From bf61549a2d8e0326f5d6e4d1718883a7212d725f Mon Sep 17 00:00:00 2001
From: Tejun Heo <tj@kernel.org>
Date: Tue, 12 Jul 2011 09:58:05 +0200
Subject: x86: Fix memblock_x86_check_reserved_size() use in
 efi_reserve_boot_services()

The return value of memblock_x86_check_reserved_size() doesn't
indicate whether there's an overlapping reservatoin or not.  It
indicates whether the caller needs to iterate further to discover all
reserved portions of the specified area.

efi_reserve_boot_esrvices() wants to check whether the boot services
area overlaps with other reservations but incorrectly used
membloc_x86_check_reserved_size().  Use memblock_is_region_reserved()
instead.

Signed-off-by: Tejun Heo <tj@kernel.org>
Link: http://lkml.kernel.org/r/1310457490-3356-2-git-send-email-tj@kernel.org
Cc: Yinghai Lu <yinghai@kernel.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
---
 arch/x86/platform/efi/efi.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c
index 899e393d8e73..a4c322ca1a5d 100644
--- a/arch/x86/platform/efi/efi.c
+++ b/arch/x86/platform/efi/efi.c
@@ -325,8 +325,7 @@ void __init efi_reserve_boot_services(void)
 		if ((start+size >= virt_to_phys(_text)
 				&& start <= virt_to_phys(_end)) ||
 			!e820_all_mapped(start, start+size, E820_RAM) ||
-			memblock_x86_check_reserved_size(&start, &size,
-							1<<EFI_PAGE_SHIFT)) {
+			memblock_is_region_reserved(start, size)) {
 			/* Could not reserve, skip it */
 			md->num_pages = 0;
 			memblock_dbg(PFX "Could not reserve boot range "
-- 
cgit v1.2.3


From 53348f27168534561c0c814843bbf181314374f4 Mon Sep 17 00:00:00 2001
From: Tejun Heo <tj@kernel.org>
Date: Tue, 12 Jul 2011 09:58:06 +0200
Subject: bootmem: Fix __free_pages_bootmem() to use @order properly

a226f6c899 (FRV: Clean up bootmem allocator's page freeing algorithm)
separated out __free_pages_bootmem() from free_all_bootmem_core().
__free_pages_bootmem() takes @order argument but it assumes @order is
either 0 or ilog2(BITS_PER_LONG).  Note that all the current users
match that assumption and this doesn't cause actual problems.

Fix it by using 1 << order instead of BITS_PER_LONG.

Signed-off-by: Tejun Heo <tj@kernel.org>
Link: http://lkml.kernel.org/r/1310457490-3356-3-git-send-email-tj@kernel.org
Cc: David Howells <dhowells@redhat.com>
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
---
 mm/page_alloc.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 9119faae6e6a..b6da6ed818a8 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -705,10 +705,10 @@ void __meminit __free_pages_bootmem(struct page *page, unsigned int order)
 		int loop;
 
 		prefetchw(page);
-		for (loop = 0; loop < BITS_PER_LONG; loop++) {
+		for (loop = 0; loop < (1 << order); loop++) {
 			struct page *p = &page[loop];
 
-			if (loop + 1 < BITS_PER_LONG)
+			if (loop + 1 < (1 << order))
 				prefetchw(p + 1);
 			__ClearPageReserved(p);
 			set_page_count(p, 0);
-- 
cgit v1.2.3


From 15fb09722df32b7685be1cbcac198bb556ddaffe Mon Sep 17 00:00:00 2001
From: Tejun Heo <tj@kernel.org>
Date: Tue, 12 Jul 2011 09:58:07 +0200
Subject: memblock: Use MEMBLOCK_ALLOC_ACCESSIBLE instead of ANYWHERE in
 memblock_alloc_try_nid()

After node affine allocation fails, memblock_alloc_try_nid() calls
memblock_alloc_base() with @max_addr set to MEMBLOCK_ALLOC_ANYWHERE.
This is inconsistent with memblock_alloc() and what the function's
sole user - sparc/mm/init_64 - expects, although it doesn't make any
difference as sparc64 doesn't have highmem and ACCESSIBLE equals
ANYWHERE.

This patch makes memblock_alloc_try_nid() use ACCESSIBLE instead of
ANYWHERE.  This isn't complete as node affine allocation doesn't
consider memblock.current_limit.  It will be handled with future
changes.

This patch doesn't introduce any behavior difference.

Signed-off-by: Tejun Heo <tj@kernel.org>
Link: http://lkml.kernel.org/r/1310457490-3356-4-git-send-email-tj@kernel.org
Cc: Yinghai Lu <yinghai@kernel.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
---
 mm/memblock.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/mm/memblock.c b/mm/memblock.c
index a0562d1a6ad4..87e512dc8018 100644
--- a/mm/memblock.c
+++ b/mm/memblock.c
@@ -612,7 +612,7 @@ phys_addr_t __init memblock_alloc_try_nid(phys_addr_t size, phys_addr_t align, i
 
 	if (res)
 		return res;
-	return memblock_alloc_base(size, align, MEMBLOCK_ALLOC_ANYWHERE);
+	return memblock_alloc_base(size, align, MEMBLOCK_ALLOC_ACCESSIBLE);
 }
 
 
-- 
cgit v1.2.3


From 348968eb151e2569ad0ebe19b2f9c3c25b5c816a Mon Sep 17 00:00:00 2001
From: Tejun Heo <tj@kernel.org>
Date: Tue, 12 Jul 2011 09:58:08 +0200
Subject: memblock: Use round_up/down() instead of memblock_align_up/down()

Signed-off-by: Tejun Heo <tj@kernel.org>
Link: http://lkml.kernel.org/r/1310457490-3356-5-git-send-email-tj@kernel.org
Cc: Yinghai Lu <yinghai@kernel.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
---
 mm/memblock.c | 21 +++++----------------
 1 file changed, 5 insertions(+), 16 deletions(-)

diff --git a/mm/memblock.c b/mm/memblock.c
index 87e512dc8018..9882a88d4a10 100644
--- a/mm/memblock.c
+++ b/mm/memblock.c
@@ -41,17 +41,6 @@ static inline const char *memblock_type_name(struct memblock_type *type)
 /*
  * Address comparison utilities
  */
-
-static phys_addr_t __init_memblock memblock_align_down(phys_addr_t addr, phys_addr_t size)
-{
-	return addr & ~(size - 1);
-}
-
-static phys_addr_t __init_memblock memblock_align_up(phys_addr_t addr, phys_addr_t size)
-{
-	return (addr + (size - 1)) & ~(size - 1);
-}
-
 static unsigned long __init_memblock memblock_addrs_overlap(phys_addr_t base1, phys_addr_t size1,
 				       phys_addr_t base2, phys_addr_t size2)
 {
@@ -87,7 +76,7 @@ static phys_addr_t __init_memblock memblock_find_region(phys_addr_t start, phys_
 	if (end < size)
 		return MEMBLOCK_ERROR;
 
-	base = memblock_align_down((end - size), align);
+	base = round_down(end - size, align);
 
 	/* Prevent allocations returning 0 as it's also used to
 	 * indicate an allocation failure
@@ -102,7 +91,7 @@ static phys_addr_t __init_memblock memblock_find_region(phys_addr_t start, phys_
 		res_base = memblock.reserved.regions[j].base;
 		if (res_base < size)
 			break;
-		base = memblock_align_down(res_base - size, align);
+		base = round_down(res_base - size, align);
 	}
 
 	return MEMBLOCK_ERROR;
@@ -486,7 +475,7 @@ phys_addr_t __init __memblock_alloc_base(phys_addr_t size, phys_addr_t align, ph
 	/* We align the size to limit fragmentation. Without this, a lot of
 	 * small allocs quickly eat up the whole reserve array on sparc
 	 */
-	size = memblock_align_up(size, align);
+	size = round_up(size, align);
 
 	found = memblock_find_base(size, align, 0, max_addr);
 	if (found != MEMBLOCK_ERROR &&
@@ -562,7 +551,7 @@ static phys_addr_t __init memblock_alloc_nid_region(struct memblock_region *mp,
 	start = mp->base;
 	end = start + mp->size;
 
-	start = memblock_align_up(start, align);
+	start = round_up(start, align);
 	while (start < end) {
 		phys_addr_t this_end;
 		int this_nid;
@@ -590,7 +579,7 @@ phys_addr_t __init memblock_alloc_nid(phys_addr_t size, phys_addr_t align, int n
 	/* We align the size to limit fragmentation. Without this, a lot of
 	 * small allocs quickly eat up the whole reserve array on sparc
 	 */
-	size = memblock_align_up(size, align);
+	size = round_up(size, align);
 
 	/* We do a bottom-up search for a region with the right
 	 * nid since that's easier considering how memblock_nid_range()
-- 
cgit v1.2.3


From 1f5026a7e21e409c2b9dd54f6dfb9446511fb7c5 Mon Sep 17 00:00:00 2001
From: Tejun Heo <tj@kernel.org>
Date: Tue, 12 Jul 2011 09:58:09 +0200
Subject: memblock: Kill MEMBLOCK_ERROR

25818f0f28 (memblock: Make MEMBLOCK_ERROR be 0) thankfully made
MEMBLOCK_ERROR 0 and there already are codes which expect error return
to be 0.  There's no point in keeping MEMBLOCK_ERROR around.  End its
misery.

