UbiquitousOS
/
OpenCloudOS-Kernel
mirror of https://gitee.com/OpenCloudOS/OpenCloudOS-Kernel.git
11
0
Fork 0
Code Issues Projects Releases Wiki Activity

Merge branch 'for-5.9/drivers' into for-5.9/block-merge 

* for-5.9/drivers: (38 commits)
  block: add max_active_zones to blk-sysfs
  block: add max_open_zones to blk-sysfs
  s390/dasd: Use struct_size() helper
  s390/dasd: fix inability to use DASD with DIAG driver
  md-cluster: fix wild pointer of unlock_all_bitmaps()
  md/raid5-cache: clear MD_SB_CHANGE_PENDING before flushing stripes
  md: fix deadlock causing by sysfs_notify
  md: improve io stats accounting
  md: raid0/linear: fix dereference before null check on pointer mddev
  rsxx: switch from 'pci_free_consistent()' to 'dma_free_coherent()'
  nvme: remove ns->disk checks
  nvme-pci: use standard block status symbolic names
  nvme-pci: use the consistent return type of nvme_pci_iod_alloc_size()
  nvme-pci: add a blank line after declarations
  nvme-pci: fix some comments issues
  nvme-pci: remove redundant segment validation
  nvme: document quirked Intel models
  nvme: expose reconnect_delay and ctrl_loss_tmo via sysfs
  nvme: support for zoned namespaces
  nvme: support for multiple Command Sets Supported and Effects log pages
  ...
This commit is contained in:
Jens Axboe 2020-07-20 15:38:27 -06:00
parent 9caaa66c91 659bf827ba
commit 4f43d64807
39 changed files with 1114 additions and 202 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

18
Documentation/ABI/testing/sysfs-block
View File

@ -273,6 +273,24 @@ Description:
device ("host-aware" or "host-managed" zone model). For regular
block devices, the value is always 0.
What: /sys/block/<disk>/queue/max_active_zones
Date: July 2020
Contact: Niklas Cassel <niklas.cassel@wdc.com>
Description:
For zoned block devices (zoned attribute indicating
"host-managed" or "host-aware"), the sum of zones belonging to
any of the zone states: EXPLICIT OPEN, IMPLICIT OPEN or CLOSED,
is limited by this value. If this value is 0, there is no limit.
What: /sys/block/<disk>/queue/max_open_zones
Date: July 2020
Contact: Niklas Cassel <niklas.cassel@wdc.com>
Description:
For zoned block devices (zoned attribute indicating
"host-managed" or "host-aware"), the sum of zones belonging to
any of the zone states: EXPLICIT OPEN or IMPLICIT OPEN,
is limited by this value. If this value is 0, there is no limit.
What: /sys/block/<disk>/queue/chunk_sectors
Date: September 2016
Contact: Hannes Reinecke <hare@suse.com>

14
Documentation/block/queue-sysfs.rst
View File

@ -117,6 +117,20 @@ Maximum number of elements in a DMA scatter/gather list with integrity
data that will be submitted by the block layer core to the associated
block driver.
max_active_zones (RO)
---------------------
For zoned block devices (zoned attribute indicating "host-managed" or
"host-aware"), the sum of zones belonging to any of the zone states:
EXPLICIT OPEN, IMPLICIT OPEN or CLOSED, is limited by this value.
If this value is 0, there is no limit.
max_open_zones (RO)
-------------------
For zoned block devices (zoned attribute indicating "host-managed" or
"host-aware"), the sum of zones belonging to any of the zone states:
EXPLICIT OPEN or IMPLICIT OPEN, is limited by this value.
If this value is 0, there is no limit.
max_sectors_kb (RW)
-------------------
This is the maximum number of kilobytes that the block layer will allow

5
block/Kconfig
View File

@ -86,9 +86,10 @@ config BLK_DEV_ZONED
select MQ_IOSCHED_DEADLINE
help
Block layer zoned block device support. This option enables
support for ZAC/ZBC host-managed and host-aware zoned block devices.
support for ZAC/ZBC/ZNS host-managed and host-aware zoned block
devices.
Say yes here if you have a ZAC or ZBC storage device.
Say yes here if you have a ZAC, ZBC, or ZNS storage device.
config BLK_DEV_THROTTLING
bool "Block layer bio throttling support"

