locks.c

嵌入式系统设计与实例开发实验教材二源码 多线程应用程序设计 串行端口程序设计 AD接口实验 CAN总线通信实验 GPS通信实验 Linux内核移植与编译实验 IC卡读写实验 SD驱动使

#define MSNFS	/* HACK HACK */
/*
 *  linux/fs/locks.c
 *
 *  Provide support for fcntl()'s F_GETLK, F_SETLK, and F_SETLKW calls.
 *  Doug Evans ([e-mail]), August 07, 1992
 *
 *  Deadlock detection added.
 *  FIXME: one thing isn't handled yet:
 *	- mandatory locks (requires lots of changes elsewhere)
 *  Kelly Carmichael (kelly@[142.24.8.65]), September 17, 1994.
 *
 *  Miscellaneous edits, and a total rewrite of posix_lock_file() code.
 *  Kai Petzke ([e-mail]), 1994
 *  
 *  Converted file_lock_table to a linked list from an array, which eliminates
 *  the limits on how many active file locks are open.
 *  Chad Page ([e-mail]), November 27, 1994
 * 
 *  Removed dependency on file descriptors. dup()'ed file descriptors now
 *  get the same locks as the original file descriptors, and a close() on
 *  any file descriptor removes ALL the locks on the file for the current
 *  process. Since locks still depend on the process id, locks are inherited
 *  after an exec() but not after a fork(). This agrees with POSIX, and both
 *  BSD and SVR4 practice.
 *  Andy Walker ([e-mail]), February 14, 1995
 *
 *  Scrapped free list which is redundant now that we allocate locks
 *  dynamically with kmalloc()/kfree().
 *  Andy Walker ([e-mail]), February 21, 1995
 *
 *  Implemented two lock personalities - FL_FLOCK and FL_POSIX.
 *
 *  FL_POSIX locks are created with calls to fcntl() and lockf() through the
 *  fcntl() system call. They have the semantics described above.
 *
 *  FL_FLOCK locks are created with calls to flock(), through the flock()
 *  system call, which is new. Old C libraries implement flock() via fcntl()
 *  and will continue to use the old, broken implementation.
 *
 *  FL_FLOCK locks follow the 4.4 BSD flock() semantics. They are associated
 *  with a file pointer (filp). As a result they can be shared by a parent
 *  process and its children after a fork(). They are removed when the last
 *  file descriptor referring to the file pointer is closed (unless explicitly
 *  unlocked). 
 *
 *  FL_FLOCK locks never deadlock, an existing lock is always removed before
 *  upgrading from shared to exclusive (or vice versa). When this happens
 *  any processes blocked by the current lock are woken up and allowed to
 *  run before the new lock is applied.
 *  Andy Walker ([e-mail]), June 09, 1995
 *
 *  Removed some race conditions in flock_lock_file(), marked other possible
 *  races. Just grep for FIXME to see them. 
 *  Dmitry Gorodchanin ([e-mail]), February 09, 1996.
 *
 *  Addressed Dmitry's concerns. Deadlock checking no longer recursive.
 *  Lock allocation changed to GFP_ATOMIC as we can't afford to sleep
 *  once we've checked for blocking and deadlocking.
 *  Andy Walker ([e-mail]), April 03, 1996.
 *
 *  Initial implementation of mandatory locks. SunOS turned out to be
 *  a rotten model, so I implemented the "obvious" semantics.
 *  See 'linux/Documentation/mandatory.txt' for details.
 *  Andy Walker ([e-mail]), April 06, 1996.
 *
 *  Don't allow mandatory locks on mmap()'ed files. Added simple functions to
 *  check if a file has mandatory locks, used by mmap(), open() and creat() to
 *  see if system call should be rejected. Ref. HP-UX/SunOS/Solaris Reference
 *  Manual, Section 2.
 *  Andy Walker ([e-mail]), April 09, 1996.
 *
 *  Tidied up block list handling. Added '/proc/locks' interface.
 *  Andy Walker ([e-mail]), April 24, 1996.
 *
 *  Fixed deadlock condition for pathological code that mixes calls to
 *  flock() and fcntl().
 *  Andy Walker ([e-mail]), April 29, 1996.
 *
 *  Allow only one type of locking scheme (FL_POSIX or FL_FLOCK) to be in use
 *  for a given file at a time. Changed the CONFIG_LOCK_MANDATORY scheme to
 *  guarantee sensible behaviour in the case where file system modules might
 *  be compiled with different options than the kernel itself.
 *  Andy Walker ([e-mail]), May 15, 1996.
 *
 *  Added a couple of missing wake_up() calls. Thanks to Thomas Meckel
 *  ([e-mail]) for spotting this.
 *  Andy Walker ([e-mail]), May 15, 1996.
 *
 *  Changed FL_POSIX locks to use the block list in the same way as FL_FLOCK
 *  locks. Changed process synchronisation to avoid dereferencing locks that
 *  have already been freed.
 *  Andy Walker ([e-mail]), Sep 21, 1996.
 *
 *  Made the block list a circular list to minimise searching in the list.
 *  Andy Walker ([e-mail]), Sep 25, 1996.
 *
 *  Made mandatory locking a mount option. Default is not to allow mandatory
 *  locking.
 *  Andy Walker ([e-mail]), Oct 04, 1996.
 *
 *  Some adaptations for NFS support.
 *  Olaf Kirch ([e-mail]), Dec 1996,
 *
 *  Fixed /proc/locks interface so that we can't overrun the buffer we are handed.
 *  Andy Walker ([e-mail]), May 12, 1997.
 *
 *  Use slab allocator instead of kmalloc/kfree.
 *  Use generic list implementation from <linux/list.h>.
 *  Sped up posix_locks_deadlock by only considering blocked locks.
 *  Matthew Wilcox <[e-mail]>, March, 2000.
 *
 *  Leases and LOCK_MAND
 *  Matthew Wilcox <[e-mail]>, June, 2000.
 *  Stephen Rothwell <[e-mail]>, June, 2000.
 */

