summaryrefslogtreecommitdiff
path: root/block
diff options
context:
space:
mode:
Diffstat (limited to 'block')
-rw-r--r--block/bio.c49
-rw-r--r--block/blk-core.c11
-rw-r--r--block/blk-flush.c5
-rw-r--r--block/blk-iocost.c13
-rw-r--r--block/blk-map.c2
-rw-r--r--block/blk-merge.c23
-rw-r--r--block/blk-settings.c2
-rw-r--r--block/blk.h1
-rw-r--r--block/bsg-lib.c2
-rw-r--r--block/compat_ioctl.c16
-rw-r--r--block/partition-generic.c26
11 files changed, 125 insertions, 25 deletions
diff --git a/block/bio.c b/block/bio.c
index a5d75f6bf4c7..94d697217887 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -539,6 +539,55 @@ void zero_fill_bio_iter(struct bio *bio, struct bvec_iter start)
EXPORT_SYMBOL(zero_fill_bio_iter);
/**
+ * bio_truncate - truncate the bio to small size of @new_size
+ * @bio: the bio to be truncated
+ * @new_size: new size for truncating the bio
+ *
+ * Description:
+ * Truncate the bio to new size of @new_size. If bio_op(bio) is
+ * REQ_OP_READ, zero the truncated part. This function should only
+ * be used for handling corner cases, such as bio eod.
+ */
+void bio_truncate(struct bio *bio, unsigned new_size)
+{
+ struct bio_vec bv;
+ struct bvec_iter iter;
+ unsigned int done = 0;
+ bool truncated = false;
+
+ if (new_size >= bio->bi_iter.bi_size)
+ return;
+
+ if (bio_op(bio) != REQ_OP_READ)
+ goto exit;
+
+ bio_for_each_segment(bv, bio, iter) {
+ if (done + bv.bv_len > new_size) {
+ unsigned offset;
+
+ if (!truncated)
+ offset = new_size - done;
+ else
+ offset = 0;
+ zero_user(bv.bv_page, offset, bv.bv_len - offset);
+ truncated = true;
+ }
+ done += bv.bv_len;
+ }
+
+ exit:
+ /*
+ * Don't touch bvec table here and make it really immutable, since
+ * fs bio user has to retrieve all pages via bio_for_each_segment_all
+ * in its .end_bio() callback.
+ *
+ * It is enough to truncate bio by updating .bi_size since we can make
+ * correct bvec with the updated .bi_size for drivers.
+ */
+ bio->bi_iter.bi_size = new_size;
+}
+
+/**
* bio_put - release a reference to a bio
* @bio: bio to release reference to
*
diff --git a/block/blk-core.c b/block/blk-core.c
index e0a094fddee5..089e890ab208 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -885,11 +885,14 @@ generic_make_request_checks(struct bio *bio)
}
/*
- * For a REQ_NOWAIT based request, return -EOPNOTSUPP
- * if queue is not a request based queue.
+ * Non-mq queues do not honor REQ_NOWAIT, so complete a bio
+ * with BLK_STS_AGAIN status in order to catch -EAGAIN and
+ * to give a chance to the caller to repeat request gracefully.
*/
- if ((bio->bi_opf & REQ_NOWAIT) && !queue_is_mq(q))
- goto not_supported;
+ if ((bio->bi_opf & REQ_NOWAIT) && !queue_is_mq(q)) {
+ status = BLK_STS_AGAIN;
+ goto end_io;
+ }
if (should_fail_bio(bio))
goto end_io;
diff --git a/block/blk-flush.c b/block/blk-flush.c
index 1777346baf06..3f977c517960 100644
--- a/block/blk-flush.c
+++ b/block/blk-flush.c
@@ -69,6 +69,7 @@
#include <linux/blkdev.h>
#include <linux/gfp.h>
#include <linux/blk-mq.h>
+#include <linux/lockdep.h>
#include "blk.h"
#include "blk-mq.h"
@@ -505,6 +506,9 @@ struct blk_flush_queue *blk_alloc_flush_queue(struct request_queue *q,
INIT_LIST_HEAD(&fq->flush_queue[1]);
INIT_LIST_HEAD(&fq->flush_data_in_flight);
+ lockdep_register_key(&fq->key);
+ lockdep_set_class(&fq->mq_flush_lock, &fq->key);
+
return fq;
fail_rq:
@@ -519,6 +523,7 @@ void blk_free_flush_queue(struct blk_flush_queue *fq)
if (!fq)
return;
+ lockdep_unregister_key(&fq->key);
kfree(fq->flush_rq);
kfree(fq);
}
diff --git a/block/blk-iocost.c b/block/blk-iocost.c
index e01267f99183..27ca68621137 100644
--- a/block/blk-iocost.c
+++ b/block/blk-iocost.c
@@ -1212,7 +1212,7 @@ static enum hrtimer_restart iocg_waitq_timer_fn(struct hrtimer *timer)
return HRTIMER_NORESTART;