27
block/blk-sysfs.c
View File

@ -306,6 +306,16 @@ static ssize_t queue_nr_zones_show(struct request_queue *q, char *page)
return queue_var_show(blk_queue_nr_zones(q), page);
}
static ssize_t queue_max_open_zones_show(struct request_queue *q, char *page)
{
return queue_var_show(queue_max_open_zones(q), page);
}
static ssize_t queue_max_active_zones_show(struct request_queue *q, char *page)
{
return queue_var_show(queue_max_active_zones(q), page);
}
static ssize_t queue_nomerges_show(struct request_queue *q, char *page)
{
return queue_var_show((blk_queue_nomerges(q) << 1) |
@ -668,6 +678,16 @@ static struct queue_sysfs_entry queue_nr_zones_entry = {
.show = queue_nr_zones_show,
};
static struct queue_sysfs_entry queue_max_open_zones_entry = {
.attr = {.name = "max_open_zones", .mode = 0444 },
.show = queue_max_open_zones_show,
};
static struct queue_sysfs_entry queue_max_active_zones_entry = {
.attr = {.name = "max_active_zones", .mode = 0444 },
.show = queue_max_active_zones_show,
};
static struct queue_sysfs_entry queue_nomerges_entry = {
.attr = {.name = "nomerges", .mode = 0644 },
.show = queue_nomerges_show,
@ -766,6 +786,8 @@ static struct attribute *queue_attrs[] = {
&queue_nonrot_entry.attr,
&queue_zoned_entry.attr,
&queue_nr_zones_entry.attr,
&queue_max_open_zones_entry.attr,
&queue_max_active_zones_entry.attr,
&queue_nomerges_entry.attr,
&queue_rq_affinity_entry.attr,
&queue_iostats_entry.attr,
@ -793,6 +815,11 @@ static umode_t queue_attr_visible(struct kobject *kobj, struct attribute *attr,
(!q->mq_ops || !q->mq_ops->timeout))
return 0;
if ((attr == &queue_max_open_zones_entry.attr ||
attr == &queue_max_active_zones_entry.attr) &&
!blk_queue_is_zoned(q))
return 0;
return attr->mode;
}

1
block/blk-zoned.c
View File

@ -312,6 +312,7 @@ int blkdev_report_zones_ioctl(struct block_device *bdev, fmode_t mode,
return ret;
rep.nr_zones = ret;
rep.flags = BLK_ZONE_REP_CAPACITY;
if (copy_to_user(argp, &rep, sizeof(struct blk_zone_report)))
return -EFAULT;
return 0;

1
drivers/block/null_blk.h
View File

@ -49,6 +49,7 @@ struct nullb_device {
unsigned long completion_nsec; /* time in ns to complete a request */
unsigned long cache_size; /* disk cache size in MB */
unsigned long zone_size; /* zone size in MB if device is zoned */
unsigned long zone_capacity; /* zone capacity in MB if device is zoned */
unsigned int zone_nr_conv; /* number of conventional zones */
unsigned int submit_queues; /* number of submission queues */
unsigned int home_node; /* home node for the device */

10
drivers/block/null_blk_main.c
View File

@ -200,6 +200,10 @@ static unsigned long g_zone_size = 256;
module_param_named(zone_size, g_zone_size, ulong, S_IRUGO);
MODULE_PARM_DESC(zone_size, "Zone size in MB when block device is zoned. Must be power-of-two: Default: 256");
static unsigned long g_zone_capacity;
module_param_named(zone_capacity, g_zone_capacity, ulong, 0444);
MODULE_PARM_DESC(zone_capacity, "Zone capacity in MB when block device is zoned. Can be less than or equal to zone size. Default: Zone size");
static unsigned int g_zone_nr_conv;
module_param_named(zone_nr_conv, g_zone_nr_conv, uint, 0444);
MODULE_PARM_DESC(zone_nr_conv, "Number of conventional zones when block device is zoned. Default: 0");
@ -341,6 +345,7 @@ NULLB_DEVICE_ATTR(mbps, uint, NULL);
NULLB_DEVICE_ATTR(cache_size, ulong, NULL);
NULLB_DEVICE_ATTR(zoned, bool, NULL);
NULLB_DEVICE_ATTR(zone_size, ulong, NULL);
NULLB_DEVICE_ATTR(zone_capacity, ulong, NULL);
NULLB_DEVICE_ATTR(zone_nr_conv, uint, NULL);
static ssize_t nullb_device_power_show(struct config_item *item, char *page)
@ -457,6 +462,7 @@ static struct configfs_attribute *nullb_device_attrs[] = {
&nullb_device_attr_badblocks,
&nullb_device_attr_zoned,
&nullb_device_attr_zone_size,
&nullb_device_attr_zone_capacity,
&nullb_device_attr_zone_nr_conv,
NULL,
};
@ -510,7 +516,8 @@ nullb_group_drop_item(struct config_group *group, struct config_item *item)
static ssize_t memb_group_features_show(struct config_item *item, char *page)
{
return snprintf(page, PAGE_SIZE, "memory_backed,discard,bandwidth,cache,badblocks,zoned,zone_size,zone_nr_conv\n");
return snprintf(page, PAGE_SIZE,
"memory_backed,discard,bandwidth,cache,badblocks,zoned,zone_size,zone_capacity,zone_nr_conv\n");
}
CONFIGFS_ATTR_RO(memb_group_, features);
@ -571,6 +578,7 @@ static struct nullb_device *null_alloc_dev(void)
dev->use_per_node_hctx = g_use_per_node_hctx;
dev->zoned = g_zoned;
dev->zone_size = g_zone_size;
dev->zone_capacity = g_zone_capacity;
dev->zone_nr_conv = g_zone_nr_conv;
return dev;
}

