[RFC PATCHSET tip:x86/mm] Remove DISCONTIGMEM support from x86-32

[RFC PATCHSET tip:x86/mm] Remove DISCONTIGMEM support from x86-32

[Tejun Heo]

Hello,

This patchset removes DISCONTIGMEM support from x86-32 leaving it with
FLATMEM for UMA and SPARSEMEM for NUMA.  At this point, DISCONTIGMEM
doesn't really have much benefit over SPARSEMEM.  The only remaining
benefit is that it can have finer granularity with memsections
regardless of the number of bits available in page->flags.

There are two obstacles to removing DISCONTIGMEM support in x86-32.
One is that ARCH_SUPPORTS_MEMORY_FAILURE is dependent on !SPARSEMEM,
so if a NUMA kernel wants to use memory failure, it has to use
DISCONTIGMEM.  At least SLE11SP1 kernel seems to have chosen that
route.

This is solved by reducing the number of page->flags bits used for
memsection selection by one, which I think is the right thing to do
regardless of this change.  Please read the patch description on the
second patch for details.

The other obstable is that due to the limited number of page->flags
bits available and the relatively large physical address area when PAE
is enabled, the granularity of sparse memsections is somewhat coarse.
It was originally 512MiB but increased to 1GiB with the second patch.

For unaligned memsections, this can result in some amount of wasted
struct page allocations, which I think shouldn't be a problem but not
completely sure and thus the RFC status.

This patchset contains the following four patches.

 0001-x86-Clean-up-memory-model-related-configs-in-arch-x8.patch
 0002-x86-32-Increment-SECTION_SIZE_BITS-to-30-when-X86_PA.patch
 0003-x86-32-Remove-restrictions-on-ARCH_SUPPORTS_MEMORY_F.patch
 0004-x86-32-NUMA-Remove-support-for-DISCONTIGMEM.patch

0001 is a cleanup which I'll probably queue regardless of this series
unless there are objections.  0002-0003 solve the first obstacle
described above and 0004 removes DISCONTIGMEM.

The patchset is also available in the following git branch.

 git://git.kernel.org/pub/scm/linux/kernel/git/tj/misc.git x86_32-remove-DISCONTIGMEM

diffstat follows.

 arch/x86/Kconfig                  |   49 +++++++++------------------------
 arch/x86/include/asm/mmzone_32.h  |   48 --------------------------------
 arch/x86/include/asm/pgtable_32.h |    5 ---
 arch/x86/include/asm/sparsemem.h  |    2 -
 arch/x86/mm/numa_32.c             |   56 ++++----------------------------------
 5 files changed, 22 insertions(+), 138 deletions(-)

Thanks.

-- 
tejun

[PATCH 1/4] x86: Clean up memory model related configs in arch/x86/Kconfig

[Tejun Heo]

* Remove bogus dependency on ARCH_SELECT_MEMORY_MODEL from
  ARCH_FLATMEM_ENABLE.  ENABLE configs don't interfere with
  SELECT_MEMORY_MODEL.  They just need to indicate whether the
  specific memory model is supported.

* Relocate HAVE_ARCH_ALLOC_REMAP, ARCH_PROC_KCORE_TEXT and
  ARCH_SPARSEMEM_DEFAULT so that memory model related configs are
  together in consistent order.

Signed-off-by: Tejun Heo <tj@kernel.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Yinghai Lu <yinghai@kernel.org>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
---
 arch/x86/Kconfig |   26 +++++++++++++-------------
 1 files changed, 13 insertions(+), 13 deletions(-)

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index cc6c53a..0db96ae 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -1223,6 +1223,10 @@ config HAVE_ARCH_BOOTMEM
 	def_bool y
 	depends on X86_32 && NUMA
 
+config HAVE_ARCH_ALLOC_REMAP
+	def_bool y
+	depends on X86_32 && NUMA
+
 config ARCH_HAVE_MEMORY_PRESENT
 	def_bool y
 	depends on X86_32 && DISCONTIGMEM
@@ -1231,13 +1235,9 @@ config NEED_NODE_MEMMAP_SIZE
 	def_bool y
 	depends on X86_32 && (DISCONTIGMEM || SPARSEMEM)
 
