FILESYSTEMS (VFS and infrastructure)
M: Alexander Viro <viro@zeniv.linux.org.uk>
M: Christian Brauner <brauner@kernel.org>
+R: Jan Kara <jack@suse.cz>
L: linux-fsdevel@vger.kernel.org
S: Maintained
F: fs/*
F: fs/fhandle.c
F: include/linux/exportfs.h
+FILESYSTEMS [IDMAPPED MOUNTS]
+M: Christian Brauner <brauner@kernel.org>
+M: Seth Forshee <sforshee@kernel.org>
+L: linux-fsdevel@vger.kernel.org
+S: Maintained
+F: Documentation/filesystems/idmappings.rst
+F: fs/mnt_idmapping.c
+F: include/linux/mnt_idmapping.*
+F: tools/testing/selftests/mount_setattr/
+
FILESYSTEMS [IOMAP]
M: Christian Brauner <brauner@kernel.org>
R: Darrick J. Wong <djwong@kernel.org>
W: https://github.com/o2genum/ideapad-slidebar
F: drivers/input/misc/ideapad_slidebar.c
-IDMAPPED MOUNTS
-M: Christian Brauner <brauner@kernel.org>
-M: Seth Forshee <sforshee@kernel.org>
-L: linux-fsdevel@vger.kernel.org
-S: Maintained
-T: git git://git.kernel.org/pub/scm/linux/kernel/git/vfs/idmapping.git
-F: Documentation/filesystems/idmappings.rst
-F: include/linux/mnt_idmapping.*
-F: tools/testing/selftests/mount_setattr/
-
IDT VersaClock 5 CLOCK DRIVER
M: Luca Ceresoli <luca@lucaceresoli.net>
S: Maintained
if (!eventfd)
return HV_STATUS_INVALID_PORT_ID;
- eventfd_signal(eventfd, 1);
+ eventfd_signal(eventfd);
return HV_STATUS_SUCCESS;
}
if (ret < 0 && ret != -ENOTCONN)
return false;
} else {
- eventfd_signal(evtchnfd->deliver.eventfd.ctx, 1);
+ eventfd_signal(evtchnfd->deliver.eventfd.ctx);
}
*r = 0;
notifier_event->events_mask |= event_mask;
if (notifier_event->eventfd)
- eventfd_signal(notifier_event->eventfd, 1);
+ eventfd_signal(notifier_event->eventfd);
mutex_unlock(¬ifier_event->lock);
}
{
struct eventfd_ctx *trigger = arg;
- eventfd_signal(trigger, 1);
+ eventfd_signal(trigger);
return IRQ_HANDLED;
}
struct syncobj_eventfd_entry *entry =
container_of(cb, struct syncobj_eventfd_entry, fence_cb);
- eventfd_signal(entry->ev_fd_ctx, 1);
+ eventfd_signal(entry->ev_fd_ctx);
syncobj_eventfd_entry_free(entry);
}
entry->fence = fence;
if (entry->flags & DRM_SYNCOBJ_WAIT_FLAGS_WAIT_AVAILABLE) {
- eventfd_signal(entry->ev_fd_ctx, 1);
+ eventfd_signal(entry->ev_fd_ctx);
syncobj_eventfd_entry_free(entry);
} else {
ret = dma_fence_add_callback(fence, &entry->fence_cb,
syncobj_eventfd_entry_fence_func);
if (ret == -ENOENT) {
- eventfd_signal(entry->ev_fd_ctx, 1);
+ eventfd_signal(entry->ev_fd_ctx);
syncobj_eventfd_entry_free(entry);
}
}
#define MSI_CAP_DATA(offset) (offset + 8)
#define MSI_CAP_EN 0x1
-static int inject_virtual_interrupt(struct intel_vgpu *vgpu)
+static void inject_virtual_interrupt(struct intel_vgpu *vgpu)
{
unsigned long offset = vgpu->gvt->device_info.msi_cap_offset;
u16 control, data;
/* Do not generate MSI if MSIEN is disabled */
if (!(control & MSI_CAP_EN))
- return 0;
+ return;
if (WARN(control & GENMASK(15, 1), "only support one MSI format\n"))
- return -EINVAL;
+ return;
trace_inject_msi(vgpu->id, addr, data);
* returned and don't inject interrupt into guest.
*/
if (!test_bit(INTEL_VGPU_STATUS_ATTACHED, vgpu->status))
- return -ESRCH;
- if (vgpu->msi_trigger && eventfd_signal(vgpu->msi_trigger, 1) != 1)
- return -EFAULT;
- return 0;
+ return;
+ if (vgpu->msi_trigger)
+ eventfd_signal(vgpu->msi_trigger);
}
static void propagate_event(struct intel_gvt_irq *irq,
list_for_each_entry_rcu(item, fd_list, xa_list) {
if (item->eventfd)
- eventfd_signal(item->eventfd, 1);
+ eventfd_signal(item->eventfd);
else
deliver_event(item, data);
}
{
struct eventfd_ctx *ev_ctx = private;
- eventfd_signal(ev_ctx, 1);
+ eventfd_signal(ev_ctx);
return IRQ_HANDLED;
}
/* Notify the guest if more CRWs are on our queue */
if (!list_empty(&private->crw) && private->crw_trigger)
- eventfd_signal(private->crw_trigger, 1);
+ eventfd_signal(private->crw_trigger);
return ret;
}
private->state = VFIO_CCW_STATE_IDLE;
if (private->io_trigger)
- eventfd_signal(private->io_trigger, 1);
+ eventfd_signal(private->io_trigger);
}
void vfio_ccw_crw_todo(struct work_struct *work)
private = container_of(work, struct vfio_ccw_private, crw_work);
if (!list_empty(&private->crw) && private->crw_trigger)
- eventfd_signal(private->crw_trigger, 1);
+ eventfd_signal(private->crw_trigger);
}
/*
case VFIO_IRQ_SET_DATA_NONE:
{
if (*ctx)
- eventfd_signal(*ctx, 1);
+ eventfd_signal(*ctx);
return 0;
}
case VFIO_IRQ_SET_DATA_BOOL:
return -EFAULT;
if (trigger && *ctx)
- eventfd_signal(*ctx, 1);
+ eventfd_signal(*ctx);
return 0;
}
case VFIO_IRQ_SET_DATA_EVENTFD:
"Relaying device request to user (#%u)\n",
count);
- eventfd_signal(private->req_trigger, 1);
+ eventfd_signal(private->req_trigger);
} else if (count == 0) {
dev_notice(dev,
"No device request channel registered, blocked until released by user\n");
"Relaying device request to user (#%u)\n",
count);
- eventfd_signal(matrix_mdev->req_trigger, 1);
+ eventfd_signal(matrix_mdev->req_trigger);
} else if (count == 0) {
dev_notice(dev,
"No device request registered, blocked until released by user\n");
io_data->kiocb->ki_complete(io_data->kiocb, ret);
if (io_data->ffs->ffs_eventfd && !kiocb_has_eventfd)
- eventfd_signal(io_data->ffs->ffs_eventfd, 1);
+ eventfd_signal(io_data->ffs->ffs_eventfd);
if (io_data->read)
kfree(io_data->to_free);
ffs->ev.types[ffs->ev.count++] = type;
wake_up_locked(&ffs->ev.waitq);
if (ffs->ffs_eventfd)
- eventfd_signal(ffs->ffs_eventfd, 1);
+ eventfd_signal(ffs->ffs_eventfd);
}
static void ffs_event_add(struct ffs_data *ffs,
goto unlock;
if (vq->kickfd)
- eventfd_signal(vq->kickfd, 1);
+ eventfd_signal(vq->kickfd);
else
vq->kicked = true;
unlock:
eventfd_ctx_put(vq->kickfd);
vq->kickfd = ctx;
if (vq->ready && vq->kicked && vq->kickfd) {
- eventfd_signal(vq->kickfd, 1);
+ eventfd_signal(vq->kickfd);
vq->kicked = false;
}
spin_unlock(&vq->kick_lock);
spin_lock_irq(&vq->irq_lock);
if (vq->ready && vq->cb.trigger) {
- eventfd_signal(vq->cb.trigger, 1);
+ eventfd_signal(vq->cb.trigger);
signal = true;
}
spin_unlock_irq(&vq->irq_lock);
{
struct vfio_fsl_mc_irq *mc_irq = (struct vfio_fsl_mc_irq *)arg;
- eventfd_signal(mc_irq->trigger, 1);
+ eventfd_signal(mc_irq->trigger);
return IRQ_HANDLED;
}
*/
down_write(&vdev->memory_lock);
if (vdev->pm_wake_eventfd_ctx) {
- eventfd_signal(vdev->pm_wake_eventfd_ctx, 1);
+ eventfd_signal(vdev->pm_wake_eventfd_ctx);
__vfio_pci_runtime_pm_exit(vdev);
}
up_write(&vdev->memory_lock);
pci_notice_ratelimited(pdev,
"Relaying device request to user (#%u)\n",
count);
- eventfd_signal(vdev->req_trigger, 1);
+ eventfd_signal(vdev->req_trigger);
} else if (count == 0) {
pci_warn(pdev,
"No device request channel registered, blocked until released by user\n");
mutex_lock(&vdev->igate);
if (vdev->err_trigger)
- eventfd_signal(vdev->err_trigger, 1);
+ eventfd_signal(vdev->err_trigger);
mutex_unlock(&vdev->igate);
ctx = vfio_irq_ctx_get(vdev, 0);
if (WARN_ON_ONCE(!ctx))
return;
- eventfd_signal(ctx->trigger, 1);
+ eventfd_signal(ctx->trigger);
}
}
{
struct eventfd_ctx *trigger = arg;
- eventfd_signal(trigger, 1);
+ eventfd_signal(trigger);
return IRQ_HANDLED;
}
if (!ctx)
continue;
if (flags & VFIO_IRQ_SET_DATA_NONE) {
- eventfd_signal(ctx->trigger, 1);
+ eventfd_signal(ctx->trigger);
} else if (flags & VFIO_IRQ_SET_DATA_BOOL) {
uint8_t *bools = data;
if (bools[i - start])
- eventfd_signal(ctx->trigger, 1);
+ eventfd_signal(ctx->trigger);
}
}
return 0;
if (flags & VFIO_IRQ_SET_DATA_NONE) {
if (*ctx) {
if (count) {
- eventfd_signal(*ctx, 1);
+ eventfd_signal(*ctx);
} else {
eventfd_ctx_put(*ctx);
*ctx = NULL;
trigger = *(uint8_t *)data;
if (trigger && *ctx)
- eventfd_signal(*ctx, 1);
+ eventfd_signal(*ctx);
return 0;
} else if (flags & VFIO_IRQ_SET_DATA_EVENTFD) {
spin_unlock_irqrestore(&irq_ctx->lock, flags);
if (ret == IRQ_HANDLED)
- eventfd_signal(irq_ctx->trigger, 1);
+ eventfd_signal(irq_ctx->trigger);
return ret;
}
{
struct vfio_platform_irq *irq_ctx = dev_id;
- eventfd_signal(irq_ctx->trigger, 1);
+ eventfd_signal(irq_ctx->trigger);
return IRQ_HANDLED;
}
struct eventfd_ctx *call_ctx = vq->call_ctx.ctx;
if (call_ctx)
- eventfd_signal(call_ctx, 1);
+ eventfd_signal(call_ctx);
return IRQ_HANDLED;
}
struct eventfd_ctx *config_ctx = v->config_ctx;
if (config_ctx)
- eventfd_signal(config_ctx, 1);
+ eventfd_signal(config_ctx);
return IRQ_HANDLED;
}
len -= l;
if (!len) {
if (vq->log_ctx)
- eventfd_signal(vq->log_ctx, 1);
+ eventfd_signal(vq->log_ctx);
return 0;
}
}
log_used(vq, (used - (void __user *)vq->used),
sizeof vq->used->flags);
if (vq->log_ctx)