16
drivers/block/null_blk_zoned.c
View File

@ -28,6 +28,15 @@ int null_init_zoned_dev(struct nullb_device *dev, struct request_queue *q)
return -EINVAL;
}
if (!dev->zone_capacity)
dev->zone_capacity = dev->zone_size;
if (dev->zone_capacity > dev->zone_size) {
pr_err("null_blk: zone capacity (%lu MB) larger than zone size (%lu MB)\n",
dev->zone_capacity, dev->zone_size);
return -EINVAL;
}
dev->zone_size_sects = dev->zone_size << ZONE_SIZE_SHIFT;
dev->nr_zones = dev_size >>
(SECTOR_SHIFT + ilog2(dev->zone_size_sects));
@ -47,6 +56,7 @@ int null_init_zoned_dev(struct nullb_device *dev, struct request_queue *q)
zone->start = sector;
zone->len = dev->zone_size_sects;
zone->capacity = zone->len;
zone->wp = zone->start + zone->len;
zone->type = BLK_ZONE_TYPE_CONVENTIONAL;
zone->cond = BLK_ZONE_COND_NOT_WP;
@ -59,6 +69,7 @@ int null_init_zoned_dev(struct nullb_device *dev, struct request_queue *q)
zone->start = zone->wp = sector;
zone->len = dev->zone_size_sects;
zone->capacity = dev->zone_capacity << ZONE_SIZE_SHIFT;
zone->type = BLK_ZONE_TYPE_SEQWRITE_REQ;
zone->cond = BLK_ZONE_COND_EMPTY;
@ -185,6 +196,9 @@ static blk_status_t null_zone_write(struct nullb_cmd *cmd, sector_t sector,
return BLK_STS_IOERR;
}
if (zone->wp + nr_sectors > zone->start + zone->capacity)
return BLK_STS_IOERR;
if (zone->cond != BLK_ZONE_COND_EXP_OPEN)
zone->cond = BLK_ZONE_COND_IMP_OPEN;
@ -193,7 +207,7 @@ static blk_status_t null_zone_write(struct nullb_cmd *cmd, sector_t sector,
return ret;
zone->wp += nr_sectors;
if (zone->wp == zone->start + zone->len)
if (zone->wp == zone->start + zone->capacity)
zone->cond = BLK_ZONE_COND_FULL;
return BLK_STS_OK;
default:

30
drivers/block/rsxx/core.c
View File

@ -562,13 +562,15 @@ static int rsxx_eeh_frozen(struct pci_dev *dev)
for (i = 0; i < card->n_targets; i++) {
if (card->ctrl[i].status.buf)
pci_free_consistent(card->dev, STATUS_BUFFER_SIZE8,
card->ctrl[i].status.buf,
card->ctrl[i].status.dma_addr);
dma_free_coherent(&card->dev->dev,
STATUS_BUFFER_SIZE8,
card->ctrl[i].status.buf,
card->ctrl[i].status.dma_addr);
if (card->ctrl[i].cmd.buf)
pci_free_consistent(card->dev, COMMAND_BUFFER_SIZE8,
card->ctrl[i].cmd.buf,
card->ctrl[i].cmd.dma_addr);
dma_free_coherent(&card->dev->dev,
COMMAND_BUFFER_SIZE8,
card->ctrl[i].cmd.buf,
card->ctrl[i].cmd.dma_addr);
}
return 0;
@ -711,15 +713,15 @@ static pci_ers_result_t rsxx_slot_reset(struct pci_dev *dev)
failed_hw_buffers_init:
for (i = 0; i < card->n_targets; i++) {
if (card->ctrl[i].status.buf)
pci_free_consistent(card->dev,
STATUS_BUFFER_SIZE8,
card->ctrl[i].status.buf,
card->ctrl[i].status.dma_addr);
dma_free_coherent(&card->dev->dev,
STATUS_BUFFER_SIZE8,
card->ctrl[i].status.buf,
card->ctrl[i].status.dma_addr);
if (card->ctrl[i].cmd.buf)
pci_free_consistent(card->dev,
COMMAND_BUFFER_SIZE8,
card->ctrl[i].cmd.buf,
card->ctrl[i].cmd.dma_addr);
dma_free_coherent(&card->dev->dev,
COMMAND_BUFFER_SIZE8,
card->ctrl[i].cmd.buf,
card->ctrl[i].cmd.dma_addr);
}
failed_hw_setup:
rsxx_eeh_failure(dev);

