[PATCH v5, part3 00/15] accurately calculate memory statisitic information

[PATCH v5, part3 00/15] accurately calculate memory statisitic information

[Jiang Liu]

The original goal of this patchset is to fix the bug reported by
https://bugzilla.kernel.org/show_bug.cgi?id=53501
Now it has also been expanded to reduce common code used by memory
initializion.

This is the third part, previous two patch sets could be accessed at:
http://marc.info/?l=linux-mm&m=136289696323825&w=2
http://marc.info/?l=linux-mm&m=136290291524901&w=2

This patchset applies to
git://git.cmpxchg.org/linux-mmotm.git v3.9-rc8-mmotm-2013-04-25-16-24

V2->V4:
1) rebase to git://git.cmpxchg.org/linux-mmotm.git
2) fix some build warnings and other minor bugs of previous patches

V4->V5:
1) rebase to v3.9-rc8-mmotm-2013-04-25-16-24
2) address comments from last round of review

We have only tested these patchset on x86 platforms, and have done basic
compliation tests using cross-compilers from ftp.kernel.org. That means
some code may not pass compilation on some architectures. So any help
to test this patchset are welcomed!

Patch 1-7:
	Bugfixes and more work for part1 and part2
Patch 8-9:
	Fix typo and minor bugs in mm core
Patch 10-14:
	Enhance the way to manage totalram_pages, totalhigh_pages and
	zone->managed_pages.
Patch 15:
	Report available pages within the node as "MemTotal" for sysfs
	interface /sys/.../node/nodex/meminfo

Jiang Liu (15):
  mm: fix build warnings caused by free_reserved_area()
  mm: enhance free_reserved_area() to support poisoning memory with
    zero
  mm/ARM64: kill poison_init_mem()
  mm/x86: use free_reserved_area() to simplify code
  mm/tile: use common help functions to free reserved pages
  mm, powertv: use free_reserved_area() to simplify code
  mm, acornfb: use free_reserved_area() to simplify code
  mm: fix some trivial typos in comments
  mm: use managed_pages to calculate default zonelist order
  mm: accurately calculate zone->managed_pages for highmem zones
  mm: use a dedicated lock to protect totalram_pages and
    zone->managed_pages
  mm: make __free_pages_bootmem() only available at boot time
  mm: correctly update zone->mamaged_pages
  mm: concentrate modification of totalram_pages into the mm core
  mm: report available pages as "MemTotal" for each NUMA node

 arch/alpha/kernel/sys_nautilus.c      |    2 +-
 arch/alpha/mm/init.c                  |    6 ++---
 arch/alpha/mm/numa.c                  |    2 +-
 arch/arc/mm/init.c                    |    2 +-
 arch/arm/mm/init.c                    |   13 ++++-----
 arch/arm64/mm/init.c                  |   15 ++---------
 arch/avr32/mm/init.c                  |    6 ++---
 arch/blackfin/mm/init.c               |    6 ++---
 arch/c6x/mm/init.c                    |    6 ++---
 arch/cris/mm/init.c                   |    4 +--
 arch/frv/mm/init.c                    |    6 ++---
 arch/h8300/mm/init.c                  |    6 ++---
 arch/hexagon/mm/init.c                |    2 +-
 arch/ia64/mm/init.c                   |    4 +--
 arch/m32r/mm/init.c                   |    6 ++---
 arch/m68k/mm/init.c                   |    8 +++---
 arch/metag/mm/init.c                  |   11 +++++---
 arch/microblaze/mm/init.c             |    6 ++---
 arch/mips/mm/init.c                   |    2 +-
 arch/mips/powertv/asic/asic_devices.c |   13 ++-------
 arch/mips/sgi-ip27/ip27-memory.c      |    2 +-
 arch/mn10300/mm/init.c                |    2 +-
 arch/openrisc/mm/init.c               |    6 ++---
 arch/parisc/mm/init.c                 |    8 +++---
 arch/powerpc/kernel/kvm.c             |    2 +-
 arch/powerpc/mm/mem.c                 |    7 +++--
 arch/s390/mm/init.c                   |    4 +--
 arch/score/mm/init.c                  |    2 +-
 arch/sh/mm/init.c                     |    6 ++---
 arch/sparc/mm/init_32.c               |    3 +--
 arch/sparc/mm/init_64.c               |    2 +-
 arch/tile/mm/init.c                   |    9 +++----
 arch/um/kernel/mem.c                  |    4 +--
 arch/unicore32/mm/init.c              |    6 ++---
 arch/x86/mm/highmem_32.c              |    6 +++++
 arch/x86/mm/init.c                    |   14 +++-------
 arch/x86/mm/init_32.c                 |    2 +-
 arch/x86/mm/init_64.c                 |   25 ++++-------------
 arch/xtensa/mm/init.c                 |    6 ++---
 drivers/video/acornfb.c               |   28 ++-----------------
 drivers/virtio/virtio_balloon.c       |    8 +++---
 drivers/xen/balloon.c                 |   23 ++++------------
 include/linux/bootmem.h               |    1 +
 include/linux/mm.h                    |   17 ++++++------
 include/linux/mmzone.h                |   14 +++++++---
 mm/bootmem.c                          |   41 +++++++++++++++++-----------
 mm/hugetlb.c                          |    2 +-
 mm/memory_hotplug.c                   |   33 +++++------------------
 mm/nobootmem.c                        |   35 ++++++++++++++----------
 mm/page_alloc.c                       |   48 ++++++++++++++++++++-------------
 50 files changed, 215 insertions(+), 277 deletions(-)

-- 
1.7.9.5

[PATCH v5, part3 01/15] mm: fix build warnings caused by free_reserved_area()

[Jiang Liu]

Fix following build warnings cuased by free_reserved_area():

arch/arm/mm/init.c: In function 'mem_init':
arch/arm/mm/init.c:603:2: warning: passing argument 1 of 'free_reserved_area' makes integer from pointer without a cast [enabled by default]
  free_reserved_area(__va(PHYS_PFN_OFFSET), swapper_pg_dir, 0, NULL);
  ^
In file included from include/linux/mman.h:4:0,
                 from arch/arm/mm/init.c:15:
include/linux/mm.h:1301:22: note: expected 'long unsigned int' but argument is of type 'void *'
 extern unsigned long free_reserved_area(unsigned long start, unsigned long end,

   mm/page_alloc.c: In function 'free_reserved_area':
>> mm/page_alloc.c:5134:3: warning: passing argument 1 of 'virt_to_phys' makes pointer from integer without a cast [enabled by default]
   In file included from arch/mips/include/asm/page.h:49:0,
                    from include/linux/mmzone.h:20,
                    from include/linux/gfp.h:4,
                    from include/linux/mm.h:8,
                    from mm/page_alloc.c:18:
   arch/mips/include/asm/io.h:119:29: note: expected 'const volatile void *' but argument is of type 'long unsigned int'
   mm/page_alloc.c: In function 'free_area_init_nodes':
   mm/page_alloc.c:5030:34: warning: array subscript is below array bounds [-Warray-bounds]

Signed-off-by: Jiang Liu <jiang.liu@huawei.com>
Reported-by: Arnd Bergmann <arnd@arndb.de>
Cc: linux-arm-kernel@lists.infradead.org
Cc: linux-kernel@vger.kernel.org
Cc: linux-mm@kvack.org
---
 arch/arm/mm/init.c |    6 ++++--
 mm/page_alloc.c    |    2 +-
 2 files changed, 5 insertions(+), 3 deletions(-)

diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c
index 9a5cdc0..7a82fcd 100644
--- a/arch/arm/mm/init.c
+++ b/arch/arm/mm/init.c
@@ -600,7 +600,8 @@ void __init mem_init(void)
 
 #ifdef CONFIG_SA1111
 	/* now that our DMA memory is actually so designated, we can free it */
-	free_reserved_area(__va(PHYS_PFN_OFFSET), swapper_pg_dir, 0, NULL);
+	free_reserved_area((unsigned long)__va(PHYS_PFN_OFFSET),
+			   (unsigned long)swapper_pg_dir, 0, NULL);
 #endif
 
 	free_highpages();
@@ -728,7 +729,8 @@ void free_initmem(void)
 	extern char __tcm_start, __tcm_end;
 
 	poison_init_mem(&__tcm_start, &__tcm_end - &__tcm_start);
-	free_reserved_area(&__tcm_start, &__tcm_end, 0, "TCM link");
+	free_reserved_area((unsigned long)&__tcm_start,
+			   (unsigned long)&__tcm_end, 0, "TCM link");
 #endif
 
 	poison_init_mem(__init_begin, __init_end - __init_begin);
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 843e33d..ce259c8 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -5196,7 +5196,7 @@ unsigned long free_reserved_area(unsigned long start, unsigned long end,
 	for (pages = 0; pos < end; pos += PAGE_SIZE, pages++) {
 		if (poison)
 			memset((void *)pos, poison, PAGE_SIZE);
-		free_reserved_page(virt_to_page(pos));
+		free_reserved_page(virt_to_page((void *)pos));
 	}
 
 	if (pages && s)
-- 
1.7.9.5

[PATCH v5, part3 02/15] mm: enhance free_reserved_area() to support poisoning memory with zero

[Jiang Liu]

Address more review comments from last round of code review.
1) Enhance free_reserved_area() to support poisoning freed memory with
   pattern '0'. This could be used to get rid of poison_init_mem()
   on ARM64.
2) A previous patch has disabled memory poison for initmem on s390
   by mistake, so restore to the original behavior.
3) Remove redundant PAGE_ALIGN() when calling free_reserved_area().

Signed-off-by: Jiang Liu <jiang.liu@huawei.com>
Cc: Geert Uytterhoeven <geert@linux-m68k.org>
---
 arch/alpha/kernel/sys_nautilus.c |    2 +-
 arch/alpha/mm/init.c             |    4 ++--
 arch/arm/mm/init.c               |    8 ++++----
 arch/arm64/mm/init.c             |    4 ++--
 arch/avr32/mm/init.c             |    4 ++--
 arch/blackfin/mm/init.c          |    4 ++--
 arch/c6x/mm/init.c               |    4 ++--
 arch/cris/mm/init.c              |    2 +-
 arch/frv/mm/init.c               |    4 ++--
 arch/h8300/mm/init.c             |    4 ++--
 arch/ia64/mm/init.c              |    2 +-
 arch/m32r/mm/init.c              |    4 ++--
 arch/m68k/mm/init.c              |    4 ++--
 arch/microblaze/mm/init.c        |    4 ++--
 arch/openrisc/mm/init.c          |    4 ++--
 arch/parisc/mm/init.c            |    4 ++--
 arch/powerpc/kernel/kvm.c        |    2 +-
 arch/powerpc/mm/mem.c            |    2 +-
 arch/s390/mm/init.c              |    2 +-
 arch/sh/mm/init.c                |    4 ++--
 arch/um/kernel/mem.c             |    2 +-
 arch/unicore32/mm/init.c         |    4 ++--
 arch/xtensa/mm/init.c            |    4 ++--
 include/linux/mm.h               |   11 ++++++-----
 mm/page_alloc.c                  |    2 +-
 25 files changed, 48 insertions(+), 47 deletions(-)

diff --git a/arch/alpha/kernel/sys_nautilus.c b/arch/alpha/kernel/sys_nautilus.c
index 1d4aabf..7c57903 100644
--- a/arch/alpha/kernel/sys_nautilus.c
+++ b/arch/alpha/kernel/sys_nautilus.c
@@ -239,7 +239,7 @@ nautilus_init_pci(void)
 		memtop = pci_mem;
 	if (memtop > alpha_mv.min_mem_address) {
 		free_reserved_area((unsigned long)__va(alpha_mv.min_mem_address),
-				   (unsigned long)__va(memtop), 0, NULL);
+				   (unsigned long)__va(memtop), -1, NULL);
 		printk("nautilus_init_pci: %ldk freed\n",
 			(memtop - alpha_mv.min_mem_address) >> 10);
 	}
diff --git a/arch/alpha/mm/init.c b/arch/alpha/mm/init.c
index 0ba85ee..9930837 100644
--- a/arch/alpha/mm/init.c
+++ b/arch/alpha/mm/init.c
@@ -319,13 +319,13 @@ mem_init(void)
 void
 free_initmem(void)
 {
-	free_initmem_default(0);
+	free_initmem_default(-1);
 }
 
 #ifdef CONFIG_BLK_DEV_INITRD
 void
 free_initrd_mem(unsigned long start, unsigned long end)
 {
-	free_reserved_area(start, end, 0, "initrd");
+	free_reserved_area(start, end, -1, "initrd");
 }
 #endif
diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c
index 7a82fcd..a2ab290 100644
--- a/arch/arm/mm/init.c
+++ b/arch/arm/mm/init.c
@@ -601,7 +601,7 @@ void __init mem_init(void)
 #ifdef CONFIG_SA1111
 	/* now that our DMA memory is actually so designated, we can free it */
 	free_reserved_area((unsigned long)__va(PHYS_PFN_OFFSET),
-			   (unsigned long)swapper_pg_dir, 0, NULL);
+			   (unsigned long)swapper_pg_dir, -1, NULL);
 #endif
 
 	free_highpages();
@@ -730,12 +730,12 @@ void free_initmem(void)
 
 	poison_init_mem(&__tcm_start, &__tcm_end - &__tcm_start);
 	free_reserved_area((unsigned long)&__tcm_start,
-			   (unsigned long)&__tcm_end, 0, "TCM link");
+			   (unsigned long)&__tcm_end, -1, "TCM link");
 #endif
 
 	poison_init_mem(__init_begin, __init_end - __init_begin);
 	if (!machine_is_integrator() && !machine_is_cintegrator())
-		free_initmem_default(0);
+		free_initmem_default(-1);
 }
 
 #ifdef CONFIG_BLK_DEV_INITRD
@@ -746,7 +746,7 @@ void free_initrd_mem(unsigned long start, unsigned long end)
 {
 	if (!keep_initrd) {
 		poison_init_mem((void *)start, PAGE_ALIGN(end) - start);
-		free_reserved_area(start, end, 0, "initrd");
+		free_reserved_area(start, end, -1, "initrd");
 	}
 }
 
diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c
index f497ca7..e58dd7f 100644
--- a/arch/arm64/mm/init.c
+++ b/arch/arm64/mm/init.c
@@ -387,7 +387,7 @@ void __init mem_init(void)
 void free_initmem(void)
 {
 	poison_init_mem(__init_begin, __init_end - __init_begin);
-	free_initmem_default(0);
+	free_initmem_default(-1);
 }
 
 #ifdef CONFIG_BLK_DEV_INITRD
@@ -398,7 +398,7 @@ void free_initrd_mem(unsigned long start, unsigned long end)
 {
 	if (!keep_initrd) {
 		poison_init_mem((void *)start, PAGE_ALIGN(end) - start);
-		free_reserved_area(start, end, 0, "initrd");
+		free_reserved_area(start, end, -1, "initrd");
 	}
 }
 
diff --git a/arch/avr32/mm/init.c b/arch/avr32/mm/init.c
index e66e840..871f98a 100644
--- a/arch/avr32/mm/init.c
+++ b/arch/avr32/mm/init.c
@@ -148,12 +148,12 @@ void __init mem_init(void)
 
 void free_initmem(void)
 {
-	free_initmem_default(0);
+	free_initmem_default(-1);
 }
 
