bitkeeper revision 1.1159.223.8 (41f04ee28OyElXpjo4VeyXy925falg)

Upgrade to linux 2.4.29

linux-2.4.29-xen-sparse/include/linux/blk.h

@@ -0,0 +1,409 @@
+#ifndef _BLK_H
+#define _BLK_H
+
+#include <linux/blkdev.h>
+#include <linux/locks.h>
+#include <linux/config.h>
+#include <linux/spinlock.h>
+
+/*
+ * Spinlock for protecting the request queue which
+ * is mucked around with in interrupts on potentially
+ * multiple CPU's..
+ */
+extern spinlock_t io_request_lock;
+
+/*
+ * Initialization functions.
+ */
+extern int isp16_init(void);
+extern int cdu31a_init(void);
+extern int acsi_init(void);
+extern int mcd_init(void);
+extern int mcdx_init(void);
+extern int sbpcd_init(void);
+extern int aztcd_init(void);
+extern int sony535_init(void);
+extern int gscd_init(void);
+extern int cm206_init(void);
+extern int optcd_init(void);
+extern int sjcd_init(void);
+extern int cdi_init(void);
+extern int hd_init(void);
+extern int ide_init(void);
+extern int xd_init(void);
+extern int mfm_init(void);
+extern int loop_init(void);
+extern int md_init(void);
+extern int ap_init(void);
+extern int ddv_init(void);
+extern int z2_init(void);
+extern int swim3_init(void);
+extern int swimiop_init(void);
+extern int amiga_floppy_init(void);
+extern int atari_floppy_init(void);
+extern int ez_init(void);
+extern int bpcd_init(void);
+extern int ps2esdi_init(void);
+extern int jsfd_init(void);
+extern int viodasd_init(void);
+extern int viocd_init(void);
+
+#if defined(CONFIG_ARCH_S390)
+extern int dasd_init(void);
+extern int xpram_init(void);
+extern int tapeblock_init(void);
+#endif /* CONFIG_ARCH_S390 */
+
+#if defined(CONFIG_XEN)
+extern int xlblk_init(void);
+#endif /* CONFIG_XEN */
+
+extern void set_device_ro(kdev_t dev,int flag);
+void add_blkdev_randomness(int major);
+
+extern int floppy_init(void);
+extern int rd_doload;		/* 1 = load ramdisk, 0 = don't load */
+extern int rd_prompt;		/* 1 = prompt for ramdisk, 0 = don't prompt */
+extern int rd_image_start;	/* starting block # of image */
+
+#ifdef CONFIG_BLK_DEV_INITRD
+
+#define INITRD_MINOR 250 /* shouldn't collide with /dev/ram* too soon ... */
+
+extern unsigned long initrd_start,initrd_end;
+extern int initrd_below_start_ok; /* 1 if it is not an error if initrd_start < memory_start */
+void initrd_init(void);
+
+#endif
+
+		 
+/*
+ * end_request() and friends. Must be called with the request queue spinlock
+ * acquired. All functions called within end_request() _must_be_ atomic.
+ *
+ * Several drivers define their own end_request and call
+ * end_that_request_first() and end_that_request_last()
+ * for parts of the original function. This prevents
+ * code duplication in drivers.
+ */
+
+static inline void blkdev_dequeue_request(struct request * req)
+{
+	list_del(&req->queue);
+}
+
+int end_that_request_first(struct request *req, int uptodate, char *name);
+void end_that_request_last(struct request *req);
+
+#if defined(MAJOR_NR) || defined(IDE_DRIVER)
+
+#undef DEVICE_ON
+#undef DEVICE_OFF
+
+/*
+ * Add entries as needed.
+ */
+
+#ifdef IDE_DRIVER
+
+#define DEVICE_NR(device)	(MINOR(device) >> PARTN_BITS)
+#define DEVICE_NAME "ide"
+
+#elif (MAJOR_NR == RAMDISK_MAJOR)
+
+/* ram disk */
+#define DEVICE_NAME "ramdisk"
+#define DEVICE_NR(device) (MINOR(device))
+#define DEVICE_NO_RANDOM
+
+#elif (MAJOR_NR == Z2RAM_MAJOR)
+
+/* Zorro II Ram */
+#define DEVICE_NAME "Z2RAM"
+#define DEVICE_REQUEST do_z2_request
+#define DEVICE_NR(device) (MINOR(device))
+
+#elif (MAJOR_NR == FLOPPY_MAJOR)
+
+static void floppy_off(unsigned int nr);
+
+#define DEVICE_NAME "floppy"
+#define DEVICE_INTR do_floppy
+#define DEVICE_REQUEST do_fd_request
+#define DEVICE_NR(device) ( (MINOR(device) & 3) | ((MINOR(device) & 0x80 ) >> 5 ))
+#define DEVICE_OFF(device) floppy_off(DEVICE_NR(device))
+
+#elif (MAJOR_NR == HD_MAJOR)
+
+/* Hard disk:  timeout is 6 seconds. */
+#define DEVICE_NAME "hard disk"
+#define DEVICE_INTR do_hd
+#define TIMEOUT_VALUE (6*HZ)
+#define DEVICE_REQUEST do_hd_request
+#define DEVICE_NR(device) (MINOR(device)>>6)
+
+#elif (SCSI_DISK_MAJOR(MAJOR_NR))
+
+#define DEVICE_NAME "scsidisk"
+#define TIMEOUT_VALUE (2*HZ)
+#define DEVICE_NR(device) (((MAJOR(device) & SD_MAJOR_MASK) << (8 - 4)) + (MINOR(device) >> 4))
+
+/* Kludge to use the same number for both char and block major numbers */
+#elif  (MAJOR_NR == MD_MAJOR) && defined(MD_DRIVER)
+
+#define DEVICE_NAME "Multiple devices driver"
+#define DEVICE_REQUEST do_md_request
+#define DEVICE_NR(device) (MINOR(device))
+
+#elif (MAJOR_NR == SCSI_TAPE_MAJOR)
+
+#define DEVICE_NAME "scsitape"
+#define DEVICE_INTR do_st  
+#define DEVICE_NR(device) (MINOR(device) & 0x7f)
+
+#elif (MAJOR_NR == OSST_MAJOR)
+
+#define DEVICE_NAME "onstream" 
+#define DEVICE_INTR do_osst
+#define DEVICE_NR(device) (MINOR(device) & 0x7f) 
+#define DEVICE_ON(device) 
+#define DEVICE_OFF(device) 
+
+#elif (MAJOR_NR == SCSI_CDROM_MAJOR)
+
+#define DEVICE_NAME "CD-ROM"
+#define DEVICE_NR(device) (MINOR(device))
+
+#elif (MAJOR_NR == XT_DISK_MAJOR)
+
+#define DEVICE_NAME "xt disk"
+#define DEVICE_REQUEST do_xd_request
+#define DEVICE_NR(device) (MINOR(device) >> 6)
+
+#elif (MAJOR_NR == PS2ESDI_MAJOR)
+
+#define DEVICE_NAME "PS/2 ESDI"
+#define DEVICE_REQUEST do_ps2esdi_request
+#define DEVICE_NR(device) (MINOR(device) >> 6)
+
+#elif (MAJOR_NR == CDU31A_CDROM_MAJOR)
+
+#define DEVICE_NAME "CDU31A"
+#define DEVICE_REQUEST do_cdu31a_request
+#define DEVICE_NR(device) (MINOR(device))
+
+#elif (MAJOR_NR == ACSI_MAJOR) && (defined(CONFIG_ATARI_ACSI) || defined(CONFIG_ATARI_ACSI_MODULE))
+
+#define DEVICE_NAME "ACSI"
+#define DEVICE_INTR do_acsi
+#define DEVICE_REQUEST do_acsi_request
+#define DEVICE_NR(device) (MINOR(device) >> 4)
+
+#elif (MAJOR_NR == MITSUMI_CDROM_MAJOR)
+
+#define DEVICE_NAME "Mitsumi CD-ROM"
+/* #define DEVICE_INTR do_mcd */
+#define DEVICE_REQUEST do_mcd_request
+#define DEVICE_NR(device) (MINOR(device))
+
+#elif (MAJOR_NR == MITSUMI_X_CDROM_MAJOR)
+
+#define DEVICE_NAME "Mitsumi CD-ROM"
+/* #define DEVICE_INTR do_mcdx */
+#define DEVICE_REQUEST do_mcdx_request
+#define DEVICE_NR(device) (MINOR(device))
+
+#elif (MAJOR_NR == MATSUSHITA_CDROM_MAJOR)
+
+#define DEVICE_NAME "Matsushita CD-ROM controller #1"
+#define DEVICE_REQUEST do_sbpcd_request
+#define DEVICE_NR(device) (MINOR(device))
+
+#elif (MAJOR_NR == MATSUSHITA_CDROM2_MAJOR)
+
+#define DEVICE_NAME "Matsushita CD-ROM controller #2"
+#define DEVICE_REQUEST do_sbpcd2_request
+#define DEVICE_NR(device) (MINOR(device))
+
+#elif (MAJOR_NR == MATSUSHITA_CDROM3_MAJOR)
+
+#define DEVICE_NAME "Matsushita CD-ROM controller #3"
+#define DEVICE_REQUEST do_sbpcd3_request
+#define DEVICE_NR(device) (MINOR(device))
+
+#elif (MAJOR_NR == MATSUSHITA_CDROM4_MAJOR)
+
+#define DEVICE_NAME "Matsushita CD-ROM controller #4"
+#define DEVICE_REQUEST do_sbpcd4_request
+#define DEVICE_NR(device) (MINOR(device))
+
+#elif (MAJOR_NR == AZTECH_CDROM_MAJOR)
+
+#define DEVICE_NAME "Aztech CD-ROM"
+#define DEVICE_REQUEST do_aztcd_request
+#define DEVICE_NR(device) (MINOR(device))
+
+#elif (MAJOR_NR == CDU535_CDROM_MAJOR)
+
+#define DEVICE_NAME "SONY-CDU535"
+#define DEVICE_INTR do_cdu535
+#define DEVICE_REQUEST do_cdu535_request
+#define DEVICE_NR(device) (MINOR(device))
+
+#elif (MAJOR_NR == GOLDSTAR_CDROM_MAJOR)
+
+#define DEVICE_NAME "Goldstar R420"
+#define DEVICE_REQUEST do_gscd_request
+#define DEVICE_NR(device) (MINOR(device))
+
+#elif (MAJOR_NR == CM206_CDROM_MAJOR)
+#define DEVICE_NAME "Philips/LMS CD-ROM cm206"
+#define DEVICE_REQUEST do_cm206_request
+#define DEVICE_NR(device) (MINOR(device))
+
+#elif (MAJOR_NR == OPTICS_CDROM_MAJOR)
+
+#define DEVICE_NAME "DOLPHIN 8000AT CD-ROM"
+#define DEVICE_REQUEST do_optcd_request
+#define DEVICE_NR(device) (MINOR(device))
+
+#elif (MAJOR_NR == SANYO_CDROM_MAJOR)
+
+#define DEVICE_NAME "Sanyo H94A CD-ROM"
+#define DEVICE_REQUEST do_sjcd_request
+#define DEVICE_NR(device) (MINOR(device))
+
+#elif (MAJOR_NR == APBLOCK_MAJOR)
+
+#define DEVICE_NAME "apblock"
+#define DEVICE_REQUEST ap_request
+#define DEVICE_NR(device) (MINOR(device))
+
+#elif (MAJOR_NR == DDV_MAJOR)
+
+#define DEVICE_NAME "ddv"
+#define DEVICE_REQUEST ddv_request