Signed-off-by: Tejun Heo <tj@kernel.org>
Link: http://lkml.kernel.org/r/1310457490-3356-6-git-send-email-tj@kernel.org
Cc: Yinghai Lu <yinghai@kernel.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
---
 arch/x86/kernel/aperture_64.c |  2 +-
 arch/x86/kernel/check.c       |  2 +-
 arch/x86/kernel/e820.c        |  2 +-
 arch/x86/kernel/setup.c       |  4 ++--
 arch/x86/kernel/trampoline.c  |  2 +-
 arch/x86/mm/init.c            |  2 +-
 arch/x86/mm/memblock.c        |  6 +++---
 arch/x86/mm/numa.c            |  6 +++---
 arch/x86/mm/numa_32.c         |  4 ++--
 arch/x86/mm/numa_emulation.c  |  2 +-
 include/linux/memblock.h      |  4 +---
 kernel/printk.c               |  2 +-
 mm/memblock.c                 | 21 ++++++++++-----------
 mm/nobootmem.c                |  2 +-
 mm/page_alloc.c               |  4 ++--
 15 files changed, 31 insertions(+), 34 deletions(-)

diff --git a/arch/x86/kernel/aperture_64.c b/arch/x86/kernel/aperture_64.c
index 3d2661ca6542..56363082bbdf 100644
--- a/arch/x86/kernel/aperture_64.c
+++ b/arch/x86/kernel/aperture_64.c
@@ -88,7 +88,7 @@ static u32 __init allocate_aperture(void)
 	 */
 	addr = memblock_find_in_range(GART_MIN_ADDR, GART_MAX_ADDR,
 				      aper_size, aper_size);
-	if (addr == MEMBLOCK_ERROR || addr + aper_size > GART_MAX_ADDR) {
+	if (!addr || addr + aper_size > GART_MAX_ADDR) {
 		printk(KERN_ERR
 			"Cannot allocate aperture memory hole (%lx,%uK)\n",
 				addr, aper_size>>10);
diff --git a/arch/x86/kernel/check.c b/arch/x86/kernel/check.c
index 452932d34730..95680fc4df5c 100644
--- a/arch/x86/kernel/check.c
+++ b/arch/x86/kernel/check.c
@@ -86,7 +86,7 @@ void __init setup_bios_corruption_check(void)
 		u64 size;
 		addr = memblock_x86_find_in_range_size(addr, &size, PAGE_SIZE);
 
-		if (addr == MEMBLOCK_ERROR)
+		if (!addr)
 			break;
 
 		if (addr >= corruption_check_size)
diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c
index 3e2ef8425316..0f9ff58d06d7 100644
--- a/arch/x86/kernel/e820.c
+++ b/arch/x86/kernel/e820.c
@@ -745,7 +745,7 @@ u64 __init early_reserve_e820(u64 startt, u64 sizet, u64 align)
 
 	for (start = startt; ; start += size) {
 		start = memblock_x86_find_in_range_size(start, &size, align);
-		if (start == MEMBLOCK_ERROR)
+		if (!start)
 			return 0;
 		if (size >= sizet)
 			break;
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index afaf38447ef5..31ffe20d5d27 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -331,7 +331,7 @@ static void __init relocate_initrd(void)
 	ramdisk_here = memblock_find_in_range(0, end_of_lowmem, area_size,
 					 PAGE_SIZE);
 
-	if (ramdisk_here == MEMBLOCK_ERROR)
+	if (!ramdisk_here)
 		panic("Cannot find place for new RAMDISK of size %lld\n",
 			 ramdisk_size);
 
@@ -554,7 +554,7 @@ static void __init reserve_crashkernel(void)
 		crash_base = memblock_find_in_range(alignment,
 			       CRASH_KERNEL_ADDR_MAX, crash_size, alignment);
 
-		if (crash_base == MEMBLOCK_ERROR) {
+		if (!crash_base) {
 			pr_info("crashkernel reservation failed - No suitable area found.\n");
 			return;
 		}
diff --git a/arch/x86/kernel/trampoline.c b/arch/x86/kernel/trampoline.c
index a91ae7709b49..a1f13ddb06e0 100644
--- a/arch/x86/kernel/trampoline.c
+++ b/arch/x86/kernel/trampoline.c
@@ -14,7 +14,7 @@ void __init setup_trampolines(void)
 
 	/* Has to be in very low memory so we can execute real-mode AP code. */
 	mem = memblock_find_in_range(0, 1<<20, size, PAGE_SIZE);
-	if (mem == MEMBLOCK_ERROR)
+	if (!mem)
 		panic("Cannot allocate trampoline\n");
 
 	x86_trampoline_base = __va(mem);
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index 30326443ab81..13cf05a61605 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -68,7 +68,7 @@ static void __init find_early_table_space(unsigned long end, int use_pse,
 #endif
 
 	base = memblock_find_in_range(start, good_end, tables, PAGE_SIZE);
-	if (base == MEMBLOCK_ERROR)
+	if (!base)
 		panic("Cannot find space for the kernel page tables");
 
 	pgt_buf_start = base >> PAGE_SHIFT;
diff --git a/arch/x86/mm/memblock.c b/arch/x86/mm/memblock.c
index 992da5ec5a64..e126117d1b03 100644
--- a/arch/x86/mm/memblock.c
+++ b/arch/x86/mm/memblock.c
@@ -66,7 +66,7 @@ u64 __init memblock_x86_find_in_range_size(u64 start, u64 *sizep, u64 align)
 			return addr;
 	}
 
-	return MEMBLOCK_ERROR;
+	return 0;
 }
 
 static __init struct range *find_range_array(int count)
@@ -78,7 +78,7 @@ static __init struct range *find_range_array(int count)
 	end = memblock.current_limit;
 
 	mem = memblock_find_in_range(0, end, size, sizeof(struct range));
-	if (mem == MEMBLOCK_ERROR)
+	if (!mem)
 		panic("can not find more space for range array");
 
 	/*
@@ -274,7 +274,7 @@ u64 __init memblock_x86_find_in_range_node(int nid, u64 start, u64 end, u64 size
 {
 	u64 addr;
 	addr = find_memory_core_early(nid, size, align, start, end);
-	if (addr != MEMBLOCK_ERROR)
+	if (addr)
 		return addr;
 
 	/* Fallback, should already have start end within node range */
diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c
index fbeaaf416610..fa1015de5cc0 100644
--- a/arch/x86/mm/numa.c
+++ b/arch/x86/mm/numa.c
@@ -226,10 +226,10 @@ static void __init setup_node_data(int nid, u64 start, u64 end)
 	} else {
 		nd_pa = memblock_x86_find_in_range_node(nid, nd_low, nd_high,
 						nd_size, SMP_CACHE_BYTES);
-		if (nd_pa == MEMBLOCK_ERROR)
+		if (!nd_pa)
 			nd_pa = memblock_find_in_range(nd_low, nd_high,
 						nd_size, SMP_CACHE_BYTES);
-		if (nd_pa == MEMBLOCK_ERROR) {
+		if (!nd_pa) {
 			pr_err("Cannot find %zu bytes in node %d\n",
 			       nd_size, nid);
 			return;
@@ -395,7 +395,7 @@ static int __init numa_alloc_distance(void)
 
 	phys = memblock_find_in_range(0, PFN_PHYS(max_pfn_mapped),
 				      size, PAGE_SIZE);
-	if (phys == MEMBLOCK_ERROR) {
+	if (!phys) {
 		pr_warning("NUMA: Warning: can't allocate distance table!\n");
 		/* don't retry until explicitly reset */
 		numa_distance = (void *)1LU;
diff --git a/arch/x86/mm/numa_32.c b/arch/x86/mm/numa_32.c
index 3adebe7e536a..58878b536ef2 100644
--- a/arch/x86/mm/numa_32.c
+++ b/arch/x86/mm/numa_32.c
@@ -199,7 +199,7 @@ void __init init_alloc_remap(int nid, u64 start, u64 end)
 
 	/* allocate node memory and the lowmem remap area */
 	node_pa = memblock_find_in_range(start, end, size, LARGE_PAGE_BYTES);
-	if (node_pa == MEMBLOCK_ERROR) {
+	if (!node_pa) {
 		pr_warning("remap_alloc: failed to allocate %lu bytes for node %d\n",
 			   size, nid);
 		return;
@@ -209,7 +209,7 @@ void __init init_alloc_remap(int nid, u64 start, u64 end)
 	remap_pa = memblock_find_in_range(min_low_pfn << PAGE_SHIFT,
 					  max_low_pfn << PAGE_SHIFT,
 					  size, LARGE_PAGE_BYTES);
-	if (remap_pa == MEMBLOCK_ERROR) {
+	if (!remap_pa) {
 		pr_warning("remap_alloc: failed to allocate %lu bytes remap area for node %d\n",
 			   size, nid);
 		memblock_x86_free_range(node_pa, node_pa + size);
diff --git a/arch/x86/mm/numa_emulation.c b/arch/x86/mm/numa_emulation.c
index d0ed086b6247..e3d471c20cdc 100644
--- a/arch/x86/mm/numa_emulation.c
+++ b/arch/x86/mm/numa_emulation.c
@@ -351,7 +351,7 @@ void __init numa_emulation(struct numa_meminfo *numa_meminfo, int numa_dist_cnt)
 
 		phys = memblock_find_in_range(0, PFN_PHYS(max_pfn_mapped),
 					      phys_size, PAGE_SIZE);
-		if (phys == MEMBLOCK_ERROR) {
+		if (!phys) {
 			pr_warning("NUMA: Warning: can't allocate copy of distance table, disabling emulation\n");
 			goto no_emu;
 		}
diff --git a/include/linux/memblock.h b/include/linux/memblock.h
index 7525e38c434d..d235ec5fe678 100644
--- a/include/linux/memblock.h
+++ b/include/linux/memblock.h
@@ -2,8 +2,6 @@
 #define _LINUX_MEMBLOCK_H
 #ifdef __KERNEL__
 
-#define MEMBLOCK_ERROR	0
-
 #ifdef CONFIG_HAVE_MEMBLOCK
 /*
  * Logical memory blocks.
@@ -164,7 +162,7 @@ static inline unsigned long memblock_region_reserved_end_pfn(const struct memblo
 #else
 static inline phys_addr_t memblock_alloc(phys_addr_t size, phys_addr_t align)
 {
-	return MEMBLOCK_ERROR;
+	return 0;
 }
 