- eventfd_signal(vq->log_ctx, 1);
+ eventfd_signal(vq->log_ctx);
}
return 0;
}
log_used(vq, (used - (void __user *)vq->used),
sizeof *vhost_avail_event(vq));
if (vq->log_ctx)
- eventfd_signal(vq->log_ctx, 1);
+ eventfd_signal(vq->log_ctx);
}
return 0;
}
log_used(vq, offsetof(struct vring_used, idx),
sizeof vq->used->idx);
if (vq->log_ctx)
- eventfd_signal(vq->log_ctx, 1);
+ eventfd_signal(vq->log_ctx);
}
return r;
}
{
/* Signal the Guest tell them we used something up. */
if (vq->call_ctx.ctx && vhost_notify(dev, vq))
- eventfd_signal(vq->call_ctx.ctx, 1);
+ eventfd_signal(vq->call_ctx.ctx);
}
EXPORT_SYMBOL_GPL(vhost_signal);
#define vq_err(vq, fmt, ...) do { \
pr_debug(pr_fmt(fmt), ##__VA_ARGS__); \
if ((vq)->error_ctx) \
- eventfd_signal((vq)->error_ctx, 1);\
+ eventfd_signal((vq)->error_ctx);\
} while (0)
enum {
mutex_lock(&client->vm->ioeventfds_lock);
p = hsm_ioeventfd_match(client->vm, addr, val, size, req->type);
if (p)
- eventfd_signal(p->eventfd, 1);
+ eventfd_signal(p->eventfd);
mutex_unlock(&client->vm->ioeventfds_lock);
return 0;
if (ioreq->addr == kioeventfd->addr + VIRTIO_MMIO_QUEUE_NOTIFY &&
ioreq->size == kioeventfd->addr_len &&
(ioreq->data & QUEUE_NOTIFY_VQ_MASK) == kioeventfd->vq) {
- eventfd_signal(kioeventfd->eventfd, 1);
+ eventfd_signal(kioeventfd->eventfd);
state = STATE_IORESP_READY;
break;
}
return ERR_CAST(inode);
inode->i_mapping->a_ops = &aio_ctx_aops;
- inode->i_mapping->private_data = ctx;
+ inode->i_mapping->i_private_data = ctx;
inode->i_size = PAGE_SIZE * nr_pages;
file = alloc_file_pseudo(inode, aio_mnt, "[aio]",
/* Prevent further access to the kioctx from migratepages */
i_mapping = aio_ring_file->f_mapping;
- spin_lock(&i_mapping->private_lock);
- i_mapping->private_data = NULL;
+ spin_lock(&i_mapping->i_private_lock);
+ i_mapping->i_private_data = NULL;
ctx->aio_ring_file = NULL;
- spin_unlock(&i_mapping->private_lock);
+ spin_unlock(&i_mapping->i_private_lock);
fput(aio_ring_file);
}
rc = 0;
- /* mapping->private_lock here protects against the kioctx teardown. */
- spin_lock(&mapping->private_lock);
- ctx = mapping->private_data;
+ /* mapping->i_private_lock here protects against the kioctx teardown. */
+ spin_lock(&mapping->i_private_lock);
+ ctx = mapping->i_private_data;
if (!ctx) {
rc = -EINVAL;
goto out;
out_unlock:
mutex_unlock(&ctx->ring_lock);
out:
- spin_unlock(&mapping->private_lock);
+ spin_unlock(&mapping->i_private_lock);
return rc;
}
#else
kmem_cache_free(kiocb_cachep, iocb);
}
+struct aio_waiter {
+ struct wait_queue_entry w;
+ size_t min_nr;
+};
+
/* aio_complete
* Called when the io request on the given iocb is complete.
*/
struct kioctx *ctx = iocb->ki_ctx;
struct aio_ring *ring;
struct io_event *ev_page, *event;
- unsigned tail, pos, head;
+ unsigned tail, pos, head, avail;
unsigned long flags;
/*
ctx->completed_events++;
if (ctx->completed_events > 1)
refill_reqs_available(ctx, head, tail);
+
+ avail = tail > head
+ ? tail - head
+ : tail + ctx->nr_events - head;
spin_unlock_irqrestore(&ctx->completion_lock, flags);
pr_debug("added to ring %p at [%u]\n", iocb, tail);
* from IRQ context.
*/
if (iocb->ki_eventfd)
- eventfd_signal(iocb->ki_eventfd, 1);
+ eventfd_signal(iocb->ki_eventfd);
/*
* We have to order our ring_info tail store above and test
*/
smp_mb();
- if (waitqueue_active(&ctx->wait))
- wake_up(&ctx->wait);
+ if (waitqueue_active(&ctx->wait)) {
+ struct aio_waiter *curr, *next;
+ unsigned long flags;
+
+ spin_lock_irqsave(&ctx->wait.lock, flags);
+ list_for_each_entry_safe(curr, next, &ctx->wait.head, w.entry)
+ if (avail >= curr->min_nr) {
+ list_del_init_careful(&curr->w.entry);
+ wake_up_process(curr->w.private);
+ }
+ spin_unlock_irqrestore(&ctx->wait.lock, flags);
+ }
}
static inline void iocb_put(struct aio_kiocb *iocb)
struct io_event __user *event,
ktime_t until)
{
- long ret = 0;
+ struct hrtimer_sleeper t;
+ struct aio_waiter w;
+ long ret = 0, ret2 = 0;
/*
* Note that aio_read_events() is being called as the conditional - i.e.
* the ringbuffer empty. So in practice we should be ok, but it's
* something to be aware of when touching this code.
*/
- if (until == 0)
- aio_read_events(ctx, min_nr, nr, event, &ret);
- else
- wait_event_interruptible_hrtimeout(ctx->wait,
- aio_read_events(ctx, min_nr, nr, event, &ret),
- until);
+ aio_read_events(ctx, min_nr, nr, event, &ret);
+ if (until == 0 || ret < 0 || ret >= min_nr)
+ return ret;
+
+ hrtimer_init_sleeper_on_stack(&t, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+ if (until != KTIME_MAX) {
+ hrtimer_set_expires_range_ns(&t.timer, until, current->timer_slack_ns);
+ hrtimer_sleeper_start_expires(&t, HRTIMER_MODE_REL);
+ }
+
+ init_wait(&w.w);
+
+ while (1) {
+ unsigned long nr_got = ret;
+
+ w.min_nr = min_nr - ret;
+
+ ret2 = prepare_to_wait_event(&ctx->wait, &w.w, TASK_INTERRUPTIBLE);
+ if (!ret2 && !t.task)
+ ret2 = -ETIME;
+
+ if (aio_read_events(ctx, min_nr, nr, event, &ret) || ret2)
+ break;
+
+ if (nr_got == ret)
+ schedule();
+ }
+
+ finish_wait(&ctx->wait, &w.w);
+ hrtimer_cancel(&t.timer);
+ destroy_hrtimer_on_stack(&t.timer);
+
return ret;
}
* the vfsmount must be passed through @idmap. This function will then
* take care to map the inode according to @idmap before checking
* permissions. On non-idmapped mounts or if permission checking is to be
- * performed on the raw inode simply passs @nop_mnt_idmap.
+ * performed on the raw inode simply pass @nop_mnt_idmap.
*
* Should be called as the first thing in ->setattr implementations,
* possibly after taking additional locks.
* will not race with any other ebs.
*/
if (page->mapping)
- lockdep_assert_held(&page->mapping->private_lock);
+ lockdep_assert_held(&page->mapping->i_private_lock);
if (fs_info->nodesize >= PAGE_SIZE) {
if (!PagePrivate(page))
* Take private lock to ensure the subpage won't be detached
* in the meantime.
*/
- spin_lock(&page->mapping->private_lock);
+ spin_lock(&page->mapping->i_private_lock);
if (!PagePrivate(page)) {
- spin_unlock(&page->mapping->private_lock);
+ spin_unlock(&page->mapping->i_private_lock);
break;
}
spin_lock_irqsave(&subpage->lock, flags);
if (!test_bit(bit_start + fs_info->subpage_info->dirty_offset,
subpage->bitmaps)) {
spin_unlock_irqrestore(&subpage->lock, flags);
- spin_unlock(&page->mapping->private_lock);
+ spin_unlock(&page->mapping->i_private_lock);
bit_start++;
continue;
}
*/
eb = find_extent_buffer_nolock(fs_info, start);
spin_unlock_irqrestore(&subpage->lock, flags);
- spin_unlock(&page->mapping->private_lock);
+ spin_unlock(&page->mapping->i_private_lock);
/*
* The eb has already reached 0 refs thus find_extent_buffer()
if (btrfs_sb(page->mapping->host->i_sb)->nodesize < PAGE_SIZE)
return submit_eb_subpage(page, wbc);
- spin_lock(&mapping->private_lock);
+ spin_lock(&mapping->i_private_lock);
if (!PagePrivate(page)) {
- spin_unlock(&mapping->private_lock);
+ spin_unlock(&mapping->i_private_lock);
return 0;
}
* crashing the machine for something we can survive anyway.
*/
if (WARN_ON(!eb)) {
- spin_unlock(&mapping->private_lock);
+ spin_unlock(&mapping->i_private_lock);
return 0;
}
if (eb == ctx->eb) {
- spin_unlock(&mapping->private_lock);
+ spin_unlock(&mapping->i_private_lock);
return 0;
}
ret = atomic_inc_not_zero(&eb->refs);
- spin_unlock(&mapping->private_lock);
+ spin_unlock(&mapping->i_private_lock);
if (!ret)
return 0;
{
struct btrfs_subpage *subpage;
- lockdep_assert_held(&page->mapping->private_lock);
+ lockdep_assert_held(&page->mapping->i_private_lock);
if (PagePrivate(page)) {
subpage = (struct btrfs_subpage *)page->private;
/*
* For mapped eb, we're going to change the page private, which should
- * be done under the private_lock.
+ * be done under the i_private_lock.
*/
if (mapped)
- spin_lock(&page->mapping->private_lock);
+ spin_lock(&page->mapping->i_private_lock);
if (!PagePrivate(page)) {
if (mapped)
- spin_unlock(&page->mapping->private_lock);
+ spin_unlock(&page->mapping->i_private_lock);
return;
}
detach_page_private(page);
}
if (mapped)
- spin_unlock(&page->mapping->private_lock);
+ spin_unlock(&page->mapping->i_private_lock);
return;
}
if (!page_range_has_eb(fs_info, page))
btrfs_detach_subpage(fs_info, page);
- spin_unlock(&page->mapping->private_lock);
+ spin_unlock(&page->mapping->i_private_lock);
}
/* Release all pages attached to the extent buffer */
/*
* Preallocate page->private for subpage case, so that we won't
- * allocate memory with private_lock nor page lock hold.