+#define DEVICE_NR(device) (MINOR(device)>>PARTN_BITS)
+
+#elif (MAJOR_NR == MFM_ACORN_MAJOR)
+
+#define DEVICE_NAME "mfm disk"
+#define DEVICE_INTR do_mfm
+#define DEVICE_REQUEST do_mfm_request
+#define DEVICE_NR(device) (MINOR(device) >> 6)
+
+#elif (MAJOR_NR == NBD_MAJOR)
+
+#define DEVICE_NAME "nbd"
+#define DEVICE_REQUEST do_nbd_request
+#define DEVICE_NR(device) (MINOR(device))
+
+#elif (MAJOR_NR == MDISK_MAJOR)
+
+#define DEVICE_NAME "mdisk"
+#define DEVICE_REQUEST mdisk_request
+#define DEVICE_NR(device) (MINOR(device))
+
+#elif (MAJOR_NR == DASD_MAJOR)
+
+#define DEVICE_NAME "dasd"
+#define DEVICE_REQUEST do_dasd_request
+#define DEVICE_NR(device) (MINOR(device) >> PARTN_BITS)
+
+#elif (MAJOR_NR == I2O_MAJOR)
+
+#define DEVICE_NAME "I2O block"
+#define DEVICE_REQUEST i2ob_request
+#define DEVICE_NR(device) (MINOR(device)>>4)
+
+#elif (MAJOR_NR == COMPAQ_SMART2_MAJOR)
+
+#define DEVICE_NAME "ida"
+#define TIMEOUT_VALUE (25*HZ)
+#define DEVICE_REQUEST do_ida_request
+#define DEVICE_NR(device) (MINOR(device) >> 4)
+
+#endif /* MAJOR_NR == whatever */
+
+/* provide DEVICE_xxx defaults, if not explicitly defined
+ * above in the MAJOR_NR==xxx if-elif tree */
+#ifndef DEVICE_ON
+#define DEVICE_ON(device) do {} while (0)
+#endif
+#ifndef DEVICE_OFF
+#define DEVICE_OFF(device) do {} while (0)
+#endif
+
+#if (MAJOR_NR != SCSI_TAPE_MAJOR) && (MAJOR_NR != OSST_MAJOR)
+#if !defined(IDE_DRIVER)
+
+#ifndef CURRENT
+#define CURRENT blkdev_entry_next_request(&blk_dev[MAJOR_NR].request_queue.queue_head)
+#endif
+#ifndef QUEUE_EMPTY
+#define QUEUE_EMPTY list_empty(&blk_dev[MAJOR_NR].request_queue.queue_head)
+#endif
+
+#ifndef DEVICE_NAME
+#define DEVICE_NAME "unknown"
+#endif
+
+#define CURRENT_DEV DEVICE_NR(CURRENT->rq_dev)
+
+#ifdef DEVICE_INTR
+static void (*DEVICE_INTR)(void) = NULL;
+#endif
+
+#define SET_INTR(x) (DEVICE_INTR = (x))
+
+#ifdef DEVICE_REQUEST
+static void (DEVICE_REQUEST)(request_queue_t *);
+#endif 
+  
+#ifdef DEVICE_INTR
+#define CLEAR_INTR SET_INTR(NULL)
+#else
+#define CLEAR_INTR
+#endif
+
+#define INIT_REQUEST \
+	if (QUEUE_EMPTY) {\
+		CLEAR_INTR; \
+		return; \
+	} \
+	if (MAJOR(CURRENT->rq_dev) != MAJOR_NR) \
+		panic(DEVICE_NAME ": request list destroyed"); \
+	if (CURRENT->bh) { \
+		if (!buffer_locked(CURRENT->bh)) \
+			panic(DEVICE_NAME ": block not locked"); \
+	}
+
+#endif /* !defined(IDE_DRIVER) */
+
+
+#ifndef LOCAL_END_REQUEST	/* If we have our own end_request, we do not want to include this mess */
+
+#if ! SCSI_BLK_MAJOR(MAJOR_NR) && (MAJOR_NR != COMPAQ_SMART2_MAJOR)
+
+static inline void end_request(int uptodate) {
+	struct request *req = CURRENT;
+
+	if (end_that_request_first(req, uptodate, DEVICE_NAME))
+		return;
+
+#ifndef DEVICE_NO_RANDOM
+	add_blkdev_randomness(MAJOR(req->rq_dev));
+#endif
+	DEVICE_OFF(req->rq_dev);
+	blkdev_dequeue_request(req);
+	end_that_request_last(req);
+}
+
+#endif /* ! SCSI_BLK_MAJOR(MAJOR_NR) */
+#endif /* LOCAL_END_REQUEST */
+
+#endif /* (MAJOR_NR != SCSI_TAPE_MAJOR) */
+#endif /* defined(MAJOR_NR) || defined(IDE_DRIVER) */
+
+#endif /* _BLK_H */

linux-2.4.29-xen-sparse/include/linux/irq.h

@@ -0,0 +1,80 @@
+#ifndef __irq_h
+#define __irq_h
+
+/*
+ * Please do not include this file in generic code.  There is currently
+ * no requirement for any architecture to implement anything held
+ * within this file.
+ *
+ * Thanks. --rmk
+ */
+
+#include <linux/config.h>
+
+#if !defined(CONFIG_ARCH_S390)
+
+#include <linux/cache.h>
+#include <linux/spinlock.h>
+
+#include <asm/irq.h>
+#include <asm/ptrace.h>
+
+/*
+ * IRQ line status.
+ */
+#define IRQ_INPROGRESS	1	/* IRQ handler active - do not enter! */
+#define IRQ_DISABLED	2	/* IRQ disabled - do not enter! */
+#define IRQ_PENDING	4	/* IRQ pending - replay on enable */
+#define IRQ_REPLAY	8	/* IRQ has been replayed but not acked yet */
+#define IRQ_AUTODETECT	16	/* IRQ is being autodetected */
+#define IRQ_WAITING	32	/* IRQ not yet seen - for autodetection */
+#define IRQ_LEVEL	64	/* IRQ level triggered */
+#define IRQ_MASKED	128	/* IRQ masked - shouldn't be seen again */
+#define IRQ_PER_CPU	256	/* IRQ is per CPU */
+
+/*
+ * Interrupt controller descriptor. This is all we need
+ * to describe about the low-level hardware. 
+ */
+struct hw_interrupt_type {
+	const char * typename;
+	unsigned int (*startup)(unsigned int irq);
+	void (*shutdown)(unsigned int irq);
+	void (*enable)(unsigned int irq);
+	void (*disable)(unsigned int irq);
+	void (*ack)(unsigned int irq);
+	void (*end)(unsigned int irq);
+	void (*set_affinity)(unsigned int irq, unsigned long mask);
+};
+
+typedef struct hw_interrupt_type  hw_irq_controller;
+
+/*
+ * This is the "IRQ descriptor", which contains various information
+ * about the irq, including what kind of hardware handling it has,
+ * whether it is disabled etc etc.
+ *
+ * Pad this out to 32 bytes for cache and indexing reasons.
+ */
+typedef struct {
+	unsigned int status;		/* IRQ status */
+	hw_irq_controller *handler;
+	struct irqaction *action;	/* IRQ action list */
+	unsigned int depth;		/* nested irq disables */
+	spinlock_t lock;
+} ____cacheline_aligned irq_desc_t;
+
+extern irq_desc_t irq_desc [NR_IRQS];
+
+#include <asm/hw_irq.h> /* the arch dependent stuff */
+
+extern int handle_IRQ_event(unsigned int, struct pt_regs *, struct irqaction *);
+extern int setup_irq(unsigned int , struct irqaction * );
+extern int teardown_irq(unsigned int , struct irqaction * );
+
+extern hw_irq_controller no_irq_type;  /* needed in every arch ? */
+extern void no_action(int cpl, void *dev_id, struct pt_regs *regs);
+
+#endif
+
+#endif /* __irq_h */

linux-2.4.29-xen-sparse/include/linux/mm.h

@@ -0,0 +1,727 @@
+#ifndef _LINUX_MM_H
+#define _LINUX_MM_H
+
+#include <linux/sched.h>
+#include <linux/errno.h>
+
+#ifdef __KERNEL__
+
+#include <linux/config.h>
+#include <linux/string.h>
+#include <linux/list.h>
+#include <linux/mmzone.h>
+#include <linux/swap.h>
+#include <linux/rbtree.h>
+
+extern unsigned long max_mapnr;
+extern unsigned long num_physpages;
+extern unsigned long num_mappedpages;
+extern void * high_memory;
+extern int page_cluster;
+/* The inactive_clean lists are per zone. */
+extern struct list_head active_list;
+extern struct list_head inactive_list;
+
+#include <asm/page.h>
+#include <asm/pgtable.h>
+#include <asm/atomic.h>
+
+/*
+ * Linux kernel virtual memory manager primitives.
+ * The idea being to have a "virtual" mm in the same way
+ * we have a virtual fs - giving a cleaner interface to the
+ * mm details, and allowing different kinds of memory mappings
+ * (from shared memory to executable loading to arbitrary
+ * mmap() functions).
+ */
+
+/*
+ * This struct defines a memory VMM memory area. There is one of these
+ * per VM-area/task.  A VM area is any part of the process virtual memory
+ * space that has a special rule for the page-fault handlers (ie a shared
+ * library, the executable area etc).
+ */
+struct vm_area_struct {
+	struct mm_struct * vm_mm;	/* The address space we belong to. */
+	unsigned long vm_start;		/* Our start address within vm_mm. */
+	unsigned long vm_end;		/* The first byte after our end address
+					   within vm_mm. */
+
+	/* linked list of VM areas per task, sorted by address */
+	struct vm_area_struct *vm_next;
+
+	pgprot_t vm_page_prot;		/* Access permissions of this VMA. */
+	unsigned long vm_flags;		/* Flags, listed below. */
+
+	rb_node_t vm_rb;
+
+	/*
+	 * For areas with an address space and backing store,
+	 * one of the address_space->i_mmap{,shared} lists,
+	 * for shm areas, the list of attaches, otherwise unused.
+	 */
+	struct vm_area_struct *vm_next_share;
+	struct vm_area_struct **vm_pprev_share;
+
+	/* Function pointers to deal with this struct. */
+	struct vm_operations_struct * vm_ops;
+
+	/* Information about our backing store: */
+	unsigned long vm_pgoff;		/* Offset (within vm_file) in PAGE_SIZE
+					   units, *not* PAGE_CACHE_SIZE */
+	struct file * vm_file;		/* File we map to (can be NULL). */
+	unsigned long vm_raend;		/* XXX: put full readahead info here. */
+	void * vm_private_data;		/* was vm_pte (shared mem) */
+};
+
+/*
+ * vm_flags..
