futex.c

linux 2.6.19 kernel source code before patching

/*
 *  Fast Userspace Mutexes (which I call "Futexes!").
 *  (C) Rusty Russell, IBM 2002
 *
 *  Generalized futexes, futex requeueing, misc fixes by Ingo Molnar
 *  (C) Copyright 2003 Red Hat Inc, All Rights Reserved
 *
 *  Removed page pinning, fix privately mapped COW pages and other cleanups
 *  (C) Copyright 2003, 2004 Jamie Lokier
 *
 *  Robust futex support started by Ingo Molnar
 *  (C) Copyright 2006 Red Hat Inc, All Rights Reserved
 *  Thanks to Thomas Gleixner for suggestions, analysis and fixes.
 *
 *  PI-futex support started by Ingo Molnar and Thomas Gleixner
 *  Copyright (C) 2006 Red Hat, Inc., Ingo Molnar <[e-mail]>
 *  Copyright (C) 2006 Timesys Corp., Thomas Gleixner <[e-mail]>
 *
 *  PRIVATE futexes by Eric Dumazet
 *  Copyright (C) 2007 Eric Dumazet <[e-mail]>
 *
 *  Thanks to Ben LaHaise for yelling "hashed waitqueues" loudly
 *  enough at me, Linus for the original (flawed) idea, Matthew
 *  Kirkwood for proof-of-concept implementation.
 *
 *  "The futexes are also cursed."
 *  "But they come in a choice of three flavours!"
 *
 *  This program is free software; you can redistribute it and/or modify
 *  it under the terms of the GNU General Public License as published by
 *  the Free Software Foundation; either version 2 of the License, or
 *  (at your option) any later version.
 *
 *  This program is distributed in the hope that it will be useful,
 *  but WITHOUT ANY WARRANTY; without even the implied warranty of
 *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 *  GNU General Public License for more details.
 *
 *  You should have received a copy of the GNU General Public License
 *  along with this program; if not, write to the Free Software
 *  Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
 */
#include <linux/slab.h>
#include <linux/poll.h>
#include <linux/fs.h>
#include <linux/file.h>
#include <linux/jhash.h>
#include <linux/init.h>
#include <linux/futex.h>
#include <linux/mount.h>
#include <linux/pagemap.h>
#include <linux/syscalls.h>
#include <linux/signal.h>
#include <linux/module.h>
#include <asm/futex.h>

#include "rtmutex_common.h"

#define FUTEX_HASHBITS (CONFIG_BASE_SMALL ? 4 : 8)

/*
 * Priority Inheritance state:
 */
struct futex_pi_state {
	/*
	 * list of 'owned' pi_state instances - these have to be
	 * cleaned up in do_exit() if the task exits prematurely:
	 */
	struct list_head list;

	/*
	 * The PI object:
	 */
	struct rt_mutex pi_mutex;

	struct task_struct *owner;
	atomic_t refcount;

	union futex_key key;
};

/*
 * We use this hashed waitqueue instead of a normal wait_queue_t, so
 * we can wake only the relevant ones (hashed queues may be shared).
 *
 * A futex_q has a woken state, just like tasks have TASK_RUNNING.
 * It is considered woken when plist_node_empty(&q->list) || q->lock_ptr == 0.
 * The order of wakup is always to make the first condition true, then
 * wake up q->waiters, then make the second condition true.
 */
struct futex_q {
	struct plist_node list;
	wait_queue_head_t waiters;

	/* Which hash list lock to use: */
	spinlock_t *lock_ptr;

	/* Key which the futex is hashed on: */
	union futex_key key;

	/* For fd, sigio sent using these: */
	int fd;
	struct file *filp;

	/* Optional priority inheritance state: */
	struct futex_pi_state *pi_state;
	struct task_struct *task;
};

/*
 * Split the global futex_lock into every hash list lock.
 */
struct futex_hash_bucket {
	spinlock_t lock;
	struct plist_head chain;
};

static struct futex_hash_bucket futex_queues[1<<FUTEX_HASHBITS];

/* Futex-fs vfsmount entry: */
static struct vfsmount *futex_mnt;

