Merge branch 'core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip
* 'core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: (63 commits) stacktrace: provide save_stack_trace_tsk() weak alias rcu: provide RCU options on non-preempt architectures too printk: fix discarding message when recursion_bug futex: clean up futex_(un)lock_pi fault handling "Tree RCU": scalable classic RCU implementation futex: rename field in futex_q to clarify single waiter semantics x86/swiotlb: add default swiotlb_arch_range_needs_mapping x86/swiotlb: add default phys<->bus conversion x86: unify pci iommu setup and allow swiotlb to compile for 32 bit x86: add swiotlb allocation functions swiotlb: consolidate swiotlb info message printing swiotlb: support bouncing of HighMem pages swiotlb: factor out copy to/from device swiotlb: add arch hook to force mapping swiotlb: allow architectures to override phys<->bus<->phys conversions swiotlb: add comment where we handle the overflow of a dma mask on 32 bit rcu: fix rcutorture behavior during reboot resources: skip sanity check of busy resources swiotlb: move some definitions to header swiotlb: allow architectures to override swiotlb pool allocation ... Fix up trivial conflicts in arch/x86/kernel/Makefile arch/x86/mm/init_32.c include/linux/hardirq.h as per Ingo's suggestions.
This commit is contained in:
351
kernel/futex.c
351
kernel/futex.c
@@ -92,11 +92,12 @@ struct futex_pi_state {
|
||||
* 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.
|
||||
* wake up q->waiter, then make the second condition true.
|
||||
*/
|
||||
struct futex_q {
|
||||
struct plist_node list;
|
||||
wait_queue_head_t waiters;
|
||||
/* There can only be a single waiter */
|
||||
wait_queue_head_t waiter;
|
||||
|
||||
/* Which hash list lock to use: */
|
||||
spinlock_t *lock_ptr;
|
||||
@@ -122,24 +123,6 @@ struct futex_hash_bucket {
|
||||
|
||||
static struct futex_hash_bucket futex_queues[1<<FUTEX_HASHBITS];
|
||||
|
||||
/*
|
||||
* Take mm->mmap_sem, when futex is shared
|
||||
*/
|
||||
static inline void futex_lock_mm(struct rw_semaphore *fshared)
|
||||
{
|
||||
if (fshared)
|
||||
down_read(fshared);
|
||||
}
|
||||
|
||||
/*
|
||||
* Release mm->mmap_sem, when the futex is shared
|
||||
*/
|
||||
static inline void futex_unlock_mm(struct rw_semaphore *fshared)
|
||||
{
|
||||
if (fshared)
|
||||
up_read(fshared);
|
||||
}
|
||||
|
||||
/*
|
||||
* We hash on the keys returned from get_futex_key (see below).
|
||||
*/
|
||||
@@ -161,6 +144,45 @@ static inline int match_futex(union futex_key *key1, union futex_key *key2)
|
||||
&& key1->both.offset == key2->both.offset);
|
||||
}
|
||||
|
||||
/*
|
||||
* Take a reference to the resource addressed by a key.
|
||||
* Can be called while holding spinlocks.
|
||||
*
|
||||
*/
|
||||
static void get_futex_key_refs(union futex_key *key)
|
||||
{
|
||||
if (!key->both.ptr)
|
||||
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;
|
||||
}
|
||||
}
|
||||
|
||||
/*
|
||||
* Drop a reference to the resource addressed by a key.
|
||||
* The hash bucket spinlock must not be held.
|
||||
*/
|
||||
static void drop_futex_key_refs(union futex_key *key)
|
||||
{
|
||||
if (!key->both.ptr)
|
||||
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;
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* get_futex_key - Get parameters which are the keys for a futex.
|
||||
* @uaddr: virtual address of the futex
|
||||
@@ -179,12 +201,10 @@ static inline int match_futex(union futex_key *key1, union futex_key *key2)
|
||||
* For other futexes, it points to ¤t->mm->mmap_sem and
|
||||
* caller must have taken the reader lock. but NOT any spinlocks.