+ */
+#define VM_READ		0x00000001	/* currently active flags */
+#define VM_WRITE	0x00000002
+#define VM_EXEC		0x00000004
+#define VM_SHARED	0x00000008
+
+#define VM_MAYREAD	0x00000010	/* limits for mprotect() etc */
+#define VM_MAYWRITE	0x00000020
+#define VM_MAYEXEC	0x00000040
+#define VM_MAYSHARE	0x00000080
+
+#define VM_GROWSDOWN	0x00000100	/* general info on the segment */
+#define VM_GROWSUP	0x00000200
+#define VM_SHM		0x00000400	/* shared memory area, don't swap out */
+#define VM_DENYWRITE	0x00000800	/* ETXTBSY on write attempts.. */
+
+#define VM_EXECUTABLE	0x00001000
+#define VM_LOCKED	0x00002000
+#define VM_IO           0x00004000	/* Memory mapped I/O or similar */
+
+					/* Used by sys_madvise() */
+#define VM_SEQ_READ	0x00008000	/* App will access data sequentially */
+#define VM_RAND_READ	0x00010000	/* App will not benefit from clustered reads */
+
+#define VM_DONTCOPY	0x00020000      /* Do not copy this vma on fork */
+#define VM_DONTEXPAND	0x00040000	/* Cannot expand with mremap() */
+#define VM_RESERVED	0x00080000	/* Don't unmap it from swap_out */
+
+#ifndef VM_STACK_FLAGS
+#define VM_STACK_FLAGS	0x00000177
+#endif
+
+#define VM_READHINTMASK			(VM_SEQ_READ | VM_RAND_READ)
+#define VM_ClearReadHint(v)		(v)->vm_flags &= ~VM_READHINTMASK
+#define VM_NormalReadHint(v)		(!((v)->vm_flags & VM_READHINTMASK))
+#define VM_SequentialReadHint(v)	((v)->vm_flags & VM_SEQ_READ)
+#define VM_RandomReadHint(v)		((v)->vm_flags & VM_RAND_READ)
+
+/* read ahead limits */
+extern int vm_min_readahead;
+extern int vm_max_readahead;
+
+/*
+ * mapping from the currently active vm_flags protection bits (the
+ * low four bits) to a page protection mask..
+ */
+extern pgprot_t protection_map[16];
+
+
+/*
+ * These are the virtual MM functions - opening of an area, closing and
+ * unmapping it (needed to keep files on disk up-to-date etc), pointer
+ * to the functions called when a no-page or a wp-page exception occurs. 
+ */
+struct vm_operations_struct {
+	void (*open)(struct vm_area_struct * area);
+	void (*close)(struct vm_area_struct * area);
+	struct page * (*nopage)(struct vm_area_struct * area, unsigned long address, int unused);
+};
+
+/*
+ * 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.
+ *
+ * Try to keep the most commonly accessed fields in single cache lines
+ * here (16 bytes or greater).  This ordering should be particularly
+ * beneficial on 32-bit processors.
+ *
+ * The first line is data used in page cache lookup, the second line
+ * is used for linear searches (eg. clock algorithm scans). 
+ *
+ * TODO: make this structure smaller, it could be as small as 32 bytes.
+ */
+typedef struct page {
+	struct list_head list;		/* ->mapping has some page lists. */
+	struct address_space *mapping;	/* The inode (or ...) we belong to. */
+	unsigned long index;		/* Our offset within mapping. */
+	struct page *next_hash;		/* Next page sharing our hash bucket in
+					   the pagecache hash table. */
+	atomic_t count;			/* Usage count, see below. */
+	unsigned long flags;		/* atomic flags, some possibly
+					   updated asynchronously */
+	struct list_head lru;		/* Pageout list, eg. active_list;
+					   protected by pagemap_lru_lock !! */
+	struct page **pprev_hash;	/* Complement to *next_hash. */
+	struct buffer_head * buffers;	/* Buffer maps us to a disk block. */
+
+	/*
+	 * On machines where all RAM is mapped into kernel address space,
+	 * we can simply calculate the virtual address. On machines with
+	 * highmem some memory is mapped into kernel virtual memory
+	 * dynamically, so we need a place to store that address.
+	 * Note that this field could be 16 bits on x86 ... ;)
+	 *
+	 * Architectures with slow multiplication can define
+	 * WANT_PAGE_VIRTUAL in asm/page.h
+	 */
+#if defined(CONFIG_HIGHMEM) || defined(WANT_PAGE_VIRTUAL)
+	void *virtual;			/* Kernel virtual address (NULL if
+					   not kmapped, ie. highmem) */
+#endif /* CONFIG_HIGMEM || WANT_PAGE_VIRTUAL */
+} mem_map_t;
+
+/*
+ * Methods to modify the page usage count.
+ *
+ * What counts for a page usage:
+ * - cache mapping   (page->mapping)
+ * - disk mapping    (page->buffers)
+ * - page mapped in a task's page tables, each mapping
+ *   is counted separately
+ *
+ * Also, many kernel routines increase the page count before a critical
+ * routine so they can be sure the page doesn't go away from under them.
+ */
+#define get_page(p)		atomic_inc(&(p)->count)
+#define put_page(p)		__free_page(p)
+#define put_page_testzero(p) 	atomic_dec_and_test(&(p)->count)
+#define page_count(p)		atomic_read(&(p)->count)
+#define set_page_count(p,v) 	atomic_set(&(p)->count, v)
+
+static inline struct page *nth_page(struct page *page, int n)
+{
+	return page + n;
+}
+
+/*
+ * Various page->flags bits:
+ *
+ * PG_reserved is set for special pages, which can never be swapped
+ * out. Some of them might not even exist (eg empty_bad_page)...
+ *
+ * Multiple processes may "see" the same page. E.g. for untouched
+ * mappings of /dev/null, all processes see the same page full of
+ * zeroes, and text pages of executables and shared libraries have
+ * only one copy in memory, at most, normally.
+ *
+ * For the non-reserved pages, page->count denotes a reference count.
+ *   page->count == 0 means the page is free.
+ *   page->count == 1 means the page is used for exactly one purpose
+ *   (e.g. a private data page of one process).
+ *
+ * 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.
+ *
+ * The other pages (we may call them "process 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 page may have buffers allocated to it. In this case,
+ * page->buffers is a circular list of these buffer heads. Else,
+ * page->buffers == NULL.
+ *
+ * For pages belonging to inodes, the page->count is the number of
+ * attaches, plus 1 if buffers are allocated to the page, plus one
+ * for the page cache itself.
+ *
+ * All pages belonging to an inode are in these doubly linked lists:
+ * mapping->clean_pages, mapping->dirty_pages and mapping->locked_pages;
+ * using the page->list list_head. These fields are also used for
+ * freelist managemet (when page->count==0).
+ *
+ * There is also a hash table mapping (mapping,index) to the page
+ * in memory if present. The lists for this hash table use the fields
+ * page->next_hash and page->pprev_hash.
+ *
+ * All process pages can do 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.
+ * 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.
+ * 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 pagemap_lru_lock, and *NOT* by the usual PG_locked bit!
+ *
+ * PG_skip is used on sparc/sparc64 architectures to "skip" certain
+ * parts of the address space.
+ *
+ * PG_error is set to indicate that an I/O error occurred on this page.
+ *
+ * PG_arch_1 is an architecture specific page state bit.  The generic
+ * code guarantees that this bit is cleared for a page when it first
+ * is entered into the page cache.
+ *
+ * PG_highmem pages are not permanently mapped into the kernel virtual
+ * address 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...
+ */
+#define PG_locked		 0	/* Page is locked. Don't touch. */
+#define PG_error		 1
+#define PG_referenced		 2
+#define PG_uptodate		 3
+#define PG_dirty		 4
+#define PG_unused		 5
+#define PG_lru			 6
+#define PG_active		 7
+#define PG_slab			 8
+#define PG_skip			10
+#define PG_highmem		11
+#define PG_checked		12	/* kill me in 2.5.<early>. */
+#define PG_arch_1		13
+#define PG_reserved		14
+#define PG_launder		15	/* written out by VM pressure.. */
+#define PG_fs_1			16	/* Filesystem specific */
+#define PG_foreign		21	/* Page belongs to foreign allocator */
+
+#ifndef arch_set_page_uptodate
+#define arch_set_page_uptodate(page)
+#endif
+
+/* Make it prettier to test the above... */
+#define UnlockPage(page)	unlock_page(page)
+#define Page_Uptodate(page)	test_bit(PG_uptodate, &(page)->flags)
+#ifndef SetPageUptodate
+#define SetPageUptodate(page)	set_bit(PG_uptodate, &(page)->flags)
+#endif
+#define ClearPageUptodate(page)	clear_bit(PG_uptodate, &(page)->flags)
+#define PageDirty(page)		test_bit(PG_dirty, &(page)->flags)
+#define SetPageDirty(page)	set_bit(PG_dirty, &(page)->flags)
+#define ClearPageDirty(page)	clear_bit(PG_dirty, &(page)->flags)
+#define PageLocked(page)	test_bit(PG_locked, &(page)->flags)
+#define LockPage(page)		set_bit(PG_locked, &(page)->flags)
+#define TryLockPage(page)	test_and_set_bit(PG_locked, &(page)->flags)
+#define PageChecked(page)	test_bit(PG_checked, &(page)->flags)
+#define SetPageChecked(page)	set_bit(PG_checked, &(page)->flags)
+#define ClearPageChecked(page)	clear_bit(PG_checked, &(page)->flags)
+#define PageLaunder(page)	test_bit(PG_launder, &(page)->flags)
+#define SetPageLaunder(page)	set_bit(PG_launder, &(page)->flags)
+#define ClearPageLaunder(page)	clear_bit(PG_launder, &(page)->flags)
+#define ClearPageArch1(page)	clear_bit(PG_arch_1, &(page)->flags)
+
+/* A foreign page uses a custom destructor rather than the buddy allocator. */
+#ifdef CONFIG_FOREIGN_PAGES
+#define PageForeign(page)	test_bit(PG_foreign, &(page)->flags)
+#define SetPageForeign(page, dtor) do {		\
+	set_bit(PG_foreign, &(page)->flags);	\
+	(page)->mapping = (void *)dtor;		\
+} while (0)
+#define ClearPageForeign(page) do {		\
+	clear_bit(PG_foreign, &(page)->flags);	\
+	(page)->mapping = NULL;			\
+} while (0)
+#define PageForeignDestructor(page)	\
+	( (void (*) (struct page *)) (page)->mapping )
+#else
+#define PageForeign(page)	0
+#define PageForeignDestructor(page)	void
+#endif
+
+/*
+ * The zone field is never updated after free_area_init_core()
+ * sets it, so none of the operations on it need to be atomic.
+ */
+#define NODE_SHIFT 4
+#define ZONE_SHIFT (BITS_PER_LONG - 8)
+
+struct zone_struct;
+extern struct zone_struct *zone_table[];
+
+static inline zone_t *page_zone(struct page *page)
+{
+	return zone_table[page->flags >> ZONE_SHIFT];
+}
+
+static inline void set_page_zone(struct page *page, unsigned long zone_num)
+{
+	page->flags &= ~(~0UL << ZONE_SHIFT);
+	page->flags |= zone_num << ZONE_SHIFT;
+}
+
+/*
+ * In order to avoid #ifdefs within C code itself, we define
+ * set_page_address to a noop for non-highmem machines, where
+ * the field isn't useful.