/*
 * We hash on the keys returned from get_futex_key (see below).
 */
static struct futex_hash_bucket *hash_futex(union futex_key *key)
{
	u32 hash = jhash2((u32*)&key->both.word,
			  (sizeof(key->both.word)+sizeof(key->both.ptr))/4,
			  key->both.offset);
	return &futex_queues[hash & ((1 << FUTEX_HASHBITS)-1)];
}

/*
 * Return 1 if two futex_keys are equal, 0 otherwise.
 */
static inline int match_futex(union futex_key *key1, union futex_key *key2)
{
	return (key1->both.word == key2->both.word
		&& key1->both.ptr == key2->both.ptr
		&& key1->both.offset == key2->both.offset);
}

/**
 * get_futex_key - Get parameters which are the keys for a futex.
 * @uaddr: virtual address of the futex
 * @shared: NULL for a PROCESS_PRIVATE futex,
 *	&current->mm->mmap_sem for a PROCESS_SHARED futex
 * @key: address where result is stored.
 *
 * Returns a negative error code or 0
 * The key words are stored in *key on success.
 *
 * For shared mappings, it's (page->index, vma->vm_file->f_path.dentry->d_inode,
 * offset_within_page).  For private mappings, it's (uaddr, current->mm).
 * We can usually work out the index without swapping in the page.
 *
 * fshared is NULL for PROCESS_PRIVATE futexes
 * For other futexes, it points to &current->mm->mmap_sem and
 * caller must have taken the reader lock. but NOT any spinlocks.
 */
int get_futex_key(u32 __user *uaddr, struct rw_semaphore *fshared,
		  union futex_key *key)
{
	unsigned long address = (unsigned long)uaddr;
	struct mm_struct *mm = current->mm;
	struct vm_area_struct *vma;
	struct page *page;
	int err;

	/*
	 * The futex address must be "naturally" aligned.
	 */
	key->both.offset = address % PAGE_SIZE;
	if (unlikely((address % sizeof(u32)) != 0))
		return -EINVAL;
	address -= key->both.offset;

	/*
	 * PROCESS_PRIVATE futexes are fast.
	 * As the mm cannot disappear under us and the 'key' only needs
	 * virtual address, we dont even have to find the underlying vma.
	 * Note : We do have to check 'uaddr' is a valid user address,
	 *        but access_ok() should be faster than find_vma()
	 */
	if (!fshared) {
		if (unlikely(!access_ok(VERIFY_WRITE, uaddr, sizeof(u32))))
			return -EFAULT;
		key->private.mm = mm;
		key->private.address = address;
		return 0;
	}
	/*
	 * The futex is hashed differently depending on whether
	 * it's in a shared or private mapping.  So check vma first.
	 */
	vma = find_extend_vma(mm, address);
	if (unlikely(!vma))
		return -EFAULT;

	/*
	 * Permissions.
	 */
	if (unlikely((vma->vm_flags & (VM_IO|VM_READ)) != VM_READ))
		return (vma->vm_flags & VM_IO) ? -EPERM : -EACCES;

	/*
	 * Private mappings are handled in a simple way.
	 *
	 * NOTE: When userspace waits on a MAP_SHARED mapping, even if
	 * it's a read-only handle, it's expected that futexes attach to
	 * the object not the particular process.  Therefore we use
	 * VM_MAYSHARE here, not VM_SHARED which is restricted to shared
	 * mappings of _writable_ handles.
	 */
	if (likely(!(vma->vm_flags & VM_MAYSHARE))) {
		key->both.offset |= FUT_OFF_MMSHARED; /* reference taken on mm */
		key->private.mm = mm;
		key->private.address = address;
		return 0;
	}

	/*
	 * Linear file mappings are also simple.
	 */
	key->shared.inode = vma->vm_file->f_path.dentry->d_inode;
	key->both.offset |= FUT_OFF_INODE; /* inode-based key. */
	if (likely(!(vma->vm_flags & VM_NONLINEAR))) {
		key->shared.pgoff = (((address - vma->vm_start) >> PAGE_SHIFT)
				     + vma->vm_pgoff);
		return 0;
	}

