Merge tag 'for-linus-20190601' of git://git.kernel.dk/linux-block
Pull block fixes from Jens Axboe:
- A set of patches fixing code comments / kerneldoc (Bart)
- Don't allow loop file change for exclusive open (Jan)
- Fix revalidate of hidden genhd (Jan)
- Init queue failure memory free fix (Jes)
- Improve rq limits failure print (John)
- Fixup for queue removal/addition (Ming)
- Missed error progagation for io_uring buffer registration (Pavel)
* tag 'for-linus-20190601' of git://git.kernel.dk/linux-block:
block: print offending values when cloned rq limits are exceeded
blk-mq: Document the blk_mq_hw_queue_to_node() arguments
blk-mq: Fix spelling in a source code comment
block: Fix bsg_setup_queue() kernel-doc header
block: Fix rq_qos_wait() kernel-doc header
block: Fix blk_mq_*_map_queues() kernel-doc headers
block: Fix throtl_pending_timer_fn() kernel-doc header
block: Convert blk_invalidate_devt() header into a non-kernel-doc header
block/partitions/ldm: Convert a kernel-doc header into a non-kernel-doc header
blk-mq: Fix memory leak in error handling
block: don't protect generic_make_request_checks with blk_queue_enter
block: move blk_exit_queue into __blk_release_queue
block: Don't revalidate bdev of hidden gendisk
loop: Don't change loop device under exclusive opener
io_uring: Fix __io_uring_register() false success
diff --git a/block/blk-core.c b/block/blk-core.c
index 1bf83a0..ee1b35f 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -282,35 +282,6 @@
}
EXPORT_SYMBOL_GPL(blk_set_queue_dying);
-/* Unconfigure the I/O scheduler and dissociate from the cgroup controller. */
-void blk_exit_queue(struct request_queue *q)
-{
- /*
- * Since the I/O scheduler exit code may access cgroup information,
- * perform I/O scheduler exit before disassociating from the block
- * cgroup controller.
- */
- if (q->elevator) {
- ioc_clear_queue(q);
- elevator_exit(q, q->elevator);
- q->elevator = NULL;
- }
-
- /*
- * Remove all references to @q from the block cgroup controller before
- * restoring @q->queue_lock to avoid that restoring this pointer causes
- * e.g. blkcg_print_blkgs() to crash.
- */
- blkcg_exit_queue(q);
-
- /*
- * Since the cgroup code may dereference the @q->backing_dev_info
- * pointer, only decrease its reference count after having removed the
- * association with the block cgroup controller.
- */
- bdi_put(q->backing_dev_info);
-}
-
/**
* blk_cleanup_queue - shutdown a request queue
* @q: request queue to shutdown
@@ -346,14 +317,6 @@
del_timer_sync(&q->backing_dev_info->laptop_mode_wb_timer);
blk_sync_queue(q);
- /*
- * I/O scheduler exit is only safe after the sysfs scheduler attribute
- * has been removed.
- */
- WARN_ON_ONCE(q->kobj.state_in_sysfs);
-
- blk_exit_queue(q);
-
if (queue_is_mq(q))
blk_mq_exit_queue(q);
@@ -994,22 +957,8 @@
* yet.
*/
struct bio_list bio_list_on_stack[2];
- blk_mq_req_flags_t flags = 0;
- struct request_queue *q = bio->bi_disk->queue;
blk_qc_t ret = BLK_QC_T_NONE;
- if (bio->bi_opf & REQ_NOWAIT)
- flags = BLK_MQ_REQ_NOWAIT;
- if (bio_flagged(bio, BIO_QUEUE_ENTERED))
- blk_queue_enter_live(q);
- else if (blk_queue_enter(q, flags) < 0) {
- if (!blk_queue_dying(q) && (bio->bi_opf & REQ_NOWAIT))
- bio_wouldblock_error(bio);
- else
- bio_io_error(bio);
- return ret;
- }
-
if (!generic_make_request_checks(bio))
goto out;
@@ -1046,22 +995,11 @@
bio_list_init(&bio_list_on_stack[0]);
current->bio_list = bio_list_on_stack;
do {
- bool enter_succeeded = true;
+ struct request_queue *q = bio->bi_disk->queue;
+ blk_mq_req_flags_t flags = bio->bi_opf & REQ_NOWAIT ?