}
-static void iocg_kick_delay(struct ioc_gq *iocg, struct ioc_now *now, u64 cost)
+static bool iocg_kick_delay(struct ioc_gq *iocg, struct ioc_now *now, u64 cost)
{
struct ioc *ioc = iocg->ioc;
struct blkcg_gq *blkg = iocg_to_blkg(iocg);
@@ -1229,11 +1229,11 @@ static void iocg_kick_delay(struct ioc_gq *iocg, struct ioc_now *now, u64 cost)
/* clear or maintain depending on the overage */
if (time_before_eq64(vtime, now->vnow)) {
blkcg_clear_delay(blkg);
- return;
+ return false;
}
if (!atomic_read(&blkg->use_delay) &&
time_before_eq64(vtime, now->vnow + vmargin))
- return;
+ return false;
/* use delay */
if (cost) {
@@ -1250,10 +1250,11 @@ static void iocg_kick_delay(struct ioc_gq *iocg, struct ioc_now *now, u64 cost)
oexpires = ktime_to_ns(hrtimer_get_softexpires(&iocg->delay_timer));
if (hrtimer_is_queued(&iocg->delay_timer) &&
abs(oexpires - expires) <= margin_ns / 4)
- return;
+ return true;
hrtimer_start_range_ns(&iocg->delay_timer, ns_to_ktime(expires),
margin_ns / 4, HRTIMER_MODE_ABS);
+ return true;
}
static enum hrtimer_restart iocg_delay_timer_fn(struct hrtimer *timer)
@@ -1739,7 +1740,9 @@ static void ioc_rqos_throttle(struct rq_qos *rqos, struct bio *bio)
*/
if (bio_issue_as_root_blkg(bio) || fatal_signal_pending(current)) {
atomic64_add(abs_cost, &iocg->abs_vdebt);
- iocg_kick_delay(iocg, &now, cost);
+ if (iocg_kick_delay(iocg, &now, cost))
+ blkcg_schedule_throttle(rqos->q,
+ (bio->bi_opf & REQ_SWAP) == REQ_SWAP);
return;
}
diff --git a/block/blk-map.c b/block/blk-map.c
index 3a62e471d81b..b0790268ed9d 100644
--- a/block/blk-map.c
+++ b/block/blk-map.c
@@ -151,7 +151,7 @@ int blk_rq_map_user_iov(struct request_queue *q, struct request *rq,
return 0;
unmap_rq:
- __blk_rq_unmap_user(bio);
+ blk_rq_unmap_user(bio);
fail:
rq->bio = NULL;
return ret;
diff --git a/block/blk-merge.c b/block/blk-merge.c
index d783bdc4559b..1534ed736363 100644
--- a/block/blk-merge.c
+++ b/block/blk-merge.c
@@ -157,17 +157,20 @@ static inline unsigned get_max_io_size(struct request_queue *q,
return sectors & (lbs - 1);
}
-static unsigned get_max_segment_size(const struct request_queue *q,
- unsigned offset)
+static inline unsigned get_max_segment_size(const struct request_queue *q,
+ struct page *start_page,
+ unsigned long offset)
{
unsigned long mask = queue_segment_boundary(q);
- /* default segment boundary mask means no boundary limit */
- if (mask == BLK_SEG_BOUNDARY_MASK)
- return queue_max_segment_size(q);
+ offset = mask & (page_to_phys(start_page) + offset);
- return min_t(unsigned long, mask - (mask & offset) + 1,
- queue_max_segment_size(q));
+ /*
+ * overflow may be triggered in case of zero page physical address
+ * on 32bit arch, use queue's max segment size when that happens.
+ */
+ return min_not_zero(mask - offset + 1,
+ (unsigned long)queue_max_segment_size(q));
}
/**
@@ -201,7 +204,8 @@ static bool bvec_split_segs(const struct request_queue *q,
unsigned seg_size = 0;
while (len && *nsegs < max_segs) {
- seg_size = get_max_segment_size(q, bv->bv_offset + total_len);
+ seg_size = get_max_segment_size(q, bv->bv_page,
+ bv->bv_offset + total_len);
seg_size = min(seg_size, len);
(*nsegs)++;
@@ -419,7 +423,8 @@ static unsigned blk_bvec_map_sg(struct request_queue *q,
while (nbytes > 0) {
unsigned offset = bvec->bv_offset + total;
- unsigned len = min(get_max_segment_size(q, offset), nbytes);
+ unsigned len = min(get_max_segment_size(q, bvec->bv_page,
+ offset), nbytes);
struct page *page = bvec->bv_page;
/*
diff --git a/block/blk-settings.c b/block/blk-settings.c
index 5f6dcc7a47bd..c8eda2e7b91e 100644
--- a/block/blk-settings.c
+++ b/block/blk-settings.c
@@ -328,7 +328,7 @@ EXPORT_SYMBOL(blk_queue_max_segment_size);
* storage device can address. The default of 512 covers most
* hardware.