+ * allocate memory with i_private_lock nor page lock hold.
*
* The memory will be freed by attach_extent_buffer_page() or freed
* manually if we exit earlier.
goto free_eb;
}
- spin_lock(&mapping->private_lock);
+ spin_lock(&mapping->i_private_lock);
exists = grab_extent_buffer(fs_info, p);
if (exists) {
- spin_unlock(&mapping->private_lock);
+ spin_unlock(&mapping->i_private_lock);
unlock_page(p);
put_page(p);
mark_extent_buffer_accessed(exists, p);
* Thus needs no special handling in error path.
*/
btrfs_page_inc_eb_refs(fs_info, p);
- spin_unlock(&mapping->private_lock);
+ spin_unlock(&mapping->i_private_lock);
WARN_ON(btrfs_page_test_dirty(fs_info, p, eb->start, eb->len));
eb->pages[i] = p;
* Finally to check if we have cleared page private, as if we have
* released all ebs in the page, the page private should be cleared now.
*/
- spin_lock(&page->mapping->private_lock);
+ spin_lock(&page->mapping->i_private_lock);
if (!PagePrivate(page))
ret = 1;
else
ret = 0;
- spin_unlock(&page->mapping->private_lock);
+ spin_unlock(&page->mapping->i_private_lock);
return ret;
}
* We need to make sure nobody is changing page->private, as we rely on
* page->private as the pointer to extent buffer.
*/
- spin_lock(&page->mapping->private_lock);
+ spin_lock(&page->mapping->i_private_lock);
if (!PagePrivate(page)) {
- spin_unlock(&page->mapping->private_lock);
+ spin_unlock(&page->mapping->i_private_lock);
return 1;
}
spin_lock(&eb->refs_lock);
if (atomic_read(&eb->refs) != 1 || extent_buffer_under_io(eb)) {
spin_unlock(&eb->refs_lock);
- spin_unlock(&page->mapping->private_lock);
+ spin_unlock(&page->mapping->i_private_lock);
return 0;
}
- spin_unlock(&page->mapping->private_lock);
+ spin_unlock(&page->mapping->i_private_lock);
/*
* If tree ref isn't set then we know the ref on this eb is a real ref,
return;
ASSERT(PagePrivate(page) && page->mapping);
- lockdep_assert_held(&page->mapping->private_lock);
+ lockdep_assert_held(&page->mapping->i_private_lock);
subpage = (struct btrfs_subpage *)page->private;
atomic_inc(&subpage->eb_refs);
return;
ASSERT(PagePrivate(page) && page->mapping);
- lockdep_assert_held(&page->mapping->private_lock);
+ lockdep_assert_held(&page->mapping->i_private_lock);
subpage = (struct btrfs_subpage *)page->private;
ASSERT(atomic_read(&subpage->eb_refs));
* Various filesystems appear to want __find_get_block to be non-blocking.
* But it's the page lock which protects the buffers. To get around this,
* we get exclusion from try_to_free_buffers with the blockdev mapping's
- * private_lock.
+ * i_private_lock.
*
- * Hack idea: for the blockdev mapping, private_lock contention
+ * Hack idea: for the blockdev mapping, i_private_lock contention
* may be quite high. This code could TryLock the page, and if that
- * succeeds, there is no need to take private_lock.
+ * succeeds, there is no need to take i_private_lock.
*/
static struct buffer_head *
__find_get_block_slow(struct block_device *bdev, sector_t block)
if (IS_ERR(folio))
goto out;
- spin_lock(&bd_mapping->private_lock);
+ spin_lock(&bd_mapping->i_private_lock);
head = folio_buffers(folio);
if (!head)
goto out_unlock;
1 << bd_inode->i_blkbits);
}
out_unlock:
- spin_unlock(&bd_mapping->private_lock);
+ spin_unlock(&bd_mapping->i_private_lock);
folio_put(folio);
out:
return ret;
*
* The functions mark_buffer_inode_dirty(), fsync_inode_buffers(),
* inode_has_buffers() and invalidate_inode_buffers() are provided for the
- * management of a list of dependent buffers at ->i_mapping->private_list.
+ * management of a list of dependent buffers at ->i_mapping->i_private_list.
*
* Locking is a little subtle: try_to_free_buffers() will remove buffers
* from their controlling inode's queue when they are being freed. But
* try_to_free_buffers() will be operating against the *blockdev* mapping
* at the time, not against the S_ISREG file which depends on those buffers.
- * So the locking for private_list is via the private_lock in the address_space
+ * So the locking for i_private_list is via the i_private_lock in the address_space
* which backs the buffers. Which is different from the address_space
* against which the buffers are listed. So for a particular address_space,
- * mapping->private_lock does *not* protect mapping->private_list! In fact,
- * mapping->private_list will always be protected by the backing blockdev's
- * ->private_lock.
+ * mapping->i_private_lock does *not* protect mapping->i_private_list! In fact,
+ * mapping->i_private_list will always be protected by the backing blockdev's
+ * ->i_private_lock.
*
* Which introduces a requirement: all buffers on an address_space's
- * ->private_list must be from the same address_space: the blockdev's.
+ * ->i_private_list must be from the same address_space: the blockdev's.
*
- * address_spaces which do not place buffers at ->private_list via these
- * utility functions are free to use private_lock and private_list for
- * whatever they want. The only requirement is that list_empty(private_list)
+ * address_spaces which do not place buffers at ->i_private_list via these
+ * utility functions are free to use i_private_lock and i_private_list for
+ * whatever they want. The only requirement is that list_empty(i_private_list)
* be true at clear_inode() time.
*
* FIXME: clear_inode should not call invalidate_inode_buffers(). The
*/
/*
- * The buffer's backing address_space's private_lock must be held
+ * The buffer's backing address_space's i_private_lock must be held
*/
static void __remove_assoc_queue(struct buffer_head *bh)
{
int inode_has_buffers(struct inode *inode)
{
- return !list_empty(&inode->i_data.private_list);
+ return !list_empty(&inode->i_data.i_private_list);
}
/*
* sync_mapping_buffers - write out & wait upon a mapping's "associated" buffers
* @mapping: the mapping which wants those buffers written
*
- * Starts I/O against the buffers at mapping->private_list, and waits upon
+ * Starts I/O against the buffers at mapping->i_private_list, and waits upon
* that I/O.
*
* Basically, this is a convenience function for fsync().
*/
int sync_mapping_buffers(struct address_space *mapping)
{
- struct address_space *buffer_mapping = mapping->private_data;
+ struct address_space *buffer_mapping = mapping->i_private_data;
- if (buffer_mapping == NULL || list_empty(&mapping->private_list))
+ if (buffer_mapping == NULL || list_empty(&mapping->i_private_list))
return 0;
- return fsync_buffers_list(&buffer_mapping->private_lock,
- &mapping->private_list);
+ return fsync_buffers_list(&buffer_mapping->i_private_lock,
+ &mapping->i_private_list);
}
EXPORT_SYMBOL(sync_mapping_buffers);
struct address_space *buffer_mapping = bh->b_folio->mapping;
mark_buffer_dirty(bh);
- if (!mapping->private_data) {
- mapping->private_data = buffer_mapping;
+ if (!mapping->i_private_data) {
+ mapping->i_private_data = buffer_mapping;
} else {
- BUG_ON(mapping->private_data != buffer_mapping);
+ BUG_ON(mapping->i_private_data != buffer_mapping);
}
if (!bh->b_assoc_map) {
- spin_lock(&buffer_mapping->private_lock);
+ spin_lock(&buffer_mapping->i_private_lock);
list_move_tail(&bh->b_assoc_buffers,
- &mapping->private_list);
+ &mapping->i_private_list);
bh->b_assoc_map = mapping;
- spin_unlock(&buffer_mapping->private_lock);
+ spin_unlock(&buffer_mapping->i_private_lock);
}
}
EXPORT_SYMBOL(mark_buffer_dirty_inode);
* bit, see a bunch of clean buffers and we'd end up with dirty buffers/clean
* page on the dirty page list.
*
- * We use private_lock to lock against try_to_free_buffers while using the
+ * We use i_private_lock to lock against try_to_free_buffers while using the
* page's buffer list. Also use this to protect against clean buffers being
* added to the page after it was set dirty.
*
struct buffer_head *head;
bool newly_dirty;
- spin_lock(&mapping->private_lock);
+ spin_lock(&mapping->i_private_lock);
head = folio_buffers(folio);
if (head) {
struct buffer_head *bh = head;
*/
folio_memcg_lock(folio);
newly_dirty = !folio_test_set_dirty(folio);
- spin_unlock(&mapping->private_lock);
+ spin_unlock(&mapping->i_private_lock);
if (newly_dirty)
__folio_mark_dirty(folio, mapping, 1);
smp_mb();
if (buffer_dirty(bh)) {
list_add(&bh->b_assoc_buffers,
- &mapping->private_list);
+ &mapping->i_private_list);
bh->b_assoc_map = mapping;
}
spin_unlock(lock);
* probably unmounting the fs, but that doesn't mean we have already
* done a sync(). Just drop the buffers from the inode list.
*
- * NOTE: we take the inode's blockdev's mapping's private_lock. Which
+ * NOTE: we take the inode's blockdev's mapping's i_private_lock. Which
* assumes that all the buffers are against the blockdev. Not true
* for reiserfs.
*/
{
if (inode_has_buffers(inode)) {
struct address_space *mapping = &inode->i_data;
- struct list_head *list = &mapping->private_list;
- struct address_space *buffer_mapping = mapping->private_data;
+ struct list_head *list = &mapping->i_private_list;
+ struct address_space *buffer_mapping = mapping->i_private_data;
- spin_lock(&buffer_mapping->private_lock);
+ spin_lock(&buffer_mapping->i_private_lock);
while (!list_empty(list))
__remove_assoc_queue(BH_ENTRY(list->next));
- spin_unlock(&buffer_mapping->private_lock);
+ spin_unlock(&buffer_mapping->i_private_lock);
}
}
EXPORT_SYMBOL(invalidate_inode_buffers);
if (inode_has_buffers(inode)) {
struct address_space *mapping = &inode->i_data;
- struct list_head *list = &mapping->private_list;
- struct address_space *buffer_mapping = mapping->private_data;
+ struct list_head *list = &mapping->i_private_list;
+ struct address_space *buffer_mapping = mapping->i_private_data;
- spin_lock(&buffer_mapping->private_lock);
+ spin_lock(&buffer_mapping->i_private_lock);
while (!list_empty(list)) {
struct buffer_head *bh = BH_ENTRY(list->next);
if (buffer_dirty(bh)) {
}
__remove_assoc_queue(bh);
}
- spin_unlock(&buffer_mapping->private_lock);
+ spin_unlock(&buffer_mapping->i_private_lock);
}
return ret;
}
* lock to be atomic wrt __find_get_block(), which does not
* run under the folio lock.
