>>>  	unsigned long addr = begin;
>>>> +	unsigned long addr_aligned, end_aligned;
>>>> +
>>>> +	/* Make sure boundaries are page aligned */
>>>> +	addr_aligned = PFN_UP(addr) << PAGE_SHIFT;
>>>> +	end_aligned = PFN_DOWN(end) << PAGE_SHIFT;
>>>> +
>>>> +	if (WARN(addr_aligned != addr || end_aligned != end, "free_init_pages: range [%#lx, %#lx] is not aligned\n", addr, end)) {
>>>> +		addr = addr_aligned;
>>>> +		end = end_aligned;
>>>> +	}
>>>
>>> Maybe realign only for when it is not aligned?  So to keep the fixup
>>> out of line.
>>>
>>> I suppose WARN_ON() is enough as it will print a stack trace which
>>> should be enough clue of what went wrong.
>>
>> we need to PFN_DOWN the end, and don't free the partial page.
>> otherwise could crash the system.
> 
> Dito.
> 
> 	if (WARN_ON(not_aligned)) {
> 		align
> 	}
> 
> is what I meant.
> 
ok i got it.

YH

[PATCH -v8] 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 warning according to linus
-v7: more test by
-v8: remove the function name according to Johannes
     WARN_ONCE will print that function name.

Signed-off-by: Ian Campbell <ian.campbell@citrix.com>
Signed-off-by: Yinghai Lu <yinghai@kernel.org>
Tested-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Tested-by: Joel Becker <joel.becker@oracle.com>
Tested-by: Stanislaw Gruszka <sgruszka@redhat.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ingo Molnar <mingo@elte.hu>
---
 kernel/early_res.c |    6 ++++++
 1 file changed, 6 insertions(+)

Index: linux-2.6/kernel/early_res.c
===================================================================
--- linux-2.6.orig/kernel/early_res.c
+++ linux-2.6/kernel/early_res.c
@@ -333,6 +333,12 @@ void __init free_early_partial(u64 start
 	struct early_res *r;
 	int i;
 
+	if (start == end)
+		return;
+
+	if (WARN_ONCE(start > end, "  wrong range [%#llx, %#llx]\n", start, end))
+		return;
+
 try_next:
 	i = find_overlapped_early(start, end);
 	if (i >= max_early_res)

[PATCH -v3] x86: Make sure free_init_pages() free pages in boundary

[Yinghai Lu]

When CONFIG_NO_BOOTMEM, it could use memory more effient, or more compact.

Example is:
Allocated new RAMDISK: 00ec2000 - 0248ce57
Move RAMDISK from 000000002ea04000 - 000000002ffcee56 to 00ec2000 - 0248ce56

The new RAMDISK's end is not page aligned.
Last page could use shared with other user.

When free_init_pages are called for initrd or .init, the page could be freed
could have chance to corrupt other data.

code segment in free_init_pages()
|        for (; addr < end; addr += PAGE_SIZE) {
|                ClearPageReserved(virt_to_page(addr));
|                init_page_count(virt_to_page(addr));
|                memset((void *)(addr & ~(PAGE_SIZE-1)),
|                        POISON_FREE_INITMEM, PAGE_SIZE);
|                free_page(addr);
|                totalram_pages++;
|        }
last half page could be used as one whole free page.

Try to make the boundaries to be page aligned.

-v2: make the original initramdisk to be aligned, according to Johannes.
     otherwise we have chance to lose one page.
     we still need to keep initrd_end not aligned, otherwise it could
     confuse decompresser.
-v3: change to WARN_ON instead according to Johannes.

Reported-by: Stanislaw Gruszka <sgruszka@redhat.com>
Signed-off-by: Yinghai Lu <yinghai@kernel.org>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Tested-by: Stanislaw Gruszka <sgruszka@redhat.com>

---
 arch/x86/kernel/head32.c |    1 +
 arch/x86/kernel/head64.c |    1 +
 arch/x86/kernel/setup.c  |   40 +++++++++++++++++++++++-----------------
 arch/x86/mm/init.c       |   24 +++++++++++++++++++++++-
 4 files changed, 48 insertions(+), 18 deletions(-)

Index: linux-2.6/arch/x86/mm/init.c
===================================================================
--- linux-2.6.orig/arch/x86/mm/init.c
+++ linux-2.6/arch/x86/mm/init.c
@@ -332,6 +332,16 @@ int devmem_is_allowed(unsigned long page
 void free_init_pages(char *what, unsigned long begin, unsigned long end)
 {
 	unsigned long addr = begin;
+	unsigned long addr_aligned, end_aligned;
+
+	/* Make sure boundaries are page aligned */
+	addr_aligned = PFN_UP(addr) << PAGE_SHIFT;
+	end_aligned = PFN_DOWN(end) << PAGE_SHIFT;
+
+	if (WARN_ON(addr_aligned != addr || end_aligned != end)) {
+		addr = addr_aligned;
+		end = end_aligned;
+	}
 
 	if (addr >= end)
 		return;
@@ -376,6 +386,18 @@ void free_initmem(void)
 #ifdef CONFIG_BLK_DEV_INITRD
 void free_initrd_mem(unsigned long start, unsigned long end)
 {
-	free_init_pages("initrd memory", start, end);
+	unsigned long end_aligned;
+
+	/*
+	 * end could be not aligned, and We can not align that,
+	 * decompresser could be confused by aligned initrd_end
+	 * We already reserve the end partial page before in
+	 *   - i386_start_kernel()
+	 *   - x86_64_start_kernel()
+	 *   - relocate_initrd()
+	 * So here we can do PFN_UP() safely to get partial page to be freed
+	 */
+	end_aligned = PFN_UP(end) << PAGE_SHIFT;
+	free_init_pages("initrd memory", start, end_aligned);
 }
 #endif
Index: linux-2.6/arch/x86/kernel/head32.c
===================================================================
--- linux-2.6.orig/arch/x86/kernel/head32.c
+++ linux-2.6/arch/x86/kernel/head32.c
@@ -47,6 +47,7 @@ void __init i386_start_kernel(void)
 		u64 ramdisk_image = boot_params.hdr.ramdisk_image;
 		u64 ramdisk_size  = boot_params.hdr.ramdisk_size;
 		u64 ramdisk_end   = ramdisk_image + ramdisk_size;
+		ramdisk_end = PFN_UP(ramdisk_end) << PAGE_SHIFT;
 		reserve_early(ramdisk_image, ramdisk_end, "RAMDISK");
 	}
 #endif
Index: linux-2.6/arch/x86/kernel/head64.c
===================================================================
--- linux-2.6.orig/arch/x86/kernel/head64.c
+++ linux-2.6/arch/x86/kernel/head64.c
@@ -106,6 +106,7 @@ void __init x86_64_start_reservations(ch
 		unsigned long ramdisk_image = boot_params.hdr.ramdisk_image;
 		unsigned long ramdisk_size  = boot_params.hdr.ramdisk_size;
 		unsigned long ramdisk_end   = ramdisk_image + ramdisk_size;
+		ramdisk_end = PFN_UP(ramdisk_end) << PAGE_SHIFT;
 		reserve_early(ramdisk_image, ramdisk_end, "RAMDISK");
 	}
 #endif
Index: linux-2.6/arch/x86/kernel/setup.c
===================================================================
--- linux-2.6.orig/arch/x86/kernel/setup.c
+++ linux-2.6/arch/x86/kernel/setup.c
@@ -317,57 +317,61 @@ static void __init relocate_initrd(void)
 