 #ifdef CONFIG_BLK_DEV_INITRD
 void free_initrd_mem(unsigned long start, unsigned long end)
 {
-	free_reserved_area(start, end, 0, "initrd");
+	free_reserved_area(start, end, -1, "initrd");
 }
 #endif
diff --git a/arch/blackfin/mm/init.c b/arch/blackfin/mm/init.c
index 82d01a7..e64286b 100644
--- a/arch/blackfin/mm/init.c
+++ b/arch/blackfin/mm/init.c
@@ -133,7 +133,7 @@ void __init mem_init(void)
 void __init free_initrd_mem(unsigned long start, unsigned long end)
 {
 #ifndef CONFIG_MPU
-	free_reserved_area(start, end, 0, "initrd");
+	free_reserved_area(start, end, -1, "initrd");
 #endif
 }
 #endif
@@ -141,7 +141,7 @@ void __init free_initrd_mem(unsigned long start, unsigned long end)
 void __init_refok free_initmem(void)
 {
 #if defined CONFIG_RAMKERNEL && !defined CONFIG_MPU
-	free_initmem_default(0);
+	free_initmem_default(-1);
 	if (memory_start == (unsigned long)(&__init_end))
 		memory_start = (unsigned long)(&__init_begin);
 #endif
diff --git a/arch/c6x/mm/init.c b/arch/c6x/mm/init.c
index a9fcd89..ce39b48 100644
--- a/arch/c6x/mm/init.c
+++ b/arch/c6x/mm/init.c
@@ -77,11 +77,11 @@ void __init mem_init(void)
 #ifdef CONFIG_BLK_DEV_INITRD
 void __init free_initrd_mem(unsigned long start, unsigned long end)
 {
-	free_reserved_area(start, end, 0, "initrd");
+	free_reserved_area(start, end, -1, "initrd");
 }
 #endif
 
 void __init free_initmem(void)
 {
-	free_initmem_default(0);
+	free_initmem_default(-1);
 }
diff --git a/arch/cris/mm/init.c b/arch/cris/mm/init.c
index 9ac8094..8fec263 100644
--- a/arch/cris/mm/init.c
+++ b/arch/cris/mm/init.c
@@ -65,5 +65,5 @@ mem_init(void)
 void 
 free_initmem(void)
 {
-	free_initmem_default(0);
+	free_initmem_default(-1);
 }
diff --git a/arch/frv/mm/init.c b/arch/frv/mm/init.c
index dee354f..a421948 100644
--- a/arch/frv/mm/init.c
+++ b/arch/frv/mm/init.c
@@ -162,7 +162,7 @@ void __init mem_init(void)
 void free_initmem(void)
 {
 #if defined(CONFIG_RAMKERNEL) && !defined(CONFIG_PROTECT_KERNEL)
-	free_initmem_default(0);
+	free_initmem_default(-1);
 #endif
 } /* end free_initmem() */
 
@@ -173,6 +173,6 @@ void free_initmem(void)
 #ifdef CONFIG_BLK_DEV_INITRD
 void __init free_initrd_mem(unsigned long start, unsigned long end)
 {
-	free_reserved_area(start, end, 0, "initrd");
+	free_reserved_area(start, end, -1, "initrd");
 } /* end free_initrd_mem() */
 #endif
diff --git a/arch/h8300/mm/init.c b/arch/h8300/mm/init.c
index ff349d7..488e2a3 100644
--- a/arch/h8300/mm/init.c
+++ b/arch/h8300/mm/init.c
@@ -161,7 +161,7 @@ void __init mem_init(void)
 #ifdef CONFIG_BLK_DEV_INITRD
 void free_initrd_mem(unsigned long start, unsigned long end)
 {
-	free_reserved_area(start, end, 0, "initrd");
+	free_reserved_area(start, end, -1, "initrd");
 }
 #endif
 
@@ -169,7 +169,7 @@ void
 free_initmem(void)
 {
 #ifdef CONFIG_RAMKERNEL
-	free_initmem_default(0);
+	free_initmem_default(-1);
 #endif
 }
 
diff --git a/arch/ia64/mm/init.c b/arch/ia64/mm/init.c
index d1fe4b4..941568a 100644
--- a/arch/ia64/mm/init.c
+++ b/arch/ia64/mm/init.c
@@ -156,7 +156,7 @@ free_initmem (void)
 {
 	free_reserved_area((unsigned long)ia64_imva(__init_begin),
 			   (unsigned long)ia64_imva(__init_end),
-			   0, "unused kernel");
+			   -1, "unused kernel");
 }
 
 void __init
diff --git a/arch/m32r/mm/init.c b/arch/m32r/mm/init.c
index ab4cbce..58ea4d6 100644
--- a/arch/m32r/mm/init.c
+++ b/arch/m32r/mm/init.c
@@ -181,7 +181,7 @@ void __init mem_init(void)
  *======================================================================*/
 void free_initmem(void)
 {
-	free_initmem_default(0);
+	free_initmem_default(-1);
 }
 
 #ifdef CONFIG_BLK_DEV_INITRD
@@ -191,6 +191,6 @@ void free_initmem(void)
  *======================================================================*/
 void free_initrd_mem(unsigned long start, unsigned long end)
 {
-	free_reserved_area(start, end, 0, "initrd");
+	free_reserved_area(start, end, -1, "initrd");
 }
 #endif
diff --git a/arch/m68k/mm/init.c b/arch/m68k/mm/init.c
index 1af2ca3..75e1cbf 100644
--- a/arch/m68k/mm/init.c
+++ b/arch/m68k/mm/init.c
@@ -110,7 +110,7 @@ void __init paging_init(void)
 void free_initmem(void)
 {
 #ifndef CONFIG_MMU_SUN3
-	free_initmem_default(0);
+	free_initmem_default(-1);
 #endif /* CONFIG_MMU_SUN3 */
 }
 
@@ -202,6 +202,6 @@ void __init mem_init(void)
 #ifdef CONFIG_BLK_DEV_INITRD
 void free_initrd_mem(unsigned long start, unsigned long end)
 {
-	free_reserved_area(start, end, 0, "initrd");
+	free_reserved_area(start, end, -1, "initrd");
 }
 #endif
diff --git a/arch/microblaze/mm/init.c b/arch/microblaze/mm/init.c
index 4ec137d..53383e4 100644
--- a/arch/microblaze/mm/init.c
+++ b/arch/microblaze/mm/init.c
@@ -235,13 +235,13 @@ void __init setup_memory(void)
 #ifdef CONFIG_BLK_DEV_INITRD
 void free_initrd_mem(unsigned long start, unsigned long end)
 {
-	free_reserved_area(start, end, 0, "initrd");
+	free_reserved_area(start, end, -1, "initrd");
 }
 #endif
 
 void free_initmem(void)
 {
-	free_initmem_default(0);
+	free_initmem_default(-1);
 }
 
 void __init mem_init(void)
diff --git a/arch/openrisc/mm/init.c b/arch/openrisc/mm/init.c
index b3cbc67..d19950c 100644
--- a/arch/openrisc/mm/init.c
+++ b/arch/openrisc/mm/init.c
@@ -261,11 +261,11 @@ void __init mem_init(void)
 #ifdef CONFIG_BLK_DEV_INITRD
 void free_initrd_mem(unsigned long start, unsigned long end)
 {
-	free_reserved_area(start, end, 0, "initrd");
+	free_reserved_area(start, end, -1, "initrd");
 }
 #endif
 
 void free_initmem(void)
 {
-	free_initmem_default(0);
+	free_initmem_default(-1);
 }
diff --git a/arch/parisc/mm/init.c b/arch/parisc/mm/init.c
index 157b931..27f3f88 100644
--- a/arch/parisc/mm/init.c
+++ b/arch/parisc/mm/init.c
@@ -532,7 +532,7 @@ void free_initmem(void)
 	 * pages are no-longer executable */
 	flush_icache_range(init_begin, init_end);
 	
-	num_physpages += free_initmem_default(0);
+	num_physpages += free_initmem_default(-1);
 
 	/* set up a new led state on systems shipped LED State panel */
 	pdc_chassis_send_status(PDC_CHASSIS_DIRECT_BCOMPLETE);
@@ -1099,6 +1099,6 @@ void flush_tlb_all(void)
 #ifdef CONFIG_BLK_DEV_INITRD
 void free_initrd_mem(unsigned long start, unsigned long end)
 {
-	num_physpages += free_reserved_area(start, end, 0, "initrd");
+	num_physpages += free_reserved_area(start, end, -1, "initrd");
 }
 #endif
diff --git a/arch/powerpc/kernel/kvm.c b/arch/powerpc/kernel/kvm.c
index 6782221..4d3e37d 100644
--- a/arch/powerpc/kernel/kvm.c
+++ b/arch/powerpc/kernel/kvm.c
@@ -756,7 +756,7 @@ static __init void kvm_free_tmp(void)
 	end = (ulong)&kvm_tmp[ARRAY_SIZE(kvm_tmp)] & PAGE_MASK;
 
 	/* Free the tmp space we don't need */
-	free_reserved_area(start, end, 0, NULL);
+	free_reserved_area(start, end, -1, NULL);
 }
 
 static int __init kvm_guest_init(void)
diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c
index 0988a26..632ab53 100644
--- a/arch/powerpc/mm/mem.c
+++ b/arch/powerpc/mm/mem.c
@@ -407,7 +407,7 @@ void free_initmem(void)
 #ifdef CONFIG_BLK_DEV_INITRD
 void __init free_initrd_mem(unsigned long start, unsigned long end)
 {
-	free_reserved_area(start, end, 0, "initrd");
+	free_reserved_area(start, end, -1, "initrd");
 }
 #endif
 
diff --git a/arch/s390/mm/init.c b/arch/s390/mm/init.c
index 0b09b23..275345e 100644
--- a/arch/s390/mm/init.c
+++ b/arch/s390/mm/init.c
@@ -164,7 +164,7 @@ void __init mem_init(void)
 
 void free_initmem(void)
 {
-	free_initmem_default(0);
+	free_initmem_default(POISON_FREE_INITMEM);
 }
 
 #ifdef CONFIG_BLK_DEV_INITRD
diff --git a/arch/sh/mm/init.c b/arch/sh/mm/init.c
index 20f9ead..31294f1 100644
--- a/arch/sh/mm/init.c
+++ b/arch/sh/mm/init.c
@@ -499,13 +499,13 @@ void __init mem_init(void)
 
 void free_initmem(void)
 {
-	free_initmem_default(0);
+	free_initmem_default(-1);
 }
 
 #ifdef CONFIG_BLK_DEV_INITRD
 void free_initrd_mem(unsigned long start, unsigned long end)
 {
-	free_reserved_area(start, end, 0, "initrd");
+	free_reserved_area(start, end, -1, "initrd");
 }
 #endif
 
diff --git a/arch/um/kernel/mem.c b/arch/um/kernel/mem.c
index 9df292b..1e84189 100644
--- a/arch/um/kernel/mem.c
+++ b/arch/um/kernel/mem.c
@@ -244,7 +244,7 @@ void free_initmem(void)
 #ifdef CONFIG_BLK_DEV_INITRD
 void free_initrd_mem(unsigned long start, unsigned long end)
 {
-	free_reserved_area(start, end, 0, "initrd");
+	free_reserved_area(start, end, -1, "initrd");
 }
 #endif
 
diff --git a/arch/unicore32/mm/init.c b/arch/unicore32/mm/init.c
index 63df12d..5614b05 100644
--- a/arch/unicore32/mm/init.c
+++ b/arch/unicore32/mm/init.c
@@ -476,7 +476,7 @@ void __init mem_init(void)
 
 void free_initmem(void)
 {
-	free_initmem_default(0);
+	free_initmem_default(-1);
 }
 
 #ifdef CONFIG_BLK_DEV_INITRD
@@ -486,7 +486,7 @@ static int keep_initrd;
 void free_initrd_mem(unsigned long start, unsigned long end)
 {
 	if (!keep_initrd)
-		free_reserved_area(start, end, 0, "initrd");
+		free_reserved_area(start, end, -1, "initrd");
 }
 
 static int __init keepinitrd_setup(char *__unused)
diff --git a/arch/xtensa/mm/init.c b/arch/xtensa/mm/init.c
index bba125b..6f70647 100644
--- a/arch/xtensa/mm/init.c
+++ b/arch/xtensa/mm/init.c
@@ -214,11 +214,11 @@ extern int initrd_is_mapped;
 void free_initrd_mem(unsigned long start, unsigned long end)
 {
 	if (initrd_is_mapped)
-		free_reserved_area(start, end, 0, "initrd");
+		free_reserved_area(start, end, -1, "initrd");
 }
 #endif
 
 void free_initmem(void)
 {
-	free_initmem_default(0);
+	free_initmem_default(-1);
 }
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 1a7f19e..9f7006f 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1298,7 +1298,7 @@ extern void free_initmem(void);
 /*
  * Free reserved pages within range [PAGE_ALIGN(start), end & PAGE_MASK)
  * into the buddy system. The freed pages will be poisoned with pattern
- * "poison" if it's non-zero.
+ * "poison" if it's within range [0, UCHAR_MAX].
  * Return pages freed into the buddy system.
  */
 extern unsigned long free_reserved_area(unsigned long start, unsigned long end,
@@ -1338,15 +1338,16 @@ static inline void mark_page_reserved(struct page *page)
 
 /*
  * Default method to free all the __init memory into the buddy system.
- * The freed pages will be poisoned with pattern "poison" if it is
- * non-zero. Return pages freed into the buddy system.
+ * The freed pages will be poisoned with pattern "poison" if it's within
+ * range [0, UCHAR_MAX].
+ * Return pages freed into the buddy system.
  */
 static inline unsigned long free_initmem_default(int poison)
 {
 	extern char __init_begin[], __init_end[];
 
-	return free_reserved_area(PAGE_ALIGN((unsigned long)&__init_begin) ,
-				  ((unsigned long)&__init_end) & PAGE_MASK,
+	return free_reserved_area((unsigned long)&__init_begin ,
+				  (unsigned long)&__init_end,
 				  poison, "unused kernel");
 }
 
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index ce259c8..2045c23 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -5194,7 +5194,7 @@ unsigned long free_reserved_area(unsigned long start, unsigned long end,
 	pos = start = PAGE_ALIGN(start);
 	end &= PAGE_MASK;
 	for (pages = 0; pos < end; pos += PAGE_SIZE, pages++) {
-		if (poison)
+		if ((unsigned int)poison <= 0xFF)
 			memset((void *)pos, poison, PAGE_SIZE);
 		free_reserved_page(virt_to_page((void *)pos));
 	}
-- 
1.7.9.5

[PATCH v5, part3 03/15] mm/ARM64: kill poison_init_mem()

[Jiang Liu]

Use free_reserved_area() to poison initmem memory pages and kill
poison_init_mem() on ARM64.