2
drivers/md/md-bitmap.c
View File

@ -1631,7 +1631,7 @@ void md_bitmap_cond_end_sync(struct bitmap *bitmap, sector_t sector, bool force)
s += blocks;
}
bitmap->last_end_sync = jiffies;
sysfs_notify(&bitmap->mddev->kobj, NULL, "sync_completed");
sysfs_notify_dirent_safe(bitmap->mddev->sysfs_completed);
}
EXPORT_SYMBOL(md_bitmap_cond_end_sync);

1
drivers/md/md-cluster.c
View File

@ -1518,6 +1518,7 @@ static void unlock_all_bitmaps(struct mddev *mddev)
}
}
kfree(cinfo->other_bitmap_lockres);
cinfo->other_bitmap_lockres = NULL;
}
}

110
drivers/md/md.c
View File

@ -463,12 +463,38 @@ check_suspended:
}
EXPORT_SYMBOL(md_handle_request);
struct md_io {
struct mddev *mddev;
bio_end_io_t *orig_bi_end_io;
void *orig_bi_private;
unsigned long start_time;
};
static void md_end_io(struct bio *bio)
{
struct md_io *md_io = bio->bi_private;
struct mddev *mddev = md_io->mddev;
disk_end_io_acct(mddev->gendisk, bio_op(bio), md_io->start_time);
bio->bi_end_io = md_io->orig_bi_end_io;
bio->bi_private = md_io->orig_bi_private;
mempool_free(md_io, &mddev->md_io_pool);
if (bio->bi_end_io)
bio->bi_end_io(bio);
}
static blk_qc_t md_submit_bio(struct bio *bio)
{
const int rw = bio_data_dir(bio);
const int sgrp = op_stat_group(bio_op(bio));
struct mddev *mddev = bio->bi_disk->private_data;
unsigned int sectors;
if (mddev == NULL || mddev->pers == NULL) {
bio_io_error(bio);
return BLK_QC_T_NONE;
}
if (unlikely(test_bit(MD_BROKEN, &mddev->flags)) && (rw == WRITE)) {
bio_io_error(bio);
@ -477,10 +503,6 @@ static blk_qc_t md_submit_bio(struct bio *bio)
blk_queue_split(&bio);
if (mddev == NULL || mddev->pers == NULL) {
bio_io_error(bio);
return BLK_QC_T_NONE;
}
if (mddev->ro == 1 && unlikely(rw == WRITE)) {
if (bio_sectors(bio) != 0)
bio->bi_status = BLK_STS_IOERR;
@ -488,21 +510,27 @@ static blk_qc_t md_submit_bio(struct bio *bio)
return BLK_QC_T_NONE;
}
/*
* save the sectors now since our bio can
* go away inside make_request
*/
sectors = bio_sectors(bio);
if (bio->bi_end_io != md_end_io) {
struct md_io *md_io;
md_io = mempool_alloc(&mddev->md_io_pool, GFP_NOIO);
md_io->mddev = mddev;
md_io->orig_bi_end_io = bio->bi_end_io;
md_io->orig_bi_private = bio->bi_private;
bio->bi_end_io = md_end_io;
bio->bi_private = md_io;
md_io->start_time = disk_start_io_acct(mddev->gendisk,
bio_sectors(bio),
bio_op(bio));
}
/* bio could be mergeable after passing to underlayer */
bio->bi_opf &= ~REQ_NOMERGE;
md_handle_request(mddev, bio);
part_stat_lock();
part_stat_inc(&mddev->gendisk->part0, ios[sgrp]);
part_stat_add(&mddev->gendisk->part0, sectors[sgrp], sectors);
part_stat_unlock();
return BLK_QC_T_NONE;
}
@ -2424,6 +2452,10 @@ static int bind_rdev_to_array(struct md_rdev *rdev, struct mddev *mddev)
if (sysfs_create_link(&rdev->kobj, ko, "block"))
/* failure here is OK */;
rdev->sysfs_state = sysfs_get_dirent_safe(rdev->kobj.sd, "state");
rdev->sysfs_unack_badblocks =
sysfs_get_dirent_safe(rdev->kobj.sd, "unacknowledged_bad_blocks");
rdev->sysfs_badblocks =
sysfs_get_dirent_safe(rdev->kobj.sd, "bad_blocks");
list_add_rcu(&rdev->same_set, &mddev->disks);
bd_link_disk_holder(rdev->bdev, mddev->gendisk);
@ -2457,7 +2489,11 @@ static void unbind_rdev_from_array(struct md_rdev *rdev)
rdev->mddev = NULL;
sysfs_remove_link(&rdev->kobj, "block");
sysfs_put(rdev->sysfs_state);
sysfs_put(rdev->sysfs_unack_badblocks);
sysfs_put(rdev->sysfs_badblocks);
rdev->sysfs_state = NULL;
rdev->sysfs_unack_badblocks = NULL;
rdev->sysfs_badblocks = NULL;
rdev->badblocks.count = 0;
/* We need to delay this, otherwise we can deadlock when
* writing to 'remove' to "dev/state". We also need
@ -2802,7 +2838,7 @@ rewrite:
goto repeat;
wake_up(&mddev->sb_wait);
if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery))
sysfs_notify(&mddev->kobj, NULL, "sync_completed");
sysfs_notify_dirent_safe(mddev->sysfs_completed);
rdev_for_each(rdev, mddev) {
if (test_and_clear_bit(FaultRecorded, &rdev->flags))
@ -4055,7 +4091,7 @@ level_store(struct mddev *mddev, const char *buf, size_t len)
mddev_resume(mddev);
if (!mddev->thread)
md_update_sb(mddev, 1);
sysfs_notify(&mddev->kobj, NULL, "level");
sysfs_notify_dirent_safe(mddev->sysfs_level);
md_new_event(mddev);
rv = len;
out_unlock:
@ -4808,7 +4844,7 @@ action_store(struct mddev *mddev, const char *page, size_t len)
}
if (err)
return err;
sysfs_notify(&mddev->kobj, NULL, "degraded");
sysfs_notify_dirent_safe(mddev->sysfs_degraded);