+ BLK_MQ_REQ_NOWAIT : 0;
- if (unlikely(q != bio->bi_disk->queue)) {
- if (q)
- blk_queue_exit(q);
- q = bio->bi_disk->queue;
- flags = 0;
- if (bio->bi_opf & REQ_NOWAIT)
- flags = BLK_MQ_REQ_NOWAIT;
- if (blk_queue_enter(q, flags) < 0) {
- enter_succeeded = false;
- q = NULL;
- }
- }
-
- if (enter_succeeded) {
+ if (likely(blk_queue_enter(q, flags) == 0)) {
struct bio_list lower, same;
/* Create a fresh bio_list for all subordinate requests */
@@ -1069,6 +1007,8 @@
bio_list_init(&bio_list_on_stack[0]);
ret = q->make_request_fn(q, bio);
+ blk_queue_exit(q);
+
/* sort new bios into those for a lower level
* and those for the same level
*/
@@ -1095,8 +1035,6 @@
current->bio_list = NULL; /* deactivate */
out:
- if (q)
- blk_queue_exit(q);
return ret;
}
EXPORT_SYMBOL(generic_make_request);
@@ -1200,7 +1138,9 @@
struct request *rq)
{
if (blk_rq_sectors(rq) > blk_queue_get_max_sectors(q, req_op(rq))) {
- printk(KERN_ERR "%s: over max size limit.\n", __func__);
+ printk(KERN_ERR "%s: over max size limit. (%u > %u)\n",
+ __func__, blk_rq_sectors(rq),
+ blk_queue_get_max_sectors(q, req_op(rq)));
return -EIO;
}
@@ -1212,7 +1152,8 @@
*/
blk_recalc_rq_segments(rq);
if (rq->nr_phys_segments > queue_max_segments(q)) {
- printk(KERN_ERR "%s: over max segments limit.\n", __func__);
+ printk(KERN_ERR "%s: over max segments limit. (%hu > %hu)\n",
+ __func__, rq->nr_phys_segments, queue_max_segments(q));
return -EIO;
}
diff --git a/block/blk-mq-cpumap.c b/block/blk-mq-cpumap.c
index 48bebf0..f945621 100644
--- a/block/blk-mq-cpumap.c
+++ b/block/blk-mq-cpumap.c
@@ -42,8 +42,8 @@
/*
* First do sequential mapping between CPUs and queues.
* In case we still have CPUs to map, and we have some number of
- * threads per cores then map sibling threads to the same queue for
- * performace optimizations.
+ * threads per cores then map sibling threads to the same queue
+ * for performance optimizations.
*/
if (cpu < nr_queues) {
map[cpu] = cpu_to_queue_index(qmap, nr_queues, cpu);
@@ -60,7 +60,11 @@
}
EXPORT_SYMBOL_GPL(blk_mq_map_queues);
-/*
+/**
+ * blk_mq_hw_queue_to_node - Look up the memory node for a hardware queue index
+ * @qmap: CPU to hardware queue map.
+ * @index: hardware queue index.
+ *
* We have no quick way of doing reverse lookups. This is only used at
* queue init time, so runtime isn't important.
*/
diff --git a/block/blk-mq-pci.c b/block/blk-mq-pci.c
index ad4545a..b595a94 100644
--- a/block/blk-mq-pci.c
+++ b/block/blk-mq-pci.c
@@ -13,7 +13,7 @@
/**
* blk_mq_pci_map_queues - provide a default queue mapping for PCI device
- * @set: tagset to provide the mapping for
+ * @qmap: CPU to hardware queue map.
* @pdev: PCI device associated with @set.
* @offset: Offset to use for the pci irq vector
*
diff --git a/block/blk-mq-rdma.c b/block/blk-mq-rdma.c
index cc921e6..14f968e 100644
--- a/block/blk-mq-rdma.c
+++ b/block/blk-mq-rdma.c
@@ -8,8 +8,8 @@
/**
* blk_mq_rdma_map_queues - provide a default queue mapping for rdma device
- * @set: tagset to provide the mapping for
- * @dev: rdma device associated with @set.
+ * @map: CPU to hardware queue map.
+ * @dev: rdma device to provide a mapping for.
* @first_vec: first interrupt vectors to use for queues (usually 0)
*
* This function assumes the rdma device @dev has at least as many available
diff --git a/block/blk-mq-virtio.c b/block/blk-mq-virtio.c
index 75a52c1..4883416 100644
--- a/block/blk-mq-virtio.c
+++ b/block/blk-mq-virtio.c
@@ -11,8 +11,8 @@
/**
* blk_mq_virtio_map_queues - provide a default queue mapping for virtio device
- * @set: tagset to provide the mapping for
- * @vdev: virtio device associated with @set.
+ * @qmap: CPU to hardware queue map.
