SWP_PAGE_DISCARD = (1 << 10), /* freed swap page-cluster discards */
SWP_STABLE_WRITES = (1 << 11), /* no overwrite PG_writeback pages */
SWP_SYNCHRONOUS_IO = (1 << 12), /* synchronous IO is efficient */
+ SWP_HIBERNATION = (1 << 13), /* pinned for hibernation */
/* add others here before... */
};
}
extern void si_swapinfo(struct sysinfo *);
-int swap_type_of(dev_t device, sector_t offset);
+extern int pin_hibernation_swap_type(dev_t device, sector_t offset);
+extern void unpin_hibernation_swap_type(int type);
+extern int find_hibernation_swap_type(dev_t device, sector_t offset);
int find_first_swap(dev_t *device);
extern unsigned int count_swap_pages(int, int);
extern sector_t swapdev_block(int, pgoff_t);
memset(&data->handle, 0, sizeof(struct snapshot_handle));
if ((filp->f_flags & O_ACCMODE) == O_RDONLY) {
/* Hibernating. The image device should be accessible. */
- data->swap = swap_type_of(swsusp_resume_device, 0);
+ data->swap = pin_hibernation_swap_type(swsusp_resume_device, 0);
data->mode = O_RDONLY;
data->free_bitmaps = false;
error = pm_notifier_call_chain_robust(PM_HIBERNATION_PREPARE, PM_POST_HIBERNATION);
data->free_bitmaps = !error;
}
}
- if (error)
+ if (error) {
+ unpin_hibernation_swap_type(data->swap);
hibernate_release();
+ }
data->frozen = false;
data->ready = false;
data = filp->private_data;
data->dev = 0;
free_all_swap_pages(data->swap);
+ unpin_hibernation_swap_type(data->swap);
if (data->frozen) {
pm_restore_gfp_mask();
free_basic_memory_bitmaps();
offset = swap_area.offset;
}
+ /*
+ * Unpin the swap device if a swap area was already
+ * set by SNAPSHOT_SET_SWAP_AREA.
+ */
+ unpin_hibernation_swap_type(data->swap);
+
/*
* User space encodes device types as two-byte values,
* so we need to recode them
*/
- data->swap = swap_type_of(swdev, offset);
+ data->swap = pin_hibernation_swap_type(swdev, offset);
if (data->swap < 0)
return swdev ? -ENODEV : -EINVAL;
data->dev = swdev;
/* May return NULL on invalid type, caller must check for NULL return */
static struct swap_info_struct *swap_type_to_info(int type)
{
- if (type >= MAX_SWAPFILES)
+ if (type < 0 || type >= MAX_SWAPFILES)
return NULL;
return READ_ONCE(swap_info[type]); /* rcu_dereference() */
}
put_swap_device(si);
}
-/*
- * Find the swap type that corresponds to given device (if any).
- *
- * @offset - number of the PAGE_SIZE-sized block of the device, starting
- * from 0, in which the swap header is expected to be located.
- *
- * This is needed for the suspend to disk (aka swsusp).
- */
-int swap_type_of(dev_t device, sector_t offset)
+static int __find_hibernation_swap_type(dev_t device, sector_t offset)
{
int type;
+ lockdep_assert_held(&swap_lock);
+
if (!device)
- return -1;
+ return -EINVAL;
- spin_lock(&swap_lock);
for (type = 0; type < nr_swapfiles; type++) {
struct swap_info_struct *sis = swap_info[type];
if (device == sis->bdev->bd_dev) {
struct swap_extent *se = first_se(sis);
- if (se->start_block == offset) {
- spin_unlock(&swap_lock);
+ if (se->start_block == offset)
return type;
- }
}
}
- spin_unlock(&swap_lock);
return -ENODEV;
}
+/**
+ * pin_hibernation_swap_type - Pin the swap device for hibernation
+ * @device: Block device containing the resume image
+ * @offset: Offset identifying the swap area
+ *
+ * Locate the swap device for @device/@offset and mark it as pinned
+ * for hibernation. While pinned, swapoff() is prevented.
+ *
+ * Only one uswsusp context may pin a swap device at a time.
+ * If already pinned, this function returns -EBUSY.
+ *
+ * Return:
+ * >= 0 on success (swap type).
+ * -EINVAL if @device is invalid.
+ * -ENODEV if the swap device is not found.
+ * -EBUSY if the device is already pinned for hibernation.
+ */
+int pin_hibernation_swap_type(dev_t device, sector_t offset)
+{
+ int type;
+ struct swap_info_struct *si;
+
+ spin_lock(&swap_lock);
+
+ type = __find_hibernation_swap_type(device, offset);
+ if (type < 0) {
+ spin_unlock(&swap_lock);
+ return type;
+ }
+
+ si = swap_type_to_info(type);
+ if (WARN_ON_ONCE(!si)) {
+ spin_unlock(&swap_lock);
+ return -ENODEV;
+ }
+
+ /*
+ * hibernate_acquire() prevents concurrent hibernation sessions.
+ * This check additionally guards against double-pinning within
+ * the same session.
+ */
+ if (WARN_ON_ONCE(si->flags & SWP_HIBERNATION)) {
+ spin_unlock(&swap_lock);
+ return -EBUSY;
+ }
+
+ si->flags |= SWP_HIBERNATION;
+
+ spin_unlock(&swap_lock);
+ return type;
+}
+
+/**
+ * unpin_hibernation_swap_type - Unpin the swap device for hibernation
+ * @type: Swap type previously returned by pin_hibernation_swap_type()
+ *
+ * Clear the hibernation pin on the given swap device, allowing
+ * swapoff() to proceed normally.
+ *
+ * If @type does not refer to a valid swap device, this function
+ * does nothing.
+ */
+void unpin_hibernation_swap_type(int type)
+{
+ struct swap_info_struct *si;
+
+ spin_lock(&swap_lock);
+ si = swap_type_to_info(type);
+ if (!si) {
+ spin_unlock(&swap_lock);
+ return;
+ }
+ si->flags &= ~SWP_HIBERNATION;
+ spin_unlock(&swap_lock);
+}
+
+/**
+ * find_hibernation_swap_type - Find swap type for hibernation
+ * @device: Block device containing the resume image
+ * @offset: Offset within the device identifying the swap area
+ *
+ * Locate the swap device corresponding to @device and @offset.
+ *
+ * Unlike pin_hibernation_swap_type(), this function only performs a
+ * lookup and does not mark the swap device as pinned for hibernation.
+ *
+ * This is safe in the sysfs-based hibernation path where user space
+ * is already frozen and swapoff() cannot run concurrently.
+ *
+ * Return:
+ * A non-negative swap type on success.
+ * -EINVAL if @device is invalid.
+ * -ENODEV if no matching swap device is found.
+ */
+int find_hibernation_swap_type(dev_t device, sector_t offset)
+{
+ int type;
+
+ spin_lock(&swap_lock);
+ type = __find_hibernation_swap_type(device, offset);
+ spin_unlock(&swap_lock);
+
+ return type;
+}
+
int find_first_swap(dev_t *device)
{
int type;
spin_unlock(&swap_lock);
goto out_dput;
}
+
+ /* Refuse swapoff while the device is pinned for hibernation */
+ if (p->flags & SWP_HIBERNATION) {
+ err = -EBUSY;
+ spin_unlock(&swap_lock);
+ goto out_dput;
+ }
+
if (!security_vm_enough_memory_mm(current->mm, p->pages))
vm_unacct_memory(p->pages);
else {