From 49c3df6aaa6a51071fc135273d1a2515d019099f Mon Sep 17 00:00:00 2001
From: Vivek Goyal <vgoyal@in.ibm.com>
Date: Wed, 2 May 2007 19:27:07 +0200
Subject: [PATCH] x86: Move swsusp __pa() dependent code to arch portion

o __pa() should be used only on kernel linearly mapped virtual addresses
  and not on kernel text and data addresses.

o Hibernation code needs to determine the physical address associated
  with kernel symbol to mark a section boundary which contains pages which
  don't have to be saved and restored during hibernate/resume operation.

o Move this piece of code in arch dependent section. So that architectures
  which don't have kernel text/data mapped into kernel linearly mapped
  region can come up with their own ways of determining physical addresses
  associated with a kernel text.

Signed-off-by: Vivek Goyal <vgoyal@in.ibm.com>
Signed-off-by: Andi Kleen <ak@suse.de>
---
 kernel/power/power.h    |  5 ++---
 kernel/power/snapshot.c | 11 -----------
 2 files changed, 2 insertions(+), 14 deletions(-)

(limited to 'kernel')

diff --git a/kernel/power/power.h b/kernel/power/power.h
index eb461b816bf..1c6eef8df4a 100644
--- a/kernel/power/power.h
+++ b/kernel/power/power.h
@@ -23,6 +23,8 @@ static inline int pm_suspend_disk(void)
 }
 #endif
 
+extern int pfn_is_nosave(unsigned long);
+
 extern struct mutex pm_mutex;
 
 #define power_attr(_name) \
@@ -37,9 +39,6 @@ static struct subsys_attribute _name##_attr = {	\
 
 extern struct subsystem power_subsys;
 
-/* References to section boundaries */
-extern const void __nosave_begin, __nosave_end;
-
 /* Preferred image size in bytes (default 500 MB) */
 extern unsigned long image_size;
 extern int in_suspend;
diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c
index fc53ad06812..704c25a3ffe 100644
--- a/kernel/power/snapshot.c
+++ b/kernel/power/snapshot.c
@@ -650,17 +650,6 @@ static inline void *saveable_highmem_page(unsigned long pfn) { return NULL; }
 static inline unsigned int count_highmem_pages(void) { return 0; }
 #endif /* CONFIG_HIGHMEM */
 
-/**
- *	pfn_is_nosave - check if given pfn is in the 'nosave' section
- */
-
-static inline int pfn_is_nosave(unsigned long pfn)
-{
-	unsigned long nosave_begin_pfn = __pa(&__nosave_begin) >> PAGE_SHIFT;
-	unsigned long nosave_end_pfn = PAGE_ALIGN(__pa(&__nosave_end)) >> PAGE_SHIFT;
-	return (pfn >= nosave_begin_pfn) && (pfn < nosave_end_pfn);
-}
-
 /**
  *	saveable - Determine whether a non-highmem page should be included in
  *	the suspend image.
-- 
cgit v1.2.3-70-g09d2


From 1b29c1643c0d82512477ccd97dc290198fe23e22 Mon Sep 17 00:00:00 2001
From: Vivek Goyal <vgoyal@in.ibm.com>
Date: Wed, 2 May 2007 19:27:07 +0200
Subject: [PATCH] x86-64: do not use virt_to_page on kernel data address

o virt_to_page() call should be used on kernel linear addresses and not
  on kernel text and data addresses. Swsusp code uses it on kernel data
  (statically allocated swsusp_header).

o Allocate swsusp_header dynamically so that virt_to_page() can be used
  safely.

o I am changing this because in next few patches, __pa() on x86_64 will
  no longer support kernel text and data addresses and hibernation breaks.

Signed-off-by: Vivek Goyal <vgoyal@in.ibm.com>
Signed-off-by: Andi Kleen <ak@suse.de>
---
 kernel/power/swap.c | 42 +++++++++++++++++++++++++++---------------
 1 file changed, 27 insertions(+), 15 deletions(-)

(limited to 'kernel')

diff --git a/kernel/power/swap.c b/kernel/power/swap.c
index 3581f8f86ac..b18c155cbb6 100644
--- a/kernel/power/swap.c
+++ b/kernel/power/swap.c
@@ -33,12 +33,14 @@ extern char resume_file[];
 
 #define SWSUSP_SIG	"S1SUSPEND"
 
-static struct swsusp_header {
+struct swsusp_header {
 	char reserved[PAGE_SIZE - 20 - sizeof(sector_t)];
 	sector_t image;
 	char	orig_sig[10];
 	char	sig[10];
-} __attribute__((packed, aligned(PAGE_SIZE))) swsusp_header;
+} __attribute__((packed));
+
+static struct swsusp_header *swsusp_header;
 
 /*
  * General things
@@ -141,14 +143,14 @@ static int mark_swapfiles(sector_t start)
 {
 	int error;
 
-	bio_read_page(swsusp_resume_block, &swsusp_header, NULL);
-	if (!memcmp("SWAP-SPACE",swsusp_header.sig, 10) ||
-	    !memcmp("SWAPSPACE2",swsusp_header.sig, 10)) {
-		memcpy(swsusp_header.orig_sig,swsusp_header.sig, 10);
-		memcpy(swsusp_header.sig,SWSUSP_SIG, 10);
-		swsusp_header.image = start;
+	bio_read_page(swsusp_resume_block, swsusp_header, NULL);
+	if (!memcmp("SWAP-SPACE",swsusp_header->sig, 10) ||
+	    !memcmp("SWAPSPACE2",swsusp_header->sig, 10)) {
+		memcpy(swsusp_header->orig_sig,swsusp_header->sig, 10);
+		memcpy(swsusp_header->sig,SWSUSP_SIG, 10);
+		swsusp_header->image = start;
 		error = bio_write_page(swsusp_resume_block,
-					&swsusp_header, NULL);
+					swsusp_header, NULL);
 	} else {
 		printk(KERN_ERR "swsusp: Swap header not found!\n");
 		error = -ENODEV;
@@ -564,7 +566,7 @@ int swsusp_read(void)
 	if (error < PAGE_SIZE)
 		return error < 0 ? error : -EFAULT;
 	header = (struct swsusp_info *)data_of(snapshot);
-	error = get_swap_reader(&handle, swsusp_header.image);
+	error = get_swap_reader(&handle, swsusp_header->image);
 	if (!error)
 		error = swap_read_page(&handle, header, NULL);
 	if (!error)
@@ -591,17 +593,17 @@ int swsusp_check(void)
 	resume_bdev = open_by_devnum(swsusp_resume_device, FMODE_READ);
 	if (!IS_ERR(resume_bdev)) {
 		set_blocksize(resume_bdev, PAGE_SIZE);
-		memset(&swsusp_header, 0, sizeof(swsusp_header));
+		memset(swsusp_header, 0, sizeof(PAGE_SIZE));
 		error = bio_read_page(swsusp_resume_block,
-					&swsusp_header, NULL);
+					swsusp_header, NULL);
 		if (error)
 			return error;
 