Signed-off-by: Jiang Liu <jiang.liu@huawei.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Will Deacon <will.deacon@arm.com>
Cc: linux-arm-kernel@lists.infradead.org
Cc: linux-kernel@vger.kernel.org
---
 arch/arm64/mm/init.c |   17 +++--------------
 1 file changed, 3 insertions(+), 14 deletions(-)

diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c
index e58dd7f..b87bdb8 100644
--- a/arch/arm64/mm/init.c
+++ b/arch/arm64/mm/init.c
@@ -197,14 +197,6 @@ void __init bootmem_init(void)
 	max_pfn = max_low_pfn = max;
 }
 
-/*
- * Poison init memory with an undefined instruction (0x0).
- */
-static inline void poison_init_mem(void *s, size_t count)
-{
-	memset(s, 0, count);
-}
-
 #ifndef CONFIG_SPARSEMEM_VMEMMAP
 static inline void free_memmap(unsigned long start_pfn, unsigned long end_pfn)
 {
@@ -386,8 +378,7 @@ void __init mem_init(void)
 
 void free_initmem(void)
 {
-	poison_init_mem(__init_begin, __init_end - __init_begin);
-	free_initmem_default(-1);
+	free_initmem_default(0);
 }
 
 #ifdef CONFIG_BLK_DEV_INITRD
@@ -396,10 +387,8 @@ static int keep_initrd;
 
 void free_initrd_mem(unsigned long start, unsigned long end)
 {
-	if (!keep_initrd) {
-		poison_init_mem((void *)start, PAGE_ALIGN(end) - start);
-		free_reserved_area(start, end, -1, "initrd");
-	}
+	if (!keep_initrd)
+		free_reserved_area(start, end, 0, "initrd");
 }
 
 static int __init keepinitrd_setup(char *__unused)
-- 
1.7.9.5

[PATCH v5, part3 04/15] mm/x86: use free_reserved_area() to simplify code

[Jiang Liu]

Use common help function free_reserved_area() to simplify code.

Signed-off-by: Jiang Liu <jiang.liu@huawei.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: x86@kernel.org
Cc: Yinghai Lu <yinghai@kernel.org>
Cc: Tang Chen <tangchen@cn.fujitsu.com>
Cc: Wen Congyang <wency@cn.fujitsu.com>
Cc: Jianguo Wu <wujianguo@huawei.com>
Cc: linux-kernel@vger.kernel.org
---
 arch/x86/mm/init.c    |   14 +++-----------
 arch/x86/mm/init_64.c |    5 ++---
 2 files changed, 5 insertions(+), 14 deletions(-)

diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index fdc5dca..6738e1b 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -477,7 +477,6 @@ int devmem_is_allowed(unsigned long pagenr)
 
 void free_init_pages(char *what, unsigned long begin, unsigned long end)
 {
-	unsigned long addr;
 	unsigned long begin_aligned, end_aligned;
 
 	/* Make sure boundaries are page aligned */
@@ -492,8 +491,6 @@ void free_init_pages(char *what, unsigned long begin, unsigned long end)
 	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
@@ -512,18 +509,13 @@ void free_init_pages(char *what, unsigned long begin, unsigned long end)
 	set_memory_nx(begin, (end - begin) >> PAGE_SHIFT);
 	set_memory_rw(begin, (end - begin) >> PAGE_SHIFT);
 
-	printk(KERN_INFO "Freeing %s: %luk freed\n", what, (end - begin) >> 10);
-
-	for (; addr < end; addr += PAGE_SIZE) {
-		memset((void *)addr, POISON_FREE_INITMEM, PAGE_SIZE);
-		free_reserved_page(virt_to_page(addr));
-	}
+	free_reserved_area(begin, end, POISON_FREE_INITMEM, what);
 #endif
 }
 
 void free_initmem(void)
 {
-	free_init_pages("unused kernel memory",
+	free_init_pages("unused kernel",
 			(unsigned long)(&__init_begin),
 			(unsigned long)(&__init_end));
 }
@@ -549,7 +541,7 @@ void __init free_initrd_mem(unsigned long start, unsigned long end)
 	 *   - 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));
+	free_init_pages("initrd", start, PAGE_ALIGN(end));
 }
 #endif
 
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index caad9a0..0c6efb8 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -1165,11 +1165,10 @@ void mark_rodata_ro(void)
 	set_memory_ro(start, (end-start) >> PAGE_SHIFT);
 #endif
 
-	free_init_pages("unused kernel memory",
+	free_init_pages("unused kernel",
 			(unsigned long) __va(__pa_symbol(text_end)),
 			(unsigned long) __va(__pa_symbol(rodata_start)));
-
-	free_init_pages("unused kernel memory",
+	free_init_pages("unused kernel",
 			(unsigned long) __va(__pa_symbol(rodata_end)),
 			(unsigned long) __va(__pa_symbol(_sdata)));
 }
-- 
1.7.9.5

[PATCH v5, part3 05/15] mm/tile: use common help functions to free reserved pages

[Jiang Liu]

Use common help functions to free reserved pages.

Signed-off-by: Jiang Liu <jiang.liu@huawei.com>
Cc: Chris Metcalf <cmetcalf@tilera.com>
Cc: Wen Congyang <wency@cn.fujitsu.com>
Cc: linux-kernel@vger.kernel.org
---
 arch/tile/mm/init.c |    7 ++-----
 1 file changed, 2 insertions(+), 5 deletions(-)

diff --git a/arch/tile/mm/init.c b/arch/tile/mm/init.c
index 2749515..ccfeb3f 100644
--- a/arch/tile/mm/init.c
+++ b/arch/tile/mm/init.c
@@ -720,7 +720,7 @@ static void __init init_free_pfn_range(unsigned long start, unsigned long end)
 		}
 		init_page_count(page);
 		__free_pages(page, order);
-		totalram_pages += count;
+		adjust_managed_page_count(page, count);
 
 		page += count;
 		pfn += count;
@@ -1024,16 +1024,13 @@ static void free_init_pages(char *what, unsigned long begin, unsigned long end)
 			pte_clear(&init_mm, addr, ptep);
 			continue;
 		}
-		__ClearPageReserved(page);
-		init_page_count(page);
 		if (pte_huge(*ptep))
 			BUG_ON(!kdata_huge);
 		else
 			set_pte_at(&init_mm, addr, ptep,
 				   pfn_pte(pfn, PAGE_KERNEL));
 		memset((void *)addr, POISON_FREE_INITMEM, PAGE_SIZE);
-		free_page(addr);
-		totalram_pages++;
+		free_reserved_page(page);
 	}
 	pr_info("Freeing %s: %ldk freed\n", what, (end - begin) >> 10);
 }
-- 
1.7.9.5

[PATCH v5, part3 06/15] mm, powertv: use free_reserved_area() to simplify code

[Jiang Liu]

Use common help function free_reserved_area() to simplify code.

Signed-off-by: Jiang Liu <jiang.liu@huawei.com>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: Jiang Liu <jiang.liu@huawei.com>
Cc: linux-mips@linux-mips.org
Cc: linux-kernel@vger.kernel.org
---
 arch/mips/powertv/asic/asic_devices.c |   13 ++-----------
 1 file changed, 2 insertions(+), 11 deletions(-)

diff --git a/arch/mips/powertv/asic/asic_devices.c b/arch/mips/powertv/asic/asic_devices.c
index d38b095..9f64c23 100644
--- a/arch/mips/powertv/asic/asic_devices.c
+++ b/arch/mips/powertv/asic/asic_devices.c
@@ -529,17 +529,8 @@ EXPORT_SYMBOL(asic_resource_get);
  */
 void platform_release_memory(void *ptr, int size)
 {
-	unsigned long addr;
-	unsigned long end;
-
-	addr = ((unsigned long)ptr + (PAGE_SIZE - 1)) & PAGE_MASK;
-	end = ((unsigned long)ptr + size) & PAGE_MASK;
-
-	for (; addr < end; addr += PAGE_SIZE) {
-		ClearPageReserved(virt_to_page(__va(addr)));
-		init_page_count(virt_to_page(__va(addr)));
-		free_page((unsigned long)__va(addr));
-	}
+	free_reserved_area((unsigned long)ptr, (unsigned long)(ptr + size),
+			   -1, NULL);
 }
 EXPORT_SYMBOL(platform_release_memory);
 
-- 
1.7.9.5

[PATCH v5, part3 07/15] mm, acornfb: use free_reserved_area() to simplify code

[Jiang Liu]

Use common help function free_reserved_area() to simplify code.

Signed-off-by: Jiang Liu <jiang.liu@huawei.com>
Cc: Florian Tobias Schandinat <FlorianSchandinat@gmx.de>
Cc: linux-fbdev@vger.kernel.org
Cc: linux-kernel@vger.kernel.org
---
 drivers/video/acornfb.c |   28 ++--------------------------
 1 file changed, 2 insertions(+), 26 deletions(-)

diff --git a/drivers/video/acornfb.c b/drivers/video/acornfb.c
index 6488a73..344f2bb 100644
--- a/drivers/video/acornfb.c
+++ b/drivers/video/acornfb.c
@@ -1188,32 +1188,8 @@ static int acornfb_detect_monitortype(void)
 static inline void
 free_unused_pages(unsigned int virtual_start, unsigned int virtual_end)
 {
-	int mb_freed = 0;
-
-	/*
-	 * Align addresses
-	 */
-	virtual_start = PAGE_ALIGN(virtual_start);
-	virtual_end = PAGE_ALIGN(virtual_end);
-
-	while (virtual_start < virtual_end) {
-		struct page *page;
-
-		/*
-		 * Clear page reserved bit,
-		 * set count to 1, and free
-		 * the page.
-		 */
-		page = virt_to_page(virtual_start);
-		ClearPageReserved(page);
-		init_page_count(page);
-		free_page(virtual_start);
-
-		virtual_start += PAGE_SIZE;
-		mb_freed += PAGE_SIZE / 1024;
-	}
-
-	printk("acornfb: freed %dK memory\n", mb_freed);
+	free_reserved_area(virtual_start, PAGE_ALIGN(virtual_end),
+			   -1, "acornfb");
 }
 
 static int acornfb_probe(struct platform_device *dev)
-- 
1.7.9.5

[PATCH v5, part3 08/15] mm: fix some trivial typos in comments

[Jiang Liu]

Fix some trivial typos in comments.

Signed-off-by: Jiang Liu <jiang.liu@huawei.com>
Cc: Wen Congyang <wency@cn.fujitsu.com>
Cc: Tang Chen <tangchen@cn.fujitsu.com>
Cc: Jiang Liu <jiang.liu@huawei.com>
Cc: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Marek Szyprowski <m.szyprowski@samsung.com>
Cc: linux-mm@kvack.org
Cc: linux-kernel@vger.kernel.org
---
 mm/memory_hotplug.c |    2 +-
 mm/page_alloc.c     |    2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index a221fac..037d41d 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -309,7 +309,7 @@ static int __meminit move_pfn_range_left(struct zone *z1, struct zone *z2,
 	/* can't move pfns which are higher than @z2 */
 	if (end_pfn > zone_end_pfn(z2))
 		goto out_fail;
-	/* the move out part mast at the left most of @z2 */
+	/* the move out part must be at the left most of @z2 */
 	if (start_pfn > z2->zone_start_pfn)
 		goto out_fail;
 	/* must included/overlap */
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 2045c23..4a9ecd8 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -2863,7 +2863,7 @@ EXPORT_SYMBOL(free_pages_exact);
  * nr_free_zone_pages() counts the number of counts pages which are beyond the
  * high watermark within all zones at or below a given zone index.  For each
  * zone, the number of pages is calculated as:
- *     present_pages - high_pages
+ *     managed_pages - high_pages
  */
 static unsigned long nr_free_zone_pages(int offset)
 {
-- 
1.7.9.5

[PATCH v5, part3 09/15] mm: use managed_pages to calculate default zonelist order

[Jiang Liu]

Use zone->managed_pages instead of zone->present_pages to calculate
default zonelist order because managed_pages means allocatable pages.

Signed-off-by: Jiang Liu <jiang.liu@huawei.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Marek Szyprowski <m.szyprowski@samsung.com>
Cc: linux-mm@kvack.org
Cc: linux-kernel@vger.kernel.org
---
 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 4a9ecd8..1b177bb 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -3449,8 +3449,8 @@ static int default_zonelist_order(void)
 			z = &NODE_DATA(nid)->node_zones[zone_type];
 			if (populated_zone(z)) {
 				if (zone_type < ZONE_NORMAL)
-					low_kmem_size += z->present_pages;
-				total_size += z->present_pages;
+					low_kmem_size += z->managed_pages;
+				total_size += z->managed_pages;
 			} else if (zone_type == ZONE_NORMAL) {
 				/*
 				 * If any node has only lowmem, then node order
-- 
1.7.9.5

[PATCH v5, part3 10/15] mm: accurately calculate zone->managed_pages for highmem zones

[Jiang Liu]

Commit "mm: introduce new field 'managed_pages' to struct zone" assumes
that all highmem pages will be freed into the buddy system by function
mem_init(). But that's not always true, some architectures may reserve
some highmem pages during boot. For example PPC may allocate highmem
pages for giagant HugeTLB pages, and several architectures have code to
check PageReserved flag to exclude highmem pages allocated during boot
when freeing highmem pages into the buddy system.

So treat highmem pages in the same way as normal pages, that is to:
1) reset zone->managed_pages to zero in mem_init().
2) recalculate managed_pages when freeing pages into the buddy system.

Signed-off-by: Jiang Liu <jiang.liu@huawei.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: x86@kernel.org
Cc: Tejun Heo <tj@kernel.org>
Cc: Joonsoo Kim <js1304@gmail.com>
Cc: Yinghai Lu <yinghai@kernel.org>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Kamezawa Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Marek Szyprowski <m.szyprowski@samsung.com>
Cc: linux-kernel@vger.kernel.org
Cc: linux-mm@kvack.org
---
 arch/metag/mm/init.c     |    6 ++++++
 arch/x86/mm/highmem_32.c |    6 ++++++
 include/linux/bootmem.h  |    1 +
 mm/bootmem.c             |   32 ++++++++++++++++++--------------
 mm/nobootmem.c           |   30 ++++++++++++++++--------------
 mm/page_alloc.c          |    1 +
 6 files changed, 48 insertions(+), 28 deletions(-)

diff --git a/arch/metag/mm/init.c b/arch/metag/mm/init.c
index d05b845..58a36f3 100644
--- a/arch/metag/mm/init.c
+++ b/arch/metag/mm/init.c
@@ -380,6 +380,12 @@ void __init mem_init(void)
 
 #ifdef CONFIG_HIGHMEM
 	unsigned long tmp;
+
+	/*
+	 * Explicitly reset zone->managed_pages because highmem pages are
+	 * freed before calling free_all_bootmem_node();
+	 */
+	reset_all_zones_managed_pages();
 	for (tmp = highstart_pfn; tmp < highend_pfn; tmp++)
 		free_highmem_page(pfn_to_page(tmp));
 	num_physpages += totalhigh_pages;
diff --git a/arch/x86/mm/highmem_32.c b/arch/x86/mm/highmem_32.c
index 252b8f5..4500142 100644
--- a/arch/x86/mm/highmem_32.c
+++ b/arch/x86/mm/highmem_32.c
@@ -1,6 +1,7 @@
 #include <linux/highmem.h>
 #include <linux/module.h>
 #include <linux/swap.h> /* for totalram_pages */
+#include <linux/bootmem.h>
 
 void *kmap(struct page *page)
 {
@@ -121,6 +122,11 @@ void __init set_highmem_pages_init(void)
 	struct zone *zone;
 	int nid;
 