*/
- spin_lock(&inode->i_mapping->private_lock);
+ spin_lock(&inode->i_mapping->i_private_lock);
link_dev_buffers(folio, bh);
end_block = folio_init_buffers(folio, bdev,
(sector_t)index << sizebits, size);
- spin_unlock(&inode->i_mapping->private_lock);
+ spin_unlock(&inode->i_mapping->i_private_lock);
done:
ret = (block < end_block) ? 1 : -ENXIO;
failed:
* and then attach the address_space's inode to its superblock's dirty
* inode list.
*
- * mark_buffer_dirty() is atomic. It takes bh->b_folio->mapping->private_lock,
+ * mark_buffer_dirty() is atomic. It takes bh->b_folio->mapping->i_private_lock,
* i_pages lock and mapping->host->i_lock.
*/
void mark_buffer_dirty(struct buffer_head *bh)
if (bh->b_assoc_map) {
struct address_space *buffer_mapping = bh->b_folio->mapping;
- spin_lock(&buffer_mapping->private_lock);
+ spin_lock(&buffer_mapping->i_private_lock);
list_del_init(&bh->b_assoc_buffers);
bh->b_assoc_map = NULL;
- spin_unlock(&buffer_mapping->private_lock);
+ spin_unlock(&buffer_mapping->i_private_lock);
}
__brelse(bh);
}
/*
* We attach and possibly dirty the buffers atomically wrt
- * block_dirty_folio() via private_lock. try_to_free_buffers
+ * block_dirty_folio() via i_private_lock. try_to_free_buffers
* is already excluded via the folio lock.
*/
struct buffer_head *create_empty_buffers(struct folio *folio,
} while (bh);
tail->b_this_page = head;
- spin_lock(&folio->mapping->private_lock);
+ spin_lock(&folio->mapping->i_private_lock);
if (folio_test_uptodate(folio) || folio_test_dirty(folio)) {
bh = head;
do {
} while (bh != head);
}
folio_attach_private(folio, head);
- spin_unlock(&folio->mapping->private_lock);
+ spin_unlock(&folio->mapping->i_private_lock);
return head;
}
if (!folio_buffers(folio))
continue;
/*
- * We use folio lock instead of bd_mapping->private_lock
+ * We use folio lock instead of bd_mapping->i_private_lock
* to pin buffers here since we can afford to sleep and
* it scales better than a global spinlock lock.
*/
* are unused, and releases them if so.
*
* Exclusion against try_to_free_buffers may be obtained by either
- * locking the folio or by holding its mapping's private_lock.
+ * locking the folio or by holding its mapping's i_private_lock.
*
* If the folio is dirty but all the buffers are clean then we need to
* be sure to mark the folio clean as well. This is because the folio
* The same applies to regular filesystem folios: if all the buffers are
* clean then we set the folio clean and proceed. To do that, we require
* total exclusion from block_dirty_folio(). That is obtained with
- * private_lock.
+ * i_private_lock.
*
* try_to_free_buffers() is non-blocking.
*/
goto out;
}
- spin_lock(&mapping->private_lock);
+ spin_lock(&mapping->i_private_lock);
ret = drop_buffers(folio, &buffers_to_free);
/*
* the folio's buffers clean. We discover that here and clean
* the folio also.
*
- * private_lock must be held over this entire operation in order
+ * i_private_lock must be held over this entire operation in order
* to synchronise against block_dirty_folio and prevent the
* dirty bit from being lost.
*/
if (ret)
folio_cancel_dirty(folio);
- spin_unlock(&mapping->private_lock);
+ spin_unlock(&mapping->i_private_lock);
out:
if (buffers_to_free) {
struct buffer_head *bh = buffers_to_free;
/* zero the edges if srcmap is a HOLE or IOMAP_UNWRITTEN */
bool zero_edge = srcmap->flags & IOMAP_F_SHARED ||
srcmap->type == IOMAP_UNWRITTEN;
- void *saddr = 0;
+ void *saddr = NULL;
int ret = 0;
if (!zero_edge) {
loff_t offset = iocb->ki_pos;
const loff_t end = offset + count;
struct dio *dio;
- struct dio_submit sdio = { 0, };
+ struct dio_submit sdio = { NULL, };
struct buffer_head map_bh = { 0, };
struct blk_plug plug;
unsigned long align = offset | iov_iter_alignment(iter);
int id;
};
-__u64 eventfd_signal_mask(struct eventfd_ctx *ctx, __u64 n, __poll_t mask)
+/**
+ * eventfd_signal_mask - Increment the event counter
+ * @ctx: [in] Pointer to the eventfd context.
+ * @mask: [in] poll mask
+ *
+ * This function is supposed to be called by the kernel in paths that do not
+ * allow sleeping. In this function we allow the counter to reach the ULLONG_MAX
+ * value, and we signal this as overflow condition by returning a EPOLLERR
+ * to poll(2).
+ */
+void eventfd_signal_mask(struct eventfd_ctx *ctx, __poll_t mask)
{
unsigned long flags;
* safe context.
*/
if (WARN_ON_ONCE(current->in_eventfd))
- return 0;
+ return;
spin_lock_irqsave(&ctx->wqh.lock, flags);
current->in_eventfd = 1;
- if (ULLONG_MAX - ctx->count < n)
- n = ULLONG_MAX - ctx->count;
- ctx->count += n;
+ if (ctx->count < ULLONG_MAX)
+ ctx->count++;
if (waitqueue_active(&ctx->wqh))
wake_up_locked_poll(&ctx->wqh, EPOLLIN | mask);
current->in_eventfd = 0;
spin_unlock_irqrestore(&ctx->wqh.lock, flags);
-
- return n;
-}
-
-/**
- * eventfd_signal - Adds @n to the eventfd counter.
- * @ctx: [in] Pointer to the eventfd context.
- * @n: [in] Value of the counter to be added to the eventfd internal counter.
- * The value cannot be negative.
- *
- * This function is supposed to be called by the kernel in paths that do not
- * allow sleeping. In this function we allow the counter to reach the ULLONG_MAX
- * value, and we signal this as overflow condition by returning a EPOLLERR
- * to poll(2).
- *
- * Returns the amount by which the counter was incremented. This will be less
- * than @n if the counter has overflowed.
- */
-__u64 eventfd_signal(struct eventfd_ctx *ctx, __u64 n)
-{
- return eventfd_signal_mask(ctx, n, 0);
}
-EXPORT_SYMBOL_GPL(eventfd_signal);
+EXPORT_SYMBOL_GPL(eventfd_signal_mask);
static void eventfd_free_ctx(struct eventfd_ctx *ctx)
{
if (ctx->id >= 0)
- ida_simple_remove(&eventfd_ida, ctx->id);
+ ida_free(&eventfd_ida, ctx->id);
kfree(ctx);
}
init_waitqueue_head(&ctx->wqh);
ctx->count = count;
ctx->flags = flags;
- ctx->id = ida_simple_get(&eventfd_ida, 0, 0, GFP_KERNEL);
+ ctx->id = ida_alloc(&eventfd_ida, GFP_KERNEL);
flags &= EFD_SHARED_FCNTL_FLAGS;
flags |= O_RDWR;
* We need to pick up the new inode size which generic_commit_write gave us
* `file' can be NULL - eg, when called from page_symlink().
*
- * ext4 never places buffers on inode->i_mapping->private_list. metadata
+ * ext4 never places buffers on inode->i_mapping->i_private_list. metadata
* buffers are managed internally.
*/
static int ext4_write_end(struct file *file,
}
/* Any metadata buffers to write? */
- if (!list_empty(&inode->i_mapping->private_list))
+ if (!list_empty(&inode->i_mapping->i_private_list))
return true;
return inode->i_state & I_DIRTY_DATASYNC;
}
mapping->host = s->s_bdev->bd_inode;
mapping->flags = 0;
mapping_set_gfp_mask(mapping, GFP_NOFS);
- mapping->private_data = NULL;
+ mapping->i_private_data = NULL;
mapping->writeback_index = 0;
}
mapping->host = sb->s_bdev->bd_inode;
mapping->flags = 0;
mapping_set_gfp_mask(mapping, GFP_NOFS);
- mapping->private_data = NULL;
+ mapping->i_private_data = NULL;
mapping->writeback_index = 0;
spin_lock_init(&sdp->sd_log_lock);
* @sector: block to read or write, for blocks of HFSPLUS_SECTOR_SIZE bytes
* @buf: buffer for I/O
* @data: output pointer for location of requested data
- * @op: direction of I/O
- * @op_flags: request op flags
+ * @opf: request op flags
*
* The unit of I/O is hfsplus_min_io_size(sb), which may be bigger than
* HFSPLUS_SECTOR_SIZE, and @buf must be sized accordingly. On reads
* that starts at the rounded-down address. As long as the data was
* read using hfsplus_submit_bio() and the same buffer is used things
* will work correctly.
+ *
+ * Returns: %0 on success else -errno code
*/
int hfsplus_submit_bio(struct super_block *sb, sector_t sector,
void *buf, void **data, blk_opf_t opf)
* at inode creation time. If this is a device special inode,
* i_mapping may not point to the original address space.
*/
- resv_map = (struct resv_map *)(&inode->i_data)->private_data;
+ resv_map = (struct resv_map *)(&inode->i_data)->i_private_data;
/* Only regular and link inodes have associated reserve maps */
if (resv_map)
resv_map_release(&resv_map->refs);
&hugetlbfs_i_mmap_rwsem_key);
inode->i_mapping->a_ops = &hugetlbfs_aops;
simple_inode_init_ts(inode);
- inode->i_mapping->private_data = resv_map;
+ inode->i_mapping->i_private_data = resv_map;
info->seals = F_SEAL_SEAL;
switch (mode & S_IFMT) {
default:
atomic_set(&mapping->nr_thps, 0);
#endif
mapping_set_gfp_mask(mapping, GFP_HIGHUSER_MOVABLE);
- mapping->private_data = NULL;
+ mapping->i_private_data = NULL;
mapping->writeback_index = 0;
init_rwsem(&mapping->invalidate_lock);
lockdep_set_class_and_name(&mapping->invalidate_lock,
{
xa_init_flags(&mapping->i_pages, XA_FLAGS_LOCK_IRQ | XA_FLAGS_ACCOUNT);
init_rwsem(&mapping->i_mmap_rwsem);
- INIT_LIST_HEAD(&mapping->private_list);
- spin_lock_init(&mapping->private_lock);
+ INIT_LIST_HEAD(&mapping->i_private_list);
+ spin_lock_init(&mapping->i_private_lock);
mapping->i_mmap = RB_ROOT_CACHED;
}
* nor even WARN_ON(!mapping_empty).
*/
xa_unlock_irq(&inode->i_data.i_pages);
- BUG_ON(!list_empty(&inode->i_data.private_list));
+ BUG_ON(!list_empty(&inode->i_data.i_private_list));
BUG_ON(!(inode->i_state & I_FREEING));
BUG_ON(inode->i_state & I_CLEAR);
BUG_ON(!list_empty(&inode->i_wb_list));
* earlier than or equal to either the ctime or mtime,
* or if at least a day has passed since the last atime update.
