Merge branch 'master' into upstream

28 files changed, 571 insertions, 253 deletions

diff --git a/include/linux/bootmem.h b/include/linux/bootmem.h
index e319c649e4f..31e9abb6d97 100644
--- a/include/linux/bootmem.h
+++ b/include/linux/bootmem.h
@@ -4,11 +4,8 @@
 #ifndef _LINUX_BOOTMEM_H
 #define _LINUX_BOOTMEM_H
 
-#include <asm/pgtable.h>
-#include <asm/dma.h>
-#include <linux/cache.h>
-#include <linux/init.h>
 #include <linux/mmzone.h>
+#include <asm/dma.h>
 
 /*
  *  simple boot-time physical memory area allocator.
@@ -41,45 +38,64 @@ typedef struct bootmem_data {
 	struct list_head list;
 } bootmem_data_t;
 
-extern unsigned long __init bootmem_bootmap_pages (unsigned long);
-extern unsigned long __init init_bootmem (unsigned long addr, unsigned long memend);
-extern void __init free_bootmem (unsigned long addr, unsigned long size);
-extern void * __init __alloc_bootmem (unsigned long size, unsigned long align, unsigned long goal);
-extern void * __init __alloc_bootmem_nopanic (unsigned long size, unsigned long align, unsigned long goal);
-extern void * __init __alloc_bootmem_low(unsigned long size,
-					 unsigned long align,
-					 unsigned long goal);
-extern void * __init __alloc_bootmem_low_node(pg_data_t *pgdat,
-					      unsigned long size,
-					      unsigned long align,
-					      unsigned long goal);
-extern void * __init __alloc_bootmem_core(struct bootmem_data *bdata,
-		unsigned long size, unsigned long align, unsigned long goal,
-		unsigned long limit);
+extern unsigned long bootmem_bootmap_pages(unsigned long);
+extern unsigned long init_bootmem(unsigned long addr, unsigned long memend);
+extern void free_bootmem(unsigned long addr, unsigned long size);
+extern void *__alloc_bootmem(unsigned long size,
+			     unsigned long align,
+			     unsigned long goal);
+extern void *__alloc_bootmem_nopanic(unsigned long size,
+				     unsigned long align,
+				     unsigned long goal);
+extern void *__alloc_bootmem_low(unsigned long size,
+				 unsigned long align,
+				 unsigned long goal);
+extern void *__alloc_bootmem_low_node(pg_data_t *pgdat,
+				      unsigned long size,
+				      unsigned long align,
+				      unsigned long goal);
+extern void *__alloc_bootmem_core(struct bootmem_data *bdata,
+				  unsigned long size,
+				  unsigned long align,
+				  unsigned long goal,
+				  unsigned long limit);
+
 #ifndef CONFIG_HAVE_ARCH_BOOTMEM_NODE
-extern void __init reserve_bootmem (unsigned long addr, unsigned long size);
+extern void reserve_bootmem(unsigned long addr, unsigned long size);
 #define alloc_bootmem(x) \
-	__alloc_bootmem((x), SMP_CACHE_BYTES, __pa(MAX_DMA_ADDRESS))
+	__alloc_bootmem(x, SMP_CACHE_BYTES, __pa(MAX_DMA_ADDRESS))
 #define alloc_bootmem_low(x) \
-	__alloc_bootmem_low((x), SMP_CACHE_BYTES, 0)
+	__alloc_bootmem_low(x, SMP_CACHE_BYTES, 0)
 #define alloc_bootmem_pages(x) \
-	__alloc_bootmem((x), PAGE_SIZE, __pa(MAX_DMA_ADDRESS))
+	__alloc_bootmem(x, PAGE_SIZE, __pa(MAX_DMA_ADDRESS))
 #define alloc_bootmem_low_pages(x) \
-	__alloc_bootmem_low((x), PAGE_SIZE, 0)
+	__alloc_bootmem_low(x, PAGE_SIZE, 0)
 #endif /* !CONFIG_HAVE_ARCH_BOOTMEM_NODE */
-extern unsigned long __init free_all_bootmem (void);
-extern void * __init __alloc_bootmem_node (pg_data_t *pgdat, unsigned long size, unsigned long align, unsigned long goal);
-extern unsigned long __init init_bootmem_node (pg_data_t *pgdat, unsigned long freepfn, unsigned long startpfn, unsigned long endpfn);
-extern void __init reserve_bootmem_node (pg_data_t *pgdat, unsigned long physaddr, unsigned long size);
-extern void __init free_bootmem_node (pg_data_t *pgdat, unsigned long addr, unsigned long size);
-extern unsigned long __init free_all_bootmem_node (pg_data_t *pgdat);
+
+extern unsigned long free_all_bootmem(void);
+extern unsigned long free_all_bootmem_node(pg_data_t *pgdat);
+extern void *__alloc_bootmem_node(pg_data_t *pgdat,
+				  unsigned long size,
+				  unsigned long align,
+				  unsigned long goal);
+extern unsigned long init_bootmem_node(pg_data_t *pgdat,
+				       unsigned long freepfn,
+				       unsigned long startpfn,
+				       unsigned long endpfn);
+extern void reserve_bootmem_node(pg_data_t *pgdat,
+				 unsigned long physaddr,
+				 unsigned long size);
+extern void free_bootmem_node(pg_data_t *pgdat,
+			      unsigned long addr,
+			      unsigned long size);
+
 #ifndef CONFIG_HAVE_ARCH_BOOTMEM_NODE
 #define alloc_bootmem_node(pgdat, x) \
-	__alloc_bootmem_node((pgdat), (x), SMP_CACHE_BYTES, __pa(MAX_DMA_ADDRESS))
+	__alloc_bootmem_node(pgdat, x, SMP_CACHE_BYTES, __pa(MAX_DMA_ADDRESS))
 #define alloc_bootmem_pages_node(pgdat, x) \
-	__alloc_bootmem_node((pgdat), (x), PAGE_SIZE, __pa(MAX_DMA_ADDRESS))
+	__alloc_bootmem_node(pgdat, x, PAGE_SIZE, __pa(MAX_DMA_ADDRESS))
 #define alloc_bootmem_low_pages_node(pgdat, x) \
-	__alloc_bootmem_low_node((pgdat), (x), PAGE_SIZE, 0)
+	__alloc_bootmem_low_node(pgdat, x, PAGE_SIZE, 0)
 #endif /* !CONFIG_HAVE_ARCH_BOOTMEM_NODE */
 
 #ifdef CONFIG_HAVE_ARCH_ALLOC_REMAP
@@ -89,19 +105,19 @@ static inline void *alloc_remap(int nid, unsigned long size)
 {
 	return NULL;
 }
-#endif
+#endif /* CONFIG_HAVE_ARCH_ALLOC_REMAP */
 
 extern unsigned long __meminitdata nr_kernel_pages;
 extern unsigned long nr_all_pages;
 
-extern void *__init alloc_large_system_hash(const char *tablename,
-					    unsigned long bucketsize,
-					    unsigned long numentries,
-					    int scale,
-					    int flags,
-					    unsigned int *_hash_shift,
-					    unsigned int *_hash_mask,
-					    unsigned long limit);
+extern void *alloc_large_system_hash(const char *tablename,
+				     unsigned long bucketsize,
+				     unsigned long numentries,
+				     int scale,
+				     int flags,
+				     unsigned int *_hash_shift,
+				     unsigned int *_hash_mask,
+				     unsigned long limit);
 
 #define HASH_HIGHMEM	0x00000001	/* Consider highmem? */
 #define HASH_EARLY	0x00000002	/* Allocating during early boot? */
diff --git a/include/linux/console.h b/include/linux/console.h
index 3bdf2155e56..76a1807726e 100644
--- a/include/linux/console.h
+++ b/include/linux/console.h
@@ -120,9 +120,14 @@ extern void console_stop(struct console *);
 extern void console_start(struct console *);
 extern int is_console_locked(void);
 
+#ifndef CONFIG_DISABLE_CONSOLE_SUSPEND
 /* Suspend and resume console messages over PM events */
 extern void suspend_console(void);
 extern void resume_console(void);
+#else
+static inline void suspend_console(void) {}
+static inline void resume_console(void) {}
+#endif /* CONFIG_DISABLE_CONSOLE_SUSPEND */
 
 /* Some debug stub to catch some of the obvious races in the VT code */
 #if 1
diff --git a/include/linux/cpu.h b/include/linux/cpu.h
index 8fb344a9abd..3fef7d67aed 100644
--- a/include/linux/cpu.h
+++ b/include/linux/cpu.h
@@ -89,4 +89,12 @@ int cpu_down(unsigned int cpu);
 static inline int cpu_is_offline(int cpu) { return 0; }
 #endif
 