+	/*
+	 * Explicitly reset zone->managed_pages because set_highmem_pages_init()
+	 * is invoked before free_all_bootmem()
+	 */
+	reset_all_zones_managed_pages();
 	for_each_zone(zone) {
 		unsigned long zone_start_pfn, zone_end_pfn;
 
diff --git a/include/linux/bootmem.h b/include/linux/bootmem.h
index 5f0b0e1..0e48c32 100644
--- a/include/linux/bootmem.h
+++ b/include/linux/bootmem.h
@@ -46,6 +46,7 @@ extern unsigned long init_bootmem(unsigned long addr, unsigned long memend);
 
 extern unsigned long free_all_bootmem_node(pg_data_t *pgdat);
 extern unsigned long free_all_bootmem(void);
+extern void reset_all_zones_managed_pages(void);
 
 extern void free_bootmem_node(pg_data_t *pgdat,
 			      unsigned long addr,
diff --git a/mm/bootmem.c b/mm/bootmem.c
index d937107..39e6156 100644
--- a/mm/bootmem.c
+++ b/mm/bootmem.c
@@ -242,20 +242,26 @@ static unsigned long __init free_all_bootmem_core(bootmem_data_t *bdata)
 	return count;
 }
 
-static void reset_node_lowmem_managed_pages(pg_data_t *pgdat)
+static int reset_managed_pages_done __initdata;
+
+static inline void __init reset_node_managed_pages(pg_data_t *pgdat)
 {
 	struct zone *z;
 
-	/*
-	 * In free_area_init_core(), highmem zone's managed_pages is set to
-	 * present_pages, and bootmem allocator doesn't allocate from highmem
-	 * zones. So there's no need to recalculate managed_pages because all
-	 * highmem pages will be managed by the buddy system. Here highmem
-	 * zone also includes highmem movable zone.
-	 */
+	if (reset_managed_pages_done)
+		return;
+
 	for (z = pgdat->node_zones; z < pgdat->node_zones + MAX_NR_ZONES; z++)
-		if (!is_highmem(z))
-			z->managed_pages = 0;
+		z->managed_pages = 0;
+}
+
+void __init reset_all_zones_managed_pages(void)
+{
+	struct pglist_data *pgdat;
+
+	for_each_online_pgdat(pgdat)
+		reset_node_managed_pages(pgdat);
+	reset_managed_pages_done = 1;
 }
 
 /**
@@ -267,7 +273,7 @@ static void reset_node_lowmem_managed_pages(pg_data_t *pgdat)
 unsigned long __init free_all_bootmem_node(pg_data_t *pgdat)
 {
 	register_page_bootmem_info_node(pgdat);
-	reset_node_lowmem_managed_pages(pgdat);
+	reset_node_managed_pages(pgdat);
 	return free_all_bootmem_core(pgdat->bdata);
 }
 
@@ -280,10 +286,8 @@ unsigned long __init free_all_bootmem(void)
 {
 	unsigned long total_pages = 0;
 	bootmem_data_t *bdata;
-	struct pglist_data *pgdat;
 
-	for_each_online_pgdat(pgdat)
-		reset_node_lowmem_managed_pages(pgdat);
+	reset_all_zones_managed_pages();
 
 	list_for_each_entry(bdata, &bdata_list, list)
 		total_pages += free_all_bootmem_core(bdata);
diff --git a/mm/nobootmem.c b/mm/nobootmem.c
index bdd3fa2..0ae8d91 100644
--- a/mm/nobootmem.c
+++ b/mm/nobootmem.c
@@ -137,20 +137,25 @@ static unsigned long __init free_low_memory_core_early(void)
 	return count;
 }
 
-static void reset_node_lowmem_managed_pages(pg_data_t *pgdat)
+static int reset_managed_pages_done __initdata;
+
+static inline void __init reset_node_managed_pages(pg_data_t *pgdat)
 {
 	struct zone *z;
 
-	/*
-	 * In free_area_init_core(), highmem zone's managed_pages is set to
-	 * present_pages, and bootmem allocator doesn't allocate from highmem
-	 * zones. So there's no need to recalculate managed_pages because all
-	 * highmem pages will be managed by the buddy system. Here highmem
-	 * zone also includes highmem movable zone.
-	 */
+	if (reset_managed_pages_done)
+		return;
 	for (z = pgdat->node_zones; z < pgdat->node_zones + MAX_NR_ZONES; z++)
-		if (!is_highmem(z))
-			z->managed_pages = 0;
+		z->managed_pages = 0;
+}
+
+void __init reset_all_zones_managed_pages(void)
+{
+	struct pglist_data *pgdat;
+
+	for_each_online_pgdat(pgdat)
+		reset_node_managed_pages(pgdat);
+	reset_managed_pages_done = 1;
 }
 
 /**
@@ -160,10 +165,7 @@ static void reset_node_lowmem_managed_pages(pg_data_t *pgdat)
  */
 unsigned long __init free_all_bootmem(void)
 {
-	struct pglist_data *pgdat;
-
-	for_each_online_pgdat(pgdat)
-		reset_node_lowmem_managed_pages(pgdat);
+	reset_all_zones_managed_pages();
 
 	/*
 	 * We need to use MAX_NUMNODES instead of NODE_DATA(0)->node_id
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 1b177bb..c5c0988 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -5211,6 +5211,7 @@ void free_highmem_page(struct page *page)
 {
 	__free_reserved_page(page);
 	totalram_pages++;
+	page_zone(page)->managed_pages++;
 	totalhigh_pages++;
 }
 #endif
-- 
1.7.9.5

[PATCH v5, part3 11/15] mm: use a dedicated lock to protect totalram_pages and zone->managed_pages

[Jiang Liu]

Currently lock_memory_hotplug()/unlock_memory_hotplug() are used to
protect totalram_pages and zone->managed_pages. Other than the memory
hotplug driver, totalram_pages and zone->managed_pages may also be
modified at runtime by other drivers, such as Xen balloon,
virtio_balloon etc. For those cases, memory hotplug lock is a little
too heavy, so introduce a dedicated lock to protect totalram_pages
and zone->managed_pages.

Now we have a simplified locking rules totalram_pages and
zone->managed_pages as:
1) no locking for read accesses because they are unsigned long.
2) no locking for write accesses at boot time in single-threaded context.
3) serialize write accesses at runtime by acquiring the dedicated
   managed_page_count_lock.

Also adjust zone->managed_pages when freeing reserved pages into the
buddy system, to keep totalram_pages and zone->managed_pages in
consistence.

Signed-off-by: Jiang Liu <jiang.liu@huawei.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Michel Lespinasse <walken@google.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Minchan Kim <minchan@kernel.org>
Cc: linux-mm@kvack.org (open list:MEMORY MANAGEMENT)
Cc: linux-kernel@vger.kernel.org (open list)
---
 include/linux/mm.h     |    6 ++----
 include/linux/mmzone.h |   14 ++++++++++----
 mm/page_alloc.c        |   12 ++++++++++++
 3 files changed, 24 insertions(+), 8 deletions(-)

diff --git a/include/linux/mm.h b/include/linux/mm.h
index 9f7006f..86014c9 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1303,6 +1303,7 @@ extern void free_initmem(void);
  */
 extern unsigned long free_reserved_area(unsigned long start, unsigned long end,
 					int poison, char *s);
+
 #ifdef	CONFIG_HIGHMEM
 /*
  * Free a highmem page into the buddy system, adjusting totalhigh_pages
@@ -1311,10 +1312,7 @@ extern unsigned long free_reserved_area(unsigned long start, unsigned long end,
 extern void free_highmem_page(struct page *page);
 #endif
 
-static inline void adjust_managed_page_count(struct page *page, long count)
-{
-	totalram_pages += count;
-}
+extern void adjust_managed_page_count(struct page *page, long count);
 
 /* Free the reserved page into the buddy system, so it gets managed. */
 static inline void __free_reserved_page(struct page *page)
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 8c9f859..14ca1a9 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -474,10 +474,16 @@ struct zone {
 	 * frequently read in proximity to zone->lock.  It's good to
 	 * give them a chance of being in the same cacheline.
 	 *
-	 * Write access to present_pages and managed_pages at runtime should
-	 * be protected by lock_memory_hotplug()/unlock_memory_hotplug().
-	 * Any reader who can't tolerant drift of present_pages and
-	 * managed_pages should hold memory hotplug lock to get a stable value.
+	 * Write access to present_pages at runtime should be protected by
+	 * lock_memory_hotplug()/unlock_memory_hotplug().  Any reader who can't
+	 * tolerant drift of present_pages should hold memory hotplug lock to
+	 * get a stable value.
+	 *
+	 * Read access to managed_pages should be safe because it's unsigned
+	 * long. Write access to zone->managed_pages and totalram_pages are
+	 * protected by managed_page_count_lock at runtime. Idealy only
+	 * adjust_managed_page_count() should be used instead of directly
+	 * touching zone->managed_pages and totalram_pages.
 	 */
 	unsigned long		spanned_pages;
 	unsigned long		present_pages;
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index c5c0988..9d8209a 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -100,6 +100,9 @@ nodemask_t node_states[NR_NODE_STATES] __read_mostly = {
 };
 EXPORT_SYMBOL(node_states);
 
+/* Protect totalram_pages and zone->managed_pages */
+static DEFINE_SPINLOCK(managed_page_count_lock);
+
 unsigned long totalram_pages __read_mostly;
 unsigned long totalreserve_pages __read_mostly;
 /*
@@ -5186,6 +5189,15 @@ early_param("movablecore", cmdline_parse_movablecore);
 
 #endif /* CONFIG_HAVE_MEMBLOCK_NODE_MAP */
 
+void adjust_managed_page_count(struct page *page, long count)
+{
+	spin_lock(&managed_page_count_lock);
+	page_zone(page)->managed_pages += count;
+	totalram_pages += count;
+	spin_unlock(&managed_page_count_lock);
+}
+EXPORT_SYMBOL(adjust_managed_page_count);
+
 unsigned long free_reserved_area(unsigned long start, unsigned long end,
 				 int poison, char *s)
 {
-- 
1.7.9.5

[PATCH v5, part3 12/15] mm: make __free_pages_bootmem() only available at boot time

[Jiang Liu]

In order to simpilify management of totalram_pages and
zone->managed_pages, make __free_pages_bootmem() only available
at boot time. With this change applied, __free_pages_bootmem()
will only be used by bootmem.c and nobootmem.c at boot time,
so mark it as __init.  Other callers of __free_pages_bootmem()
have been converted to use free_reserved_page(), which handles
totalram_pages and zone->managed_pages in a safer way.

This patch also fix a bug in free_pagetable() for x86_64, which
should increase zone->managed_pages instead of zone->present_pages
when freeing reserved pages.

And now we have managed_pages_count_lock to protect totalram_pages
and zone->managed_pages, so remove the redundant ppb_lock lock in
put_page_bootmem(). This greatly simplifies the locking rules.

Signed-off-by: Jiang Liu <jiang.liu@huawei.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Yinghai Lu <yinghai@kernel.org>
Cc: x86@kernel.org
Cc: Wen Congyang <wency@cn.fujitsu.com>
Cc: Tang Chen <tangchen@cn.fujitsu.com>
Cc: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Minchan Kim <minchan@kernel.org>
Cc: linux-kernel@vger.kernel.org
Cc: linux-mm@kvack.org
---
 arch/x86/mm/init_64.c |   18 ++----------------
 mm/memory_hotplug.c   |   16 ++--------------
 mm/page_alloc.c       |    9 +--------
 3 files changed, 5 insertions(+), 38 deletions(-)

diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index 0c6efb8..6ab46f2 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -711,36 +711,22 @@ EXPORT_SYMBOL_GPL(arch_add_memory);
 
 static void __meminit free_pagetable(struct page *page, int order)
 {
-	struct zone *zone;
-	bool bootmem = false;
 	unsigned long magic;
 	unsigned int nr_pages = 1 << order;
 
 	/* bootmem page has reserved flag */
 	if (PageReserved(page)) {
 		__ClearPageReserved(page);
-		bootmem = true;
 
 		magic = (unsigned long)page->lru.next;
 		if (magic == SECTION_INFO || magic == MIX_SECTION_INFO) {
 			while (nr_pages--)
 				put_page_bootmem(page++);
 		} else
-			__free_pages_bootmem(page, order);
+			while (nr_pages--)
+				free_reserved_page(page++);
 	} else
 		free_pages((unsigned long)page_address(page), order);
-
-	/*
-	 * SECTION_INFO pages and MIX_SECTION_INFO pages
-	 * are all allocated by bootmem.
-	 */
-	if (bootmem) {
-		zone = page_zone(page);
-		zone_span_writelock(zone);
-		zone->present_pages += nr_pages;
-		zone_span_writeunlock(zone);
-		totalram_pages += nr_pages;
-	}
 }
 
 static void __meminit free_pte_table(pte_t *pte_start, pmd_t *pmd)
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 037d41d..c291295 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -101,12 +101,9 @@ void get_page_bootmem(unsigned long info,  struct page *page,
 	atomic_inc(&page->_count);
 }
 
-/* reference to __meminit __free_pages_bootmem is valid
- * so use __ref to tell modpost not to generate a warning */
-void __ref put_page_bootmem(struct page *page)
+void put_page_bootmem(struct page *page)
 {
 	unsigned long type;
-	static DEFINE_MUTEX(ppb_lock);
 
 	type = (unsigned long) page->lru.next;
 	BUG_ON(type < MEMORY_HOTPLUG_MIN_BOOTMEM_TYPE ||
@@ -116,17 +113,8 @@ void __ref put_page_bootmem(struct page *page)
 		ClearPagePrivate(page);
 		set_page_private(page, 0);
 		INIT_LIST_HEAD(&page->lru);
-
-		/*
-		 * Please refer to comment for __free_pages_bootmem()
-		 * for why we serialize here.
-		 */
-		mutex_lock(&ppb_lock);
-		__free_pages_bootmem(page, 0);
-		mutex_unlock(&ppb_lock);
-		totalram_pages++;
+		free_reserved_page(page);
 	}
-
 }
 
 #ifdef CONFIG_HAVE_BOOTMEM_INFO_NODE
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 9d8209a..58b4523 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -745,14 +745,7 @@ static void __free_pages_ok(struct page *page, unsigned int order)
 	local_irq_restore(flags);
 }
 
-/*
- * Read access to zone->managed_pages is safe because it's unsigned long,
- * but we still need to serialize writers. Currently all callers of
- * __free_pages_bootmem() except put_page_bootmem() should only be used
- * at boot time. So for shorter boot time, we shift the burden to
- * put_page_bootmem() to serialize writers.
- */
-void __meminit __free_pages_bootmem(struct page *page, unsigned int order)
+void __init __free_pages_bootmem(struct page *page, unsigned int order)
 {
 	unsigned int nr_pages = 1 << order;
 	unsigned int loop;
-- 
1.7.9.5

[PATCH v5, part3 13/15] mm: correctly update zone->mamaged_pages

[Jiang Liu]

Enhance adjust_managed_page_count() to adjust totalhigh_pages for
highmem pages. And change code which directly adjusts totalram_pages
to use adjust_managed_page_count() because it adjusts totalram_pages,
totalhigh_pages and zone->managed_pages altogether in a safe way.

Remove inc_totalhigh_pages() and dec_totalhigh_pages() from xen/balloon
driver bacause adjust_managed_page_count() has already adjusted
totalhigh_pages.

This patch also fixes two bugs:
1) enhances virtio_balloon driver to adjust totalhigh_pages when
   reserve/unreserve pages.
2) enhance memory_hotplug.c to adjust totalhigh_pages when hot-removing
   memory.

We still need to deal with modifications of totalram_pages in file
arch/powerpc/platforms/pseries/cmm.c, but need help from PPC experts.