+ * The same is true for page_address() in arch-dependent code.
+ */
+#if defined(CONFIG_HIGHMEM) || defined(WANT_PAGE_VIRTUAL)
+
+#define set_page_address(page, address)			\
+	do {						\
+		(page)->virtual = (address);		\
+	} while(0)
+
+#else /* CONFIG_HIGHMEM || WANT_PAGE_VIRTUAL */
+#define set_page_address(page, address)  do { } while(0)
+#endif /* CONFIG_HIGHMEM || WANT_PAGE_VIRTUAL */
+
+/*
+ * Permanent address of a page. Obviously must never be
+ * called on a highmem page.
+ */
+#if defined(CONFIG_HIGHMEM) || defined(WANT_PAGE_VIRTUAL)
+
+#define page_address(page) ((page)->virtual)
+
+#else /* CONFIG_HIGHMEM || WANT_PAGE_VIRTUAL */
+
+#define page_address(page)						\
+	__va( (((page) - page_zone(page)->zone_mem_map) << PAGE_SHIFT)	\
+			+ page_zone(page)->zone_start_paddr)
+
+#endif /* CONFIG_HIGHMEM || WANT_PAGE_VIRTUAL */
+
+extern void FASTCALL(set_page_dirty(struct page *));
+
+/*
+ * The first mb is necessary to safely close the critical section opened by the
+ * TryLockPage(), the second mb is necessary to enforce ordering between
+ * the clear_bit and the read of the waitqueue (to avoid SMP races with a
+ * parallel wait_on_page).
+ */
+#define PageError(page)		test_bit(PG_error, &(page)->flags)
+#define SetPageError(page)	set_bit(PG_error, &(page)->flags)
+#define ClearPageError(page)	clear_bit(PG_error, &(page)->flags)
+#define PageReferenced(page)	test_bit(PG_referenced, &(page)->flags)
+#define SetPageReferenced(page)	set_bit(PG_referenced, &(page)->flags)
+#define ClearPageReferenced(page)	clear_bit(PG_referenced, &(page)->flags)
+#define PageTestandClearReferenced(page)	test_and_clear_bit(PG_referenced, &(page)->flags)
+#define PageSlab(page)		test_bit(PG_slab, &(page)->flags)
+#define PageSetSlab(page)	set_bit(PG_slab, &(page)->flags)
+#define PageClearSlab(page)	clear_bit(PG_slab, &(page)->flags)
+#define PageReserved(page)	test_bit(PG_reserved, &(page)->flags)
+
+#define PageActive(page)	test_bit(PG_active, &(page)->flags)
+#define SetPageActive(page)	set_bit(PG_active, &(page)->flags)
+#define ClearPageActive(page)	clear_bit(PG_active, &(page)->flags)
+
+#define PageLRU(page)		test_bit(PG_lru, &(page)->flags)
+#define TestSetPageLRU(page)	test_and_set_bit(PG_lru, &(page)->flags)
+#define TestClearPageLRU(page)	test_and_clear_bit(PG_lru, &(page)->flags)
+
+#ifdef CONFIG_HIGHMEM
+#define PageHighMem(page)		test_bit(PG_highmem, &(page)->flags)
+#else
+#define PageHighMem(page)		0 /* needed to optimize away at compile time */
+#endif
+
+#define SetPageReserved(page)		set_bit(PG_reserved, &(page)->flags)
+#define ClearPageReserved(page)		clear_bit(PG_reserved, &(page)->flags)
+
+/*
+ * Error return values for the *_nopage functions
+ */
+#define NOPAGE_SIGBUS	(NULL)
+#define NOPAGE_OOM	((struct page *) (-1))
+
+/* The array of struct pages */
+extern mem_map_t * mem_map;
+
+/*
+ * There is only one page-allocator function, and two main namespaces to
+ * it. The alloc_page*() variants return 'struct page *' and as such
+ * can allocate highmem pages, the *get*page*() variants return
+ * virtual kernel addresses to the allocated page(s).
+ */
+extern struct page * FASTCALL(_alloc_pages(unsigned int gfp_mask, unsigned int order));
+extern struct page * FASTCALL(__alloc_pages(unsigned int gfp_mask, unsigned int order, zonelist_t *zonelist));
+extern struct page * alloc_pages_node(int nid, unsigned int gfp_mask, unsigned int order);
+
+static inline struct page * alloc_pages(unsigned int gfp_mask, unsigned int order)
+{
+	/*
+	 * Gets optimized away by the compiler.
+	 */
+	if (order >= MAX_ORDER)
+		return NULL;
+	return _alloc_pages(gfp_mask, order);
+}
+
+#define alloc_page(gfp_mask) alloc_pages(gfp_mask, 0)
+
+extern unsigned long FASTCALL(__get_free_pages(unsigned int gfp_mask, unsigned int order));
+extern unsigned long FASTCALL(get_zeroed_page(unsigned int gfp_mask));
+
+#define __get_free_page(gfp_mask) \
+		__get_free_pages((gfp_mask),0)
+
+#define __get_dma_pages(gfp_mask, order) \
+		__get_free_pages((gfp_mask) | GFP_DMA,(order))
+
+/*
+ * The old interface name will be removed in 2.5:
+ */
+#define get_free_page get_zeroed_page
+
+/*
+ * 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));
+
+#define __free_page(page) __free_pages((page), 0)
+#define free_page(addr) free_pages((addr),0)
+
+extern void show_free_areas(void);
+extern void show_free_areas_node(pg_data_t *pgdat);
+
+extern void clear_page_tables(struct mm_struct *, unsigned long, int);
+
+extern int fail_writepage(struct page *);
+struct page * shmem_nopage(struct vm_area_struct * vma, unsigned long address, int unused);
+struct file *shmem_file_setup(char * name, loff_t size);
+extern void shmem_lock(struct file * file, int lock);
+extern int shmem_zero_setup(struct vm_area_struct *);
+
+extern void zap_page_range(struct mm_struct *mm, unsigned long address, unsigned long size);
+extern int copy_page_range(struct mm_struct *dst, struct mm_struct *src, struct vm_area_struct *vma);
+extern int remap_page_range(unsigned long from, unsigned long to, unsigned long size, pgprot_t prot);
+extern int zeromap_page_range(unsigned long from, unsigned long size, pgprot_t prot);
+
+extern int vmtruncate(struct inode * inode, loff_t offset);
+extern pmd_t *FASTCALL(__pmd_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long address));
+extern pte_t *FASTCALL(pte_alloc(struct mm_struct *mm, pmd_t *pmd, unsigned long address));
+extern int handle_mm_fault(struct mm_struct *mm,struct vm_area_struct *vma, unsigned long address, int write_access);
+extern int make_pages_present(unsigned long addr, unsigned long end);
+extern int access_process_vm(struct task_struct *tsk, unsigned long addr, void *buf, int len, int write);
+extern int ptrace_readdata(struct task_struct *tsk, unsigned long src, char *dst, int len);
+extern int ptrace_writedata(struct task_struct *tsk, char * src, unsigned long dst, int len);
+extern int ptrace_attach(struct task_struct *tsk);
+extern int ptrace_detach(struct task_struct *, unsigned int);
+extern void ptrace_disable(struct task_struct *);
+extern int ptrace_check_attach(struct task_struct *task, int kill);
+
+int get_user_pages(struct task_struct *tsk, struct mm_struct *mm, unsigned long start,
+		int len, int write, int force, struct page **pages, struct vm_area_struct **vmas);
+
+/*
+ * On a two-level page table, this ends up being trivial. Thus the
+ * inlining and the symmetry break with pte_alloc() that does all
+ * of this out-of-line.
+ */
+static inline pmd_t *pmd_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long address)
+{
+	if (pgd_none(*pgd))
+		return __pmd_alloc(mm, pgd, address);
+	return pmd_offset(pgd, address);
+}
+
+extern int pgt_cache_water[2];
+extern int check_pgt_cache(void);
+
+extern void free_area_init(unsigned long * zones_size);
+extern void free_area_init_node(int nid, pg_data_t *pgdat, struct page *pmap,
+	unsigned long * zones_size, unsigned long zone_start_paddr, 
+	unsigned long *zholes_size);
+extern void mem_init(void);
+extern void show_mem(void);
+extern void si_meminfo(struct sysinfo * val);
+extern void swapin_readahead(swp_entry_t);
+
+extern struct address_space swapper_space;
+#define PageSwapCache(page) ((page)->mapping == &swapper_space)
+
+static inline int is_page_cache_freeable(struct page * page)
+{
+	return page_count(page) - !!page->buffers == 1;
+}
+
+extern int FASTCALL(can_share_swap_page(struct page *));
+extern int FASTCALL(remove_exclusive_swap_page(struct page *));
+
+extern void __free_pte(pte_t);
+
+/* mmap.c */
+extern void lock_vma_mappings(struct vm_area_struct *);
+extern void unlock_vma_mappings(struct vm_area_struct *);
+extern int insert_vm_struct(struct mm_struct *, struct vm_area_struct *);
+extern void __insert_vm_struct(struct mm_struct *, struct vm_area_struct *);
+extern void build_mmap_rb(struct mm_struct *);
+extern void exit_mmap(struct mm_struct *);
+
+extern unsigned long get_unmapped_area(struct file *, unsigned long, unsigned long, unsigned long, unsigned long);
+
+extern unsigned long do_mmap_pgoff(struct file *file, unsigned long addr,
+	unsigned long len, unsigned long prot,
+	unsigned long flag, unsigned long pgoff);
+
+static inline unsigned long do_mmap(struct file *file, unsigned long addr,
+	unsigned long len, unsigned long prot,
+	unsigned long flag, unsigned long offset)
+{
+	unsigned long ret = -EINVAL;
+	if ((offset + PAGE_ALIGN(len)) < offset)
+		goto out;
+	if (!(offset & ~PAGE_MASK))
+		ret = do_mmap_pgoff(file, addr, len, prot, flag, offset >> PAGE_SHIFT);
+out:
+	return ret;
+}
+
+extern int do_munmap(struct mm_struct *, unsigned long, size_t);
+
+extern unsigned long do_brk(unsigned long, unsigned long);
+
+static inline void __vma_unlink(struct mm_struct * mm, struct vm_area_struct * vma, struct vm_area_struct * prev)
+{
+	prev->vm_next = vma->vm_next;
+	rb_erase(&vma->vm_rb, &mm->mm_rb);
+	if (mm->mmap_cache == vma)
+		mm->mmap_cache = prev;
+}
+
+static inline int can_vma_merge(struct vm_area_struct * vma, unsigned long vm_flags)
+{
+	if (!vma->vm_file && vma->vm_flags == vm_flags)
+		return 1;
+	else
+		return 0;
+}
+
+struct zone_t;
+/* filemap.c */
+extern void remove_inode_page(struct page *);
+extern unsigned long page_unuse(struct page *);
+extern void truncate_inode_pages(struct address_space *, loff_t);
+
+/* generic vm_area_ops exported for stackable file systems */
+extern int filemap_sync(struct vm_area_struct *, unsigned long,	size_t, unsigned int);
+extern struct page *filemap_nopage(struct vm_area_struct *, unsigned long, int);
+
+/*
+ * GFP bitmasks..