-		if (!memcmp(SWSUSP_SIG, swsusp_header.sig, 10)) {
-			memcpy(swsusp_header.sig, swsusp_header.orig_sig, 10);
+		if (!memcmp(SWSUSP_SIG, swsusp_header->sig, 10)) {
+			memcpy(swsusp_header->sig, swsusp_header->orig_sig, 10);
 			/* Reset swap signature now */
 			error = bio_write_page(swsusp_resume_block,
-						&swsusp_header, NULL);
+						swsusp_header, NULL);
 		} else {
 			return -EINVAL;
 		}
@@ -632,3 +634,13 @@ void swsusp_close(void)
 
 	blkdev_put(resume_bdev);
 }
+
+static int swsusp_header_init(void)
+{
+	swsusp_header = (struct swsusp_header*) __get_free_page(GFP_KERNEL);
+	if (!swsusp_header)
+		panic("Could not allocate memory for swsusp_header\n");
+	return 0;
+}
+
+core_initcall(swsusp_header_init);
-- 
cgit v1.2.3-70-g09d2


From b00742d399513a4100c24cc2accefdc1bb1e0b15 Mon Sep 17 00:00:00 2001
From: Jeremy Fitzhardinge <jeremy@goop.org>
Date: Wed, 2 May 2007 19:27:11 +0200
Subject: [PATCH] x86-64: Account for module percpu space separately from
 kernel percpu

Rather than using a single constant PERCPU_ENOUGH_ROOM, compute it as
the sum of kernel_percpu + PERCPU_MODULE_RESERVE.  This is now common
to all architectures; if an architecture wants to set
PERCPU_ENOUGH_ROOM to something special, then it may do so (ia64 is
the only one which does).

Signed-off-by: Jeremy Fitzhardinge <jeremy@xensource.com>
Signed-off-by: Andi Kleen <ak@suse.de>
Cc: Rusty Russell <rusty@rustcorp.com.au>
Cc: Eric W. Biederman <ebiederm@xmission.com>
Cc: Andi Kleen <ak@suse.de>
---
 include/asm-alpha/percpu.h   | 14 --------------
 include/asm-sparc64/percpu.h | 10 ----------
 include/asm-x86_64/percpu.h  | 10 ----------
 include/linux/percpu.h       |  9 ++++++++-
 kernel/module.c              |  2 +-
 5 files changed, 9 insertions(+), 36 deletions(-)

(limited to 'kernel')

diff --git a/include/asm-alpha/percpu.h b/include/asm-alpha/percpu.h
index 651ebb141b2..48348fe34c1 100644
--- a/include/asm-alpha/percpu.h
+++ b/include/asm-alpha/percpu.h
@@ -1,20 +1,6 @@
 #ifndef __ALPHA_PERCPU_H
 #define __ALPHA_PERCPU_H
 
-/*
- * Increase the per cpu area for Alpha so that
- * modules using percpu area can load.
- */
-#ifdef CONFIG_MODULES
-# define PERCPU_MODULE_RESERVE 8192
-#else
-# define PERCPU_MODULE_RESERVE 0
-#endif
-
-#define PERCPU_ENOUGH_ROOM \
-	(ALIGN(__per_cpu_end - __per_cpu_start, SMP_CACHE_BYTES) + \
-	 PERCPU_MODULE_RESERVE)
-
 #include <asm-generic/percpu.h>
 
 #endif /* __ALPHA_PERCPU_H */
diff --git a/include/asm-sparc64/percpu.h b/include/asm-sparc64/percpu.h
index 0d3df76aa47..ced8cbde046 100644
--- a/include/asm-sparc64/percpu.h
+++ b/include/asm-sparc64/percpu.h
@@ -5,16 +5,6 @@
 
 #ifdef CONFIG_SMP
 
-#ifdef CONFIG_MODULES
-# define PERCPU_MODULE_RESERVE 8192
-#else
-# define PERCPU_MODULE_RESERVE 0
-#endif
-
-#define PERCPU_ENOUGH_ROOM \
-	(ALIGN(__per_cpu_end - __per_cpu_start, SMP_CACHE_BYTES) + \
-	 PERCPU_MODULE_RESERVE)
-
 extern void setup_per_cpu_areas(void);
 
 extern unsigned long __per_cpu_base;
diff --git a/include/asm-x86_64/percpu.h b/include/asm-x86_64/percpu.h
index 5ed0ef34084..c6fbb67eac9 100644
--- a/include/asm-x86_64/percpu.h
+++ b/include/asm-x86_64/percpu.h
@@ -11,16 +11,6 @@
 
 #include <asm/pda.h>
 
-#ifdef CONFIG_MODULES
-# define PERCPU_MODULE_RESERVE 8192
-#else
-# define PERCPU_MODULE_RESERVE 0
-#endif
-
-#define PERCPU_ENOUGH_ROOM \
-	(ALIGN(__per_cpu_end - __per_cpu_start, SMP_CACHE_BYTES) + \
-	 PERCPU_MODULE_RESERVE)
-
 #define __per_cpu_offset(cpu) (cpu_pda(cpu)->data_offset)
 #define __my_cpu_offset() read_pda(data_offset)
 
diff --git a/include/linux/percpu.h b/include/linux/percpu.h
index 600e3d387ff..b72be2f79e6 100644
--- a/include/linux/percpu.h
+++ b/include/linux/percpu.h
@@ -11,9 +11,16 @@
 
 /* Enough to cover all DEFINE_PER_CPUs in kernel, including modules. */
 #ifndef PERCPU_ENOUGH_ROOM
-#define PERCPU_ENOUGH_ROOM 32768
+#ifdef CONFIG_MODULES
+#define PERCPU_MODULE_RESERVE	8192
+#else
+#define PERCPU_MODULE_RESERVE	0
 #endif
 