+#ifdef CONFIG_SUSPEND_SMP
+extern int disable_nonboot_cpus(void);
+extern void enable_nonboot_cpus(void);
+#else
+static inline int disable_nonboot_cpus(void) { return 0; }
+static inline void enable_nonboot_cpus(void) {}
+#endif
+
 #endif /* _LINUX_CPU_H_ */
diff --git a/include/linux/dccp.h b/include/linux/dccp.h
index 2d7671c92c0..d6f4ec467a4 100644
--- a/include/linux/dccp.h
+++ b/include/linux/dccp.h
@@ -169,6 +169,12 @@ enum {
 	DCCPO_MAX_CCID_SPECIFIC = 255,
 };
 
+/* DCCP CCIDS */
+enum {
+	DCCPC_CCID2 = 2,
+	DCCPC_CCID3 = 3,
+};
+
 /* DCCP features */
 enum {
 	DCCPF_RESERVED = 0,
@@ -320,7 +326,7 @@ static inline unsigned int dccp_hdr_len(const struct sk_buff *skb)
 /* initial values for each feature */
 #define DCCPF_INITIAL_SEQUENCE_WINDOW		100
 #define DCCPF_INITIAL_ACK_RATIO			2
-#define DCCPF_INITIAL_CCID			2
+#define DCCPF_INITIAL_CCID			DCCPC_CCID2
 #define DCCPF_INITIAL_SEND_ACK_VECTOR		1
 /* FIXME: for now we're default to 1 but it should really be 0 */
 #define DCCPF_INITIAL_SEND_NDP_COUNT		1
@@ -404,6 +410,7 @@ struct dccp_service_list {
 };
 
 #define DCCP_SERVICE_INVALID_VALUE htonl((__u32)-1)
+#define DCCP_SERVICE_CODE_IS_ABSENT 		 0
 
 static inline int dccp_list_has_service(const struct dccp_service_list *sl,
 					const __be32 service)
@@ -484,11 +491,6 @@ static inline struct dccp_minisock *dccp_msk(const struct sock *sk)
 	return (struct dccp_minisock *)&dccp_sk(sk)->dccps_minisock;
 }
 
-static inline int dccp_service_not_initialized(const struct sock *sk)
-{
-	return dccp_sk(sk)->dccps_service == DCCP_SERVICE_INVALID_VALUE;
-}
-
 static inline const char *dccp_role(const struct sock *sk)
 {
 	switch (dccp_sk(sk)->dccps_role) {
diff --git a/include/linux/elf-em.h b/include/linux/elf-em.h
index 6a5796c81c9..666e0a5f00f 100644
--- a/include/linux/elf-em.h
+++ b/include/linux/elf-em.h
@@ -31,6 +31,7 @@
 #define EM_M32R		88	/* Renesas M32R */
 #define EM_H8_300	46	/* Renesas H8/300,300H,H8S */
 #define EM_FRV		0x5441	/* Fujitsu FR-V */
+#define EM_AVR32	0x18ad	/* Atmel AVR32 */
 
 /*
  * This is an interim value that we will use until the committee comes
diff --git a/include/linux/elfnote.h b/include/linux/elfnote.h
new file mode 100644
index 00000000000..67396db141e
--- /dev/null
+++ b/include/linux/elfnote.h
@@ -0,0 +1,90 @@
+#ifndef _LINUX_ELFNOTE_H
+#define _LINUX_ELFNOTE_H
+/*
+ * Helper macros to generate ELF Note structures, which are put into a
+ * PT_NOTE segment of the final vmlinux image.  These are useful for
+ * including name-value pairs of metadata into the kernel binary (or
+ * modules?) for use by external programs.
+ *
+ * Each note has three parts: a name, a type and a desc.  The name is
+ * intended to distinguish the note's originator, so it would be a
+ * company, project, subsystem, etc; it must be in a suitable form for
+ * use in a section name.  The type is an integer which is used to tag
+ * the data, and is considered to be within the "name" namespace (so
+ * "FooCo"'s type 42 is distinct from "BarProj"'s type 42).  The
+ * "desc" field is the actual data.  There are no constraints on the
+ * desc field's contents, though typically they're fairly small.
+ *
+ * All notes from a given NAME are put into a section named
+ * .note.NAME.  When the kernel image is finally linked, all the notes
+ * are packed into a single .notes section, which is mapped into the
+ * PT_NOTE segment.  Because notes for a given name are grouped into
+ * the same section, they'll all be adjacent the output file.
+ *
+ * This file defines macros for both C and assembler use.  Their
+ * syntax is slightly different, but they're semantically similar.
+ *
+ * See the ELF specification for more detail about ELF notes.
+ */
+
+#ifdef __ASSEMBLER__
+/*
+ * Generate a structure with the same shape as Elf{32,64}_Nhdr (which
+ * turn out to be the same size and shape), followed by the name and
+ * desc data with appropriate padding.  The 'desctype' argument is the
+ * assembler pseudo op defining the type of the data e.g. .asciz while
+ * 'descdata' is the data itself e.g.  "hello, world".
+ *
+ * e.g. ELFNOTE(XYZCo, 42, .asciz, "forty-two")
+ *      ELFNOTE(XYZCo, 12, .long, 0xdeadbeef)
+ */
+#define ELFNOTE(name, type, desctype, descdata)	\
+.pushsection .note.name			;	\
+  .align 4				;	\
+  .long 2f - 1f		/* namesz */	;	\
+  .long 4f - 3f		/* descsz */	;	\
+  .long type				;	\
+1:.asciz "name"				;	\
+2:.align 4				;	\
+3:desctype descdata			;	\
+4:.align 4				;	\
+.popsection				;
+#else	/* !__ASSEMBLER__ */
+#include <linux/elf.h>
+/*
+ * Use an anonymous structure which matches the shape of
+ * Elf{32,64}_Nhdr, but includes the name and desc data.  The size and
+ * type of name and desc depend on the macro arguments.  "name" must
+ * be a literal string, and "desc" must be passed by value.  You may
+ * only define one note per line, since __LINE__ is used to generate
+ * unique symbols.
+ */
+#define _ELFNOTE_PASTE(a,b)	a##b
+#define _ELFNOTE(size, name, unique, type, desc)			\
+	static const struct {						\
+		struct elf##size##_note _nhdr;				\
+		unsigned char _name[sizeof(name)]			\
+		__attribute__((aligned(sizeof(Elf##size##_Word))));	\
+		typeof(desc) _desc					\
+			     __attribute__((aligned(sizeof(Elf##size##_Word)))); \
+	} _ELFNOTE_PASTE(_note_, unique)				\
+		__attribute_used__					\
+		__attribute__((section(".note." name),			\
+			       aligned(sizeof(Elf##size##_Word)),	\
+			       unused)) = {				\
+		{							\
+			sizeof(name),					\
+			sizeof(desc),					\
+			type,						\
+		},							\
+		name,							\
+		desc							\
+	}
+#define ELFNOTE(size, name, type, desc)		\
+	_ELFNOTE(size, name, __LINE__, type, desc)
+
+#define ELFNOTE32(name, type, desc) ELFNOTE(32, name, type, desc)
+#define ELFNOTE64(name, type, desc) ELFNOTE(64, name, type, desc)
+#endif	/* __ASSEMBLER__ */
+
+#endif /* _LINUX_ELFNOTE_H */
diff --git a/include/linux/gfp.h b/include/linux/gfp.h
index cc9e6084448..8b34aabfe4c 100644
--- a/include/linux/gfp.h
+++ b/include/linux/gfp.h
@@ -9,17 +9,16 @@ struct vm_area_struct;
 
 /*
  * GFP bitmasks..
+ *
+ * Zone modifiers (see linux/mmzone.h - low three bits)
+ *
+ * Do not put any conditional on these. If necessary modify the definitions
+ * without the underscores and use the consistently. The definitions here may
+ * be used in bit comparisons.
  */
-/* Zone modifiers in GFP_ZONEMASK (see linux/mmzone.h - low three bits) */
 #define __GFP_DMA	((__force gfp_t)0x01u)
 #define __GFP_HIGHMEM	((__force gfp_t)0x02u)
-#ifdef CONFIG_DMA_IS_DMA32
-#define __GFP_DMA32	((__force gfp_t)0x01)	/* ZONE_DMA is ZONE_DMA32 */
-#elif BITS_PER_LONG < 64
-#define __GFP_DMA32	((__force gfp_t)0x00)	/* ZONE_NORMAL is ZONE_DMA32 */
-#else
-#define __GFP_DMA32	((__force gfp_t)0x04)	/* Has own ZONE_DMA32 */
-#endif
+#define __GFP_DMA32	((__force gfp_t)0x04u)
 