 #endif /* CONFIG_HAVE_MEMBLOCK */
diff --git a/kernel/printk.c b/kernel/printk.c
index 35185392173f..b1d5a6174d65 100644
--- a/kernel/printk.c
+++ b/kernel/printk.c
@@ -199,7 +199,7 @@ void __init setup_log_buf(int early)
 		unsigned long mem;
 
 		mem = memblock_alloc(new_log_buf_len, PAGE_SIZE);
-		if (mem == MEMBLOCK_ERROR)
+		if (!mem)
 			return;
 		new_log_buf = __va(mem);
 	} else {
diff --git a/mm/memblock.c b/mm/memblock.c
index 9882a88d4a10..196993661346 100644
--- a/mm/memblock.c
+++ b/mm/memblock.c
@@ -74,7 +74,7 @@ static phys_addr_t __init_memblock memblock_find_region(phys_addr_t start, phys_
 
 	/* In case, huge size is requested */
 	if (end < size)
-		return MEMBLOCK_ERROR;
+		return 0;
 
 	base = round_down(end - size, align);
 
@@ -94,7 +94,7 @@ static phys_addr_t __init_memblock memblock_find_region(phys_addr_t start, phys_
 		base = round_down(res_base - size, align);
 	}
 
-	return MEMBLOCK_ERROR;
+	return 0;
 }
 
 static phys_addr_t __init_memblock memblock_find_base(phys_addr_t size,
@@ -126,10 +126,10 @@ static phys_addr_t __init_memblock memblock_find_base(phys_addr_t size,
 		if (bottom >= top)
 			continue;
 		found = memblock_find_region(bottom, top, size, align);
-		if (found != MEMBLOCK_ERROR)
+		if (found)
 			return found;
 	}
-	return MEMBLOCK_ERROR;
+	return 0;
 }
 
 /*
@@ -214,10 +214,10 @@ static int __init_memblock memblock_double_array(struct memblock_type *type)
 	 */
 	if (use_slab) {
 		new_array = kmalloc(new_size, GFP_KERNEL);
-		addr = new_array == NULL ? MEMBLOCK_ERROR : __pa(new_array);
+		addr = new_array ? __pa(new_array) : 0;
 	} else
 		addr = memblock_find_base(new_size, sizeof(phys_addr_t), 0, MEMBLOCK_ALLOC_ACCESSIBLE);
-	if (addr == MEMBLOCK_ERROR) {
+	if (!addr) {
 		pr_err("memblock: Failed to double %s array from %ld to %ld entries !\n",
 		       memblock_type_name(type), type->max, type->max * 2);
 		return -1;
@@ -478,8 +478,7 @@ phys_addr_t __init __memblock_alloc_base(phys_addr_t size, phys_addr_t align, ph
 	size = round_up(size, align);
 
 	found = memblock_find_base(size, align, 0, max_addr);
-	if (found != MEMBLOCK_ERROR &&
-	    !memblock_add_region(&memblock.reserved, found, size))
+	if (found && !memblock_add_region(&memblock.reserved, found, size))
 		return found;
 
 	return 0;
@@ -559,14 +558,14 @@ static phys_addr_t __init memblock_alloc_nid_region(struct memblock_region *mp,
 		this_end = memblock_nid_range(start, end, &this_nid);
 		if (this_nid == nid) {
 			phys_addr_t ret = memblock_find_region(start, this_end, size, align);
-			if (ret != MEMBLOCK_ERROR &&
+			if (ret &&
 			    !memblock_add_region(&memblock.reserved, ret, size))
 				return ret;
 		}
 		start = this_end;
 	}
 
-	return MEMBLOCK_ERROR;
+	return 0;
 }
 
 phys_addr_t __init memblock_alloc_nid(phys_addr_t size, phys_addr_t align, int nid)
@@ -588,7 +587,7 @@ phys_addr_t __init memblock_alloc_nid(phys_addr_t size, phys_addr_t align, int n
 	for (i = 0; i < mem->cnt; i++) {
 		phys_addr_t ret = memblock_alloc_nid_region(&mem->regions[i],
 					       size, align, nid);
-		if (ret != MEMBLOCK_ERROR)
+		if (ret)
 			return ret;
 	}
 
diff --git a/mm/nobootmem.c b/mm/nobootmem.c
index 6e93dc7f2586..5b0eb06ecb4e 100644
--- a/mm/nobootmem.c
+++ b/mm/nobootmem.c
@@ -43,7 +43,7 @@ static void * __init __alloc_memory_core_early(int nid, u64 size, u64 align,
 
 	addr = find_memory_core_early(nid, size, align, goal, limit);
 
-	if (addr == MEMBLOCK_ERROR)
+	if (!addr)
 		return NULL;
 
 	ptr = phys_to_virt(addr);
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index b6da6ed818a8..c7f0e5be4a31 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -3878,13 +3878,13 @@ u64 __init find_memory_core_early(int nid, u64 size, u64 align,
 
 		addr = memblock_find_in_range(final_start, final_end, size, align);
 
-		if (addr == MEMBLOCK_ERROR)
+		if (!addr)
 			continue;
 
 		return addr;
 	}
 
-	return MEMBLOCK_ERROR;
+	return 0;
 }
 #endif
 
-- 
cgit v1.2.3


From fc769a8e70a3348d5de49e5f69f6aff810157360 Mon Sep 17 00:00:00 2001
From: Tejun Heo <tj@kernel.org>
Date: Tue, 12 Jul 2011 09:58:10 +0200
Subject: memblock: Replace memblock_find_base() with memblock_find_in_range()

memblock_find_base() is a static function with two callers in
memblock.c and memblock_find_in_range() is a wrapper around it which
just changes the types and order of parameters.

Make memblock_find_in_range() take phys_addr_t instead of u64 for
consistency and replace memblock_find_base() with it.

Signed-off-by: Tejun Heo <tj@kernel.org>
Link: http://lkml.kernel.org/r/1310457490-3356-7-git-send-email-tj@kernel.org
Cc: Yinghai Lu <yinghai@kernel.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
---
 include/linux/memblock.h |  3 ++-
 mm/memblock.c            | 19 +++++++------------
 2 files changed, 9 insertions(+), 13 deletions(-)

diff --git a/include/linux/memblock.h b/include/linux/memblock.h
index d235ec5fe678..349688899cb0 100644
--- a/include/linux/memblock.h
+++ b/include/linux/memblock.h
@@ -46,7 +46,8 @@ extern int memblock_can_resize;
 #define memblock_dbg(fmt, ...) \
 	if (memblock_debug) printk(KERN_INFO pr_fmt(fmt), ##__VA_ARGS__)
 
-u64 memblock_find_in_range(u64 start, u64 end, u64 size, u64 align);
+phys_addr_t memblock_find_in_range(phys_addr_t start, phys_addr_t end,
+				   phys_addr_t size, phys_addr_t align);
 int memblock_free_reserved_regions(void);
 int memblock_reserve_reserved_regions(void);
 
diff --git a/mm/memblock.c b/mm/memblock.c
index 196993661346..0f9626f01b5e 100644
--- a/mm/memblock.c
+++ b/mm/memblock.c
@@ -97,8 +97,11 @@ static phys_addr_t __init_memblock memblock_find_region(phys_addr_t start, phys_
 	return 0;
 }
 
-static phys_addr_t __init_memblock memblock_find_base(phys_addr_t size,
-			phys_addr_t align, phys_addr_t start, phys_addr_t end)
+/*
+ * Find a free area with specified alignment in a specific range.
+ */
+phys_addr_t __init_memblock memblock_find_in_range(phys_addr_t start, phys_addr_t end,
+					phys_addr_t size, phys_addr_t align)
 {
 	long i;
 
@@ -132,14 +135,6 @@ static phys_addr_t __init_memblock memblock_find_base(phys_addr_t size,
 	return 0;
 }
 
-/*
- * Find a free area with specified alignment in a specific range.
- */
-u64 __init_memblock memblock_find_in_range(u64 start, u64 end, u64 size, u64 align)
-{
-	return memblock_find_base(size, align, start, end);
-}
-
 /*
  * Free memblock.reserved.regions
  */
@@ -216,7 +211,7 @@ static int __init_memblock memblock_double_array(struct memblock_type *type)
 		new_array = kmalloc(new_size, GFP_KERNEL);
 		addr = new_array ? __pa(new_array) : 0;
 	} else
-		addr = memblock_find_base(new_size, sizeof(phys_addr_t), 0, MEMBLOCK_ALLOC_ACCESSIBLE);
+		addr = memblock_find_in_range(0, MEMBLOCK_ALLOC_ACCESSIBLE, new_size, sizeof(phys_addr_t));
 	if (!addr) {
 		pr_err("memblock: Failed to double %s array from %ld to %ld entries !\n",
 		       memblock_type_name(type), type->max, type->max * 2);
@@ -477,7 +472,7 @@ phys_addr_t __init __memblock_alloc_base(phys_addr_t size, phys_addr_t align, ph
 	 */
 	size = round_up(size, align);
 
-	found = memblock_find_base(size, align, 0, max_addr);
+	found = memblock_find_in_range(0, max_addr, size, align);
 	if (found && !memblock_add_region(&memblock.reserved, found, size))
 		return found;
 
-- 
cgit v1.2.3


From 5dfe8660a3d7f1ee1265c3536433ee53da3f98a3 Mon Sep 17 00:00:00 2001
From: Tejun Heo <tj@kernel.org>
Date: Thu, 14 Jul 2011 09:46:10 +0200
Subject: bootmem: Replace work_with_active_regions() with
 for_each_mem_pfn_range()

Callback based iteration is cumbersome and much less useful than
for_each_*() iterator.  This patch implements for_each_mem_pfn_range()
which replaces work_with_active_regions().  All the current users of
work_with_active_regions() are converted.