 	u64 ramdisk_image = boot_params.hdr.ramdisk_image;
 	u64 ramdisk_size  = boot_params.hdr.ramdisk_size;
+	u64 ramdisk_end   = ramdisk_image + ramdisk_size;
 	u64 end_of_lowmem = max_low_pfn_mapped << PAGE_SHIFT;
+	u64 image, size_aligned;
 	u64 ramdisk_here;
 	unsigned long slop, clen, mapaddr;
 	char *p, *q;
 
+	ramdisk_end = PFN_UP(ramdisk_end) << PAGE_SHIFT;
+	size_aligned = ramdisk_end - ramdisk_image;
+
 	/* We need to move the initrd down into lowmem */
-	ramdisk_here = find_e820_area(0, end_of_lowmem, ramdisk_size,
+	ramdisk_here = find_e820_area(0, end_of_lowmem, size_aligned,
 					 PAGE_SIZE);
 
 	if (ramdisk_here == -1ULL)
 		panic("Cannot find place for new RAMDISK of size %lld\n",
-			 ramdisk_size);
+			 size_aligned);
 
 	/* Note: this includes all the lowmem currently occupied by
 	   the initrd, we rely on that fact to keep the data intact. */
-	reserve_early(ramdisk_here, ramdisk_here + ramdisk_size,
+	reserve_early(ramdisk_here, ramdisk_here + size_aligned,
 			 "NEW RAMDISK");
 	initrd_start = ramdisk_here + PAGE_OFFSET;
 	initrd_end   = initrd_start + ramdisk_size;
 	printk(KERN_INFO "Allocated new RAMDISK: %08llx - %08llx\n",
-			 ramdisk_here, ramdisk_here + ramdisk_size);
+			 ramdisk_here, ramdisk_here + size_aligned);
 
 	q = (char *)initrd_start;
 
 	/* Copy any lowmem portion of the initrd */
-	if (ramdisk_image < end_of_lowmem) {
-		clen = end_of_lowmem - ramdisk_image;
-		p = (char *)__va(ramdisk_image);
+	image = ramdisk_image;
+	if (image < end_of_lowmem) {
+		clen = end_of_lowmem - image;
+		p = (char *)__va(image);
 		memcpy(q, p, clen);
 		q += clen;
-		ramdisk_image += clen;
-		ramdisk_size  -= clen;
+		image += clen;
+		size_aligned  -= clen;
 	}
 
 	/* Copy the highmem portion of the initrd */
-	while (ramdisk_size) {
-		slop = ramdisk_image & ~PAGE_MASK;
-		clen = ramdisk_size;
+	while (size_aligned) {
+		slop = image & ~PAGE_MASK;
+		clen = size_aligned;
 		if (clen > MAX_MAP_CHUNK-slop)
 			clen = MAX_MAP_CHUNK-slop;
-		mapaddr = ramdisk_image & PAGE_MASK;
+		mapaddr = image & PAGE_MASK;
 		p = early_memremap(mapaddr, clen+slop);
 		memcpy(q, p+slop, clen);
 		early_iounmap(p, clen+slop);
 		q += clen;
-		ramdisk_image += clen;
-		ramdisk_size  -= clen;
+		image += clen;
+		size_aligned  -= clen;
 	}
 	/* high pages is not converted by early_res_to_bootmem */
-	ramdisk_image = boot_params.hdr.ramdisk_image;
-	ramdisk_size  = boot_params.hdr.ramdisk_size;
 	printk(KERN_INFO "Move RAMDISK from %016llx - %016llx to"
 		" %08llx - %08llx\n",
 		ramdisk_image, ramdisk_image + ramdisk_size - 1,
@@ -385,6 +389,8 @@ static void __init reserve_initrd(void)
 	    !ramdisk_image || !ramdisk_size)
 		return;		/* No initrd provided by bootloader */
 
+	ramdisk_end = PFN_UP(ramdisk_end) << PAGE_SHIFT;
+
 	initrd_start = 0;
 
 	if (ramdisk_size >= (end_of_lowmem>>1)) {

Re: [PATCH -v3] x86: Make sure free_init_pages() free pages in boundary

[Johannes Weiner]

Hi,

On Fri, Mar 26, 2010 at 06:19:33PM -0700, Yinghai Lu wrote:
> 
> 
> When CONFIG_NO_BOOTMEM, it could use memory more effient, or more compact.
> 
> Example is:
> Allocated new RAMDISK: 00ec2000 - 0248ce57
> Move RAMDISK from 000000002ea04000 - 000000002ffcee56 to 00ec2000 - 0248ce56
> 
> The new RAMDISK's end is not page aligned.
> Last page could use shared with other user.
> 
> When free_init_pages are called for initrd or .init, the page could be freed
> could have chance to corrupt other data.
> 
> code segment in free_init_pages()
> |        for (; addr < end; addr += PAGE_SIZE) {
> |                ClearPageReserved(virt_to_page(addr));
> |                init_page_count(virt_to_page(addr));
> |                memset((void *)(addr & ~(PAGE_SIZE-1)),
> |                        POISON_FREE_INITMEM, PAGE_SIZE);
> |                free_page(addr);
> |                totalram_pages++;
> |        }
> last half page could be used as one whole free page.
> 
> Try to make the boundaries to be page aligned.
> 
> -v2: make the original initramdisk to be aligned, according to Johannes.
>      otherwise we have chance to lose one page.
>      we still need to keep initrd_end not aligned, otherwise it could
>      confuse decompresser.
> -v3: change to WARN_ON instead according to Johannes.
> 
> Reported-by: Stanislaw Gruszka <sgruszka@redhat.com>
> Signed-off-by: Yinghai Lu <yinghai@kernel.org>
> Acked-by: Johannes Weiner <hannes@cmpxchg.org>

Here is what I had in mind when I wrote what you did not read, maybe diff
works better?