} else {
if (cmd_match(page, "check"))
set_bit(MD_RECOVERY_CHECK, &mddev->recovery);
@ -5514,6 +5550,13 @@ static void md_free(struct kobject *ko)
if (mddev->sysfs_state)
sysfs_put(mddev->sysfs_state);
if (mddev->sysfs_completed)
sysfs_put(mddev->sysfs_completed);
if (mddev->sysfs_degraded)
sysfs_put(mddev->sysfs_degraded);
if (mddev->sysfs_level)
sysfs_put(mddev->sysfs_level);
if (mddev->gendisk)
del_gendisk(mddev->gendisk);
@ -5525,6 +5568,7 @@ static void md_free(struct kobject *ko)
bioset_exit(&mddev->bio_set);
bioset_exit(&mddev->sync_set);
mempool_exit(&mddev->md_io_pool);
kfree(mddev);
}
@ -5620,6 +5664,11 @@ static int md_alloc(dev_t dev, char *name)
*/
mddev->hold_active = UNTIL_STOP;
error = mempool_init_kmalloc_pool(&mddev->md_io_pool, BIO_POOL_SIZE,
sizeof(struct md_io));
if (error)
goto abort;
error = -ENOMEM;
mddev->queue = blk_alloc_queue(NUMA_NO_NODE);
if (!mddev->queue)
@ -5676,6 +5725,9 @@ static int md_alloc(dev_t dev, char *name)
if (!error && mddev->kobj.sd) {
kobject_uevent(&mddev->kobj, KOBJ_ADD);
mddev->sysfs_state = sysfs_get_dirent_safe(mddev->kobj.sd, "array_state");
mddev->sysfs_completed = sysfs_get_dirent_safe(mddev->kobj.sd, "sync_completed");
mddev->sysfs_degraded = sysfs_get_dirent_safe(mddev->kobj.sd, "degraded");
mddev->sysfs_level = sysfs_get_dirent_safe(mddev->kobj.sd, "level");
}
mddev_put(mddev);
return error;
@ -6028,7 +6080,7 @@ static int do_md_run(struct mddev *mddev)
kobject_uevent(&disk_to_dev(mddev->gendisk)->kobj, KOBJ_CHANGE);
sysfs_notify_dirent_safe(mddev->sysfs_state);
sysfs_notify_dirent_safe(mddev->sysfs_action);
sysfs_notify(&mddev->kobj, NULL, "degraded");
sysfs_notify_dirent_safe(mddev->sysfs_degraded);
out:
clear_bit(MD_NOT_READY, &mddev->flags);
return err;
@ -8742,7 +8794,7 @@ void md_do_sync(struct md_thread *thread)
} else
mddev->curr_resync = 3; /* no longer delayed */
mddev->curr_resync_completed = j;
sysfs_notify(&mddev->kobj, NULL, "sync_completed");
sysfs_notify_dirent_safe(mddev->sysfs_completed);
md_new_event(mddev);
update_time = jiffies;
@ -8770,7 +8822,7 @@ void md_do_sync(struct md_thread *thread)
mddev->recovery_cp = j;
update_time = jiffies;
set_bit(MD_SB_CHANGE_CLEAN, &mddev->sb_flags);
sysfs_notify(&mddev->kobj, NULL, "sync_completed");
sysfs_notify_dirent_safe(mddev->sysfs_completed);
}
while (j >= mddev->resync_max &&
@ -8877,7 +8929,7 @@ void md_do_sync(struct md_thread *thread)
!test_bit(MD_RECOVERY_INTR, &mddev->recovery) &&
mddev->curr_resync > 3) {
mddev->curr_resync_completed = mddev->curr_resync;
sysfs_notify(&mddev->kobj, NULL, "sync_completed");
sysfs_notify_dirent_safe(mddev->sysfs_completed);
}
mddev->pers->sync_request(mddev, max_sectors, &skipped);
@ -9007,7 +9059,7 @@ static int remove_and_add_spares(struct mddev *mddev,
}
if (removed && mddev->kobj.sd)
sysfs_notify(&mddev->kobj, NULL, "degraded");
sysfs_notify_dirent_safe(mddev->sysfs_degraded);
if (this && removed)
goto no_add;
@ -9290,8 +9342,7 @@ void md_reap_sync_thread(struct mddev *mddev)
/* success...*/
/* activate any spares */
if (mddev->pers->spare_active(mddev)) {
sysfs_notify(&mddev->kobj, NULL,
"degraded");
sysfs_notify_dirent_safe(mddev->sysfs_degraded);
set_bit(MD_SB_CHANGE_DEVS, &mddev->sb_flags);
}
}
@ -9381,8 +9432,7 @@ int rdev_set_badblocks(struct md_rdev *rdev, sector_t s, int sectors,
if (rv == 0) {
/* Make sure they get written out promptly */
if (test_bit(ExternalBbl, &rdev->flags))
sysfs_notify(&rdev->kobj, NULL,
"unacknowledged_bad_blocks");
sysfs_notify_dirent_safe(rdev->sysfs_unack_badblocks);
sysfs_notify_dirent_safe(rdev->sysfs_state);
set_mask_bits(&mddev->sb_flags, 0,
BIT(MD_SB_CHANGE_CLEAN) | BIT(MD_SB_CHANGE_PENDING));
@ -9403,7 +9453,7 @@ int rdev_clear_badblocks(struct md_rdev *rdev, sector_t s, int sectors,
s += rdev->data_offset;
rv = badblocks_clear(&rdev->badblocks, s, sectors);
if ((rv == 0) && test_bit(ExternalBbl, &rdev->flags))
sysfs_notify(&rdev->kobj, NULL, "bad_blocks");
sysfs_notify_dirent_safe(rdev->sysfs_badblocks);
return rv;
}
EXPORT_SYMBOL_GPL(rdev_clear_badblocks);
@ -9633,7 +9683,7 @@ static int read_rdev(struct mddev *mddev, struct md_rdev *rdev)
if (rdev->recovery_offset == MaxSector &&
!test_bit(In_sync, &rdev->flags) &&
mddev->pers->spare_active(mddev))
sysfs_notify(&mddev->kobj, NULL, "degraded");
sysfs_notify_dirent_safe(mddev->sysfs_degraded);
put_page(swapout);
return 0;