+#define PERCPU_ENOUGH_ROOM						\
+	(__per_cpu_end - __per_cpu_start + PERCPU_MODULE_RESERVE)
+#endif	/* PERCPU_ENOUGH_ROOM */
+
 /*
  * Must be an lvalue. Since @var must be a simple identifier,
  * we force a syntax error here if it isn't.
diff --git a/kernel/module.c b/kernel/module.c
index 9da5af668a2..cf49ca25fcc 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -430,7 +430,7 @@ static int percpu_modinit(void)
 	pcpu_size = kmalloc(sizeof(pcpu_size[0]) * pcpu_num_allocated,
 			    GFP_KERNEL);
 	/* Static in-kernel percpu data (used). */
-	pcpu_size[0] = -ALIGN(__per_cpu_end-__per_cpu_start, SMP_CACHE_BYTES);
+	pcpu_size[0] = -(__per_cpu_end-__per_cpu_start);
 	/* Free room. */
 	pcpu_size[1] = PERCPU_ENOUGH_ROOM + pcpu_size[0];
 	if (pcpu_size[1] < 0) {
-- 
cgit v1.2.3-70-g09d2


From b6e3590f8145c77b8fcef3247e2412335221412f Mon Sep 17 00:00:00 2001
From: Jeremy Fitzhardinge <jeremy@goop.org>
Date: Wed, 2 May 2007 19:27:12 +0200
Subject: [PATCH] x86: Allow percpu variables to be page-aligned

Let's allow page-alignment in general for per-cpu data (wanted by Xen, and
Ingo suggested KVM as well).

Because larger alignments can use more room, we increase the max per-cpu
memory to 64k rather than 32k: it's getting a little tight.

Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
Signed-off-by: Jeremy Fitzhardinge <jeremy@xensource.com>
Signed-off-by: Andi Kleen <ak@suse.de>
Acked-by: Ingo Molnar <mingo@elte.hu>
Cc: Andi Kleen <ak@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 arch/alpha/kernel/vmlinux.lds.S   | 2 +-
 arch/arm/kernel/vmlinux.lds.S     | 2 +-
 arch/cris/arch-v32/vmlinux.lds.S  | 1 +
 arch/frv/kernel/vmlinux.lds.S     | 1 +
 arch/i386/kernel/vmlinux.lds.S    | 2 +-
 arch/m32r/kernel/vmlinux.lds.S    | 2 +-
 arch/mips/kernel/vmlinux.lds.S    | 2 +-
 arch/parisc/kernel/vmlinux.lds.S  | 2 +-
 arch/powerpc/kernel/setup_64.c    | 4 ++--
 arch/powerpc/kernel/vmlinux.lds.S | 6 +-----
 arch/ppc/kernel/vmlinux.lds.S     | 2 +-
 arch/s390/kernel/vmlinux.lds.S    | 2 +-
 arch/sh/kernel/vmlinux.lds.S      | 2 +-
 arch/sh64/kernel/vmlinux.lds.S    | 2 +-
 arch/sparc/kernel/vmlinux.lds.S   | 2 +-
 arch/sparc64/kernel/smp.c         | 6 +++---
 arch/x86_64/kernel/setup64.c      | 4 ++--
 arch/x86_64/kernel/vmlinux.lds.S  | 2 +-
 arch/xtensa/kernel/vmlinux.lds.S  | 2 +-
 init/main.c                       | 8 ++------
 kernel/module.c                   | 8 ++++----
 21 files changed, 29 insertions(+), 35 deletions(-)

(limited to 'kernel')

diff --git a/arch/alpha/kernel/vmlinux.lds.S b/arch/alpha/kernel/vmlinux.lds.S
index 4cc44bd33d3..cf1e6fc6c68 100644
--- a/arch/alpha/kernel/vmlinux.lds.S
+++ b/arch/alpha/kernel/vmlinux.lds.S
@@ -69,7 +69,7 @@ SECTIONS
   . = ALIGN(8);
   SECURITY_INIT
 
-  . = ALIGN(64);
+  . = ALIGN(8192);
   __per_cpu_start = .;
   .data.percpu : { *(.data.percpu) }
   __per_cpu_end = .;
diff --git a/arch/arm/kernel/vmlinux.lds.S b/arch/arm/kernel/vmlinux.lds.S
index ddbdad48f5b..d1a6a597ed9 100644
--- a/arch/arm/kernel/vmlinux.lds.S
+++ b/arch/arm/kernel/vmlinux.lds.S
@@ -59,7 +59,7 @@ SECTIONS
 			usr/built-in.o(.init.ramfs)
 		__initramfs_end = .;
 #endif
-		. = ALIGN(64);
+		. = ALIGN(4096);
 		__per_cpu_start = .;
 			*(.data.percpu)
 		__per_cpu_end = .;
diff --git a/arch/cris/arch-v32/vmlinux.lds.S b/arch/cris/arch-v32/vmlinux.lds.S
index e124fcd766d..dfa25e1542b 100644
--- a/arch/cris/arch-v32/vmlinux.lds.S
+++ b/arch/cris/arch-v32/vmlinux.lds.S
@@ -91,6 +91,7 @@ SECTIONS
 	}
 	SECURITY_INIT
 
+	. =  ALIGN (8192);
 	__per_cpu_start = .;
 	.data.percpu  : { *(.data.percpu) }
 	__per_cpu_end = .;
diff --git a/arch/frv/kernel/vmlinux.lds.S b/arch/frv/kernel/vmlinux.lds.S
index 97910e01682..28eae9735ad 100644
--- a/arch/frv/kernel/vmlinux.lds.S
+++ b/arch/frv/kernel/vmlinux.lds.S
@@ -57,6 +57,7 @@ SECTIONS
   __alt_instructions_end = .;
  .altinstr_replacement : { *(.altinstr_replacement) }
 
+  . = ALIGN(4096);
   __per_cpu_start = .;
   .data.percpu  : { *(.data.percpu) }
   __per_cpu_end = .;
diff --git a/arch/i386/kernel/vmlinux.lds.S b/arch/i386/kernel/vmlinux.lds.S
index f4ec7223183..97fe6eac47c 100644
--- a/arch/i386/kernel/vmlinux.lds.S
+++ b/arch/i386/kernel/vmlinux.lds.S
@@ -194,7 +194,7 @@ SECTIONS
 	__initramfs_end = .;
   }
 #endif
-  . = ALIGN(L1_CACHE_BYTES);
+  . = ALIGN(4096);
   .data.percpu  : AT(ADDR(.data.percpu) - LOAD_OFFSET) {
 	__per_cpu_start = .;
 	*(.data.percpu)
diff --git a/arch/m32r/kernel/vmlinux.lds.S b/arch/m32r/kernel/vmlinux.lds.S
index 439cc257cd1..6c73bca3f47 100644
--- a/arch/m32r/kernel/vmlinux.lds.S
+++ b/arch/m32r/kernel/vmlinux.lds.S
@@ -110,7 +110,7 @@ SECTIONS
   __initramfs_end = .;
 #endif
 