*/
-static int relatime_need_update(struct vfsmount *mnt, struct inode *inode,
+static bool relatime_need_update(struct vfsmount *mnt, struct inode *inode,
struct timespec64 now)
{
struct timespec64 atime, mtime, ctime;
if (!(mnt->mnt_flags & MNT_RELATIME))
- return 1;
+ return true;
/*
* Is mtime younger than or equal to atime? If yes, update atime:
*/
atime = inode_get_atime(inode);
mtime = inode_get_mtime(inode);
if (timespec64_compare(&mtime, &atime) >= 0)
- return 1;
+ return true;
/*
* Is ctime younger than or equal to atime? If yes, update atime:
*/
ctime = inode_get_ctime(inode);
if (timespec64_compare(&ctime, &atime) >= 0)
- return 1;
+ return true;
/*
* Is the previous atime value older than a day? If yes,
* update atime:
*/
if ((long)(now.tv_sec - atime.tv_sec) >= 24*60*60)
- return 1;
+ return true;
/*
* Good, we can skip the atime update:
*/
- return 0;
+ return false;
}
/**
* the vfsmount must be passed through @idmap. This function will then take
* care to map the inode according to @idmap before checking permissions.
* On non-idmapped mounts or if permission checking is to be performed on the
- * raw inode simply passs @nop_mnt_idmap.
+ * raw inode simply pass @nop_mnt_idmap.
*/
bool inode_owner_or_capable(struct mnt_idmap *idmap,
const struct inode *inode)
#include "internal.h"
+/*
+ * Outside of this file vfs{g,u}id_t are always created from k{g,u}id_t,
+ * never from raw values. These are just internal helpers.
+ */
+#define VFSUIDT_INIT_RAW(val) (vfsuid_t){ val }
+#define VFSGIDT_INIT_RAW(val) (vfsgid_t){ val }
+
struct mnt_idmap {
- struct user_namespace *owner;
+ struct uid_gid_map uid_map;
+ struct uid_gid_map gid_map;
refcount_t count;
};
* mapped to {g,u}id 1, [...], {g,u}id 1000 to {g,u}id 1000, [...].
*/
struct mnt_idmap nop_mnt_idmap = {
- .owner = &init_user_ns,
.count = REFCOUNT_INIT(1),
};
EXPORT_SYMBOL_GPL(nop_mnt_idmap);
-/**
- * check_fsmapping - check whether an mount idmapping is allowed
- * @idmap: idmap of the relevent mount
- * @sb: super block of the filesystem
- *
- * Return: true if @idmap is allowed, false if not.
- */
-bool check_fsmapping(const struct mnt_idmap *idmap,
- const struct super_block *sb)
-{
- return idmap->owner != sb->s_user_ns;
-}
-
/**
* initial_idmapping - check whether this is the initial mapping
* @ns: idmapping to check
return ns == &init_user_ns;
}
-/**
- * no_idmapping - check whether we can skip remapping a kuid/gid
- * @mnt_userns: the mount's idmapping
- * @fs_userns: the filesystem's idmapping
- *
- * This function can be used to check whether a remapping between two
- * idmappings is required.
- * An idmapped mount is a mount that has an idmapping attached to it that
- * is different from the filsystem's idmapping and the initial idmapping.
- * If the initial mapping is used or the idmapping of the mount and the
- * filesystem are identical no remapping is required.
- *
- * Return: true if remapping can be skipped, false if not.
- */
-static inline bool no_idmapping(const struct user_namespace *mnt_userns,
- const struct user_namespace *fs_userns)
-{
- return initial_idmapping(mnt_userns) || mnt_userns == fs_userns;
-}
-
/**
* make_vfsuid - map a filesystem kuid according to an idmapping
* @idmap: the mount's idmapping
* Take a @kuid and remap it from @fs_userns into @idmap. Use this
* function when preparing a @kuid to be reported to userspace.
*
- * If no_idmapping() determines that this is not an idmapped mount we can
- * simply return @kuid unchanged.
+ * If initial_idmapping() determines that this is not an idmapped mount
+ * we can simply return @kuid unchanged.
* If initial_idmapping() tells us that the filesystem is not mounted with an
* idmapping we know the value of @kuid won't change when calling
* from_kuid() so we can simply retrieve the value via __kuid_val()
*/
vfsuid_t make_vfsuid(struct mnt_idmap *idmap,
- struct user_namespace *fs_userns,
- kuid_t kuid)
+ struct user_namespace *fs_userns,
+ kuid_t kuid)
{
uid_t uid;
- struct user_namespace *mnt_userns = idmap->owner;
- if (no_idmapping(mnt_userns, fs_userns))
+ if (idmap == &nop_mnt_idmap)
return VFSUIDT_INIT(kuid);
if (initial_idmapping(fs_userns))
uid = __kuid_val(kuid);
uid = from_kuid(fs_userns, kuid);
if (uid == (uid_t)-1)
return INVALID_VFSUID;
- return VFSUIDT_INIT(make_kuid(mnt_userns, uid));
+ return VFSUIDT_INIT_RAW(map_id_down(&idmap->uid_map, uid));
}
EXPORT_SYMBOL_GPL(make_vfsuid);
* Take a @kgid and remap it from @fs_userns into @idmap. Use this
* function when preparing a @kgid to be reported to userspace.
*
- * If no_idmapping() determines that this is not an idmapped mount we can
- * simply return @kgid unchanged.
+ * If initial_idmapping() determines that this is not an idmapped mount
+ * we can simply return @kgid unchanged.
* If initial_idmapping() tells us that the filesystem is not mounted with an
* idmapping we know the value of @kgid won't change when calling
* from_kgid() so we can simply retrieve the value via __kgid_val()
struct user_namespace *fs_userns, kgid_t kgid)
{
gid_t gid;
- struct user_namespace *mnt_userns = idmap->owner;
- if (no_idmapping(mnt_userns, fs_userns))
+ if (idmap == &nop_mnt_idmap)
return VFSGIDT_INIT(kgid);
if (initial_idmapping(fs_userns))
gid = __kgid_val(kgid);
gid = from_kgid(fs_userns, kgid);
if (gid == (gid_t)-1)
return INVALID_VFSGID;
- return VFSGIDT_INIT(make_kgid(mnt_userns, gid));
+ return VFSGIDT_INIT_RAW(map_id_down(&idmap->gid_map, gid));
}
EXPORT_SYMBOL_GPL(make_vfsgid);
struct user_namespace *fs_userns, vfsuid_t vfsuid)
{
uid_t uid;
- struct user_namespace *mnt_userns = idmap->owner;
- if (no_idmapping(mnt_userns, fs_userns))
+ if (idmap == &nop_mnt_idmap)
return AS_KUIDT(vfsuid);
- uid = from_kuid(mnt_userns, AS_KUIDT(vfsuid));
+ uid = map_id_up(&idmap->uid_map, __vfsuid_val(vfsuid));
if (uid == (uid_t)-1)
return INVALID_UID;
if (initial_idmapping(fs_userns))
struct user_namespace *fs_userns, vfsgid_t vfsgid)
{
gid_t gid;
- struct user_namespace *mnt_userns = idmap->owner;
- if (no_idmapping(mnt_userns, fs_userns))
+ if (idmap == &nop_mnt_idmap)
return AS_KGIDT(vfsgid);
- gid = from_kgid(mnt_userns, AS_KGIDT(vfsgid));
+ gid = map_id_up(&idmap->gid_map, __vfsgid_val(vfsgid));
if (gid == (gid_t)-1)
return INVALID_GID;
if (initial_idmapping(fs_userns))
#endif
EXPORT_SYMBOL_GPL(vfsgid_in_group_p);
+static int copy_mnt_idmap(struct uid_gid_map *map_from,
+ struct uid_gid_map *map_to)
+{
+ struct uid_gid_extent *forward, *reverse;
+ u32 nr_extents = READ_ONCE(map_from->nr_extents);
+ /* Pairs with smp_wmb() when writing the idmapping. */
+ smp_rmb();
+
+ /*
+ * Don't blindly copy @map_to into @map_from if nr_extents is
+ * smaller or equal to UID_GID_MAP_MAX_BASE_EXTENTS. Since we
+ * read @nr_extents someone could have written an idmapping and
+ * then we might end up with inconsistent data. So just don't do
+ * anything at all.
+ */
+ if (nr_extents == 0)
+ return 0;
+
+ /*
+ * Here we know that nr_extents is greater than zero which means
+ * a map has been written. Since idmappings can't be changed
+ * once they have been written we know that we can safely copy
+ * from @map_to into @map_from.
+ */
+
+ if (nr_extents <= UID_GID_MAP_MAX_BASE_EXTENTS) {
+ *map_to = *map_from;
+ return 0;
+ }
+
+ forward = kmemdup(map_from->forward,
+ nr_extents * sizeof(struct uid_gid_extent),
+ GFP_KERNEL_ACCOUNT);
+ if (!forward)
+ return -ENOMEM;
+
+ reverse = kmemdup(map_from->reverse,
+ nr_extents * sizeof(struct uid_gid_extent),
+ GFP_KERNEL_ACCOUNT);
+ if (!reverse) {
+ kfree(forward);
+ return -ENOMEM;
+ }
+
+ /*
+ * The idmapping isn't exposed anywhere so we don't need to care
+ * about ordering between extent pointers and @nr_extents
+ * initialization.
+ */
+ map_to->forward = forward;
+ map_to->reverse = reverse;
+ map_to->nr_extents = nr_extents;
+ return 0;
+}
+
+static void free_mnt_idmap(struct mnt_idmap *idmap)
+{
+ if (idmap->uid_map.nr_extents > UID_GID_MAP_MAX_BASE_EXTENTS) {
+ kfree(idmap->uid_map.forward);
+ kfree(idmap->uid_map.reverse);
+ }
+ if (idmap->gid_map.nr_extents > UID_GID_MAP_MAX_BASE_EXTENTS) {
+ kfree(idmap->gid_map.forward);
+ kfree(idmap->gid_map.reverse);
+ }
+ kfree(idmap);
+}
+
struct mnt_idmap *alloc_mnt_idmap(struct user_namespace *mnt_userns)
{
struct mnt_idmap *idmap;
+ int ret;
idmap = kzalloc(sizeof(struct mnt_idmap), GFP_KERNEL_ACCOUNT);
if (!idmap)
return ERR_PTR(-ENOMEM);
- idmap->owner = get_user_ns(mnt_userns);
refcount_set(&idmap->count, 1);
+ ret = copy_mnt_idmap(&mnt_userns->uid_map, &idmap->uid_map);
+ if (!ret)
+ ret = copy_mnt_idmap(&mnt_userns->gid_map, &idmap->gid_map);
+ if (ret) {
+ free_mnt_idmap(idmap);
+ idmap = ERR_PTR(ret);
+ }
return idmap;
}
*/
void mnt_idmap_put(struct mnt_idmap *idmap)
{
- if (idmap != &nop_mnt_idmap && refcount_dec_and_test(&idmap->count)) {
- put_user_ns(idmap->owner);
- kfree(idmap);
- }
+ if (idmap != &nop_mnt_idmap && refcount_dec_and_test(&idmap->count))
+ free_mnt_idmap(idmap);
}
EXPORT_SYMBOL_GPL(mnt_idmap_put);
* the vfsmount must be passed through @idmap. This function will then take
* care to map the inode according to @idmap before checking permissions.
