Merge tag 'nvme-5.15-2021-10-14' of git://git.infradead.org/nvme into block-5.15
Pull NVMe fixes from Christoph:
"nvme fixes for Linux 5.15:
- fix the abort command id (Keith Busch)
- nvme: fix per-namespace chardev deletion (Adam Manzanares)"
* tag 'nvme-5.15-2021-10-14' of git://git.infradead.org/nvme:
nvme: fix per-namespace chardev deletion
nvme-pci: Fix abort command id
diff --git a/block/bdev.c b/block/bdev.c
index cf2780c..485a258 100644
--- a/block/bdev.c
+++ b/block/bdev.c
@@ -490,7 +490,6 @@
bdev = I_BDEV(inode);
mutex_init(&bdev->bd_fsfreeze_mutex);
spin_lock_init(&bdev->bd_size_lock);
- bdev->bd_disk = disk;
bdev->bd_partno = partno;
bdev->bd_inode = inode;
bdev->bd_stats = alloc_percpu(struct disk_stats);
@@ -498,6 +497,7 @@
iput(inode);
return NULL;
}
+ bdev->bd_disk = disk;
return bdev;
}
diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c
index dd13c2b..480e1a1 100644
--- a/block/bfq-iosched.c
+++ b/block/bfq-iosched.c
@@ -2662,15 +2662,6 @@
* are likely to increase the throughput.
*/
bfqq->new_bfqq = new_bfqq;
- /*
- * The above assignment schedules the following redirections:
- * each time some I/O for bfqq arrives, the process that
- * generated that I/O is disassociated from bfqq and
- * associated with new_bfqq. Here we increases new_bfqq->ref
- * in advance, adding the number of processes that are
- * expected to be associated with new_bfqq as they happen to
- * issue I/O.
- */
new_bfqq->ref += process_refs;
return new_bfqq;
}
@@ -2733,10 +2724,6 @@
{
struct bfq_queue *in_service_bfqq, *new_bfqq;
- /* if a merge has already been setup, then proceed with that first */
- if (bfqq->new_bfqq)
- return bfqq->new_bfqq;
-
/*
* Check delayed stable merge for rotational or non-queueing
* devs. For this branch to be executed, bfqq must not be
@@ -2838,6 +2825,9 @@
if (bfq_too_late_for_merging(bfqq))
return NULL;
+ if (bfqq->new_bfqq)
+ return bfqq->new_bfqq;
+
if (!io_struct || unlikely(bfqq == &bfqd->oom_bfqq))
return NULL;
diff --git a/block/bio.c b/block/bio.c
index 5df3dd2..a6fb6a0 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -1466,7 +1466,7 @@
if (!bio_integrity_endio(bio))
return;
- if (bio->bi_bdev)
+ if (bio->bi_bdev && bio_flagged(bio, BIO_TRACKED))
rq_qos_done_bio(bio->bi_bdev->bd_disk->queue, bio);
if (bio->bi_bdev && bio_flagged(bio, BIO_TRACE_COMPLETION)) {
diff --git a/block/blk-mq-debugfs.c b/block/blk-mq-debugfs.c
index 4b66d27..3b38d15 100644
--- a/block/blk-mq-debugfs.c
+++ b/block/blk-mq-debugfs.c
@@ -129,6 +129,7 @@
QUEUE_FLAG_NAME(PCI_P2PDMA),
QUEUE_FLAG_NAME(ZONE_RESETALL),
QUEUE_FLAG_NAME(RQ_ALLOC_TIME),
+ QUEUE_FLAG_NAME(HCTX_ACTIVE),
QUEUE_FLAG_NAME(NOWAIT),
};
#undef QUEUE_FLAG_NAME
diff --git a/block/fops.c b/block/fops.c
index ffce6f6..1e970c2 100644
--- a/block/fops.c
+++ b/block/fops.c
@@ -14,6 +14,7 @@
#include <linux/task_io_accounting_ops.h>
#include <linux/falloc.h>
#include <linux/suspend.h>
+#include <linux/fs.h>
#include "blk.h"
static struct inode *bdev_file_inode(struct file *file)
@@ -553,7 +554,8 @@
static long blkdev_fallocate(struct file *file, int mode, loff_t start,
loff_t len)
{
- struct block_device *bdev = I_BDEV(bdev_file_inode(file));
+ struct inode *inode = bdev_file_inode(file);
+ struct block_device *bdev = I_BDEV(inode);
loff_t end = start + len - 1;
loff_t isize;
int error;
@@ -580,10 +582,12 @@
if ((start | len) & (bdev_logical_block_size(bdev) - 1))
return -EINVAL;
+ filemap_invalidate_lock(inode->i_mapping);
+
/* Invalidate the page cache, including dirty pages. */
error = truncate_bdev_range(bdev, file->f_mode, start, end);
if (error)
- return error;
+ goto fail;
switch (mode) {
case FALLOC_FL_ZERO_RANGE:
@@ -600,17 +604,12 @@
GFP_KERNEL, 0);
break;
default:
- return -EOPNOTSUPP;
+ error = -EOPNOTSUPP;
}
- if (error)
- return error;
- /*
- * Invalidate the page cache again; if someone wandered in and dirtied
- * a page, we just discard it - userspace has no way of knowing whether
- * the write happened before or after discard completing...