-  . = ALIGN(32);
+  . = ALIGN(4096);
   __per_cpu_start = .;
   .data.percpu  : { *(.data.percpu) }
   __per_cpu_end = .;
diff --git a/arch/mips/kernel/vmlinux.lds.S b/arch/mips/kernel/vmlinux.lds.S
index c76b793310c..043f637e3d1 100644
--- a/arch/mips/kernel/vmlinux.lds.S
+++ b/arch/mips/kernel/vmlinux.lds.S
@@ -119,7 +119,7 @@ SECTIONS
   .init.ramfs : { *(.init.ramfs) }
   __initramfs_end = .;
 #endif
-  . = ALIGN(32);
+  . = ALIGN(_PAGE_SIZE);
   __per_cpu_start = .;
   .data.percpu  : { *(.data.percpu) }
   __per_cpu_end = .;
diff --git a/arch/parisc/kernel/vmlinux.lds.S b/arch/parisc/kernel/vmlinux.lds.S
index 2a8253358c6..c7458599059 100644
--- a/arch/parisc/kernel/vmlinux.lds.S
+++ b/arch/parisc/kernel/vmlinux.lds.S
@@ -181,7 +181,7 @@ SECTIONS
   .init.ramfs : { *(.init.ramfs) }
   __initramfs_end = .;
 #endif
-  . = ALIGN(32);
+  . = ALIGN(ASM_PAGE_SIZE);
   __per_cpu_start = .;
   .data.percpu  : { *(.data.percpu) }
   __per_cpu_end = .;
diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c
index 22083ce3cc3..6018178708a 100644
--- a/arch/powerpc/kernel/setup_64.c
+++ b/arch/powerpc/kernel/setup_64.c
@@ -582,14 +582,14 @@ void __init setup_per_cpu_areas(void)
 	char *ptr;
 
 	/* Copy section for each CPU (we discard the original) */
-	size = ALIGN(__per_cpu_end - __per_cpu_start, SMP_CACHE_BYTES);
+	size = ALIGN(__per_cpu_end - __per_cpu_start, PAGE_SIZE);
 #ifdef CONFIG_MODULES
 	if (size < PERCPU_ENOUGH_ROOM)
 		size = PERCPU_ENOUGH_ROOM;
 #endif
 
 	for_each_possible_cpu(i) {
-		ptr = alloc_bootmem_node(NODE_DATA(cpu_to_node(i)), size);
+		ptr = alloc_bootmem_pages_node(NODE_DATA(cpu_to_node(i)), size);
 		if (!ptr)
 			panic("Cannot allocate cpu data for CPU %d\n", i);
 
diff --git a/arch/powerpc/kernel/vmlinux.lds.S b/arch/powerpc/kernel/vmlinux.lds.S
index 7eefeb4a30e..13206731314 100644
--- a/arch/powerpc/kernel/vmlinux.lds.S
+++ b/arch/powerpc/kernel/vmlinux.lds.S
@@ -139,11 +139,7 @@ SECTIONS
 		__initramfs_end = .;
 	}
 #endif
-#ifdef CONFIG_PPC32
-	. = ALIGN(32);
-#else
-	. = ALIGN(128);
-#endif
+	. = ALIGN(PAGE_SIZE);
 	.data.percpu : {
 		__per_cpu_start = .;
 		*(.data.percpu)
diff --git a/arch/ppc/kernel/vmlinux.lds.S b/arch/ppc/kernel/vmlinux.lds.S
index a0625562a44..44cd128fb71 100644
--- a/arch/ppc/kernel/vmlinux.lds.S
+++ b/arch/ppc/kernel/vmlinux.lds.S
@@ -130,7 +130,7 @@ SECTIONS
   __ftr_fixup : { *(__ftr_fixup) }
   __stop___ftr_fixup = .;
 
-  . = ALIGN(32);
+  . = ALIGN(4096);
   __per_cpu_start = .;
   .data.percpu  : { *(.data.percpu) }
   __per_cpu_end = .;
diff --git a/arch/s390/kernel/vmlinux.lds.S b/arch/s390/kernel/vmlinux.lds.S
index 418f6426a94..e9d3432aba6 100644
--- a/arch/s390/kernel/vmlinux.lds.S
+++ b/arch/s390/kernel/vmlinux.lds.S
@@ -107,7 +107,7 @@ SECTIONS
   . = ALIGN(2);
   __initramfs_end = .;
 #endif
-  . = ALIGN(256);
+  . = ALIGN(4096);
   __per_cpu_start = .;
   .data.percpu  : { *(.data.percpu) }
   __per_cpu_end = .;
diff --git a/arch/sh/kernel/vmlinux.lds.S b/arch/sh/kernel/vmlinux.lds.S
index 78a6c09875b..2f606d0ce1f 100644
--- a/arch/sh/kernel/vmlinux.lds.S
+++ b/arch/sh/kernel/vmlinux.lds.S
@@ -54,7 +54,7 @@ SECTIONS
   . = ALIGN(PAGE_SIZE);
   .data.page_aligned : { *(.data.page_aligned) }
 
-  . = ALIGN(L1_CACHE_BYTES);
+  . = ALIGN(PAGE_SIZE);
   __per_cpu_start = .;
   .data.percpu : { *(.data.percpu) }
   __per_cpu_end = .;
diff --git a/arch/sh64/kernel/vmlinux.lds.S b/arch/sh64/kernel/vmlinux.lds.S
index a59c5e99813..4f9616f3983 100644
--- a/arch/sh64/kernel/vmlinux.lds.S
+++ b/arch/sh64/kernel/vmlinux.lds.S
@@ -85,7 +85,7 @@ SECTIONS
   . = ALIGN(PAGE_SIZE);
   .data.page_aligned : C_PHYS(.data.page_aligned) { *(.data.page_aligned) }
 
-  . = ALIGN(L1_CACHE_BYTES);
+  . = ALIGN(PAGE_SIZE);
   __per_cpu_start = .;
   .data.percpu : C_PHYS(.data.percpu) { *(.data.percpu) }
   __per_cpu_end = . ;
diff --git a/arch/sparc/kernel/vmlinux.lds.S b/arch/sparc/kernel/vmlinux.lds.S
index e5c24e0521d..f0bb6e60e62 100644
--- a/arch/sparc/kernel/vmlinux.lds.S
+++ b/arch/sparc/kernel/vmlinux.lds.S
@@ -65,7 +65,7 @@ SECTIONS
   __initramfs_end = .;
 #endif
 
-  . = ALIGN(32);
+  . = ALIGN(4096);
   __per_cpu_start = .;
   .data.percpu  : { *(.data.percpu) }
   __per_cpu_end = .;
diff --git a/arch/sparc64/kernel/smp.c b/arch/sparc64/kernel/smp.c
index d4f0a70f484..1fac215252e 100644
--- a/arch/sparc64/kernel/smp.c
+++ b/arch/sparc64/kernel/smp.c
@@ -1343,11 +1343,11 @@ void __init setup_per_cpu_areas(void)
 	/* Copy section for each CPU (we discard the original) */
 	goal = PERCPU_ENOUGH_ROOM;
 
