Merge master.kernel.org:/home/davem/BK/net-2.5

into penguin.transmeta.com:/home/penguin/torvalds/repositories/kernel/linux

26 files changed, 396 insertions, 107 deletions

diff --git a/include/linux/eventpoll.h b/include/linux/eventpoll.h
new file mode 100644
index 000000000000..c028d5b7576b
--- /dev/null
+++ b/include/linux/eventpoll.h
@@ -0,0 +1,51 @@
+/*
+ *  include/linux/eventpoll.h ( Efficent event polling implementation )
+ *  Copyright (C) 2001,...,2002  Davide Libenzi
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License as published by
+ *  the Free Software Foundation; either version 2 of the License, or
+ *  (at your option) any later version.
+ *
+ *  Davide Libenzi <davidel@xmailserver.org>
+ *
+ */
+
+#ifndef _LINUX_EVENTPOLL_H
+#define _LINUX_EVENTPOLL_H
+
+
+#define EVENTPOLL_MINOR	124
+#define POLLFD_X_PAGE (PAGE_SIZE / sizeof(struct pollfd))
+#define MAX_FDS_IN_EVENTPOLL (1024 * 128)
+#define MAX_EVENTPOLL_PAGES (MAX_FDS_IN_EVENTPOLL / POLLFD_X_PAGE)
+#define EVENT_PAGE_INDEX(n) ((n) / POLLFD_X_PAGE)
+#define EVENT_PAGE_REM(n) ((n) % POLLFD_X_PAGE)
+#define EVENT_PAGE_OFFSET(n) (((n) % POLLFD_X_PAGE) * sizeof(struct pollfd))
+#define EP_FDS_PAGES(n) (((n) + POLLFD_X_PAGE - 1) / POLLFD_X_PAGE)
+#define EP_MAP_SIZE(n) (EP_FDS_PAGES(n) * PAGE_SIZE * 2)
+
+
+struct evpoll {
+	int ep_timeout;
+	unsigned long ep_resoff;
+};
+
+#define EP_ALLOC _IOR('P', 1, int)
+#define EP_POLL _IOWR('P', 2, struct evpoll)
+#define EP_FREE _IO('P', 3)
+#define EP_ISPOLLED _IOWR('P', 4, struct pollfd)
+
+#define EP_CTL_ADD 1
+#define EP_CTL_DEL 2
+#define EP_CTL_MOD 3
+
+
+asmlinkage int sys_epoll_create(int maxfds);
+asmlinkage int sys_epoll_ctl(int epfd, int op, int fd, unsigned int events);
+asmlinkage int sys_epoll_wait(int epfd, struct pollfd const **events, int timeout);
+
+
+
+#endif
+
diff --git a/include/linux/fcblist.h b/include/linux/fcblist.h
new file mode 100644
index 000000000000..85be93ae40fd
--- /dev/null
+++ b/include/linux/fcblist.h
@@ -0,0 +1,71 @@
+/*
+ *  include/linux/fcblist.h ( File event callbacks handling )
+ *  Copyright (C) 2001,...,2002  Davide Libenzi
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License as published by
+ *  the Free Software Foundation; either version 2 of the License, or
+ *  (at your option) any later version.
+ *
+ *  Davide Libenzi <davidel@xmailserver.org>
+ *
+ */
+
+#ifndef __LINUX_FCBLIST_H
+#define __LINUX_FCBLIST_H
+
+#include <linux/config.h>
+#include <linux/list.h>
+#include <linux/spinlock.h>
+#include <linux/fs.h>
+#include <linux/file.h>
+
+
+
+/* file callback notification events */
+#define ION_IN		1
+#define ION_OUT		2
+#define ION_HUP		3
+#define ION_ERR		4
+
+#define FCB_LOCAL_SIZE	4
+
+
+struct fcb_struct {
+	struct list_head llink;
+	void (*cbproc)(struct file *, void *, unsigned long *, long *);
+	void *data;
+	unsigned long local[FCB_LOCAL_SIZE];
+};
+
+
+extern long ion_band_table[];
+extern long poll_band_table[];
+
+
+void file_notify_event(struct file *filep, long *event);
+
+int file_notify_addcb(struct file *filep,
+		      void (*cbproc)(struct file *, void *, unsigned long *, long *),
+		      void *data);
+
+int file_notify_delcb(struct file *filep,
+		      void (*cbproc)(struct file *, void *, unsigned long *, long *));
+
+void file_notify_cleanup(struct file *filep);
+
+
+static inline void file_notify_init(struct file *filep)
+{
+	rwlock_init(&filep->f_cblock);
+	INIT_LIST_HEAD(&filep->f_cblist);
+}
+
+static inline void file_send_notify(struct file *filep, long ioevt, long plevt)
+{
+	long event[] = { ioevt, plevt, -1 };
+
+	file_notify_event(filep, event);
+}
+
+#endif
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 5694a661878e..9a3e78ba7592 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -504,6 +504,10 @@ struct file {
 
 	/* needed for tty driver, and maybe others */
 	void			*private_data;
+
+	/* file callback list */
+	rwlock_t f_cblock;
+	struct list_head f_cblist;
 };
 extern spinlock_t files_lock;
 #define file_list_lock() spin_lock(&files_lock);
@@ -791,6 +795,8 @@ struct seq_file;
 
 extern ssize_t vfs_read(struct file *, char *, size_t, loff_t *);
 extern ssize_t vfs_write(struct file *, const char *, size_t, loff_t *);
+extern ssize_t vfs_readv(struct file *, struct iovec *, int, size_t, loff_t *);
+extern ssize_t vfs_writev(struct file *, const struct iovec *, int, size_t, loff_t *);
 
 /*
  * NOTE: write_inode, delete_inode, clear_inode, put_inode can be called
diff --git a/include/linux/gfp.h b/include/linux/gfp.h
index 939f16910233..8e093813e4f7 100644
--- a/include/linux/gfp.h
+++ b/include/linux/gfp.h
@@ -17,6 +17,7 @@
 #define __GFP_IO	0x40	/* Can start low memory physical IO? */
 #define __GFP_HIGHIO	0x80	/* Can start high mem physical IO? */
 #define __GFP_FS	0x100	/* Can call down to low-level FS? */
+#define __GFP_COLD	0x200	/* Cache-cold page required */
 
 #define GFP_NOHIGHIO	(             __GFP_WAIT | __GFP_IO)
 #define GFP_NOIO	(             __GFP_WAIT)
@@ -32,6 +33,7 @@
 
 #define GFP_DMA		__GFP_DMA
 
+
 /*
  * There is only one page-allocator function, and two main namespaces to
  * it. The alloc_page*() variants return 'struct page *' and as such
@@ -77,13 +79,14 @@ extern unsigned long FASTCALL(get_zeroed_page(unsigned int gfp_mask));
 #define __get_dma_pages(gfp_mask, order) \
 		__get_free_pages((gfp_mask) | GFP_DMA,(order))
 
-/*
- * There is only one 'core' page-freeing function.
- */
 extern void FASTCALL(__free_pages(struct page *page, unsigned int order));
 extern void FASTCALL(free_pages(unsigned long addr, unsigned int order));
+extern void FASTCALL(free_hot_page(struct page *page));
+extern void FASTCALL(free_cold_page(struct page *page));
 
 #define __free_page(page) __free_pages((page), 0)
 #define free_page(addr) free_pages((addr),0)
 
+void page_alloc_init(void);
+
 #endif /* __LINUX_GFP_H */
diff --git a/include/linux/kobject.h b/include/linux/kobject.h
new file mode 100644
index 000000000000..d2f0629a6189
--- /dev/null
+++ b/include/linux/kobject.h
@@ -0,0 +1,57 @@
+/*
+ * kobject.h - generic kernel object infrastructure.
+ *
+ */
+
+#ifndef _KOBJECT_H_
+#define _KOBJECT_H_
+
+#include <linux/types.h>
+#include <linux/list.h>
+#include <linux/sysfs.h>
+#include <linux/rwsem.h>
+#include <asm/atomic.h>
+
+struct kobject {
+	char			name[16];
+	atomic_t		refcount;
+	struct list_head	entry;
+	struct kobject		* parent;
+	struct subsystem	* subsys;
+	struct dentry		* dentry;
+};
+
+extern void kobject_init(struct kobject *);
+
+extern int kobject_register(struct kobject *);
+extern void kobject_unregister(struct kobject *);
+
+extern struct kobject * kobject_get(struct kobject *);
+extern void kobject_put(struct kobject *);
+
+
+struct subsystem {
+	struct kobject		kobj;
+	struct list_head	list;
+	struct rw_semaphore	rwsem;
+	struct subsystem	* parent;
+	void (*release)(struct kobject *);
+	struct sysfs_ops	* sysfs_ops;
+	struct attribute	** default_attrs;
+};
+
+extern void subsystem_init(struct subsystem *);
+extern int subsystem_register(struct subsystem *);
+extern void subsystem_unregister(struct subsystem *);
+
+static inline struct subsystem * subsys_get(struct subsystem * s)
+{
+	return container_of(kobject_get(&s->kobj),struct subsystem,kobj);
+}
+
+static inline void subsys_put(struct subsystem * s)
+{
+	kobject_put(&s->kobj);
+}
+
+#endif /* _KOBJECT_H_ */
diff --git a/include/linux/mm.h b/include/linux/mm.h
index cab2c4342047..d9d2f20732d4 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -211,7 +211,6 @@ struct page {
 #define set_page_count(p,v) 	atomic_set(&(p)->count, v)
 
 extern void FASTCALL(__page_cache_release(struct page *));
-void FASTCALL(__free_pages_ok(struct page *page, unsigned int order));
 
 static inline void put_page(struct page *page)
 {
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 10c4ee968020..d80490b1265c 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -9,6 +9,7 @@
 #include <linux/list.h>
 #include <linux/wait.h>
 #include <linux/cache.h>
+#include <linux/threads.h>
 #include <asm/atomic.h>
 #ifdef CONFIG_DISCONTIGMEM
 #include <asm/numnodes.h>
@@ -46,6 +47,18 @@ struct zone_padding {
 #define ZONE_PADDING(name)
 #endif
 
+struct per_cpu_pages {
+	int count;		/* number of pages in the list */
+	int low;		/* low watermark, refill needed */
+	int high;		/* high watermark, emptying needed */
+	int batch;		/* chunk size for buddy add/remove */
+	struct list_head list;	/* the list of pages */
+};
+
+struct per_cpu_pageset {
+	struct per_cpu_pages pcp[2];	/* 0: hot.  1: cold */
+} ____cacheline_aligned_in_smp;
+
 /*
  * On machines where it is needed (eg PCs) we divide physical memory
  * into multiple physical zones. On a PC we have 3 zones:
@@ -107,6 +120,10 @@ struct zone {
 	unsigned long		wait_table_size;
 	unsigned long		wait_table_bits;
 
+	ZONE_PADDING(_pad3_)
+
+	struct per_cpu_pageset	pageset[NR_CPUS];
+
 	/*
 	 * Discontig memory support fields.
 	 */
diff --git a/include/linux/nfsd/cache.h b/include/linux/nfsd/cache.h
index ae2da13bed23..b780f9635930 100644
--- a/include/linux/nfsd/cache.h
+++ b/include/linux/nfsd/cache.h
@@ -32,12 +32,12 @@ struct svc_cacherep {
 	u32			c_vers;
 	unsigned long		c_timestamp;
 	union {
-		struct svc_buf	u_buffer;
+		struct iovec	u_vec;
 		u32		u_status;
 	}			c_u;
 };
 
-#define c_replbuf		c_u.u_buffer
+#define c_replvec		c_u.u_vec
 #define c_replstat		c_u.u_status
 
 /* cache entry states */
diff --git a/include/linux/nfsd/export.h b/include/linux/nfsd/export.h
index 4d692bb2797f..864e3b801f0f 100644
--- a/include/linux/nfsd/export.h
+++ b/include/linux/nfsd/export.h
@@ -83,6 +83,7 @@ struct svc_expkey {
  */
 void			nfsd_export_init(void);
 void			nfsd_export_shutdown(void);
+void			nfsd_export_flush(void);
 void			exp_readlock(void);
 void			exp_readunlock(void);
 struct svc_expkey *	exp_find_key(struct auth_domain *clp, 
diff --git a/include/linux/nfsd/nfsd.h b/include/linux/nfsd/nfsd.h
index c72354852e2b..1b8b01067391 100644
--- a/include/linux/nfsd/nfsd.h
+++ b/include/linux/nfsd/nfsd.h
@@ -48,16 +48,7 @@
  * Callback function for readdir
  */
 struct readdir_cd {
-	struct svc_rqst *	rqstp;
-	struct svc_fh *		dirfh;
-	u32 *			buffer;
-	int			buflen;
-	u32 *			offset;		/* previous dirent->d_next */
-	char			plus;		/* readdirplus */
-	char			eob;		/* end of buffer */
-	char			dotonly;
-	int			nfserr;		/* v4 only */
-	u32			bmval[2];	/* v4 only */
+	int			err;	/* 0, nfserr, or nfserr_eof */
 };
 typedef int		(*encode_dent_fn)(struct readdir_cd *, const char *,
 						int, loff_t, ino_t, unsigned int);
@@ -97,9 +88,9 @@ int		nfsd_open(struct svc_rqst *, struct svc_fh *, int,
 				int, struct file *);
 void		nfsd_close(struct file *);
 int		nfsd_read(struct svc_rqst *, struct svc_fh *,
-				loff_t, char *, unsigned long *);
+				loff_t, struct iovec *,int, unsigned long *);
 int		nfsd_write(struct svc_rqst *, struct svc_fh *,
-				loff_t, char *, unsigned long, int *);
+				loff_t, struct iovec *,int, unsigned long, int *);
 int		nfsd_readlink(struct svc_rqst *, struct svc_fh *,
 				char *, int *);
 int		nfsd_symlink(struct svc_rqst *, struct svc_fh *,
@@ -117,9 +108,7 @@ int		nfsd_unlink(struct svc_rqst *, struct svc_fh *, int type,
 int		nfsd_truncate(struct svc_rqst *, struct svc_fh *,
 				unsigned long size);
 int		nfsd_readdir(struct svc_rqst *, struct svc_fh *,
-				loff_t, encode_dent_fn,
-				u32 *buffer, int *countp, u32 *verf,
-				u32 *bmval);
+			     loff_t *, struct readdir_cd *, encode_dent_fn);
 int		nfsd_statfs(struct svc_rqst *, struct svc_fh *,
 				struct statfs *);
 
@@ -180,10 +169,13 @@ void		nfsd_lockd_shutdown(void);
 #define	nfserr_readdir_nospc	__constant_htonl(NFSERR_READDIR_NOSPC)
 #define	nfserr_bad_xdr		__constant_htonl(NFSERR_BAD_XDR)
 