+ * @vdev: virtio device to provide a mapping for.
* @first_vec: first interrupt vectors to use for queues (usually 0)
*
* This function assumes the virtio device @vdev has at least as many available
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 32b8ad3..ce0f5f4 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -2865,7 +2865,7 @@
goto err_exit;
if (blk_mq_alloc_ctxs(q))
- goto err_exit;
+ goto err_poll;
/* init q->mq_kobj and sw queues' kobjects */
blk_mq_sysfs_init(q);
@@ -2929,6 +2929,9 @@
kfree(q->queue_hw_ctx);
err_sys_init:
blk_mq_sysfs_deinit(q);
+err_poll:
+ blk_stat_free_callback(q->poll_cb);
+ q->poll_cb = NULL;
err_exit:
q->mq_ops = NULL;
return ERR_PTR(-ENOMEM);
diff --git a/block/blk-rq-qos.c b/block/blk-rq-qos.c
index 3f55b56..659ccb8 100644
--- a/block/blk-rq-qos.c
+++ b/block/blk-rq-qos.c
@@ -209,9 +209,10 @@
/**
* rq_qos_wait - throttle on a rqw if we need to
- * @private_data - caller provided specific data
- * @acquire_inflight_cb - inc the rqw->inflight counter if we can
- * @cleanup_cb - the callback to cleanup in case we race with a waker
+ * @rqw: rqw to throttle on
+ * @private_data: caller provided specific data
+ * @acquire_inflight_cb: inc the rqw->inflight counter if we can
+ * @cleanup_cb: the callback to cleanup in case we race with a waker
*
* This provides a uniform place for the rq_qos users to do their throttling.
* Since you can end up with a lot of things sleeping at once, this manages the
diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c
index a16a02c..75b5281c 100644
--- a/block/blk-sysfs.c
+++ b/block/blk-sysfs.c
@@ -840,6 +840,36 @@
kmem_cache_free(blk_requestq_cachep, q);
}
+/* Unconfigure the I/O scheduler and dissociate from the cgroup controller. */
+static void blk_exit_queue(struct request_queue *q)
+{
+ /*
+ * Since the I/O scheduler exit code may access cgroup information,
+ * perform I/O scheduler exit before disassociating from the block
+ * cgroup controller.
+ */
+ if (q->elevator) {
+ ioc_clear_queue(q);
+ elevator_exit(q, q->elevator);
+ q->elevator = NULL;
+ }
+
+ /*
+ * Remove all references to @q from the block cgroup controller before
+ * restoring @q->queue_lock to avoid that restoring this pointer causes
+ * e.g. blkcg_print_blkgs() to crash.
+ */
+ blkcg_exit_queue(q);
+
+ /*
+ * Since the cgroup code may dereference the @q->backing_dev_info
+ * pointer, only decrease its reference count after having removed the
+ * association with the block cgroup controller.
+ */
+ bdi_put(q->backing_dev_info);
+}
+
+
/**
* __blk_release_queue - release a request queue
* @work: pointer to the release_work member of the request queue to be released
@@ -860,23 +890,10 @@
blk_stat_remove_callback(q, q->poll_cb);
blk_stat_free_callback(q->poll_cb);
- if (!blk_queue_dead(q)) {
- /*
- * Last reference was dropped without having called
- * blk_cleanup_queue().
- */
- WARN_ONCE(blk_queue_init_done(q),
- "request queue %p has been registered but blk_cleanup_queue() has not been called for that queue\n",
- q);
- blk_exit_queue(q);
- }
-
- WARN(blk_queue_root_blkg(q),
- "request queue %p is being released but it has not yet been removed from the blkcg controller\n",
- q);
-
blk_free_queue_stats(q->stats);
+ blk_exit_queue(q);
+
blk_queue_free_zone_bitmaps(q);
if (queue_is_mq(q))
diff --git a/block/blk-throttle.c b/block/blk-throttle.c
index 1b97a73..9ea7c0e 100644
--- a/block/blk-throttle.c
+++ b/block/blk-throttle.c
@@ -1220,7 +1220,7 @@
struct throtl_grp *this_tg);
/**
* throtl_pending_timer_fn - timer function for service_queue->pending_timer
- * @arg: the throtl_service_queue being serviced
+ * @t: the pending_timer member of the throtl_service_queue being serviced
*
* This timer is armed when a child throtl_grp with active bio's become
* pending and queued on the service_queue's pending_tree and expires when
diff --git a/block/blk.h b/block/blk.h
index e27fd15..91b3581 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -50,7 +50,6 @@
int node, int cmd_size, gfp_t flags);
void blk_free_flush_queue(struct blk_flush_queue *q);
-void blk_exit_queue(struct request_queue *q);
void blk_rq_bio_prep(struct request_queue *q, struct request *rq,
struct bio *bio);
void blk_freeze_queue(struct request_queue *q);
diff --git a/block/bsg-lib.c b/block/bsg-lib.c
index b898a1c..785dd58 100644
--- a/block/bsg-lib.c
+++ b/block/bsg-lib.c
@@ -354,6 +354,7 @@
* @dev: device to attach bsg device to
* @name: device to give bsg device
* @job_fn: bsg job handler
+ * @timeout: timeout handler function pointer
* @dd_job_size: size of LLD data needed for each job
*/
struct request_queue *bsg_setup_queue(struct device *dev, const char *name,
diff --git a/block/genhd.c b/block/genhd.c
index ad68266..24654e1 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -532,8 +532,8 @@
}
}
-/**
- * We invalidate devt by assigning NULL pointer for devt in idr.
