Documentation/filesystems/quota.txt


1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65


Quota subsystem
===============

Quota subsystem allows system administrator to set limits on used space and
number of used inodes (inode is a filesystem structure which is associated with
each file or directory) for users and/or groups. For both used space and number
of used inodes there are actually two limits. The first one is called softlimit
and the second one hardlimit.  An user can never exceed a hardlimit for any
resource (unless he has CAP_SYS_RESOURCE capability). User is allowed to exceed
softlimit but only for limited period of time. This period is called "grace
period" or "grace time". When grace time is over, user is not able to allocate
more space/inodes until he frees enough of them to get below softlimit.

Quota limits (and amount of grace time) are set independently for each
filesystem.

For more details about quota design, see the documentation in quota-tools package
(http://sourceforge.net/projects/linuxquota).

Quota netlink interface
=======================
When user exceeds a softlimit, runs out of grace time or reaches hardlimit,
quota subsystem traditionally printed a message to the controlling terminal of
the process which caused the excess. This method has the disadvantage that
when user is using a graphical desktop he usually cannot see the message.
Thus quota netlink interface has been designed to pass information about
the above events to userspace. There they can be captured by an application
and processed accordingly.

The interface uses generic netlink framework (see
http://lwn.net/Articles/208755/ and http://people.suug.ch/~tgr/libnl/ for more
details about this layer). The name of the quota generic netlink interface
is "VFS_DQUOT". Definitions of constants below are in <linux/quota.h>.
  Currently, the interface supports only one message type QUOTA_NL_C_WARNING.
This command is used to send a notification about any of the above mentioned
events. Each message has six attributes. These are (type of the argument is
in parentheses):
        QUOTA_NL_A_QTYPE (u32)
	  - type of quota being exceeded (one of USRQUOTA, GRPQUOTA)
        QUOTA_NL_A_EXCESS_ID (u64)
	  - UID/GID (depends on quota type) of user / group whose limit
	    is being exceeded.
        QUOTA_NL_A_CAUSED_ID (u64)
	  - UID of a user who caused the event
        QUOTA_NL_A_WARNING (u32)
	  - what kind of limit is exceeded:
		QUOTA_NL_IHARDWARN - inode hardlimit
		QUOTA_NL_ISOFTLONGWARN - inode softlimit is exceeded longer
		  than given grace period
		QUOTA_NL_ISOFTWARN - inode softlimit
		QUOTA_NL_BHARDWARN - space (block) hardlimit
		QUOTA_NL_BSOFTLONGWARN - space (block) softlimit is exceeded
		  longer than given grace period.
		QUOTA_NL_BSOFTWARN - space (block) softlimit
	  - four warnings are also defined for the event when user stops
	    exceeding some limit:
		QUOTA_NL_IHARDBELOW - inode hardlimit
		QUOTA_NL_ISOFTBELOW - inode softlimit
		QUOTA_NL_BHARDBELOW - space (block) hardlimit
		QUOTA_NL_BSOFTBELOW - space (block) softlimit
        QUOTA_NL_A_DEV_MAJOR (u32)
	  - major number of a device with the affected filesystem
        QUOTA_NL_A_DEV_MINOR (u32)
	  - minor number of a device with the affected filesystem
/*
 * Copyright (c) 2008 Intel Corporation
 * Author: Matthew Wilcox <willy@linux.intel.com>
 *
 * Distributed under the terms of the GNU GPL, version 2
 *
 * This file implements counting semaphores.
 * A counting semaphore may be acquired 'n' times before sleeping.
 * See mutex.c for single-acquisition sleeping locks which enforce
 * rules which allow code to be debugged more easily.
 */

/*
 * Some notes on the implementation:
 *
 * The spinlock controls access to the other members of the semaphore.
 * down_trylock() and up() can be called from interrupt context, so we
 * have to disable interrupts when taking the lock.  It turns out various
 * parts of the kernel expect to be able to use down() on a semaphore in
 * interrupt context when they know it will succeed, so we have to use
 * irqsave variants for down(), down_interruptible() and down_killable()
 * too.
 *
 * The ->count variable represents how many more tasks can acquire this
 * semaphore.  If it's zero, there may be tasks waiting on the wait_list.
 */

#include <linux/compiler.h>
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/sched.h>
#include <linux/semaphore.h>
#include <linux/spinlock.h>
#include <linux/ftrace.h>

static noinline void __down(struct semaphore *sem);
static noinline int __down_interruptible(struct semaphore *sem);
static noinline int __down_killable(struct semaphore *sem);
static noinline int __down_timeout(struct semaphore *sem, long jiffies);
static noinline void __up(struct semaphore *sem);

/**
 * down - acquire the semaphore
 * @sem: the semaphore to be acquired
 *
 * Acquires the semaphore.  If no more tasks are allowed to acquire the
 * semaphore, calling this function will put the task to sleep until the
 * semaphore is released.
 *
 * Use of this function is deprecated, please use down_interruptible() or
 * down_killable() instead.
 */
void down(struct semaphore *sem)
{
	unsigned long flags;

	spin_lock_irqsave(&sem->lock, flags);
	if (likely(sem->count > 0))
		sem->count--;
	else
		__down(sem);
	spin_unlock_irqrestore(&sem->lock, flags);
}
EXPORT_SYMBOL(down);