 /*
  * Action modifiers - doesn't change the zoning
@@ -46,6 +45,7 @@ struct vm_area_struct;
 #define __GFP_ZERO	((__force gfp_t)0x8000u)/* Return zeroed page on success */
 #define __GFP_NOMEMALLOC ((__force gfp_t)0x10000u) /* Don't use emergency reserves */
 #define __GFP_HARDWALL   ((__force gfp_t)0x20000u) /* Enforce hardwall cpuset memory allocs */
+#define __GFP_THISNODE	((__force gfp_t)0x40000u)/* No fallback, no policies */
 
 #define __GFP_BITS_SHIFT 20	/* Room for 20 __GFP_FOO bits */
 #define __GFP_BITS_MASK ((__force gfp_t)((1 << __GFP_BITS_SHIFT) - 1))
@@ -54,7 +54,7 @@ struct vm_area_struct;
 #define GFP_LEVEL_MASK (__GFP_WAIT|__GFP_HIGH|__GFP_IO|__GFP_FS| \
 			__GFP_COLD|__GFP_NOWARN|__GFP_REPEAT| \
 			__GFP_NOFAIL|__GFP_NORETRY|__GFP_NO_GROW|__GFP_COMP| \
-			__GFP_NOMEMALLOC|__GFP_HARDWALL)
+			__GFP_NOMEMALLOC|__GFP_HARDWALL|__GFP_THISNODE)
 
 /* This equals 0, but use constants in case they ever change */
 #define GFP_NOWAIT	(GFP_ATOMIC & ~__GFP_HIGH)
@@ -67,6 +67,8 @@ struct vm_area_struct;
 #define GFP_HIGHUSER	(__GFP_WAIT | __GFP_IO | __GFP_FS | __GFP_HARDWALL | \
 			 __GFP_HIGHMEM)
 
+#define GFP_THISNODE	(__GFP_THISNODE | __GFP_NOWARN | __GFP_NORETRY)
+
 /* Flag - indicates that the buffer will be suitable for DMA.  Ignored on some
    platforms, used as appropriate on others */
 
@@ -76,11 +78,19 @@ struct vm_area_struct;
 #define GFP_DMA32	__GFP_DMA32
 
 
-static inline int gfp_zone(gfp_t gfp)
+static inline enum zone_type gfp_zone(gfp_t flags)
 {
-	int zone = GFP_ZONEMASK & (__force int) gfp;
-	BUG_ON(zone >= GFP_ZONETYPES);
-	return zone;
+	if (flags & __GFP_DMA)
+		return ZONE_DMA;
+#ifdef CONFIG_ZONE_DMA32
+	if (flags & __GFP_DMA32)
+		return ZONE_DMA32;
+#endif
+#ifdef CONFIG_HIGHMEM
+	if (flags & __GFP_HIGHMEM)
+		return ZONE_HIGHMEM;
+#endif
+	return ZONE_NORMAL;
 }
 
 /*
diff --git a/include/linux/highmem.h b/include/linux/highmem.h
index 85ce7ef9a51..fd7d12daa94 100644
--- a/include/linux/highmem.h
+++ b/include/linux/highmem.h
@@ -24,11 +24,15 @@ static inline void flush_kernel_dcache_page(struct page *page)
 
 /* declarations for linux/mm/highmem.c */
 unsigned int nr_free_highpages(void);
+extern unsigned long totalhigh_pages;
 
 #else /* CONFIG_HIGHMEM */
 
 static inline unsigned int nr_free_highpages(void) { return 0; }
 
+#define totalhigh_pages 0
+
+#ifndef ARCH_HAS_KMAP
 static inline void *kmap(struct page *page)
 {
 	might_sleep();
@@ -41,6 +45,7 @@ static inline void *kmap(struct page *page)
 #define kunmap_atomic(addr, idx)	do { } while (0)
 #define kmap_atomic_pfn(pfn, idx)	page_address(pfn_to_page(pfn))
 #define kmap_atomic_to_page(ptr)	virt_to_page(ptr)
+#endif
 
 #endif /* CONFIG_HIGHMEM */
 
diff --git a/include/linux/irq.h b/include/linux/irq.h
index fbf6d901e9c..48d3cb3b6a4 100644
--- a/include/linux/irq.h
+++ b/include/linux/irq.h
@@ -320,7 +320,9 @@ handle_irq_name(void fastcall (*handle)(unsigned int, struct irq_desc *,
  * Monolithic do_IRQ implementation.
  * (is an explicit fastcall, because i386 4KSTACKS calls it from assembly)
  */
+#ifndef CONFIG_GENERIC_HARDIRQS_NO__DO_IRQ
 extern fastcall unsigned int __do_IRQ(unsigned int irq, struct pt_regs *regs);
+#endif
 
 /*
  * Architectures call this to let the generic IRQ layer
@@ -332,10 +334,14 @@ static inline void generic_handle_irq(unsigned int irq, struct pt_regs *regs)
 {
 	struct irq_desc *desc = irq_desc + irq;
 
+#ifdef CONFIG_GENERIC_HARDIRQS_NO__DO_IRQ
+	desc->handle_irq(irq, desc, regs);
+#else
 	if (likely(desc->handle_irq))
 		desc->handle_irq(irq, desc, regs);
 	else
 		__do_IRQ(irq, regs);
+#endif
 }
 
 /* Handling of unhandled and spurious interrupts: */
diff --git a/include/linux/kernel.h b/include/linux/kernel.h
index 2b2ae4fdce8..e44a37e2c71 100644
--- a/include/linux/kernel.h
+++ b/include/linux/kernel.h
@@ -33,6 +33,7 @@ extern const char linux_banner[];
 #define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0]))
 #define ALIGN(x,a) (((x)+(a)-1UL)&~((a)-1UL))
 #define FIELD_SIZEOF(t, f) (sizeof(((t*)0)->f))
+#define DIV_ROUND_UP(n,d) (((n) + (d) - 1) / (d))
 #define roundup(x, y) ((((x) + ((y) - 1)) / (y)) * (y))
 
 #define	KERN_EMERG	"<0>"	/* system is unusable			*/
diff --git a/include/linux/mempolicy.h b/include/linux/mempolicy.h
index 72440f0a443..09f0f575ddf 100644
--- a/include/linux/mempolicy.h
+++ b/include/linux/mempolicy.h
@@ -162,9 +162,9 @@ extern struct zonelist *huge_zonelist(struct vm_area_struct *vma,
 		unsigned long addr);
 extern unsigned slab_node(struct mempolicy *policy);
 
-extern int policy_zone;
+extern enum zone_type policy_zone;
 
-static inline void check_highest_zone(int k)
+static inline void check_highest_zone(enum zone_type k)
 {
 	if (k > policy_zone)
 		policy_zone = k;
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 224178a000d..856f0ee7e84 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -15,6 +15,7 @@
 #include <linux/fs.h>
 #include <linux/mutex.h>
 #include <linux/debug_locks.h>
+#include <linux/backing-dev.h>
 
 struct mempolicy;
 struct anon_vma;
@@ -218,7 +219,8 @@ struct inode;
  * Each physical page in the system has a struct page associated with
  * it to keep track of whatever it is we are using the page for at the
  * moment. Note that we have no way to track which tasks are using
- * a page.
+ * a page, though if it is a pagecache page, rmap structures can tell us
+ * who is mapping it.
  */
 struct page {
 	unsigned long flags;		/* Atomic flags, some possibly
@@ -278,6 +280,12 @@ struct page {
  */
 #include <linux/page-flags.h>
 
+#ifdef CONFIG_DEBUG_VM
+#define VM_BUG_ON(cond) BUG_ON(cond)
+#else
+#define VM_BUG_ON(condition) do { } while(0)
+#endif
+
 /*
  * Methods to modify the page usage count.
  *
@@ -292,12 +300,11 @@ struct page {
  */
 
 /*
- * Drop a ref, return true if the logical refcount fell to zero (the page has
- * no users)
+ * Drop a ref, return true if the refcount fell to zero (the page has no users)
  */
 static inline int put_page_testzero(struct page *page)
 {
-	BUG_ON(atomic_read(&page->_count) == 0);
+	VM_BUG_ON(atomic_read(&page->_count) == 0);
 	return atomic_dec_and_test(&page->_count);
 }
 
@@ -307,11 +314,10 @@ static inline int put_page_testzero(struct page *page)
  */
 static inline int get_page_unless_zero(struct page *page)
 {
+	VM_BUG_ON(PageCompound(page));
 	return atomic_inc_not_zero(&page->_count);
 }
 
-extern void FASTCALL(__page_cache_release(struct page *));
-
 static inline int page_count(struct page *page)
 {
 	if (unlikely(PageCompound(page)))
@@ -323,6 +329,7 @@ static inline void get_page(struct page *page)
 {
 	if (unlikely(PageCompound(page)))
 		page = (struct page *)page_private(page);
+	VM_BUG_ON(atomic_read(&page->_count) == 0);
 	atomic_inc(&page->_count);
 }
 