* On non-idmapped mounts or if permission checking is to be performed on the
- * raw inode simply passs @nop_mnt_idmap.
+ * raw inode simply pass @nop_mnt_idmap.
*/
static int check_acl(struct mnt_idmap *idmap,
struct inode *inode, int mask)
* the vfsmount must be passed through @idmap. This function will then take
* care to map the inode according to @idmap before checking permissions.
* On non-idmapped mounts or if permission checking is to be performed on the
- * raw inode simply passs @nop_mnt_idmap.
+ * raw inode simply pass @nop_mnt_idmap.
*/
static int acl_permission_check(struct mnt_idmap *idmap,
struct inode *inode, int mask)
* the vfsmount must be passed through @idmap. This function will then take
* care to map the inode according to @idmap before checking permissions.
* On non-idmapped mounts or if permission checking is to be performed on the
- * raw inode simply passs @nop_mnt_idmap.
+ * raw inode simply pass @nop_mnt_idmap.
*/
int generic_permission(struct mnt_idmap *idmap, struct inode *inode,
int mask)
return PTR_ERR(step_into(nd, WALK_NOFOLLOW, nd->path.dentry));
}
-/* Returns 0 and nd will be valid on success; Retuns error, otherwise. */
+/* Returns 0 and nd will be valid on success; Returns error, otherwise. */
static int path_lookupat(struct nameidata *nd, unsigned flags, struct path *path)
{
const char *s = path_init(nd, flags);
return retval;
}
-/* Returns 0 and nd will be valid on success; Retuns error, otherwise. */
+/* Returns 0 and nd will be valid on success; Returns error, otherwise. */
static int path_parentat(struct nameidata *nd, unsigned flags,
struct path *parent)
{
* the vfsmount must be passed through @idmap. This function will then take
* care to map the inode according to @idmap before checking permissions.
* On non-idmapped mounts or if permission checking is to be performed on the
- * raw inode simply passs @nop_mnt_idmap.
+ * raw inode simply pass @nop_mnt_idmap.
*/
int vfs_create(struct mnt_idmap *idmap, struct inode *dir,
struct dentry *dentry, umode_t mode, bool want_excl)
* the vfsmount must be passed through @idmap. This function will then take
* care to map the inode according to @idmap before checking permissions.
* On non-idmapped mounts or if permission checking is to be performed on the
- * raw inode simply passs @nop_mnt_idmap.
+ * raw inode simply pass @nop_mnt_idmap.
*/
static int vfs_tmpfile(struct mnt_idmap *idmap,
const struct path *parentpath,
* the vfsmount must be passed through @idmap. This function will then take
* care to map the inode according to @idmap before checking permissions.
* On non-idmapped mounts or if permission checking is to be performed on the
- * raw inode simply passs @nop_mnt_idmap.
+ * raw inode simply pass @nop_mnt_idmap.
*/
int vfs_mknod(struct mnt_idmap *idmap, struct inode *dir,
struct dentry *dentry, umode_t mode, dev_t dev)
* the vfsmount must be passed through @idmap. This function will then take
* care to map the inode according to @idmap before checking permissions.
* On non-idmapped mounts or if permission checking is to be performed on the
- * raw inode simply passs @nop_mnt_idmap.
+ * raw inode simply pass @nop_mnt_idmap.
*/
int vfs_mkdir(struct mnt_idmap *idmap, struct inode *dir,
struct dentry *dentry, umode_t mode)
* the vfsmount must be passed through @idmap. This function will then take
* care to map the inode according to @idmap before checking permissions.
* On non-idmapped mounts or if permission checking is to be performed on the
- * raw inode simply passs @nop_mnt_idmap.
+ * raw inode simply pass @nop_mnt_idmap.
*/
int vfs_rmdir(struct mnt_idmap *idmap, struct inode *dir,
struct dentry *dentry)
* the vfsmount must be passed through @idmap. This function will then take
* care to map the inode according to @idmap before checking permissions.
* On non-idmapped mounts or if permission checking is to be performed on the
- * raw inode simply passs @nop_mnt_idmap.
+ * raw inode simply pass @nop_mnt_idmap.
*/
int vfs_unlink(struct mnt_idmap *idmap, struct inode *dir,
struct dentry *dentry, struct inode **delegated_inode)
* the vfsmount must be passed through @idmap. This function will then take
* care to map the inode according to @idmap before checking permissions.
* On non-idmapped mounts or if permission checking is to be performed on the
- * raw inode simply passs @nop_mnt_idmap.
+ * raw inode simply pass @nop_mnt_idmap.
*/
int vfs_symlink(struct mnt_idmap *idmap, struct inode *dir,
struct dentry *dentry, const char *oldname)
* the vfsmount must be passed through @idmap. This function will then take
* care to map the inode according to @idmap before checking permissions.
* On non-idmapped mounts or if permission checking is to be performed on the
- * raw inode simply passs @nop_mnt_idmap.
+ * raw inode simply pass @nop_mnt_idmap.
*/
int vfs_link(struct dentry *old_dentry, struct mnt_idmap *idmap,
struct inode *dir, struct dentry *new_dentry,
* can_move_mount_beneath - check that we can mount beneath the top mount
* @from: mount to mount beneath
* @to: mount under which to mount
+ * @mp: mountpoint of @to
*
* - Make sure that @to->dentry is actually the root of a mount under
* which we can mount another mount.
* Creating an idmapped mount with the filesystem wide idmapping
* doesn't make sense so block that. We don't allow mushy semantics.
*/
- if (!check_fsmapping(kattr->mnt_idmap, m->mnt_sb))
+ if (kattr->mnt_userns == m->mnt_sb->s_user_ns)
return -EINVAL;
/*
if (!folio_test_private(folio))
return NULL;
- spin_lock(&mapping->private_lock);
+ spin_lock(&mapping->i_private_lock);
req = nfs_folio_private_request(folio);
if (req) {
WARN_ON_ONCE(req->wb_head != req);
kref_get(&req->wb_kref);
}
- spin_unlock(&mapping->private_lock);
+ spin_unlock(&mapping->i_private_lock);
return req;
}
* Swap-space should not get truncated. Hence no need to plug the race
* with invalidate/truncate.
*/
- spin_lock(&mapping->private_lock);
+ spin_lock(&mapping->i_private_lock);
if (likely(!folio_test_swapcache(folio))) {
set_bit(PG_MAPPED, &req->wb_flags);
folio_set_private(folio);
folio->private = req;
}
- spin_unlock(&mapping->private_lock);
+ spin_unlock(&mapping->i_private_lock);
atomic_long_inc(&nfsi->nrequests);
/* this a head request for a page group - mark it as having an
* extra reference so sub groups can follow suit.
struct folio *folio = nfs_page_to_folio(req->wb_head);
struct address_space *mapping = folio_file_mapping(folio);
- spin_lock(&mapping->private_lock);
+ spin_lock(&mapping->i_private_lock);
if (likely(folio && !folio_test_swapcache(folio))) {
folio->private = NULL;
folio_clear_private(folio);
clear_bit(PG_MAPPED, &req->wb_head->wb_flags);
}
- spin_unlock(&mapping->private_lock);
+ spin_unlock(&mapping->i_private_lock);
}
if (test_and_clear_bit(PG_INODE_REF, &req->wb_flags)) {
/*
* The page may not be locked, eg if called from try_to_unmap_one()
*/
- spin_lock(&mapping->private_lock);
+ spin_lock(&mapping->i_private_lock);
head = folio_buffers(folio);
if (head) {
struct buffer_head *bh = head;
} else if (ret) {
nr_dirty = 1 << (folio_shift(folio) - inode->i_blkbits);
}
- spin_unlock(&mapping->private_lock);
+ spin_unlock(&mapping->i_private_lock);
if (nr_dirty)
nilfs_set_file_dirty(inode, nr_dirty);
*
* If the page does not have buffers, we create them and set them uptodate.
* The page may not be locked which is why we need to handle the buffers under
- * the mapping->private_lock. Once the buffers are marked dirty we no longer
+ * the mapping->i_private_lock. Once the buffers are marked dirty we no longer
* need the lock since try_to_free_buffers() does not free dirty buffers.
*/
void mark_ntfs_record_dirty(struct page *page, const unsigned int ofs) {
BUG_ON(!PageUptodate(page));
end = ofs + ni->itype.index.block_size;
bh_size = VFS_I(ni)->i_sb->s_blocksize;
- spin_lock(&mapping->private_lock);
+ spin_lock(&mapping->i_private_lock);
if (unlikely(!page_has_buffers(page))) {
- spin_unlock(&mapping->private_lock);
+ spin_unlock(&mapping->i_private_lock);
bh = head = alloc_page_buffers(page, bh_size, true);
- spin_lock(&mapping->private_lock);
+ spin_lock(&mapping->i_private_lock);
if (likely(!page_has_buffers(page))) {
struct buffer_head *tail;
break;
set_buffer_dirty(bh);
} while ((bh = bh->b_this_page) != head);
- spin_unlock(&mapping->private_lock);
+ spin_unlock(&mapping->i_private_lock);
filemap_dirty_folio(mapping, page_folio(page));
if (unlikely(buffers_to_free)) {
do {
/**
* ntfs_dir_fsync - sync a directory to disk
* @filp: directory to be synced
- * @dentry: dentry describing the directory to sync
+ * @start: offset in bytes of the beginning of data range to sync
+ * @end: offset in bytes of the end of data range (inclusive)
* @datasync: if non-zero only flush user data and not metadata
*
* Data integrity sync of a directory to disk. Used for fsync, fdatasync, and
* 'get_current_cred()' function), that will clear the
* non_rcu field, because now that other user may be
* expecting RCU freeing. But normal thread-synchronous
- * cred accesses will keep things non-RCY.
+ * cred accesses will keep things non-racy to avoid RCU
+ * freeing.
*/
override_cred->non_rcu = 1;
bool was_empty = false;
bool wake_next_writer = false;
+ /*
+ * Reject writing to watch queue pipes before the point where we lock
+ * the pipe.
+ * Otherwise, lockdep would be unhappy if the caller already has another
+ * pipe locked.
+ * If we had to support locking a normal pipe and a notification pipe at
+ * the same time, we could set up lockdep annotations for that, but
+ * since we don't actually need that, it's simpler to just bail here.