+ */
+/* Zone modifiers in GFP_ZONEMASK (see linux/mmzone.h - low four bits) */
+#define __GFP_DMA	0x01
+#define __GFP_HIGHMEM	0x02
+
+/* Action modifiers - doesn't change the zoning */
+#define __GFP_WAIT	0x10	/* Can wait and reschedule? */
+#define __GFP_HIGH	0x20	/* Should access emergency pools? */
+#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_NOHIGHIO	(__GFP_HIGH | __GFP_WAIT | __GFP_IO)
+#define GFP_NOIO	(__GFP_HIGH | __GFP_WAIT)
+#define GFP_NOFS	(__GFP_HIGH | __GFP_WAIT | __GFP_IO | __GFP_HIGHIO)
+#define GFP_ATOMIC	(__GFP_HIGH)
+#define GFP_USER	(             __GFP_WAIT | __GFP_IO | __GFP_HIGHIO | __GFP_FS)
+#define GFP_HIGHUSER	(             __GFP_WAIT | __GFP_IO | __GFP_HIGHIO | __GFP_FS | __GFP_HIGHMEM)
+#define GFP_KERNEL	(__GFP_HIGH | __GFP_WAIT | __GFP_IO | __GFP_HIGHIO | __GFP_FS)
+#define GFP_NFS		(__GFP_HIGH | __GFP_WAIT | __GFP_IO | __GFP_HIGHIO | __GFP_FS)
+#define GFP_KSWAPD	(             __GFP_WAIT | __GFP_IO | __GFP_HIGHIO | __GFP_FS)
+
+/* Flag - indicates that the buffer will be suitable for DMA.  Ignored on some
+   platforms, used as appropriate on others */
+
+#define GFP_DMA		__GFP_DMA
+
+static inline unsigned int pf_gfp_mask(unsigned int gfp_mask)
+{
+	/* avoid all memory balancing I/O methods if this task cannot block on I/O */
+	if (current->flags & PF_NOIO)
+		gfp_mask &= ~(__GFP_IO | __GFP_HIGHIO | __GFP_FS);
+
+	return gfp_mask;
+}
+	
+/* vma is the first one with  address < vma->vm_end,
+ * and even  address < vma->vm_start. Have to extend vma. */
+static inline int expand_stack(struct vm_area_struct * vma, unsigned long address)
+{
+	unsigned long grow;
+
+	/*
+	 * vma->vm_start/vm_end cannot change under us because the caller
+	 * is required to hold the mmap_sem in read mode.  We need the
+	 * page_table_lock lock to serialize against concurrent expand_stacks.
+	 */
+	address &= PAGE_MASK;
+ 	spin_lock(&vma->vm_mm->page_table_lock);
+
+	/* already expanded while we were spinning? */
+	if (vma->vm_start <= address) {
+		spin_unlock(&vma->vm_mm->page_table_lock);
+		return 0;
+	}
+
+	grow = (vma->vm_start - address) >> PAGE_SHIFT;
+	if (vma->vm_end - address > current->rlim[RLIMIT_STACK].rlim_cur ||
+	    ((vma->vm_mm->total_vm + grow) << PAGE_SHIFT) > current->rlim[RLIMIT_AS].rlim_cur) {
+		spin_unlock(&vma->vm_mm->page_table_lock);
+		return -ENOMEM;
+	}
+
+	if ((vma->vm_flags & VM_LOCKED) &&
+      	    ((vma->vm_mm->locked_vm + grow) << PAGE_SHIFT) > current->rlim[RLIMIT_MEMLOCK].rlim_cur) {
+		spin_unlock(&vma->vm_mm->page_table_lock);
+		return -ENOMEM;
+	}
+
+
+	vma->vm_start = address;
+	vma->vm_pgoff -= grow;
+	vma->vm_mm->total_vm += grow;
+	if (vma->vm_flags & VM_LOCKED)
+		vma->vm_mm->locked_vm += grow;
+	spin_unlock(&vma->vm_mm->page_table_lock);
+	return 0;
+}
+
+/* Look up the first VMA which satisfies  addr < vm_end,  NULL if none. */
+extern struct vm_area_struct * find_vma(struct mm_struct * mm, unsigned long addr);
+extern struct vm_area_struct * find_vma_prev(struct mm_struct * mm, unsigned long addr,
+					     struct vm_area_struct **pprev);
+
+/* Look up the first VMA which intersects the interval start_addr..end_addr-1,
+   NULL if none.  Assume start_addr < end_addr. */
+static inline struct vm_area_struct * find_vma_intersection(struct mm_struct * mm, unsigned long start_addr, unsigned long end_addr)
+{
+	struct vm_area_struct * vma = find_vma(mm,start_addr);
+
+	if (vma && end_addr <= vma->vm_start)
+		vma = NULL;
+	return vma;
+}
+
+extern struct vm_area_struct *find_extend_vma(struct mm_struct *mm, unsigned long addr);
+
+extern struct page * vmalloc_to_page(void *addr);
+
+#endif /* __KERNEL__ */
+
+#endif

linux-2.4.29-xen-sparse/include/linux/sched.h

@@ -0,0 +1,971 @@
+#ifndef _LINUX_SCHED_H
+#define _LINUX_SCHED_H
+
+#include <asm/param.h>	/* for HZ */
+
+extern unsigned long event;
+
+#include <linux/config.h>
+#include <linux/binfmts.h>
+#include <linux/threads.h>
+#include <linux/kernel.h>
+#include <linux/types.h>
+#include <linux/times.h>
+#include <linux/timex.h>
+#include <linux/rbtree.h>
+
+#include <asm/system.h>
+#include <asm/semaphore.h>
+#include <asm/page.h>
+#include <asm/ptrace.h>
+#include <asm/mmu.h>
+
+#include <linux/smp.h>
+#include <linux/tty.h>
+#include <linux/sem.h>
+#include <linux/signal.h>
+#include <linux/securebits.h>
+#include <linux/fs_struct.h>
+
+struct exec_domain;
+
+/*
+ * cloning flags:
+ */
+#define CSIGNAL		0x000000ff	/* signal mask to be sent at exit */
+#define CLONE_VM	0x00000100	/* set if VM shared between processes */
+#define CLONE_FS	0x00000200	/* set if fs info shared between processes */
+#define CLONE_FILES	0x00000400	/* set if open files shared between processes */
+#define CLONE_SIGHAND	0x00000800	/* set if signal handlers and blocked signals shared */
+#define CLONE_PID	0x00001000	/* set if pid shared */
+#define CLONE_PTRACE	0x00002000	/* set if we want to let tracing continue on the child too */
+#define CLONE_VFORK	0x00004000	/* set if the parent wants the child to wake it up on mm_release */
+#define CLONE_PARENT	0x00008000	/* set if we want to have the same parent as the cloner */
+#define CLONE_THREAD	0x00010000	/* Same thread group? */
+#define CLONE_NEWNS	0x00020000	/* New namespace group? */
+
+#define CLONE_SIGNAL	(CLONE_SIGHAND | CLONE_THREAD)
+
+/*
+ * These are the constant used to fake the fixed-point load-average
+ * counting. Some notes:
+ *  - 11 bit fractions expand to 22 bits by the multiplies: this gives
+ *    a load-average precision of 10 bits integer + 11 bits fractional
+ *  - if you want to count load-averages more often, you need more
+ *    precision, or rounding will get you. With 2-second counting freq,
+ *    the EXP_n values would be 1981, 2034 and 2043 if still using only
+ *    11 bit fractions.
+ */
+extern unsigned long avenrun[];		/* Load averages */
+
+#define FSHIFT		11		/* nr of bits of precision */
+#define FIXED_1		(1<<FSHIFT)	/* 1.0 as fixed-point */
+#define LOAD_FREQ	(5*HZ)		/* 5 sec intervals */
+#define EXP_1		1884		/* 1/exp(5sec/1min) as fixed-point */
+#define EXP_5		2014		/* 1/exp(5sec/5min) */
+#define EXP_15		2037		/* 1/exp(5sec/15min) */
+
+#define CALC_LOAD(load,exp,n) \
+	load *= exp; \
+	load += n*(FIXED_1-exp); \
+	load >>= FSHIFT;
+
+#define CT_TO_SECS(x)	((x) / HZ)
+#define CT_TO_USECS(x)	(((x) % HZ) * 1000000/HZ)
+
+extern int nr_running, nr_threads;
+extern int last_pid;
+
+#include <linux/fs.h>
+#include <linux/time.h>
+#include <linux/param.h>
+#include <linux/resource.h>
+#ifdef __KERNEL__
+#include <linux/timer.h>
+#endif
+
+#include <asm/processor.h>
+
+#define TASK_RUNNING		0
+#define TASK_INTERRUPTIBLE	1
+#define TASK_UNINTERRUPTIBLE	2
+#define TASK_ZOMBIE		4
+#define TASK_STOPPED		8
+
+#define __set_task_state(tsk, state_value)		\
+	do { (tsk)->state = (state_value); } while (0)
+#define set_task_state(tsk, state_value)		\
+	set_mb((tsk)->state, (state_value))
+
+#define __set_current_state(state_value)			\
+	do { current->state = (state_value); } while (0)
+#define set_current_state(state_value)		\
+	set_mb(current->state, (state_value))
+
+/*
+ * Scheduling policies
+ */
+#define SCHED_OTHER		0
+#define SCHED_FIFO		1
+#define SCHED_RR		2
+
+/*
+ * This is an additional bit set when we want to
+ * yield the CPU for one re-schedule..
+ */
+#define SCHED_YIELD		0x10
+
+struct sched_param {
+	int sched_priority;
+};
+
+struct completion;
+
+#ifdef __KERNEL__
+
+#include <linux/spinlock.h>
+
+/*
+ * This serializes "schedule()" and also protects
+ * the run-queue from deletions/modifications (but
+ * _adding_ to the beginning of the run-queue has
+ * a separate lock).
+ */
+extern rwlock_t tasklist_lock;
+extern spinlock_t runqueue_lock;
+extern spinlock_t mmlist_lock;
+
+extern void sched_init(void);
+extern void init_idle(void);
+extern void show_state(void);
+extern void cpu_init (void);
+extern void trap_init(void);
+extern void update_process_times(int user);
+#ifdef CONFIG_NO_IDLE_HZ
+extern void update_process_times_us(int user, int system);
+#endif
+extern void update_one_process(struct task_struct *p, unsigned long user,
+			       unsigned long system, int cpu);
+
+#define	MAX_SCHEDULE_TIMEOUT	LONG_MAX
+extern signed long FASTCALL(schedule_timeout(signed long timeout));
+asmlinkage void schedule(void);
+
+extern int schedule_task(struct tq_struct *task);
+extern void flush_scheduled_tasks(void);
+extern int start_context_thread(void);
+extern int current_is_keventd(void);
+
+#if CONFIG_SMP
+extern void set_cpus_allowed(struct task_struct *p, unsigned long new_mask);
+#else
+# define set_cpus_allowed(p, new_mask) do { } while (0)
+#endif
+
+/*
+ * The default fd array needs to be at least BITS_PER_LONG,
+ * as this is the granularity returned by copy_fdset().