#include <linux/slab.h>
#include <linux/file.h>
#include <linux/smp_lock.h>
#include <linux/init.h>
#include <linux/capability.h>
#include <linux/sched.h>

#include <asm/semaphore.h>
#include <asm/uaccess.h>

int leases_enable = 1;
int lease_break_time = 45;

LIST_HEAD(file_lock_list);
static LIST_HEAD(blocked_list);

static kmem_cache_t *filelock_cache;

/* Allocate an empty lock structure. */
static struct file_lock *locks_alloc_lock(int account)
{
	struct file_lock *fl;
	if (account && current->locks >= current->rlim[RLIMIT_LOCKS].rlim_cur)
		return NULL;
	fl = kmem_cache_alloc(filelock_cache, SLAB_KERNEL);
	if (fl)
		current->locks++;
	return fl;
}

/* Free a lock which is not in use. */
static inline void locks_free_lock(struct file_lock *fl)
{
	if (fl == NULL) {
		BUG();
		return;
	}
	current->locks--;
	if (waitqueue_active(&fl->fl_wait))
		panic("Attempting to free lock with active wait queue");

	if (!list_empty(&fl->fl_block))
		panic("Attempting to free lock with active block list");

	if (!list_empty(&fl->fl_link))
		panic("Attempting to free lock on active lock list");

	kmem_cache_free(filelock_cache, fl);
}

void locks_init_lock(struct file_lock *fl)
{
	INIT_LIST_HEAD(&fl->fl_link);
	INIT_LIST_HEAD(&fl->fl_block);
	init_waitqueue_head(&fl->fl_wait);
	fl->fl_next = NULL;
	fl->fl_fasync = NULL;
	fl->fl_owner = 0;
	fl->fl_pid = 0;
	fl->fl_file = NULL;
	fl->fl_flags = 0;
	fl->fl_type = 0;
	fl->fl_start = fl->fl_end = 0;
	fl->fl_notify = NULL;
	fl->fl_insert = NULL;
	fl->fl_remove = NULL;
}