Main differences:
  o only fix the area allocation in relocate_initrd(), no need to do
    copy the alignment bits
  o keep alignment fixups in free_init_pages() out of line
  o use PAGE_SIZE(); you might dislike the name, it is still the proper
    operation here.  if you want to fix it, please do it properly

diff --git a/arch/x86/kernel/head32.c b/arch/x86/kernel/head32.c
index adedeef..ec7c672 100644
--- a/arch/x86/kernel/head32.c
+++ b/arch/x86/kernel/head32.c
@@ -46,7 +46,8 @@ void __init i386_start_kernel(void)
 	if (boot_params.hdr.type_of_loader && boot_params.hdr.ramdisk_image) {
 		u64 ramdisk_image = boot_params.hdr.ramdisk_image;
 		u64 ramdisk_size  = boot_params.hdr.ramdisk_size;
-		u64 ramdisk_end   = ramdisk_image + ramdisk_size;
+		u64 ramdisk_end   = PAGE_ALIGN(ramdisk_image + ramdisk_size);
+
 		reserve_early(ramdisk_image, ramdisk_end, "RAMDISK");
 	}
 #endif
diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c
index b5a9896..a26a8fd 100644
--- a/arch/x86/kernel/head64.c
+++ b/arch/x86/kernel/head64.c
@@ -105,7 +105,9 @@ void __init x86_64_start_reservations(char *real_mode_data)
 	if (boot_params.hdr.type_of_loader && boot_params.hdr.ramdisk_image) {
 		unsigned long ramdisk_image = boot_params.hdr.ramdisk_image;
 		unsigned long ramdisk_size  = boot_params.hdr.ramdisk_size;
-		unsigned long ramdisk_end   = ramdisk_image + ramdisk_size;
+		unsigned long ramdisk_end   = PAGE_ALIGN(ramdisk_image +
+							 ramdisk_size);
+
 		reserve_early(ramdisk_image, ramdisk_end, "RAMDISK");
 	}
 #endif
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index ca3f8fa..0594923 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -317,13 +317,14 @@ static void __init relocate_initrd(void)
 
 	u64 ramdisk_image = boot_params.hdr.ramdisk_image;
 	u64 ramdisk_size  = boot_params.hdr.ramdisk_size;
+	u64 area_size     = PAGE_ALIGN(ramdisk_size);
 	u64 end_of_lowmem = max_low_pfn_mapped << PAGE_SHIFT;
 	u64 ramdisk_here;
 	unsigned long slop, clen, mapaddr;
 	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_e820_area(0, end_of_lowmem, area_size,
 					 PAGE_SIZE);
 
 	if (ramdisk_here == -1ULL)
@@ -332,7 +333,7 @@ static void __init relocate_initrd(void)
 
 	/* Note: this includes all the lowmem currently occupied by
 	   the initrd, we rely on that fact to keep the data intact. */
-	reserve_early(ramdisk_here, ramdisk_here + ramdisk_size,
+	reserve_early(ramdisk_here, ramdisk_here + area_size,
 			 "NEW RAMDISK");
 	initrd_start = ramdisk_here + PAGE_OFFSET;
 	initrd_end   = initrd_start + ramdisk_size;
@@ -378,7 +379,7 @@ static void __init reserve_initrd(void)
 {
 	u64 ramdisk_image = boot_params.hdr.ramdisk_image;
 	u64 ramdisk_size  = boot_params.hdr.ramdisk_size;
-	u64 ramdisk_end   = ramdisk_image + ramdisk_size;
+	u64 ramdisk_end   = PAGE_ALIGN(ramdisk_image + ramdisk_size);
 	u64 end_of_lowmem = max_low_pfn_mapped << PAGE_SHIFT;
 
 	if (!boot_params.hdr.type_of_loader ||
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index e71c5cb..018e793 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -336,6 +336,11 @@ void free_init_pages(char *what, unsigned long begin, unsigned long end)
 	if (addr >= end)
 		return;
 
+	if (WARN_ON(addr & ~PAGE_MASK || end & ~PAGE_MASK)) {
+		addr = PAGE_ALIGN(addr);
+		end &= PAGE_MASK;
+	}
+
 	/*
 	 * If debugging page accesses then do not free this memory but
 	 * mark them not present - any buggy init-section access will
@@ -355,11 +360,10 @@ void free_init_pages(char *what, unsigned long begin, unsigned long end)
 
 	printk(KERN_INFO "Freeing %s: %luk freed\n", what, (end - begin) >> 10);
 
-	for (; addr < end; addr += PAGE_SIZE) {
+	for (; addr != end; addr += PAGE_SIZE) {
 		ClearPageReserved(virt_to_page(addr));
 		init_page_count(virt_to_page(addr));
-		memset((void *)(addr & ~(PAGE_SIZE-1)),
-			POISON_FREE_INITMEM, PAGE_SIZE);
+		memset((void *)addr, POISON_FREE_INITMEM, PAGE_SIZE);
 		free_page(addr);
 		totalram_pages++;
 	}
@@ -376,6 +380,6 @@ void free_initmem(void)
 #ifdef CONFIG_BLK_DEV_INITRD
 void free_initrd_mem(unsigned long start, unsigned long end)
 {
-	free_init_pages("initrd memory", start, end);
+	free_init_pages("initrd memory", start, PAGE_ALIGN(end));
 }
 #endif

Re: [PATCH -v3] x86: Make sure free_init_pages() free pages in boundary

[Yinghai Lu]

