Commit 1e512b08 authored by Linus Torvalds's avatar Linus Torvalds
Browse files

Merge branch 'for-linus' of git://git.kernel.dk/linux-block 

Pull block fixes from Jens Axboe:
 "Mainly sending this off now for the writeback fixes, since they fix a
  real regression introduced with the cgroup writeback changes.  The
  NVMe fix could wait for next pull for this series, but it's simple
  enough that we might as well include it.

  This contains:

   - two cgroup writeback fixes from Tejun, fixing a user reported issue
     with luks crypt devices hanging when being closed.

   - NVMe error cleanup fix from Jon Derrick, fixing a case where we'd
     attempt to free an unregistered IRQ"

* 'for-linus' of git://git.kernel.dk/linux-block:
  NVMe: Fix irq freeing when queue_request_irq fails
  writeback: don't drain bdi_writeback_congested on bdi destruction
  writeback: don't embed root bdi_writeback_congested in bdi_writeback
parents 1c65ae63 758dd7fd

drivers/block/nvme-core.c

+7 −2
Original line number Diff line number Diff line
@@ -1474,6 +1474,7 @@ static struct nvme_queue *nvme_alloc_queue(struct nvme_dev *dev, int qid, 
	nvmeq->q_db = &dev->dbs[qid * 2 * dev->db_stride];

	nvmeq->q_depth = depth;

	nvmeq->qid = qid;

	nvmeq->cq_vector = -1;

	dev->queues[qid] = nvmeq;



	/* make sure queue descriptor is set before queue count, for kthread */
@@ -1726,8 +1727,10 @@ static int nvme_configure_admin_queue(struct nvme_dev *dev) 


	nvmeq->cq_vector = 0;

	result = queue_request_irq(dev, nvmeq, nvmeq->irqname);

	if (result)

	if (result) {

		nvmeq->cq_vector = -1;

		goto free_nvmeq;

	}



	return result;
@@ -2213,8 +2216,10 @@ static int nvme_setup_io_queues(struct nvme_dev *dev) 
	dev->max_qid = nr_io_queues;



	result = queue_request_irq(dev, adminq, adminq->irqname);

	if (result)

	if (result) {

		adminq->cq_vector = -1;

		goto free_queues;

	}



	/* Free previously allocated queues that are no longer usable */

	nvme_free_queues(dev, nr_io_queues + 1);

include/linux/backing-dev-defs.h

+3 −2
Original line number Diff line number Diff line
@@ -50,10 +50,10 @@ enum wb_stat_item { 
 */

struct bdi_writeback_congested {

	unsigned long state;		/* WB_[a]sync_congested flags */

	atomic_t refcnt;		/* nr of attached wb's and blkg */



#ifdef CONFIG_CGROUP_WRITEBACK

	struct backing_dev_info *bdi;	/* the associated bdi */

	atomic_t refcnt;		/* nr of attached wb's and blkg */

	int blkcg_id;			/* ID of the associated blkcg */

	struct rb_node rb_node;		/* on bdi->cgwb_congestion_tree */

#endif
@@ -150,11 +150,12 @@ struct backing_dev_info { 
	atomic_long_t tot_write_bandwidth;



	struct bdi_writeback wb;  /* the root writeback info for this bdi */

	struct bdi_writeback_congested wb_congested; /* its congested state */

#ifdef CONFIG_CGROUP_WRITEBACK

	struct radix_tree_root cgwb_tree; /* radix tree of active cgroup wbs */

	struct rb_root cgwb_congested_tree; /* their congested states */

	atomic_t usage_cnt; /* counts both cgwbs and cgwb_contested's */

#else

	struct bdi_writeback_congested *wb_congested;

#endif

	wait_queue_head_t wb_waitq;

include/linux/backing-dev.h

+5 −1
Original line number Diff line number Diff line
@@ -15,6 +15,7 @@ 
#include <linux/writeback.h>

#include <linux/blk-cgroup.h>

#include <linux/backing-dev-defs.h>

#include <linux/slab.h>



int __must_check bdi_init(struct backing_dev_info *bdi);

void bdi_destroy(struct backing_dev_info *bdi);
@@ -465,11 +466,14 @@ static inline bool inode_cgwb_enabled(struct inode *inode) 
static inline struct bdi_writeback_congested *

wb_congested_get_create(struct backing_dev_info *bdi, int blkcg_id, gfp_t gfp)

{

	return bdi->wb.congested;

	atomic_inc(&bdi->wb_congested->refcnt);

	return bdi->wb_congested;