9
drivers/md/md.h
View File

@ -126,7 +126,10 @@ struct md_rdev {
struct kernfs_node *sysfs_state; /* handle for 'state'
* sysfs entry */
/* handle for 'unacknowledged_bad_blocks' sysfs dentry */
struct kernfs_node *sysfs_unack_badblocks;
/* handle for 'bad_blocks' sysfs dentry */
struct kernfs_node *sysfs_badblocks;
struct badblocks badblocks;
struct {
@ -420,6 +423,9 @@ struct mddev {
* file in sysfs.
*/
struct kernfs_node *sysfs_action; /* handle for 'sync_action' */
struct kernfs_node *sysfs_completed; /*handle for 'sync_completed' */
struct kernfs_node *sysfs_degraded; /*handle for 'degraded' */
struct kernfs_node *sysfs_level; /*handle for 'level' */
struct work_struct del_work; /* used for delayed sysfs removal */
@ -481,6 +487,7 @@ struct mddev {
struct bio_set sync_set; /* for sync operations like
* metadata and bitmap writes
*/
mempool_t md_io_pool;
/* Generic flush handling.
* The last to finish preflush schedules a worker to submit

2
drivers/md/raid10.c
View File

@ -4429,7 +4429,7 @@ static sector_t reshape_request(struct mddev *mddev, sector_t sector_nr,
sector_nr = conf->reshape_progress;
if (sector_nr) {
mddev->curr_resync_completed = sector_nr;
sysfs_notify(&mddev->kobj, NULL, "sync_completed");
sysfs_notify_dirent_safe(mddev->sysfs_completed);
*skipped = 1;
return sector_nr;
}