@@ -349,43 +356,55 @@ void split_page(struct page *page, unsigned int order);
  * For the non-reserved pages, page_count(page) denotes a reference count.
  *   page_count() == 0 means the page is free. page->lru is then used for
  *   freelist management in the buddy allocator.
- *   page_count() == 1 means the page is used for exactly one purpose
- *   (e.g. a private data page of one process).
+ *   page_count() > 0  means the page has been allocated.
+ *
+ * Pages are allocated by the slab allocator in order to provide memory
+ * to kmalloc and kmem_cache_alloc. In this case, the management of the
+ * page, and the fields in 'struct page' are the responsibility of mm/slab.c
+ * unless a particular usage is carefully commented. (the responsibility of
+ * freeing the kmalloc memory is the caller's, of course).
  *
- * A page may be used for kmalloc() or anyone else who does a
- * __get_free_page(). In this case the page_count() is at least 1, and
- * all other fields are unused but should be 0 or NULL. The
- * management of this page is the responsibility of the one who uses
- * it.
+ * A page may be used by anyone else who does a __get_free_page().
+ * In this case, page_count still tracks the references, and should only
+ * be used through the normal accessor functions. The top bits of page->flags
+ * and page->virtual store page management information, but all other fields
+ * are unused and could be used privately, carefully. The management of this
+ * page is the responsibility of the one who allocated it, and those who have
+ * subsequently been given references to it.
  *
- * The other pages (we may call them "process pages") are completely
+ * The other pages (we may call them "pagecache pages") are completely
  * managed by the Linux memory manager: I/O, buffers, swapping etc.
  * The following discussion applies only to them.
  *
- * A page may belong to an inode's memory mapping. In this case,
- * page->mapping is the pointer to the inode, and page->index is the
- * file offset of the page, in units of PAGE_CACHE_SIZE.
+ * A pagecache page contains an opaque `private' member, which belongs to the
+ * page's address_space. Usually, this is the address of a circular list of
+ * the page's disk buffers. PG_private must be set to tell the VM to call
+ * into the filesystem to release these pages.
  *
- * A page contains an opaque `private' member, which belongs to the
- * page's address_space.  Usually, this is the address of a circular
- * list of the page's disk buffers.
+ * A page may belong to an inode's memory mapping. In this case, page->mapping
+ * is the pointer to the inode, and page->index is the file offset of the page,
+ * in units of PAGE_CACHE_SIZE.
  *
- * For pages belonging to inodes, the page_count() is the number of
- * attaches, plus 1 if `private' contains something, plus one for
- * the page cache itself.
+ * If pagecache pages are not associated with an inode, they are said to be
+ * anonymous pages. These may become associated with the swapcache, and in that
+ * case PG_swapcache is set, and page->private is an offset into the swapcache.
  *
- * Instead of keeping dirty/clean pages in per address-space lists, we instead
- * now tag pages as dirty/under writeback in the radix tree.
+ * In either case (swapcache or inode backed), the pagecache itself holds one
+ * reference to the page. Setting PG_private should also increment the
+ * refcount. The each user mapping also has a reference to the page.
  *
- * There is also a per-mapping radix tree mapping index to the page
- * in memory if present. The tree is rooted at mapping->root.  
+ * The pagecache pages are stored in a per-mapping radix tree, which is
+ * rooted at mapping->page_tree, and indexed by offset.
+ * Where 2.4 and early 2.6 kernels kept dirty/clean pages in per-address_space
+ * lists, we instead now tag pages as dirty/writeback in the radix tree.
  *
- * All process pages can do I/O:
+ * All pagecache pages may be subject to I/O:
  * - inode pages may need to be read from disk,
  * - inode pages which have been modified and are MAP_SHARED may need
- *   to be written to disk,
- * - private pages which have been modified may need to be swapped out
- *   to swap space and (later) to be read back into memory.
+ *   to be written back to the inode on disk,
+ * - anonymous pages (including MAP_PRIVATE file mappings) which have been
+ *   modified may need to be swapped out to swap space and (later) to be read
+ *   back into memory.
  */
 
 /*
@@ -463,7 +482,7 @@ void split_page(struct page *page, unsigned int order);
 #define SECTIONS_MASK		((1UL << SECTIONS_WIDTH) - 1)
 #define ZONETABLE_MASK		((1UL << ZONETABLE_SHIFT) - 1)
 
-static inline unsigned long page_zonenum(struct page *page)
+static inline enum zone_type page_zonenum(struct page *page)
 {
 	return (page->flags >> ZONES_PGSHIFT) & ZONES_MASK;
 }
@@ -480,23 +499,29 @@ static inline struct zone *page_zone(struct page *page)
 	return zone_table[page_zone_id(page)];
 }
 
+static inline unsigned long zone_to_nid(struct zone *zone)
+{
+	return zone->zone_pgdat->node_id;
+}
+
 static inline unsigned long page_to_nid(struct page *page)
 {
 	if (FLAGS_HAS_NODE)
 		return (page->flags >> NODES_PGSHIFT) & NODES_MASK;
 	else
-		return page_zone(page)->zone_pgdat->node_id;
+		return zone_to_nid(page_zone(page));
 }
 static inline unsigned long page_to_section(struct page *page)
 {
 	return (page->flags >> SECTIONS_PGSHIFT) & SECTIONS_MASK;
 }
 
-static inline void set_page_zone(struct page *page, unsigned long zone)
+static inline void set_page_zone(struct page *page, enum zone_type zone)
 {
 	page->flags &= ~(ZONES_MASK << ZONES_PGSHIFT);
 	page->flags |= (zone & ZONES_MASK) << ZONES_PGSHIFT;
 }
+
 static inline void set_page_node(struct page *page, unsigned long node)
 {
 	page->flags &= ~(NODES_MASK << NODES_PGSHIFT);
@@ -508,7 +533,7 @@ static inline void set_page_section(struct page *page, unsigned long section)
 	page->flags |= (section & SECTIONS_MASK) << SECTIONS_PGSHIFT;
 }
 
-static inline void set_page_links(struct page *page, unsigned long zone,
+static inline void set_page_links(struct page *page, enum zone_type zone,
 	unsigned long node, unsigned long pfn)
 {
 	set_page_zone(page, zone);
@@ -802,6 +827,39 @@ struct shrinker;
 extern struct shrinker *set_shrinker(int, shrinker_t);
 extern void remove_shrinker(struct shrinker *shrinker);
 
+/*
+ * Some shared mappigns will want the pages marked read-only
+ * to track write events. If so, we'll downgrade vm_page_prot
+ * to the private version (using protection_map[] without the
+ * VM_SHARED bit).
+ */
+static inline int vma_wants_writenotify(struct vm_area_struct *vma)
+{
+	unsigned int vm_flags = vma->vm_flags;
+
+	/* If it was private or non-writable, the write bit is already clear */
+	if ((vm_flags & (VM_WRITE|VM_SHARED)) != ((VM_WRITE|VM_SHARED)))
+		return 0;
+
+	/* The backer wishes to know when pages are first written to? */
+	if (vma->vm_ops && vma->vm_ops->page_mkwrite)
+		return 1;
+
+	/* The open routine did something to the protections already? */
+	if (pgprot_val(vma->vm_page_prot) !=
+	    pgprot_val(protection_map[vm_flags &
+		    (VM_READ|VM_WRITE|VM_EXEC|VM_SHARED)]))
+		return 0;
+
+	/* Specialty mapping? */
+	if (vm_flags & (VM_PFNMAP|VM_INSERTPAGE))
+		return 0;
+
+	/* Can the mapping track the dirty pages? */
+	return vma->vm_file && vma->vm_file->f_mapping &&
+		mapping_cap_account_dirty(vma->vm_file->f_mapping);
+}
+
 extern pte_t *FASTCALL(get_locked_pte(struct mm_struct *mm, unsigned long addr, spinlock_t **ptl));
 
 int __pud_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long address);
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index f45163c528e..3693f1a5278 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -51,7 +51,8 @@ enum zone_stat_item {
 	NR_FILE_MAPPED,	/* pagecache pages mapped into pagetables.
 			   only modified from process context */
 	NR_FILE_PAGES,
-	NR_SLAB,	/* Pages used by slab allocator */
+	NR_SLAB_RECLAIMABLE,
+	NR_SLAB_UNRECLAIMABLE,
 	NR_PAGETABLE,	/* used for pagetables */
 	NR_FILE_DIRTY,
 	NR_WRITEBACK,
@@ -88,53 +89,68 @@ struct per_cpu_pageset {
 #define zone_pcp(__z, __cpu) (&(__z)->pageset[(__cpu)])
 #endif
 