This simplifies walking over early_node_map and will allow converting
internal logics in page_alloc to use iterator instead of walking
early_node_map directly, which in turn will enable moving node
information to memblock.

powerpc change is only compile tested.

Signed-off-by: Tejun Heo <tj@kernel.org>
Link: http://lkml.kernel.org/r/20110714074610.GD3455@htj.dyndns.org
Cc: Yinghai Lu <yinghai@kernel.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
---
 arch/powerpc/mm/numa.c    | 50 ++++++++++++++---------------------------------
 arch/x86/mm/memblock.c    | 23 ++++------------------
 drivers/pci/intel-iommu.c | 24 +++++++++--------------
 include/linux/mm.h        | 22 +++++++++++++++++++--
 mm/page_alloc.c           | 40 +++++++++++++++++++++++++------------
 5 files changed, 76 insertions(+), 83 deletions(-)

diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c
index 2164006fe170..6f06ea53bca2 100644
--- a/arch/powerpc/mm/numa.c
+++ b/arch/powerpc/mm/numa.c
@@ -127,45 +127,25 @@ static int __cpuinit fake_numa_create_new_node(unsigned long end_pfn,
 }
 
 /*
- * get_active_region_work_fn - A helper function for get_node_active_region
- *	Returns datax set to the start_pfn and end_pfn if they contain
- *	the initial value of datax->start_pfn between them
- * @start_pfn: start page(inclusive) of region to check
- * @end_pfn: end page(exclusive) of region to check
- * @datax: comes in with ->start_pfn set to value to search for and
- *	goes out with active range if it contains it
- * Returns 1 if search value is in range else 0
- */
-static int __init get_active_region_work_fn(unsigned long start_pfn,
-					unsigned long end_pfn, void *datax)
-{
-	struct node_active_region *data;
-	data = (struct node_active_region *)datax;
-
-	if (start_pfn <= data->start_pfn && end_pfn > data->start_pfn) {
-		data->start_pfn = start_pfn;
-		data->end_pfn = end_pfn;
-		return 1;
-	}
-	return 0;
-
-}
-
-/*
- * get_node_active_region - Return active region containing start_pfn
+ * get_node_active_region - Return active region containing pfn
  * Active range returned is empty if none found.
- * @start_pfn: The page to return the region for.
- * @node_ar: Returned set to the active region containing start_pfn
+ * @pfn: The page to return the region for
+ * @node_ar: Returned set to the active region containing @pfn
  */
-static void __init get_node_active_region(unsigned long start_pfn,
-		       struct node_active_region *node_ar)
+static void __init get_node_active_region(unsigned long pfn,
+					  struct node_active_region *node_ar)
 {
-	int nid = early_pfn_to_nid(start_pfn);
+	unsigned long start_pfn, end_pfn;
+	int i, nid;
 
-	node_ar->nid = nid;
-	node_ar->start_pfn = start_pfn;
-	node_ar->end_pfn = start_pfn;
-	work_with_active_regions(nid, get_active_region_work_fn, node_ar);
+	for_each_mem_pfn_range(i, MAX_NUMNODES, &start_pfn, &end_pfn, &nid) {
+		if (pfn >= start_pfn && pfn < end_pfn) {
+			node_ar->nid = nid;
+			node_ar->start_pfn = start_pfn;
+			node_ar->end_pfn = end_pfn;
+			break;
+		}
+	}
 }
 
 static void map_cpu_to_node(int cpu, int node)
diff --git a/arch/x86/mm/memblock.c b/arch/x86/mm/memblock.c
index e126117d1b03..da0d5c84586e 100644
--- a/arch/x86/mm/memblock.c
+++ b/arch/x86/mm/memblock.c
@@ -115,28 +115,13 @@ static void __init memblock_x86_subtract_reserved(struct range *range, int az)
 	memblock_reserve_reserved_regions();
 }
 
-struct count_data {
-	int nr;
-};
-
-static int __init count_work_fn(unsigned long start_pfn,
-				unsigned long end_pfn, void *datax)
-{
-	struct count_data *data = datax;
-
-	data->nr++;
-
-	return 0;
-}
-
 static int __init count_early_node_map(int nodeid)
 {
-	struct count_data data;
-
-	data.nr = 0;
-	work_with_active_regions(nodeid, count_work_fn, &data);
+	int i, cnt = 0;
 
-	return data.nr;
+	for_each_mem_pfn_range(i, nodeid, NULL, NULL, NULL)
+		cnt++;
+	return cnt;
 }
 
 int __init __get_free_all_memory_range(struct range **rangep, int nodeid,
diff --git a/drivers/pci/intel-iommu.c b/drivers/pci/intel-iommu.c
index f02c34d26d1b..8ec352077e1a 100644
--- a/drivers/pci/intel-iommu.c
+++ b/drivers/pci/intel-iommu.c
@@ -2178,18 +2178,6 @@ static inline void iommu_prepare_isa(void)
 
 static int md_domain_init(struct dmar_domain *domain, int guest_width);
 
-static int __init si_domain_work_fn(unsigned long start_pfn,
-				    unsigned long end_pfn, void *datax)
-{
-	int *ret = datax;
-
-	*ret = iommu_domain_identity_map(si_domain,
-					 (uint64_t)start_pfn << PAGE_SHIFT,
-					 (uint64_t)end_pfn << PAGE_SHIFT);
-	return *ret;
-
-}
-
 static int __init si_domain_init(int hw)
 {
 	struct dmar_drhd_unit *drhd;
@@ -2221,9 +2209,15 @@ static int __init si_domain_init(int hw)
 		return 0;
 
 	for_each_online_node(nid) {
-		work_with_active_regions(nid, si_domain_work_fn, &ret);
-		if (ret)
-			return ret;
+		unsigned long start_pfn, end_pfn;
+		int i;
+
+		for_each_mem_pfn_range(i, nid, &start_pfn, &end_pfn, NULL) {
+			ret = iommu_domain_identity_map(si_domain,
+					PFN_PHYS(start_pfn), PFN_PHYS(end_pfn));
+			if (ret)
+				return ret;
+		}
 	}
 
 	return 0;
diff --git a/include/linux/mm.h b/include/linux/mm.h
index c70a326b8f26..57e4c9ffdff8 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1327,9 +1327,27 @@ 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);
-typedef int (*work_fn_t)(unsigned long, unsigned long, void *);
-extern void work_with_active_regions(int nid, work_fn_t work_fn, void *data);
 extern void sparse_memory_present_with_active_regions(int nid);
+
+extern void __next_mem_pfn_range(int *idx, int nid,
+				 unsigned long *out_start_pfn,
+				 unsigned long *out_end_pfn, int *out_nid);
+
+/**
+ * for_each_mem_pfn_range - early memory pfn range iterator
+ * @i: an integer used as loop variable
+ * @nid: node selector, %MAX_NUMNODES for all nodes
+ * @p_start: ptr to ulong for start pfn of the range, can be %NULL
+ * @p_end: ptr to ulong for end pfn of the range, can be %NULL
+ * @p_nid: ptr to int for nid of the range, can be %NULL
+ *
+ * Walks over configured memory ranges.  Available after early_node_map is
+ * populated.
+ */
+#define for_each_mem_pfn_range(i, nid, p_start, p_end, p_nid)		\
+	for (i = -1, __next_mem_pfn_range(&i, nid, p_start, p_end, p_nid); \
+	     i >= 0; __next_mem_pfn_range(&i, nid, p_start, p_end, p_nid))
+
 #endif /* CONFIG_ARCH_POPULATES_NODE_MAP */
 
 #if !defined(CONFIG_ARCH_POPULATES_NODE_MAP) && \
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index c7f0e5be4a31..69fffabf61b7 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -3903,18 +3903,6 @@ int __init add_from_early_node_map(struct range *range, int az,
 	return nr_range;
 }
 
-void __init work_with_active_regions(int nid, work_fn_t work_fn, void *data)
-{
-	int i;
-	int ret;
-
-	for_each_active_range_index_in_nid(i, nid) {
-		ret = work_fn(early_node_map[i].start_pfn,
-			      early_node_map[i].end_pfn, data);
-		if (ret)
-			break;
-	}
-}
 /**
  * sparse_memory_present_with_active_regions - Call memory_present for each active range
  * @nid: The node to call memory_present for. If MAX_NUMNODES, all nodes will be used.
@@ -4421,6 +4409,34 @@ static inline void setup_nr_node_ids(void)
 }
 #endif
 
+/*
+ * Common iterator interface used to define for_each_mem_pfn_range().
+ */
+void __meminit __next_mem_pfn_range(int *idx, int nid,
+				    unsigned long *out_start_pfn,
+				    unsigned long *out_end_pfn, int *out_nid)
+{
+	struct node_active_region *r = NULL;
+
+	while (++*idx < nr_nodemap_entries) {
+		if (nid == MAX_NUMNODES || nid == early_node_map[*idx].nid) {
+			r = &early_node_map[*idx];
+			break;
+		}
+	}
+	if (!r) {
+		*idx = -1;
+		return;
+	}
+
+	if (out_start_pfn)
+		*out_start_pfn = r->start_pfn;
+	if (out_end_pfn)
+		*out_end_pfn = r->end_pfn;
+	if (out_nid)
+		*out_nid = r->nid;
+}
+
 /**
  * add_active_range - Register a range of PFNs backed by physical memory
  * @nid: The node ID the range resides on
-- 
cgit v1.2.3


From 96e907d1360240d1958fe8ce3a3ac640733330d4 Mon Sep 17 00:00:00 2001
From: Tejun Heo <tj@kernel.org>
Date: Tue, 12 Jul 2011 10:46:29 +0200
Subject: bootmem: Reimplement __absent_pages_in_range() using
 for_each_mem_pfn_range()

__absent_pages_in_range() was needlessly complex.  Reimplement it
using for_each_mem_pfn_range().

Also, update zone_absent_pages_in_node() such that it doesn't call
__absent_pages_in_range() with @zone_start_pfn which is larger than
@zone_end_pfn.