- */
- return truncate_bdev_range(bdev, file->f_mode, start, end);
+ fail:
+ filemap_invalidate_unlock(inode->i_mapping);
+ return error;
}
const struct file_operations def_blk_fops = {
diff --git a/block/genhd.c b/block/genhd.c
index 7b6e5e1..496e845 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -1268,6 +1268,7 @@
out_destroy_part_tbl:
xa_destroy(&disk->part_tbl);
+ disk->part0->bd_disk = NULL;
iput(disk->part0->bd_inode);
out_free_bdi:
bdi_put(disk->bdi);
diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c
index 5170a63..1183f78 100644
--- a/drivers/block/nbd.c
+++ b/drivers/block/nbd.c
@@ -97,13 +97,18 @@
atomic_t recv_threads;
wait_queue_head_t recv_wq;
- loff_t blksize;
+ unsigned int blksize_bits;
loff_t bytesize;
#if IS_ENABLED(CONFIG_DEBUG_FS)
struct dentry *dbg_dir;
#endif
};
+static inline unsigned int nbd_blksize(struct nbd_config *config)
+{
+ return 1u << config->blksize_bits;
+}
+
struct nbd_device {
struct blk_mq_tag_set tag_set;
@@ -146,7 +151,7 @@
#define NBD_MAGIC 0x68797548
-#define NBD_DEF_BLKSIZE 1024
+#define NBD_DEF_BLKSIZE_BITS 10
static unsigned int nbds_max = 16;
static int max_part = 16;
@@ -317,12 +322,12 @@
loff_t blksize)
{
if (!blksize)
- blksize = NBD_DEF_BLKSIZE;
+ blksize = 1u << NBD_DEF_BLKSIZE_BITS;
if (blksize < 512 || blksize > PAGE_SIZE || !is_power_of_2(blksize))
return -EINVAL;
nbd->config->bytesize = bytesize;
- nbd->config->blksize = blksize;
+ nbd->config->blksize_bits = __ffs(blksize);
if (!nbd->task_recv)
return 0;
@@ -1337,7 +1342,7 @@
args->index = i;
queue_work(nbd->recv_workq, &args->work);
}
- return nbd_set_size(nbd, config->bytesize, config->blksize);
+ return nbd_set_size(nbd, config->bytesize, nbd_blksize(config));
}
static int nbd_start_device_ioctl(struct nbd_device *nbd, struct block_device *bdev)
@@ -1406,11 +1411,11 @@
case NBD_SET_BLKSIZE:
return nbd_set_size(nbd, config->bytesize, arg);
case NBD_SET_SIZE:
- return nbd_set_size(nbd, arg, config->blksize);
+ return nbd_set_size(nbd, arg, nbd_blksize(config));
case NBD_SET_SIZE_BLOCKS:
- if (check_mul_overflow((loff_t)arg, config->blksize, &bytesize))
+ if (check_shl_overflow(arg, config->blksize_bits, &bytesize))
return -EINVAL;
- return nbd_set_size(nbd, bytesize, config->blksize);
+ return nbd_set_size(nbd, bytesize, nbd_blksize(config));
case NBD_SET_TIMEOUT:
nbd_set_cmd_timeout(nbd, arg);
return 0;
@@ -1476,7 +1481,7 @@
atomic_set(&config->recv_threads, 0);
init_waitqueue_head(&config->recv_wq);
init_waitqueue_head(&config->conn_wait);
- config->blksize = NBD_DEF_BLKSIZE;
+ config->blksize_bits = NBD_DEF_BLKSIZE_BITS;
atomic_set(&config->live_connections, 0);
try_module_get(THIS_MODULE);
return config;
@@ -1604,7 +1609,7 @@
debugfs_create_file("tasks", 0444, dir, nbd, &nbd_dbg_tasks_fops);
debugfs_create_u64("size_bytes", 0444, dir, &config->bytesize);
debugfs_create_u32("timeout", 0444, dir, &nbd->tag_set.timeout);
- debugfs_create_u64("blocksize", 0444, dir, &config->blksize);
+ debugfs_create_u32("blocksize_bits", 0444, dir, &config->blksize_bits);
debugfs_create_file("flags", 0444, dir, nbd, &nbd_dbg_flags_fops);
return 0;
@@ -1826,7 +1831,7 @@
static int nbd_genl_size_set(struct genl_info *info, struct nbd_device *nbd)
{
struct nbd_config *config = nbd->config;
- u64 bsize = config->blksize;
+ u64 bsize = nbd_blksize(config);
u64 bytes = config->bytesize;