|
||||
*/
|
||||
static int get_futex_key(u32 __user *uaddr, struct rw_semaphore *fshared,
|
||||
union futex_key *key)
|
||||
static int get_futex_key(u32 __user *uaddr, int 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;
|
||||
|
||||
@@ -208,100 +228,50 @@ static int get_futex_key(u32 __user *uaddr, struct rw_semaphore *fshared,
|
||||
return -EFAULT;
|
||||
key->private.mm = mm;
|
||||
key->private.address = address;
|
||||
get_futex_key_refs(key);
|
||||
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;
|
||||
again:
|
||||
err = get_user_pages_fast(address, 1, 0, &page);
|
||||
if (err < 0)
|
||||
return err;
|
||||
|
||||
lock_page(page);
|
||||
if (!page->mapping) {
|
||||
unlock_page(page);
|
||||
put_page(page);
|
||||
goto again;
|
||||
}
|
||||
|
||||
/*
|
||||
* 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.
|
||||
* the object not the particular process.
|
||||
*/
|
||||
if (likely(!(vma->vm_flags & VM_MAYSHARE))) {
|
||||
key->both.offset |= FUT_OFF_MMSHARED; /* reference taken on mm */
|
||||
if (PageAnon(page)) {
|
||||
key->both.offset |= FUT_OFF_MMSHARED; /* ref taken on mm */
|
||||
key->private.mm = mm;
|
||||
key->private.address = address;
|
||||
return 0;
|
||||
} else {
|
||||
key->both.offset |= FUT_OFF_INODE; /* inode-based key */
|
||||
key->shared.inode = page->mapping->host;
|
||||
key->shared.pgoff = page->index;
|
||||
}
|
||||
|
||||
/*
|
||||
* 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;
|
||||
}
|
||||
get_futex_key_refs(key);
|
||||
|
||||
/*
|
||||
* 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;
|
||||
unlock_page(page);
|
||||
put_page(page);
|
||||
return 0;
|
||||
}
|
||||
|
||||
/*
|
||||
* Take a reference to the resource addressed by a key.
|
||||
* Can be called while holding spinlocks.
|
||||
*
|
||||
*/
|
||||
static void get_futex_key_refs(union futex_key *key)
|
||||
static inline
|
||||
void put_futex_key(int fshared, union futex_key *key)
|
||||
{
|
||||
if (key->both.ptr == NULL)
|
||||
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;
|
||||
}
|
||||
}
|
||||
|
||||
/*
|
||||
* Drop a reference to the resource addressed by a key.
|
||||
* The hash bucket spinlock must not be held.
|
||||
*/
|
||||
static void drop_futex_key_refs(union futex_key *key)
|
||||
{
|
||||
if (!key->both.ptr)
|
||||
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;
|
||||
}
|
||||
drop_futex_key_refs(key);
|
||||
}
|
||||
|
||||
static u32 cmpxchg_futex_value_locked(u32 __user *uaddr, u32 uval, u32 newval)
|
||||
@@ -328,10 +298,8 @@ static int get_futex_value_locked(u32 *dest, u32 __user *from)
|
||||
|
||||
/*
|
||||
* 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)
|
||||
static int futex_handle_fault(unsigned long address, int attempt)
|
||||
{
|
||||
struct vm_area_struct * vma;
|
||||
struct mm_struct *mm = current->mm;
|
||||
@@ -340,8 +308,7 @@ static int futex_handle_fault(unsigned long address,
|
||||
if (attempt > 2)
|
||||
return ret;
|
||||
|
||||
if (!fshared)
|
||||
down_read(&mm->mmap_sem);
|
||||
down_read(&mm->mmap_sem);
|
||||
vma = find_vma(mm, address);
|
||||
if (vma && address >= vma->vm_start &&
|
||||
(vma->vm_flags & VM_WRITE)) {
|
||||
@@ -361,8 +328,7 @@ static int futex_handle_fault(unsigned long address,
|
||||
current->min_flt++;
|
||||
}
|
||||
}
|
||||
if (!fshared)
|
||||
up_read(&mm->mmap_sem);
|
||||
up_read(&mm->mmap_sem);
|
||||
return ret;
|
||||
}
|
||||
|
||||
@@ -385,6 +351,7 @@ static int refill_pi_state_cache(void)
|
||||
/* pi_mutex gets initialized later */
|
||||
pi_state->owner = NULL;
|
||||
atomic_set(&pi_state->refcount, 1);
|
||||
pi_state->key = FUTEX_KEY_INIT;
|
||||
|
||||
current->pi_state_cache = pi_state;
|
||||
|
||||
@@ -469,7 +436,7 @@ 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;
|
||||
union futex_key key = FUTEX_KEY_INIT;
|
||||
|
||||
if (!futex_cmpxchg_enabled)
|
||||
return;
|
||||
@@ -614,7 +581,7 @@ static void wake_futex(struct futex_q *q)
|
||||
* The lock in wake_up_all() is a crucial memory barrier after the
|
||||
* plist_del() and also before assigning to q->lock_ptr.
|
||||
*/
|
||||
wake_up_all(&q->waiters);
|
||||
wake_up(&q->waiter);
|
||||
/*
|
||||
* The waiting task can free the futex_q as soon as this is written,
|
||||
* without taking any locks. This must come last.
|
||||
@@ -726,20 +693,17 @@ double_lock_hb(struct futex_hash_bucket *hb1, struct futex_hash_bucket *hb2)
|
||||
* Wake up all waiters hashed on the physical page that is mapped
|
||||
* to this virtual address:
|
||||
*/
|
||||
static int futex_wake(u32 __user *uaddr, struct rw_semaphore *fshared,
|
||||
int nr_wake, u32 bitset)
|
||||
static int futex_wake(u32 __user *uaddr, int fshared, int nr_wake, u32 bitset)
|
||||
{
|
||||
struct futex_hash_bucket *hb;
|
||||
struct futex_q *this, *next;
|
||||
struct plist_head *head;
|
||||
union futex_key key;
|
||||
union futex_key key = FUTEX_KEY_INIT;
|
||||
int ret;
|
||||
|
||||
if (!bitset)
|
||||
return -EINVAL;
|
||||
|
||||
futex_lock_mm(fshared);
|
||||
|
||||
ret = get_futex_key(uaddr, fshared, &key);
|
||||
if (unlikely(ret != 0))
|
||||
goto out;
|
||||
@@ -767,7 +731,7 @@ static int futex_wake(u32 __user *uaddr, struct rw_semaphore *fshared,
|
||||
|
||||
spin_unlock(&hb->lock);
|
||||
out:
|
||||
futex_unlock_mm(fshared);
|
||||
put_futex_key(fshared, &key);
|
||||
return ret;
|
||||
}
|
||||
|
||||
@@ -776,19 +740,16 @@ out:
|
||||
* to this virtual address:
|
||||
*/
|
||||
static int
|
||||
futex_wake_op(u32 __user *uaddr1, struct rw_semaphore *fshared,
|
||||
u32 __user *uaddr2,
|
||||
futex_wake_op(u32 __user *uaddr1, int fshared, u32 __user *uaddr2,
|
||||
int nr_wake, int nr_wake2, int op)
|
||||
{
|
||||
union futex_key key1, key2;
|
||||
union futex_key key1 = FUTEX_KEY_INIT, key2 = FUTEX_KEY_INIT;
|
||||
struct futex_hash_bucket *hb1, *hb2;
|
||||
struct plist_head *head;
|
||||
struct futex_q *this, *next;
|
||||
int ret, op_ret, attempt = 0;
|
||||
|
||||
retryfull:
|
||||
futex_lock_mm(fshared);
|
||||
|
||||
ret = get_futex_key(uaddr1, fshared, &key1);
|
||||
if (unlikely(ret != 0))
|
||||
goto out;
|
||||
@@ -833,18 +794,12 @@ retry:
|
||||
*/
|
||||
if (attempt++) {
|
||||
ret = futex_handle_fault((unsigned long)uaddr2,
|
||||
fshared, attempt);
|
||||
attempt);
|
||||
if (ret)
|
||||
goto out;
|
||||
goto retry;
|
||||
}
|
||||
|
||||
/*
|
||||
* If we would have faulted, release mmap_sem,
|
||||
* fault it in and start all over again.
|
||||
*/
|
||||
futex_unlock_mm(fshared);
|
||||
|
||||
ret = get_user(dummy, uaddr2);
|
||||
if (ret)
|
||||
return ret;
|
||||
@@ -880,7 +835,8 @@ retry:
|
||||
if (hb1 != hb2)
|
||||
spin_unlock(&hb2->lock);
|
||||
out:
|
||||
futex_unlock_mm(fshared);
|
||||
put_futex_key(fshared, &key2);
|
||||
put_futex_key(fshared, &key1);
|
||||
|
||||
return ret;
|
||||
}
|
||||
@@ -889,19 +845,16 @@ out:
|
||||
* Requeue all waiters hashed on one physical page to another
|
||||
* physical page.
|
||||
*/
|
||||
static int futex_requeue(u32 __user *uaddr1, struct rw_semaphore *fshared,
|
||||
u32 __user *uaddr2,
|
||||
static int futex_requeue(u32 __user *uaddr1, int fshared, u32 __user *uaddr2,
|
||||
int nr_wake, int nr_requeue, u32 *cmpval)
|
||||
{
|
||||
union futex_key key1, key2;
|
||||
union futex_key key1 = FUTEX_KEY_INIT, key2 = FUTEX_KEY_INIT;
|
||||
struct futex_hash_bucket *hb1, *hb2;
|
||||
struct plist_head *head1;
|
||||
struct futex_q *this, *next;
|
||||
int ret, drop_count = 0;
|
||||
|
||||
retry:
|
||||
futex_lock_mm(fshared);
|
||||
|
||||
ret = get_futex_key(uaddr1, fshared, &key1);
|
||||
if (unlikely(ret != 0))
|
||||
goto out;
|
||||
@@ -924,12 +877,6 @@ static int futex_requeue(u32 __user *uaddr1, struct rw_semaphore *fshared,
|
||||
if (hb1 != hb2)
|
||||
spin_unlock(&hb2->lock);
|
||||
|
||||
/*
|
||||
* If we would have faulted, release mmap_sem, fault
|
||||
* it in and start all over again.
|
||||
*/
|
||||
futex_unlock_mm(fshared);
|
||||
|
||||
ret = get_user(curval, uaddr1);
|
||||
|
||||
if (!ret)
|
||||
@@ -981,7 +928,8 @@ out_unlock:
|
||||
drop_futex_key_refs(&key1);
|
||||
|
||||
out:
|
||||
futex_unlock_mm(fshared);
|
||||
put_futex_key(fshared, &key2);
|
||||
put_futex_key(fshared, &key1);
|
||||
return ret;
|
||||
}
|
||||
|
||||
@@ -990,7 +938,7 @@ static inline struct futex_hash_bucket *queue_lock(struct futex_q *q)
|
||||
{
|
||||
struct futex_hash_bucket *hb;
|
||||
|
||||
init_waitqueue_head(&q->waiters);
|
||||
init_waitqueue_head(&q->waiter);
|
||||
|
||||
get_futex_key_refs(&q->key);
|
||||
hb = hash_futex(&q->key);
|
||||
@@ -1103,8 +1051,7 @@ static void unqueue_me_pi(struct futex_q *q)
|
||||
* private futexes.
|
||||
*/
|
||||
static int fixup_pi_state_owner(u32 __user *uaddr, struct futex_q *q,
|
||||
struct task_struct *newowner,
|
||||
struct rw_semaphore *fshared)
|
||||
struct task_struct *newowner, int fshared)
|
||||
{
|
||||
u32 newtid = task_pid_vnr(newowner) | FUTEX_WAITERS;
|
||||
struct futex_pi_state *pi_state = q->pi_state;
|
||||
@@ -1183,7 +1130,7 @@ retry:
|
||||
handle_fault:
|
||||
spin_unlock(q->lock_ptr);
|
||||
|
||||
ret = futex_handle_fault((unsigned long)uaddr, fshared, attempt++);
|
||||
ret = futex_handle_fault((unsigned long)uaddr, attempt++);
|
||||
|
||||
spin_lock(q->lock_ptr);
|
||||
|
||||
@@ -1203,12 +1150,13 @@ handle_fault:
|
||||
* In case we must use restart_block to restart a futex_wait,
|
||||
* we encode in the 'flags' shared capability
|
||||
*/
|
||||
#define FLAGS_SHARED 1
|
||||
#define FLAGS_SHARED 0x01
|
||||
#define FLAGS_CLOCKRT 0x02
|
||||
|
||||
static long futex_wait_restart(struct restart_block *restart);
|
||||
|
||||
static int futex_wait(u32 __user *uaddr, struct rw_semaphore *fshared,
|
||||
u32 val, ktime_t *abs_time, u32 bitset)
|
||||
static int futex_wait(u32 __user *uaddr, int fshared,
|
||||
u32 val, ktime_t *abs_time, u32 bitset, int clockrt)
|
||||
{
|
||||
struct task_struct *curr = current;
|
||||
DECLARE_WAITQUEUE(wait, curr);
|
||||
@@ -1225,8 +1173,7 @@ static int futex_wait(u32 __user *uaddr, struct rw_semaphore *fshared,
|
||||
q.pi_state = NULL;
|
||||
q.bitset = bitset;
|
||||
retry:
|
||||
futex_lock_mm(fshared);
|
||||
|
||||
q.key = FUTEX_KEY_INIT;
|
||||
ret = get_futex_key(uaddr, fshared, &q.key);
|
||||
if (unlikely(ret != 0))
|
||||
goto out_release_sem;
|
||||
@@ -1258,12 +1205,6 @@ static int futex_wait(u32 __user *uaddr, struct rw_semaphore *fshared,
|
||||
if (unlikely(ret)) {
|
||||
queue_unlock(&q, hb);
|
||||
|
||||
/*
|
||||
* If we would have faulted, release mmap_sem, fault it in and
|
||||
* start all over again.
|
||||
*/
|
||||
futex_unlock_mm(fshared);
|
||||
|
||||
ret = get_user(uval, uaddr);
|
||||
|
||||
if (!ret)
|
||||
@@ -1277,12 +1218,6 @@ static int futex_wait(u32 __user *uaddr, struct rw_semaphore *fshared,
|
||||
/* Only actually queue if *uaddr contained val. */
|
||||
queue_me(&q, hb);
|
||||
|
||||
/*
|
||||
* Now the futex is queued and we have checked the data, we
|
||||
* don't want to hold mmap_sem while we sleep.
|
||||
*/
|
||||
futex_unlock_mm(fshared);
|
||||
|
||||
/*
|
||||
* There might have been scheduling since the queue_me(), as we
|
||||
* cannot hold a spinlock across the get_user() in case it
|
||||
@@ -1294,7 +1229,7 @@ static int futex_wait(u32 __user *uaddr, struct rw_semaphore *fshared,
|
||||
|
||||
/* add_wait_queue is the barrier after __set_current_state. */
|
||||
__set_current_state(TASK_INTERRUPTIBLE);
|
||||
add_wait_queue(&q.waiters, &wait);
|
||||
add_wait_queue(&q.waiter, &wait);
|
||||
/*
|
||||
* !plist_node_empty() is safe here without any lock.
|
||||
* q.lock_ptr != 0 is not safe, because of ordering against wakeup.
|
||||
@@ -1307,8 +1242,10 @@ static int futex_wait(u32 __user *uaddr, struct rw_semaphore *fshared,
|
||||
slack = current->timer_slack_ns;
|
||||
if (rt_task(current))
|
||||
slack = 0;
|
||||
hrtimer_init_on_stack(&t.timer, CLOCK_MONOTONIC,
|
||||
HRTIMER_MODE_ABS);
|
||||
hrtimer_init_on_stack(&t.timer,
|
||||
clockrt ? CLOCK_REALTIME :
|
||||
CLOCK_MONOTONIC,
|
||||
HRTIMER_MODE_ABS);
|
||||
hrtimer_init_sleeper(&t, current);
|
||||
hrtimer_set_expires_range_ns(&t.timer, *abs_time, slack);
|
||||
|
||||
@@ -1363,6 +1300,8 @@ static int futex_wait(u32 __user *uaddr, struct rw_semaphore *fshared,
|
||||
|
||||
if (fshared)
|
||||
restart->futex.flags |= FLAGS_SHARED;
|
||||
if (clockrt)
|
||||
restart->futex.flags |= FLAGS_CLOCKRT;
|
||||
return -ERESTART_RESTARTBLOCK;
|
||||
}
|
||||
|
||||
@@ -1370,7 +1309,7 @@ static int futex_wait(u32 __user *uaddr, struct rw_semaphore *fshared,
|
||||
queue_unlock(&q, hb);
|
||||
|
||||
out_release_sem:
|
||||
futex_unlock_mm(fshared);
|
||||
put_futex_key(fshared, &q.key);
|
||||
return ret;
|
||||
}
|
||||
|
||||
@@ -1378,15 +1317,16 @@ static int futex_wait(u32 __user *uaddr, struct rw_semaphore *fshared,
|
||||
static long futex_wait_restart(struct restart_block *restart)
|
||||
{
|
||||
u32 __user *uaddr = (u32 __user *)restart->futex.uaddr;
|
||||
struct rw_semaphore *fshared = NULL;
|
||||
int fshared = 0;
|
||||
ktime_t t;
|
||||
|
||||
t.tv64 = restart->futex.time;
|
||||
restart->fn = do_no_restart_syscall;
|
||||
if (restart->futex.flags & FLAGS_SHARED)
|
||||
fshared = ¤t->mm->mmap_sem;
|
||||
fshared = 1;
|
||||
return (long)futex_wait(uaddr, fshared, restart->futex.val, &t,
|
||||
restart->futex.bitset);
|
||||
restart->futex.bitset,
|
||||
restart->futex.flags & FLAGS_CLOCKRT);
|
||||
}
|
||||
|
||||
|
||||
@@ -1396,7 +1336,7 @@ static long futex_wait_restart(struct restart_block *restart)
|
||||
* if there are waiters then it will block, it does PI, etc. (Due to
|
||||
* races the kernel might see a 0 value of the futex too.)
|
||||
*/
|
||||
static int futex_lock_pi(u32 __user *uaddr, struct rw_semaphore *fshared,
|
||||
static int futex_lock_pi(u32 __user *uaddr, int fshared,
|
||||
int detect, ktime_t *time, int trylock)
|
||||
{
|
||||
struct hrtimer_sleeper timeout, *to = NULL;
|
||||
@@ -1419,8 +1359,7 @@ static int futex_lock_pi(u32 __user *uaddr, struct rw_semaphore *fshared,
|
||||
|
||||
q.pi_state = NULL;
|
||||
retry:
|
||||
futex_lock_mm(fshared);
|
||||
|
||||
q.key = FUTEX_KEY_INIT;
|
||||
ret = get_futex_key(uaddr, fshared, &q.key);
|
||||
if (unlikely(ret != 0))
|
||||
goto out_release_sem;
|
||||
@@ -1509,7 +1448,6 @@ static int futex_lock_pi(u32 __user *uaddr, struct rw_semaphore *fshared,
|
||||
* exit to complete.
|
||||
*/
|
||||
queue_unlock(&q, hb);
|
||||
futex_unlock_mm(fshared);
|
||||
cond_resched();
|
||||
goto retry;
|
||||
|
||||
@@ -1541,12 +1479,6 @@ static int futex_lock_pi(u32 __user *uaddr, struct rw_semaphore *fshared,
|
||||
*/
|
||||
queue_me(&q, hb);
|
||||
|
||||
/*
|
||||
* Now the futex is queued and we have checked the data, we
|
||||
* don't want to hold mmap_sem while we sleep.
|
||||
*/
|
||||
futex_unlock_mm(fshared);
|
||||
|
||||
WARN_ON(!q.pi_state);
|
||||
/*
|
||||
* Block on the PI mutex:
|
||||
@@ -1559,7 +1491,6 @@ static int futex_lock_pi(u32 __user *uaddr, struct rw_semaphore *fshared,
|
||||
ret = ret ? 0 : -EWOULDBLOCK;
|
||||
}
|
||||
|
||||
futex_lock_mm(fshared);
|
||||
spin_lock(q.lock_ptr);
|
||||
|
||||
if (!ret) {
|
||||
@@ -1625,7 +1556,6 @@ static int futex_lock_pi(u32 __user *uaddr, struct rw_semaphore *fshared,
|
||||
|
||||
/* Unqueue and drop the lock */
|
||||
unqueue_me_pi(&q);
|
||||
futex_unlock_mm(fshared);
|
||||
|
||||
if (to)
|
||||
destroy_hrtimer_on_stack(&to->timer);
|
||||
@@ -1635,34 +1565,30 @@ static int futex_lock_pi(u32 __user *uaddr, struct rw_semaphore *fshared,
|
||||
queue_unlock(&q, hb);
|
||||
|
||||
out_release_sem:
|
||||
futex_unlock_mm(fshared);
|
||||
put_futex_key(fshared, &q.key);
|
||||
if (to)
|
||||
destroy_hrtimer_on_stack(&to->timer);
|
||||
return ret;
|
||||
|
||||
uaddr_faulted:
|
||||
/*
|
||||
* We have to r/w *(int __user *)uaddr, but we can't modify it
|
||||
* non-atomically. Therefore, if get_user below is not
|
||||
* enough, we need to handle the fault ourselves, while
|
||||
* still holding the mmap_sem.
|
||||
*
|
||||
* ... and hb->lock. :-) --ANK
|
||||
* We have to r/w *(int __user *)uaddr, and we have to modify it
|
||||
* atomically. Therefore, if we continue to fault after get_user()
|
||||
* below, we need to handle the fault ourselves, while still holding
|
||||
* the mmap_sem. This can occur if the uaddr is under contention as
|
||||
* we have to drop the mmap_sem in order to call get_user().
|
||||
*/
|
||||
queue_unlock(&q, hb);
|
||||
|
||||
if (attempt++) {
|
||||
ret = futex_handle_fault((unsigned long)uaddr, fshared,
|
||||
attempt);
|
||||
ret = futex_handle_fault((unsigned long)uaddr, attempt);
|
||||
if (ret)
|
||||
goto out_release_sem;
|
||||
goto retry_unlocked;
|
||||
}
|
||||
|
||||
futex_unlock_mm(fshared);
|
||||
|
||||
ret = get_user(uval, uaddr);
|
||||
if (!ret && (uval != -EFAULT))
|
||||
if (!ret)
|
||||
goto retry;
|
||||
|
||||
if (to)
|
||||
@@ -1675,13 +1601,13 @@ static int futex_lock_pi(u32 __user *uaddr, struct rw_semaphore *fshared,
|
||||
* This is the in-kernel slowpath: we look up the PI state (if any),
|
||||
* and do the rt-mutex unlock.
|
||||
*/
|
||||
static int futex_unlock_pi(u32 __user *uaddr, struct rw_semaphore *fshared)
|
||||
static int futex_unlock_pi(u32 __user *uaddr, int fshared)
|
||||
{
|
||||
struct futex_hash_bucket *hb;
|
||||
struct futex_q *this, *next;
|
||||
u32 uval;
|
||||
struct plist_head *head;
|
||||
union futex_key key;
|
||||
union futex_key key = FUTEX_KEY_INIT;
|
||||
int ret, attempt = 0;
|
||||
|
||||
retry:
|
||||
@@ -1692,10 +1618,6 @@ retry:
|
||||
*/
|
||||
if ((uval & FUTEX_TID_MASK) != task_pid_vnr(current))
|
||||
return -EPERM;
|
||||
/*
|
||||
* First take all the futex related locks:
|
||||
*/
|
||||
futex_lock_mm(fshared);
|
||||
|
||||
ret = get_futex_key(uaddr, fshared, &key);
|
||||
if (unlikely(ret != 0))
|
||||
@@ -1754,34 +1676,30 @@ retry_unlocked:
|
||||
out_unlock:
|
||||
spin_unlock(&hb->lock);
|
||||
out:
|
||||
futex_unlock_mm(fshared);
|
||||
put_futex_key(fshared, &key);
|
||||
|
||||
return ret;
|
||||
|
||||
pi_faulted:
|
||||
/*
|
||||
* We have to r/w *(int __user *)uaddr, but we can't modify it
|
||||
* non-atomically. Therefore, if get_user below is not
|
||||
* enough, we need to handle the fault ourselves, while
|
||||
* still holding the mmap_sem.