-	__per_cpu_shift = 0;
-	for (size = 1UL; size < goal; size <<= 1UL)
+	__per_cpu_shift = PAGE_SHIFT;
+	for (size = PAGE_SIZE; size < goal; size <<= 1UL)
 		__per_cpu_shift++;
 
-	ptr = alloc_bootmem(size * NR_CPUS);
+	ptr = alloc_bootmem_pages(size * NR_CPUS);
 
 	__per_cpu_base = ptr - __per_cpu_start;
 
diff --git a/arch/x86_64/kernel/setup64.c b/arch/x86_64/kernel/setup64.c
index 53064a9a365..64379a80d76 100644
--- a/arch/x86_64/kernel/setup64.c
+++ b/arch/x86_64/kernel/setup64.c
@@ -103,9 +103,9 @@ void __init setup_per_cpu_areas(void)
 		if (!NODE_DATA(cpu_to_node(i))) {
 			printk("cpu with no node %d, num_online_nodes %d\n",
 			       i, num_online_nodes());
-			ptr = alloc_bootmem(size);
+			ptr = alloc_bootmem_pages(size);
 		} else { 
-			ptr = alloc_bootmem_node(NODE_DATA(cpu_to_node(i)), size);
+			ptr = alloc_bootmem_pages_node(NODE_DATA(cpu_to_node(i)), size);
 		}
 		if (!ptr)
 			panic("Cannot allocate cpu data for CPU %d\n", i);
diff --git a/arch/x86_64/kernel/vmlinux.lds.S b/arch/x86_64/kernel/vmlinux.lds.S
index 3bdeb88d28f..7ef0b8820cd 100644
--- a/arch/x86_64/kernel/vmlinux.lds.S
+++ b/arch/x86_64/kernel/vmlinux.lds.S
@@ -195,7 +195,7 @@ SECTIONS
   __initramfs_end = .;
 #endif
 
-    . = ALIGN(CONFIG_X86_L1_CACHE_BYTES);
+  . = ALIGN(4096);
   __per_cpu_start = .;
   .data.percpu  : AT(ADDR(.data.percpu) - LOAD_OFFSET) { *(.data.percpu) }
   __per_cpu_end = .;
diff --git a/arch/xtensa/kernel/vmlinux.lds.S b/arch/xtensa/kernel/vmlinux.lds.S
index ab6370054ce..4fbd66a52a8 100644
--- a/arch/xtensa/kernel/vmlinux.lds.S
+++ b/arch/xtensa/kernel/vmlinux.lds.S
@@ -198,7 +198,7 @@ SECTIONS
   __ftr_fixup : { *(__ftr_fixup) }
   __stop___ftr_fixup = .;
 
-  . = ALIGN(32);
+  . = ALIGN(4096);
   __per_cpu_start = .;
   .data.percpu  : { *(.data.percpu) }
   __per_cpu_end = .;
diff --git a/init/main.c b/init/main.c
index a92989e7836..80f09f31bfa 100644
--- a/init/main.c
+++ b/init/main.c
@@ -369,12 +369,8 @@ static void __init setup_per_cpu_areas(void)
 	unsigned long nr_possible_cpus = num_possible_cpus();
 
 	/* Copy section for each CPU (we discard the original) */
-	size = ALIGN(__per_cpu_end - __per_cpu_start, SMP_CACHE_BYTES);
-#ifdef CONFIG_MODULES
-	if (size < PERCPU_ENOUGH_ROOM)
-		size = PERCPU_ENOUGH_ROOM;
-#endif
-	ptr = alloc_bootmem(size * nr_possible_cpus);
+	size = ALIGN(PERCPU_ENOUGH_ROOM, PAGE_SIZE);
+	ptr = alloc_bootmem_pages(size * nr_possible_cpus);
 
 	for_each_possible_cpu(i) {
 		__per_cpu_offset[i] = ptr - __per_cpu_start;
diff --git a/kernel/module.c b/kernel/module.c
index cf49ca25fcc..4dc4a257545 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -346,10 +346,10 @@ static void *percpu_modalloc(unsigned long size, unsigned long align,
 	unsigned int i;
 	void *ptr;
 
-	if (align > SMP_CACHE_BYTES) {
-		printk(KERN_WARNING "%s: per-cpu alignment %li > %i\n",
-		       name, align, SMP_CACHE_BYTES);
-		align = SMP_CACHE_BYTES;
+	if (align > PAGE_SIZE) {
+		printk(KERN_WARNING "%s: per-cpu alignment %li > %li\n",
+		       name, align, PAGE_SIZE);
+		align = PAGE_SIZE;
 	}
 
 	ptr = __per_cpu_start;
-- 
cgit v1.2.3-70-g09d2


From d6dd61c831226f9cd7750885da04d360d6455101 Mon Sep 17 00:00:00 2001
From: Jeremy Fitzhardinge <jeremy@goop.org>
Date: Wed, 2 May 2007 19:27:14 +0200
Subject: [PATCH] x86: PARAVIRT: add hooks to intercept mm creation and
 destruction

Add hooks to allow a paravirt implementation to track the lifetime of
an mm.  Paravirtualization requires three hooks, but only two are
needed in common code.  They are:

arch_dup_mmap, which is called when a new mmap is created at fork

arch_exit_mmap, which is called when the last process reference to an
  mm is dropped, which typically happens on exit and exec.

The third hook is activate_mm, which is called from the arch-specific
activate_mm() macro/function, and so doesn't need stub versions for
other architectures.  It's called when an mm is first used.

Signed-off-by: Jeremy Fitzhardinge <jeremy@xensource.com>
Signed-off-by: Andi Kleen <ak@suse.de>
Cc: linux-arch@vger.kernel.org
Cc: James Bottomley <James.Bottomley@SteelEye.com>
Acked-by: Ingo Molnar <mingo@elte.hu>
---
 arch/i386/kernel/paravirt.c         |  4 ++++
 include/asm-alpha/mmu_context.h     |  1 +
 include/asm-arm/mmu_context.h       |  1 +
 include/asm-arm26/mmu_context.h     |  2 ++
 include/asm-avr32/mmu_context.h     |  1 +
 include/asm-cris/mmu_context.h      |  2 ++
 include/asm-frv/mmu_context.h       |  1 +
 include/asm-generic/mm_hooks.h      | 18 ++++++++++++++++++
 include/asm-h8300/mmu_context.h     |  1 +
 include/asm-i386/mmu_context.h      | 17 +++++++++++++++--
 include/asm-i386/paravirt.h         | 23 +++++++++++++++++++++++
 include/asm-ia64/mmu_context.h      |  1 +
 include/asm-m32r/mmu_context.h      |  1 +
 include/asm-m68k/mmu_context.h      |  1 +
 include/asm-m68knommu/mmu_context.h |  1 +
 include/asm-mips/mmu_context.h      |  1 +
 include/asm-parisc/mmu_context.h    |  1 +
 include/asm-powerpc/mmu_context.h   |  1 +
 include/asm-ppc/mmu_context.h       |  1 +
 include/asm-s390/mmu_context.h      |  2 ++
 include/asm-sh/mmu_context.h        |  1 +
 include/asm-sh64/mmu_context.h      |  2 +-
 include/asm-sparc/mmu_context.h     |  2 ++
 include/asm-sparc64/mmu_context.h   |  1 +
 include/asm-um/mmu_context.h        |  2 ++
 include/asm-v850/mmu_context.h      |  2 ++
 include/asm-x86_64/mmu_context.h    |  1 +
 include/asm-xtensa/mmu_context.h    |  1 +
 kernel/fork.c                       |  2 ++
 mm/mmap.c                           |  4 ++++
 30 files changed, 96 insertions(+), 3 deletions(-)
 create mode 100644 include/asm-generic/mm_hooks.h

(limited to 'kernel')

diff --git a/arch/i386/kernel/paravirt.c b/arch/i386/kernel/paravirt.c
index 2040a831d5b..54cc14d9974 100644
--- a/arch/i386/kernel/paravirt.c
+++ b/arch/i386/kernel/paravirt.c
@@ -237,6 +237,10 @@ struct paravirt_ops paravirt_ops = {
 	.irq_enable_sysexit = native_irq_enable_sysexit,
 	.iret = native_iret,
 
+	.dup_mmap = paravirt_nop,
+	.exit_mmap = paravirt_nop,
+	.activate_mm = paravirt_nop,
+
 	.startup_ipi_hook = paravirt_nop,
 };
 
diff --git a/include/asm-alpha/mmu_context.h b/include/asm-alpha/mmu_context.h
index fe249e9d336..0bd7bd2ccb9 100644
--- a/include/asm-alpha/mmu_context.h
+++ b/include/asm-alpha/mmu_context.h
@@ -10,6 +10,7 @@
 #include <asm/system.h>
 #include <asm/machvec.h>
 #include <asm/compiler.h>
+#include <asm-generic/mm_hooks.h>
 
 /*
  * Force a context reload. This is needed when we change the page
diff --git a/include/asm-arm/mmu_context.h b/include/asm-arm/mmu_context.h
index d1a65b1edca..f8755c818b5 100644
--- a/include/asm-arm/mmu_context.h
+++ b/include/asm-arm/mmu_context.h
@@ -16,6 +16,7 @@
 #include <linux/compiler.h>
 #include <asm/cacheflush.h>
 #include <asm/proc-fns.h>
+#include <asm-generic/mm_hooks.h>
 
 void __check_kvm_seq(struct mm_struct *mm);
 
diff --git a/include/asm-arm26/mmu_context.h b/include/asm-arm26/mmu_context.h
index 1a929bfe5c3..16c821f81b8 100644
--- a/include/asm-arm26/mmu_context.h
+++ b/include/asm-arm26/mmu_context.h
@@ -13,6 +13,8 @@
 #ifndef __ASM_ARM_MMU_CONTEXT_H
 #define __ASM_ARM_MMU_CONTEXT_H
 
+#include <asm-generic/mm_hooks.h>
+
 #define init_new_context(tsk,mm)	0
 #define destroy_context(mm)		do { } while(0)
 
diff --git a/include/asm-avr32/mmu_context.h b/include/asm-avr32/mmu_context.h
index 31add1ae808..c37c391faef 100644
--- a/include/asm-avr32/mmu_context.h
+++ b/include/asm-avr32/mmu_context.h
@@ -15,6 +15,7 @@
 #include <asm/tlbflush.h>
 #include <asm/pgalloc.h>
 #include <asm/sysreg.h>
+#include <asm-generic/mm_hooks.h>
 
 /*
  * The MMU "context" consists of two things:
diff --git a/include/asm-cris/mmu_context.h b/include/asm-cris/mmu_context.h
index e6e659dc757..72ba08dcfd1 100644
--- a/include/asm-cris/mmu_context.h
+++ b/include/asm-cris/mmu_context.h
@@ -1,6 +1,8 @@
 #ifndef __CRIS_MMU_CONTEXT_H
 #define __CRIS_MMU_CONTEXT_H
 
+#include <asm-generic/mm_hooks.h>
+
 extern int init_new_context(struct task_struct *tsk, struct mm_struct *mm);
 extern void get_mmu_context(struct mm_struct *mm);
 extern void destroy_context(struct mm_struct *mm);
diff --git a/include/asm-frv/mmu_context.h b/include/asm-frv/mmu_context.h
index 72edcaaccd5..c7daa395156 100644
--- a/include/asm-frv/mmu_context.h
+++ b/include/asm-frv/mmu_context.h
@@ -15,6 +15,7 @@
 #include <asm/setup.h>
 #include <asm/page.h>
 #include <asm/pgalloc.h>
+#include <asm-generic/mm_hooks.h>
 
 static inline void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk)
 {
diff --git a/include/asm-generic/mm_hooks.h b/include/asm-generic/mm_hooks.h
new file mode 100644
index 00000000000..67dea812368
--- /dev/null
+++ b/include/asm-generic/mm_hooks.h
@@ -0,0 +1,18 @@
+/*
+ * Define generic no-op hooks for arch_dup_mmap and arch_exit_mmap, to
+ * be included in asm-FOO/mmu_context.h for any arch FOO which doesn't
+ * need to hook these.
+ */
+#ifndef _ASM_GENERIC_MM_HOOKS_H
+#define _ASM_GENERIC_MM_HOOKS_H
+
+static inline void arch_dup_mmap(struct mm_struct *oldmm,
+				 struct mm_struct *mm)
+{
+}
+
+static inline void arch_exit_mmap(struct mm_struct *mm)
+{
+}
+
+#endif	/* _ASM_GENERIC_MM_HOOKS_H */
diff --git a/include/asm-h8300/mmu_context.h b/include/asm-h8300/mmu_context.h
index 5c165f7bee0..f44b730da54 100644
--- a/include/asm-h8300/mmu_context.h
+++ b/include/asm-h8300/mmu_context.h
@@ -4,6 +4,7 @@
 #include <asm/setup.h>
 #include <asm/page.h>
 #include <asm/pgalloc.h>
+#include <asm-generic/mm_hooks.h>
 
 static inline void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk)
 {
diff --git a/include/asm-i386/mmu_context.h b/include/asm-i386/mmu_context.h
index e6aa30f8de5..8198d1cca1f 100644
--- a/include/asm-i386/mmu_context.h
+++ b/include/asm-i386/mmu_context.h
@@ -5,6 +5,16 @@
 #include <asm/atomic.h>
 #include <asm/pgalloc.h>
 #include <asm/tlbflush.h>
+#include <asm/paravirt.h>
+#ifndef CONFIG_PARAVIRT
+#include <asm-generic/mm_hooks.h>
+
+static inline void paravirt_activate_mm(struct mm_struct *prev,
+					struct mm_struct *next)
+{
+}
+#endif	/* !CONFIG_PARAVIRT */
+
 