Signed-off-by: Tejun Heo <tj@kernel.org>
Link: http://lkml.kernel.org/r/1310460395-30913-3-git-send-email-tj@kernel.org
Cc: Yinghai Lu <yinghai@kernel.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
---
 mm/page_alloc.c | 54 ++++++++++++------------------------------------------
 1 file changed, 12 insertions(+), 42 deletions(-)

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 69fffabf61b7..3092a97268d1 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -4044,46 +4044,16 @@ unsigned long __meminit __absent_pages_in_range(int nid,
 				unsigned long range_start_pfn,
 				unsigned long range_end_pfn)
 {
-	int i = 0;
-	unsigned long prev_end_pfn = 0, hole_pages = 0;
-	unsigned long start_pfn;
-
-	/* Find the end_pfn of the first active range of pfns in the node */
-	i = first_active_region_index_in_nid(nid);
-	if (i == -1)
-		return 0;
-
-	prev_end_pfn = min(early_node_map[i].start_pfn, range_end_pfn);
-
-	/* Account for ranges before physical memory on this node */
-	if (early_node_map[i].start_pfn > range_start_pfn)
-		hole_pages = prev_end_pfn - range_start_pfn;
-
-	/* Find all holes for the zone within the node */
-	for (; i != -1; i = next_active_region_index_in_nid(i, nid)) {
-
-		/* No need to continue if prev_end_pfn is outside the zone */
-		if (prev_end_pfn >= range_end_pfn)
-			break;
-
-		/* Make sure the end of the zone is not within the hole */
-		start_pfn = min(early_node_map[i].start_pfn, range_end_pfn);
-		prev_end_pfn = max(prev_end_pfn, range_start_pfn);
+	unsigned long nr_absent = range_end_pfn - range_start_pfn;
+	unsigned long start_pfn, end_pfn;
+	int i;
 
-		/* Update the hole size cound and move on */
-		if (start_pfn > range_start_pfn) {
-			BUG_ON(prev_end_pfn > start_pfn);
-			hole_pages += start_pfn - prev_end_pfn;
-		}
-		prev_end_pfn = early_node_map[i].end_pfn;
+	for_each_mem_pfn_range(i, nid, &start_pfn, &end_pfn, NULL) {
+		start_pfn = clamp(start_pfn, range_start_pfn, range_end_pfn);
+		end_pfn = clamp(end_pfn, range_start_pfn, range_end_pfn);
+		nr_absent -= end_pfn - start_pfn;
 	}
-
-	/* Account for ranges past physical memory on this node */
-	if (range_end_pfn > prev_end_pfn)
-		hole_pages += range_end_pfn -
-				max(range_start_pfn, prev_end_pfn);
-
-	return hole_pages;
+	return nr_absent;
 }
 
 /**
@@ -4104,14 +4074,14 @@ static unsigned long __meminit zone_absent_pages_in_node(int nid,
 					unsigned long zone_type,
 					unsigned long *ignored)
 {
+	unsigned long zone_low = arch_zone_lowest_possible_pfn[zone_type];
+	unsigned long zone_high = arch_zone_highest_possible_pfn[zone_type];
 	unsigned long node_start_pfn, node_end_pfn;
 	unsigned long zone_start_pfn, zone_end_pfn;
 
 	get_pfn_range_for_nid(nid, &node_start_pfn, &node_end_pfn);
-	zone_start_pfn = max(arch_zone_lowest_possible_pfn[zone_type],
-							node_start_pfn);
-	zone_end_pfn = min(arch_zone_highest_possible_pfn[zone_type],
-							node_end_pfn);
+	zone_start_pfn = clamp(node_start_pfn, zone_low, zone_high);
+	zone_end_pfn = clamp(node_end_pfn, zone_low, zone_high);
 
 	adjust_zone_range_for_zone_movable(nid, zone_type,
 			node_start_pfn, node_end_pfn,
-- 
cgit v1.2.3


From c13291a536b835b2ab278ab201f2cb1ce22f2785 Mon Sep 17 00:00:00 2001
From: Tejun Heo <tj@kernel.org>
Date: Tue, 12 Jul 2011 10:46:30 +0200
Subject: bootmem: Use for_each_mem_pfn_range() in page_alloc.c

The previous patch added for_each_mem_pfn_range() which is more
versatile than for_each_active_range_index_in_nid().  This patch
replaces for_each_active_range_index_in_nid() and open coded
early_node_map[] walks with for_each_mem_pfn_range().

All conversions in this patch are straight-forward and shouldn't cause
any functional difference.  After the conversions,
for_each_active_range_index_in_nid() doesn't have any user left and is
removed.

Signed-off-by: Tejun Heo <tj@kernel.org>
Link: http://lkml.kernel.org/r/1310460395-30913-4-git-send-email-tj@kernel.org
Cc: Yinghai Lu <yinghai@kernel.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
---
 mm/page_alloc.c | 165 +++++++++++++++++++-------------------------------------
 1 file changed, 56 insertions(+), 109 deletions(-)

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 3092a97268d1..902f03a4fd6b 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -3711,34 +3711,6 @@ __meminit int init_currently_empty_zone(struct zone *zone,
 }
 
 #ifdef CONFIG_ARCH_POPULATES_NODE_MAP
-/*
- * Basic iterator support. Return the first range of PFNs for a node
- * Note: nid == MAX_NUMNODES returns first region regardless of node
- */
-static int __meminit first_active_region_index_in_nid(int nid)
-{
-	int i;
-
-	for (i = 0; i < nr_nodemap_entries; i++)
-		if (nid == MAX_NUMNODES || early_node_map[i].nid == nid)
-			return i;
-
-	return -1;
-}
-
-/*
- * Basic iterator support. Return the next active range of PFNs for a node
- * Note: nid == MAX_NUMNODES returns next region regardless of node
- */
-static int __meminit next_active_region_index_in_nid(int index, int nid)
-{
-	for (index = index + 1; index < nr_nodemap_entries; index++)
-		if (nid == MAX_NUMNODES || early_node_map[index].nid == nid)
-			return index;
-
-	return -1;
-}
-
 #ifndef CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID
 /*
  * Required by SPARSEMEM. Given a PFN, return what node the PFN is on.
@@ -3748,15 +3720,12 @@ static int __meminit next_active_region_index_in_nid(int index, int nid)
  */
 int __meminit __early_pfn_to_nid(unsigned long pfn)
 {
-	int i;
-
-	for (i = 0; i < nr_nodemap_entries; i++) {
-		unsigned long start_pfn = early_node_map[i].start_pfn;
-		unsigned long end_pfn = early_node_map[i].end_pfn;
+	unsigned long start_pfn, end_pfn;
+	int i, nid;
 
+	for_each_mem_pfn_range(i, MAX_NUMNODES, &start_pfn, &end_pfn, &nid)
 		if (start_pfn <= pfn && pfn < end_pfn)
-			return early_node_map[i].nid;
-	}
+			return nid;
 	/* This is a memory hole */
 	return -1;
 }
@@ -3785,11 +3754,6 @@ bool __meminit early_pfn_in_nid(unsigned long pfn, int node)
 }
 #endif
 
-/* Basic iterator support to walk early_node_map[] */
-#define for_each_active_range_index_in_nid(i, nid) \
-	for (i = first_active_region_index_in_nid(nid); i != -1; \
-				i = next_active_region_index_in_nid(i, nid))
-
 /**
  * free_bootmem_with_active_regions - Call free_bootmem_node for each active range
  * @nid: The node to free memory on. If MAX_NUMNODES, all nodes are freed.
@@ -3799,25 +3763,19 @@ bool __meminit early_pfn_in_nid(unsigned long pfn, int node)
  * add_active_ranges() contain no holes and may be freed, this
  * this function may be used instead of calling free_bootmem() manually.
  */
-void __init free_bootmem_with_active_regions(int nid,
-						unsigned long max_low_pfn)
+void __init free_bootmem_with_active_regions(int nid, unsigned long max_low_pfn)
 {
-	int i;
-
-	for_each_active_range_index_in_nid(i, nid) {
-		unsigned long size_pages = 0;
-		unsigned long end_pfn = early_node_map[i].end_pfn;
-
-		if (early_node_map[i].start_pfn >= max_low_pfn)
-			continue;
+	unsigned long start_pfn, end_pfn;
+	int i, this_nid;
 
-		if (end_pfn > max_low_pfn)
-			end_pfn = max_low_pfn;
+	for_each_mem_pfn_range(i, nid, &start_pfn, &end_pfn, &this_nid) {
+		start_pfn = min(start_pfn, max_low_pfn);
+		end_pfn = min(end_pfn, max_low_pfn);
 
-		size_pages = end_pfn - early_node_map[i].start_pfn;
-		free_bootmem_node(NODE_DATA(early_node_map[i].nid),
-				PFN_PHYS(early_node_map[i].start_pfn),
-				size_pages << PAGE_SHIFT);
+		if (start_pfn < end_pfn)
+			free_bootmem_node(NODE_DATA(this_nid),
+					  PFN_PHYS(start_pfn),
+					  (end_pfn - start_pfn) << PAGE_SHIFT);
 	}
 }
 
@@ -3891,15 +3849,12 @@ u64 __init find_memory_core_early(int nid, u64 size, u64 align,
 int __init add_from_early_node_map(struct range *range, int az,
 				   int nr_range, int nid)
 {
+	unsigned long start_pfn, end_pfn;
 	int i;
-	u64 start, end;
 