/*
 * Initialises the fields of the file lock which are invariant for
 * free file_locks.
 */
static void init_once(void *foo, kmem_cache_t *cache, unsigned long flags)
{
	struct file_lock *lock = (struct file_lock *) foo;

	if ((flags & (SLAB_CTOR_VERIFY|SLAB_CTOR_CONSTRUCTOR)) !=
					SLAB_CTOR_CONSTRUCTOR)
		return;

	locks_init_lock(lock);
}

/*
 * Initialize a new lock from an existing file_lock structure.
 */
void locks_copy_lock(struct file_lock *new, struct file_lock *fl)
{
	new->fl_owner = fl->fl_owner;
	new->fl_pid = fl->fl_pid;
	new->fl_file = fl->fl_file;
	new->fl_flags = fl->fl_flags;
	new->fl_type = fl->fl_type;
	new->fl_start = fl->fl_start;
	new->fl_end = fl->fl_end;
	new->fl_notify = fl->fl_notify;
	new->fl_insert = fl->fl_insert;
	new->fl_remove = fl->fl_remove;
	new->fl_u = fl->fl_u;
}

/* Fill in a file_lock structure with an appropriate FLOCK lock. */
static struct file_lock *flock_make_lock(struct file *filp, unsigned int type)
{
	struct file_lock *fl = locks_alloc_lock(1);
	if (fl == NULL)
		return NULL;

	fl->fl_owner = NULL;
	fl->fl_file = filp;
	fl->fl_pid = current->pid;
	fl->fl_flags = FL_FLOCK;
	fl->fl_type = type;
	fl->fl_start = 0;
	fl->fl_end = OFFSET_MAX;
	fl->fl_notify = NULL;
	fl->fl_insert = NULL;
	fl->fl_remove = NULL;
	
	return fl;
}

static int assign_type(struct file_lock *fl, int type)
{
	switch (type) {
	case F_RDLCK:
	case F_WRLCK:
	case F_UNLCK:
		fl->fl_type = type;
		break;
	default:
		return -EINVAL;
	}
	return 0;
}

/* Verify a "struct flock" and copy it to a "struct file_lock" as a POSIX
 * style lock.
 */
static int flock_to_posix_lock(struct file *filp, struct file_lock *fl,
			       struct flock *l)
{
	off_t start, end;

	switch (l->l_whence) {
	case 0: /*SEEK_SET*/
		start = 0;
		break;
	case 1: /*SEEK_CUR*/
		start = filp->f_pos;
		break;
	case 2: /*SEEK_END*/
		start = filp->f_dentry->d_inode->i_size;
		break;
	default:
		return -EINVAL;
	}

	if (((start += l->l_start) < 0) || (l->l_len < 0))
		return -EINVAL;
	end = start + l->l_len - 1;
	if (l->l_len > 0 && end < 0)
		return -EOVERFLOW;
	fl->fl_start = start;	/* we record the absolute position */
	fl->fl_end = end;
	if (l->l_len == 0)
		fl->fl_end = OFFSET_MAX;
	
	fl->fl_owner = current->files;
	fl->fl_pid = current->pid;
	fl->fl_file = filp;
	fl->fl_flags = FL_POSIX;
	fl->fl_notify = NULL;
	fl->fl_insert = NULL;
	fl->fl_remove = NULL;

	return assign_type(fl, l->l_type);
}

#if BITS_PER_LONG == 32
static int flock64_to_posix_lock(struct file *filp, struct file_lock *fl,
				 struct flock64 *l)
{
	loff_t start;

	switch (l->l_whence) {
	case 0: /*SEEK_SET*/
		start = 0;
		break;
	case 1: /*SEEK_CUR*/
		start = filp->f_pos;
		break;
	case 2: /*SEEK_END*/
		start = filp->f_dentry->d_inode->i_size;
		break;
	default:
		return -EINVAL;
	}

	if (((start += l->l_start) < 0) || (l->l_len < 0))
		return -EINVAL;
	fl->fl_end = start + l->l_len - 1;
	if (l->l_len > 0 && fl->fl_end < 0)
		return -EOVERFLOW;
	fl->fl_start = start;	/* we record the absolute position */
	if (l->l_len == 0)
		fl->fl_end = OFFSET_MAX;
	
	fl->fl_owner = current->files;
	fl->fl_pid = current->pid;
	fl->fl_file = filp;
	fl->fl_flags = FL_POSIX;
	fl->fl_notify = NULL;
	fl->fl_insert = NULL;
	fl->fl_remove = NULL;

	switch (l->l_type) {
	case F_RDLCK:
	case F_WRLCK:
	case F_UNLCK:
		fl->fl_type = l->l_type;
		break;
	default:
		return -EINVAL;
	}

	return (0);
}
#endif

/* Allocate a file_lock initialised to this type of lease */
static int lease_alloc(struct file *filp, int type, struct file_lock **flp)
{
	struct file_lock *fl = locks_alloc_lock(1);
	if (fl == NULL)
		return -ENOMEM;

	fl->fl_owner = current->files;
	fl->fl_pid = current->pid;

	fl->fl_file = filp;
	fl->fl_flags = FL_LEASE;
	if (assign_type(fl, type) != 0) {
		locks_free_lock(fl);
		return -EINVAL;
	}
	fl->fl_start = 0;
	fl->fl_end = OFFSET_MAX;
	fl->fl_notify = NULL;
	fl->fl_insert = NULL;
	fl->fl_remove = NULL;