 /*
  * Used for LDT copy/destruction.
@@ -65,7 +75,10 @@ static inline void switch_mm(struct mm_struct *prev,
 #define deactivate_mm(tsk, mm)			\
 	asm("movl %0,%%gs": :"r" (0));
 
-#define activate_mm(prev, next) \
-	switch_mm((prev),(next),NULL)
+#define activate_mm(prev, next)				\
+	do {						\
+		paravirt_activate_mm(prev, next);	\
+		switch_mm((prev),(next),NULL);		\
+	} while(0);
 
 #endif
diff --git a/include/asm-i386/paravirt.h b/include/asm-i386/paravirt.h
index f93599dc775..61c03f1e0c2 100644
--- a/include/asm-i386/paravirt.h
+++ b/include/asm-i386/paravirt.h
@@ -119,6 +119,12 @@ struct paravirt_ops
 
 	void (*io_delay)(void);
 
+	void (*activate_mm)(struct mm_struct *prev,
+			    struct mm_struct *next);
+	void (*dup_mmap)(struct mm_struct *oldmm,
+			 struct mm_struct *mm);
+	void (*exit_mmap)(struct mm_struct *mm);
+
 #ifdef CONFIG_X86_LOCAL_APIC
 	void (*apic_write)(unsigned long reg, unsigned long v);
 	void (*apic_write_atomic)(unsigned long reg, unsigned long v);
@@ -395,6 +401,23 @@ static inline void startup_ipi_hook(int phys_apicid, unsigned long start_eip,
 }
 #endif
 
+static inline void paravirt_activate_mm(struct mm_struct *prev,
+					struct mm_struct *next)
+{
+	paravirt_ops.activate_mm(prev, next);
+}
+
+static inline void arch_dup_mmap(struct mm_struct *oldmm,
+				 struct mm_struct *mm)
+{
+	paravirt_ops.dup_mmap(oldmm, mm);
+}
+
+static inline void arch_exit_mmap(struct mm_struct *mm)
+{
+	paravirt_ops.exit_mmap(mm);
+}
+
 #define __flush_tlb() paravirt_ops.flush_tlb_user()
 #define __flush_tlb_global() paravirt_ops.flush_tlb_kernel()
 #define __flush_tlb_single(addr) paravirt_ops.flush_tlb_single(addr)
diff --git a/include/asm-ia64/mmu_context.h b/include/asm-ia64/mmu_context.h
index b5c65081a3a..cef2400983f 100644
--- a/include/asm-ia64/mmu_context.h
+++ b/include/asm-ia64/mmu_context.h
@@ -29,6 +29,7 @@
 #include <linux/spinlock.h>
 
 #include <asm/processor.h>
+#include <asm-generic/mm_hooks.h>
 
 struct ia64_ctx {
 	spinlock_t lock;
diff --git a/include/asm-m32r/mmu_context.h b/include/asm-m32r/mmu_context.h
index 1f40d4a0acf..91909e5dd9d 100644
--- a/include/asm-m32r/mmu_context.h
+++ b/include/asm-m32r/mmu_context.h
@@ -15,6 +15,7 @@
 #include <asm/pgalloc.h>
 #include <asm/mmu.h>
 #include <asm/tlbflush.h>
+#include <asm-generic/mm_hooks.h>
 
 /*
  * Cache of MMU context last used.
diff --git a/include/asm-m68k/mmu_context.h b/include/asm-m68k/mmu_context.h
index 231d11bd8e3..894dacbcee1 100644
--- a/include/asm-m68k/mmu_context.h
+++ b/include/asm-m68k/mmu_context.h
@@ -1,6 +1,7 @@
 #ifndef __M68K_MMU_CONTEXT_H
 #define __M68K_MMU_CONTEXT_H
 
+#include <asm-generic/mm_hooks.h>
 
 static inline void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk)
 {
diff --git a/include/asm-m68knommu/mmu_context.h b/include/asm-m68knommu/mmu_context.h
index 6c077d3a257..9ccee4278c9 100644
--- a/include/asm-m68knommu/mmu_context.h
+++ b/include/asm-m68knommu/mmu_context.h
@@ -4,6 +4,7 @@
 #include <asm/setup.h>
 #include <asm/page.h>
 #include <asm/pgalloc.h>
+#include <asm-generic/mm_hooks.h>
 
 static inline void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk)
 {
diff --git a/include/asm-mips/mmu_context.h b/include/asm-mips/mmu_context.h
index fe065d6070c..65024ffd787 100644
--- a/include/asm-mips/mmu_context.h
+++ b/include/asm-mips/mmu_context.h
@@ -20,6 +20,7 @@
 #include <asm/mipsmtregs.h>
 #include <asm/smtc.h>
 #endif /* SMTC */
+#include <asm-generic/mm_hooks.h>
 
 /*
  * For the fast tlb miss handlers, we keep a per cpu array of pointers
diff --git a/include/asm-parisc/mmu_context.h b/include/asm-parisc/mmu_context.h
index 9c05836239a..bad690298f0 100644
--- a/include/asm-parisc/mmu_context.h
+++ b/include/asm-parisc/mmu_context.h
@@ -5,6 +5,7 @@
 #include <asm/atomic.h>
 #include <asm/pgalloc.h>
 #include <asm/pgtable.h>
+#include <asm-generic/mm_hooks.h>
 
 static inline void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk)
 {
diff --git a/include/asm-powerpc/mmu_context.h b/include/asm-powerpc/mmu_context.h
index 083ac917bd2..c0d7795e3d2 100644
--- a/include/asm-powerpc/mmu_context.h
+++ b/include/asm-powerpc/mmu_context.h
@@ -10,6 +10,7 @@
 #include <linux/mm.h>	
 #include <asm/mmu.h>	
 #include <asm/cputable.h>
+#include <asm-generic/mm_hooks.h>
 