+ */
+ if (pipe_has_watch_queue(pipe))
+ return -EXDEV;
+
/* Null write succeeds. */
if (unlikely(total_len == 0))
return 0;
goto out;
}
- if (pipe_has_watch_queue(pipe)) {
- ret = -EXDEV;
- goto out;
- }
-
/*
* If it wasn't empty we try to merge new data into
* the last buffer.
pipe->tail = tail;
pipe->head = head;
+ if (!pipe_has_watch_queue(pipe)) {
+ pipe->max_usage = nr_slots;
+ pipe->nr_accounted = nr_slots;
+ }
+
spin_unlock_irq(&pipe->rd_wait.lock);
/* This might have made more room for writers */
if (ret < 0)
goto out_revert_acct;
- pipe->max_usage = nr_slots;
- pipe->nr_accounted = nr_slots;
return pipe->max_usage * PAGE_SIZE;
out_revert_acct:
* the vfsmount must be passed through @idmap. This function will then
* take care to map the inode according to @idmap before checking
* permissions. On non-idmapped mounts or if permission checking is to be
- * performed on the raw inode simply passs @nop_mnt_idmap.
+ * performed on the raw inode simply pass @nop_mnt_idmap.
*/
int
posix_acl_chmod(struct mnt_idmap *idmap, struct dentry *dentry,
* the vfsmount must be passed through @idmap. This function will then
* take care to map the inode according to @idmap before checking
* permissions. On non-idmapped mounts or if permission checking is to be
- * performed on the raw inode simply passs @nop_mnt_idmap.
+ * performed on the raw inode simply pass @nop_mnt_idmap.
*
* Called from set_acl inode operations.
*/
const char *name = NULL;
if (file) {
- struct inode *inode = file_inode(vma->vm_file);
+ const struct inode *inode = file_user_inode(vma->vm_file);
+
dev = inode->i_sb->s_dev;
ino = inode->i_ino;
pgoff = ((loff_t)vma->vm_pgoff) << PAGE_SHIFT;
* the vfsmount must be passed through @idmap. This function will then
* take care to map the inode according to @idmap before filling in the
* uid and gid filds. On non-idmapped mounts or if permission checking is to be
- * performed on the raw inode simply passs @nop_mnt_idmap.
+ * performed on the raw inode simply pass @nop_mnt_idmap.
*/
void generic_fillattr(struct mnt_idmap *idmap, u32 request_mask,
struct inode *inode, struct kstat *stat)
static struct super_block *alloc_super(struct file_system_type *type, int flags,
struct user_namespace *user_ns)
{
- struct super_block *s = kzalloc(sizeof(struct super_block), GFP_USER);
+ struct super_block *s = kzalloc(sizeof(struct super_block), GFP_KERNEL);
static const struct super_operations default_op;
int i;
struct file *eventfd_fget(int fd);
struct eventfd_ctx *eventfd_ctx_fdget(int fd);
struct eventfd_ctx *eventfd_ctx_fileget(struct file *file);
-__u64 eventfd_signal(struct eventfd_ctx *ctx, __u64 n);
-__u64 eventfd_signal_mask(struct eventfd_ctx *ctx, __u64 n, __poll_t mask);
+void eventfd_signal_mask(struct eventfd_ctx *ctx, __poll_t mask);
int eventfd_ctx_remove_wait_queue(struct eventfd_ctx *ctx, wait_queue_entry_t *wait,
__u64 *cnt);
void eventfd_ctx_do_read(struct eventfd_ctx *ctx, __u64 *cnt);
return ERR_PTR(-ENOSYS);
}
-static inline int eventfd_signal(struct eventfd_ctx *ctx, __u64 n)
+static inline void eventfd_signal_mask(struct eventfd_ctx *ctx, __poll_t mask)
{
- return -ENOSYS;
-}
-
-static inline int eventfd_signal_mask(struct eventfd_ctx *ctx, __u64 n,
- unsigned mask)
-{
- return -ENOSYS;
}
static inline void eventfd_ctx_put(struct eventfd_ctx *ctx)
#endif
+static inline void eventfd_signal(struct eventfd_ctx *ctx)
+{
+ eventfd_signal_mask(ctx, 0);
+}
+
#endif /* _LINUX_EVENTFD_H */
* @a_ops: Methods.
* @flags: Error bits and flags (AS_*).
* @wb_err: The most recent error which has occurred.
- * @private_lock: For use by the owner of the address_space.
- * @private_list: For use by the owner of the address_space.
- * @private_data: For use by the owner of the address_space.
+ * @i_private_lock: For use by the owner of the address_space.
+ * @i_private_list: For use by the owner of the address_space.
+ * @i_private_data: For use by the owner of the address_space.
*/
struct address_space {
struct inode *host;
unsigned long flags;
struct rw_semaphore i_mmap_rwsem;
errseq_t wb_err;
- spinlock_t private_lock;
- struct list_head private_list;
- void *private_data;
+ spinlock_t i_private_lock;
+ struct list_head i_private_list;
+ void * i_private_data;
} __attribute__((aligned(sizeof(long)))) __randomize_layout;
/*
* On most architectures that alignment is already the case; but
struct path *backing_file_user_path(struct file *f);
/*
- * file_user_path - get the path to display for memory mapped file
- *
* When mmapping a file on a stackable filesystem (e.g., overlayfs), the file
* stored in ->vm_file is a backing file whose f_inode is on the underlying
- * filesystem. When the mapped file path is displayed to user (e.g. via
- * /proc/<pid>/maps), this helper should be used to get the path to display
- * to the user, which is the path of the fd that user has requested to map.
+ * filesystem. When the mapped file path and inode number are displayed to
+ * user (e.g. via /proc/<pid>/maps), these helpers should be used to get the
+ * path and inode number to display to the user, which is the path of the fd
+ * that user has requested to map and the inode number that would be returned
+ * by fstat() on that same fd.
*/
+/* Get the path to display in /proc/<pid>/maps */
static inline const struct path *file_user_path(struct file *f)
{
if (unlikely(f->f_mode & FMODE_BACKING))
return backing_file_user_path(f);
return &f->f_path;
}
+/* Get the inode whose inode number to display in /proc/<pid>/maps */
+static inline const struct inode *file_user_inode(struct file *f)
+{
+ if (unlikely(f->f_mode & FMODE_BACKING))
+ return d_inode(backing_file_user_path(f)->dentry);
+ return file_inode(f);
+}
static inline struct file *file_clone_open(struct file *file)
{
return from_vfsgid(idmap, fs_userns, VFSGIDT_INIT(current_fsgid()));
}
-bool check_fsmapping(const struct mnt_idmap *idmap,
- const struct super_block *sb);
-
#endif /* _LINUX_MNT_IDMAPPING_H */
struct user_namespace;
extern struct user_namespace init_user_ns;
+struct uid_gid_map;
typedef struct {
uid_t val;
return from_kgid(ns, gid) != (gid_t) -1;
}
+u32 map_id_down(struct uid_gid_map *map, u32 id);
+u32 map_id_up(struct uid_gid_map *map, u32 id);
+
#else
static inline kuid_t make_kuid(struct user_namespace *from, uid_t uid)
return gid_valid(gid);
}
+static inline u32 map_id_down(struct uid_gid_map *map, u32 id)
+{
+ return id;
+}
+
+static inline u32 map_id_up(struct uid_gid_map *map, u32 id)
+{
+ return id;
+}
#endif /* CONFIG_USER_NS */
#endif /* _LINUX_UIDGID_H */
/* writeback.h requires fs.h; it, too, is not included from here. */
static inline void wait_on_inode(struct inode *inode)
{
- might_sleep();
wait_on_bit(&inode->i_state, __I_NEW, TASK_UNINTERRUPTIBLE);
}
int ops = atomic_xchg(&ev_fd->ops, 0);
if (ops & BIT(IO_EVENTFD_OP_SIGNAL_BIT))
- eventfd_signal_mask(ev_fd->cq_ev_fd, 1, EPOLL_URING_WAKE);
+ eventfd_signal_mask(ev_fd->cq_ev_fd, EPOLL_URING_WAKE);
/* IO_EVENTFD_OP_FREE_BIT may not be set here depending on callback
* ordering in a race but if references are 0 we know we have to free
goto out;
if (likely(eventfd_signal_allowed())) {
- eventfd_signal_mask(ev_fd->cq_ev_fd, 1, EPOLL_URING_WAKE);
+ eventfd_signal_mask(ev_fd->cq_ev_fd, EPOLL_URING_WAKE);
} else {
atomic_inc(&ev_fd->refs);
if (!atomic_fetch_or(BIT(IO_EVENTFD_OP_SIGNAL_BIT), &ev_fd->ops))
}
EXPORT_SYMBOL(__put_user_ns);
-/**
+/*
* struct idmap_key - holds the information necessary to find an idmapping in a
* sorted idmap array. It is passed to cmp_map_id() as first argument.
*/
u32 count; /* == 0 unless used with map_id_range_down() */
};
-/**
+/*
* cmp_map_id - Function to be passed to bsearch() to find the requested
* idmapping. Expects struct idmap_key to be passed via @k.
*/
return 1;
}
-/**
+/*
* map_id_range_down_max - Find idmap via binary search in ordered idmap array.
* Can only be called if number of mappings exceeds UID_GID_MAP_MAX_BASE_EXTENTS.
*/
sizeof(struct uid_gid_extent), cmp_map_id);
}
-/**
+/*
* map_id_range_down_base - Find idmap via binary search in static extent array.
* Can only be called if number of mappings is equal or less than
* UID_GID_MAP_MAX_BASE_EXTENTS.
return id;
}
-static u32 map_id_down(struct uid_gid_map *map, u32 id)
+u32 map_id_down(struct uid_gid_map *map, u32 id)
{
return map_id_range_down(map, id, 1);
}
-/**
+/*
* map_id_up_base - Find idmap via binary search in static extent array.
* Can only be called if number of mappings is equal or less than
* UID_GID_MAP_MAX_BASE_EXTENTS.
return NULL;
}
-/**
+/*
* map_id_up_max - Find idmap via binary search in ordered idmap array.
* Can only be called if number of mappings exceeds UID_GID_MAP_MAX_BASE_EXTENTS.
*/
sizeof(struct uid_gid_extent), cmp_map_id);
}
-static u32 map_id_up(struct uid_gid_map *map, u32 id)
+u32 map_id_up(struct uid_gid_map *map, u32 id)
{
struct uid_gid_extent *extent;
unsigned extents = map->nr_extents;
return false;
}
-/**
+/*
* insert_extent - Safely insert a new idmap extent into struct uid_gid_map.
* Takes care to allocate a 4K block of memory if the number of mappings exceeds
* UID_GID_MAP_MAX_BASE_EXTENTS.
return 0;
}
-/**
+/*
* sort_idmaps - Sorts an array of idmap entries.
* Can only be called if number of mappings exceeds UID_GID_MAP_MAX_BASE_EXTENTS.
*/
goto error;
ret = -ENOMEM;
- pages = kcalloc(sizeof(struct page *), nr_pages, GFP_KERNEL);
+ pages = kcalloc(nr_pages, sizeof(struct page *), GFP_KERNEL);
if (!pages)
goto error;
* The VERY common case is inode->mapping == &inode->i_data but,
* this may not be true for device special inodes.
*/
- return (struct resv_map *)(&inode->i_data)->private_data;
+ return (struct resv_map *)(&inode->i_data)->i_private_data;
}
static struct resv_map *vma_resv_map(struct vm_area_struct *vma)
* only one element of the array here.
*/
for (; i >= 0 && unlikely(t->entries[i].threshold > usage); i--)
- eventfd_signal(t->entries[i].eventfd, 1);
+ eventfd_signal(t->entries[i].eventfd);
/* i = current_threshold + 1 */
i++;
* only one element of the array here.
