summaryrefslogtreecommitdiff
path: root/drivers/block
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/block')
-rw-r--r--drivers/block/loop.c73
-rw-r--r--drivers/block/loop.h1
-rw-r--r--drivers/block/mtip32xx/mtip32xx.c2
-rw-r--r--drivers/block/rbd.c2
-rw-r--r--drivers/block/virtio_blk.c20
-rw-r--r--drivers/block/xen-blkfront.c65
6 files changed, 85 insertions, 78 deletions
diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index 01cbbfc4e9e2..19fe19eaa50e 100644
--- a/drivers/block/loop.c
+++ b/drivers/block/loop.c
@@ -79,6 +79,7 @@
#include <linux/ioprio.h>
#include <linux/blk-cgroup.h>
#include <linux/sched/mm.h>
+#include <linux/statfs.h>
#include "loop.h"
@@ -774,8 +775,13 @@ static void loop_config_discard(struct loop_device *lo)
granularity = 0;
} else {
+ struct kstatfs sbuf;
+
max_discard_sectors = UINT_MAX >> 9;
- granularity = inode->i_sb->s_blocksize;
+ if (!vfs_statfs(&file->f_path, &sbuf))
+ granularity = sbuf.f_bsize;
+ else
+ max_discard_sectors = 0;
}
if (max_discard_sectors) {
@@ -1082,7 +1088,7 @@ out_putf:
return error;
}
-static void __loop_clr_fd(struct loop_device *lo)
+static void __loop_clr_fd(struct loop_device *lo, bool release)
{
struct file *filp;
gfp_t gfp = lo->old_gfp_mask;
@@ -1144,6 +1150,8 @@ static void __loop_clr_fd(struct loop_device *lo)
/* let user-space know about this change */
kobject_uevent(&disk_to_dev(lo->lo_disk)->kobj, KOBJ_CHANGE);
mapping_set_gfp_mask(filp->f_mapping, gfp);
+ /* This is safe: open() is still holding a reference. */
+ module_put(THIS_MODULE);
blk_mq_unfreeze_queue(lo->lo_queue);
disk_force_media_change(lo->lo_disk, DISK_EVENT_MEDIA_CHANGE);
@@ -1151,52 +1159,44 @@ static void __loop_clr_fd(struct loop_device *lo)
if (lo->lo_flags & LO_FLAGS_PARTSCAN) {
int err;
- mutex_lock(&lo->lo_disk->open_mutex);
+ /*
+ * open_mutex has been held already in release path, so don't
+ * acquire it if this function is called in such case.
+ *
+ * If the reread partition isn't from release path, lo_refcnt
+ * must be at least one and it can only become zero when the
+ * current holder is released.
+ */
+ if (!release)
+ mutex_lock(&lo->lo_disk->open_mutex);
err = bdev_disk_changed(lo->lo_disk, false);
- mutex_unlock(&lo->lo_disk->open_mutex);
+ if (!release)
+ mutex_unlock(&lo->lo_disk->open_mutex);
if (err)
pr_warn("%s: partition scan of loop%d failed (rc=%d)\n",
__func__, lo->lo_number, err);
/* Device is gone, no point in returning error */
}
+ /*
+ * lo->lo_state is set to Lo_unbound here after above partscan has
+ * finished. There cannot be anybody else entering __loop_clr_fd() as
+ * Lo_rundown state protects us from all the other places trying to
+ * change the 'lo' device.
+ */
lo->lo_flags = 0;
if (!part_shift)
lo->lo_disk->flags |= GENHD_FL_NO_PART;
-
- fput(filp);
-}
-
-static void loop_rundown_completed(struct loop_device *lo)
-{
mutex_lock(&lo->lo_mutex);
lo->lo_state = Lo_unbound;
mutex_unlock(&lo->lo_mutex);
- module_put(THIS_MODULE);
-}
-
-static void loop_rundown_workfn(struct work_struct *work)
-{
- struct loop_device *lo = container_of(work, struct loop_device,
- rundown_work);
- struct block_device *bdev = lo->lo_device;
- struct gendisk *disk = lo->lo_disk;
-
- __loop_clr_fd(lo);
- kobject_put(&bdev->bd_device.kobj);
- module_put(disk->fops->owner);
- loop_rundown_completed(lo);
-}
-
-static void loop_schedule_rundown(struct loop_device *lo)
-{
- struct block_device *bdev = lo->lo_device;
- struct gendisk *disk = lo->lo_disk;
- __module_get(disk->fops->owner);
- kobject_get(&bdev->bd_device.kobj);
- INIT_WORK(&lo->rundown_work, loop_rundown_workfn);
- queue_work(system_long_wq, &lo->rundown_work);
+ /*
+ * Need not hold lo_mutex to fput backing file. Calling fput holding
+ * lo_mutex triggers a circular lock dependency possibility warning as
+ * fput can take open_mutex which is usually taken before lo_mutex.
+ */
+ fput(filp);
}
static int loop_clr_fd(struct loop_device *lo)
@@ -1228,8 +1228,7 @@ static int loop_clr_fd(struct loop_device *lo)
lo->lo_state = Lo_rundown;
mutex_unlock(&lo->lo_mutex);
- __loop_clr_fd(lo);
- loop_rundown_completed(lo);
+ __loop_clr_fd(lo, false);
return 0;
}
@@ -1754,7 +1753,7 @@ static void lo_release(struct gendisk *disk, fmode_t mode)
* In autoclear mode, stop the loop thread
* and remove configuration after last close.
*/
- loop_schedule_rundown(lo);
+ __loop_clr_fd(lo, true);
return;
} else if (lo->lo_state == Lo_bound) {
/*
diff --git a/drivers/block/loop.h b/drivers/block/loop.h
index 918a7a2dc025..082d4b6bfc6a 100644
--- a/drivers/block/loop.h
+++ b/drivers/block/loop.h
@@ -56,7 +56,6 @@ struct loop_device {
struct gendisk *lo_disk;
struct mutex lo_mutex;
bool idr_visible;
- struct work_struct rundown_work;
};
struct loop_cmd {
diff --git a/drivers/block/mtip32xx/mtip32xx.c b/drivers/block/mtip32xx/mtip32xx.c
index 2d43ab5b5cc0..4fbaf0b4958b 100644
--- a/drivers/block/mtip32xx/mtip32xx.c
+++ b/drivers/block/mtip32xx/mtip32xx.c
@@ -4109,7 +4109,7 @@ static void mtip_pci_remove(struct pci_dev *pdev)
"Completion workers still active!\n");
}
- blk_set_queue_dying(dd->queue);
+ blk_mark_disk_dead(dd->disk);
set_bit(MTIP_DDF_REMOVE_PENDING_BIT, &dd->dd_flag);
/* Clean up the block layer. */
diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c
index 4203cdab8abf..b844432bad20 100644
--- a/drivers/block/rbd.c
+++ b/drivers/block/rbd.c
@@ -7185,7 +7185,7 @@ static ssize_t do_rbd_remove(struct bus_type *bus,
* IO to complete/fail.
*/
blk_mq_freeze_queue(rbd_dev->disk->queue);
- blk_set_queue_dying(rbd_dev->disk->queue);
+ blk_mark_disk_dead(rbd_dev->disk);
}
del_gendisk(rbd_dev->disk);
diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c
index 5c636ca7f1a7..35399a9eae0e 100644
--- a/drivers/block/virtio_blk.c
+++ b/drivers/block/virtio_blk.c
@@ -69,9 +69,6 @@ struct virtio_blk {
/* Process context for config space updates */
struct work_struct config_work;
- /* What host tells us, plus 2 for header & tailer. */
- unsigned int sg_elems;
-
/* Ida index - used to track minor number allocations. */
int index;
@@ -315,8 +312,6 @@ static blk_status_t virtio_queue_rq(struct blk_mq_hw_ctx *hctx,
blk_status_t status;
int err;
- BUG_ON(req->nr_phys_segments + 2 > vblk->sg_elems);
-
status = virtblk_setup_cmd(vblk->vdev, req, vbr);
if (unlikely(status))
return status;
@@ -747,8 +742,6 @@ static int virtblk_probe(struct virtio_device *vdev)
/* Prevent integer overflows and honor max vq size */
sg_elems = min_t(u32, sg_elems, VIRTIO_BLK_MAX_SG_ELEMS - 2);
- /* We need extra sg elements at head and tail. */
- sg_elems += 2;
vdev->priv = vblk = kmalloc(sizeof(*vblk), GFP_KERNEL);
if (!vblk) {
err = -ENOMEM;
@@ -758,7 +751,6 @@ static int virtblk_probe(struct virtio_device *vdev)
mutex_init(&vblk->vdev_mutex);
vblk->vdev = vdev;
- vblk->sg_elems = sg_elems;
INIT_WORK(&vblk->config_work, virtblk_config_changed_work);
@@ -815,7 +807,7 @@ static int virtblk_probe(struct virtio_device *vdev)
set_disk_ro(vblk->disk, 1);
/* We can handle whatever the host told us to handle. */
- blk_queue_max_segments(q, vblk->sg_elems-2);
+ blk_queue_max_segments(q, sg_elems);
/* No real sector limit. */
blk_queue_max_hw_sectors(q, -1U);
@@ -887,9 +879,15 @@ static int virtblk_probe(struct virtio_device *vdev)
virtio_cread(vdev, struct virtio_blk_config, max_discard_seg,
&v);
+
+ /*
+ * max_discard_seg == 0 is out of spec but we always
+ * handled it.
+ */
+ if (!v)
+ v = sg_elems;
blk_queue_max_discard_segments(q,
- min_not_zero(v,
- MAX_DISCARD_SEGMENTS));
+ min(v, MAX_DISCARD_SEGMENTS));
blk_queue_flag_set(QUEUE_FLAG_DISCARD, q);
}
diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c
index ccd0dd0c6b83..03b5fb341e58 100644
--- a/drivers/block/xen-blkfront.c
+++ b/drivers/block/xen-blkfront.c
@@ -1288,7 +1288,8 @@ free_shadow:
rinfo->ring_ref[i] = GRANT_INVALID_REF;
}
}
- free_pages((unsigned long)rinfo->ring.sring, get_order(info->nr_ring_pages * XEN_PAGE_SIZE));
+ free_pages_exact(rinfo->ring.sring,
+ info->nr_ring_pages * XEN_PAGE_SIZE);
rinfo->ring.sring = NULL;
if (rinfo->irq)
@@ -1372,9 +1373,15 @@ static int blkif_get_final_status(enum blk_req_status s1,
return BLKIF_RSP_OKAY;
}
-static bool blkif_completion(unsigned long *id,
- struct blkfront_ring_info *rinfo,
- struct blkif_response *bret)
+/*
+ * Return values:
+ * 1 response processed.
+ * 0 missing further responses.
+ * -1 error while processing.
+ */
+static int blkif_completion(unsigned long *id,
+ struct blkfront_ring_info *rinfo,
+ struct blkif_response *bret)
{
int i = 0;
struct scatterlist *sg;
@@ -1397,7 +1404,7 @@ static bool blkif_completion(unsigned long *id,
/* Wait the second response if not yet here. */
if (s2->status < REQ_DONE)
- return false;
+ return 0;
bret->status = blkif_get_final_status(s->status,
s2->status);
@@ -1448,42 +1455,43 @@ static bool blkif_completion(unsigned long *id,
}
/* Add the persistent grant into the list of free grants */
for (i = 0; i < num_grant; i++) {
- if (gnttab_query_foreign_access(s->grants_used[i]->gref)) {
+ if (!gnttab_try_end_foreign_access(s->grants_used[i]->gref)) {
/*
* If the grant is still mapped by the backend (the
* backend has chosen to make this grant persistent)
* we add it at the head of the list, so it will be
* reused first.
*/
- if (!info->feature_persistent)
- pr_alert_ratelimited("backed has not unmapped grant: %u\n",
- s->grants_used[i]->gref);
+ if (!info->feature_persistent) {
+ pr_alert("backed has not unmapped grant: %u\n",
+ s->grants_used[i]->gref);
+ return -1;
+ }
list_add(&s->grants_used[i]->node, &rinfo->grants);
rinfo->persistent_gnts_c++;
} else {
/*
- * If the grant is not mapped by the backend we end the
- * foreign access and add it to the tail of the list,
- * so it will not be picked again unless we run out of
- * persistent grants.
+ * If the grant is not mapped by the backend we add it
+ * to the tail of the list, so it will not be picked
+ * again unless we run out of persistent grants.