-config HAVE_ARCH_ALLOC_REMAP
-	def_bool y
-	depends on X86_32 && NUMA
-
 config ARCH_FLATMEM_ENABLE
 	def_bool y
-	depends on X86_32 && ARCH_SELECT_MEMORY_MODEL && !NUMA
+	depends on X86_32 && !NUMA
 
 config ARCH_DISCONTIGMEM_ENABLE
 	def_bool y
@@ -1247,20 +1247,16 @@ config ARCH_DISCONTIGMEM_DEFAULT
 	def_bool y
 	depends on NUMA && X86_32
 
-config ARCH_PROC_KCORE_TEXT
-	def_bool y
-	depends on X86_64 && PROC_KCORE
-
-config ARCH_SPARSEMEM_DEFAULT
-	def_bool y
-	depends on X86_64
-
 config ARCH_SPARSEMEM_ENABLE
 	def_bool y
 	depends on X86_64 || NUMA || (EXPERIMENTAL && X86_32) || X86_32_NON_STANDARD
 	select SPARSEMEM_STATIC if X86_32
 	select SPARSEMEM_VMEMMAP_ENABLE if X86_64
 
+config ARCH_SPARSEMEM_DEFAULT
+	def_bool y
+	depends on X86_64
+
 config ARCH_SELECT_MEMORY_MODEL
 	def_bool y
 	depends on ARCH_SPARSEMEM_ENABLE
@@ -1269,6 +1265,10 @@ config ARCH_MEMORY_PROBE
 	def_bool X86_64
 	depends on MEMORY_HOTPLUG
 
+config ARCH_PROC_KCORE_TEXT
+	def_bool y
+	depends on X86_64 && PROC_KCORE
+
 config ILLEGAL_POINTER_VALUE
        hex
        default 0 if X86_32
-- 
1.7.1

Re: [PATCH 1/4] x86: Clean up memory model related configs in arch/x86/Kconfig

[Christoph Lameter]

On Thu, 31 Mar 2011, Tejun Heo wrote:

> * Remove bogus dependency on ARCH_SELECT_MEMORY_MODEL from
>   ARCH_FLATMEM_ENABLE.  ENABLE configs don't interfere with
>   SELECT_MEMORY_MODEL.  They just need to indicate whether the
>   specific memory model is supported.

Reviewed-by: Christoph Lameter <cl@linux.com>

[PATCH 2/4] x86-32: Increment SECTION_SIZE_BITS to 30 when X86_PAE

[Tejun Heo]

When X86_PAE is enabled, SECTION_SIZE_BITS is 29 and MAX_PHYSADDR_BITS
36 making SECTIONS_WIDTH 7, which is different from !X86_PAE case
where the width is 6.  On x86, when all the related options are
enabled, NR_PAGEFLAGS reaches 26 and thus can accomodate only 6 more
bits, not 7.

This direcrepancy leads to confusing Kconfig restrictions like
disabling of ARCH_SUPPORTS_MEMORY_FAILURE depending on combinations of
options.

This patch bumps SECTION_SIZE_BITS to 30 when X86_PAE.  This change
increases sparse memory model granuality from 512MiB to 1GiB which in
turn can increase the amount of wasted memory in memmap when the
memory sections aren't aligned.  The amount of wastage can be a few
MiB per unaligned section.

Signed-off-by: Tejun Heo <tj@kernel.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Yinghai Lu <yinghai@kernel.org>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
---
 arch/x86/include/asm/sparsemem.h |    2 +-
 1 files changed, 1 insertions(+), 1 deletions(-)

diff --git a/arch/x86/include/asm/sparsemem.h b/arch/x86/include/asm/sparsemem.h
index 4517d6b..71b8671 100644
--- a/arch/x86/include/asm/sparsemem.h
+++ b/arch/x86/include/asm/sparsemem.h
@@ -16,7 +16,7 @@
 
 #ifdef CONFIG_X86_32
 # ifdef CONFIG_X86_PAE
-#  define SECTION_SIZE_BITS	29
+#  define SECTION_SIZE_BITS	30
 #  define MAX_PHYSADDR_BITS	36
 #  define MAX_PHYSMEM_BITS	36
 # else
-- 
1.7.1

[PATCH 3/4] x86-32: Remove restrictions on ARCH_SUPPORTS_MEMORY_FAILURE

[Tejun Heo]

d949f36f18 (x86: Fix hwpoison code related build failure on 32-bit
NUMAQ) disabled ARCH_SUPPORTS_MEMORY_FAILURE on some 32bit
configurations because the extra page flag usage triggered build
failure when combined with memory section/node bits.