 /*
  * Copyright (C) 2001 PPC 64 Team, IBM Corp
diff --git a/include/asm-ppc/mmu_context.h b/include/asm-ppc/mmu_context.h
index 2bc8589cc45..a6441a063e5 100644
--- a/include/asm-ppc/mmu_context.h
+++ b/include/asm-ppc/mmu_context.h
@@ -6,6 +6,7 @@
 #include <asm/bitops.h>
 #include <asm/mmu.h>
 #include <asm/cputable.h>
+#include <asm-generic/mm_hooks.h>
 
 /*
  * On 32-bit PowerPC 6xx/7xx/7xxx CPUs, we use a set of 16 VSIDs
diff --git a/include/asm-s390/mmu_context.h b/include/asm-s390/mmu_context.h
index 1d21da220d4..501cb9b0631 100644
--- a/include/asm-s390/mmu_context.h
+++ b/include/asm-s390/mmu_context.h
@@ -10,6 +10,8 @@
 #define __S390_MMU_CONTEXT_H
 
 #include <asm/pgalloc.h>
+#include <asm-generic/mm_hooks.h>
+
 /*
  * get a new mmu context.. S390 don't know about contexts.
  */
diff --git a/include/asm-sh/mmu_context.h b/include/asm-sh/mmu_context.h
index 342024425b7..01acaaae975 100644
--- a/include/asm-sh/mmu_context.h
+++ b/include/asm-sh/mmu_context.h
@@ -12,6 +12,7 @@
 #include <asm/tlbflush.h>
 #include <asm/uaccess.h>
 #include <asm/io.h>
+#include <asm-generic/mm_hooks.h>
 
 /*
  * The MMU "context" consists of two things:
diff --git a/include/asm-sh64/mmu_context.h b/include/asm-sh64/mmu_context.h
index 8c860dab2d0..507bf72bb8e 100644
--- a/include/asm-sh64/mmu_context.h
+++ b/include/asm-sh64/mmu_context.h
@@ -27,7 +27,7 @@
 extern unsigned long mmu_context_cache;
 
 #include <asm/page.h>
-
+#include <asm-generic/mm_hooks.h>
 
 /* Current mm's pgd */
 extern pgd_t *mmu_pdtp_cache;
diff --git a/include/asm-sparc/mmu_context.h b/include/asm-sparc/mmu_context.h
index ed1e01d04d2..671a997b9e6 100644
--- a/include/asm-sparc/mmu_context.h
+++ b/include/asm-sparc/mmu_context.h
@@ -5,6 +5,8 @@
 
 #ifndef __ASSEMBLY__
 
+#include <asm-generic/mm_hooks.h>
+
 static inline void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk)
 {
 }
diff --git a/include/asm-sparc64/mmu_context.h b/include/asm-sparc64/mmu_context.h
index 2337eb48771..8d129032013 100644
--- a/include/asm-sparc64/mmu_context.h
+++ b/include/asm-sparc64/mmu_context.h
@@ -9,6 +9,7 @@
 #include <linux/spinlock.h>
 #include <asm/system.h>
 #include <asm/spitfire.h>
+#include <asm-generic/mm_hooks.h>
 
 static inline void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk)
 {
diff --git a/include/asm-um/mmu_context.h b/include/asm-um/mmu_context.h
index f709c784bf1..9aa4b44e8cc 100644
--- a/include/asm-um/mmu_context.h
+++ b/include/asm-um/mmu_context.h
@@ -6,6 +6,8 @@
 #ifndef __UM_MMU_CONTEXT_H
 #define __UM_MMU_CONTEXT_H
 
+#include <asm-generic/mm_hooks.h>
+
 #include "linux/sched.h"
 #include "choose-mode.h"
 #include "um_mmu.h"
diff --git a/include/asm-v850/mmu_context.h b/include/asm-v850/mmu_context.h
index f521c8050d3..01daacd5474 100644
--- a/include/asm-v850/mmu_context.h
+++ b/include/asm-v850/mmu_context.h
@@ -1,6 +1,8 @@
 #ifndef __V850_MMU_CONTEXT_H__
 #define __V850_MMU_CONTEXT_H__
 
+#include <asm-generic/mm_hooks.h>
+
 #define destroy_context(mm)		((void)0)
 #define init_new_context(tsk,mm)	0
 #define switch_mm(prev,next,tsk)	((void)0)
diff --git a/include/asm-x86_64/mmu_context.h b/include/asm-x86_64/mmu_context.h
index af03b9f852d..0cce83a7837 100644
--- a/include/asm-x86_64/mmu_context.h
+++ b/include/asm-x86_64/mmu_context.h
@@ -7,6 +7,7 @@
 #include <asm/pda.h>
 #include <asm/pgtable.h>
 #include <asm/tlbflush.h>
+#include <asm-generic/mm_hooks.h>
 
 /*
  * possibly do the LDT unload here?
diff --git a/include/asm-xtensa/mmu_context.h b/include/asm-xtensa/mmu_context.h
index f14851f086c..92f948392eb 100644
--- a/include/asm-xtensa/mmu_context.h
+++ b/include/asm-xtensa/mmu_context.h
@@ -18,6 +18,7 @@
 #include <asm/pgtable.h>
 #include <asm/cacheflush.h>
 #include <asm/tlbflush.h>
+#include <asm-generic/mm_hooks.h>
 
 #define XCHAL_MMU_ASID_BITS	8
 
diff --git a/kernel/fork.c b/kernel/fork.c
index 6af959c034d..ffccefb28b6 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -286,6 +286,8 @@ static inline int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm)
 		if (retval)
 			goto out;
 	}
+	/* a new mm has just been created */
+	arch_dup_mmap(oldmm, mm);
 	retval = 0;
 out:
 	up_write(&mm->mmap_sem);
diff --git a/mm/mmap.c b/mm/mmap.c
index 84f997da78d..88da687bde8 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -29,6 +29,7 @@
 #include <asm/uaccess.h>
 #include <asm/cacheflush.h>
 #include <asm/tlb.h>
+#include <asm/mmu_context.h>
 
 #ifndef arch_mmap_check
 #define arch_mmap_check(addr, len, flags)	(0)
@@ -1979,6 +1980,9 @@ void exit_mmap(struct mm_struct *mm)
 	unsigned long nr_accounted = 0;
 	unsigned long end;
 
+	/* mm's last user has gone, and its about to be pulled down */
+	arch_exit_mmap(mm);
+
 	lru_add_drain();
 	flush_cache_mm(mm);
 	tlb = tlb_gather_mmu(mm, 1);
-- 
cgit v1.2.3-70-g09d2