*/
- gnttab_end_foreign_access(s->grants_used[i]->gref, 0, 0UL);
s->grants_used[i]->gref = GRANT_INVALID_REF;
list_add_tail(&s->grants_used[i]->node, &rinfo->grants);
}
}
if (s->req.operation == BLKIF_OP_INDIRECT) {
for (i = 0; i < INDIRECT_GREFS(num_grant); i++) {
- if (gnttab_query_foreign_access(s->indirect_grants[i]->gref)) {
- if (!info->feature_persistent)
- pr_alert_ratelimited("backed has not unmapped grant: %u\n",
- s->indirect_grants[i]->gref);
+ if (!gnttab_try_end_foreign_access(s->indirect_grants[i]->gref)) {
+ if (!info->feature_persistent) {
+ pr_alert("backed has not unmapped grant: %u\n",
+ s->indirect_grants[i]->gref);
+ return -1;
+ }
list_add(&s->indirect_grants[i]->node, &rinfo->grants);
rinfo->persistent_gnts_c++;
} else {
struct page *indirect_page;
- gnttab_end_foreign_access(s->indirect_grants[i]->gref, 0, 0UL);
/*
* Add the used indirect page back to the list of
* available pages for indirect grefs.
@@ -1498,7 +1506,7 @@ static bool blkif_completion(unsigned long *id,
}
}
- return true;
+ return 1;
}
static irqreturn_t blkif_interrupt(int irq, void *dev_id)
@@ -1564,12 +1572,17 @@ static irqreturn_t blkif_interrupt(int irq, void *dev_id)
}
if (bret.operation != BLKIF_OP_DISCARD) {
+ int ret;
+
/*
* We may need to wait for an extra response if the
* I/O request is split in 2
*/
- if (!blkif_completion(&id, rinfo, &bret))
+ ret = blkif_completion(&id, rinfo, &bret);
+ if (!ret)
continue;
+ if (unlikely(ret < 0))
+ goto err;
}
if (add_id_to_freelist(rinfo, id)) {
@@ -1676,8 +1689,7 @@ static int setup_blkring(struct xenbus_device *dev,
for (i = 0; i < info->nr_ring_pages; i++)
rinfo->ring_ref[i] = GRANT_INVALID_REF;
- sring = (struct blkif_sring *)__get_free_pages(GFP_NOIO | __GFP_HIGH,
- get_order(ring_size));
+ sring = alloc_pages_exact(ring_size, GFP_NOIO);
if (!sring) {
xenbus_dev_fatal(dev, -ENOMEM, "allocating shared ring");
return -ENOMEM;
@@ -1687,7 +1699,7 @@ static int setup_blkring(struct xenbus_device *dev,
err = xenbus_grant_ring(dev, rinfo->ring.sring, info->nr_ring_pages, gref);
if (err < 0) {
- free_pages((unsigned long)sring, get_order(ring_size));
+ free_pages_exact(sring, ring_size);
rinfo->ring.sring = NULL;
goto fail;
}
@@ -2126,7 +2138,7 @@ static void blkfront_closing(struct blkfront_info *info)
/* No more blkif_request(). */
blk_mq_stop_hw_queues(info->rq);
- blk_set_queue_dying(info->rq);
+ blk_mark_disk_dead(info->gd);
set_capacity(info->gd, 0);
for_each_rinfo(info, rinfo, i) {
@@ -2532,11 +2544,10 @@ static void purge_persistent_grants(struct blkfront_info *info)
list_for_each_entry_safe(gnt_list_entry, tmp, &rinfo->grants,
node) {
if (gnt_list_entry->gref == GRANT_INVALID_REF ||
- gnttab_query_foreign_access(gnt_list_entry->gref))
+ !gnttab_try_end_foreign_access(gnt_list_entry->gref))
continue;
list_del(&gnt_list_entry->node);
- gnttab_end_foreign_access(gnt_list_entry->gref, 0, 0UL);
rinfo->persistent_gnts_c--;
gnt_list_entry->gref = GRANT_INVALID_REF;
list_add_tail(&gnt_list_entry->node, &rinfo->grants);
generated by cgit v1.2.3 (git 2.39.0) at 2025-01-13 14:46:31 +0300