}



static inline void wb_congested_put(struct bdi_writeback_congested *congested)

{

	if (atomic_dec_and_test(&congested->refcnt))

		kfree(congested);

}



static inline struct bdi_writeback *wb_find_current(struct backing_dev_info *bdi)

mm/backing-dev.c

+62 −47
Original line number Diff line number Diff line
@@ -287,7 +287,7 @@ void wb_wakeup_delayed(struct bdi_writeback *wb) 
#define INIT_BW		(100 << (20 - PAGE_SHIFT))



static int wb_init(struct bdi_writeback *wb, struct backing_dev_info *bdi,

		   gfp_t gfp)

		   int blkcg_id, gfp_t gfp)

{

	int i, err;
@@ -311,22 +311,30 @@ static int wb_init(struct bdi_writeback *wb, struct backing_dev_info *bdi, 
	INIT_LIST_HEAD(&wb->work_list);

	INIT_DELAYED_WORK(&wb->dwork, wb_workfn);



	wb->congested = wb_congested_get_create(bdi, blkcg_id, gfp);

	if (!wb->congested)

		return -ENOMEM;



	err = fprop_local_init_percpu(&wb->completions, gfp);

	if (err)

		return err;

		goto out_put_cong;



	for (i = 0; i < NR_WB_STAT_ITEMS; i++) {

		err = percpu_counter_init(&wb->stat[i], 0, gfp);

		if (err) {

		if (err)

			goto out_destroy_stat;

	}



	return 0;



out_destroy_stat:

	while (--i)

		percpu_counter_destroy(&wb->stat[i]);

	fprop_local_destroy_percpu(&wb->completions);

out_put_cong:

	wb_congested_put(wb->congested);

	return err;

}

	}



	return 0;

}



/*

 * Remove bdi from the global list and shutdown any threads we have running
@@ -361,6 +369,7 @@ static void wb_exit(struct bdi_writeback *wb) 
		percpu_counter_destroy(&wb->stat[i]);



	fprop_local_destroy_percpu(&wb->completions);

	wb_congested_put(wb->congested);

}



#ifdef CONFIG_CGROUP_WRITEBACK
@@ -392,9 +401,6 @@ wb_congested_get_create(struct backing_dev_info *bdi, int blkcg_id, gfp_t gfp) 
	struct bdi_writeback_congested *new_congested = NULL, *congested;

	struct rb_node **node, *parent;

	unsigned long flags;



	if (blkcg_id == 1)

		return &bdi->wb_congested;

retry:

	spin_lock_irqsave(&cgwb_lock, flags);
@@ -419,7 +425,6 @@ retry: 
		new_congested = NULL;

		rb_link_node(&congested->rb_node, parent, node);

		rb_insert_color(&congested->rb_node, &bdi->cgwb_congested_tree);

		atomic_inc(&bdi->usage_cnt);

		goto found;

	}
@@ -450,24 +455,23 @@ found: 
 */

void wb_congested_put(struct bdi_writeback_congested *congested)

{

	struct backing_dev_info *bdi = congested->bdi;

	unsigned long flags;



	if (congested->blkcg_id == 1)

		return;



	local_irq_save(flags);

	if (!atomic_dec_and_lock(&congested->refcnt, &cgwb_lock)) {

		local_irq_restore(flags);

		return;

	}



	rb_erase(&congested->rb_node, &congested->bdi->cgwb_congested_tree);

	/* bdi might already have been destroyed leaving @congested unlinked */

	if (congested->bdi) {

		rb_erase(&congested->rb_node,

			 &congested->bdi->cgwb_congested_tree);

		congested->bdi = NULL;

	}



	spin_unlock_irqrestore(&cgwb_lock, flags);

	kfree(congested);



	if (atomic_dec_and_test(&bdi->usage_cnt))

		wake_up_all(&cgwb_release_wait);

}



static void cgwb_release_workfn(struct work_struct *work)
@@ -480,7 +484,6 @@ static void cgwb_release_workfn(struct work_struct *work) 


	css_put(wb->memcg_css);

	css_put(wb->blkcg_css);

	wb_congested_put(wb->congested);



	fprop_local_destroy_percpu(&wb->memcg_completions);

	percpu_ref_exit(&wb->refcnt);
@@ -541,7 +544,7 @@ static int cgwb_create(struct backing_dev_info *bdi, 
	if (!wb)

		return -ENOMEM;



	ret = wb_init(wb, bdi, gfp);

	ret = wb_init(wb, bdi, blkcg_css->id, gfp);

	if (ret)

		goto err_free;
@@ -553,12 +556,6 @@ static int cgwb_create(struct backing_dev_info *bdi, 
	if (ret)

		goto err_ref_exit;



	wb->congested = wb_congested_get_create(bdi, blkcg_css->id, gfp);

	if (!wb->congested) {

		ret = -ENOMEM;

		goto err_fprop_exit;