-/* error code for internal use - if a request fails due to
- * kmalloc failure, it gets dropped.  Client should resend eventually
+/* error codes for internal use */
+/* if a request fails due to kmalloc failure, it gets dropped.
+ *  Client should resend eventually
  */
 #define	nfserr_dropit		__constant_htonl(30000)
+/* end-of-file indicator in readdir */
+#define	nfserr_eof		__constant_htonl(30001)
 
 /* Check for dir entries '.' and '..' */
 #define isdotent(n, l)	(l < 3 && n[0] == '.' && (l == 1 || n[1] == '.'))
diff --git a/include/linux/nfsd/xdr.h b/include/linux/nfsd/xdr.h
index d81b71fefe6d..97078834e430 100644
--- a/include/linux/nfsd/xdr.h
+++ b/include/linux/nfsd/xdr.h
@@ -29,16 +29,16 @@ struct nfsd_readargs {
 	struct svc_fh		fh;
 	__u32			offset;
 	__u32			count;
-	__u32			totalsize;
+	struct iovec		vec[RPCSVC_MAXPAGES];
+	int			vlen;
 };
 
 struct nfsd_writeargs {
 	svc_fh			fh;
-	__u32			beginoffset;
 	__u32			offset;
-	__u32			totalcount;
-	__u8 *			data;
 	int			len;
+	struct iovec		vec[RPCSVC_MAXPAGES];
+	int			vlen;
 };
 
 struct nfsd_createargs {
@@ -98,6 +98,11 @@ struct nfsd_readres {
 
 struct nfsd_readdirres {
 	int			count;
+
+	struct readdir_cd	common;
+	u32 *			buffer;
+	int			buflen;
+	u32 *			offset;
 };
 
 struct nfsd_statfsres {
diff --git a/include/linux/nfsd/xdr3.h b/include/linux/nfsd/xdr3.h
index 35d167ad6cd2..1576a6db4a17 100644
--- a/include/linux/nfsd/xdr3.h
+++ b/include/linux/nfsd/xdr3.h
@@ -33,6 +33,8 @@ struct nfsd3_readargs {
 	struct svc_fh		fh;
 	__u64			offset;
 	__u32			count;
+	struct iovec		vec[RPCSVC_MAXPAGES];
+	int			vlen;
 };
 
 struct nfsd3_writeargs {
@@ -40,8 +42,9 @@ struct nfsd3_writeargs {
 	__u64			offset;
 	__u32			count;
 	int			stable;
-	__u8 *			data;
 	int			len;
+	struct iovec		vec[RPCSVC_MAXPAGES];
+	int			vlen;
 };
 
 struct nfsd3_createargs {
@@ -156,6 +159,13 @@ struct nfsd3_readdirres {
 	struct svc_fh		fh;
 	int			count;
 	__u32			verf[2];
+
+	struct readdir_cd	common;
+	u32 *			buffer;
+	int			buflen;
+	u32 *			offset;
+	struct svc_rqst *	rqstp;
+
 };
 
 struct nfsd3_fsstatres {
diff --git a/include/linux/nfsd/xdr4.h b/include/linux/nfsd/xdr4.h
index 2bf2c5d3b24e..4238cb04ad90 100644
--- a/include/linux/nfsd/xdr4.h
+++ b/include/linux/nfsd/xdr4.h
@@ -185,6 +185,11 @@ struct nfsd4_readdir {
 	u32		rd_bmval[2];        /* request */
 	struct svc_rqst *rd_rqstp;          /* response */
 	struct svc_fh * rd_fhp;             /* response */
+
+	struct readdir_cd	common;
+	u32 *			buffer;
+	int			buflen;
+	u32 *			offset;
 };
 
 struct nfsd4_readlink {
diff --git a/include/linux/notifier.h b/include/linux/notifier.h
index 05d2e7968646..f9638ff66bb9 100644
--- a/include/linux/notifier.h
+++ b/include/linux/notifier.h
@@ -60,7 +60,11 @@ extern int notifier_call_chain(struct notifier_block **n, unsigned long val, voi
 
 #define NETLINK_URELEASE	0x0001	/* Unicast netlink socket released */
 
-#define CPU_ONLINE	0x0002 /* CPU (unsigned)v coming up */
+#define CPU_ONLINE	0x0002 /* CPU (unsigned)v is up */
+#define CPU_UP_PREPARE	0x0003 /* CPU (unsigned)v coming up */
+#define CPU_UP_CANCELED	0x0004 /* CPU (unsigned)v NOT coming up */
+#define CPU_OFFLINE	0x0005 /* CPU (unsigned)v offline (still scheduling) */
+#define CPU_DEAD	0x0006 /* CPU (unsigned)v dead */
 
 #endif /* __KERNEL__ */
 #endif /* _LINUX_NOTIFIER_H */
diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
index 5c770f49787a..282902bb9816 100644
--- a/include/linux/page-flags.h
+++ b/include/linux/page-flags.h
@@ -5,6 +5,8 @@
 #ifndef PAGE_FLAGS_H
 #define PAGE_FLAGS_H
 