7
drivers/md/raid5-cache.c
View File

@ -2430,10 +2430,15 @@ static void r5c_recovery_flush_data_only_stripes(struct r5l_log *log,
struct mddev *mddev = log->rdev->mddev;
struct r5conf *conf = mddev->private;
struct stripe_head *sh, *next;
bool cleared_pending = false;
if (ctx->data_only_stripes == 0)
return;
if (test_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags)) {
cleared_pending = true;
clear_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags);
}
log->r5c_journal_mode = R5C_JOURNAL_MODE_WRITE_BACK;
list_for_each_entry_safe(sh, next, &ctx->cached_list, lru) {
@ -2448,6 +2453,8 @@ static void r5c_recovery_flush_data_only_stripes(struct r5l_log *log,
atomic_read(&conf->active_stripes) == 0);
log->r5c_journal_mode = R5C_JOURNAL_MODE_WRITE_THROUGH;
if (cleared_pending)
set_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags);
}
static int r5l_recovery_log(struct r5l_log *log)

6
drivers/md/raid5.c
View File

@ -5777,7 +5777,7 @@ static sector_t reshape_request(struct mddev *mddev, sector_t sector_nr, int *sk
sector_div(sector_nr, new_data_disks);
if (sector_nr) {
mddev->curr_resync_completed = sector_nr;
sysfs_notify(&mddev->kobj, NULL, "sync_completed");
sysfs_notify_dirent_safe(mddev->sysfs_completed);
*skipped = 1;
retn = sector_nr;
goto finish;
@ -5891,7 +5891,7 @@ static sector_t reshape_request(struct mddev *mddev, sector_t sector_nr, int *sk
conf->reshape_safe = mddev->reshape_position;
spin_unlock_irq(&conf->device_lock);
wake_up(&conf->wait_for_overlap);
sysfs_notify(&mddev->kobj, NULL, "sync_completed");
sysfs_notify_dirent_safe(mddev->sysfs_completed);
}
INIT_LIST_HEAD(&stripes);
@ -5998,7 +5998,7 @@ finish:
conf->reshape_safe = mddev->reshape_position;
spin_unlock_irq(&conf->device_lock);
wake_up(&conf->wait_for_overlap);
sysfs_notify(&mddev->kobj, NULL, "sync_completed");
sysfs_notify_dirent_safe(mddev->sysfs_completed);
}
ret:
return retn;

1
drivers/nvme/host/Makefile
View File

@ -13,6 +13,7 @@ nvme-core-y := core.o
nvme-core-$(CONFIG_TRACING) += trace.o
nvme-core-$(CONFIG_NVME_MULTIPATH) += multipath.o
nvme-core-$(CONFIG_NVM) += lightnvm.o
nvme-core-$(CONFIG_BLK_DEV_ZONED) += zns.o
nvme-core-$(CONFIG_FAULT_INJECTION_DEBUG_FS) += fault_inject.o
nvme-core-$(CONFIG_NVME_HWMON) += hwmon.o