Signed-off-by: Jiang Liu <jiang.liu@huawei.com>
Cc: Chris Metcalf <cmetcalf@tilera.com>
Cc: Rusty Russell <rusty@rustcorp.com.au>
Cc: "Michael S. Tsirkin" <mst@redhat.com>
Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Cc: Jeremy Fitzhardinge <jeremy@goop.org>
Cc: Wen Congyang <wency@cn.fujitsu.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Tang Chen <tangchen@cn.fujitsu.com>
Cc: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Minchan Kim <minchan@kernel.org>
Cc: linux-kernel@vger.kernel.org
Cc: virtualization@lists.linux-foundation.org
Cc: xen-devel@lists.xensource.com
Cc: linux-mm@kvack.org
---
 drivers/virtio/virtio_balloon.c |    8 +++++---
 drivers/xen/balloon.c           |   23 +++++------------------
 mm/hugetlb.c                    |    2 +-
 mm/memory_hotplug.c             |   15 +++------------
 mm/page_alloc.c                 |   10 +++++-----
 5 files changed, 19 insertions(+), 39 deletions(-)

diff --git a/drivers/virtio/virtio_balloon.c b/drivers/virtio/virtio_balloon.c
index bd3ae32..6649968 100644
--- a/drivers/virtio/virtio_balloon.c
+++ b/drivers/virtio/virtio_balloon.c
@@ -148,7 +148,7 @@ static void fill_balloon(struct virtio_balloon *vb, size_t num)
 		}
 		set_page_pfns(vb->pfns + vb->num_pfns, page);
 		vb->num_pages += VIRTIO_BALLOON_PAGES_PER_PAGE;
-		totalram_pages--;
+		adjust_managed_page_count(page, -1);
 	}
 
 	/* Did we get any? */
@@ -160,11 +160,13 @@ static void fill_balloon(struct virtio_balloon *vb, size_t num)
 static void release_pages_by_pfn(const u32 pfns[], unsigned int num)
 {
 	unsigned int i;
+	struct page *page;
 
 	/* Find pfns pointing at start of each page, get pages and free them. */
 	for (i = 0; i < num; i += VIRTIO_BALLOON_PAGES_PER_PAGE) {
-		balloon_page_free(balloon_pfn_to_page(pfns[i]));
-		totalram_pages++;
+		page = balloon_pfn_to_page(pfns[i]);
+		balloon_page_free(page);
+		adjust_managed_page_count(page, 1);
 	}
 }
 
diff --git a/drivers/xen/balloon.c b/drivers/xen/balloon.c
index d42da3b..a453c05 100644
--- a/drivers/xen/balloon.c
+++ b/drivers/xen/balloon.c
@@ -89,14 +89,6 @@ EXPORT_SYMBOL_GPL(balloon_stats);
 /* We increase/decrease in batches which fit in a page */
 static xen_pfn_t frame_list[PAGE_SIZE / sizeof(unsigned long)];
 
-#ifdef CONFIG_HIGHMEM
-#define inc_totalhigh_pages() (totalhigh_pages++)
-#define dec_totalhigh_pages() (totalhigh_pages--)
-#else
-#define inc_totalhigh_pages() do {} while (0)
-#define dec_totalhigh_pages() do {} while (0)
-#endif
-
 /* List of ballooned pages, threaded through the mem_map array. */
 static LIST_HEAD(ballooned_pages);
 
@@ -132,9 +124,7 @@ static void __balloon_append(struct page *page)
 static void balloon_append(struct page *page)
 {
 	__balloon_append(page);
-	if (PageHighMem(page))
-		dec_totalhigh_pages();
-	totalram_pages--;
+	adjust_managed_page_count(page, -1);
 }
 
 /* balloon_retrieve: rescue a page from the balloon, if it is not empty. */
@@ -151,13 +141,12 @@ static struct page *balloon_retrieve(bool prefer_highmem)
 		page = list_entry(ballooned_pages.next, struct page, lru);
 	list_del(&page->lru);
 
-	if (PageHighMem(page)) {
+	if (PageHighMem(page))
 		balloon_stats.balloon_high--;
-		inc_totalhigh_pages();
-	} else
+	else
 		balloon_stats.balloon_low--;
 
-	totalram_pages++;
+	adjust_managed_page_count(page, 1);
 
 	return page;
 }
@@ -374,9 +363,7 @@ static enum bp_state increase_reservation(unsigned long nr_pages)
 #endif
 
 		/* Relinquish the page back to the allocator. */
-		ClearPageReserved(page);
-		init_page_count(page);
-		__free_page(page);
+		__free_reserved_page(page);
 	}
 
 	balloon_stats.current_pages += rc;
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index f8feeec..95c5a6b 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -1246,7 +1246,7 @@ static void __init gather_bootmem_prealloc(void)
 		 * side-effects, like CommitLimit going negative.
 		 */
 		if (h->order > (MAX_ORDER - 1))
-			totalram_pages += 1 << h->order;
+			adjust_managed_page_count(page, 1 << h->order);
 	}
 }
 
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index c291295..304ada7 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -769,20 +769,13 @@ EXPORT_SYMBOL_GPL(__online_page_set_limits);
 
 void __online_page_increment_counters(struct page *page)
 {
-	totalram_pages++;
-
-#ifdef CONFIG_HIGHMEM
-	if (PageHighMem(page))
-		totalhigh_pages++;
-#endif
+	adjust_managed_page_count(page, 1);
 }
 EXPORT_SYMBOL_GPL(__online_page_increment_counters);
 
 void __online_page_free(struct page *page)
 {
-	ClearPageReserved(page);
-	init_page_count(page);
-	__free_page(page);
+	__free_reserved_page(page);
 }
 EXPORT_SYMBOL_GPL(__online_page_free);
 
@@ -979,7 +972,6 @@ int __ref online_pages(unsigned long pfn, unsigned long nr_pages, int online_typ
 		return ret;
 	}
 
-	zone->managed_pages += onlined_pages;
 	zone->present_pages += onlined_pages;
 	zone->zone_pgdat->node_present_pages += onlined_pages;
 	if (onlined_pages) {
@@ -1563,10 +1555,9 @@ repeat:
 	/* reset pagetype flags and makes migrate type to be MOVABLE */
 	undo_isolate_page_range(start_pfn, end_pfn, MIGRATE_MOVABLE);
 	/* removal success */
-	zone->managed_pages -= offlined_pages;
+	adjust_managed_page_count(pfn_to_page(start_pfn), -offlined_pages);
 	zone->present_pages -= offlined_pages;
 	zone->zone_pgdat->node_present_pages -= offlined_pages;
-	totalram_pages -= offlined_pages;
 
 	init_per_zone_wmark_min();
 
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 58b4523..eabfbcb 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -780,11 +780,7 @@ void __init init_cma_reserved_pageblock(struct page *page)
 	set_page_refcounted(page);
 	set_pageblock_migratetype(page, MIGRATE_CMA);
 	__free_pages(page, pageblock_order);
-	totalram_pages += pageblock_nr_pages;
-#ifdef CONFIG_HIGHMEM
-	if (PageHighMem(page))
-		totalhigh_pages += pageblock_nr_pages;
-#endif
+	adjust_managed_page_count(page, pageblock_nr_pages);
 }
 #endif
 
@@ -5187,6 +5183,10 @@ void adjust_managed_page_count(struct page *page, long count)
 	spin_lock(&managed_page_count_lock);
 	page_zone(page)->managed_pages += count;
 	totalram_pages += count;
+#ifdef	CONFIG_HIGHMEM
+	if (PageHighMem(page))
+		totalhigh_pages += count;
+#endif
 	spin_unlock(&managed_page_count_lock);
 }
 EXPORT_SYMBOL(adjust_managed_page_count);
-- 
1.7.9.5

[PATCH v5, part3 14/15] mm: concentrate modification of totalram_pages into the mm core

[Jiang Liu]

Concentrate code to modify totalram_pages into the mm core, so the arch
memory initialized code doesn't need to take care of it. With these
changes applied, only following functions from mm core modify global
variable totalram_pages:
free_bootmem_late(), free_all_bootmem(), free_all_bootmem_node(),
adjust_managed_page_count().

With this patch applied, it will be much more easier for us to keep
totalram_pages and zone->managed_pages in consistence.

Signed-off-by: Jiang Liu <jiang.liu@huawei.com>
---
 arch/alpha/mm/init.c             |    2 +-
 arch/alpha/mm/numa.c             |    2 +-
 arch/arc/mm/init.c               |    2 +-
 arch/arm/mm/init.c               |    3 +--
 arch/arm64/mm/init.c             |    2 +-
 arch/avr32/mm/init.c             |    2 --
 arch/blackfin/mm/init.c          |    2 +-
 arch/c6x/mm/init.c               |    2 +-
 arch/cris/mm/init.c              |    2 +-
 arch/frv/mm/init.c               |    2 +-
 arch/h8300/mm/init.c             |    2 +-
 arch/hexagon/mm/init.c           |    2 +-
 arch/ia64/mm/init.c              |    2 +-
 arch/m32r/mm/init.c              |    2 +-
 arch/m68k/mm/init.c              |    4 ++--
 arch/metag/mm/init.c             |    5 +----
 arch/microblaze/mm/init.c        |    2 +-
 arch/mips/mm/init.c              |    2 +-
 arch/mips/sgi-ip27/ip27-memory.c |    2 +-
 arch/mn10300/mm/init.c           |    2 +-
 arch/openrisc/mm/init.c          |    2 +-
 arch/parisc/mm/init.c            |    4 ++--
 arch/powerpc/mm/mem.c            |    5 ++---
 arch/s390/mm/init.c              |    2 +-
 arch/score/mm/init.c             |    2 +-
 arch/sh/mm/init.c                |    2 +-
 arch/sparc/mm/init_32.c          |    3 +--
 arch/sparc/mm/init_64.c          |    2 +-
 arch/tile/mm/init.c              |    2 +-
 arch/um/kernel/mem.c             |    2 +-
 arch/unicore32/mm/init.c         |    2 +-
 arch/x86/mm/init_32.c            |    2 +-
 arch/x86/mm/init_64.c            |    2 +-
 arch/xtensa/mm/init.c            |    2 +-
 mm/bootmem.c                     |    9 ++++++++-
 mm/nobootmem.c                   |    7 ++++++-
 36 files changed, 50 insertions(+), 46 deletions(-)

diff --git a/arch/alpha/mm/init.c b/arch/alpha/mm/init.c
index 9930837..ca07a97 100644
--- a/arch/alpha/mm/init.c
+++ b/arch/alpha/mm/init.c
@@ -309,7 +309,7 @@ void __init
 mem_init(void)
 {
 	max_mapnr = num_physpages = max_low_pfn;
-	totalram_pages += free_all_bootmem();
+	free_all_bootmem();
 	high_memory = (void *) __va(max_low_pfn * PAGE_SIZE);
 
 	printk_memory_info();
diff --git a/arch/alpha/mm/numa.c b/arch/alpha/mm/numa.c
index 3388504..857452c 100644
--- a/arch/alpha/mm/numa.c
+++ b/arch/alpha/mm/numa.c
@@ -334,7 +334,7 @@ void __init mem_init(void)
 		/*
 		 * This will free up the bootmem, ie, slot 0 memory
 		 */
-		totalram_pages += free_all_bootmem_node(NODE_DATA(nid));
+		free_all_bootmem_node(NODE_DATA(nid));
 
 		pfn = NODE_DATA(nid)->node_start_pfn;
 		for (i = 0; i < node_spanned_pages(nid); i++, pfn++)
diff --git a/arch/arc/mm/init.c b/arch/arc/mm/init.c
index 4a17736..78d8c31 100644
--- a/arch/arc/mm/init.c
+++ b/arch/arc/mm/init.c
@@ -111,7 +111,7 @@ void __init mem_init(void)
 
 	high_memory = (void *)(CONFIG_LINUX_LINK_BASE + arc_mem_sz);
 
-	totalram_pages = free_all_bootmem();
+	free_all_bootmem();
 
 	/* count all reserved pages [kernel code/data/mem_map..] */
 	reserved_pages = 0;
diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c
index a2ab290..add4fcb 100644
--- a/arch/arm/mm/init.c
+++ b/arch/arm/mm/init.c
@@ -595,8 +595,7 @@ void __init mem_init(void)
 
 	/* this will put all unused low memory onto the freelists */
 	free_unused_memmap(&meminfo);
-
-	totalram_pages += free_all_bootmem();
+	free_all_bootmem();
 
 #ifdef CONFIG_SA1111
 	/* now that our DMA memory is actually so designated, we can free it */
diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c
index b87bdb8..0f2cf5d 100644
--- a/arch/arm64/mm/init.c
+++ b/arch/arm64/mm/init.c
@@ -284,7 +284,7 @@ void __init mem_init(void)
 	free_unused_memmap();
 #endif
 
-	totalram_pages += free_all_bootmem();
+	free_all_bootmem();
 
 	reserved_pages = free_pages = 0;
 
diff --git a/arch/avr32/mm/init.c b/arch/avr32/mm/init.c
index 871f98a..7e8d55a 100644
--- a/arch/avr32/mm/init.c
+++ b/arch/avr32/mm/init.c
@@ -117,8 +117,6 @@ void __init mem_init(void)
 		if (pgdat->node_spanned_pages != 0)
 			node_pages = free_all_bootmem_node(pgdat);
 
-		totalram_pages += node_pages;
-
 		for (i = 0; i < node_pages; i++)
 			if (PageReserved(pgdat->node_mem_map + i))
 				reservedpages++;
diff --git a/arch/blackfin/mm/init.c b/arch/blackfin/mm/init.c
index e64286b..1cc8607 100644
--- a/arch/blackfin/mm/init.c
+++ b/arch/blackfin/mm/init.c
@@ -104,7 +104,7 @@ void __init mem_init(void)
 	printk(KERN_DEBUG "Kernel managed physical pages: %lu\n", num_physpages);
 
 	/* This will put all low memory onto the freelists. */
-	totalram_pages = free_all_bootmem();
+	free_all_bootmem();
 
 	reservedpages = 0;
 	for (tmp = ARCH_PFN_OFFSET; tmp < max_mapnr; tmp++)
diff --git a/arch/c6x/mm/init.c b/arch/c6x/mm/init.c
index ce39b48..2c51474 100644
--- a/arch/c6x/mm/init.c
+++ b/arch/c6x/mm/init.c
@@ -64,7 +64,7 @@ void __init mem_init(void)
 	high_memory = (void *)(memory_end & PAGE_MASK);
 
 	/* this will put all memory onto the freelists */
-	totalram_pages = free_all_bootmem();
+	free_all_bootmem();
 
 	codek = (_etext - _stext) >> 10;
 	datak = (_end - _sdata) >> 10;
diff --git a/arch/cris/mm/init.c b/arch/cris/mm/init.c
index 8fec263..52b8b56 100644
--- a/arch/cris/mm/init.c
+++ b/arch/cris/mm/init.c
@@ -33,7 +33,7 @@ mem_init(void)
 	max_mapnr = num_physpages = max_low_pfn - min_low_pfn;
  
 	/* this will put all memory onto the freelists */
-        totalram_pages = free_all_bootmem();
+        free_all_bootmem();
 
 	reservedpages = 0;
 	for (tmp = 0; tmp < max_mapnr; tmp++) {
diff --git a/arch/frv/mm/init.c b/arch/frv/mm/init.c
index a421948..4215822 100644
--- a/arch/frv/mm/init.c
+++ b/arch/frv/mm/init.c
@@ -123,7 +123,7 @@ void __init mem_init(void)
 	int codek = 0, datak = 0;
 