+#include <linux/percpu.h>
+
 /*
  * Various page->flags bits:
  *
@@ -73,7 +75,7 @@
  * Global page accounting.  One instance per CPU.  Only unsigned longs are
  * allowed.
  */
-extern struct page_state {
+struct page_state {
 	unsigned long nr_dirty;
 	unsigned long nr_writeback;
 	unsigned long nr_pagecache;
@@ -103,7 +105,9 @@ extern struct page_state {
 	unsigned long kswapd_steal;
 	unsigned long pageoutrun;
 	unsigned long allocstall;
-} ____cacheline_aligned_in_smp page_states[NR_CPUS];
+};
+
+DECLARE_PER_CPU(struct page_state, page_states);
 
 extern void get_page_state(struct page_state *ret);
 extern void get_full_page_state(struct page_state *ret);
@@ -111,7 +115,7 @@ extern void get_full_page_state(struct page_state *ret);
 #define mod_page_state(member, delta)					\
 	do {								\
 		int cpu = get_cpu();					\
-		page_states[cpu].member += (delta);			\
+		per_cpu(page_states, cpu).member += (delta);		\
 		put_cpu();						\
 	} while (0)
 
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index 1fe640eaf601..04751ceba493 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -24,13 +24,18 @@
 
 #define page_cache_get(page)		get_page(page)
 #define page_cache_release(page)	put_page(page)
-void release_pages(struct page **pages, int nr);
+void release_pages(struct page **pages, int nr, int cold);
 
 static inline struct page *page_cache_alloc(struct address_space *x)
 {
 	return alloc_pages(x->gfp_mask, 0);
 }
 
+static inline struct page *page_cache_alloc_cold(struct address_space *x)
+{
+	return alloc_pages(x->gfp_mask|__GFP_COLD, 0);
+}
+
 typedef int filler_t(void *, struct page *);
 
 extern struct page * find_get_page(struct address_space *mapping,
diff --git a/include/linux/pagevec.h b/include/linux/pagevec.h
index 0207270b0fe7..d149e0688b1e 100644
--- a/include/linux/pagevec.h
+++ b/include/linux/pagevec.h
@@ -12,6 +12,7 @@ struct address_space;
 
 struct pagevec {
 	unsigned nr;
+	int cold;
 	struct page *pages[PAGEVEC_SIZE];
 };
 
@@ -25,7 +26,13 @@ void pagevec_strip(struct pagevec *pvec);
 unsigned int pagevec_lookup(struct pagevec *pvec, struct address_space *mapping,
 		pgoff_t start, unsigned int nr_pages);
 
-static inline void pagevec_init(struct pagevec *pvec)
+static inline void pagevec_init(struct pagevec *pvec, int cold)
+{
+	pvec->nr = 0;
+	pvec->cold = cold;
+}
+
+static inline void pagevec_reinit(struct pagevec *pvec)
 {
 	pvec->nr = 0;
 }
@@ -49,6 +56,7 @@ static inline unsigned pagevec_add(struct pagevec *pvec, struct page *page)
 	return pagevec_space(pvec);
 }
 
+
 static inline void pagevec_release(struct pagevec *pvec)
 {
 	if (pagevec_count(pvec))
diff --git a/include/linux/pipe_fs_i.h b/include/linux/pipe_fs_i.h
index 407c0e0b3e84..bdf0a3686916 100644
--- a/include/linux/pipe_fs_i.h
+++ b/include/linux/pipe_fs_i.h
@@ -12,6 +12,8 @@ struct pipe_inode_info {
 	unsigned int waiting_writers;
 	unsigned int r_counter;
 	unsigned int w_counter;
+	struct file *rdfile;
+	struct file *wrfile;
 	struct fasync_struct *fasync_readers;
 	struct fasync_struct *fasync_writers;
 };
@@ -30,6 +32,8 @@ struct pipe_inode_info {
 #define PIPE_WAITING_WRITERS(inode)	((inode).i_pipe->waiting_writers)
 #define PIPE_RCOUNTER(inode)	((inode).i_pipe->r_counter)
 #define PIPE_WCOUNTER(inode)	((inode).i_pipe->w_counter)
+#define PIPE_READFILE(inode)	((inode).i_pipe->rdfile)
+#define PIPE_WRITEFILE(inode)	((inode).i_pipe->wrfile)
 #define PIPE_FASYNC_READERS(inode)     (&((inode).i_pipe->fasync_readers))
 #define PIPE_FASYNC_WRITERS(inode)     (&((inode).i_pipe->fasync_writers))
 
diff --git a/include/linux/raid/md_k.h b/include/linux/raid/md_k.h
index 453324c18bdd..f658735d28b2 100644
--- a/include/linux/raid/md_k.h
+++ b/include/linux/raid/md_k.h
@@ -151,8 +151,9 @@ struct mdk_rdev_s
 	struct block_device *bdev;	/* block device handle */
 
 	struct page	*sb_page;
-	mdp_super_t	*sb;
+	int		sb_loaded;
 	sector_t	sb_offset;
+	int		preferred_minor;	/* autorun support */
 