+ */
+#define NR_OPEN_DEFAULT BITS_PER_LONG
+
+struct namespace;
+/*
+ * Open file table structure
+ */
+struct files_struct {
+	atomic_t count;
+	rwlock_t file_lock;	/* Protects all the below members.  Nests inside tsk->alloc_lock */
+	int max_fds;
+	int max_fdset;
+	int next_fd;
+	struct file ** fd;	/* current fd array */
+	fd_set *close_on_exec;
+	fd_set *open_fds;
+	fd_set close_on_exec_init;
+	fd_set open_fds_init;
+	struct file * fd_array[NR_OPEN_DEFAULT];
+};
+
+#define INIT_FILES \
+{ 							\
+	count:		ATOMIC_INIT(1), 		\
+	file_lock:	RW_LOCK_UNLOCKED, 		\
+	max_fds:	NR_OPEN_DEFAULT, 		\
+	max_fdset:	__FD_SETSIZE, 			\
+	next_fd:	0, 				\
+	fd:		&init_files.fd_array[0], 	\
+	close_on_exec:	&init_files.close_on_exec_init, \
+	open_fds:	&init_files.open_fds_init, 	\
+	close_on_exec_init: { { 0, } }, 		\
+	open_fds_init:	{ { 0, } }, 			\
+	fd_array:	{ NULL, } 			\
+}
+
+/* Maximum number of active map areas.. This is a random (large) number */
+#define DEFAULT_MAX_MAP_COUNT	(65536)
+
+extern int max_map_count;
+
+struct mm_struct {
+	struct vm_area_struct * mmap;		/* list of VMAs */
+	rb_root_t mm_rb;
+	struct vm_area_struct * mmap_cache;	/* last find_vma result */
+	pgd_t * pgd;
+	atomic_t mm_users;			/* How many users with user space? */
+	atomic_t mm_count;			/* How many references to "struct mm_struct" (users count as 1) */
+	int map_count;				/* number of VMAs */
+	struct rw_semaphore mmap_sem;
+	spinlock_t page_table_lock;		/* Protects task page tables and mm->rss */
+
+	struct list_head mmlist;		/* List of all active mm's.  These are globally strung
+						 * together off init_mm.mmlist, and are protected
+						 * by mmlist_lock
+						 */
+
+	unsigned long start_code, end_code, start_data, end_data;
+	unsigned long start_brk, brk, start_stack;
+	unsigned long arg_start, arg_end, env_start, env_end;
+	unsigned long rss, total_vm, locked_vm;
+	unsigned long def_flags;
+	unsigned long cpu_vm_mask;
+	unsigned long swap_address;
+
+	unsigned dumpable:1;
+
+	/* Architecture-specific MM context */
+	mm_context_t context;
+};
+
+extern int mmlist_nr;
+
+#define INIT_MM(name) \
+{			 				\
+	mm_rb:		RB_ROOT,			\
+	pgd:		swapper_pg_dir, 		\
+	mm_users:	ATOMIC_INIT(2), 		\
+	mm_count:	ATOMIC_INIT(1), 		\
+	mmap_sem:	__RWSEM_INITIALIZER(name.mmap_sem), \
+	page_table_lock: SPIN_LOCK_UNLOCKED, 		\
+	mmlist:		LIST_HEAD_INIT(name.mmlist),	\
+}
+
+struct signal_struct {
+	atomic_t		count;
+	struct k_sigaction	action[_NSIG];
+	spinlock_t		siglock;
+};
+
+
+#define INIT_SIGNALS {	\
+	count:		ATOMIC_INIT(1), 		\
+	action:		{ {{0,}}, }, 			\
+	siglock:	SPIN_LOCK_UNLOCKED 		\
+}
+
+/*
+ * Some day this will be a full-fledged user tracking system..
+ */
+struct user_struct {
+	atomic_t __count;	/* reference count */
+	atomic_t processes;	/* How many processes does this user have? */
+	atomic_t files;		/* How many open files does this user have? */
+
+	/* Hash table maintenance information */
+	struct user_struct *next, **pprev;
+	uid_t uid;
+};
+
+#define get_current_user() ({ 				\
+	struct user_struct *__tmp_user = current->user;	\
+	atomic_inc(&__tmp_user->__count);		\
+	__tmp_user; })
+
+extern struct user_struct root_user;
+#define INIT_USER (&root_user)
+
+struct task_struct {
+	/*
+	 * offsets of these are hardcoded elsewhere - touch with care
+	 */
+	volatile long state;	/* -1 unrunnable, 0 runnable, >0 stopped */
+	unsigned long flags;	/* per process flags, defined below */
+	int sigpending;
+	mm_segment_t addr_limit;	/* thread address space:
+					 	0-0xBFFFFFFF for user-thead
+						0-0xFFFFFFFF for kernel-thread
+					 */
+	struct exec_domain *exec_domain;
+	volatile long need_resched;
+	unsigned long ptrace;
+
+	int lock_depth;		/* Lock depth */
+
+/*
+ * offset 32 begins here on 32-bit platforms. We keep
+ * all fields in a single cacheline that are needed for
+ * the goodness() loop in schedule().
+ */
+	long counter;
+	long nice;
+	unsigned long policy;
+	struct mm_struct *mm;
+	int processor;
+	/*
+	 * cpus_runnable is ~0 if the process is not running on any
+	 * CPU. It's (1 << cpu) if it's running on a CPU. This mask
+	 * is updated under the runqueue lock.
+	 *
+	 * To determine whether a process might run on a CPU, this
+	 * mask is AND-ed with cpus_allowed.
+	 */
+	unsigned long cpus_runnable, cpus_allowed;
+	/*
+	 * (only the 'next' pointer fits into the cacheline, but
+	 * that's just fine.)
+	 */
+	struct list_head run_list;
+	unsigned long sleep_time;
+
+	struct task_struct *next_task, *prev_task;
+	struct mm_struct *active_mm;
+	struct list_head local_pages;
+	unsigned int allocation_order, nr_local_pages;
+
+/* task state */
+	struct linux_binfmt *binfmt;
+	int exit_code, exit_signal;
+	int pdeath_signal;  /*  The signal sent when the parent dies  */
+	/* ??? */
+	unsigned long personality;
+	int did_exec:1;
+	unsigned task_dumpable:1;
+	pid_t pid;
+	pid_t pgrp;
+	pid_t tty_old_pgrp;
+	pid_t session;
+	pid_t tgid;
+	/* boolean value for session group leader */
+	int leader;
+	/* 
+	 * pointers to (original) parent process, youngest child, younger sibling,
+	 * older sibling, respectively.  (p->father can be replaced with 
+	 * p->p_pptr->pid)
+	 */
+	struct task_struct *p_opptr, *p_pptr, *p_cptr, *p_ysptr, *p_osptr;
+	struct list_head thread_group;
+
+	/* PID hash table linkage. */
+	struct task_struct *pidhash_next;
+	struct task_struct **pidhash_pprev;
+
+	wait_queue_head_t wait_chldexit;	/* for wait4() */
+	struct completion *vfork_done;		/* for vfork() */
+	unsigned long rt_priority;
+	unsigned long it_real_value, it_prof_value, it_virt_value;
+	unsigned long it_real_incr, it_prof_incr, it_virt_incr;
+	struct timer_list real_timer;
+	struct tms times;
+	unsigned long start_time;
+	long per_cpu_utime[NR_CPUS], per_cpu_stime[NR_CPUS];
+/* mm fault and swap info: this can arguably be seen as either mm-specific or thread-specific */
+	unsigned long min_flt, maj_flt, nswap, cmin_flt, cmaj_flt, cnswap;
+	int swappable:1;
+/* process credentials */
+	uid_t uid,euid,suid,fsuid;
+	gid_t gid,egid,sgid,fsgid;
+	int ngroups;
+	gid_t	groups[NGROUPS];
+	kernel_cap_t   cap_effective, cap_inheritable, cap_permitted;
+	int keep_capabilities:1;
+	struct user_struct *user;
+/* limits */
+	struct rlimit rlim[RLIM_NLIMITS];
+	unsigned short used_math;
+	char comm[16];
+/* file system info */
+	int link_count, total_link_count;
+	struct tty_struct *tty; /* NULL if no tty */
+	unsigned int locks; /* How many file locks are being held */
+/* ipc stuff */
+	struct sem_undo *semundo;
+	struct sem_queue *semsleeping;
+/* CPU-specific state of this task */
+	struct thread_struct thread;
+/* filesystem information */
+	struct fs_struct *fs;
+/* open file information */
+	struct files_struct *files;
+/* namespace */
+	struct namespace *namespace;
+/* signal handlers */
+	spinlock_t sigmask_lock;	/* Protects signal and blocked */
+	struct signal_struct *sig;
+
+	sigset_t blocked;
+	struct sigpending pending;
+
+	unsigned long sas_ss_sp;
+	size_t sas_ss_size;
+	int (*notifier)(void *priv);
+	void *notifier_data;
+	sigset_t *notifier_mask;
+	
+/* Thread group tracking */
+   	u32 parent_exec_id;
+   	u32 self_exec_id;
+/* Protection of (de-)allocation: mm, files, fs, tty */
+	spinlock_t alloc_lock;
+
+/* journalling filesystem info */
+	void *journal_info;
+};
+
+/*
+ * Per process flags
+ */
+#define PF_ALIGNWARN	0x00000001	/* Print alignment warning msgs */
+					/* Not implemented yet, only for 486*/
+#define PF_STARTING	0x00000002	/* being created */
+#define PF_EXITING	0x00000004	/* getting shut down */
+#define PF_FORKNOEXEC	0x00000040	/* forked but didn't exec */
+#define PF_SUPERPRIV	0x00000100	/* used super-user privileges */
+#define PF_DUMPCORE	0x00000200	/* dumped core */
+#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_NOIO		0x00004000	/* avoid generating further I/O */
+#define PF_FSTRANS	0x00008000	/* inside a filesystem transaction */
+
+#define PF_USEDFPU	0x00100000	/* task used FPU this quantum (SMP) */
+
+/*
+ * Ptrace flags
+ */
+
+#define PT_PTRACED	0x00000001
+#define PT_TRACESYS	0x00000002
+#define PT_DTRACE	0x00000004	/* delayed trace (used on m68k, i386) */
+#define PT_TRACESYSGOOD	0x00000008
+#define PT_PTRACE_CAP	0x00000010	/* ptracer can follow suid-exec */
+
+#define is_dumpable(tsk)    ((tsk)->task_dumpable && (tsk)->mm && (tsk)->mm->dumpable)
+
+/*
+ * Limit the stack by to some sane default: root can always
+ * increase this limit if needed..  8MB seems reasonable.
+ */
+#define _STK_LIM	(8*1024*1024)
+
+#define DEF_COUNTER	(10*HZ/100)	/* 100 ms time slice */
+#define MAX_COUNTER	(20*HZ/100)
+#define DEF_NICE	(0)
+
+extern void yield(void);
+
+/*
+ * The default (Linux) execution domain.