 	/* this will put all low memory onto the freelists */
-	totalram_pages = free_all_bootmem();
+	free_all_bootmem();
 
 #ifdef CONFIG_MMU
 	for (loop = 0 ; loop < npages ; loop++)
diff --git a/arch/h8300/mm/init.c b/arch/h8300/mm/init.c
index 488e2a3..22fd869 100644
--- a/arch/h8300/mm/init.c
+++ b/arch/h8300/mm/init.c
@@ -140,7 +140,7 @@ void __init mem_init(void)
 	max_mapnr = num_physpages = MAP_NR(high_memory);
 
 	/* this will put all low memory onto the freelists */
-	totalram_pages = free_all_bootmem();
+	free_all_bootmem();
 
 	codek = (_etext - _stext) >> 10;
 	datak = (__bss_stop - _sdata) >> 10;
diff --git a/arch/hexagon/mm/init.c b/arch/hexagon/mm/init.c
index 2561d25..0ab5b43 100644
--- a/arch/hexagon/mm/init.c
+++ b/arch/hexagon/mm/init.c
@@ -70,7 +70,7 @@ unsigned long long kmap_generation;
 void __init mem_init(void)
 {
 	/*  No idea where this is actually declared.  Seems to evade LXR.  */
-	totalram_pages += free_all_bootmem();
+	free_all_bootmem();
 	num_physpages = bootmem_lastpg-ARCH_PFN_OFFSET;
 
 	printk(KERN_INFO "totalram_pages = %ld\n", totalram_pages);
diff --git a/arch/ia64/mm/init.c b/arch/ia64/mm/init.c
index 941568a..b5b71e8 100644
--- a/arch/ia64/mm/init.c
+++ b/arch/ia64/mm/init.c
@@ -623,7 +623,7 @@ mem_init (void)
 
 	for_each_online_pgdat(pgdat)
 		if (pgdat->bdata->node_bootmem_map)
-			totalram_pages += free_all_bootmem_node(pgdat);
+			free_all_bootmem_node(pgdat);
 
 	reserved_pages = 0;
 	efi_memmap_walk(count_reserved_pages, &reserved_pages);
diff --git a/arch/m32r/mm/init.c b/arch/m32r/mm/init.c
index 58ea4d6..c421c31 100644
--- a/arch/m32r/mm/init.c
+++ b/arch/m32r/mm/init.c
@@ -158,7 +158,7 @@ void __init mem_init(void)
 
 	/* this will put all low memory onto the freelists */
 	for_each_online_node(nid)
-		totalram_pages += free_all_bootmem_node(NODE_DATA(nid));
+		free_all_bootmem_node(NODE_DATA(nid));
 
 	reservedpages = reservedpages_count() - hole_pages;
 	codesize = (unsigned long) &_etext - (unsigned long)&_text;
diff --git a/arch/m68k/mm/init.c b/arch/m68k/mm/init.c
index 75e1cbf..2485a8c 100644
--- a/arch/m68k/mm/init.c
+++ b/arch/m68k/mm/init.c
@@ -155,11 +155,11 @@ void __init mem_init(void)
 	int i;
 
 	/* this will put all memory onto the freelists */
-	totalram_pages = num_physpages = 0;
+	num_physpages = 0;
 	for_each_online_pgdat(pgdat) {
 		num_physpages += pgdat->node_present_pages;
 
-		totalram_pages += free_all_bootmem_node(pgdat);
+		free_all_bootmem_node(pgdat);
 		for (i = 0; i < pgdat->node_spanned_pages; i++) {
 			struct page *page = pgdat->node_mem_map + i;
 			char *addr = page_to_virt(page);
diff --git a/arch/metag/mm/init.c b/arch/metag/mm/init.c
index 58a36f3..279d701 100644
--- a/arch/metag/mm/init.c
+++ b/arch/metag/mm/init.c
@@ -393,14 +393,11 @@ void __init mem_init(void)
 
 	for_each_online_node(nid) {
 		pg_data_t *pgdat = NODE_DATA(nid);
-		unsigned long node_pages = 0;
 
 		num_physpages += pgdat->node_present_pages;
 
 		if (pgdat->node_spanned_pages)
-			node_pages = free_all_bootmem_node(pgdat);
-
-		totalram_pages += node_pages;
+			free_all_bootmem_node(pgdat);
 	}
 
 	pr_info("Memory: %luk/%luk available\n",
diff --git a/arch/microblaze/mm/init.c b/arch/microblaze/mm/init.c
index 53383e4..fb7f248 100644
--- a/arch/microblaze/mm/init.c
+++ b/arch/microblaze/mm/init.c
@@ -252,7 +252,7 @@ void __init mem_init(void)
 	high_memory = (void *)__va(memory_start + lowmem_size - 1);
 
 	/* this will put all memory onto the freelists */
-	totalram_pages += free_all_bootmem();
+	free_all_bootmem();
 
 	for_each_online_pgdat(pgdat) {
 		unsigned long i;
diff --git a/arch/mips/mm/init.c b/arch/mips/mm/init.c
index 3d0346d..de4ff2f 100644
--- a/arch/mips/mm/init.c
+++ b/arch/mips/mm/init.c
@@ -373,7 +373,7 @@ void __init mem_init(void)
 #endif
 	high_memory = (void *) __va(max_low_pfn << PAGE_SHIFT);
 
-	totalram_pages += free_all_bootmem();
+	free_all_bootmem();
 	setup_zero_pages();	/* Setup zeroed pages.  */
 
 	reservedpages = ram = 0;
diff --git a/arch/mips/sgi-ip27/ip27-memory.c b/arch/mips/sgi-ip27/ip27-memory.c
index 5f2bddb..936e617 100644
--- a/arch/mips/sgi-ip27/ip27-memory.c
+++ b/arch/mips/sgi-ip27/ip27-memory.c
@@ -489,7 +489,7 @@ void __init mem_init(void)
 		/*
 		 * This will free up the bootmem, ie, slot 0 memory.
 		 */
-		totalram_pages += free_all_bootmem_node(NODE_DATA(node));
+		free_all_bootmem_node(NODE_DATA(node));
 	}
 
 	setup_zero_pages();	/* This comes from node 0 */
diff --git a/arch/mn10300/mm/init.c b/arch/mn10300/mm/init.c
index 5a8ace6..d7312aa 100644
--- a/arch/mn10300/mm/init.c
+++ b/arch/mn10300/mm/init.c
@@ -114,7 +114,7 @@ void __init mem_init(void)
 	memset(empty_zero_page, 0, PAGE_SIZE);
 
 	/* this will put all low memory onto the freelists */
-	totalram_pages += free_all_bootmem();
+	free_all_bootmem();
 
 	reservedpages = 0;
 	for (tmp = 0; tmp < num_physpages; tmp++)
diff --git a/arch/openrisc/mm/init.c b/arch/openrisc/mm/init.c
index d19950c..da26482 100644
--- a/arch/openrisc/mm/init.c
+++ b/arch/openrisc/mm/init.c
@@ -207,7 +207,7 @@ static int __init free_pages_init(void)
 	int reservedpages, pfn;
 
 	/* this will put all low memory onto the freelists */
-	totalram_pages = free_all_bootmem();
+	free_all_bootmem();
 
 	reservedpages = 0;
 	for (pfn = 0; pfn < max_low_pfn; pfn++) {
diff --git a/arch/parisc/mm/init.c b/arch/parisc/mm/init.c
index 27f3f88..1fe9d841 100644
--- a/arch/parisc/mm/init.c
+++ b/arch/parisc/mm/init.c
@@ -593,13 +593,13 @@ void __init mem_init(void)
 
 #ifndef CONFIG_DISCONTIGMEM
 	max_mapnr = page_to_pfn(virt_to_page(high_memory - 1)) + 1;
-	totalram_pages += free_all_bootmem();
+	free_all_bootmem();
 #else
 	{
 		int i;
 
 		for (i = 0; i < npmem_ranges; i++)
-			totalram_pages += free_all_bootmem_node(NODE_DATA(i));
+			free_all_bootmem_node(NODE_DATA(i));
 	}
 #endif
 
diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c
index 632ab53..b890245 100644
--- a/arch/powerpc/mm/mem.c
+++ b/arch/powerpc/mm/mem.c
@@ -318,13 +318,12 @@ void __init mem_init(void)
         for_each_online_node(nid) {
 		if (NODE_DATA(nid)->node_spanned_pages != 0) {
 			printk("freeing bootmem node %d\n", nid);
-			totalram_pages +=
-				free_all_bootmem_node(NODE_DATA(nid));
+			free_all_bootmem_node(NODE_DATA(nid));
 		}
 	}
 #else
 	max_mapnr = max_pfn;
-	totalram_pages += free_all_bootmem();
+	free_all_bootmem();
 #endif
 	for_each_online_pgdat(pgdat) {
 		for (i = 0; i < pgdat->node_spanned_pages; i++) {
diff --git a/arch/s390/mm/init.c b/arch/s390/mm/init.c
index 275345e..24d52aa 100644
--- a/arch/s390/mm/init.c
+++ b/arch/s390/mm/init.c
@@ -142,7 +142,7 @@ void __init mem_init(void)
 	cmma_init();
 
 	/* this will put all low memory onto the freelists */
-	totalram_pages += free_all_bootmem();
+	free_all_bootmem();
 	setup_zero_pages();	/* Setup zeroed pages. */
 
 	reservedpages = 0;
diff --git a/arch/score/mm/init.c b/arch/score/mm/init.c
index 1592aad..579fc4e 100644
--- a/arch/score/mm/init.c
+++ b/arch/score/mm/init.c
@@ -81,7 +81,7 @@ void __init mem_init(void)
 	unsigned long tmp, ram = 0;
 
 	high_memory = (void *) __va(max_low_pfn << PAGE_SHIFT);
-	totalram_pages += free_all_bootmem();
+	free_all_bootmem();
 	setup_zero_page();	/* Setup zeroed pages. */
 	reservedpages = 0;
 
diff --git a/arch/sh/mm/init.c b/arch/sh/mm/init.c
index 31294f1..aecd913 100644
--- a/arch/sh/mm/init.c
+++ b/arch/sh/mm/init.c
@@ -422,7 +422,7 @@ void __init mem_init(void)
 		num_physpages += pgdat->node_present_pages;
 
 		if (pgdat->node_spanned_pages)
-			totalram_pages += free_all_bootmem_node(pgdat);
+			free_all_bootmem_node(pgdat);
 
 
 		node_high_memory = (void *)__va((pgdat->node_start_pfn +
diff --git a/arch/sparc/mm/init_32.c b/arch/sparc/mm/init_32.c
index af472cf..e96afed 100644
--- a/arch/sparc/mm/init_32.c
+++ b/arch/sparc/mm/init_32.c
@@ -323,8 +323,7 @@ void __init mem_init(void)
 
 	max_mapnr = last_valid_pfn - pfn_base;
 	high_memory = __va(max_low_pfn << PAGE_SHIFT);
-
-	totalram_pages = free_all_bootmem();
+	free_all_bootmem();
 
 	for (i = 0; sp_banks[i].num_bytes != 0; i++) {
 		unsigned long start_pfn = sp_banks[i].base_addr >> PAGE_SHIFT;
diff --git a/arch/sparc/mm/init_64.c b/arch/sparc/mm/init_64.c
index a717199..c93c7c2 100644
--- a/arch/sparc/mm/init_64.c
+++ b/arch/sparc/mm/init_64.c
@@ -2054,7 +2054,7 @@ void __init mem_init(void)
 	high_memory = __va(last_valid_pfn << PAGE_SHIFT);
 
 	register_page_bootmem_info();
-	totalram_pages = free_all_bootmem();
+	free_all_bootmem();
 
 	/* We subtract one to account for the mem_map_zero page
 	 * allocated below.
diff --git a/arch/tile/mm/init.c b/arch/tile/mm/init.c
index ccfeb3f..45ce26d 100644
--- a/arch/tile/mm/init.c
+++ b/arch/tile/mm/init.c
@@ -846,7 +846,7 @@ void __init mem_init(void)
 	set_max_mapnr_init();
 
 	/* this will put all bootmem onto the freelists */
-	totalram_pages += free_all_bootmem();
+	free_all_bootmem();
 
 #ifndef CONFIG_64BIT
 	/* count all remaining LOWMEM and give all HIGHMEM to page allocator */
diff --git a/arch/um/kernel/mem.c b/arch/um/kernel/mem.c
index 1e84189..a7dc6c1 100644
--- a/arch/um/kernel/mem.c
+++ b/arch/um/kernel/mem.c
@@ -65,7 +65,7 @@ void __init mem_init(void)
 	uml_reserved = brk_end;
 
 	/* this will put all low memory onto the freelists */
-	totalram_pages = free_all_bootmem();
+	free_all_bootmem();
 	max_low_pfn = totalram_pages;
 #ifdef CONFIG_HIGHMEM
 	setup_highmem(end_iomem, highmem);
diff --git a/arch/unicore32/mm/init.c b/arch/unicore32/mm/init.c
index 5614b05..119b9e8 100644
--- a/arch/unicore32/mm/init.c
+++ b/arch/unicore32/mm/init.c
@@ -392,7 +392,7 @@ void __init mem_init(void)
 	free_unused_memmap(&meminfo);
 
 	/* this will put all unused low memory onto the freelists */
-	totalram_pages += free_all_bootmem();
+	free_all_bootmem();
 
 	reserved_pages = free_pages = 0;
 
diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c
index 3ac7e31..9fa46ba 100644
--- a/arch/x86/mm/init_32.c
+++ b/arch/x86/mm/init_32.c
@@ -759,7 +759,7 @@ void __init mem_init(void)
 	set_highmem_pages_init();
 
 	/* this will put all low memory onto the freelists */
-	totalram_pages += free_all_bootmem();
+	free_all_bootmem();
 
 	reservedpages = 0;
 	for (tmp = 0; tmp < max_low_pfn; tmp++)
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index 6ab46f2..65116e5 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -1053,7 +1053,7 @@ void __init mem_init(void)
 	register_page_bootmem_info();
 
 	/* this will put all memory onto the freelists */
-	totalram_pages = free_all_bootmem();
+	free_all_bootmem();
 
 	absent_pages = absent_pages_in_range(0, max_pfn);
 	reservedpages = max_pfn - totalram_pages - absent_pages;
diff --git a/arch/xtensa/mm/init.c b/arch/xtensa/mm/init.c
index 6f70647..dc6e009 100644
--- a/arch/xtensa/mm/init.c
+++ b/arch/xtensa/mm/init.c
@@ -184,7 +184,7 @@ void __init mem_init(void)
 #error HIGHGMEM not implemented in init.c
 #endif
 
-	totalram_pages += free_all_bootmem();
+	free_all_bootmem();
 
 	reservedpages = ram = 0;
 	for (tmp = 0; tmp < max_mapnr; tmp++) {
diff --git a/mm/bootmem.c b/mm/bootmem.c
index 39e6156..a19404b 100644
--- a/mm/bootmem.c
+++ b/mm/bootmem.c
@@ -272,9 +272,14 @@ void __init reset_all_zones_managed_pages(void)
  */
 unsigned long __init free_all_bootmem_node(pg_data_t *pgdat)
 {
+	unsigned long pages;
+
 	register_page_bootmem_info_node(pgdat);
 	reset_node_managed_pages(pgdat);
-	return free_all_bootmem_core(pgdat->bdata);
+	pages = free_all_bootmem_core(pgdat->bdata);
+	totalram_pages += pages;
+
+	return pages;
 }
 
 /**
@@ -292,6 +297,8 @@ unsigned long __init free_all_bootmem(void)
 	list_for_each_entry(bdata, &bdata_list, list)
 		total_pages += free_all_bootmem_core(bdata);
 
+	totalram_pages += total_pages;
+
 	return total_pages;
 }
 
diff --git a/mm/nobootmem.c b/mm/nobootmem.c
index 0ae8d91..61107cf 100644
--- a/mm/nobootmem.c
+++ b/mm/nobootmem.c
@@ -165,6 +165,8 @@ void __init reset_all_zones_managed_pages(void)
  */
 unsigned long __init free_all_bootmem(void)
 {
+	unsigned long pages;
+
 	reset_all_zones_managed_pages();
 
 	/*
@@ -172,7 +174,10 @@ unsigned long __init free_all_bootmem(void)
 	 *  because in some case like Node0 doesn't have RAM installed
 	 *  low ram will be on Node1
 	 */
-	return free_low_memory_core_early();
+	pages = free_low_memory_core_early();
+	totalram_pages += pages;
+
+	return pages;
 }
 
 /**
-- 
1.7.9.5

[PATCH v5, part3 15/15] mm: report available pages as "MemTotal" for each NUMA node

[Jiang Liu]

As reported by https://bugzilla.kernel.org/show_bug.cgi?id=53501,
"MemTotal" from /proc/meminfo means memory pages managed by the buddy
system (managed_pages), but "MemTotal" from /sys/.../node/nodex/meminfo
means phsical pages present (present_pages) within the NUMA node.
There's a difference between managed_pages and present_pages due to
bootmem allocator and reserved pages.