if (info->attrs[NBD_ATTR_SIZE_BYTES])
@@ -1835,7 +1840,7 @@
if (info->attrs[NBD_ATTR_BLOCK_SIZE_BYTES])
bsize = nla_get_u64(info->attrs[NBD_ATTR_BLOCK_SIZE_BYTES]);
- if (bytes != config->bytesize || bsize != config->blksize)
+ if (bytes != config->bytesize || bsize != nbd_blksize(config))
return nbd_set_size(nbd, bytes, bsize);
return 0;
}
diff --git a/drivers/block/rnbd/rnbd-clt-sysfs.c b/drivers/block/rnbd/rnbd-clt-sysfs.c
index 4b93fd8..44e45af 100644
--- a/drivers/block/rnbd/rnbd-clt-sysfs.c
+++ b/drivers/block/rnbd/rnbd-clt-sysfs.c
@@ -71,8 +71,10 @@
int opt_mask = 0;
int token;
int ret = -EINVAL;
- int i, dest_port, nr_poll_queues;
+ int nr_poll_queues = 0;
+ int dest_port = 0;
int p_cnt = 0;
+ int i;
options = kstrdup(buf, GFP_KERNEL);
if (!options)
diff --git a/drivers/md/md.c b/drivers/md/md.c
index ae8fe54..6c0c3d0 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -5700,10 +5700,6 @@
disk->flags |= GENHD_FL_EXT_DEVT;
disk->events |= DISK_EVENT_MEDIA_CHANGE;
mddev->gendisk = disk;
- /* As soon as we call add_disk(), another thread could get
- * through to md_open, so make sure it doesn't get too far
- */
- mutex_lock(&mddev->open_mutex);
add_disk(disk);
error = kobject_add(&mddev->kobj, &disk_to_dev(disk)->kobj, "%s", "md");
@@ -5718,7 +5714,6 @@
if (mddev->kobj.sd &&
sysfs_create_group(&mddev->kobj, &md_bitmap_group))
pr_debug("pointless warning\n");
- mutex_unlock(&mddev->open_mutex);
abort:
mutex_unlock(&disks_mutex);
if (!error && mddev->kobj.sd) {
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 587385b..f8dd664 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -978,6 +978,7 @@
blk_status_t nvme_setup_cmd(struct nvme_ns *ns, struct request *req)
{
struct nvme_command *cmd = nvme_req(req)->cmd;
+ struct nvme_ctrl *ctrl = nvme_req(req)->ctrl;
blk_status_t ret = BLK_STS_OK;
if (!(req->rq_flags & RQF_DONTPREP)) {
@@ -1026,7 +1027,8 @@
return BLK_STS_IOERR;
}
- nvme_req(req)->genctr++;
+ if (!(ctrl->quirks & NVME_QUIRK_SKIP_CID_GEN))
+ nvme_req(req)->genctr++;
cmd->common.command_id = nvme_cid(req);
trace_nvme_setup_cmd(req, cmd);
return ret;
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index 9871c0c..ed79a6c 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -138,6 +138,12 @@
* 48 bits.
*/
NVME_QUIRK_DMA_ADDRESS_BITS_48 = (1 << 16),
+
+ /*
+ * The controller requires the command_id value be be limited, so skip
+ * encoding the generation sequence number.
+ */
+ NVME_QUIRK_SKIP_CID_GEN = (1 << 17),
};
/*
diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index 7fc992a..149ecf7 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -3369,7 +3369,8 @@
{ PCI_DEVICE(PCI_VENDOR_ID_APPLE, 0x2005),
.driver_data = NVME_QUIRK_SINGLE_VECTOR |
NVME_QUIRK_128_BYTES_SQES |
- NVME_QUIRK_SHARED_TAGS },
+ NVME_QUIRK_SHARED_TAGS |
+ NVME_QUIRK_SKIP_CID_GEN },
{ PCI_DEVICE_CLASS(PCI_CLASS_STORAGE_EXPRESS, 0xffffff) },
{ 0, }
diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c
index c221e4c..fa91f39 100644
--- a/kernel/trace/blktrace.c
+++ b/kernel/trace/blktrace.c
@@ -1605,6 +1605,14 @@
if (bt == NULL)
return -EINVAL;
+ if (bt->trace_state == Blktrace_running) {
+ bt->trace_state = Blktrace_stopped;
+ spin_lock_irq(&running_trace_lock);
+ list_del_init(&bt->running_list);
+ spin_unlock_irq(&running_trace_lock);
+ relay_flush(bt->rchan);
+ }
+
put_probe_ref();
synchronize_rcu();
blk_trace_free(bt);