+ */
+extern struct exec_domain	default_exec_domain;
+
+/*
+ *  INIT_TASK is used to set up the first task table, touch at
+ * your own risk!. Base=0, limit=0x1fffff (=2MB)
+ */
+#define INIT_TASK(tsk)	\
+{									\
+    state:		0,						\
+    flags:		0,						\
+    sigpending:		0,						\
+    addr_limit:		KERNEL_DS,					\
+    exec_domain:	&default_exec_domain,				\
+    lock_depth:		-1,						\
+    counter:		DEF_COUNTER,					\
+    nice:		DEF_NICE,					\
+    policy:		SCHED_OTHER,					\
+    mm:			NULL,						\
+    active_mm:		&init_mm,					\
+    cpus_runnable:	~0UL,						\
+    cpus_allowed:	~0UL,						\
+    run_list:		LIST_HEAD_INIT(tsk.run_list),			\
+    next_task:		&tsk,						\
+    prev_task:		&tsk,						\
+    p_opptr:		&tsk,						\
+    p_pptr:		&tsk,						\
+    thread_group:	LIST_HEAD_INIT(tsk.thread_group),		\
+    wait_chldexit:	__WAIT_QUEUE_HEAD_INITIALIZER(tsk.wait_chldexit),\
+    real_timer:		{						\
+	function:		it_real_fn				\
+    },									\
+    cap_effective:	CAP_INIT_EFF_SET,				\
+    cap_inheritable:	CAP_INIT_INH_SET,				\
+    cap_permitted:	CAP_FULL_SET,					\
+    keep_capabilities:	0,						\
+    rlim:		INIT_RLIMITS,					\
+    user:		INIT_USER,					\
+    comm:		"swapper",					\
+    thread:		INIT_THREAD,					\
+    fs:			&init_fs,					\
+    files:		&init_files,					\
+    sigmask_lock:	SPIN_LOCK_UNLOCKED,				\
+    sig:		&init_signals,					\
+    pending:		{ NULL, &tsk.pending.head, {{0}}},		\
+    blocked:		{{0}},						\
+    alloc_lock:		SPIN_LOCK_UNLOCKED,				\
+    journal_info:	NULL,						\
+}
+
+
+#ifndef INIT_TASK_SIZE
+# define INIT_TASK_SIZE	2048*sizeof(long)
+#endif
+
+union task_union {
+	struct task_struct task;
+	unsigned long stack[INIT_TASK_SIZE/sizeof(long)];
+};
+
+extern union task_union init_task_union;
+
+extern struct   mm_struct init_mm;
+extern struct task_struct *init_tasks[NR_CPUS];
+
+/* PID hashing. (shouldnt this be dynamic?) */
+#define PIDHASH_SZ (4096 >> 2)
+extern struct task_struct *pidhash[PIDHASH_SZ];
+
+#define pid_hashfn(x)	((((x) >> 8) ^ (x)) & (PIDHASH_SZ - 1))
+
+static inline void hash_pid(struct task_struct *p)
+{
+	struct task_struct **htable = &pidhash[pid_hashfn(p->pid)];
+
+	if((p->pidhash_next = *htable) != NULL)
+		(*htable)->pidhash_pprev = &p->pidhash_next;
+	*htable = p;
+	p->pidhash_pprev = htable;
+}
+
+static inline void unhash_pid(struct task_struct *p)
+{
+	if(p->pidhash_next)
+		p->pidhash_next->pidhash_pprev = p->pidhash_pprev;
+	*p->pidhash_pprev = p->pidhash_next;
+}
+
+static inline struct task_struct *find_task_by_pid(int pid)
+{
+	struct task_struct *p, **htable = &pidhash[pid_hashfn(pid)];
+
+	for(p = *htable; p && p->pid != pid; p = p->pidhash_next)
+		;
+
+	return p;
+}
+
+#define task_has_cpu(tsk) ((tsk)->cpus_runnable != ~0UL)
+
+static inline void task_set_cpu(struct task_struct *tsk, unsigned int cpu)
+{
+	tsk->processor = cpu;
+	tsk->cpus_runnable = 1UL << cpu;
+}
+
+static inline void task_release_cpu(struct task_struct *tsk)
+{
+	tsk->cpus_runnable = ~0UL;
+}
+
+/* per-UID process charging. */
+extern struct user_struct * alloc_uid(uid_t);
+extern void free_uid(struct user_struct *);
+extern void switch_uid(struct user_struct *);
+
+#include <asm/current.h>
+
+extern unsigned long volatile jiffies;
+extern unsigned long itimer_ticks;
+extern unsigned long itimer_next;
+extern struct timeval xtime;
+extern void do_timer(struct pt_regs *);
+#ifdef CONFIG_NO_IDLE_HZ
+extern void do_timer_ticks(int ticks);
+#endif
+
+extern unsigned int * prof_buffer;
+extern unsigned long prof_len;
+extern unsigned long prof_shift;
+
+#define CURRENT_TIME (xtime.tv_sec)
+
+extern void FASTCALL(__wake_up(wait_queue_head_t *q, unsigned int mode, int nr));
+extern void FASTCALL(__wake_up_sync(wait_queue_head_t *q, unsigned int mode, int nr));
+extern void FASTCALL(sleep_on(wait_queue_head_t *q));
+extern long FASTCALL(sleep_on_timeout(wait_queue_head_t *q,
+				      signed long timeout));
+extern void FASTCALL(interruptible_sleep_on(wait_queue_head_t *q));
+extern long FASTCALL(interruptible_sleep_on_timeout(wait_queue_head_t *q,
+						    signed long timeout));
+extern int FASTCALL(wake_up_process(struct task_struct * tsk));
+
+#define wake_up(x)			__wake_up((x),TASK_UNINTERRUPTIBLE | TASK_INTERRUPTIBLE, 1)
+#define wake_up_nr(x, nr)		__wake_up((x),TASK_UNINTERRUPTIBLE | TASK_INTERRUPTIBLE, nr)
+#define wake_up_all(x)			__wake_up((x),TASK_UNINTERRUPTIBLE | TASK_INTERRUPTIBLE, 0)
+#define wake_up_sync(x)			__wake_up_sync((x),TASK_UNINTERRUPTIBLE | TASK_INTERRUPTIBLE, 1)
+#define wake_up_sync_nr(x, nr)		__wake_up_sync((x),TASK_UNINTERRUPTIBLE | TASK_INTERRUPTIBLE, nr)
+#define wake_up_interruptible(x)	__wake_up((x),TASK_INTERRUPTIBLE, 1)
+#define wake_up_interruptible_nr(x, nr)	__wake_up((x),TASK_INTERRUPTIBLE, nr)
+#define wake_up_interruptible_all(x)	__wake_up((x),TASK_INTERRUPTIBLE, 0)
+#define wake_up_interruptible_sync(x)	__wake_up_sync((x),TASK_INTERRUPTIBLE, 1)
+#define wake_up_interruptible_sync_nr(x, nr) __wake_up_sync((x),TASK_INTERRUPTIBLE,  nr)
+asmlinkage long sys_wait4(pid_t pid,unsigned int * stat_addr, int options, struct rusage * ru);
+
+extern int in_group_p(gid_t);
+extern int in_egroup_p(gid_t);
+
+extern void proc_caches_init(void);
+extern void flush_signals(struct task_struct *);
+extern void flush_signal_handlers(struct task_struct *);
+extern void sig_exit(int, int, struct siginfo *);
+extern int dequeue_signal(sigset_t *, siginfo_t *);
+extern void block_all_signals(int (*notifier)(void *priv), void *priv,
+			      sigset_t *mask);
+extern void unblock_all_signals(void);
+extern int send_sig_info(int, struct siginfo *, struct task_struct *);
+extern int force_sig_info(int, struct siginfo *, struct task_struct *);
+extern int kill_pg_info(int, struct siginfo *, pid_t);
+extern int kill_sl_info(int, struct siginfo *, pid_t);
+extern int kill_proc_info(int, struct siginfo *, pid_t);
+extern void notify_parent(struct task_struct *, int);
+extern void do_notify_parent(struct task_struct *, int);
+extern void force_sig(int, struct task_struct *);
+extern int send_sig(int, struct task_struct *, int);
+extern int kill_pg(pid_t, int, int);
+extern int kill_sl(pid_t, int, int);
+extern int kill_proc(pid_t, int, int);
+extern int do_sigaction(int, const struct k_sigaction *, struct k_sigaction *);
+extern int do_sigaltstack(const stack_t *, stack_t *, unsigned long);
+
+static inline int signal_pending(struct task_struct *p)
+{
+	return (p->sigpending != 0);
+}
+
+/*
+ * Re-calculate pending state from the set of locally pending
+ * signals, globally pending signals, and blocked signals.
+ */
+static inline int has_pending_signals(sigset_t *signal, sigset_t *blocked)
+{
+	unsigned long ready;
+	long i;
+
+	switch (_NSIG_WORDS) {
+	default:
+		for (i = _NSIG_WORDS, ready = 0; --i >= 0 ;)
+			ready |= signal->sig[i] &~ blocked->sig[i];
+		break;
+
+	case 4: ready  = signal->sig[3] &~ blocked->sig[3];
+		ready |= signal->sig[2] &~ blocked->sig[2];
+		ready |= signal->sig[1] &~ blocked->sig[1];
+		ready |= signal->sig[0] &~ blocked->sig[0];
+		break;
+
+	case 2: ready  = signal->sig[1] &~ blocked->sig[1];
+		ready |= signal->sig[0] &~ blocked->sig[0];
+		break;
+
+	case 1: ready  = signal->sig[0] &~ blocked->sig[0];
+	}
+	return ready !=	0;
+}
+
+/* Reevaluate whether the task has signals pending delivery.
+   This is required every time the blocked sigset_t changes.
+   All callers should have t->sigmask_lock.  */
+
+static inline void recalc_sigpending(struct task_struct *t)
+{
+	t->sigpending = has_pending_signals(&t->pending.signal, &t->blocked);
+}
+
+/* True if we are on the alternate signal stack.  */
+
+static inline int on_sig_stack(unsigned long sp)
+{
+	return (sp - current->sas_ss_sp < current->sas_ss_size);
+}
+
+static inline int sas_ss_flags(unsigned long sp)
+{
+	return (current->sas_ss_size == 0 ? SS_DISABLE
+		: on_sig_stack(sp) ? SS_ONSTACK : 0);
+}
+
+extern int request_irq(unsigned int,
+		       void (*handler)(int, void *, struct pt_regs *),
+		       unsigned long, const char *, void *);
+extern void free_irq(unsigned int, void *);
+
+/*
+ * This has now become a routine instead of a macro, it sets a flag if
+ * it returns true (to do BSD-style accounting where the process is flagged
+ * if it uses root privs). The implication of this is that you should do
+ * normal permissions checks first, and check suser() last.
+ *
+ * [Dec 1997 -- Chris Evans]
+ * For correctness, the above considerations need to be extended to
+ * fsuser(). This is done, along with moving fsuser() checks to be
+ * last.