+/*
+ * We invalidate devt by assigning NULL pointer for devt in idr.
*/
void blk_invalidate_devt(dev_t devt)
{
diff --git a/block/partitions/ldm.c b/block/partitions/ldm.c
index 6db573f..fe5d970 100644
--- a/block/partitions/ldm.c
+++ b/block/partitions/ldm.c
@@ -19,7 +19,7 @@
#include "check.h"
#include "msdos.h"
-/**
+/*
* ldm_debug/info/error/crit - Output an error message
* @f: A printf format string containing the message
* @...: Variables to substitute into @f
diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index 102d795..f11b7dc 100644
--- a/drivers/block/loop.c
+++ b/drivers/block/loop.c
@@ -945,9 +945,20 @@
if (!file)
goto out;
+ /*
+ * If we don't hold exclusive handle for the device, upgrade to it
+ * here to avoid changing device under exclusive owner.
+ */
+ if (!(mode & FMODE_EXCL)) {
+ bdgrab(bdev);
+ error = blkdev_get(bdev, mode | FMODE_EXCL, loop_set_fd);
+ if (error)
+ goto out_putf;
+ }
+
error = mutex_lock_killable(&loop_ctl_mutex);
if (error)
- goto out_putf;
+ goto out_bdev;
error = -EBUSY;
if (lo->lo_state != Lo_unbound)
@@ -1012,10 +1023,15 @@
mutex_unlock(&loop_ctl_mutex);
if (partscan)
loop_reread_partitions(lo, bdev);
+ if (!(mode & FMODE_EXCL))
+ blkdev_put(bdev, mode | FMODE_EXCL);
return 0;
out_unlock:
mutex_unlock(&loop_ctl_mutex);
+out_bdev:
+ if (!(mode & FMODE_EXCL))
+ blkdev_put(bdev, mode | FMODE_EXCL);
out_putf:
fput(file);
out:
diff --git a/fs/block_dev.c b/fs/block_dev.c
index e6886c9..749f598 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -1406,20 +1406,27 @@
*/
int revalidate_disk(struct gendisk *disk)
{
- struct block_device *bdev;
int ret = 0;
if (disk->fops->revalidate_disk)
ret = disk->fops->revalidate_disk(disk);
- bdev = bdget_disk(disk, 0);
- if (!bdev)
- return ret;
- mutex_lock(&bdev->bd_mutex);
- check_disk_size_change(disk, bdev, ret == 0);
- bdev->bd_invalidated = 0;
- mutex_unlock(&bdev->bd_mutex);
- bdput(bdev);
+ /*
+ * Hidden disks don't have associated bdev so there's no point in
+ * revalidating it.
+ */
+ if (!(disk->flags & GENHD_FL_HIDDEN)) {
+ struct block_device *bdev = bdget_disk(disk, 0);
+
+ if (!bdev)
+ return ret;
+
+ mutex_lock(&bdev->bd_mutex);
+ check_disk_size_change(disk, bdev, ret == 0);
+ bdev->bd_invalidated = 0;
+ mutex_unlock(&bdev->bd_mutex);
+ bdput(bdev);
+ }
return ret;
}
EXPORT_SYMBOL(revalidate_disk);
diff --git a/fs/io_uring.c b/fs/io_uring.c
index 310f8d1..0fbb486 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -2616,7 +2616,7 @@
ret = io_copy_iov(ctx, &iov, arg, i);
if (ret)
- break;
+ goto err;
/*
* Don't impose further limits on the size and buffer