*/
for (; i < t->size && unlikely(t->entries[i].threshold <= usage); i++)
- eventfd_signal(t->entries[i].eventfd, 1);
+ eventfd_signal(t->entries[i].eventfd);
/* Update current_threshold */
t->current_threshold = i - 1;
spin_lock(&memcg_oom_lock);
list_for_each_entry(ev, &memcg->oom_notify, list)
- eventfd_signal(ev->eventfd, 1);
+ eventfd_signal(ev->eventfd);
spin_unlock(&memcg_oom_lock);
return 0;
/* already in OOM ? */
if (memcg->under_oom)
- eventfd_signal(eventfd, 1);
+ eventfd_signal(eventfd);
spin_unlock(&memcg_oom_lock);
return 0;
event->unregister_event(memcg, event->eventfd);
/* Notify userspace the event is going away. */
- eventfd_signal(event->eventfd, 1);
+ eventfd_signal(event->eventfd);
eventfd_ctx_put(event->eventfd);
kfree(event);
recheck_buffers:
busy = false;
- spin_lock(&mapping->private_lock);
+ spin_lock(&mapping->i_private_lock);
bh = head;
do {
if (atomic_read(&bh->b_count)) {
rc = -EAGAIN;
goto unlock_buffers;
}
- spin_unlock(&mapping->private_lock);
+ spin_unlock(&mapping->i_private_lock);
invalidate_bh_lrus();
invalidated = true;
goto recheck_buffers;
rc = MIGRATEPAGE_SUCCESS;
unlock_buffers:
if (check_refs)
- spin_unlock(&mapping->private_lock);
+ spin_unlock(&mapping->i_private_lock);
bh = head;
do {
unlock_buffer(bh);
continue;
if (level < ev->level)
continue;
- eventfd_signal(ev->efd, 1);
+ eventfd_signal(ev->efd);
ret = true;
}
mutex_unlock(&vmpr->events_lock);
if (is_msi(mdev_state)) {
if (mdev_state->msi_evtfd)
- eventfd_signal(mdev_state->msi_evtfd, 1);
+ eventfd_signal(mdev_state->msi_evtfd);
} else if (is_intx(mdev_state)) {
if (mdev_state->intx_evtfd && !mdev_state->intx_mask) {
- eventfd_signal(mdev_state->intx_evtfd, 1);
+ eventfd_signal(mdev_state->intx_evtfd);
mdev_state->intx_mask = true;
}
}
TARGETS += filesystems/binderfs
TARGETS += filesystems/epoll
TARGETS += filesystems/fat
+TARGETS += filesystems/overlayfs
TARGETS += firmware
TARGETS += fpu
TARGETS += ftrace
--- /dev/null
+# SPDX-License-Identifier: GPL-2.0-only
+dev_in_maps
--- /dev/null
+# SPDX-License-Identifier: GPL-2.0
+
+TEST_GEN_PROGS := dev_in_maps
+
+CFLAGS := -Wall -Werror
+
+include ../../lib.mk
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+#define _GNU_SOURCE
+
+#include <inttypes.h>
+#include <unistd.h>
+#include <stdio.h>
+
+#include <linux/unistd.h>
+#include <linux/types.h>
+#include <linux/mount.h>
+#include <sys/syscall.h>
+#include <sys/stat.h>
+#include <sys/mount.h>
+#include <sys/mman.h>
+#include <sched.h>
+#include <fcntl.h>
+
+#include "../../kselftest.h"
+#include "log.h"
+
+static int sys_fsopen(const char *fsname, unsigned int flags)
+{
+ return syscall(__NR_fsopen, fsname, flags);
+}
+
+static int sys_fsconfig(int fd, unsigned int cmd, const char *key, const char *value, int aux)
+{
+ return syscall(__NR_fsconfig, fd, cmd, key, value, aux);
+}
+
+static int sys_fsmount(int fd, unsigned int flags, unsigned int attr_flags)
+{
+ return syscall(__NR_fsmount, fd, flags, attr_flags);
+}
+
+static int sys_move_mount(int from_dfd, const char *from_pathname,
+ int to_dfd, const char *to_pathname,
+ unsigned int flags)
+{
+ return syscall(__NR_move_mount, from_dfd, from_pathname, to_dfd, to_pathname, flags);
+}
+
+static long get_file_dev_and_inode(void *addr, struct statx *stx)
+{
+ char buf[4096];
+ FILE *mapf;
+
+ mapf = fopen("/proc/self/maps", "r");
+ if (mapf == NULL)
+ return pr_perror("fopen(/proc/self/maps)");
+
+ while (fgets(buf, sizeof(buf), mapf)) {
+ unsigned long start, end;
+ uint32_t maj, min;
+ __u64 ino;
+
+ if (sscanf(buf, "%lx-%lx %*s %*s %x:%x %llu",
+ &start, &end, &maj, &min, &ino) != 5)
+ return pr_perror("unable to parse: %s", buf);
+ if (start == (unsigned long)addr) {
+ stx->stx_dev_major = maj;
+ stx->stx_dev_minor = min;
+ stx->stx_ino = ino;
+ return 0;
+ }
+ }
+
+ return pr_err("unable to find the mapping");
+}
+
+static int ovl_mount(void)
+{
+ int tmpfs, fsfd, ovl;
+
+ fsfd = sys_fsopen("tmpfs", 0);
+ if (fsfd == -1)
+ return pr_perror("fsopen(tmpfs)");
+
+ if (sys_fsconfig(fsfd, FSCONFIG_CMD_CREATE, NULL, NULL, 0) == -1)
+ return pr_perror("FSCONFIG_CMD_CREATE");
+
+ tmpfs = sys_fsmount(fsfd, 0, 0);
+ if (tmpfs == -1)
+ return pr_perror("fsmount");
+
+ close(fsfd);
+
+ /* overlayfs can't be constructed on top of a detached mount. */
+ if (sys_move_mount(tmpfs, "", AT_FDCWD, "/tmp", MOVE_MOUNT_F_EMPTY_PATH))
+ return pr_perror("move_mount");
+ close(tmpfs);
+
+ if (mkdir("/tmp/w", 0755) == -1 ||
+ mkdir("/tmp/u", 0755) == -1 ||
+ mkdir("/tmp/l", 0755) == -1)
+ return pr_perror("mkdir");
+
+ fsfd = sys_fsopen("overlay", 0);
+ if (fsfd == -1)
+ return pr_perror("fsopen(overlay)");
+ if (sys_fsconfig(fsfd, FSCONFIG_SET_STRING, "source", "test", 0) == -1 ||
+ sys_fsconfig(fsfd, FSCONFIG_SET_STRING, "lowerdir", "/tmp/l", 0) == -1 ||
+ sys_fsconfig(fsfd, FSCONFIG_SET_STRING, "upperdir", "/tmp/u", 0) == -1 ||
+ sys_fsconfig(fsfd, FSCONFIG_SET_STRING, "workdir", "/tmp/w", 0) == -1)
+ return pr_perror("fsconfig");
+ if (sys_fsconfig(fsfd, FSCONFIG_CMD_CREATE, NULL, NULL, 0) == -1)
+ return pr_perror("fsconfig");
+ ovl = sys_fsmount(fsfd, 0, 0);
+ if (ovl == -1)
+ return pr_perror("fsmount");
+
+ return ovl;
+}
+
+/*
+ * Check that the file device and inode shown in /proc/pid/maps match values
+ * returned by stat(2).
+ */
+static int test(void)
+{
+ struct statx stx, mstx;
+ int ovl, fd;
+ void *addr;
+
+ ovl = ovl_mount();
+ if (ovl == -1)
+ return -1;
+
+ fd = openat(ovl, "test", O_RDWR | O_CREAT, 0644);
+ if (fd == -1)
+ return pr_perror("openat");
+
+ addr = mmap(NULL, 4096, PROT_READ | PROT_WRITE, MAP_FILE | MAP_SHARED, fd, 0);
+ if (addr == MAP_FAILED)
+ return pr_perror("mmap");
+
+ if (get_file_dev_and_inode(addr, &mstx))
+ return -1;
+ if (statx(fd, "", AT_EMPTY_PATH | AT_STATX_SYNC_AS_STAT, STATX_INO, &stx))
+ return pr_perror("statx");
+
+ if (stx.stx_dev_major != mstx.stx_dev_major ||
+ stx.stx_dev_minor != mstx.stx_dev_minor ||
+ stx.stx_ino != mstx.stx_ino)
+ return pr_fail("unmatched dev:ino %x:%x:%llx (expected %x:%x:%llx)\n",
+ mstx.stx_dev_major, mstx.stx_dev_minor, mstx.stx_ino,
+ stx.stx_dev_major, stx.stx_dev_minor, stx.stx_ino);
+
+ ksft_test_result_pass("devices are matched\n");
+ return 0;
+}
+
+int main(int argc, char **argv)
+{
+ int fsfd;
+
+ fsfd = sys_fsopen("overlay", 0);
+ if (fsfd == -1) {
+ ksft_test_result_skip("unable to create overlay mount\n");
+ return 1;
+ }
+ close(fsfd);
+
+ /* Create a new mount namespace to not care about cleaning test mounts. */
+ if (unshare(CLONE_NEWNS) == -1) {
+ ksft_test_result_skip("unable to create a new mount namespace\n");
+ return 1;
+ }
+
+ if (mount(NULL, "/", NULL, MS_SLAVE | MS_REC, NULL) == -1) {
+ pr_perror("mount");
+ return 1;
+ }
+
+ ksft_set_plan(1);
+
+ if (test())
+ return 1;
+
+ ksft_exit_pass();
+ return 0;
+}
--- /dev/null
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef __SELFTEST_TIMENS_LOG_H__
+#define __SELFTEST_TIMENS_LOG_H__
+
+#define pr_msg(fmt, lvl, ...) \
+ ksft_print_msg("[%s] (%s:%d)\t" fmt "\n", \
+ lvl, __FILE__, __LINE__, ##__VA_ARGS__)
+
+#define pr_p(func, fmt, ...) func(fmt ": %m", ##__VA_ARGS__)
+
+#define pr_err(fmt, ...) \
+ ({ \
+ ksft_test_result_error(fmt "\n", ##__VA_ARGS__); \
+ -1; \
+ })
+
+#define pr_fail(fmt, ...) \
+ ({ \
+ ksft_test_result_fail(fmt, ##__VA_ARGS__); \
+ -1; \
+ })
+
+#define pr_perror(fmt, ...) pr_p(pr_err, fmt, ##__VA_ARGS__)
+
+#endif
list_for_each_entry_srcu(irqfd, &resampler->list, resampler_link,
srcu_read_lock_held(&resampler->kvm->irq_srcu))
- eventfd_signal(irqfd->resamplefd, 1);
+ eventfd_signal(irqfd->resamplefd);
}
/*
if (!ioeventfd_in_range(p, addr, len, val))
return -EOPNOTSUPP;
- eventfd_signal(p->eventfd, 1);
+ eventfd_signal(p->eventfd);
return 0;
}