On 03/27/2010 05:03 PM, Johannes Weiner wrote:
> Hi,
> 
> On Fri, Mar 26, 2010 at 06:19:33PM -0700, Yinghai Lu wrote:
>>
>>
>> When CONFIG_NO_BOOTMEM, it could use memory more effient, or more compact.
>>
>> Example is:
>> Allocated new RAMDISK: 00ec2000 - 0248ce57
>> Move RAMDISK from 000000002ea04000 - 000000002ffcee56 to 00ec2000 - 0248ce56
>>
>> The new RAMDISK's end is not page aligned.
>> Last page could use shared with other user.
>>
>> When free_init_pages are called for initrd or .init, the page could be freed
>> could have chance to corrupt other data.
>>
>> code segment in free_init_pages()
>> |        for (; addr < end; addr += PAGE_SIZE) {
>> |                ClearPageReserved(virt_to_page(addr));
>> |                init_page_count(virt_to_page(addr));
>> |                memset((void *)(addr & ~(PAGE_SIZE-1)),
>> |                        POISON_FREE_INITMEM, PAGE_SIZE);
>> |                free_page(addr);
>> |                totalram_pages++;
>> |        }
>> last half page could be used as one whole free page.
>>
>> Try to make the boundaries to be page aligned.
>>
>> -v2: make the original initramdisk to be aligned, according to Johannes.
>>      otherwise we have chance to lose one page.
>>      we still need to keep initrd_end not aligned, otherwise it could
>>      confuse decompresser.
>> -v3: change to WARN_ON instead according to Johannes.
>>
>> Reported-by: Stanislaw Gruszka <sgruszka@redhat.com>
>> Signed-off-by: Yinghai Lu <yinghai@kernel.org>
>> Acked-by: Johannes Weiner <hannes@cmpxchg.org>
> 
> Here is what I had in mind when I wrote what you did not read, maybe diff
> works better?
> 
> Main differences:
>   o only fix the area allocation in relocate_initrd(), no need to do
>     copy the alignment bits
>   o keep alignment fixups in free_init_pages() out of line
>   o use PAGE_SIZE(); you might dislike the name, it is still the proper
>     operation here.  if you want to fix it, please do it properly
...
> diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
> index e71c5cb..018e793 100644
> --- a/arch/x86/mm/init.c
> +++ b/arch/x86/mm/init.c
> @@ -336,6 +336,11 @@ void free_init_pages(char *what, unsigned long begin, unsigned long end)
>  	if (addr >= end)
>  		return;
>  
> +	if (WARN_ON(addr & ~PAGE_MASK || end & ~PAGE_MASK)) {
> +		addr = PAGE_ALIGN(addr);
> +		end &= PAGE_MASK;
> +	}
> +
>  	/*
>  	 * If debugging page accesses then do not free this memory but
>  	 * mark them not present - any buggy init-section access will
> @@ -355,11 +360,10 @@ void free_init_pages(char *what, unsigned long begin, unsigned long end)
>  
>  	printk(KERN_INFO "Freeing %s: %luk freed\n", what, (end - begin) >> 10);
>  
> -	for (; addr < end; addr += PAGE_SIZE) {
> +	for (; addr != end; addr += PAGE_SIZE) {
>  		ClearPageReserved(virt_to_page(addr));
>  		init_page_count(virt_to_page(addr));
> -		memset((void *)(addr & ~(PAGE_SIZE-1)),
> -			POISON_FREE_INITMEM, PAGE_SIZE);
> +		memset((void *)addr, POISON_FREE_INITMEM, PAGE_SIZE);
>  		free_page(addr);
>  		totalram_pages++;
>  	}
something wrong here, if someone pass (0x10, 0x20), the will be aligned to [0x1000, 0]
you will get dead loop 

will update that.

YH

Re: [PATCH -v3] x86: Make sure free_init_pages() free pages in boundary

[Johannes Weiner]

On Sat, Mar 27, 2010 at 05:50:06PM -0700, Yinghai Lu wrote:
> > diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
> > index e71c5cb..018e793 100644
> > --- a/arch/x86/mm/init.c
> > +++ b/arch/x86/mm/init.c
> > @@ -336,6 +336,11 @@ void free_init_pages(char *what, unsigned long begin, unsigned long end)
> >  	if (addr >= end)
> >  		return;
> >  
> > +	if (WARN_ON(addr & ~PAGE_MASK || end & ~PAGE_MASK)) {
> > +		addr = PAGE_ALIGN(addr);
> > +		end &= PAGE_MASK;
> > +	}
> > +
> >  	/*
> >  	 * If debugging page accesses then do not free this memory but
> >  	 * mark them not present - any buggy init-section access will
> > @@ -355,11 +360,10 @@ void free_init_pages(char *what, unsigned long begin, unsigned long end)
> >  
> >  	printk(KERN_INFO "Freeing %s: %luk freed\n", what, (end - begin) >> 10);
> >  
> > -	for (; addr < end; addr += PAGE_SIZE) {
> > +	for (; addr != end; addr += PAGE_SIZE) {
> >  		ClearPageReserved(virt_to_page(addr));
> >  		init_page_count(virt_to_page(addr));
> > -		memset((void *)(addr & ~(PAGE_SIZE-1)),
> > -			POISON_FREE_INITMEM, PAGE_SIZE);
> > +		memset((void *)addr, POISON_FREE_INITMEM, PAGE_SIZE);
> >  		free_page(addr);
> >  		totalram_pages++;
> >  	}
> something wrong here, if someone pass (0x10, 0x20), the will be aligned to [0x1000, 0]
> you will get dead loop

You are right!  It should be enough to move the alignment fixup above the addr >= end
check and in that case?  So we would get the warning and then simply return.

> will update that.

Thanks!

> YH

	Hannes

Re: [PATCH -v3] x86: Make sure free_init_pages() free pages in boundary

[Yinghai Lu]

please check.

I keep the comments about we are safe to use PAGE_ALIGN() with the initrd_end.

Thanks

Yinghai



Subject: [PATCH -v4] x86: Make sure free_init_pages() free pages in boundary

When CONFIG_NO_BOOTMEM, it could use memory more effient, or more compact.

Example is:
Allocated new RAMDISK: 00ec2000 - 0248ce57
Move RAMDISK from 000000002ea04000 - 000000002ffcee56 to 00ec2000 - 0248ce56

The new RAMDISK's end is not page aligned.
Last page could use shared with other user.

When free_init_pages are called for initrd or .init, the page could be freed
could have chance to corrupt other data.

code segment in free_init_pages()
|        for (; addr < end; addr += PAGE_SIZE) {
|                ClearPageReserved(virt_to_page(addr));
|                init_page_count(virt_to_page(addr));
|                memset((void *)(addr & ~(PAGE_SIZE-1)),
|                        POISON_FREE_INITMEM, PAGE_SIZE);
|                free_page(addr);
|                totalram_pages++;
|        }
last half page could be used as one whole free page.

Try to make the boundaries to be page aligned.

-v2: make the original initramdisk to be aligned, according to Johannes.
     otherwise we have chance to lose one page.
     we still need to keep initrd_end not aligned, otherwise it could
     confuse decompresser.
-v3: change to WARN_ON instead according to Johannes.
-v4: use PAGE_ALIGN according to Johannes.
     We may fix that MARCO name later to PAGE_ALIGN_UP, and PAGE_ALIGN_DOWN
     Add comments about assuming ramdisk start is aligned
     in relocate_initrd(), change to re get ramdisk_image instead of save it
	to make diff smaller.
     Add WARN for wrong range according Johannes.

Reported-by: Stanislaw Gruszka <sgruszka@redhat.com>
Signed-off-by: Yinghai Lu <yinghai@kernel.org>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Tested-by: Stanislaw Gruszka <sgruszka@redhat.com>

---
 arch/x86/kernel/head32.c |    3 ++-
 arch/x86/kernel/head64.c |    3 ++-
 arch/x86/kernel/setup.c  |   19 ++++++++++---------
 arch/x86/mm/init.c       |   32 ++++++++++++++++++++++++++------
 4 files changed, 40 insertions(+), 17 deletions(-)

Index: linux-2.6/arch/x86/mm/init.c
===================================================================
--- linux-2.6.orig/arch/x86/mm/init.c
+++ linux-2.6/arch/x86/mm/init.c
@@ -331,11 +331,23 @@ int devmem_is_allowed(unsigned long page
 
 void free_init_pages(char *what, unsigned long begin, unsigned long end)
 {
-	unsigned long addr = begin;
+	unsigned long addr;
+	unsigned long begin_aligned, end_aligned;
 
-	if (addr >= end)
+	/* Make sure boundaries are page aligned */
+	begin_aligned = PAGE_ALIGN(begin);
+	end_aligned   = end & PAGE_MASK;
+
+	if (WARN(begin_aligned >= end_aligned, "wrong range: [%#lx, %#lx]\n", begin, end))
 		return;
 
+	if (WARN_ON(begin_aligned != begin || end_aligned != end)) {
+		begin = begin_aligned;
+		end   = end_aligned;
+	}
+
+	addr = begin;
+
 	/*
 	 * If debugging page accesses then do not free this memory but
 	 * mark them not present - any buggy init-section access will
@@ -343,7 +355,7 @@ void free_init_pages(char *what, unsigne
 	 */
 #ifdef CONFIG_DEBUG_PAGEALLOC
 	printk(KERN_INFO "debug: unmapping init memory %08lx..%08lx\n",
-		begin, PAGE_ALIGN(end));
+		begin, end);
 	set_memory_np(begin, (end - begin) >> PAGE_SHIFT);
 #else
 	/*
@@ -358,8 +370,7 @@ void free_init_pages(char *what, unsigne
 	for (; addr < end; addr += PAGE_SIZE) {
 		ClearPageReserved(virt_to_page(addr));
 		init_page_count(virt_to_page(addr));
-		memset((void *)(addr & ~(PAGE_SIZE-1)),
-			POISON_FREE_INITMEM, PAGE_SIZE);
+		memset((void *)addr, POISON_FREE_INITMEM, PAGE_SIZE);
 		free_page(addr);
 		totalram_pages++;
 	}
@@ -376,6 +387,15 @@ void free_initmem(void)
 #ifdef CONFIG_BLK_DEV_INITRD
 void free_initrd_mem(unsigned long start, unsigned long end)
 {
-	free_init_pages("initrd memory", start, end);
+	/*
+	 * end could be not aligned, and We can not align that,
+	 * decompresser could be confused by aligned initrd_end
+	 * We already reserve the end partial page before in
+	 *   - i386_start_kernel()
+	 *   - x86_64_start_kernel()
+	 *   - relocate_initrd()
+	 * So here We can do PAGE_ALIGN() safely to get partial page to be freed
+	 */
+	free_init_pages("initrd memory", start, PAGE_ALIGN(end));
 }
 #endif
Index: linux-2.6/arch/x86/kernel/head32.c
===================================================================
--- linux-2.6.orig/arch/x86/kernel/head32.c
+++ linux-2.6/arch/x86/kernel/head32.c
@@ -44,9 +44,10 @@ void __init i386_start_kernel(void)
 #ifdef CONFIG_BLK_DEV_INITRD
 	/* Reserve INITRD */
 	if (boot_params.hdr.type_of_loader && boot_params.hdr.ramdisk_image) {
+		/* Assume only end is not page aligned */
 		u64 ramdisk_image = boot_params.hdr.ramdisk_image;
 		u64 ramdisk_size  = boot_params.hdr.ramdisk_size;
-		u64 ramdisk_end   = ramdisk_image + ramdisk_size;
+		u64 ramdisk_end   = PAGE_ALIGN(ramdisk_image + ramdisk_size);
 		reserve_early(ramdisk_image, ramdisk_end, "RAMDISK");
 	}
 #endif
Index: linux-2.6/arch/x86/kernel/head64.c
===================================================================
--- linux-2.6.orig/arch/x86/kernel/head64.c
+++ linux-2.6/arch/x86/kernel/head64.c
@@ -103,9 +103,10 @@ void __init x86_64_start_reservations(ch
 #ifdef CONFIG_BLK_DEV_INITRD
 	/* Reserve INITRD */
 	if (boot_params.hdr.type_of_loader && boot_params.hdr.ramdisk_image) {
+		/* Assume only end is not page aligned */
 		unsigned long ramdisk_image = boot_params.hdr.ramdisk_image;
 		unsigned long ramdisk_size  = boot_params.hdr.ramdisk_size;
-		unsigned long ramdisk_end   = ramdisk_image + ramdisk_size;
+		unsigned long ramdisk_end   = PAGE_ALIGN(ramdisk_image + ramdisk_size);
 		reserve_early(ramdisk_image, ramdisk_end, "RAMDISK");
 	}
 #endif
Index: linux-2.6/arch/x86/kernel/setup.c
===================================================================
--- linux-2.6.orig/arch/x86/kernel/setup.c
+++ linux-2.6/arch/x86/kernel/setup.c
@@ -314,16 +314,17 @@ static void __init reserve_brk(void)
 #define MAX_MAP_CHUNK	(NR_FIX_BTMAPS << PAGE_SHIFT)
 static void __init relocate_initrd(void)
 {
-
+	/* Assume only end is not page aligned */
 	u64 ramdisk_image = boot_params.hdr.ramdisk_image;
 	u64 ramdisk_size  = boot_params.hdr.ramdisk_size;
+	u64 area_size     = PAGE_ALIGN(ramdisk_size);
 	u64 end_of_lowmem = max_low_pfn_mapped << PAGE_SHIFT;
 	u64 ramdisk_here;
 	unsigned long slop, clen, mapaddr;
 	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_e820_area(0, end_of_lowmem, area_size,
 					 PAGE_SIZE);
 
 	if (ramdisk_here == -1ULL)
@@ -332,7 +333,7 @@ static void __init relocate_initrd(void)
 
 	/* Note: this includes all the lowmem currently occupied by
 	   the initrd, we rely on that fact to keep the data intact. */
-	reserve_early(ramdisk_here, ramdisk_here + ramdisk_size,
+	reserve_early(ramdisk_here, ramdisk_here + area_size,
 			 "NEW RAMDISK");
 	initrd_start = ramdisk_here + PAGE_OFFSET;
 	initrd_end   = initrd_start + ramdisk_size;
@@ -348,13 +349,13 @@ static void __init relocate_initrd(void)
 		memcpy(q, p, clen);
 		q += clen;
 		ramdisk_image += clen;
-		ramdisk_size  -= clen;
+		area_size  -= clen;
 	}
 
 	/* Copy the highmem portion of the initrd */
-	while (ramdisk_size) {
+	while (area_size) {
 		slop = ramdisk_image & ~PAGE_MASK;
-		clen = ramdisk_size;
+		clen = area_size;
 		if (clen > MAX_MAP_CHUNK-slop)
 			clen = MAX_MAP_CHUNK-slop;
 		mapaddr = ramdisk_image & PAGE_MASK;
@@ -363,11 +364,10 @@ static void __init relocate_initrd(void)
 		early_iounmap(p, clen+slop);
 		q += clen;
 		ramdisk_image += clen;
-		ramdisk_size  -= clen;
+		area_size     -= clen;
 	}
 	/* high pages is not converted by early_res_to_bootmem */
 	ramdisk_image = boot_params.hdr.ramdisk_image;
-	ramdisk_size  = boot_params.hdr.ramdisk_size;
 	printk(KERN_INFO "Move RAMDISK from %016llx - %016llx to"
 		" %08llx - %08llx\n",
 		ramdisk_image, ramdisk_image + ramdisk_size - 1,
@@ -376,9 +376,10 @@ static void __init relocate_initrd(void)
 
 static void __init reserve_initrd(void)
 {
+	/* Assume only end is not page aligned */
 	u64 ramdisk_image = boot_params.hdr.ramdisk_image;
 	u64 ramdisk_size  = boot_params.hdr.ramdisk_size;
-	u64 ramdisk_end   = ramdisk_image + ramdisk_size;
+	u64 ramdisk_end   = PAGE_ALIGN(ramdisk_image + ramdisk_size);
 	u64 end_of_lowmem = max_low_pfn_mapped << PAGE_SHIFT;
 
 	if (!boot_params.hdr.type_of_loader ||

[patch v5] x86: page-alin initrd area size

[Johannes Weiner]

Initrd memory is freed late and page-wise, so allocate full pages and
not share the last one with somebody else.

Also add a warning and a fixup in free_init_pages() to catch unaligned
ranges more explicitely in the future.

Signed-off-by: Yinghai Lu <yinghai@kernel.org>
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
---
 arch/x86/kernel/head32.c |    8 +++++++-
 arch/x86/kernel/head64.c |    8 +++++++-
 arch/x86/kernel/setup.c  |   14 ++++++++++----
 arch/x86/mm/init.c       |   12 ++++++++----
 4 files changed, 32 insertions(+), 10 deletions(-)

On Sat, Mar 27, 2010 at 06:58:38PM -0700, Yinghai Lu wrote:
> please check.

I am really fed up with you replying to one point of an email and
skipping over five others.  So here is my version of the patch,
the maintainers can choose.

Differences:
  o only align the allocation area size, no need to also copy
    alignment bits in relocate_initrd()
  o keep the alignment fixup in free_init_pages() out of line and
    self-contained

diff --git a/arch/x86/kernel/head32.c b/arch/x86/kernel/head32.c
index adedeef..086392a 100644
--- a/arch/x86/kernel/head32.c
+++ b/arch/x86/kernel/head32.c
@@ -46,7 +46,13 @@ void __init i386_start_kernel(void)
 	if (boot_params.hdr.type_of_loader && boot_params.hdr.ramdisk_image) {
 		u64 ramdisk_image = boot_params.hdr.ramdisk_image;
 		u64 ramdisk_size  = boot_params.hdr.ramdisk_size;
-		u64 ramdisk_end   = ramdisk_image + ramdisk_size;
+		u64 ramdisk_end;
+		/*
+		 * Initrd memory is freed late and page-wise, so make
+		 * sure not to share a page with other users.  Assume
+		 * start is aligned.
+		 */
+		ramdisk_end = PAGE_ALIGN(ramdisk_image + ramdisk_size);
 		reserve_early(ramdisk_image, ramdisk_end, "RAMDISK");
 	}
 #endif
diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c
index b5a9896..b2c2321 100644
--- a/arch/x86/kernel/head64.c
+++ b/arch/x86/kernel/head64.c
@@ -105,7 +105,13 @@ void __init x86_64_start_reservations(char *real_mode_data)
 	if (boot_params.hdr.type_of_loader && boot_params.hdr.ramdisk_image) {
 		unsigned long ramdisk_image = boot_params.hdr.ramdisk_image;
 		unsigned long ramdisk_size  = boot_params.hdr.ramdisk_size;
-		unsigned long ramdisk_end   = ramdisk_image + ramdisk_size;
+		unsigned long ramdisk_end;
+		/*
+		 * Initrd memory is freed late and page-wise, so make
+		 * sure not to share a page with other users.  Assume
+		 * start is aligned.
+		 */
+		ramdisk_end = PAGE_ALIGN(ramdisk_image + ramdisk_size);
 		reserve_early(ramdisk_image, ramdisk_end, "RAMDISK");
 	}
 #endif
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 5d7ba1a..f5bde5f 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -318,12 +318,18 @@ static void __init relocate_initrd(void)
 	u64 ramdisk_image = boot_params.hdr.ramdisk_image;
 	u64 ramdisk_size  = boot_params.hdr.ramdisk_size;
 	u64 end_of_lowmem = max_low_pfn_mapped << PAGE_SHIFT;
-	u64 ramdisk_here;
+	u64 ramdisk_here, area_size;
 	unsigned long slop, clen, mapaddr;
 	char *p, *q;
 
+	/*	
+	 * Initrd memory is freed late and page-wise, so make sure not
+	 * to share a page with other users.  Assume start is aligned.
+	 */
+	area_size = PAGE_ALIGN(ramdisk_size);
+
 	/* We need to move the initrd down into lowmem */
-	ramdisk_here = find_e820_area(0, end_of_lowmem, ramdisk_size,
+	ramdisk_here = find_e820_area(0, end_of_lowmem, area_size,
 					 PAGE_SIZE);
 
 	if (ramdisk_here == -1ULL)
@@ -332,7 +338,7 @@ static void __init relocate_initrd(void)
 
 	/* Note: this includes all the lowmem currently occupied by
 	   the initrd, we rely on that fact to keep the data intact. */
-	reserve_early(ramdisk_here, ramdisk_here + ramdisk_size,
+	reserve_early(ramdisk_here, ramdisk_here + area_size,
 			 "NEW RAMDISK");
 	initrd_start = ramdisk_here + PAGE_OFFSET;
 	initrd_end   = initrd_start + ramdisk_size;
@@ -378,7 +384,7 @@ static void __init reserve_initrd(void)
 {
 	u64 ramdisk_image = boot_params.hdr.ramdisk_image;
 	u64 ramdisk_size  = boot_params.hdr.ramdisk_size;
-	u64 ramdisk_end   = ramdisk_image + ramdisk_size;
+	u64 ramdisk_end   = PAGE_ALIGN(ramdisk_image + ramdisk_size);
 	u64 end_of_lowmem = max_low_pfn_mapped << PAGE_SHIFT;
 
 	if (!boot_params.hdr.type_of_loader ||
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index e71c5cb..4b28d5e 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -333,6 +333,11 @@ void free_init_pages(char *what, unsigned long begin, unsigned long end)
 {
 	unsigned long addr = begin;
 
+	if (WARN_ON(addr & ~PAGE_MASK || end & ~PAGE_MASK)) {
+		addr = PAGE_ALIGN(addr);
+		end &= PAGE_MASK;
+	}
+
 	if (addr >= end)
 		return;
 
@@ -355,11 +360,10 @@ void free_init_pages(char *what, unsigned long begin, unsigned long end)
 
 	printk(KERN_INFO "Freeing %s: %luk freed\n", what, (end - begin) >> 10);
 
-	for (; addr < end; addr += PAGE_SIZE) {
+	for (; addr != end; addr += PAGE_SIZE) {
 		ClearPageReserved(virt_to_page(addr));
 		init_page_count(virt_to_page(addr));
-		memset((void *)(addr & ~(PAGE_SIZE-1)),
-			POISON_FREE_INITMEM, PAGE_SIZE);
+		memset((void *)addr, POISON_FREE_INITMEM, PAGE_SIZE);
 		free_page(addr);
 		totalram_pages++;
 	}
@@ -376,6 +380,6 @@ void free_initmem(void)
 #ifdef CONFIG_BLK_DEV_INITRD
 void free_initrd_mem(unsigned long start, unsigned long end)
 {
-	free_init_pages("initrd memory", start, end);
+	free_init_pages("initrd memory", start, PAGE_ALIGN(end));
 }
 #endif
-- 
1.7.0.2

Re: [patch v5] x86: page-alin initrd area size

[Yinghai Lu]

On 03/28/2010 04:35 PM, Johannes Weiner wrote:
> Initrd memory is freed late and page-wise, so allocate full pages and
> not share the last one with somebody else.
> 
> Also add a warning and a fixup in free_init_pages() to catch unaligned
> ranges more explicitely in the future.
> 
> Signed-off-by: Yinghai Lu <yinghai@kernel.org>
> Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
> ---
>  arch/x86/kernel/head32.c |    8 +++++++-
>  arch/x86/kernel/head64.c |    8 +++++++-
>  arch/x86/kernel/setup.c  |   14 ++++++++++----
>  arch/x86/mm/init.c       |   12 ++++++++----
>  4 files changed, 32 insertions(+), 10 deletions(-)
> 
> On Sat, Mar 27, 2010 at 06:58:38PM -0700, Yinghai Lu wrote:
>> please check.
> 
> I am really fed up with you replying to one point of an email and
> skipping over five others.  So here is my version of the patch,
> the maintainers can choose.

thought I prefer to put calculating out of if

> 
> Differences:
>   o only align the allocation area size, no need to also copy
>     alignment bits in relocate_initrd()
good point.
>   o keep the alignment fixup in free_init_pages() out of line and
>     self-contained

why calulate them two times ?

also prefer to put the fat comments in one place.

also we need to align begin too, so don't confuse set_memory_np() and set_memory_rw().

Thanks

Yinghai

Subject: [PATCH -v6] x86: Make sure free_init_pages() free pages in boundary

When CONFIG_NO_BOOTMEM, it could use memory more effient, or more compact.

Example is:
Allocated new RAMDISK: 00ec2000 - 0248ce57
Move RAMDISK from 000000002ea04000 - 000000002ffcee56 to 00ec2000 - 0248ce56

The new RAMDISK's end is not page aligned.
Last page could use shared with other user.

When free_init_pages are called for initrd or .init, the page could be freed
could have chance to corrupt other data.

code segment in free_init_pages()
|        for (; addr < end; addr += PAGE_SIZE) {
|                ClearPageReserved(virt_to_page(addr));
|                init_page_count(virt_to_page(addr));
|                memset((void *)(addr & ~(PAGE_SIZE-1)),
|                        POISON_FREE_INITMEM, PAGE_SIZE);
|                free_page(addr);
|                totalram_pages++;
|        }
last half page could be used as one whole free page.

Try to make the boundaries to be page aligned.

-v2: make the original initramdisk to be aligned, according to Johannes.
     otherwise we have chance to lose one page.
     we still need to keep initrd_end not aligned, otherwise it could
     confuse decompresser.
-v3: change to WARN_ON instead according to Johannes.
-v4: use PAGE_ALIGN according to Johannes.
     We may fix that MARCO name later to PAGE_ALIGN_UP, and PAGE_ALIGN_DOWN
     Add comments about assuming ramdisk start is aligned
     in relocate_initrd(), change to re get ramdisk_image instead of save it
	to make diff smaller.
     Add WARN for wrong range according Johannes.
-v6: remove one WARN
     We need align begin in free_init_pages()
     not copy more than ramdisk_size according to Johannes

Reported-by: Stanislaw Gruszka <sgruszka@redhat.com>
Signed-off-by: Yinghai Lu <yinghai@kernel.org>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Tested-by: Stanislaw Gruszka <sgruszka@redhat.com>

---
 arch/x86/kernel/head32.c |    3 ++-
 arch/x86/kernel/head64.c |    3 ++-
 arch/x86/kernel/setup.c  |   10 ++++++----
 arch/x86/mm/init.c       |   32 ++++++++++++++++++++++++++------
 4 files changed, 36 insertions(+), 12 deletions(-)

Index: linux-2.6/arch/x86/mm/init.c
===================================================================
--- linux-2.6.orig/arch/x86/mm/init.c
+++ linux-2.6/arch/x86/mm/init.c
@@ -331,11 +331,23 @@ int devmem_is_allowed(unsigned long page
 
 void free_init_pages(char *what, unsigned long begin, unsigned long end)
 {
-	unsigned long addr = begin;
+	unsigned long addr;
+	unsigned long begin_aligned, end_aligned;
 