And Documentation/filesystems/proc.txt says
    MemTotal: Total usable ram (i.e. physical ram minus a few reserved
              bits and the kernel binary code)

So change /sys/.../node/nodex/meminfo to report available pages within
the node as "MemTotal".

Signed-off-by: Jiang Liu <jiang.liu@huawei.com>
Reported-by: sworddragon2@aol.com
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Minchan Kim <minchan@kernel.org>
Cc: linux-mm@kvack.org
Cc: linux-kernel@vger.kernel.org
---
 mm/page_alloc.c |    6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index eabfbcb..d49cb72 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -2922,9 +2922,13 @@ EXPORT_SYMBOL(si_meminfo);
 #ifdef CONFIG_NUMA
 void si_meminfo_node(struct sysinfo *val, int nid)
 {
+	int zone_type;		/* needs to be signed */
+	unsigned long managed_pages = 0;
 	pg_data_t *pgdat = NODE_DATA(nid);
 
-	val->totalram = pgdat->node_present_pages;
+	for (zone_type = 0; zone_type < MAX_NR_ZONES; zone_type++)
+		managed_pages += pgdat->node_zones[zone_type].managed_pages;
+	val->totalram = managed_pages;
 	val->freeram = node_page_state(nid, NR_FREE_PAGES);
 #ifdef CONFIG_HIGHMEM
 	val->totalhigh = pgdat->node_zones[ZONE_HIGHMEM].managed_pages;
-- 
1.7.9.5

Re: [PATCH v5, part3 11/15] mm: use a dedicated lock to protect totalram_pages and zone->managed_pages

[Jiang Liu]

On 05/08/2013 11:27 PM, Rik van Riel wrote:
> On 05/08/2013 11:17 AM, Jiang Liu wrote:
> 
>> @@ -5186,6 +5189,15 @@ early_param("movablecore", cmdline_parse_movablecore);
>>
>>   #endif /* CONFIG_HAVE_MEMBLOCK_NODE_MAP */
>>
>> +void adjust_managed_page_count(struct page *page, long count)
>> +{
>> +    spin_lock(&managed_page_count_lock);
>> +    page_zone(page)->managed_pages += count;
>> +    totalram_pages += count;
>> +    spin_unlock(&managed_page_count_lock);
>> +}
>> +EXPORT_SYMBOL(adjust_managed_page_count);
>> +
> 
> Something I should have thought of when I reviewed the patch
> last time, but forgot...
> 
> What happens when the hotplug event adds more pages than fit
> in this zone, and some of the pages should go in the next
> zone?
> 
> For example, think about a 3GB x86_64 machine, which gets
> 2GB of memory hot-added. Roughly half may get added to the
> DMA32 zone, the rest to the NORMAL zone.
> 
> Do the callers of adjust_managed_page_count correctly make
> one call for each zone, or does the above code open up a
> window for a bug?
Hi Rik,
	Thanks for review! 
	Yes, the caller will make one call for each zone. Actually it will
call adjust_managed_page_count() for each page.
	Regards!
	Gerry

Re: [PATCH v5, part3 01/15] mm: fix build warnings caused by free_reserved_area()

[Russell King - ARM Linux]

On Wed, May 08, 2013 at 11:17:00PM +0800, Jiang Liu wrote:
> Fix following build warnings cuased by free_reserved_area():
> 
> arch/arm/mm/init.c: In function 'mem_init':
> arch/arm/mm/init.c:603:2: warning: passing argument 1 of 'free_reserved_area' makes integer from pointer without a cast [enabled by default]
>   free_reserved_area(__va(PHYS_PFN_OFFSET), swapper_pg_dir, 0, NULL);
>   ^
> In file included from include/linux/mman.h:4:0,
>                  from arch/arm/mm/init.c:15:
> include/linux/mm.h:1301:22: note: expected 'long unsigned int' but argument is of type 'void *'
>  extern unsigned long free_reserved_area(unsigned long start, unsigned long end,
> 
>    mm/page_alloc.c: In function 'free_reserved_area':
> >> mm/page_alloc.c:5134:3: warning: passing argument 1 of 'virt_to_phys' makes pointer from integer without a cast [enabled by default]
>    In file included from arch/mips/include/asm/page.h:49:0,
>                     from include/linux/mmzone.h:20,
>                     from include/linux/gfp.h:4,
>                     from include/linux/mm.h:8,
>                     from mm/page_alloc.c:18:
>    arch/mips/include/asm/io.h:119:29: note: expected 'const volatile void *' but argument is of type 'long unsigned int'
>    mm/page_alloc.c: In function 'free_area_init_nodes':
>    mm/page_alloc.c:5030:34: warning: array subscript is below array bounds [-Warray-bounds]
> 
> Signed-off-by: Jiang Liu <jiang.liu@huawei.com>
> Reported-by: Arnd Bergmann <arnd@arndb.de>
> Cc: linux-arm-kernel@lists.infradead.org
> Cc: linux-kernel@vger.kernel.org
> Cc: linux-mm@kvack.org
> ---
>  arch/arm/mm/init.c |    6 ++++--
>  mm/page_alloc.c    |    2 +-
>  2 files changed, 5 insertions(+), 3 deletions(-)
> 
> diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c
> index 9a5cdc0..7a82fcd 100644
> --- a/arch/arm/mm/init.c
> +++ b/arch/arm/mm/init.c
> @@ -600,7 +600,8 @@ void __init mem_init(void)
>  
>  #ifdef CONFIG_SA1111
>  	/* now that our DMA memory is actually so designated, we can free it */
> -	free_reserved_area(__va(PHYS_PFN_OFFSET), swapper_pg_dir, 0, NULL);
> +	free_reserved_area((unsigned long)__va(PHYS_PFN_OFFSET),
> +			   (unsigned long)swapper_pg_dir, 0, NULL);

*YUCK*.

As I've said before, fixing the arguments on free_reserved_area() would
be much better than throwing these horrid casts all over the code.

You're casting pointers to integers, and then immediately casting them
back to pointers in free_reserved_area().  Please fix the function
argument types to be sane.

[PATCH] mm: change signature of free_reserved_area() to fix building warnings

[Jiang Liu]

Change signature of free_reserved_area() according to Russell King's
suggestion to fix following build warnings:

arch/arm/mm/init.c: In function 'mem_init':
arch/arm/mm/init.c:603:2: warning: passing argument 1 of 'free_reserved_area' makes integer from pointer without a cast [enabled by default]
  free_reserved_area(__va(PHYS_PFN_OFFSET), swapper_pg_dir, 0, NULL);
  ^
In file included from include/linux/mman.h:4:0,
                 from arch/arm/mm/init.c:15:
include/linux/mm.h:1301:22: note: expected 'long unsigned int' but argument is of type 'void *'
 extern unsigned long free_reserved_area(unsigned long start, unsigned long end,

   mm/page_alloc.c: In function 'free_reserved_area':
>> mm/page_alloc.c:5134:3: warning: passing argument 1 of 'virt_to_phys' makes pointer from integer without a cast [enabled by default]
   In file included from arch/mips/include/asm/page.h:49:0,
                    from include/linux/mmzone.h:20,
                    from include/linux/gfp.h:4,
                    from include/linux/mm.h:8,
                    from mm/page_alloc.c:18:
   arch/mips/include/asm/io.h:119:29: note: expected 'const volatile void *' but argument is of type 'long unsigned int'
   mm/page_alloc.c: In function 'free_area_init_nodes':
   mm/page_alloc.c:5030:34: warning: array subscript is below array bounds [-Warray-bounds]

Signed-off-by: Jiang Liu <jiang.liu@huawei.com>
Reported-by: Arnd Bergmann <arnd@arndb.de>
Cc: linux-arm-kernel@lists.infradead.org
Cc: linux-kernel@vger.kernel.org
Cc: linux-mm@kvack.org
---
Hi Russell,
	Thanks for your review. How about this change to fix the building
warning by change signature of free_reserved_area()?
	Thanks!
	Gerry
---
 arch/alpha/kernel/sys_nautilus.c |    4 ++--
 arch/alpha/mm/init.c             |    2 +-
 arch/arc/mm/init.c               |    2 +-
 arch/arm/mm/init.c               |    2 +-
 arch/arm64/mm/init.c             |    2 +-
 arch/avr32/mm/init.c             |    2 +-
 arch/blackfin/mm/init.c          |    2 +-
 arch/c6x/mm/init.c               |    2 +-
 arch/frv/mm/init.c               |    2 +-
 arch/h8300/mm/init.c             |    2 +-
 arch/ia64/mm/init.c              |    3 +--
 arch/m32r/mm/init.c              |    2 +-
 arch/m68k/mm/init.c              |    2 +-
 arch/metag/mm/init.c             |    3 ++-
 arch/microblaze/mm/init.c        |    2 +-
 arch/mips/mm/init.c              |    3 ++-
 arch/mn10300/mm/init.c           |    3 ++-
 arch/openrisc/mm/init.c          |    2 +-
 arch/parisc/mm/init.c            |    3 ++-
 arch/powerpc/kernel/kvm.c        |    2 +-
 arch/powerpc/mm/mem.c            |    2 +-
 arch/s390/mm/init.c              |    3 ++-
 arch/score/mm/init.c             |    3 ++-
 arch/sh/mm/init.c                |    2 +-
 arch/sparc/mm/init_32.c          |    4 ++--
 arch/sparc/mm/init_64.c          |    4 ++--
 arch/um/kernel/mem.c             |    2 +-
 arch/unicore32/mm/init.c         |    2 +-
 arch/xtensa/mm/init.c            |    2 +-
 include/linux/mm.h               |    5 ++---
 mm/page_alloc.c                  |   16 ++++++++--------
 31 files changed, 48 insertions(+), 44 deletions(-)

diff --git a/arch/alpha/kernel/sys_nautilus.c b/arch/alpha/kernel/sys_nautilus.c
index 1d4aabf..891bd27 100644
--- a/arch/alpha/kernel/sys_nautilus.c
+++ b/arch/alpha/kernel/sys_nautilus.c
@@ -238,8 +238,8 @@ nautilus_init_pci(void)
 	if (pci_mem < memtop)
 		memtop = pci_mem;
 	if (memtop > alpha_mv.min_mem_address) {
-		free_reserved_area((unsigned long)__va(alpha_mv.min_mem_address),
-				   (unsigned long)__va(memtop), 0, NULL);
+		free_reserved_area(__va(alpha_mv.min_mem_address),
+				   __va(memtop), 0, NULL);
 		printk("nautilus_init_pci: %ldk freed\n",
 			(memtop - alpha_mv.min_mem_address) >> 10);
 	}
diff --git a/arch/alpha/mm/init.c b/arch/alpha/mm/init.c
index 0ba85ee..d54848d 100644
--- a/arch/alpha/mm/init.c
+++ b/arch/alpha/mm/init.c
@@ -326,6 +326,6 @@ free_initmem(void)
 void
 free_initrd_mem(unsigned long start, unsigned long end)
 {
-	free_reserved_area(start, end, 0, "initrd");
+	free_reserved_area((void *)start, (void *)end, 0, "initrd");
 }
 #endif
diff --git a/arch/arc/mm/init.c b/arch/arc/mm/init.c
index 4a17736..dce02e4 100644
--- a/arch/arc/mm/init.c
+++ b/arch/arc/mm/init.c
@@ -152,7 +152,7 @@ void __init_refok free_initmem(void)
 #ifdef CONFIG_BLK_DEV_INITRD
 void __init free_initrd_mem(unsigned long start, unsigned long end)
 {
-	free_reserved_area(start, end, 0, "initrd");
+	free_reserved_area((void *)start, (void *)end, 0, "initrd");
 }
 #endif
 
diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c
index 9a5cdc0..59d6f76 100644
--- a/arch/arm/mm/init.c
+++ b/arch/arm/mm/init.c
@@ -744,7 +744,7 @@ void free_initrd_mem(unsigned long start, unsigned long end)
 {
 	if (!keep_initrd) {
 		poison_init_mem((void *)start, PAGE_ALIGN(end) - start);
-		free_reserved_area(start, end, 0, "initrd");
+		free_reserved_area((void *)start, (void *)end, 0, "initrd");
 	}
 }
 
diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c
index f497ca7..6041e40 100644
--- a/arch/arm64/mm/init.c
+++ b/arch/arm64/mm/init.c
@@ -398,7 +398,7 @@ void free_initrd_mem(unsigned long start, unsigned long end)
 {
 	if (!keep_initrd) {
 		poison_init_mem((void *)start, PAGE_ALIGN(end) - start);
-		free_reserved_area(start, end, 0, "initrd");
+		free_reserved_area((void *)start, (void *)end, 0, "initrd");
 	}
 }
 
diff --git a/arch/avr32/mm/init.c b/arch/avr32/mm/init.c
index e66e840..5a79fa0 100644
--- a/arch/avr32/mm/init.c
+++ b/arch/avr32/mm/init.c
@@ -154,6 +154,6 @@ void free_initmem(void)
 #ifdef CONFIG_BLK_DEV_INITRD
 void free_initrd_mem(unsigned long start, unsigned long end)
 {
-	free_reserved_area(start, end, 0, "initrd");
+	free_reserved_area((void *)start, (void *)end, 0, "initrd");
 }
 #endif
diff --git a/arch/blackfin/mm/init.c b/arch/blackfin/mm/init.c
index 82d01a7..8e9eab2 100644
--- a/arch/blackfin/mm/init.c
+++ b/arch/blackfin/mm/init.c
@@ -133,7 +133,7 @@ void __init mem_init(void)
 void __init free_initrd_mem(unsigned long start, unsigned long end)
 {
 #ifndef CONFIG_MPU
-	free_reserved_area(start, end, 0, "initrd");
+	free_reserved_area((void *)start, (void *)end, 0, "initrd");
 #endif
 }
 #endif
diff --git a/arch/c6x/mm/init.c b/arch/c6x/mm/init.c
index a9fcd89..97914e5 100644
--- a/arch/c6x/mm/init.c
+++ b/arch/c6x/mm/init.c
@@ -77,7 +77,7 @@ void __init mem_init(void)
 #ifdef CONFIG_BLK_DEV_INITRD
 void __init free_initrd_mem(unsigned long start, unsigned long end)
 {
-	free_reserved_area(start, end, 0, "initrd");
+	free_reserved_area((void *)start, (void *)end, 0, "initrd");
 }
 #endif
 