	*flp = fl;
	return 0;
}

/* Check if two locks overlap each other.
 */
static inline int locks_overlap(struct file_lock *fl1, struct file_lock *fl2)
{
	return ((fl1->fl_end >= fl2->fl_start) &&
		(fl2->fl_end >= fl1->fl_start));
}

/*
 * Check whether two locks have the same owner
 * N.B. Do we need the test on PID as well as owner?
 * (Clone tasks should be considered as one "owner".)
 */
static inline int
locks_same_owner(struct file_lock *fl1, struct file_lock *fl2)
{
	return (fl1->fl_owner == fl2->fl_owner) &&
	       (fl1->fl_pid   == fl2->fl_pid);
}

/* Remove waiter from blocker's block list.
 * When blocker ends up pointing to itself then the list is empty.
 */
static void locks_delete_block(struct file_lock *waiter)
{
	list_del(&waiter->fl_block);
	INIT_LIST_HEAD(&waiter->fl_block);
	list_del(&waiter->fl_link);
	INIT_LIST_HEAD(&waiter->fl_link);
	waiter->fl_next = NULL;
}

/* Insert waiter into blocker's block list.
 * We use a circular list so that processes can be easily woken up in
 * the order they blocked. The documentation doesn't require this but
 * it seems like the reasonable thing to do.
 */
static void locks_insert_block(struct file_lock *blocker, 
			       struct file_lock *waiter)
{
	if (!list_empty(&waiter->fl_block)) {
		printk(KERN_ERR "locks_insert_block: removing duplicated lock "
			"(pid=%d %Ld-%Ld type=%d)\n", waiter->fl_pid,
			waiter->fl_start, waiter->fl_end, waiter->fl_type);
		locks_delete_block(waiter);
	}
	list_add_tail(&waiter->fl_block, &blocker->fl_block);
	waiter->fl_next = blocker;
	list_add(&waiter->fl_link, &blocked_list);
}

static inline
void locks_notify_blocked(struct file_lock *waiter)
{
	if (waiter->fl_notify)
		waiter->fl_notify(waiter);
	else
		wake_up(&waiter->fl_wait);
}

/* Wake up processes blocked waiting for blocker.
 * If told to wait then schedule the processes until the block list
 * is empty, otherwise empty the block list ourselves.
 */
static void locks_wake_up_blocks(struct file_lock *blocker, unsigned int wait)
{
	while (!list_empty(&blocker->fl_block)) {
		struct file_lock *waiter = list_entry(blocker->fl_block.next, struct file_lock, fl_block);

		if (wait) {
			locks_notify_blocked(waiter);
			/* Let the blocked process remove waiter from the
			 * block list when it gets scheduled.
			 */
			current->policy |= SCHED_YIELD;
			schedule();
		} else {
			/* Remove waiter from the block list, because by the
			 * time it wakes up blocker won't exist any more.
			 */
			locks_delete_block(waiter);
			locks_notify_blocked(waiter);
		}
	}
}

/* Insert file lock fl into an inode's lock list at the position indicated
 * by pos. At the same time add the lock to the global file lock list.
 */
static void locks_insert_lock(struct file_lock **pos, struct file_lock *fl)
{
	list_add(&fl->fl_link, &file_lock_list);

	/* insert into file's list */
	fl->fl_next = *pos;
	*pos = fl;

	if (fl->fl_insert)
		fl->fl_insert(fl);
}

/*
 * Remove lock from the lock lists
 */
static inline void _unhash_lock(struct file_lock **thisfl_p)
{
	struct file_lock *fl = *thisfl_p;

	*thisfl_p = fl->fl_next;
	fl->fl_next = NULL;

	list_del_init(&fl->fl_link);
}

/*