	/*
	 * We could walk the page table to read the non-linear
	 * pte, and get the page index without fetching the page
	 * from swap.  But that's a lot of code to duplicate here
	 * for a rare case, so we simply fetch the page.
	 */
	err = get_user_pages(current, mm, address, 1, 0, 0, &page, NULL);
	if (err >= 0) {
		key->shared.pgoff =
			page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT);
		put_page(page);
		return 0;
	}
	return err;
}
EXPORT_SYMBOL_GPL(get_futex_key);

/*
 * Take a reference to the resource addressed by a key.
 * Can be called while holding spinlocks.
 *
 */
inline void get_futex_key_refs(union futex_key *key)
{
	if (key->both.ptr == 0)
		return;
	switch (key->both.offset & (FUT_OFF_INODE|FUT_OFF_MMSHARED)) {
		case FUT_OFF_INODE:
			atomic_inc(&key->shared.inode->i_count);
			break;
		case FUT_OFF_MMSHARED:
			atomic_inc(&key->private.mm->mm_count);
			break;
	}
}
EXPORT_SYMBOL_GPL(get_futex_key_refs);

/*
 * Drop a reference to the resource addressed by a key.
 * The hash bucket spinlock must not be held.
 */
void drop_futex_key_refs(union futex_key *key)
{
	if (key->both.ptr == 0)
		return;
	switch (key->both.offset & (FUT_OFF_INODE|FUT_OFF_MMSHARED)) {
		case FUT_OFF_INODE:
			iput(key->shared.inode);
			break;
		case FUT_OFF_MMSHARED:
			mmdrop(key->private.mm);
			break;
	}
}
EXPORT_SYMBOL_GPL(drop_futex_key_refs);

static inline int get_futex_value_locked(u32 *dest, u32 __user *from)
{
	int ret;

	pagefault_disable();
	ret = __copy_from_user_inatomic(dest, from, sizeof(u32));
	pagefault_enable();

	return ret ? -EFAULT : 0;
}

/*
 * Fault handling.
 * if fshared is non NULL, current->mm->mmap_sem is already held
 */
static int futex_handle_fault(unsigned long address,
			      struct rw_semaphore *fshared, int attempt)
{
	struct vm_area_struct * vma;
	struct mm_struct *mm = current->mm;
	int ret = -EFAULT;

	if (attempt > 2)
		return ret;

	if (!fshared)
		down_read(&mm->mmap_sem);
	vma = find_vma(mm, address);
	if (vma && address >= vma->vm_start &&
	    (vma->vm_flags & VM_WRITE)) {
		switch (handle_mm_fault(mm, vma, address, 1)) {
		case VM_FAULT_MINOR:
			ret = 0;
			current->min_flt++;
			break;
		case VM_FAULT_MAJOR:
			ret = 0;
			current->maj_flt++;
			break;
		}
	}
	if (!fshared)
		up_read(&mm->mmap_sem);
	return ret;
}

/*
 * PI code:
 */
static int refill_pi_state_cache(void)
{
	struct futex_pi_state *pi_state;

	if (likely(current->pi_state_cache))
		return 0;

	pi_state = kzalloc(sizeof(*pi_state), GFP_KERNEL);

	if (!pi_state)
		return -ENOMEM;

	INIT_LIST_HEAD(&pi_state->list);
	/* pi_mutex gets initialized later */
	pi_state->owner = NULL;
	atomic_set(&pi_state->refcount, 1);

	current->pi_state_cache = pi_state;

	return 0;
}

static struct futex_pi_state * alloc_pi_state(void)
{
	struct futex_pi_state *pi_state = current->pi_state_cache;

	WARN_ON(!pi_state);
	current->pi_state_cache = NULL;

	return pi_state;
}

static void free_pi_state(struct futex_pi_state *pi_state)
{
	if (!atomic_dec_and_test(&pi_state->refcount))
		return;