**/
-void blk_queue_logical_block_size(struct request_queue *q, unsigned short size)
+void blk_queue_logical_block_size(struct request_queue *q, unsigned int size)
{
q->limits.logical_block_size = size;
diff --git a/block/blk.h b/block/blk.h
index 6842f28c033e..0b8884353f6b 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -30,6 +30,7 @@ struct blk_flush_queue {
* at the same time
*/
struct request *orig_rq;
+ struct lock_class_key key;
spinlock_t mq_flush_lock;
};
diff --git a/block/bsg-lib.c b/block/bsg-lib.c
index 347dda16c2f4..6cbb7926534c 100644
--- a/block/bsg-lib.c
+++ b/block/bsg-lib.c
@@ -266,7 +266,7 @@ static blk_status_t bsg_queue_rq(struct blk_mq_hw_ctx *hctx,
struct request *req = bd->rq;
struct bsg_set *bset =
container_of(q->tag_set, struct bsg_set, tag_set);
- int sts = BLK_STS_IOERR;
+ blk_status_t sts = BLK_STS_IOERR;
int ret;
blk_mq_start_request(req);
diff --git a/block/compat_ioctl.c b/block/compat_ioctl.c
index 6ca015f92766..3ed7a0f144a9 100644
--- a/block/compat_ioctl.c
+++ b/block/compat_ioctl.c
@@ -6,6 +6,7 @@
#include <linux/compat.h>
#include <linux/elevator.h>
#include <linux/hdreg.h>
+#include <linux/pr.h>
#include <linux/slab.h>
#include <linux/syscalls.h>
#include <linux/types.h>
@@ -354,6 +355,13 @@ long compat_blkdev_ioctl(struct file *file, unsigned cmd, unsigned long arg)
* but we call blkdev_ioctl, which gets the lock for us
*/
case BLKRRPART:
+ case BLKREPORTZONE:
+ case BLKRESETZONE:
+ case BLKOPENZONE:
+ case BLKCLOSEZONE:
+ case BLKFINISHZONE:
+ case BLKGETZONESZ:
+ case BLKGETNRZONES:
return blkdev_ioctl(bdev, mode, cmd,
(unsigned long)compat_ptr(arg));
case BLKBSZSET_32:
@@ -401,6 +409,14 @@ long compat_blkdev_ioctl(struct file *file, unsigned cmd, unsigned long arg)
case BLKTRACETEARDOWN: /* compatible */
ret = blk_trace_ioctl(bdev, cmd, compat_ptr(arg));
return ret;
+ case IOC_PR_REGISTER:
+ case IOC_PR_RESERVE:
+ case IOC_PR_RELEASE:
+ case IOC_PR_PREEMPT:
+ case IOC_PR_PREEMPT_ABORT:
+ case IOC_PR_CLEAR:
+ return blkdev_ioctl(bdev, mode, cmd,
+ (unsigned long)compat_ptr(arg));
default:
if (disk->fops->compat_ioctl)
ret = disk->fops->compat_ioctl(bdev, mode, cmd, arg);
diff --git a/block/partition-generic.c b/block/partition-generic.c
index 1d20c9cf213f..564fae77711d 100644
--- a/block/partition-generic.c
+++ b/block/partition-generic.c
@@ -321,6 +321,24 @@ struct hd_struct *add_partition(struct gendisk *disk, int partno,
const char *dname;
int err;
+ /*
+ * Partitions are not supported on zoned block devices that are used as
+ * such.
+ */
+ switch (disk->queue->limits.zoned) {
+ case BLK_ZONED_HM:
+ pr_warn("%s: partitions not supported on host managed zoned block device\n",
+ disk->disk_name);
+ return ERR_PTR(-ENXIO);
+ case BLK_ZONED_HA:
+ pr_info("%s: disabling host aware zoned block device support due to partitions\n",
+ disk->disk_name);
+ disk->queue->limits.zoned = BLK_ZONED_NONE;
+ break;
+ case BLK_ZONED_NONE:
+ break;
+ }
+
err = disk_expand_part_tbl(disk, partno);
if (err)
return ERR_PTR(err);
@@ -501,7 +519,7 @@ static bool blk_add_partition(struct gendisk *disk, struct block_device *bdev,
part = add_partition(disk, p, from, size, state->parts[p].flags,
&state->parts[p].info);
- if (IS_ERR(part)) {
+ if (IS_ERR(part) && PTR_ERR(part) != -ENXIO) {
printk(KERN_ERR " %s: p%d could not be added: %ld\n",
disk->disk_name, p, -PTR_ERR(part));
return true;
@@ -540,10 +558,10 @@ int blk_add_partitions(struct gendisk *disk, struct block_device *bdev)
}
/*
- * Partitions are not supported on zoned block devices.
+ * Partitions are not supported on host managed zoned block devices.
*/
- if (bdev_is_zoned(bdev)) {
- pr_warn("%s: ignoring partition table on zoned block device\n",
+ if (disk->queue->limits.zoned == BLK_ZONED_HM) {
+ pr_warn("%s: ignoring partition table on host managed zoned block device\n",
disk->disk_name);
ret = 0;
goto out_free_state;