/**
 * down_interruptible - acquire the semaphore unless interrupted
 * @sem: the semaphore to be acquired
 *
 * Attempts to acquire the semaphore.  If no more tasks are allowed to
 * acquire the semaphore, calling this function will put the task to sleep.
 * If the sleep is interrupted by a signal, this function will return -EINTR.
 * If the semaphore is successfully acquired, this function returns 0.
 */
int down_interruptible(struct semaphore *sem)
{
	unsigned long flags;
	int result = 0;

	spin_lock_irqsave(&sem->lock, flags);
	if (likely(sem->count > 0))
		sem->count--;
	else
		result = __down_interruptible(sem);
	spin_unlock_irqrestore(&sem->lock, flags);

	return result;
}
EXPORT_SYMBOL(down_interruptible);

/**
 * down_killable - acquire the semaphore unless killed
 * @sem: the semaphore to be acquired
 *
 * Attempts to acquire the semaphore.  If no more tasks are allowed to
 * acquire the semaphore, calling this function will put the task to sleep.
 * If the sleep is interrupted by a fatal signal, this function will return
 * -EINTR.  If the semaphore is successfully acquired, this function returns
 * 0.
 */
int down_killable(struct semaphore *sem)
{
	unsigned long flags;
	int result = 0;

	spin_lock_irqsave(&sem->lock, flags);
	if (likely(sem->count > 0))
		sem->count--;
	else
		result = __down_killable(sem);
	spin_unlock_irqrestore(&sem->lock, flags);

	return result;
}
EXPORT_SYMBOL(down_killable);

/**
 * down_trylock - try to acquire the semaphore, without waiting
 * @sem: the semaphore to be acquired
 *
 * Try to acquire the semaphore atomically.  Returns 0 if the mutex has
 * been acquired successfully or 1 if it it cannot be acquired.
 *
 * NOTE: This return value is inverted from both spin_trylock and
 * mutex_trylock!  Be careful about this when converting code.
 *
 * Unlike mutex_trylock, this function can be used from interrupt context,
 * and the semaphore can be released by any task or interrupt.
 */
int down_trylock(struct semaphore *sem)
{
	unsigned long flags;
	int count;

	spin_lock_irqsave(&sem->lock, flags);
	count = sem->count - 1;
	if (likely(count >= 0))
		sem->count = count;
	spin_unlock_irqrestore(&sem->lock, flags);

	return (count < 0);
}
EXPORT_SYMBOL(down_trylock);

/**
 * down_timeout - acquire the semaphore within a specified time
 * @sem: the semaphore to be acquired
 * @jiffies: how long to wait before failing
 *
 * Attempts to acquire the semaphore.  If no more tasks are allowed to
 * acquire the semaphore, calling this function will put the task to sleep.
 * If the semaphore is not released within the specified number of jiffies,
 * this function returns -ETIME.  It returns 0 if the semaphore was acquired.
 */
int down_timeout(struct semaphore *sem, long jiffies)
{
	unsigned long flags;
	int result = 0;

	spin_lock_irqsave(&sem->lock, flags);
	if (likely(sem->count > 0))
		sem->count--;
	else
		result = __down_timeout(sem, jiffies);
	spin_unlock_irqrestore(&sem->lock, flags);

	return result;
}
EXPORT_SYMBOL(down_timeout);

/**
 * up - release the semaphore
 * @sem: the semaphore to release
 *
 * Release the semaphore.  Unlike mutexes, up() may be called from any
 * context and even by tasks which have never called down().
 */
void up(struct semaphore *sem)
{
	unsigned long flags;

	spin_lock_irqsave(&sem->lock, flags);
	if (likely(list_empty(&sem->wait_list)))
		sem->count++;
	else
		__up(sem);
	spin_unlock_irqrestore(&sem->lock, flags);
}
EXPORT_SYMBOL(up);

/* Functions for the contended case */

struct semaphore_waiter {
	struct list_head list;
	struct task_struct *task;
	int up;
};

/*
 * Because this function is inlined, the 'state' parameter will be
 * constant, and thus optimised away by the compiler.  Likewise the
 * 'timeout' parameter for the cases without timeouts.
 */
static inline int __sched __down_common(struct semaphore *sem, long state,
								long timeout)
{
	struct task_struct *task = current;
	struct semaphore_waiter waiter;

	list_add_tail(&waiter.list, &sem->wait_list);
	waiter.task = task;
	waiter.up = 0;

	for (;;) {
		if (signal_pending_state(state, task))
			goto interrupted;
		if (timeout <= 0)
			goto timed_out;
		__set_task_state(task, state);
		spin_unlock_irq(&sem->lock);
		timeout = schedule_timeout(timeout);
		spin_lock_irq(&sem->lock);
		if (waiter.up)
			return 0;
	}

 timed_out:
	list_del(&waiter.list);
	return -ETIME;

 interrupted:
	list_del(&waiter.list);
	return -EINTR;
}

static noinline void __sched __down(struct semaphore *sem)
{
	__down_common(sem, TASK_UNINTERRUPTIBLE, MAX_SCHEDULE_TIMEOUT);
}

static noinline int __sched __down_interruptible(struct semaphore *sem)
{
	return __down_common(sem, TASK_INTERRUPTIBLE, MAX_SCHEDULE_TIMEOUT);
}

static noinline int __sched __down_killable(struct semaphore *sem)
{
	return __down_common(sem, TASK_KILLABLE, MAX_SCHEDULE_TIMEOUT);
}

static noinline int __sched __down_timeout(struct semaphore *sem, long jiffies)
{
	return __down_common(sem, TASK_UNINTERRUPTIBLE, jiffies);
}

static noinline void __sched __up(struct semaphore *sem)
{
	struct semaphore_waiter *waiter = list_first_entry(&sem->wait_list,
						struct semaphore_waiter, list);
	list_del(&waiter->list);
	waiter->up = 1;
	wake_up_process(waiter->task);
}