-#define ZONE_DMA		0
-#define ZONE_DMA32		1
-#define ZONE_NORMAL		2
-#define ZONE_HIGHMEM		3
-
-#define MAX_NR_ZONES		4	/* Sync this with ZONES_SHIFT */
-#define ZONES_SHIFT		2	/* ceil(log2(MAX_NR_ZONES)) */
-
+enum zone_type {
+	/*
+	 * ZONE_DMA is used when there are devices that are not able
+	 * to do DMA to all of addressable memory (ZONE_NORMAL). Then we
+	 * carve out the portion of memory that is needed for these devices.
+	 * The range is arch specific.
+	 *
+	 * Some examples
+	 *
+	 * Architecture		Limit
+	 * ---------------------------
+	 * parisc, ia64, sparc	<4G
+	 * s390			<2G
+	 * arm26		<48M
+	 * arm			Various
+	 * alpha		Unlimited or 0-16MB.
+	 *
+	 * i386, x86_64 and multiple other arches
+	 * 			<16M.
+	 */
+	ZONE_DMA,
+#ifdef CONFIG_ZONE_DMA32
+	/*
+	 * x86_64 needs two ZONE_DMAs because it supports devices that are
+	 * only able to do DMA to the lower 16M but also 32 bit devices that
+	 * can only do DMA areas below 4G.
+	 */
+	ZONE_DMA32,
+#endif
+	/*
+	 * Normal addressable memory is in ZONE_NORMAL. DMA operations can be
+	 * performed on pages in ZONE_NORMAL if the DMA devices support
+	 * transfers to all addressable memory.
+	 */
+	ZONE_NORMAL,
+#ifdef CONFIG_HIGHMEM
+	/*
+	 * A memory area that is only addressable by the kernel through
+	 * mapping portions into its own address space. This is for example
+	 * used by i386 to allow the kernel to address the memory beyond
+	 * 900MB. The kernel will set up special mappings (page
+	 * table entries on i386) for each page that the kernel needs to
+	 * access.
+	 */
+	ZONE_HIGHMEM,
+#endif
+	MAX_NR_ZONES
+};
 
 /*
  * When a memory allocation must conform to specific limitations (such
  * as being suitable for DMA) the caller will pass in hints to the
  * allocator in the gfp_mask, in the zone modifier bits.  These bits
  * are used to select a priority ordered list of memory zones which
- * match the requested limits.  GFP_ZONEMASK defines which bits within
- * the gfp_mask should be considered as zone modifiers.  Each valid
- * combination of the zone modifier bits has a corresponding list
- * of zones (in node_zonelists).  Thus for two zone modifiers there
- * will be a maximum of 4 (2 ** 2) zonelists, for 3 modifiers there will
- * be 8 (2 ** 3) zonelists.  GFP_ZONETYPES defines the number of possible
- * combinations of zone modifiers in "zone modifier space".
- *
- * As an optimisation any zone modifier bits which are only valid when
- * no other zone modifier bits are set (loners) should be placed in
- * the highest order bits of this field.  This allows us to reduce the
- * extent of the zonelists thus saving space.  For example in the case
- * of three zone modifier bits, we could require up to eight zonelists.
- * If the left most zone modifier is a "loner" then the highest valid
- * zonelist would be four allowing us to allocate only five zonelists.
- * Use the first form for GFP_ZONETYPES when the left most bit is not
- * a "loner", otherwise use the second.
- *
- * NOTE! Make sure this matches the zones in <linux/gfp.h>
+ * match the requested limits. See gfp_zone() in include/linux/gfp.h
  */
-#define GFP_ZONEMASK	0x07
-/* #define GFP_ZONETYPES       (GFP_ZONEMASK + 1) */           /* Non-loner */
-#define GFP_ZONETYPES  ((GFP_ZONEMASK + 1) / 2 + 1)            /* Loner */
 
-/*
- * On machines where it is needed (eg PCs) we divide physical memory
- * into multiple physical zones. On a 32bit PC we have 4 zones:
- *
- * ZONE_DMA	  < 16 MB	ISA DMA capable memory
- * ZONE_DMA32	     0 MB 	Empty
- * ZONE_NORMAL	16-896 MB	direct mapped by the kernel
- * ZONE_HIGHMEM	 > 896 MB	only page cache and user processes
- */
+#if !defined(CONFIG_ZONE_DMA32) && !defined(CONFIG_HIGHMEM)
+#define ZONES_SHIFT 1
+#else
+#define ZONES_SHIFT 2
+#endif
 
 struct zone {
 	/* Fields commonly accessed by the page allocator */
@@ -154,7 +170,8 @@ struct zone {
 	/*
 	 * zone reclaim becomes active if more unmapped pages exist.
 	 */
-	unsigned long		min_unmapped_ratio;
+	unsigned long		min_unmapped_pages;
+	unsigned long		min_slab_pages;
 	struct per_cpu_pageset	*pageset[NR_CPUS];
 #else
 	struct per_cpu_pageset	pageset[NR_CPUS];
@@ -266,7 +283,6 @@ struct zone {
 	char			*name;
 } ____cacheline_internodealigned_in_smp;
 
-
 /*
  * The "priority" of VM scanning is how much of the queues we will scan in one
  * go. A value of 12 for DEF_PRIORITY implies that we will scan 1/4096th of the
@@ -304,7 +320,7 @@ struct zonelist {
 struct bootmem_data;
 typedef struct pglist_data {
 	struct zone node_zones[MAX_NR_ZONES];
-	struct zonelist node_zonelists[GFP_ZONETYPES];
+	struct zonelist node_zonelists[MAX_NR_ZONES];
 	int nr_zones;
 #ifdef CONFIG_FLAT_NODE_MEM_MAP
 	struct page *node_mem_map;
@@ -373,12 +389,16 @@ static inline int populated_zone(struct zone *zone)
 	return (!!zone->present_pages);
 }
 
-static inline int is_highmem_idx(int idx)
+static inline int is_highmem_idx(enum zone_type idx)
 {
+#ifdef CONFIG_HIGHMEM
 	return (idx == ZONE_HIGHMEM);
+#else
+	return 0;
+#endif
 }
 
-static inline int is_normal_idx(int idx)
+static inline int is_normal_idx(enum zone_type idx)
 {
 	return (idx == ZONE_NORMAL);
 }
@@ -391,7 +411,11 @@ static inline int is_normal_idx(int idx)
  */
 static inline int is_highmem(struct zone *zone)
 {
+#ifdef CONFIG_HIGHMEM
 	return zone == zone->zone_pgdat->node_zones + ZONE_HIGHMEM;
+#else
+	return 0;
+#endif
 }
 
 static inline int is_normal(struct zone *zone)
@@ -401,7 +425,11 @@ static inline int is_normal(struct zone *zone)
 
 static inline int is_dma32(struct zone *zone)
 {
+#ifdef CONFIG_ZONE_DMA32
 	return zone == zone->zone_pgdat->node_zones + ZONE_DMA32;
+#else
+	return 0;
+#endif
 }
 
 static inline int is_dma(struct zone *zone)
@@ -421,6 +449,8 @@ int percpu_pagelist_fraction_sysctl_handler(struct ctl_table *, int, struct file
 					void __user *, size_t *, loff_t *);
 int sysctl_min_unmapped_ratio_sysctl_handler(struct ctl_table *, int,
 			struct file *, void __user *, size_t *, loff_t *);
+int sysctl_min_slab_ratio_sysctl_handler(struct ctl_table *, int,
+			struct file *, void __user *, size_t *, loff_t *);
 
 #include <linux/topology.h>
 /* Returns the number of the current Node. */
diff --git a/include/linux/netfilter/Kbuild b/include/linux/netfilter/Kbuild
index 9a285cecf24..312bd2ffee3 100644
--- a/include/linux/netfilter/Kbuild
+++ b/include/linux/netfilter/Kbuild
@@ -10,6 +10,8 @@ header-y += xt_connmark.h
 header-y += xt_CONNMARK.h
 header-y += xt_conntrack.h
 header-y += xt_dccp.h
+header-y += xt_dscp.h
+header-y += xt_DSCP.h
 header-y += xt_esp.h
 header-y += xt_helper.h
 header-y += xt_length.h
diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
index 5748642e9f3..9d7921dd50f 100644
--- a/include/linux/page-flags.h
+++ b/include/linux/page-flags.h
@@ -13,24 +13,25 @@
  * PG_reserved is set for special pages, which can never be swapped out. Some
  * of them might not even exist (eg empty_bad_page)...
  *
- * The PG_private bitflag is set if page->private contains a valid value.
+ * The PG_private bitflag is set on pagecache pages if they contain filesystem
+ * specific data (which is normally at page->private). It can be used by
+ * private allocations for its own usage.
  *
- * During disk I/O, PG_locked is used. This bit is set before I/O and
- * reset when I/O completes. page_waitqueue(page) is a wait queue of all tasks
- * waiting for the I/O on this page to complete.
+ * During initiation of disk I/O, PG_locked is set. This bit is set before I/O
+ * and cleared when writeback _starts_ or when read _completes_. PG_writeback
+ * is set before writeback starts and cleared when it finishes.
+ *
+ * PG_locked also pins a page in pagecache, and blocks truncation of the file
+ * while it is held.
+ *
+ * page_waitqueue(page) is a wait queue of all tasks waiting for the page
+ * to become unlocked.
  *
  * PG_uptodate tells whether the page's contents is valid.  When a read
  * completes, the page becomes uptodate, unless a disk I/O error happened.
  *
- * For choosing which pages to swap out, inode pages carry a PG_referenced bit,
- * which is set any time the system accesses that page through the (mapping,
- * index) hash table.  This referenced bit, together with the referenced bit
- * in the page tables, is used to manipulate page->age and move the page across
- * the active, inactive_dirty and inactive_clean lists.
- *
- * Note that the referenced bit, the page->lru list_head and the active,
- * inactive_dirty and inactive_clean lists are protected by the
- * zone->lru_lock, and *NOT* by the usual PG_locked bit!
+ * PG_referenced, PG_reclaim are used for page reclaim for anonymous and
+ * file-backed pagecache (see mm/vmscan.c).
  *
  * PG_error is set to indicate that an I/O error occurred on this page.
  *
@@ -42,6 +43,10 @@
  * space, they need to be kmapped separately for doing IO on the pages.  The
  * struct page (these bits with information) are always mapped into kernel
  * address space...
+ *
+ * PG_buddy is set to indicate that the page is free and in the buddy system
+ * (see mm/page_alloc.c).
+ *
  */
 
 /*
@@ -74,7 +79,7 @@
 #define PG_checked		 8	/* kill me in 2.5.<early>. */
 #define PG_arch_1		 9
 #define PG_reserved		10
-#define PG_private		11	/* Has something at ->private */
+#define PG_private		11	/* If pagecache, has fs-private data */
 
 #define PG_writeback		12	/* Page is under writeback */
 #define PG_nosave		13	/* Used for system suspend/resume */
@@ -83,7 +88,7 @@
 
 #define PG_mappedtodisk		16	/* Has blocks allocated on-disk */
 #define PG_reclaim		17	/* To be reclaimed asap */
-#define PG_nosave_free		18	/* Free, should not be written */
+#define PG_nosave_free		18	/* Used for system suspend/resume */
 #define PG_buddy		19	/* Page is free, on buddy lists */
 
 
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index 0a2f5d27f60..64f95092515 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -130,14 +130,29 @@ static inline pgoff_t linear_page_index(struct vm_area_struct *vma,
 }
 
 extern void FASTCALL(__lock_page(struct page *page));
+extern void FASTCALL(__lock_page_nosync(struct page *page));
 extern void FASTCALL(unlock_page(struct page *page));
 
+/*
+ * lock_page may only be called if we have the page's inode pinned.
+ */
 static inline void lock_page(struct page *page)
 {
 	might_sleep();
 	if (TestSetPageLocked(page))
 		__lock_page(page);
 }
+
+/*
+ * lock_page_nosync should only be used if we can't pin the page's inode.
+ * Doesn't play quite so well with block device plugging.
+ */
+static inline void lock_page_nosync(struct page *page)
+{
+	might_sleep();
+	if (TestSetPageLocked(page))
+		__lock_page_nosync(page);
+}
 	
 /*
  * This is exported only for wait_on_page_locked/wait_on_page_writeback.
diff --git a/include/linux/percpu.h b/include/linux/percpu.h
index cb9039a21f2..3835a9642f1 100644
--- a/include/linux/percpu.h
+++ b/include/linux/percpu.h
@@ -1,9 +1,12 @@
 #ifndef __LINUX_PERCPU_H
 #define __LINUX_PERCPU_H
+
 #include <linux/spinlock.h> /* For preempt_disable() */
 #include <linux/slab.h> /* For kmalloc() */
 #include <linux/smp.h>
 #include <linux/string.h> /* For memset() */
+#include <linux/cpumask.h>
+
 #include <asm/percpu.h>
 
 /* Enough to cover all DEFINE_PER_CPUs in kernel, including modules. */
@@ -11,8 +14,14 @@
 #define PERCPU_ENOUGH_ROOM 32768
 #endif
 
-/* Must be an lvalue. */
-#define get_cpu_var(var) (*({ preempt_disable(); &__get_cpu_var(var); }))
+/*
+ * Must be an lvalue. Since @var must be a simple identifier,
+ * we force a syntax error here if it isn't.
+ */
+#define get_cpu_var(var) (*({				\
+	extern int simple_indentifier_##var(void);	\
+	preempt_disable();				\
+	&__get_cpu_var(var); }))
 #define put_cpu_var(var) preempt_enable()
 
 #ifdef CONFIG_SMP
@@ -21,39 +30,77 @@ struct percpu_data {
 	void *ptrs[NR_CPUS];
 };
 
+#define __percpu_disguise(pdata) (struct percpu_data *)~(unsigned long)(pdata)
 /* 
- * Use this to get to a cpu's version of the per-cpu object allocated using
- * alloc_percpu.  Non-atomic access to the current CPU's version should
+ * Use this to get to a cpu's version of the per-cpu object dynamically
+ * allocated. Non-atomic access to the current CPU's version should
  * probably be combined with get_cpu()/put_cpu().
  */ 
-#define per_cpu_ptr(ptr, cpu)                   \
-({                                              \
-        struct percpu_data *__p = (struct percpu_data *)~(unsigned long)(ptr); \
-        (__typeof__(ptr))__p->ptrs[(cpu)];	\
+#define percpu_ptr(ptr, cpu)                              \
+({                                                        \
+        struct percpu_data *__p = __percpu_disguise(ptr); \
+        (__typeof__(ptr))__p->ptrs[(cpu)];	          \
 })
 
-extern void *__alloc_percpu(size_t size);
-extern void free_percpu(const void *);
+extern void *percpu_populate(void *__pdata, size_t size, gfp_t gfp, int cpu);
+extern void percpu_depopulate(void *__pdata, int cpu);
+extern int __percpu_populate_mask(void *__pdata, size_t size, gfp_t gfp,
+				  cpumask_t *mask);
+extern void __percpu_depopulate_mask(void *__pdata, cpumask_t *mask);
+extern void *__percpu_alloc_mask(size_t size, gfp_t gfp, cpumask_t *mask);
+extern void percpu_free(void *__pdata);
 
 #else /* CONFIG_SMP */
 
-#define per_cpu_ptr(ptr, cpu) ({ (void)(cpu); (ptr); })
+#define percpu_ptr(ptr, cpu) ({ (void)(cpu); (ptr); })
+
+static inline void percpu_depopulate(void *__pdata, int cpu)
+{
+}
+
+static inline void __percpu_depopulate_mask(void *__pdata, cpumask_t *mask)
+{
+}
 
-static inline void *__alloc_percpu(size_t size)
+static inline void *percpu_populate(void *__pdata, size_t size, gfp_t gfp,
+				    int cpu)
 {
-	void *ret = kmalloc(size, GFP_KERNEL);
-	if (ret)
-		memset(ret, 0, size);
-	return ret;
+	return percpu_ptr(__pdata, cpu);
 }
-static inline void free_percpu(const void *ptr)
-{	
-	kfree(ptr);
+
+static inline int __percpu_populate_mask(void *__pdata, size_t size, gfp_t gfp,
+					 cpumask_t *mask)
+{
+	return 0;
+}
+
+static inline void *__percpu_alloc_mask(size_t size, gfp_t gfp, cpumask_t *mask)
+{
+	return kzalloc(size, gfp);
+}
+
+static inline void percpu_free(void *__pdata)
+{
+	kfree(__pdata);
 }
 
 #endif /* CONFIG_SMP */
 
-/* Simple wrapper for the common case: zeros memory. */
-#define alloc_percpu(type)	((type *)(__alloc_percpu(sizeof(type))))
+#define percpu_populate_mask(__pdata, size, gfp, mask) \
+	__percpu_populate_mask((__pdata), (size), (gfp), &(mask))
+#define percpu_depopulate_mask(__pdata, mask) \
+	__percpu_depopulate_mask((__pdata), &(mask))
+#define percpu_alloc_mask(size, gfp, mask) \
+	__percpu_alloc_mask((size), (gfp), &(mask))
+
+#define percpu_alloc(size, gfp) percpu_alloc_mask((size), (gfp), cpu_online_map)
+
+/* (legacy) interface for use without CPU hotplug handling */
+
+#define __alloc_percpu(size)	percpu_alloc_mask((size), GFP_KERNEL, \
+						  cpu_possible_map)
+#define alloc_percpu(type)	(type *)__alloc_percpu(sizeof(type))
+#define free_percpu(ptr)	percpu_free((ptr))
+#define per_cpu_ptr(ptr, cpu)	percpu_ptr((ptr), (cpu))
 
 #endif /* __LINUX_PERCPU_H */
diff --git a/include/linux/resume-trace.h b/include/linux/resume-trace.h
index a376bd4ade3..81e9299ca14 100644
--- a/include/linux/resume-trace.h
+++ b/include/linux/resume-trace.h
@@ -3,21 +3,25 @@
 
 #ifdef CONFIG_PM_TRACE
 
+extern int pm_trace_enabled;
+
 struct device;
 extern void set_trace_device(struct device *);
 extern void generate_resume_trace(void *tracedata, unsigned int user);
 
 #define TRACE_DEVICE(dev) set_trace_device(dev)
-#define TRACE_RESUME(user) do {				\
-	void *tracedata;				\
-	asm volatile("movl $1f,%0\n"			\
-		".section .tracedata,\"a\"\n"		\
-		"1:\t.word %c1\n"			\
-		"\t.long %c2\n"				\
-		".previous"				\
-		:"=r" (tracedata)			\
-		: "i" (__LINE__), "i" (__FILE__));	\
-	generate_resume_trace(tracedata, user);		\
+#define TRACE_RESUME(user) do {					\
+	if (pm_trace_enabled) {					\
+		void *tracedata;				\
+		asm volatile("movl $1f,%0\n"			\
+			".section .tracedata,\"a\"\n"		\
+			"1:\t.word %c1\n"			\
+			"\t.long %c2\n"				\
+			".previous"				\
+			:"=r" (tracedata)			\
+			: "i" (__LINE__), "i" (__FILE__));	\
+		generate_resume_trace(tracedata, user);		\
+	}							\
 } while (0)
 
 #else
diff --git a/include/linux/rmap.h b/include/linux/rmap.h
index bf97b090001..db2c1df4fef 100644
--- a/include/linux/rmap.h
+++ b/include/linux/rmap.h
@@ -103,6 +103,14 @@ pte_t *page_check_address(struct page *, struct mm_struct *,
  */
 unsigned long page_address_in_vma(struct page *, struct vm_area_struct *);
 
+/*
+ * Cleans the PTEs of shared mappings.
+ * (and since clean PTEs should also be readonly, write protects them too)
+ *
+ * returns the number of cleaned PTEs.
+ */
+int page_mkclean(struct page *);
+
 #else	/* !CONFIG_MMU */
 
 #define anon_vma_init()		do {} while (0)
@@ -112,6 +120,12 @@ unsigned long page_address_in_vma(struct page *, struct vm_area_struct *);
 #define page_referenced(page,l) TestClearPageReferenced(page)
 #define try_to_unmap(page, refs) SWAP_FAIL
 
+static inline int page_mkclean(struct page *page)
+{
+	return 0;
+}
+
+
 #endif	/* CONFIG_MMU */
 
 /*
diff --git a/include/linux/selinux.h b/include/linux/selinux.h
index aad4e390d6a..d1b7ca6c1c5 100644
--- a/include/linux/selinux.h
+++ b/include/linux/selinux.h
@@ -46,7 +46,7 @@ void selinux_audit_rule_free(struct selinux_audit_rule *rule);
 
 /**
  *	selinux_audit_rule_match - determine if a context ID matches a rule.
- *	@ctxid: the context ID to check
+ *	@sid: the context ID to check
  *	@field: the field this rule refers to
  *	@op: the operater the rule uses
  *	@rule: pointer to the audit rule to check against
@@ -55,7 +55,7 @@ void selinux_audit_rule_free(struct selinux_audit_rule *rule);
  *	Returns 1 if the context id matches the rule, 0 if it does not, and
  *	-errno on failure.
  */
-int selinux_audit_rule_match(u32 ctxid, u32 field, u32 op,
+int selinux_audit_rule_match(u32 sid, u32 field, u32 op,
                              struct selinux_audit_rule *rule,
                              struct audit_context *actx);
 
@@ -70,18 +70,8 @@ int selinux_audit_rule_match(u32 ctxid, u32 field, u32 op,
 void selinux_audit_set_callback(int (*callback)(void));
 
 /**
- *	selinux_task_ctxid - determine a context ID for a process.
- *	@tsk: the task object
- *	@ctxid: ID value returned via this
- *
- *	On return, ctxid will contain an ID for the context.  This value
- *	should only be used opaquely.
- */
-void selinux_task_ctxid(struct task_struct *tsk, u32 *ctxid);
-
-/**
- *     selinux_ctxid_to_string - map a security context ID to a string
- *     @ctxid: security context ID to be converted.
+ *     selinux_sid_to_string - map a security context ID to a string
+ *     @sid: security context ID to be converted.
  *     @ctx: address of context string to be returned
  *     @ctxlen: length of returned context string.
  *
@@ -89,7 +79,7 @@ void selinux_task_ctxid(struct task_struct *tsk, u32 *ctxid);
  *     string will be allocated internally, and the caller must call
  *     kfree() on it after use.
  */
-int selinux_ctxid_to_string(u32 ctxid, char **ctx, u32 *ctxlen);
+int selinux_sid_to_string(u32 sid, char **ctx, u32 *ctxlen);
 
 /**
  *     selinux_get_inode_sid - get the inode's security context ID
@@ -154,7 +144,7 @@ static inline void selinux_audit_rule_free(struct selinux_audit_rule *rule)
 	return;
 }
 
-static inline int selinux_audit_rule_match(u32 ctxid, u32 field, u32 op,
+static inline int selinux_audit_rule_match(u32 sid, u32 field, u32 op,
                                            struct selinux_audit_rule *rule,
                                            struct audit_context *actx)
 {
@@ -166,12 +156,7 @@ static inline void selinux_audit_set_callback(int (*callback)(void))
 	return;
 }
 
-static inline void selinux_task_ctxid(struct task_struct *tsk, u32 *ctxid)
-{
-	*ctxid = 0;
-}
-
-static inline int selinux_ctxid_to_string(u32 ctxid, char **ctx, u32 *ctxlen)
+static inline int selinux_sid_to_string(u32 sid, char **ctx, u32 *ctxlen)
 {
        *ctx = NULL;
        *ctxlen = 0;
diff --git a/include/linux/slab.h b/include/linux/slab.h
index 45ad55b70d1..66d6eb78d1c 100644
--- a/include/linux/slab.h
+++ b/include/linux/slab.h
@@ -67,7 +67,6 @@ extern void *kmem_cache_zalloc(struct kmem_cache *, gfp_t);
 extern void kmem_cache_free(kmem_cache_t *, void *);
 extern unsigned int kmem_cache_size(kmem_cache_t *);
 extern const char *kmem_cache_name(kmem_cache_t *);
-extern kmem_cache_t *kmem_find_general_cachep(size_t size, gfp_t gfpflags);
 
 /* Size description struct for general caches. */
 struct cache_sizes {
@@ -203,7 +202,30 @@ extern int slab_is_available(void);
 
 #ifdef CONFIG_NUMA
 extern void *kmem_cache_alloc_node(kmem_cache_t *, gfp_t flags, int node);
-extern void *kmalloc_node(size_t size, gfp_t flags, int node);
+extern void *__kmalloc_node(size_t size, gfp_t flags, int node);
+
+static inline void *kmalloc_node(size_t size, gfp_t flags, int node)
+{
+	if (__builtin_constant_p(size)) {
+		int i = 0;
+#define CACHE(x) \
+		if (size <= x) \
+			goto found; \
+		else \
+			i++;
+#include "kmalloc_sizes.h"
+#undef CACHE
+		{
+			extern void __you_cannot_kmalloc_that_much(void);
+			__you_cannot_kmalloc_that_much();
+		}
+found:
+		return kmem_cache_alloc_node((flags & GFP_DMA) ?
+			malloc_sizes[i].cs_dmacachep :
+			malloc_sizes[i].cs_cachep, flags, node);
+	}
+	return __kmalloc_node(size, flags, node);
+}
 #else
 static inline void *kmem_cache_alloc_node(kmem_cache_t *cachep, gfp_t flags, int node)
 {
@@ -223,7 +245,6 @@ extern int FASTCALL(kmem_ptr_validate(kmem_cache_t *cachep, void *ptr));
 /* SLOB allocator routines */
 
 void kmem_cache_init(void);
-struct kmem_cache *kmem_find_general_cachep(size_t, gfp_t gfpflags);
 struct kmem_cache *kmem_cache_create(const char *c, size_t, size_t,
 	unsigned long,
 	void (*)(void *, struct kmem_cache *, unsigned long),
@@ -263,8 +284,6 @@ extern kmem_cache_t	*fs_cachep;
 extern kmem_cache_t	*sighand_cachep;
 extern kmem_cache_t	*bio_cachep;
 