 	/* need to go over early_node_map to find out good range for node */
-	for_each_active_range_index_in_nid(i, nid) {
-		start = early_node_map[i].start_pfn;
-		end = early_node_map[i].end_pfn;
-		nr_range = add_range(range, az, nr_range, start, end);
-	}
+	for_each_mem_pfn_range(i, nid, &start_pfn, &end_pfn, NULL)
+		nr_range = add_range(range, az, nr_range, start_pfn, end_pfn);
 	return nr_range;
 }
 
@@ -3913,12 +3868,11 @@ int __init add_from_early_node_map(struct range *range, int az,
  */
 void __init sparse_memory_present_with_active_regions(int nid)
 {
-	int i;
+	unsigned long start_pfn, end_pfn;
+	int i, this_nid;
 
-	for_each_active_range_index_in_nid(i, nid)
-		memory_present(early_node_map[i].nid,
-				early_node_map[i].start_pfn,
-				early_node_map[i].end_pfn);
+	for_each_mem_pfn_range(i, nid, &start_pfn, &end_pfn, &this_nid)
+		memory_present(this_nid, start_pfn, end_pfn);
 }
 
 /**
@@ -3935,13 +3889,15 @@ void __init sparse_memory_present_with_active_regions(int nid)
 void __meminit get_pfn_range_for_nid(unsigned int nid,
 			unsigned long *start_pfn, unsigned long *end_pfn)
 {
+	unsigned long this_start_pfn, this_end_pfn;
 	int i;
+
 	*start_pfn = -1UL;
 	*end_pfn = 0;
 
-	for_each_active_range_index_in_nid(i, nid) {
-		*start_pfn = min(*start_pfn, early_node_map[i].start_pfn);
-		*end_pfn = max(*end_pfn, early_node_map[i].end_pfn);
+	for_each_mem_pfn_range(i, nid, &this_start_pfn, &this_end_pfn, NULL) {
+		*start_pfn = min(*start_pfn, this_start_pfn);
+		*end_pfn = max(*end_pfn, this_end_pfn);
 	}
 
 	if (*start_pfn == -1UL)
@@ -4484,6 +4440,7 @@ void __init add_active_range(unsigned int nid, unsigned long start_pfn,
 void __init remove_active_range(unsigned int nid, unsigned long start_pfn,
 				unsigned long end_pfn)
 {
+	unsigned long this_start_pfn, this_end_pfn;
 	int i, j;
 	int removed = 0;
 
@@ -4491,26 +4448,22 @@ void __init remove_active_range(unsigned int nid, unsigned long start_pfn,
 			  nid, start_pfn, end_pfn);
 
 	/* Find the old active region end and shrink */
-	for_each_active_range_index_in_nid(i, nid) {
-		if (early_node_map[i].start_pfn >= start_pfn &&
-		    early_node_map[i].end_pfn <= end_pfn) {
+	for_each_mem_pfn_range(i, nid, &this_start_pfn, &this_end_pfn, NULL) {
+		if (this_start_pfn >= start_pfn && this_end_pfn <= end_pfn) {
 			/* clear it */
 			early_node_map[i].start_pfn = 0;
 			early_node_map[i].end_pfn = 0;
 			removed = 1;
 			continue;
 		}
-		if (early_node_map[i].start_pfn < start_pfn &&
-		    early_node_map[i].end_pfn > start_pfn) {
-			unsigned long temp_end_pfn = early_node_map[i].end_pfn;
+		if (this_start_pfn < start_pfn && this_end_pfn > start_pfn) {
 			early_node_map[i].end_pfn = start_pfn;
-			if (temp_end_pfn > end_pfn)
-				add_active_range(nid, end_pfn, temp_end_pfn);
+			if (this_end_pfn > end_pfn)
+				add_active_range(nid, end_pfn, this_end_pfn);
 			continue;
 		}
-		if (early_node_map[i].start_pfn >= start_pfn &&
-		    early_node_map[i].end_pfn > end_pfn &&
-		    early_node_map[i].start_pfn < end_pfn) {
+		if (this_start_pfn >= start_pfn && this_end_pfn > end_pfn &&
+		    this_start_pfn < end_pfn) {
 			early_node_map[i].start_pfn = end_pfn;
 			continue;
 		}
@@ -4593,15 +4546,11 @@ void __init sort_node_map(void)
 unsigned long __init node_map_pfn_alignment(void)
 {
 	unsigned long accl_mask = 0, last_end = 0;
+	unsigned long start, end, mask;
 	int last_nid = -1;
-	int i;
-
-	for_each_active_range_index_in_nid(i, MAX_NUMNODES) {
-		int nid = early_node_map[i].nid;
-		unsigned long start = early_node_map[i].start_pfn;
-		unsigned long end = early_node_map[i].end_pfn;
-		unsigned long mask;
+	int i, nid;
 
+	for_each_mem_pfn_range(i, MAX_NUMNODES, &start, &end, &nid) {
 		if (!start || last_nid < 0 || last_nid == nid) {
 			last_nid = nid;
 			last_end = end;
@@ -4628,12 +4577,12 @@ unsigned long __init node_map_pfn_alignment(void)
 /* Find the lowest pfn for a node */
 static unsigned long __init find_min_pfn_for_node(int nid)
 {
-	int i;
 	unsigned long min_pfn = ULONG_MAX;
+	unsigned long start_pfn;
+	int i;
 
-	/* Assuming a sorted map, the first range found has the starting pfn */
-	for_each_active_range_index_in_nid(i, nid)
-		min_pfn = min(min_pfn, early_node_map[i].start_pfn);
+	for_each_mem_pfn_range(i, nid, &start_pfn, NULL, NULL)
+		min_pfn = min(min_pfn, start_pfn);
 
 	if (min_pfn == ULONG_MAX) {
 		printk(KERN_WARNING
@@ -4662,15 +4611,16 @@ unsigned long __init find_min_pfn_with_active_regions(void)
  */
 static unsigned long __init early_calculate_totalpages(void)
 {
-	int i;
 	unsigned long totalpages = 0;
+	unsigned long start_pfn, end_pfn;
+	int i, nid;
+
+	for_each_mem_pfn_range(i, MAX_NUMNODES, &start_pfn, &end_pfn, &nid) {
+		unsigned long pages = end_pfn - start_pfn;
 
-	for (i = 0; i < nr_nodemap_entries; i++) {
-		unsigned long pages = early_node_map[i].end_pfn -
-						early_node_map[i].start_pfn;
 		totalpages += pages;
 		if (pages)
-			node_set_state(early_node_map[i].nid, N_HIGH_MEMORY);
+			node_set_state(nid, N_HIGH_MEMORY);
 	}
   	return totalpages;
 }
@@ -4725,6 +4675,8 @@ restart:
 	/* Spread kernelcore memory as evenly as possible throughout nodes */
 	kernelcore_node = required_kernelcore / usable_nodes;
 	for_each_node_state(nid, N_HIGH_MEMORY) {
+		unsigned long start_pfn, end_pfn;
+
 		/*
 		 * Recalculate kernelcore_node if the division per node
 		 * now exceeds what is necessary to satisfy the requested
@@ -4741,13 +4693,10 @@ restart:
 		kernelcore_remaining = kernelcore_node;
 
 		/* Go through each range of PFNs within this node */
-		for_each_active_range_index_in_nid(i, nid) {
-			unsigned long start_pfn, end_pfn;
+		for_each_mem_pfn_range(i, nid, &start_pfn, &end_pfn, NULL) {
 			unsigned long size_pages;
 
-			start_pfn = max(early_node_map[i].start_pfn,
-						zone_movable_pfn[nid]);
-			end_pfn = early_node_map[i].end_pfn;
+			start_pfn = max(start_pfn, zone_movable_pfn[nid]);
 			if (start_pfn >= end_pfn)
 				continue;
 
@@ -4849,8 +4798,8 @@ static void check_for_regular_memory(pg_data_t *pgdat)
  */
 void __init free_area_init_nodes(unsigned long *max_zone_pfn)
 {
-	unsigned long nid;
-	int i;
+	unsigned long start_pfn, end_pfn;
+	int i, nid;
 
 	/* Sort early_node_map as initialisation assumes it is sorted */
 	sort_node_map();
@@ -4900,11 +4849,9 @@ void __init free_area_init_nodes(unsigned long *max_zone_pfn)
 	}
 
 	/* Print out the early_node_map[] */
-	printk("early_node_map[%d] active PFN ranges\n", nr_nodemap_entries);
-	for (i = 0; i < nr_nodemap_entries; i++)
-		printk("  %3d: %0#10lx -> %0#10lx\n", early_node_map[i].nid,
-						early_node_map[i].start_pfn,
-						early_node_map[i].end_pfn);
+	printk("Early memory PFN ranges\n");
+	for_each_mem_pfn_range(i, MAX_NUMNODES, &start_pfn, &end_pfn, &nid)
+		printk("  %3d: %0#10lx -> %0#10lx\n", nid, start_pfn, end_pfn);
 
 	/* Initialise every node */
 	mminit_verify_pageflags_layout();
-- 
cgit v1.2.3


From b2fea988f4f3b38ff4edfc1556a843c91932804c Mon Sep 17 00:00:00 2001
From: Tejun Heo <tj@kernel.org>
Date: Tue, 12 Jul 2011 10:46:31 +0200
Subject: memblock: Improve generic memblock_nid_range() using
 for_each_mem_pfn_range()

Given an address range, memblock_nid_range() determines the node the
start of the range belongs to and upto where the range stays in the
same node.

It's implemented by calling get_pfn_range_for_nid(), which determines
min and max pfns for a given node, for each node and testing whether
start address falls in there.  This is not only inefficient but also
incorrect when nodes interleave as min-max ranges for nodes overlap.

This patch reimplements memblock_nid_range() using
for_each_mem_pfn_range().  It's simpler, walks the mem ranges once and
can find the exact range the start address falls in.

Signed-off-by: Tejun Heo <tj@kernel.org>
Link: http://lkml.kernel.org/r/1310460395-30913-5-git-send-email-tj@kernel.org
Cc: Yinghai Lu <yinghai@kernel.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
---
 mm/memblock.c | 20 +++-----------------
 1 file changed, 3 insertions(+), 17 deletions(-)

diff --git a/mm/memblock.c b/mm/memblock.c
index 0f9626f01b5e..97f3486ce4d6 100644
--- a/mm/memblock.c
+++ b/mm/memblock.c
@@ -511,28 +511,14 @@ phys_addr_t __init memblock_alloc(phys_addr_t size, phys_addr_t align)
 phys_addr_t __weak __init memblock_nid_range(phys_addr_t start, phys_addr_t end, int *nid)
 {
 #ifdef CONFIG_ARCH_POPULATES_NODE_MAP
-	/*
-	 * This code originates from sparc which really wants use to walk by addresses
-	 * and returns the nid. This is not very convenient for early_pfn_map[] users
-	 * as the map isn't sorted yet, and it really wants to be walked by nid.
-	 *
-	 * For now, I implement the inefficient method below which walks the early
-	 * map multiple times. Eventually we may want to use an ARCH config option
-	 * to implement a completely different method for both case.
-	 */
 	unsigned long start_pfn, end_pfn;
 	int i;
 
-	for (i = 0; i < MAX_NUMNODES; i++) {
-		get_pfn_range_for_nid(i, &start_pfn, &end_pfn);
-		if (start < PFN_PHYS(start_pfn) || start >= PFN_PHYS(end_pfn))
-			continue;
-		*nid = i;
-		return min(end, PFN_PHYS(end_pfn));
-	}
+	for_each_mem_pfn_range(i, MAX_NUMNODES, &start_pfn, &end_pfn, nid)
+		if (start >= PFN_PHYS(start_pfn) && start < PFN_PHYS(end_pfn))
+			return min(end, PFN_PHYS(end_pfn));
 #endif
 	*nid = 0;
-
 	return end;
 }
 
-- 
cgit v1.2.3


From f9b18db3b1cedc75e5d002a4d7097891c3399736 Mon Sep 17 00:00:00 2001
From: Tejun Heo <tj@kernel.org>
Date: Tue, 12 Jul 2011 10:46:32 +0200
Subject: memblock: Don't allow archs to override memblock_nid_range()

memblock_nid_range() is used to implement memblock_[try_]alloc_nid().
The generic version determines the range by walking early_node_map
with for_each_mem_pfn_range().  The generic version is defined __weak
to allow arch override.

Currently, only sparc overrides it; however, with the previous update
to the generic implementation, there isn't much to be gained with arch
override.  Sparc would behave exactly the same with the generic
implementation.

This patch disallows arch override for memblock_nid_range() and make
both generic and sparc versions static.

sparc is only compile tested.

Signed-off-by: Tejun Heo <tj@kernel.org>
Link: http://lkml.kernel.org/r/1310460395-30913-6-git-send-email-tj@kernel.org
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Yinghai Lu <yinghai@kernel.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
---
 arch/sparc/mm/init_64.c  | 4 ++--
 include/linux/memblock.h | 1 -
 mm/memblock.c            | 2 +-
 3 files changed, 3 insertions(+), 4 deletions(-)

diff --git a/arch/sparc/mm/init_64.c b/arch/sparc/mm/init_64.c
index 3fd8e18bed80..8415f614ce0c 100644
--- a/arch/sparc/mm/init_64.c
+++ b/arch/sparc/mm/init_64.c
@@ -785,7 +785,7 @@ static int find_node(unsigned long addr)
 	return -1;
 }
 
-u64 memblock_nid_range(u64 start, u64 end, int *nid)
+static u64 memblock_nid_range(u64 start, u64 end, int *nid)
 {
 	*nid = find_node(start);
 	start += PAGE_SIZE;
@@ -803,7 +803,7 @@ u64 memblock_nid_range(u64 start, u64 end, int *nid)
 	return start;
 }
 #else
-u64 memblock_nid_range(u64 start, u64 end, int *nid)
+static u64 memblock_nid_range(u64 start, u64 end, int *nid)
 {
 	*nid = 0;
 	return end;
diff --git a/include/linux/memblock.h b/include/linux/memblock.h
index 349688899cb0..329ffb26c1c9 100644
--- a/include/linux/memblock.h
+++ b/include/linux/memblock.h
@@ -89,7 +89,6 @@ extern int memblock_is_region_reserved(phys_addr_t base, phys_addr_t size);
 extern void memblock_dump_all(void);
 
 /* Provided by the architecture */
-extern phys_addr_t memblock_nid_range(phys_addr_t start, phys_addr_t end, int *nid);
 extern int memblock_memory_can_coalesce(phys_addr_t addr1, phys_addr_t size1,
 				   phys_addr_t addr2, phys_addr_t size2);
 
diff --git a/mm/memblock.c b/mm/memblock.c
index 97f3486ce4d6..22cd999b0d4e 100644
--- a/mm/memblock.c
+++ b/mm/memblock.c
@@ -508,7 +508,7 @@ phys_addr_t __init memblock_alloc(phys_addr_t size, phys_addr_t align)
  * have been done to populate it.
  */
 
-phys_addr_t __weak __init memblock_nid_range(phys_addr_t start, phys_addr_t end, int *nid)
+static phys_addr_t __init memblock_nid_range(phys_addr_t start, phys_addr_t end, int *nid)
 {
 #ifdef CONFIG_ARCH_POPULATES_NODE_MAP
 	unsigned long start_pfn, end_pfn;
-- 
cgit v1.2.3


From 34e1845548418e5cecee0568ba721e1f089c092c Mon Sep 17 00:00:00 2001
From: Tejun Heo <tj@kernel.org>
Date: Tue, 12 Jul 2011 10:46:33 +0200
Subject: memblock: Make memblock_alloc_[try_]nid() top-down

NUMA aware memblock alloc functions - memblock_alloc_[try_]nid() -
weren't properly top-down because memblock_nid_range() scanned
forward.  This patch reverses memblock_nid_range(), renames it to
memblock_nid_range_rev() and updates related functions to implement
proper top-down allocation.

Signed-off-by: Tejun Heo <tj@kernel.org>
Link: http://lkml.kernel.org/r/1310460395-30913-7-git-send-email-tj@kernel.org
Cc: Yinghai Lu <yinghai@kernel.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
---
 mm/memblock.c | 29 +++++++++++------------------
 1 file changed, 11 insertions(+), 18 deletions(-)

diff --git a/mm/memblock.c b/mm/memblock.c
index 22cd999b0d4e..447cf64304ba 100644
--- a/mm/memblock.c
+++ b/mm/memblock.c
@@ -499,27 +499,26 @@ phys_addr_t __init memblock_alloc(phys_addr_t size, phys_addr_t align)
 
 
 /*
- * Additional node-local allocators. Search for node memory is bottom up
- * and walks memblock regions within that node bottom-up as well, but allocation
- * within an memblock region is top-down. XXX I plan to fix that at some stage
+ * Additional node-local top-down allocators.
  *
  * WARNING: Only available after early_node_map[] has been populated,
  * on some architectures, that is after all the calls to add_active_range()
  * have been done to populate it.
  */
 
-static phys_addr_t __init memblock_nid_range(phys_addr_t start, phys_addr_t end, int *nid)
+static phys_addr_t __init memblock_nid_range_rev(phys_addr_t start,
+						 phys_addr_t end, int *nid)
 {
 #ifdef CONFIG_ARCH_POPULATES_NODE_MAP
 	unsigned long start_pfn, end_pfn;
 	int i;
 
 	for_each_mem_pfn_range(i, MAX_NUMNODES, &start_pfn, &end_pfn, nid)
-		if (start >= PFN_PHYS(start_pfn) && start < PFN_PHYS(end_pfn))
-			return min(end, PFN_PHYS(end_pfn));
+		if (end > PFN_PHYS(start_pfn) && end <= PFN_PHYS(end_pfn))
+			return max(start, PFN_PHYS(start_pfn));
 #endif
 	*nid = 0;
-	return end;
+	return start;
 }
 
 static phys_addr_t __init memblock_alloc_nid_region(struct memblock_region *mp,
@@ -531,21 +530,19 @@ static phys_addr_t __init memblock_alloc_nid_region(struct memblock_region *mp,
 	start = mp->base;
 	end = start + mp->size;
 
-	start = round_up(start, align);
 	while (start < end) {
-		phys_addr_t this_end;
+		phys_addr_t this_start;
 		int this_nid;
 
-		this_end = memblock_nid_range(start, end, &this_nid);
+		this_start = memblock_nid_range_rev(start, end, &this_nid);
 		if (this_nid == nid) {
-			phys_addr_t ret = memblock_find_region(start, this_end, size, align);
+			phys_addr_t ret = memblock_find_region(this_start, end, size, align);
 			if (ret &&
 			    !memblock_add_region(&memblock.reserved, ret, size))
 				return ret;
 		}
-		start = this_end;
+		end = this_start;
 	}
-
 	return 0;
 }
 
@@ -561,11 +558,7 @@ phys_addr_t __init memblock_alloc_nid(phys_addr_t size, phys_addr_t align, int n
 	 */
 	size = round_up(size, align);
 
-	/* We do a bottom-up search for a region with the right
-	 * nid since that's easier considering how memblock_nid_range()
-	 * works
-	 */
-	for (i = 0; i < mem->cnt; i++) {
+	for (i = mem->cnt - 1; i >= 0; i--) {
 		phys_addr_t ret = memblock_alloc_nid_region(&mem->regions[i],
 					       size, align, nid);
 		if (ret)
-- 
cgit v1.2.3


From e64980405cc6aa74ef178d8d9aa4018c867ceed1 Mon Sep 17 00:00:00 2001
From: Tejun Heo <tj@kernel.org>
Date: Tue, 12 Jul 2011 10:46:34 +0200
Subject: memblock: Separate out memblock_find_in_range_node()

Node affine memblock allocation logic is currently implemented across
memblock_alloc_nid() and memblock_alloc_nid_region().  This
reorganizes it such that it resembles that of non-NUMA allocation API.