+ *
+ * These will be removed, but in the mean time, when the SECURE_NOROOT 
+ * flag is set, uids don't grant privilege.
+ */
+static inline int suser(void)
+{
+	if (!issecure(SECURE_NOROOT) && current->euid == 0) { 
+		current->flags |= PF_SUPERPRIV;
+		return 1;
+	}
+	return 0;
+}
+
+static inline int fsuser(void)
+{
+	if (!issecure(SECURE_NOROOT) && current->fsuid == 0) {
+		current->flags |= PF_SUPERPRIV;
+		return 1;
+	}
+	return 0;
+}
+
+/*
+ * capable() checks for a particular capability.  
+ * New privilege checks should use this interface, rather than suser() or
+ * fsuser(). See include/linux/capability.h for defined capabilities.
+ */
+
+static inline int capable(int cap)
+{
+#if 1 /* ok now */
+	if (cap_raised(current->cap_effective, cap))
+#else
+	if (cap_is_fs_cap(cap) ? current->fsuid == 0 : current->euid == 0)
+#endif
+	{
+		current->flags |= PF_SUPERPRIV;
+		return 1;
+	}
+	return 0;
+}
+
+/*
+ * Routines for handling mm_structs
+ */
+extern struct mm_struct * mm_alloc(void);
+
+extern struct mm_struct * start_lazy_tlb(void);
+extern void end_lazy_tlb(struct mm_struct *mm);
+
+/* mmdrop drops the mm and the page tables */
+extern void FASTCALL(__mmdrop(struct mm_struct *));
+static inline void mmdrop(struct mm_struct * mm)
+{
+	if (atomic_dec_and_test(&mm->mm_count))
+		__mmdrop(mm);
+}
+
+/* mmput gets rid of the mappings and all user-space */
+extern void mmput(struct mm_struct *);
+/* Remove the current tasks stale references to the old mm_struct */
+extern void mm_release(void);
+
+/*
+ * Routines for handling the fd arrays
+ */
+extern struct file ** alloc_fd_array(int);
+extern int expand_fd_array(struct files_struct *, int nr);
+extern void free_fd_array(struct file **, int);
+
+extern fd_set *alloc_fdset(int);
+extern int expand_fdset(struct files_struct *, int nr);
+extern void free_fdset(fd_set *, int);
+
+extern int  copy_thread(int, unsigned long, unsigned long, unsigned long, struct task_struct *, struct pt_regs *);
+extern void flush_thread(void);
+extern void exit_thread(void);
+
+extern void exit_mm(struct task_struct *);
+extern void exit_files(struct task_struct *);
+extern void exit_sighand(struct task_struct *);
+
+extern void reparent_to_init(void);
+extern void daemonize(void);
+
+extern int do_execve(char *, char **, char **, struct pt_regs *);
+extern int do_fork(unsigned long, unsigned long, struct pt_regs *, unsigned long);
+
+extern void set_task_comm(struct task_struct *tsk, char *from);
+extern void get_task_comm(char *to, struct task_struct *tsk);
+
+extern void FASTCALL(add_wait_queue(wait_queue_head_t *q, wait_queue_t * wait));
+extern void FASTCALL(add_wait_queue_exclusive(wait_queue_head_t *q, wait_queue_t * wait));
+extern void FASTCALL(remove_wait_queue(wait_queue_head_t *q, wait_queue_t * wait));
+
+extern long kernel_thread(int (*fn)(void *), void * arg, unsigned long flags);
+
+#define __wait_event(wq, condition) 					\
+do {									\
+	wait_queue_t __wait;						\
+	init_waitqueue_entry(&__wait, current);				\
+									\
+	add_wait_queue(&wq, &__wait);					\
+	for (;;) {							\
+		set_current_state(TASK_UNINTERRUPTIBLE);		\
+		if (condition)						\
+			break;						\
+		schedule();						\
+	}								\
+	current->state = TASK_RUNNING;					\
+	remove_wait_queue(&wq, &__wait);				\
+} while (0)
+
+#define wait_event(wq, condition) 					\
+do {									\
+	if (condition)	 						\
+		break;							\
+	__wait_event(wq, condition);					\
+} while (0)
+
+#define __wait_event_interruptible(wq, condition, ret)			\
+do {									\
+	wait_queue_t __wait;						\
+	init_waitqueue_entry(&__wait, current);				\
+									\
+	add_wait_queue(&wq, &__wait);					\
+	for (;;) {							\
+		set_current_state(TASK_INTERRUPTIBLE);			\
+		if (condition)						\
+			break;						\
+		if (!signal_pending(current)) {				\
+			schedule();					\
+			continue;					\
+		}							\
+		ret = -ERESTARTSYS;					\
+		break;							\
+	}								\
+	current->state = TASK_RUNNING;					\
+	remove_wait_queue(&wq, &__wait);				\
+} while (0)
+	
+#define wait_event_interruptible(wq, condition)				\
+({									\
+	int __ret = 0;							\
+	if (!(condition))						\
+		__wait_event_interruptible(wq, condition, __ret);	\
+	__ret;								\
+})
+
+#define REMOVE_LINKS(p) do { \
+	(p)->next_task->prev_task = (p)->prev_task; \
+	(p)->prev_task->next_task = (p)->next_task; \
+	if ((p)->p_osptr) \
+		(p)->p_osptr->p_ysptr = (p)->p_ysptr; \
+	if ((p)->p_ysptr) \
+		(p)->p_ysptr->p_osptr = (p)->p_osptr; \
+	else \
+		(p)->p_pptr->p_cptr = (p)->p_osptr; \
+	} while (0)
+
+#define SET_LINKS(p) do { \
+	(p)->next_task = &init_task; \
+	(p)->prev_task = init_task.prev_task; \
+	init_task.prev_task->next_task = (p); \
+	init_task.prev_task = (p); \
+	(p)->p_ysptr = NULL; \
+	if (((p)->p_osptr = (p)->p_pptr->p_cptr) != NULL) \
+		(p)->p_osptr->p_ysptr = p; \
+	(p)->p_pptr->p_cptr = p; \
+	} while (0)
+
+#define for_each_task(p) \
+	for (p = &init_task ; (p = p->next_task) != &init_task ; )
+
+#define for_each_thread(task) \
+	for (task = next_thread(current) ; task != current ; task = next_thread(task))
+
+#define next_thread(p) \
+	list_entry((p)->thread_group.next, struct task_struct, thread_group)
+
+#define thread_group_leader(p)	(p->pid == p->tgid)
+
+static inline void del_from_runqueue(struct task_struct * p)
+{
+	nr_running--;
+	p->sleep_time = jiffies;
+	list_del(&p->run_list);
+	p->run_list.next = NULL;
+}
+
+static inline int task_on_runqueue(struct task_struct *p)
+{
+	return (p->run_list.next != NULL);
+}
+
+static inline void unhash_process(struct task_struct *p)
+{
+	if (task_on_runqueue(p))
+		out_of_line_bug();
+	write_lock_irq(&tasklist_lock);
+	nr_threads--;
+	unhash_pid(p);
+	REMOVE_LINKS(p);
+	list_del(&p->thread_group);
+	write_unlock_irq(&tasklist_lock);
+}
+
+/* Protects ->fs, ->files, ->mm, and synchronises with wait4().  Nests inside tasklist_lock */
+static inline void task_lock(struct task_struct *p)
+{
+	spin_lock(&p->alloc_lock);
+}
+
+static inline void task_unlock(struct task_struct *p)
+{
+	spin_unlock(&p->alloc_lock);
+}
+
+/* write full pathname into buffer and return start of pathname */
+static inline char * d_path(struct dentry *dentry, struct vfsmount *vfsmnt,
+				char *buf, int buflen)
+{
+	char *res;
+	struct vfsmount *rootmnt;
+	struct dentry *root;
+	read_lock(&current->fs->lock);
+	rootmnt = mntget(current->fs->rootmnt);
+	root = dget(current->fs->root);
+	read_unlock(&current->fs->lock);
+	spin_lock(&dcache_lock);
+	res = __d_path(dentry, vfsmnt, root, rootmnt, buf, buflen);
+	spin_unlock(&dcache_lock);
+	dput(root);
+	mntput(rootmnt);
+	return res;
+}
+
+static inline int need_resched(void)
+{
+	return (unlikely(current->need_resched));
+}
+
+extern void __cond_resched(void);
+static inline void cond_resched(void)
+{
+	if (need_resched())
+		__cond_resched();
+}
+
+#endif /* __KERNEL__ */
+#endif

linux-2.4.29-xen-sparse/include/linux/timer.h

@@ -0,0 +1,77 @@
+#ifndef _LINUX_TIMER_H
+#define _LINUX_TIMER_H
+
+#include <linux/config.h>
+#include <linux/list.h>
+
+/*
+ * In Linux 2.4, static timers have been removed from the kernel.
+ * Timers may be dynamically created and destroyed, and should be initialized
+ * by a call to init_timer() upon creation.
+ *
+ * The "data" field enables use of a common timeout function for several
+ * timeouts. You can use this field to distinguish between the different
+ * invocations.
+ */
+struct timer_list {
+	struct list_head list;
+	unsigned long expires;
+	unsigned long data;
+	void (*function)(unsigned long);
+};
+
+extern void add_timer(struct timer_list * timer);
+extern int del_timer(struct timer_list * timer);
+#ifdef CONFIG_NO_IDLE_HZ
+extern struct timer_list *next_timer_event(void);
+#endif
+
+#ifdef CONFIG_SMP
+extern int del_timer_sync(struct timer_list * timer);
+extern void sync_timers(void);
+#else
+#define del_timer_sync(t)	del_timer(t)
+#define sync_timers()		do { } while (0)
+#endif
+
+/*
+ * mod_timer is a more efficient way to update the expire field of an
+ * active timer (if the timer is inactive it will be activated)
+ * mod_timer(a,b) is equivalent to del_timer(a); a->expires = b; add_timer(a).
+ * If the timer is known to be not pending (ie, in the handler), mod_timer
+ * is less efficient than a->expires = b; add_timer(a).
+ */
+int mod_timer(struct timer_list *timer, unsigned long expires);
+
+extern void it_real_fn(unsigned long);
+
+static inline void init_timer(struct timer_list * timer)
+{
+	timer->list.next = timer->list.prev = NULL;
+}
+
+static inline int timer_pending (const struct timer_list * timer)
+{
+	return timer->list.next != NULL;
+}
+
+/*
+ *	These inlines deal with timer wrapping correctly. You are 
+ *	strongly encouraged to use them
+ *	1. Because people otherwise forget
+ *	2. Because if the timer wrap changes in future you wont have to
+ *	   alter your driver code.
+ *
+ * time_after(a,b) returns true if the time a is after time b.
+ *
+ * Do this with "<0" and ">=0" to only test the sign of the result. A
+ * good compiler would generate better code (and a really good compiler
+ * wouldn't care). Gcc is currently neither.
+ */
+#define time_after(a,b)		((long)(b) - (long)(a) < 0)
+#define time_before(a,b)	time_after(b,a)
+
+#define time_after_eq(a,b)	((long)(a) - (long)(b) >= 0)
+#define time_before_eq(a,b)	time_after_eq(b,a)
+
+#endif