	}



	wb->memcg_css = memcg_css;

	wb->blkcg_css = blkcg_css;

	INIT_WORK(&wb->release_work, cgwb_release_workfn);
@@ -588,12 +585,10 @@ static int cgwb_create(struct backing_dev_info *bdi, 
	if (ret) {

		if (ret == -EEXIST)

			ret = 0;

		goto err_put_congested;

		goto err_fprop_exit;

	}

	goto out_put;



err_put_congested:

	wb_congested_put(wb->congested);

err_fprop_exit:

	fprop_local_destroy_percpu(&wb->memcg_completions);

err_ref_exit:
@@ -662,26 +657,41 @@ struct bdi_writeback *wb_get_create(struct backing_dev_info *bdi, 
	return wb;

}



static void cgwb_bdi_init(struct backing_dev_info *bdi)

static int cgwb_bdi_init(struct backing_dev_info *bdi)

{

	bdi->wb.memcg_css = mem_cgroup_root_css;

	bdi->wb.blkcg_css = blkcg_root_css;

	bdi->wb_congested.blkcg_id = 1;

	int ret;



	INIT_RADIX_TREE(&bdi->cgwb_tree, GFP_ATOMIC);

	bdi->cgwb_congested_tree = RB_ROOT;

	atomic_set(&bdi->usage_cnt, 1);



	ret = wb_init(&bdi->wb, bdi, 1, GFP_KERNEL);

	if (!ret) {

		bdi->wb.memcg_css = mem_cgroup_root_css;

		bdi->wb.blkcg_css = blkcg_root_css;

	}

	return ret;

}



static void cgwb_bdi_destroy(struct backing_dev_info *bdi)

{

	struct radix_tree_iter iter;

	struct bdi_writeback_congested *congested, *congested_n;

	void **slot;



	WARN_ON(test_bit(WB_registered, &bdi->wb.state));



	spin_lock_irq(&cgwb_lock);



	radix_tree_for_each_slot(slot, &bdi->cgwb_tree, &iter, 0)

		cgwb_kill(*slot);



	rbtree_postorder_for_each_entry_safe(congested, congested_n,

					&bdi->cgwb_congested_tree, rb_node) {

		rb_erase(&congested->rb_node, &bdi->cgwb_congested_tree);

		congested->bdi = NULL;	/* mark @congested unlinked */

	}



	spin_unlock_irq(&cgwb_lock);



	/*
@@ -732,15 +742,28 @@ void wb_blkcg_offline(struct blkcg *blkcg) 


#else	/* CONFIG_CGROUP_WRITEBACK */



static void cgwb_bdi_init(struct backing_dev_info *bdi) { }

static int cgwb_bdi_init(struct backing_dev_info *bdi)

{

	int err;



	bdi->wb_congested = kzalloc(sizeof(*bdi->wb_congested), GFP_KERNEL);

	if (!bdi->wb_congested)

		return -ENOMEM;



	err = wb_init(&bdi->wb, bdi, 1, GFP_KERNEL);

	if (err) {

		kfree(bdi->wb_congested);

		return err;

	}

	return 0;

}



static void cgwb_bdi_destroy(struct backing_dev_info *bdi) { }



#endif	/* CONFIG_CGROUP_WRITEBACK */



int bdi_init(struct backing_dev_info *bdi)

{

	int err;



	bdi->dev = NULL;



	bdi->min_ratio = 0;
@@ -749,15 +772,7 @@ int bdi_init(struct backing_dev_info *bdi) 
	INIT_LIST_HEAD(&bdi->bdi_list);

	init_waitqueue_head(&bdi->wb_waitq);



	err = wb_init(&bdi->wb, bdi, GFP_KERNEL);

	if (err)

		return err;



	bdi->wb_congested.state = 0;

	bdi->wb.congested = &bdi->wb_congested;



	cgwb_bdi_init(bdi);

	return 0;

	return cgwb_bdi_init(bdi);

}

EXPORT_SYMBOL(bdi_init);

CRA Git | Maintained and supported by SUSTech CRA and CCSE