	/*
	 * If pi_state->owner is NULL, the owner is most probably dying
	 * and has cleaned up the pi_state already
	 */
	if (pi_state->owner) {
		spin_lock_irq(&pi_state->owner->pi_lock);
		list_del_init(&pi_state->list);
		spin_unlock_irq(&pi_state->owner->pi_lock);

		rt_mutex_proxy_unlock(&pi_state->pi_mutex, pi_state->owner);
	}

	if (current->pi_state_cache)
		kfree(pi_state);
	else {
		/*
		 * pi_state->list is already empty.
		 * clear pi_state->owner.
		 * refcount is at 0 - put it back to 1.
		 */
		pi_state->owner = NULL;
		atomic_set(&pi_state->refcount, 1);
		current->pi_state_cache = pi_state;
	}
}

/*
 * Look up the task based on what TID userspace gave us.
 * We dont trust it.
 */
static struct task_struct * futex_find_get_task(pid_t pid)
{
	struct task_struct *p;

	rcu_read_lock();
	p = find_task_by_pid(pid);

	if (!p || ((current->euid != p->euid) && (current->euid != p->uid)))
		p = ERR_PTR(-ESRCH);
	else
		get_task_struct(p);

	rcu_read_unlock();

	return p;
}

/*
 * This task is holding PI mutexes at exit time => bad.
 * Kernel cleans up PI-state, but userspace is likely hosed.
 * (Robust-futex cleanup is separate and might save the day for userspace.)
 */
void exit_pi_state_list(struct task_struct *curr)
{
	struct list_head *next, *head = &curr->pi_state_list;
	struct futex_pi_state *pi_state;
	struct futex_hash_bucket *hb;
	union futex_key key;

	/*
	 * We are a ZOMBIE and nobody can enqueue itself on
	 * pi_state_list anymore, but we have to be careful
	 * versus waiters unqueueing themselves:
	 */
	spin_lock_irq(&curr->pi_lock);
	while (!list_empty(head)) {

		next = head->next;
		pi_state = list_entry(next, struct futex_pi_state, list);
		key = pi_state->key;
		hb = hash_futex(&key);
		spin_unlock_irq(&curr->pi_lock);

		spin_lock(&hb->lock);

		spin_lock_irq(&curr->pi_lock);
		/*
		 * We dropped the pi-lock, so re-check whether this
		 * task still owns the PI-state:
		 */
		if (head->next != next) {
			spin_unlock(&hb->lock);
			continue;
		}

		WARN_ON(pi_state->owner != curr);
		WARN_ON(list_empty(&pi_state->list));
		list_del_init(&pi_state->list);
		pi_state->owner = NULL;
		spin_unlock_irq(&curr->pi_lock);

		rt_mutex_unlock(&pi_state->pi_mutex);

		spin_unlock(&hb->lock);

		spin_lock_irq(&curr->pi_lock);
	}
	spin_unlock_irq(&curr->pi_lock);
}

static int
lookup_pi_state(u32 uval, struct futex_hash_bucket *hb,
		union futex_key *key, struct futex_pi_state **ps)
{
	struct futex_pi_state *pi_state = NULL;
	struct futex_q *this, *next;
	struct plist_head *head;
	struct task_struct *p;
	pid_t pid = uval & FUTEX_TID_MASK;

	head = &hb->chain;

	plist_for_each_entry_safe(this, next, head, list) {
		if (match_futex(&this->key, key)) {
			/*
			 * Another waiter already exists - bump up
			 * the refcount and return its pi_state:
			 */
			pi_state = this->pi_state;
			/*
			 * Userspace might have messed up non PI and PI futexes
			 */
			if (unlikely(!pi_state))
				return -EINVAL;

			WARN_ON(!atomic_read(&pi_state->refcount));
			WARN_ON(pid && pi_state->owner &&
				pi_state->owner->pid != pid);

			atomic_inc(&pi_state->refcount);
			*ps = pi_state;

			return 0;
		}
	}

	/*
	 * We are the first waiter - try to look up the real owner and attach
	 * the new pi_state to it, but bail out when TID = 0
	 */
	if (!pid)
		return -ESRCH;
	p = futex_find_get_task(pid);
	if (IS_ERR(p))
		return PTR_ERR(p);

	/*
	 * We need to look at the task state flags to figure out,
	 * whether the task is exiting. To protect against the do_exit
	 * change of the task flags, we do this protected by
	 * p->pi_lock: