return;
}
+ dec_zone_page_state(page, NR_MLOCK);
+ count_vm_event(UNEVICTABLE_PGCLEARED);
if (!isolate_lru_page(page)) {
putback_lru_page(page);
} else {
/*
- * Page not on the LRU yet. Flush all pagevecs and retry.
+ * We lost the race. the page already moved to evictable list.
*/
- lru_add_drain_all();
- if (!isolate_lru_page(page))
- putback_lru_page(page);
+ if (PageUnevictable(page))
+ count_vm_event(UNEVICTABLE_PGSTRANDED);
}
}
{
BUG_ON(!PageLocked(page));
- if (!TestSetPageMlocked(page) && !isolate_lru_page(page))
- putback_lru_page(page);
+ if (!TestSetPageMlocked(page)) {
+ inc_zone_page_state(page, NR_MLOCK);
+ count_vm_event(UNEVICTABLE_PGMLOCKED);
+ if (!isolate_lru_page(page))
+ putback_lru_page(page);
+ }
}
/*
{
BUG_ON(!PageLocked(page));
- if (TestClearPageMlocked(page) && !isolate_lru_page(page)) {
- try_to_munlock(page);
- putback_lru_page(page);
+ if (TestClearPageMlocked(page)) {
+ dec_zone_page_state(page, NR_MLOCK);
+ if (!isolate_lru_page(page)) {
+ int ret = try_to_munlock(page);
+ /*
+ * did try_to_unlock() succeed or punt?
+ */
+ if (ret == SWAP_SUCCESS || ret == SWAP_AGAIN)
+ count_vm_event(UNEVICTABLE_PGMUNLOCKED);
+
+ putback_lru_page(page);
+ } else {
+ /*
+ * We lost the race. let try_to_unmap() deal
+ * with it. At least we get the page state and
+ * mlock stats right. However, page is still on
+ * the noreclaim list. We'll fix that up when
+ * the page is eventually freed or we scan the
+ * noreclaim list.
+ */
+ if (PageUnevictable(page))
+ count_vm_event(UNEVICTABLE_PGSTRANDED);
+ else
+ count_vm_event(UNEVICTABLE_PGMUNLOCKED);
+ }
}
}
unsigned long addr = start;
struct page *pages[16]; /* 16 gives a reasonable batch */
int nr_pages = (end - start) / PAGE_SIZE;
- int ret;
+ int ret = 0;
int gup_flags = 0;
VM_BUG_ON(start & ~PAGE_MASK);
(atomic_read(&mm->mm_users) != 0));
/*
- * mlock: don't page populate if page has PROT_NONE permission.
- * munlock: the pages always do munlock althrough
- * its has PROT_NONE permission.
+ * mlock: don't page populate if vma has PROT_NONE permission.
+ * munlock: always do munlock although the vma has PROT_NONE
+ * permission, or SIGKILL is pending.
*/
if (!mlock)
- gup_flags |= GUP_FLAGS_IGNORE_VMA_PERMISSIONS;
+ gup_flags |= GUP_FLAGS_IGNORE_VMA_PERMISSIONS |
+ GUP_FLAGS_IGNORE_SIGKILL;
if (vma->vm_flags & VM_WRITE)
gup_flags |= GUP_FLAGS_WRITE;
- lru_add_drain_all(); /* push cached pages to LRU */
-
while (nr_pages > 0) {
int i;
addr += PAGE_SIZE; /* for next get_user_pages() */
nr_pages--;
}
+ ret = 0;
}
- lru_add_drain_all(); /* to update stats */
+ return ret; /* count entire vma as locked_vm */
+}
- return 0; /* count entire vma as locked_vm */
+/*
+ * convert get_user_pages() return value to posix mlock() error
+ */
+static int __mlock_posix_error_return(long retval)
+{
+ if (retval == -EFAULT)
+ retval = -ENOMEM;
+ else if (retval == -ENOMEM)
+ retval = -EAGAIN;
+ return retval;
}
#else /* CONFIG_UNEVICTABLE_LRU */
int mlock)
{
if (mlock && (vma->vm_flags & VM_LOCKED))
- make_pages_present(start, end);
+ return make_pages_present(start, end);
return 0;
}
+
+static inline int __mlock_posix_error_return(long retval)
+{
+ return 0;
+}
+
#endif /* CONFIG_UNEVICTABLE_LRU */
/**
*
* return number of pages [> 0] to be removed from locked_vm on success
* of "special" vmas.
- *
- * return negative error if vma spanning @start-@range disappears while
- * mmap semaphore is dropped. Unlikely?
*/
long mlock_vma_pages_range(struct vm_area_struct *vma,
unsigned long start, unsigned long end)
{
- struct mm_struct *mm = vma->vm_mm;
int nr_pages = (end - start) / PAGE_SIZE;
BUG_ON(!(vma->vm_flags & VM_LOCKED));
if (!((vma->vm_flags & (VM_DONTEXPAND | VM_RESERVED)) ||
is_vm_hugetlb_page(vma) ||
vma == get_gate_vma(current))) {
- long error;
- downgrade_write(&mm->mmap_sem);
- error = __mlock_vma_pages_range(vma, start, end, 1);
+ __mlock_vma_pages_range(vma, start, end, 1);
- up_read(&mm->mmap_sem);
- /* vma can change or disappear */
- down_write(&mm->mmap_sem);
- vma = find_vma(mm, start);
- /* non-NULL vma must contain @start, but need to check @end */
- if (!vma || end > vma->vm_end)
- return -ENOMEM;
-
- return 0; /* hide other errors from mmap(), et al */
+ /* Hide errors from mmap() and other callers */
+ return 0;
}
/*
vma->vm_flags = newflags;
if (lock) {
- /*
- * mmap_sem is currently held for write. Downgrade the write
- * lock to a read lock so that other faults, mmap scans, ...
- * while we fault in all pages.
- */
- downgrade_write(&mm->mmap_sem);
-
ret = __mlock_vma_pages_range(vma, start, end, 1);
+
if (ret > 0) {
mm->locked_vm -= ret;
ret = 0;
- }
- /*
- * Need to reacquire mmap sem in write mode, as our callers
- * expect this. We have no support for atomically upgrading
- * a sem to write, so we need to check for ranges while sem
- * is unlocked.
- */
- up_read(&mm->mmap_sem);
- /* vma can change or disappear */
- down_write(&mm->mmap_sem);
- *prev = find_vma(mm, start);
- /* non-NULL *prev must contain @start, but need to check @end */
- if (!(*prev) || end > (*prev)->vm_end)
- ret = -ENOMEM;
+ } else
+ ret = __mlock_posix_error_return(ret); /* translate if needed */
} else {
- /*
- * TODO: for unlocking, pages will already be resident, so
- * we don't need to wait for allocations/reclaim/pagein, ...
- * However, unlocking a very large region can still take a
- * while. Should we downgrade the semaphore for both lock
- * AND unlock ?
- */
__mlock_vma_pages_range(vma, start, end, 0);
}
return error;
}
-asmlinkage long sys_mlock(unsigned long start, size_t len)
+SYSCALL_DEFINE2(mlock, unsigned long, start, size_t, len)
{
unsigned long locked;
unsigned long lock_limit;
if (!can_do_mlock())
return -EPERM;
+ lru_add_drain_all(); /* flush pagevec */
+
down_write(¤t->mm->mmap_sem);
len = PAGE_ALIGN(len + (start & ~PAGE_MASK));
start &= PAGE_MASK;
return error;
}
-asmlinkage long sys_munlock(unsigned long start, size_t len)
+SYSCALL_DEFINE2(munlock, unsigned long, start, size_t, len)
{
int ret;
return 0;
}
-asmlinkage long sys_mlockall(int flags)
+SYSCALL_DEFINE1(mlockall, int, flags)
{
unsigned long lock_limit;
int ret = -EINVAL;
if (!can_do_mlock())
goto out;
+ lru_add_drain_all(); /* flush pagevec */
+
down_write(¤t->mm->mmap_sem);
lock_limit = current->signal->rlim[RLIMIT_MEMLOCK].rlim_cur;
return ret;
}
-asmlinkage long sys_munlockall(void)
+SYSCALL_DEFINE0(munlockall)
{
int ret;
spin_unlock(&shmlock_user_lock);
free_uid(user);
}
+
+void *alloc_locked_buffer(size_t size)
+{
+ unsigned long rlim, vm, pgsz;
+ void *buffer = NULL;
+
+ pgsz = PAGE_ALIGN(size) >> PAGE_SHIFT;
+
+ down_write(¤t->mm->mmap_sem);
+
+ rlim = current->signal->rlim[RLIMIT_AS].rlim_cur >> PAGE_SHIFT;
+ vm = current->mm->total_vm + pgsz;
+ if (rlim < vm)
+ goto out;
+
+ rlim = current->signal->rlim[RLIMIT_MEMLOCK].rlim_cur >> PAGE_SHIFT;
+ vm = current->mm->locked_vm + pgsz;
+ if (rlim < vm)
+ goto out;
+
+ buffer = kzalloc(size, GFP_KERNEL);
+ if (!buffer)
+ goto out;
+
+ current->mm->total_vm += pgsz;
+ current->mm->locked_vm += pgsz;
+
+ out:
+ up_write(¤t->mm->mmap_sem);
+ return buffer;
+}
+
+void release_locked_buffer(void *buffer, size_t size)
+{
+ unsigned long pgsz = PAGE_ALIGN(size) >> PAGE_SHIFT;
+
+ down_write(¤t->mm->mmap_sem);
+
+ current->mm->total_vm -= pgsz;
+ current->mm->locked_vm -= pgsz;
+
+ up_write(¤t->mm->mmap_sem);
+}
+
+void free_locked_buffer(void *buffer, size_t size)
+{
+ release_locked_buffer(buffer, size);
+
+ kfree(buffer);
+}