 	/* A device can be in one of three states based on two flags:
 	 * Not working:   faulty==1 in_sync==0
@@ -196,6 +197,7 @@ struct mddev_s
 	time_t				ctime, utime;
 	int				level, layout;
 	int				raid_disks;
+	int				max_disks;
 	unsigned long			state;
 	sector_t			size; /* used size of component devices */
 	__u64				events;
diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index a5ffb7bb5743..e9e2287e1e1c 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -39,6 +39,7 @@
 #include <linux/list.h>
 #include <linux/spinlock.h>
 #include <linux/threads.h>
+#include <linux/percpu.h>
 
 /**
  * struct rcu_head - callback structure for use with RCU
@@ -94,16 +95,16 @@ struct rcu_data {
         long  	       	batch;           /* Batch # for current RCU batch */
         struct list_head  nxtlist;
         struct list_head  curlist;
-} ____cacheline_aligned_in_smp;
+};
 
-extern struct rcu_data rcu_data[NR_CPUS];
+DECLARE_PER_CPU(struct rcu_data, rcu_data);
 extern struct rcu_ctrlblk rcu_ctrlblk;
 
-#define RCU_qsctr(cpu) 		(rcu_data[(cpu)].qsctr)
-#define RCU_last_qsctr(cpu) 	(rcu_data[(cpu)].last_qsctr)
-#define RCU_batch(cpu) 		(rcu_data[(cpu)].batch)
-#define RCU_nxtlist(cpu) 	(rcu_data[(cpu)].nxtlist)
-#define RCU_curlist(cpu) 	(rcu_data[(cpu)].curlist)
+#define RCU_qsctr(cpu) 		(per_cpu(rcu_data, (cpu)).qsctr)
+#define RCU_last_qsctr(cpu) 	(per_cpu(rcu_data, (cpu)).last_qsctr)
+#define RCU_batch(cpu) 		(per_cpu(rcu_data, (cpu)).batch)
+#define RCU_nxtlist(cpu) 	(per_cpu(rcu_data, (cpu)).nxtlist)
+#define RCU_curlist(cpu) 	(per_cpu(rcu_data, (cpu)).curlist)
 
 #define RCU_QSCTR_INVALID	0
 
diff --git a/include/linux/sched.h b/include/linux/sched.h
index b5e63d8ade25..65f9799aa896 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -293,9 +293,6 @@ struct task_struct {
 	struct list_head ptrace_list;
 
 	struct mm_struct *mm, *active_mm;
-	struct list_head local_pages;
-
-	unsigned int allocation_order, nr_local_pages;
 
 /* task state */
 	struct linux_binfmt *binfmt;
@@ -411,16 +408,15 @@ do { if (atomic_dec_and_test(&(tsk)->usage)) __put_task_struct(tsk); } while(0)
 #define PF_SIGNALED	0x00000400	/* killed by a signal */
 #define PF_MEMALLOC	0x00000800	/* Allocating memory */
 #define PF_MEMDIE	0x00001000	/* Killed for out-of-memory */
-#define PF_FREE_PAGES	0x00002000	/* per process page freeing */
-#define PF_FLUSHER	0x00004000	/* responsible for disk writeback */
-#define PF_NOWARN	0x00008000	/* debug: don't warn if alloc fails */
-
-#define PF_FREEZE	0x00010000	/* this task should be frozen for suspend */
-#define PF_IOTHREAD	0x00020000	/* this thread is needed for doing I/O to swap */
-#define PF_FROZEN	0x00040000	/* frozen for system suspend */
-#define PF_SYNC		0x00080000	/* performing fsync(), etc */
-#define PF_FSTRANS	0x00100000	/* inside a filesystem transaction */
-#define PF_KSWAPD	0x00200000	/* I am kswapd */
+#define PF_FLUSHER	0x00002000	/* responsible for disk writeback */
+#define PF_NOWARN	0x00004000	/* debug: don't warn if alloc fails */
+
+#define PF_FREEZE	0x00008000	/* this task should be frozen for suspend */
+#define PF_IOTHREAD	0x00010000	/* this thread is needed for doing I/O to swap */
+#define PF_FROZEN	0x00020000	/* frozen for system suspend */
+#define PF_SYNC		0x00040000	/* performing fsync(), etc */
+#define PF_FSTRANS	0x00080000	/* inside a filesystem transaction */
+#define PF_KSWAPD	0x00100000	/* I am kswapd */
 
 /*
  * Ptrace flags
diff --git a/include/linux/sonypi.h b/include/linux/sonypi.h
index 4a53f5b8852a..8828b98b3029 100644
--- a/include/linux/sonypi.h
+++ b/include/linux/sonypi.h
@@ -75,6 +75,16 @@
 #define SONYPI_EVENT_LID_OPENED			37
 #define SONYPI_EVENT_BLUETOOTH_ON		38
 #define SONYPI_EVENT_BLUETOOTH_OFF		39
+#define SONYPI_EVENT_HELP_PRESSED		40
+#define SONYPI_EVENT_FNKEY_ONLY			41
+#define SONYPI_EVENT_JOGDIAL_FAST_DOWN		42
+#define SONYPI_EVENT_JOGDIAL_FAST_UP		43
+#define SONYPI_EVENT_JOGDIAL_FAST_DOWN_PRESSED	44
+#define SONYPI_EVENT_JOGDIAL_FAST_UP_PRESSED	45
+#define SONYPI_EVENT_JOGDIAL_VFAST_DOWN		46
+#define SONYPI_EVENT_JOGDIAL_VFAST_UP		47
+#define SONYPI_EVENT_JOGDIAL_VFAST_DOWN_PRESSED	48
+#define SONYPI_EVENT_JOGDIAL_VFAST_UP_PRESSED	49
 