The root cause of build failures depending on config options is
SECTIONS_WIDTH difference depending on X86_PAE.  As the previous patch
removes the problem, we can remove the restrictions on MEMORY_FAILURE.

This makes the configuration more consistent.  For example,
TRANSPARENT_HUGEPAGE also consumes a page flag but didn't trigger
build failure thanks to the removal of PG_buddy and Kconfig ends up
enforcing rather arbitrary preference for TRANSPARENT_HUGEPAGE over
MEMORY_FAILURE.

Signed-off-by: Tejun Heo <tj@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Yinghai Lu <yinghai@kernel.org>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
---
 arch/x86/Kconfig |   11 +----------
 1 files changed, 1 insertions(+), 10 deletions(-)

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 0db96ae..7f83405 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -446,16 +446,6 @@ config X86_NUMAQ
 	  of Flat Logical.  You will need a new lynxer.elf file to flash your
 	  firmware with - send email to <Martin.Bligh@us.ibm.com>.
 
-config X86_SUPPORTS_MEMORY_FAILURE
-	def_bool y
-	# MCE code calls memory_failure():
-	depends on X86_MCE
-	# On 32-bit this adds too big of NODES_SHIFT and we run out of page flags:
-	depends on !X86_NUMAQ
-	# On 32-bit SPARSEMEM adds too big of SECTIONS_WIDTH:
-	depends on X86_64 || !SPARSEMEM
-	select ARCH_SUPPORTS_MEMORY_FAILURE
-
 config X86_VISWS
 	bool "SGI 320/540 (Visual Workstation)"
 	depends on X86_32 && PCI && X86_MPPARSE && PCI_GODIRECT
@@ -845,6 +835,7 @@ config X86_REROUTE_FOR_BROKEN_BOOT_IRQS
 
 config X86_MCE
 	bool "Machine Check / overheating reporting"
+	select ARCH_SUPPORTS_MEMORY_FAILURE
 	---help---
 	  Machine Check support allows the processor to notify the
 	  kernel if it detects a problem (e.g. overheating, data corruption).
-- 
1.7.1

[PATCH 4/4] x86-32, NUMA: Remove support for DISCONTIGMEM

[Tejun Heo]

There's no meaningful performance difference between DISCONTIGMEM and
SPARSEMEM, and sparse memory model has been stable for quite some time
now.

At this point, the only difference between the two is that sparsemem
might waste some amount of memory for memmap if the memory sections
aren't aligned to 1 << SECTION_SIZE_BITS which is 1GiB is PAE is
enabled and 64MiB otherwise.

Drop DISCONTIGMEM support and use SPARSEMEM on NUMA configurations.
Note that due to the shortage of vmalloc space, SPARSEMEM_VMMEMAP
can't be enabled and thus there's performance difference between
FLATMEM and SPARSEMEM, so x86-32 can't drop FLATMEM and just use
sparse like x86-64.

The following is from Christoph Lameter's page alloc benchmark module.