-extern atomic_t slab_reclaim_pages;
-
 #endif	/* __KERNEL__ */
 
 #endif	/* _LINUX_SLAB_H */
diff --git a/include/linux/smp.h b/include/linux/smp.h
index 837e8bce134..51649987f69 100644
--- a/include/linux/smp.h
+++ b/include/linux/smp.h
@@ -53,6 +53,9 @@ extern void smp_cpus_done(unsigned int max_cpus);
  */
 int smp_call_function(void(*func)(void *info), void *info, int retry, int wait);
 
+int smp_call_function_single(int cpuid, void (*func) (void *info), void *info,
+				int retry, int wait);
+
 /*
  * Call a function on all processors
  */
diff --git a/include/linux/suspend.h b/include/linux/suspend.h
index 96e31aa64cc..b1237f16ecd 100644
--- a/include/linux/suspend.h
+++ b/include/linux/suspend.h
@@ -10,29 +10,11 @@
 #include <linux/pm.h>
 
 /* page backup entry */
-typedef struct pbe {
+struct pbe {
 	unsigned long address;		/* address of the copy */
 	unsigned long orig_address;	/* original address of page */
 	struct pbe *next;
-} suspend_pagedir_t;
-
-#define for_each_pbe(pbe, pblist) \
-	for (pbe = pblist ; pbe ; pbe = pbe->next)
-
-#define PBES_PER_PAGE      (PAGE_SIZE/sizeof(struct pbe))
-#define PB_PAGE_SKIP       (PBES_PER_PAGE-1)
-
-#define for_each_pb_page(pbe, pblist) \
-	for (pbe = pblist ; pbe ; pbe = (pbe+PB_PAGE_SKIP)->next)
-
-
-#define SWAP_FILENAME_MAXLENGTH	32
-
-
-extern dev_t swsusp_resume_device;
-   
-/* mm/vmscan.c */
-extern int shrink_mem(void);
+};
 
 /* mm/page_alloc.c */
 extern void drain_local_pages(void);
@@ -53,18 +35,10 @@ static inline void pm_restore_console(void) {}
 static inline int software_suspend(void)
 {
 	printk("Warning: fake suspend called\n");
-	return -EPERM;
+	return -ENOSYS;
 }
 #endif /* CONFIG_PM */
 
-#ifdef CONFIG_SUSPEND_SMP
-extern void disable_nonboot_cpus(void);
-extern void enable_nonboot_cpus(void);
-#else
-static inline void disable_nonboot_cpus(void) {}
-static inline void enable_nonboot_cpus(void) {}
-#endif
-
 void save_processor_state(void);
 void restore_processor_state(void);
 struct saved_context;
diff --git a/include/linux/swap.h b/include/linux/swap.h
index 5e59184c909..e7c36ba2a2d 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -10,6 +10,10 @@
 #include <asm/atomic.h>
 #include <asm/page.h>
 
+struct notifier_block;
+
+struct bio;
+
 #define SWAP_FLAG_PREFER	0x8000	/* set if swap priority specified */
 #define SWAP_FLAG_PRIO_MASK	0x7fff
 #define SWAP_FLAG_PRIO_SHIFT	0
@@ -156,13 +160,14 @@ struct swap_list_t {
 
 /* linux/mm/oom_kill.c */
 extern void out_of_memory(struct zonelist *zonelist, gfp_t gfp_mask, int order);
+extern int register_oom_notifier(struct notifier_block *nb);
+extern int unregister_oom_notifier(struct notifier_block *nb);
 
 /* linux/mm/memory.c */
 extern void swapin_readahead(swp_entry_t, unsigned long, struct vm_area_struct *);
 
 /* linux/mm/page_alloc.c */
 extern unsigned long totalram_pages;
-extern unsigned long totalhigh_pages;
 extern unsigned long totalreserve_pages;
 extern long nr_swap_pages;
 extern unsigned int nr_free_pages(void);
@@ -190,6 +195,7 @@ extern long vm_total_pages;
 #ifdef CONFIG_NUMA
 extern int zone_reclaim_mode;
 extern int sysctl_min_unmapped_ratio;
+extern int sysctl_min_slab_ratio;
 extern int zone_reclaim(struct zone *, gfp_t, unsigned int);
 #else
 #define zone_reclaim_mode 0
@@ -212,7 +218,9 @@ extern void swap_unplug_io_fn(struct backing_dev_info *, struct page *);
 /* linux/mm/page_io.c */
 extern int swap_readpage(struct file *, struct page *);
 extern int swap_writepage(struct page *page, struct writeback_control *wbc);
-extern int rw_swap_page_sync(int, swp_entry_t, struct page *);
+extern int rw_swap_page_sync(int rw, swp_entry_t entry, struct page *page,
+				struct bio **bio_chain);
+extern int end_swap_bio_read(struct bio *bio, unsigned int bytes_done, int err);
 
 /* linux/mm/swap_state.c */
 extern struct address_space swapper_space;
diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h
index 736ed917a4f..eca555781d0 100644
--- a/include/linux/sysctl.h
+++ b/include/linux/sysctl.h
@@ -191,6 +191,7 @@ enum
 	VM_MIN_UNMAPPED=32,	/* Set min percent of unmapped pages */
 	VM_PANIC_ON_OOM=33,	/* panic at out-of-memory */
 	VM_VDSO_ENABLED=34,	/* map VDSO into new processes? */
+	VM_MIN_SLAB=35,		 /* Percent pages ignored by zone reclaim */
 };
 
 
diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h
index 71b6363caaa..dee88c6b6fa 100644
--- a/include/linux/vmalloc.h
+++ b/include/linux/vmalloc.h
@@ -44,8 +44,6 @@ extern void *vmalloc_32_user(unsigned long size);
 extern void *__vmalloc(unsigned long size, gfp_t gfp_mask, pgprot_t prot);
 extern void *__vmalloc_area(struct vm_struct *area, gfp_t gfp_mask,
 				pgprot_t prot);
-extern void *__vmalloc_node(unsigned long size, gfp_t gfp_mask,
-				pgprot_t prot, int node);
 extern void vfree(void *addr);
 
 extern void *vmap(struct page **pages, unsigned int count,
diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h
index 2d9b1b60798..176c7f79733 100644
--- a/include/linux/vmstat.h
+++ b/include/linux/vmstat.h
@@ -18,7 +18,19 @@
  * generated will simply be the increment of a global address.
  */
 
-#define FOR_ALL_ZONES(x) x##_DMA, x##_DMA32, x##_NORMAL, x##_HIGH
+#ifdef CONFIG_ZONE_DMA32
+#define DMA32_ZONE(xx) xx##_DMA32,
+#else
+#define DMA32_ZONE(xx)
+#endif
+
+#ifdef CONFIG_HIGHMEM
+#define HIGHMEM_ZONE(xx) , xx##_HIGH
+#else
+#define HIGHMEM_ZONE(xx)
+#endif
+
+#define FOR_ALL_ZONES(xx) xx##_DMA, DMA32_ZONE(xx) xx##_NORMAL HIGHMEM_ZONE(xx)
 
 enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT,
 		FOR_ALL_ZONES(PGALLOC),
@@ -124,12 +136,10 @@ static inline unsigned long node_page_state(int node,
 	struct zone *zones = NODE_DATA(node)->node_zones;
 
 	return
-#ifndef CONFIG_DMA_IS_NORMAL
-#if !defined(CONFIG_DMA_IS_DMA32) && BITS_PER_LONG >= 64
+#ifdef CONFIG_ZONE_DMA32
 		zone_page_state(&zones[ZONE_DMA32], item) +
 #endif
 		zone_page_state(&zones[ZONE_NORMAL], item) +
-#endif
 #ifdef CONFIG_HIGHMEM
 		zone_page_state(&zones[ZONE_HIGHMEM], item) +
 #endif
diff --git a/include/linux/writeback.h b/include/linux/writeback.h
index 0422036af4e..56a23a0e7f2 100644
--- a/include/linux/writeback.h
+++ b/include/linux/writeback.h
@@ -116,6 +116,7 @@ int sync_page_range(struct inode *inode, struct address_space *mapping,
 			loff_t pos, loff_t count);
 int sync_page_range_nolock(struct inode *inode, struct address_space *mapping,
 			   loff_t pos, loff_t count);
+void set_page_dirty_balance(struct page *page);
 
 /* pdflush.c */
 extern int nr_pdflush_threads;	/* Global so it can be exported to sysctl