|
||||
*
|
||||
* ... and hb->lock. --ANK
|
||||
* We have to r/w *(int __user *)uaddr, and we have to modify it
|
||||
* atomically. Therefore, if we continue to fault after get_user()
|
||||
* below, we need to handle the fault ourselves, while still holding
|
||||
* the mmap_sem. This can occur if the uaddr is under contention as
|
||||
* we have to drop the mmap_sem in order to call get_user().
|
||||
*/
|
||||
spin_unlock(&hb->lock);
|
||||
|
||||
if (attempt++) {
|
||||
ret = futex_handle_fault((unsigned long)uaddr, fshared,
|
||||
attempt);
|
||||
ret = futex_handle_fault((unsigned long)uaddr, attempt);
|
||||
if (ret)
|
||||
goto out;
|
||||
uval = 0;
|
||||
goto retry_unlocked;
|
||||
}
|
||||
|
||||
futex_unlock_mm(fshared);
|
||||
|
||||
ret = get_user(uval, uaddr);
|
||||
if (!ret && (uval != -EFAULT))
|
||||
if (!ret)
|
||||
goto retry;
|
||||
|
||||
return ret;
|
||||
@@ -1908,8 +1826,7 @@ retry:
|
||||
* PI futexes happens in exit_pi_state():
|
||||
*/
|
||||
if (!pi && (uval & FUTEX_WAITERS))
|
||||
futex_wake(uaddr, &curr->mm->mmap_sem, 1,
|
||||
FUTEX_BITSET_MATCH_ANY);
|
||||
futex_wake(uaddr, 1, 1, FUTEX_BITSET_MATCH_ANY);
|
||||
}
|
||||
return 0;
|
||||
}
|
||||
@@ -2003,18 +1920,22 @@ void exit_robust_list(struct task_struct *curr)
|
||||
long do_futex(u32 __user *uaddr, int op, u32 val, ktime_t *timeout,
|
||||
u32 __user *uaddr2, u32 val2, u32 val3)
|
||||
{
|
||||
int ret = -ENOSYS;
|
||||
int clockrt, ret = -ENOSYS;
|
||||
int cmd = op & FUTEX_CMD_MASK;
|
||||
struct rw_semaphore *fshared = NULL;
|
||||
int fshared = 0;
|
||||
|
||||
if (!(op & FUTEX_PRIVATE_FLAG))
|
||||
fshared = ¤t->mm->mmap_sem;
|
||||
fshared = 1;
|
||||
|
||||
clockrt = op & FUTEX_CLOCK_REALTIME;
|
||||
if (clockrt && cmd != FUTEX_WAIT_BITSET)
|
||||
return -ENOSYS;
|
||||
|
||||
switch (cmd) {
|
||||
case FUTEX_WAIT:
|
||||
val3 = FUTEX_BITSET_MATCH_ANY;
|
||||
case FUTEX_WAIT_BITSET:
|
||||
ret = futex_wait(uaddr, fshared, val, timeout, val3);
|
||||
ret = futex_wait(uaddr, fshared, val, timeout, val3, clockrt);
|
||||
break;
|
||||
case FUTEX_WAKE:
|
||||
val3 = FUTEX_BITSET_MATCH_ANY;
|
||||
|
Reference in New Issue
Block a user