DISCONTIGMEM

 Single thread testing
 =====================
 1. Repeatedly allocate then free test
 1000 times alloc_page(,0) -> 1017 cycles __free_pages(,0)-> 359 cycles
 1000 times alloc_page(,1) -> 1041 cycles __free_pages(,1)-> 424 cycles
 1000 times alloc_page(,2) -> 1215 cycles __free_pages(,2)-> 565 cycles
 1000 times alloc_page(,3) -> 1256 cycles __free_pages(,3)-> 613 cycles
 1000 times alloc_page(,4) -> 1554 cycles __free_pages(,4)-> 697 cycles
 1000 times alloc_page(,5) -> 1990 cycles __free_pages(,5)-> 1114 cycles
 1000 times alloc_page(,6) -> 3072 cycles __free_pages(,6)-> 1788 cycles
 1000 times alloc_page(,7) -> 5215 cycles __free_pages(,7)-> 5550 cycles
 2. alloc/free test
 1000 times alloc( ,0)/free -> 662 cycles
 1000 times alloc( ,1)/free -> 853 cycles
 1000 times alloc( ,2)/free -> 926 cycles
 1000 times alloc( ,3)/free -> 1013 cycles
 1000 times alloc( ,4)/free -> 1249 cycles
 1000 times alloc( ,5)/free -> 1614 cycles
 1000 times alloc( ,6)/free -> 2454 cycles
 1000 times alloc( ,7)/free -> 4000 cycles
 Concurrent allocs
 =================
 Page alloc N*alloc N*free(0): 0=5143/5868 1=5245/6051 2=5199/5982 3=5220/6045 4=5191/5876 5=5270/6066 6=966/5902 7=5243/6035 Average=4684/5978
 Page alloc N*alloc N*free(1): 0=19537/24032 1=19569/24080 2=19555/24039 3=19580/24073 4=19590/24075 5=19595/24080 6=19585/24073 7=19586/24079 Average=19574/24066
 Page alloc N*alloc N*free(2): 0=19466/24490 1=19433/24439 2=19470/24502 3=19472/24493 4=19450/24496 5=19441/24483 6=19446/24488 7=19428/24478 Average=19451/24484
 Page alloc N*alloc N*free(3): 0=19072/25386 1=19036/25381 2=19029/25377 3=19034/25376 4=18799/25382 5=18905/25347 6=18880/25266 7=18891/25379 Average=18956/25362
 Page alloc N*alloc N*free(4): 0=19252/26454 1=19183/26451 2=19199/26454 3=19205/26450 4=19180/26458 5=19170/26437 6=19131/26373 7=19179/26447 Average=19188/26440
 ----Fastpath---
 Page N*(alloc free)(0): 0=639 1=639 2=639 3=638 4=641 5=642 6=655 7=638 Average=641
 Page N*(alloc free)(1): 0=36697 1=36717 2=36746 3=36747 4=36748 5=36753 6=36751 7=36751 Average=36739
 Page N*(alloc free)(2): 0=35753 1=35756 2=35780 3=35757 4=35782 5=35784 6=35778 7=35779 Average=35771
 Page N*(alloc free)(3): 0=37499 1=37527 2=37544 3=37547 4=37545 5=37550 6=37547 7=37543 Average=37538
 Page N*(alloc free)(4): 0=36374 1=36381 2=36378 3=36395 4=36391 5=36390 6=36390 7=36391 Average=36386
 Remote free test
 ================
 N*remote free(0): 0=5/4157 1=4907/0 2=4838/0 3=4846/0 4=4891/0 5=4883/0 6=4880/0 7=4904/0 Average=4269/519
 N*remote free(1): 0=4/5832 1=15285/0 2=15243/0 3=15270/0 4=15299/0 5=15306/0 6=15304/0 7=15294/0 Average=13376/729
 N*remote free(2): 0=4/9441 1=15489/0 2=15492/0 3=15483/0 4=15440/0 5=15476/0 6=15468/0 7=15471/0 Average=13540/1180
 N*remote free(3): 0=5/13038 1=15725/0 2=15727/0 3=15711/0 4=15713/0 5=15710/0 6=15704/0 7=15710/0 Average=13751/1629
 N*remote free(4): 0=6/21888 1=16137/0 2=16142/0 3=16157/0 4=16156/0 5=16160/0 6=16156/0 7=16158/0 Average=14134/2736

SPARSEMEM

 Single thread testing
 =====================
 1. Repeatedly allocate then free test
 1000 times alloc_page(,0) -> 1033 cycles __free_pages(,0)-> 358 cycles
 1000 times alloc_page(,1) -> 1061 cycles __free_pages(,1)-> 477 cycles
 1000 times alloc_page(,2) -> 1191 cycles __free_pages(,2)-> 578 cycles
 1000 times alloc_page(,3) -> 1219 cycles __free_pages(,3)-> 604 cycles
 1000 times alloc_page(,4) -> 1440 cycles __free_pages(,4)-> 681 cycles
 1000 times alloc_page(,5) -> 1820 cycles __free_pages(,5)-> 1179 cycles
 1000 times alloc_page(,6) -> 2757 cycles __free_pages(,6)-> 2062 cycles
 1000 times alloc_page(,7) -> 4601 cycles __free_pages(,7)-> 5539 cycles
 2. alloc/free test
 1000 times alloc( ,0)/free -> 649 cycles
 1000 times alloc( ,1)/free -> 850 cycles
 1000 times alloc( ,2)/free -> 886 cycles
 1000 times alloc( ,3)/free -> 984 cycles
 1000 times alloc( ,4)/free -> 1161 cycles
 1000 times alloc( ,5)/free -> 1458 cycles
 1000 times alloc( ,6)/free -> 2145 cycles
 1000 times alloc( ,7)/free -> 3293 cycles
 Concurrent allocs
 =================
 Page alloc N*alloc N*free(0): 0=5054/6282 1=5032/6212 2=4994/6246 3=5034/6295 4=4987/6057 5=928/6211 6=5103/6311 7=5067/6267 Average=4525/6235
 Page alloc N*alloc N*free(1): 0=19551/24798 1=19599/24851 2=19609/24871 3=19599/24821 4=19604/24869 5=19615/24866 6=19615/24841 7=19616/24872 Average=19601/24848
 Page alloc N*alloc N*free(2): 0=19332/24555 1=19342/24568 2=19363/24588 3=19363/24594 4=19362/24593 5=19365/24595 6=19360/24590 7=19360/24586 Average=19356/24584
 Page alloc N*alloc N*free(3): 0=19145/25868 1=19099/25865 2=19094/25858 3=19089/25865 4=18941/25873 5=18985/25840 6=18962/25838 7=18932/25836 Average=19031/25855
 Page alloc N*alloc N*free(4): 0=19202/27147 1=19151/27142 2=19155/27143 3=19144/27141 4=19104/27145 5=19051/27082 6=19068/27113 7=19080/27139 Average=19119/27132
 ----Fastpath---
 Page N*(alloc free)(0): 0=683 1=702 2=667 3=666 4=668 5=671 6=683 7=685 Average=678
 Page N*(alloc free)(1): 0=37829 1=37843 2=37856 3=37843 4=37856 5=37857 6=37853 7=37854 Average=37849
 Page N*(alloc free)(2): 0=36966 1=36952 2=36970 3=36977 4=36988 5=36988 6=36990 7=36987 Average=36977
 Page N*(alloc free)(3): 0=40647 1=40626 2=40662 3=40653 4=40664 5=40665 6=40667 7=40660 Average=40656
 Page N*(alloc free)(4): 0=38194 1=38153 2=38145 3=38152 4=38178 5=38170 6=38174 7=38182 Average=38169
 Remote free test
 ================
 N*remote free(0): 0=4/4335 1=4791/0 2=4895/0 3=4886/0 4=4901/0 5=4856/0 6=4902/0 7=4909/0 Average=4268/542
 N*remote free(1): 0=4/5972 1=15298/0 2=15275/0 3=15284/0 4=15314/0 5=15309/0 6=15313/0 7=15299/0 Average=13387/746
 N*remote free(2): 0=4/9684 1=15441/0 2=15433/0 3=15418/0 4=15423/0 5=15388/0 6=15432/0 7=15430/0 Average=13496/1210
 N*remote free(3): 0=5/13320 1=15716/0 2=15720/0 3=15716/0 4=15683/0 5=15645/0 6=15682/0 7=15688/0 Average=13732/1665
 N*remote free(4): 0=6/22219 1=15946/0 2=15957/0 3=15949/0 4=15928/0 5=15924/0 6=15948/0 7=15942/0 Average=13950/2777

Signed-off-by: Tejun Heo <tj@kernel.org>
Cc: Christoph Lameter <cl@linux-foundation.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Yinghai Lu <yinghai@kernel.org>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
---
 arch/x86/Kconfig                  |   18 ++----------
 arch/x86/include/asm/mmzone_32.h  |   48 -------------------------------
 arch/x86/include/asm/pgtable_32.h |    5 +--
 arch/x86/mm/numa_32.c             |   56 ++++---------------------------------
 4 files changed, 10 insertions(+), 117 deletions(-)

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 7f83405..07584e2 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -1218,26 +1218,14 @@ config HAVE_ARCH_ALLOC_REMAP
 	def_bool y
 	depends on X86_32 && NUMA
 
-config ARCH_HAVE_MEMORY_PRESENT
-	def_bool y
-	depends on X86_32 && DISCONTIGMEM
-
 config NEED_NODE_MEMMAP_SIZE
 	def_bool y
-	depends on X86_32 && (DISCONTIGMEM || SPARSEMEM)
+	depends on X86_32 && SPARSEMEM
 
 config ARCH_FLATMEM_ENABLE
 	def_bool y
 	depends on X86_32 && !NUMA
 
-config ARCH_DISCONTIGMEM_ENABLE
-	def_bool y
-	depends on NUMA && X86_32
-
-config ARCH_DISCONTIGMEM_DEFAULT
-	def_bool y
-	depends on NUMA && X86_32
-
 config ARCH_SPARSEMEM_ENABLE
 	def_bool y
 	depends on X86_64 || NUMA || (EXPERIMENTAL && X86_32) || X86_32_NON_STANDARD
@@ -1246,11 +1234,11 @@ config ARCH_SPARSEMEM_ENABLE
 
 config ARCH_SPARSEMEM_DEFAULT
 	def_bool y
-	depends on X86_64
+	depends on X86_64 || (X86_32 && NUMA)
 
 config ARCH_SELECT_MEMORY_MODEL
 	def_bool y
-	depends on ARCH_SPARSEMEM_ENABLE
+	depends on ARCH_FLATMEM_ENABLE
 
 config ARCH_MEMORY_PROBE
 	def_bool X86_64
diff --git a/arch/x86/include/asm/mmzone_32.h b/arch/x86/include/asm/mmzone_32.h
index 91df7c5..39912b0 100644
--- a/arch/x86/include/asm/mmzone_32.h
+++ b/arch/x86/include/asm/mmzone_32.h
@@ -42,54 +42,6 @@ static inline void resume_map_numa_kva(pgd_t *pgd) {}
 
 #endif /* CONFIG_NUMA */
 
-#ifdef CONFIG_DISCONTIGMEM
-
-/*
- * generic node memory support, the following assumptions apply:
- *
- * 1) memory comes in 64Mb contiguous chunks which are either present or not
- * 2) we will not have more than 64Gb in total
- *
- * for now assume that 64Gb is max amount of RAM for whole system
- *    64Gb / 4096bytes/page = 16777216 pages
- */
-#define MAX_NR_PAGES 16777216
-#define MAX_ELEMENTS 1024
-#define PAGES_PER_ELEMENT (MAX_NR_PAGES/MAX_ELEMENTS)
-
-extern s8 physnode_map[];
-
-static inline int pfn_to_nid(unsigned long pfn)
-{
-#ifdef CONFIG_NUMA
-	return((int) physnode_map[(pfn) / PAGES_PER_ELEMENT]);
-#else
-	return 0;
-#endif
-}
-
-/*
- * Following are macros that each numa implmentation must define.
- */
-
-#define node_start_pfn(nid)	(NODE_DATA(nid)->node_start_pfn)
-#define node_end_pfn(nid)						\
-({									\
-	pg_data_t *__pgdat = NODE_DATA(nid);				\
-	__pgdat->node_start_pfn + __pgdat->node_spanned_pages;		\
-})
-
-static inline int pfn_valid(int pfn)
-{
-	int nid = pfn_to_nid(pfn);
-
-	if (nid >= 0)
-		return (pfn < node_end_pfn(nid));
-	return 0;
-}
-
-#endif /* CONFIG_DISCONTIGMEM */
-
 #ifdef CONFIG_NEED_MULTIPLE_NODES
 /* always use node 0 for bootmem on this numa platform */
 #define bootmem_arch_preferred_node(__bdata, size, align, goal, limit)	\
diff --git a/arch/x86/include/asm/pgtable_32.h b/arch/x86/include/asm/pgtable_32.h
index 0c92113..ee5c54d 100644
--- a/arch/x86/include/asm/pgtable_32.h
+++ b/arch/x86/include/asm/pgtable_32.h
@@ -74,10 +74,7 @@ do {						\
 
 #endif /* !__ASSEMBLY__ */
 
-/*
- * kern_addr_valid() is (1) for FLATMEM and (0) for
- * SPARSEMEM and DISCONTIGMEM
- */
+/* kern_addr_valid() is (1) for FLATMEM and (0) for SPARSEMEM */
 #ifdef CONFIG_FLATMEM
 #define kern_addr_valid(addr)	(1)
 #else
diff --git a/arch/x86/mm/numa_32.c b/arch/x86/mm/numa_32.c
index bde3906..7d95167 100644
--- a/arch/x86/mm/numa_32.c
+++ b/arch/x86/mm/numa_32.c
@@ -55,50 +55,6 @@ EXPORT_SYMBOL(node_data);
 unsigned long node_start_pfn[MAX_NUMNODES] __read_mostly;
 unsigned long node_end_pfn[MAX_NUMNODES] __read_mostly;
 
-
-#ifdef CONFIG_DISCONTIGMEM
-/*
- * 4) physnode_map     - the mapping between a pfn and owning node
- * physnode_map keeps track of the physical memory layout of a generic
- * numa node on a 64Mb break (each element of the array will
- * represent 64Mb of memory and will be marked by the node id.  so,
- * if the first gig is on node 0, and the second gig is on node 1
- * physnode_map will contain:
- *
- *     physnode_map[0-15] = 0;
- *     physnode_map[16-31] = 1;
- *     physnode_map[32- ] = -1;
- */
-s8 physnode_map[MAX_ELEMENTS] __read_mostly = { [0 ... (MAX_ELEMENTS - 1)] = -1};
-EXPORT_SYMBOL(physnode_map);
-
-void memory_present(int nid, unsigned long start, unsigned long end)
-{
-	unsigned long pfn;
-
-	printk(KERN_INFO "Node: %d, start_pfn: %lx, end_pfn: %lx\n",
-			nid, start, end);
-	printk(KERN_DEBUG "  Setting physnode_map array to node %d for pfns:\n", nid);
-	printk(KERN_DEBUG "  ");
-	for (pfn = start; pfn < end; pfn += PAGES_PER_ELEMENT) {
-		physnode_map[pfn / PAGES_PER_ELEMENT] = nid;
-		printk(KERN_CONT "%lx ", pfn);
-	}
-	printk(KERN_CONT "\n");
-}
-
-unsigned long node_memmap_size_bytes(int nid, unsigned long start_pfn,
-					      unsigned long end_pfn)
-{
-	unsigned long nr_pages = end_pfn - start_pfn;
-
-	if (!nr_pages)
-		return 0;
-
-	return (nr_pages + 1) * sizeof(struct page);
-}
-#endif
-
 extern unsigned long find_max_low_pfn(void);
 extern unsigned long highend_pfn, highstart_pfn;
 
@@ -182,12 +138,12 @@ static void __init allocate_pgdat(int nid)
 }
 
 /*
- * In the DISCONTIGMEM and SPARSEMEM memory model, a portion of the kernel
- * virtual address space (KVA) is reserved and portions of nodes are mapped
- * using it. This is to allow node-local memory to be allocated for
- * structures that would normally require ZONE_NORMAL. The memory is
- * allocated with alloc_remap() and callers should be prepared to allocate
- * from the bootmem allocator instead.
+ * In the SPARSEMEM memory model, a portion of the kernel virtual address
+ * space (KVA) is reserved and portions of nodes are mapped using it. This
+ * is to allow node-local memory to be allocated for structures that would
+ * normally require ZONE_NORMAL. The memory is allocated with alloc_remap()
+ * and callers should be prepared to allocate from the bootmem allocator
+ * instead.
  */
 static unsigned long node_remap_start_pfn[MAX_NUMNODES];
 static void *node_remap_end_vaddr[MAX_NUMNODES];
-- 
1.7.1