diff --git a/arch/frv/mm/init.c b/arch/frv/mm/init.c
index dee354f..a67f3a5 100644
--- a/arch/frv/mm/init.c
+++ b/arch/frv/mm/init.c
@@ -173,6 +173,6 @@ void free_initmem(void)
 #ifdef CONFIG_BLK_DEV_INITRD
 void __init free_initrd_mem(unsigned long start, unsigned long end)
 {
-	free_reserved_area(start, end, 0, "initrd");
+	free_reserved_area((void *)start, (void *)end, 0, "initrd");
 } /* end free_initrd_mem() */
 #endif
diff --git a/arch/h8300/mm/init.c b/arch/h8300/mm/init.c
index ff349d7..57e03c5 100644
--- a/arch/h8300/mm/init.c
+++ b/arch/h8300/mm/init.c
@@ -161,7 +161,7 @@ void __init mem_init(void)
 #ifdef CONFIG_BLK_DEV_INITRD
 void free_initrd_mem(unsigned long start, unsigned long end)
 {
-	free_reserved_area(start, end, 0, "initrd");
+	free_reserved_area((void *)start, (void *)end, 0, "initrd");
 }
 #endif
 
diff --git a/arch/ia64/mm/init.c b/arch/ia64/mm/init.c
index d1fe4b4..da568c2 100644
--- a/arch/ia64/mm/init.c
+++ b/arch/ia64/mm/init.c
@@ -154,8 +154,7 @@ ia64_init_addr_space (void)
 void
 free_initmem (void)
 {
-	free_reserved_area((unsigned long)ia64_imva(__init_begin),
-			   (unsigned long)ia64_imva(__init_end),
+	free_reserved_area(ia64_imva(__init_begin), ia64_imva(__init_end),
 			   0, "unused kernel");
 }
 
diff --git a/arch/m32r/mm/init.c b/arch/m32r/mm/init.c
index ab4cbce..d80412d 100644
--- a/arch/m32r/mm/init.c
+++ b/arch/m32r/mm/init.c
@@ -191,6 +191,6 @@ void free_initmem(void)
  *======================================================================*/
 void free_initrd_mem(unsigned long start, unsigned long end)
 {
-	free_reserved_area(start, end, 0, "initrd");
+	free_reserved_area((void *)start, (void *)end, 0, "initrd");
 }
 #endif
diff --git a/arch/m68k/mm/init.c b/arch/m68k/mm/init.c
index 1af2ca3..95de725 100644
--- a/arch/m68k/mm/init.c
+++ b/arch/m68k/mm/init.c
@@ -202,6 +202,6 @@ void __init mem_init(void)
 #ifdef CONFIG_BLK_DEV_INITRD
 void free_initrd_mem(unsigned long start, unsigned long end)
 {
-	free_reserved_area(start, end, 0, "initrd");
+	free_reserved_area((void *)start, (void *)end, 0, "initrd");
 }
 #endif
diff --git a/arch/metag/mm/init.c b/arch/metag/mm/init.c
index d05b845..5e2238d 100644
--- a/arch/metag/mm/init.c
+++ b/arch/metag/mm/init.c
@@ -414,7 +414,8 @@ void free_initmem(void)
 #ifdef CONFIG_BLK_DEV_INITRD
 void free_initrd_mem(unsigned long start, unsigned long end)
 {
-	free_reserved_area(start, end, POISON_FREE_INITMEM, "initrd");
+	free_reserved_area((void *)start, (void *)end, POISON_FREE_INITMEM,
+			   "initrd");
 }
 #endif
 
diff --git a/arch/microblaze/mm/init.c b/arch/microblaze/mm/init.c
index 4ec137d..73a49c4 100644
--- a/arch/microblaze/mm/init.c
+++ b/arch/microblaze/mm/init.c
@@ -235,7 +235,7 @@ void __init setup_memory(void)
 #ifdef CONFIG_BLK_DEV_INITRD
 void free_initrd_mem(unsigned long start, unsigned long end)
 {
-	free_reserved_area(start, end, 0, "initrd");
+	free_reserved_area((void *)start, (void *)end, 0, "initrd");
 }
 #endif
 
diff --git a/arch/mips/mm/init.c b/arch/mips/mm/init.c
index 3d0346d..3931be5 100644
--- a/arch/mips/mm/init.c
+++ b/arch/mips/mm/init.c
@@ -439,7 +439,8 @@ void free_init_pages(const char *what, unsigned long begin, unsigned long end)
 #ifdef CONFIG_BLK_DEV_INITRD
 void free_initrd_mem(unsigned long start, unsigned long end)
 {
-	free_reserved_area(start, end, POISON_FREE_INITMEM, "initrd");
+	free_reserved_area((void *)start, (void *)end, POISON_FREE_INITMEM,
+			   "initrd");
 }
 #endif
 
diff --git a/arch/mn10300/mm/init.c b/arch/mn10300/mm/init.c
index 5a8ace6..e19049d 100644
--- a/arch/mn10300/mm/init.c
+++ b/arch/mn10300/mm/init.c
@@ -152,6 +152,7 @@ void free_initmem(void)
 #ifdef CONFIG_BLK_DEV_INITRD
 void free_initrd_mem(unsigned long start, unsigned long end)
 {
-	free_reserved_area(start, end, POISON_FREE_INITMEM, "initrd");
+	free_reserved_area((void *)start, (void *)end, POISON_FREE_INITMEM,
+			   "initrd");
 }
 #endif
diff --git a/arch/openrisc/mm/init.c b/arch/openrisc/mm/init.c
index b3cbc67..ab11332 100644
--- a/arch/openrisc/mm/init.c
+++ b/arch/openrisc/mm/init.c
@@ -261,7 +261,7 @@ void __init mem_init(void)
 #ifdef CONFIG_BLK_DEV_INITRD
 void free_initrd_mem(unsigned long start, unsigned long end)
 {
-	free_reserved_area(start, end, 0, "initrd");
+	free_reserved_area((void *)start, (void *)end, 0, "initrd");
 }
 #endif
 
diff --git a/arch/parisc/mm/init.c b/arch/parisc/mm/init.c
index 157b931..7fd8c8d 100644
--- a/arch/parisc/mm/init.c
+++ b/arch/parisc/mm/init.c
@@ -1099,6 +1099,7 @@ void flush_tlb_all(void)
 #ifdef CONFIG_BLK_DEV_INITRD
 void free_initrd_mem(unsigned long start, unsigned long end)
 {
-	num_physpages += free_reserved_area(start, end, 0, "initrd");
+	num_physpages += free_reserved_area((void *)start, (void *)end, 0,
+					    "initrd");
 }
 #endif
diff --git a/arch/powerpc/kernel/kvm.c b/arch/powerpc/kernel/kvm.c
index 6782221..5e4830a 100644
--- a/arch/powerpc/kernel/kvm.c
+++ b/arch/powerpc/kernel/kvm.c
@@ -756,7 +756,7 @@ static __init void kvm_free_tmp(void)
 	end = (ulong)&kvm_tmp[ARRAY_SIZE(kvm_tmp)] & PAGE_MASK;
 
 	/* Free the tmp space we don't need */
-	free_reserved_area(start, end, 0, NULL);
+	free_reserved_area((void *)start, (void *)end, 0, NULL);
 }
 
 static int __init kvm_guest_init(void)
diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c
index 0988a26..347c5b1 100644
--- a/arch/powerpc/mm/mem.c
+++ b/arch/powerpc/mm/mem.c
@@ -407,7 +407,7 @@ void free_initmem(void)
 #ifdef CONFIG_BLK_DEV_INITRD
 void __init free_initrd_mem(unsigned long start, unsigned long end)
 {
-	free_reserved_area(start, end, 0, "initrd");
+	free_reserved_area((void *)start, (void *)end, 0, "initrd");
 }
 #endif
 
diff --git a/arch/s390/mm/init.c b/arch/s390/mm/init.c
index 0b09b23..4c01c3a 100644
--- a/arch/s390/mm/init.c
+++ b/arch/s390/mm/init.c
@@ -170,7 +170,8 @@ void free_initmem(void)
 #ifdef CONFIG_BLK_DEV_INITRD
 void __init free_initrd_mem(unsigned long start, unsigned long end)
 {
-	free_reserved_area(start, end, POISON_FREE_INITMEM, "initrd");
+	free_reserved_area((void *)start, (void *)end, POISON_FREE_INITMEM,
+			   "initrd");
 }
 #endif
 
diff --git a/arch/score/mm/init.c b/arch/score/mm/init.c
index 1592aad..7b78bd1 100644
--- a/arch/score/mm/init.c
+++ b/arch/score/mm/init.c
@@ -110,7 +110,8 @@ void __init mem_init(void)
 #ifdef CONFIG_BLK_DEV_INITRD
 void free_initrd_mem(unsigned long start, unsigned long end)
 {
-	free_reserved_area(start, end, POISON_FREE_INITMEM, "initrd");
+	free_reserved_area((void *)start, (void *)end, POISON_FREE_INITMEM,
+			   "initrd");
 }
 #endif
 
diff --git a/arch/sh/mm/init.c b/arch/sh/mm/init.c
index 20f9ead..b892a9b 100644
--- a/arch/sh/mm/init.c
+++ b/arch/sh/mm/init.c
@@ -505,7 +505,7 @@ void free_initmem(void)
 #ifdef CONFIG_BLK_DEV_INITRD
 void free_initrd_mem(unsigned long start, unsigned long end)
 {
-	free_reserved_area(start, end, 0, "initrd");
+	free_reserved_area((void *)start, (void *)end, 0, "initrd");
 }
 #endif
 
diff --git a/arch/sparc/mm/init_32.c b/arch/sparc/mm/init_32.c
index af472cf..d5f9c02 100644
--- a/arch/sparc/mm/init_32.c
+++ b/arch/sparc/mm/init_32.c
@@ -372,8 +372,8 @@ void free_initmem (void)
 #ifdef CONFIG_BLK_DEV_INITRD
 void free_initrd_mem(unsigned long start, unsigned long end)
 {
-	num_physpages += free_reserved_area(start, end, POISON_FREE_INITMEM,
-					    "initrd");
+	num_physpages += free_reserved_area((void *)start, (void *)end,
+					    POISON_FREE_INITMEM, "initrd");
 }
 #endif
 
diff --git a/arch/sparc/mm/init_64.c b/arch/sparc/mm/init_64.c
index a717199..a54cdcd 100644
--- a/arch/sparc/mm/init_64.c
+++ b/arch/sparc/mm/init_64.c
@@ -2124,8 +2124,8 @@ void free_initmem(void)
 #ifdef CONFIG_BLK_DEV_INITRD
 void free_initrd_mem(unsigned long start, unsigned long end)
 {
-	num_physpages += free_reserved_area(start, end, POISON_FREE_INITMEM,
-					    "initrd");
+	num_physpages += free_reserved_area((void *)start, (void *)end,
+					    POISON_FREE_INITMEM, "initrd");
 }
 #endif
 
diff --git a/arch/um/kernel/mem.c b/arch/um/kernel/mem.c
index 9df292b..2aa7a24 100644
--- a/arch/um/kernel/mem.c
+++ b/arch/um/kernel/mem.c
@@ -244,7 +244,7 @@ void free_initmem(void)
 #ifdef CONFIG_BLK_DEV_INITRD
 void free_initrd_mem(unsigned long start, unsigned long end)
 {
-	free_reserved_area(start, end, 0, "initrd");
+	free_reserved_area((void *)start, (void *)end, 0, "initrd");
 }
 #endif
 
diff --git a/arch/unicore32/mm/init.c b/arch/unicore32/mm/init.c
index 63df12d..220755c 100644
--- a/arch/unicore32/mm/init.c
+++ b/arch/unicore32/mm/init.c
@@ -486,7 +486,7 @@ static int keep_initrd;
 void free_initrd_mem(unsigned long start, unsigned long end)
 {
 	if (!keep_initrd)
-		free_reserved_area(start, end, 0, "initrd");
+		free_reserved_area((void *)start, (void *)end, 0, "initrd");
 }
 
 static int __init keepinitrd_setup(char *__unused)
diff --git a/arch/xtensa/mm/init.c b/arch/xtensa/mm/init.c
index bba125b..4d658ef 100644
--- a/arch/xtensa/mm/init.c
+++ b/arch/xtensa/mm/init.c
@@ -214,7 +214,7 @@ extern int initrd_is_mapped;
 void free_initrd_mem(unsigned long start, unsigned long end)
 {
 	if (initrd_is_mapped)
-		free_reserved_area(start, end, 0, "initrd");
+		free_reserved_area((void *)start, (void *)end, 0, "initrd");
 }
 #endif
 
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 1a7f19e..4daa3d1 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1301,7 +1301,7 @@ extern void free_initmem(void);
  * "poison" if it's non-zero.
  * Return pages freed into the buddy system.
  */
-extern unsigned long free_reserved_area(unsigned long start, unsigned long end,
+extern unsigned long free_reserved_area(void *start, void *end,
 					int poison, char *s);
 #ifdef	CONFIG_HIGHMEM
 /*
@@ -1345,8 +1345,7 @@ static inline unsigned long free_initmem_default(int poison)
 {
 	extern char __init_begin[], __init_end[];
 
-	return free_reserved_area(PAGE_ALIGN((unsigned long)&__init_begin) ,
-				  ((unsigned long)&__init_end) & PAGE_MASK,
+	return free_reserved_area(&__init_begin, &__init_end,
 				  poison, "unused kernel");
 }
 
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 843e33d..91ceebc 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -5186,21 +5186,21 @@ early_param("movablecore", cmdline_parse_movablecore);
 
 #endif /* CONFIG_HAVE_MEMBLOCK_NODE_MAP */
 
-unsigned long free_reserved_area(unsigned long start, unsigned long end,
-				 int poison, char *s)
+unsigned long free_reserved_area(void *start, void *end, int poison, char *s)
 {
-	unsigned long pages, pos;
+	void *pos;
+	unsigned long pages = 0;
 
-	pos = start = PAGE_ALIGN(start);
-	end &= PAGE_MASK;
-	for (pages = 0; pos < end; pos += PAGE_SIZE, pages++) {
+	start = (void *)PAGE_ALIGN((unsigned long)start);
+	end = (void *)((unsigned long)end & PAGE_MASK);
+	for (pos = start; pos < end; pos += PAGE_SIZE, pages++) {
 		if (poison)
-			memset((void *)pos, poison, PAGE_SIZE);
+			memset(pos, poison, PAGE_SIZE);
 		free_reserved_page(virt_to_page(pos));
 	}
 
 	if (pages && s)
-		pr_info("Freeing %s memory: %ldK (%lx - %lx)\n",
+		pr_info("Freeing %s memory: %ldK (%p - %p)\n",
 			s, pages << (PAGE_SHIFT - 10), start, end);
 
 	return pages;
-- 
1.7.9.5