-	if (addr >= end)
+	/* Make sure boundaries are page aligned */
+	begin_aligned = PAGE_ALIGN(begin);
+	end_aligned   = end & PAGE_MASK;
+
+	if (WARN_ON(begin_aligned != begin || end_aligned != end)) {
+		begin = begin_aligned;
+		end   = end_aligned;
+	}
+
+	if (begin >= end)
 		return;
 
+	addr = begin;
+
 	/*
 	 * If debugging page accesses then do not free this memory but
 	 * mark them not present - any buggy init-section access will
@@ -343,7 +355,7 @@ void free_init_pages(char *what, unsigne
 	 */
 #ifdef CONFIG_DEBUG_PAGEALLOC
 	printk(KERN_INFO "debug: unmapping init memory %08lx..%08lx\n",
-		begin, PAGE_ALIGN(end));
+		begin, end);
 	set_memory_np(begin, (end - begin) >> PAGE_SHIFT);
 #else
 	/*
@@ -358,8 +370,7 @@ void free_init_pages(char *what, unsigne
 	for (; addr < end; addr += PAGE_SIZE) {
 		ClearPageReserved(virt_to_page(addr));
 		init_page_count(virt_to_page(addr));
-		memset((void *)(addr & ~(PAGE_SIZE-1)),
-			POISON_FREE_INITMEM, PAGE_SIZE);
+		memset((void *)addr, POISON_FREE_INITMEM, PAGE_SIZE);
 		free_page(addr);
 		totalram_pages++;
 	}
@@ -376,6 +387,15 @@ void free_initmem(void)
 #ifdef CONFIG_BLK_DEV_INITRD
 void free_initrd_mem(unsigned long start, unsigned long end)
 {
-	free_init_pages("initrd memory", start, end);
+	/*
+	 * end could be not aligned, and We can not align that,
+	 * decompresser could be confused by aligned initrd_end
+	 * We already reserve the end partial page before in
+	 *   - i386_start_kernel()
+	 *   - x86_64_start_kernel()
+	 *   - relocate_initrd()
+	 * So here We can do PAGE_ALIGN() safely to get partial page to be freed
+	 */
+	free_init_pages("initrd memory", start, PAGE_ALIGN(end));
 }
 #endif
Index: linux-2.6/arch/x86/kernel/head32.c
===================================================================
--- linux-2.6.orig/arch/x86/kernel/head32.c
+++ linux-2.6/arch/x86/kernel/head32.c
@@ -44,9 +44,10 @@ void __init i386_start_kernel(void)
 #ifdef CONFIG_BLK_DEV_INITRD
 	/* Reserve INITRD */
 	if (boot_params.hdr.type_of_loader && boot_params.hdr.ramdisk_image) {
+		/* Assume only end is not page aligned */
 		u64 ramdisk_image = boot_params.hdr.ramdisk_image;
 		u64 ramdisk_size  = boot_params.hdr.ramdisk_size;
-		u64 ramdisk_end   = ramdisk_image + ramdisk_size;
+		u64 ramdisk_end   = PAGE_ALIGN(ramdisk_image + ramdisk_size);
 		reserve_early(ramdisk_image, ramdisk_end, "RAMDISK");
 	}
 #endif
Index: linux-2.6/arch/x86/kernel/head64.c
===================================================================
--- linux-2.6.orig/arch/x86/kernel/head64.c
+++ linux-2.6/arch/x86/kernel/head64.c
@@ -103,9 +103,10 @@ void __init x86_64_start_reservations(ch
 #ifdef CONFIG_BLK_DEV_INITRD
 	/* Reserve INITRD */
 	if (boot_params.hdr.type_of_loader && boot_params.hdr.ramdisk_image) {
+		/* Assume only end is not page aligned */
 		unsigned long ramdisk_image = boot_params.hdr.ramdisk_image;
 		unsigned long ramdisk_size  = boot_params.hdr.ramdisk_size;
-		unsigned long ramdisk_end   = ramdisk_image + ramdisk_size;
+		unsigned long ramdisk_end   = PAGE_ALIGN(ramdisk_image + ramdisk_size);
 		reserve_early(ramdisk_image, ramdisk_end, "RAMDISK");
 	}
 #endif
Index: linux-2.6/arch/x86/kernel/setup.c
===================================================================
--- linux-2.6.orig/arch/x86/kernel/setup.c
+++ linux-2.6/arch/x86/kernel/setup.c
@@ -314,16 +314,17 @@ static void __init reserve_brk(void)
 #define MAX_MAP_CHUNK	(NR_FIX_BTMAPS << PAGE_SHIFT)
 static void __init relocate_initrd(void)
 {
-
+	/* Assume only end is not page aligned */
 	u64 ramdisk_image = boot_params.hdr.ramdisk_image;
 	u64 ramdisk_size  = boot_params.hdr.ramdisk_size;
+	u64 area_size     = PAGE_ALIGN(ramdisk_size);
 	u64 end_of_lowmem = max_low_pfn_mapped << PAGE_SHIFT;
 	u64 ramdisk_here;
 	unsigned long slop, clen, mapaddr;
 	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_e820_area(0, end_of_lowmem, area_size,
 					 PAGE_SIZE);
 
 	if (ramdisk_here == -1ULL)
@@ -332,7 +333,7 @@ static void __init relocate_initrd(void)
 
 	/* Note: this includes all the lowmem currently occupied by
 	   the initrd, we rely on that fact to keep the data intact. */
-	reserve_early(ramdisk_here, ramdisk_here + ramdisk_size,
+	reserve_early(ramdisk_here, ramdisk_here + area_size,
 			 "NEW RAMDISK");
 	initrd_start = ramdisk_here + PAGE_OFFSET;
 	initrd_end   = initrd_start + ramdisk_size;
@@ -376,9 +377,10 @@ static void __init relocate_initrd(void)
 
 static void __init reserve_initrd(void)
 {
+	/* Assume only end is not page aligned */
 	u64 ramdisk_image = boot_params.hdr.ramdisk_image;
 	u64 ramdisk_size  = boot_params.hdr.ramdisk_size;
-	u64 ramdisk_end   = ramdisk_image + ramdisk_size;
+	u64 ramdisk_end   = PAGE_ALIGN(ramdisk_image + ramdisk_size);
 	u64 end_of_lowmem = max_low_pfn_mapped << PAGE_SHIFT;
 
 	if (!boot_params.hdr.type_of_loader ||