Area finding is collected and moved into new exported function
memblock_find_in_range_node() which is symmetrical to non-NUMA
counterpart - it handles @start/@end and understands ANYWHERE and
ACCESSIBLE.  memblock_alloc_nid() now simply calls
memblock_find_in_range_node() and reserves the returned area.

This makes memblock_alloc[_try]_nid() observe ACCESSIBLE limit on node
affine allocations too (again, this doesn't make any difference for
the current sole user - sparc64).

Signed-off-by: Tejun Heo <tj@kernel.org>
Link: http://lkml.kernel.org/r/1310460395-30913-8-git-send-email-tj@kernel.org
Cc: Yinghai Lu <yinghai@kernel.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
---
 include/linux/memblock.h |  4 ++++
 mm/memblock.c            | 57 +++++++++++++++++++++++++++---------------------
 2 files changed, 36 insertions(+), 25 deletions(-)

diff --git a/include/linux/memblock.h b/include/linux/memblock.h
index 329ffb26c1c9..7400d029df48 100644
--- a/include/linux/memblock.h
+++ b/include/linux/memblock.h
@@ -61,6 +61,10 @@ extern long memblock_reserve(phys_addr_t base, phys_addr_t size);
 /* The numa aware allocator is only available if
  * CONFIG_ARCH_POPULATES_NODE_MAP is set
  */
+extern phys_addr_t memblock_find_in_range_node(phys_addr_t start,
+					       phys_addr_t end,
+					       phys_addr_t size,
+					       phys_addr_t align, int nid);
 extern phys_addr_t memblock_alloc_nid(phys_addr_t size, phys_addr_t align,
 					int nid);
 extern phys_addr_t memblock_alloc_try_nid(phys_addr_t size, phys_addr_t align,
diff --git a/mm/memblock.c b/mm/memblock.c
index 447cf64304ba..a8edb422795b 100644
--- a/mm/memblock.c
+++ b/mm/memblock.c
@@ -521,49 +521,56 @@ static phys_addr_t __init memblock_nid_range_rev(phys_addr_t start,
 	return start;
 }
 
-static phys_addr_t __init memblock_alloc_nid_region(struct memblock_region *mp,
+phys_addr_t __init memblock_find_in_range_node(phys_addr_t start,
+					       phys_addr_t end,
 					       phys_addr_t size,
 					       phys_addr_t align, int nid)
 {
-	phys_addr_t start, end;
+	struct memblock_type *mem = &memblock.memory;
+	int i;
 
-	start = mp->base;
-	end = start + mp->size;
+	BUG_ON(0 == size);
 
-	while (start < end) {
-		phys_addr_t this_start;
-		int this_nid;
+	/* Pump up max_addr */
+	if (end == MEMBLOCK_ALLOC_ACCESSIBLE)
+		end = memblock.current_limit;
 
-		this_start = memblock_nid_range_rev(start, end, &this_nid);
-		if (this_nid == nid) {
-			phys_addr_t ret = memblock_find_region(this_start, end, size, align);
-			if (ret &&
-			    !memblock_add_region(&memblock.reserved, ret, size))
-				return ret;
+	for (i = mem->cnt - 1; i >= 0; i--) {
+		struct memblock_region *r = &mem->regions[i];
+		phys_addr_t base = max(start, r->base);
+		phys_addr_t top = min(end, r->base + r->size);
+
+		while (base < top) {
+			phys_addr_t tbase, ret;
+			int tnid;
+
+			tbase = memblock_nid_range_rev(base, top, &tnid);
+			if (nid == MAX_NUMNODES || tnid == nid) {
+				ret = memblock_find_region(tbase, top, size, align);
+				if (ret)
+					return ret;
+			}
+			top = tbase;
 		}
-		end = this_start;
 	}
+
 	return 0;
 }
 
 phys_addr_t __init memblock_alloc_nid(phys_addr_t size, phys_addr_t align, int nid)
 {
-	struct memblock_type *mem = &memblock.memory;
-	int i;
-
-	BUG_ON(0 == size);
+	phys_addr_t found;
 
-	/* We align the size to limit fragmentation. Without this, a lot of
+	/*
+	 * We align the size to limit fragmentation. Without this, a lot of
 	 * small allocs quickly eat up the whole reserve array on sparc
 	 */
 	size = round_up(size, align);
 
-	for (i = mem->cnt - 1; i >= 0; i--) {
-		phys_addr_t ret = memblock_alloc_nid_region(&mem->regions[i],
-					       size, align, nid);
-		if (ret)
-			return ret;
-	}
+	found = memblock_find_in_range_node(0, MEMBLOCK_ALLOC_ACCESSIBLE,
+					    size, align, nid);
+	if (found && !memblock_add_region(&memblock.reserved, found, size))
+		return found;
 
 	return 0;
 }
-- 
cgit v1.2.3


From eb40c4c27f1722f058e4713ccfedebac577d5190 Mon Sep 17 00:00:00 2001
From: Tejun Heo <tj@kernel.org>
Date: Tue, 12 Jul 2011 10:46:35 +0200
Subject: memblock, x86: Replace memblock_x86_find_in_range_node() with generic
 memblock calls

With the previous changes, generic NUMA aware memblock API has feature
parity with memblock_x86_find_in_range_node().  There currently are
two users - x86 setup_node_data() and __alloc_memory_core_early() in
nobootmem.c.

This patch converts the former to use memblock_alloc_nid() and the
latter memblock_find_range_in_node(), and kills
memblock_x86_find_in_range_node() and related functions including
find_memory_early_core_early() in page_alloc.c.

Signed-off-by: Tejun Heo <tj@kernel.org>
Link: http://lkml.kernel.org/r/1310460395-30913-9-git-send-email-tj@kernel.org
Cc: Yinghai Lu <yinghai@kernel.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
---
 arch/x86/include/asm/memblock.h |  1 -
 arch/x86/mm/memblock.c          | 15 ---------
 arch/x86/mm/numa.c              |  9 +-----
 include/linux/mm.h              |  2 --
 mm/nobootmem.c                  |  3 +-
 mm/page_alloc.c                 | 67 -----------------------------------------
 6 files changed, 2 insertions(+), 95 deletions(-)

diff --git a/arch/x86/include/asm/memblock.h b/arch/x86/include/asm/memblock.h
index 0cd3800f33b9..161792ec524f 100644
--- a/arch/x86/include/asm/memblock.h
+++ b/arch/x86/include/asm/memblock.h
@@ -15,7 +15,6 @@ int get_free_all_memory_range(struct range **rangep, int nodeid);
 void memblock_x86_register_active_regions(int nid, unsigned long start_pfn,
 					 unsigned long last_pfn);
 u64 memblock_x86_hole_size(u64 start, u64 end);
-u64 memblock_x86_find_in_range_node(int nid, u64 start, u64 end, u64 size, u64 align);
 u64 memblock_x86_free_memory_in_range(u64 addr, u64 limit);
 u64 memblock_x86_memory_in_range(u64 addr, u64 limit);
 bool memblock_x86_check_reserved_size(u64 *addrp, u64 *sizep, u64 align);
diff --git a/arch/x86/mm/memblock.c b/arch/x86/mm/memblock.c
index da0d5c84586e..e4569f85b390 100644
--- a/arch/x86/mm/memblock.c
+++ b/arch/x86/mm/memblock.c
@@ -251,21 +251,6 @@ void __init memblock_x86_free_range(u64 start, u64 end)
 	memblock_free(start, end - start);
 }
 
-/*
- * Need to call this function after memblock_x86_register_active_regions,
- * so early_node_map[] is filled already.
- */
-u64 __init memblock_x86_find_in_range_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)
-		return addr;
-
-	/* Fallback, should already have start end within node range */
-	return memblock_find_in_range(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 memblock entry.
diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c
index fa1015de5cc0..824efadc5741 100644
--- a/arch/x86/mm/numa.c
+++ b/arch/x86/mm/numa.c
@@ -192,8 +192,6 @@ int __init numa_add_memblk(int nid, u64 start, u64 end)
 /* Initialize NODE_DATA for a node on the local memory */
 static void __init setup_node_data(int nid, u64 start, u64 end)
 {
-	const u64 nd_low = PFN_PHYS(MAX_DMA_PFN);
-	const u64 nd_high = PFN_PHYS(max_pfn_mapped);
 	const size_t nd_size = roundup(sizeof(pg_data_t), PAGE_SIZE);
 	bool remapped = false;
 	u64 nd_pa;
@@ -224,17 +222,12 @@ static void __init setup_node_data(int nid, u64 start, u64 end)
 		nd_pa = __pa(nd);
 		remapped = true;
 	} else {
-		nd_pa = memblock_x86_find_in_range_node(nid, nd_low, nd_high,
-						nd_size, SMP_CACHE_BYTES);
-		if (!nd_pa)
-			nd_pa = memblock_find_in_range(nd_low, nd_high,
-						nd_size, SMP_CACHE_BYTES);
+		nd_pa = memblock_alloc_nid(nd_size, SMP_CACHE_BYTES, nid);
 		if (!nd_pa) {
 			pr_err("Cannot find %zu bytes in node %d\n",
 			       nd_size, nid);
 			return;
 		}
-		memblock_x86_reserve_range(nd_pa, nd_pa + nd_size, "NODE_DATA");