 /* get/set brightness */
 #define SONYPI_IOCGBRT		_IOR('v', 0, __u8)
diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h
index 9ad879d9bea7..24464d66411a 100644
--- a/include/linux/sunrpc/svc.h
+++ b/include/linux/sunrpc/svc.h
@@ -48,43 +48,49 @@ struct svc_serv {
  * This is use to determine the max number of pages nfsd is
  * willing to return in a single READ operation.
  */
-#define RPCSVC_MAXPAYLOAD	16384u
+#define RPCSVC_MAXPAYLOAD	(64*1024u)
 
 /*
- * Buffer to store RPC requests or replies in.
- * Each server thread has one of these beasts.
+ * RPC Requsts and replies are stored in one or more pages.
+ * We maintain an array of pages for each server thread.
+ * Requests are copied into these pages as they arrive.  Remaining
+ * pages are available to write the reply into.
  *
- * Area points to the allocated memory chunk currently owned by the
- * buffer. Base points to the buffer containing the request, which is
- * different from area when directly reading from an sk_buff. buf is
- * the current read/write position while processing an RPC request.
+ * Currently pages are all re-used by the same server.  Later we 
+ * will use ->sendpage to transmit pages with reduced copying.  In
+ * that case we will need to give away the page and allocate new ones.
+ * In preparation for this, we explicitly move pages off the recv
+ * list onto the transmit list, and back.
  *
- * The array of iovecs can hold additional data that the server process
- * may not want to copy into the RPC reply buffer, but pass to the 
- * network sendmsg routines directly. The prime candidate for this
- * will of course be NFS READ operations, but one might also want to
- * do something about READLINK and READDIR. It might be worthwhile
- * to implement some generic readdir cache in the VFS layer...
+ * We use xdr_buf for holding responses as it fits well with NFS
+ * read responses (that have a header, and some data pages, and possibly
+ * a tail) and means we can share some client side routines.
  *
- * On the receiving end of the RPC server, the iovec may be used to hold
- * the list of IP fragments once we get to process fragmented UDP
- * datagrams directly.
+ * The xdr_buf.head iovec always points to the first page in the rq_*pages
+ * list.  The xdr_buf.pages pointer points to the second page on that
+ * list.  xdr_buf.tail points to the end of the first page.
+ * This assumes that the non-page part of an rpc reply will fit
+ * in a page - NFSd ensures this.  lockd also has no trouble.
  */
-#define RPCSVC_MAXIOV		((RPCSVC_MAXPAYLOAD+PAGE_SIZE-1)/PAGE_SIZE + 1)
-struct svc_buf {
-	u32 *			area;	/* allocated memory */
-	u32 *			base;	/* base of RPC datagram */
-	int			buflen;	/* total length of buffer */
-	u32 *			buf;	/* read/write pointer */
-	int			len;	/* current end of buffer */
-
-	/* iovec for zero-copy NFS READs */
-	struct iovec		iov[RPCSVC_MAXIOV];
-	int			nriov;
-};
-#define svc_getu32(argp, val)	{ (val) = *(argp)->buf++; (argp)->len--; }
-#define svc_putu32(resp, val)	{ *(resp)->buf++ = (val); (resp)->len++; }
+#define RPCSVC_MAXPAGES		((RPCSVC_MAXPAYLOAD+PAGE_SIZE-1)/PAGE_SIZE + 1)
+
+static inline u32 svc_getu32(struct iovec *iov)
+{
+	u32 val, *vp;
+	vp = iov->iov_base;
+	val = *vp++;
+	iov->iov_base = (void*)vp;
+	iov->iov_len -= sizeof(u32);
+	return val;
+}
+static inline void svc_putu32(struct iovec *iov, u32 val)
+{
+	u32 *vp = iov->iov_base + iov->iov_len;
+	*vp = val;
+	iov->iov_len += sizeof(u32);
+}
 
+	
 /*
  * The context of a single thread, including the request currently being
  * processed.
@@ -102,9 +108,15 @@ struct svc_rqst {
 	struct svc_cred		rq_cred;	/* auth info */
 	struct sk_buff *	rq_skbuff;	/* fast recv inet buffer */
 	struct svc_deferred_req*rq_deferred;	/* deferred request we are replaying */
-	struct svc_buf		rq_defbuf;	/* default buffer */
-	struct svc_buf		rq_argbuf;	/* argument buffer */
-	struct svc_buf		rq_resbuf;	/* result buffer */
+
+	struct xdr_buf		rq_arg;
+	struct xdr_buf		rq_res;
+	struct page *		rq_argpages[RPCSVC_MAXPAGES];
+	struct page *		rq_respages[RPCSVC_MAXPAGES];
+	short			rq_argused;	/* pages used for argument */
+	short			rq_arghi;	/* pages available in argument page list */
+	short			rq_resused;	/* pages used for result */
+
 	u32			rq_xid;		/* transmission id */
 	u32			rq_prog;	/* program number */
 	u32			rq_vers;	/* program version */
@@ -136,6 +148,38 @@ struct svc_rqst {
 	wait_queue_head_t	rq_wait;	/* synchronization */
 };
 
+/*
+ * Check buffer bounds after decoding arguments
+ */
+static inline int
+xdr_argsize_check(struct svc_rqst *rqstp, u32 *p)
+{
+	char *cp = (char *)p;
+	struct iovec *vec = &rqstp->rq_arg.head[0];
+	return cp - (char*)vec->iov_base <= vec->iov_len;
+}
+
+static inline int
+xdr_ressize_check(struct svc_rqst *rqstp, u32 *p)
+{
+	struct iovec *vec = &rqstp->rq_res.head[0];
+	char *cp = (char*)p;
+
+	vec->iov_len = cp - (char*)vec->iov_base;
+	rqstp->rq_res.len = vec->iov_len;
+
+	return vec->iov_len <= PAGE_SIZE;
+}
+
+static int inline take_page(struct svc_rqst *rqstp)
+{
+	if (rqstp->rq_arghi <= rqstp->rq_argused)
+		return -ENOMEM;
+	rqstp->rq_respages[rqstp->rq_resused++] =
+		rqstp->rq_argpages[--rqstp->rq_arghi];
+	return 0;
+}
+
 struct svc_deferred_req {
 	struct svc_serv		*serv;
 	u32			prot;	/* protocol (UDP or TCP) */
diff --git a/include/linux/sys.h b/include/linux/sys.h
index dcd3256684cf..95b431dbebff 100644
--- a/include/linux/sys.h
+++ b/include/linux/sys.h
@@ -4,7 +4,7 @@
 /*
  * system call entry points ... but not all are defined
  */
-#define NR_syscalls 256
+#define NR_syscalls 260
 
 /*
  * These are system calls that will be removed at some time
diff --git a/include/linux/sysfs.h b/include/linux/sysfs.h
index 6479902e1d20..7a46c9f0c308 100644
--- a/include/linux/sysfs.h
+++ b/include/linux/sysfs.h
@@ -11,19 +11,11 @@
 
 struct driver_dir_entry;
 struct attribute;
+struct kobject;
 
 struct sysfs_ops {
-	int	(*open)(struct driver_dir_entry *);
-	int	(*close)(struct driver_dir_entry *);
-	ssize_t	(*show)(struct driver_dir_entry *, struct attribute *,char *, size_t, loff_t);
-	ssize_t	(*store)(struct driver_dir_entry *,struct attribute *,const char *, size_t, loff_t);
-};
-
-struct driver_dir_entry {
-	char			* name;
-	struct dentry		* dentry;
-	mode_t			mode;
-	struct sysfs_ops	* ops;
+	ssize_t	(*show)(struct kobject *, struct attribute *,char *, size_t, loff_t);
+	ssize_t	(*store)(struct kobject *,struct attribute *,const char *, size_t, loff_t);
 };
 
 struct attribute {
@@ -32,20 +24,21 @@ struct attribute {
 };
 
 extern int
-sysfs_create_dir(struct driver_dir_entry *, struct driver_dir_entry *);
+sysfs_create_dir(struct kobject *);
 
 extern void
-sysfs_remove_dir(struct driver_dir_entry * entry);
+sysfs_remove_dir(struct kobject *);
 
 extern int
-sysfs_create_file(struct attribute * attr,
-		     struct driver_dir_entry * parent);
+sysfs_create_file(struct kobject *, struct attribute *);
+
+extern void
+sysfs_remove_file(struct kobject *, struct attribute *);
 
 extern int 
-sysfs_create_symlink(struct driver_dir_entry * parent, 
-			char * name, char * target);
+sysfs_create_link(struct kobject * kobj, struct kobject * target, char * name);
 
 extern void
-sysfs_remove_file(struct driver_dir_entry *, const char * name);
+sysfs_remove_link(struct kobject *, char * name);
 
 #endif /* _SYSFS_H_ */
diff --git a/include/linux/timer.h b/include/linux/timer.h
index cfedb5e8bb07..d8ed753c8caa 100644
--- a/include/linux/timer.h
+++ b/include/linux/timer.h
@@ -44,6 +44,7 @@ static inline int timer_pending(const struct timer_list * timer)
 }
 
 extern void add_timer(struct timer_list * timer);
+extern void add_timer_on(struct timer_list *timer, int cpu);
 extern int del_timer(struct timer_list * timer);
 extern int mod_timer(struct timer_list *timer, unsigned long expires);