301
drivers/nvme/host/core.c
View File

@ -89,7 +89,7 @@ static dev_t nvme_chr_devt;
static struct class *nvme_class;
static struct class *nvme_subsys_class;
static int nvme_revalidate_disk(struct gendisk *disk);
static int _nvme_revalidate_disk(struct gendisk *disk);
static void nvme_put_subsystem(struct nvme_subsystem *subsys);
static void nvme_remove_invalid_namespaces(struct nvme_ctrl *ctrl,
unsigned nsid);
@ -100,7 +100,7 @@ static void nvme_set_queue_dying(struct nvme_ns *ns)
* Revalidating a dead namespace sets capacity to 0. This will end
* buffered writers dirtying pages that can't be synced.
*/
if (!ns->disk || test_and_set_bit(NVME_NS_DEAD, &ns->flags))
if (test_and_set_bit(NVME_NS_DEAD, &ns->flags))
return;
blk_set_queue_dying(ns->queue);
/* Forcibly unquiesce queues to avoid blocking dispatch */
@ -287,6 +287,10 @@ void nvme_complete_rq(struct request *req)
nvme_retry_req(req);
return;
}
} else if (IS_ENABLED(CONFIG_BLK_DEV_ZONED) &&
req_op(req) == REQ_OP_ZONE_APPEND) {
req->__sector = nvme_lba_to_sect(req->q->queuedata,
le64_to_cpu(nvme_req(req)->result.u64));
}
nvme_trace_bio_complete(req, status);
@ -555,7 +559,7 @@ static int nvme_configure_directives(struct nvme_ctrl *ctrl)
goto out_disable_stream;
}
ctrl->nr_streams = min_t(unsigned, ctrl->nssa, BLK_MAX_WRITE_HINTS - 1);
ctrl->nr_streams = min_t(u16, ctrl->nssa, BLK_MAX_WRITE_HINTS - 1);
dev_info(ctrl->device, "Using %u streams\n", ctrl->nr_streams);
return 0;
@ -673,7 +677,8 @@ static inline blk_status_t nvme_setup_write_zeroes(struct nvme_ns *ns,
}
static inline blk_status_t nvme_setup_rw(struct nvme_ns *ns,
struct request *req, struct nvme_command *cmnd)
struct request *req, struct nvme_command *cmnd,
enum nvme_opcode op)
{
struct nvme_ctrl *ctrl = ns->ctrl;
u16 control = 0;
@ -687,7 +692,7 @@ static inline blk_status_t nvme_setup_rw(struct nvme_ns *ns,
if (req->cmd_flags & REQ_RAHEAD)
dsmgmt |= NVME_RW_DSM_FREQ_PREFETCH;
cmnd->rw.opcode = (rq_data_dir(req) ? nvme_cmd_write : nvme_cmd_read);
cmnd->rw.opcode = op;
cmnd->rw.nsid = cpu_to_le32(ns->head->ns_id);
cmnd->rw.slba = cpu_to_le64(nvme_sect_to_lba(ns, blk_rq_pos(req)));
cmnd->rw.length = cpu_to_le16((blk_rq_bytes(req) >> ns->lba_shift) - 1);
@ -716,6 +721,8 @@ static inline blk_status_t nvme_setup_rw(struct nvme_ns *ns,
case NVME_NS_DPS_PI_TYPE2:
control |= NVME_RW_PRINFO_PRCHK_GUARD |
NVME_RW_PRINFO_PRCHK_REF;
if (op == nvme_cmd_zone_append)
control |= NVME_RW_APPEND_PIREMAP;
cmnd->rw.reftag = cpu_to_le32(t10_pi_ref_tag(req));
break;
}
@ -756,6 +763,19 @@ blk_status_t nvme_setup_cmd(struct nvme_ns *ns, struct request *req,
case REQ_OP_FLUSH:
nvme_setup_flush(ns, cmd);
break;
case REQ_OP_ZONE_RESET_ALL:
case REQ_OP_ZONE_RESET:
ret = nvme_setup_zone_mgmt_send(ns, req, cmd, NVME_ZONE_RESET);
break;
case REQ_OP_ZONE_OPEN:
ret = nvme_setup_zone_mgmt_send(ns, req, cmd, NVME_ZONE_OPEN);
break;
case REQ_OP_ZONE_CLOSE:
ret = nvme_setup_zone_mgmt_send(ns, req, cmd, NVME_ZONE_CLOSE);
break;
case REQ_OP_ZONE_FINISH:
ret = nvme_setup_zone_mgmt_send(ns, req, cmd, NVME_ZONE_FINISH);
break;
case REQ_OP_WRITE_ZEROES:
ret = nvme_setup_write_zeroes(ns, req, cmd);
break;
@ -763,8 +783,13 @@ blk_status_t nvme_setup_cmd(struct nvme_ns *ns, struct request *req,
ret = nvme_setup_discard(ns, req, cmd);
break;
case REQ_OP_READ:
ret = nvme_setup_rw(ns, req, cmd, nvme_cmd_read);
break;
case REQ_OP_WRITE:
ret = nvme_setup_rw(ns, req, cmd);
ret = nvme_setup_rw(ns, req, cmd, nvme_cmd_write);
break;
case REQ_OP_ZONE_APPEND:
ret = nvme_setup_rw(ns, req, cmd, nvme_cmd_zone_append);
break;
default:
WARN_ON_ONCE(1);
@ -1056,8 +1081,13 @@ static int nvme_identify_ctrl(struct nvme_ctrl *dev, struct nvme_id_ctrl **id)
return error;
}
static bool nvme_multi_css(struct nvme_ctrl *ctrl)
{
return (ctrl->ctrl_config & NVME_CC_CSS_MASK) == NVME_CC_CSS_CSI;
}
static int nvme_process_ns_desc(struct nvme_ctrl *ctrl, struct nvme_ns_ids *ids,
struct nvme_ns_id_desc *cur)
struct nvme_ns_id_desc *cur, bool *csi_seen)
{
const char *warn_str = "ctrl returned bogus length:";
void *data = cur;
@ -1087,6 +1117,15 @@ static int nvme_process_ns_desc(struct nvme_ctrl *ctrl, struct nvme_ns_ids *ids,
}
uuid_copy(&ids->uuid, data + sizeof(*cur));
return NVME_NIDT_UUID_LEN;
case NVME_NIDT_CSI:
if (cur->nidl != NVME_NIDT_CSI_LEN) {
dev_warn(ctrl->device, "%s %d for NVME_NIDT_CSI\n",
warn_str, cur->nidl);
return -1;
}
memcpy(&ids->csi, data + sizeof(*cur), NVME_NIDT_CSI_LEN);
*csi_seen = true;
return NVME_NIDT_CSI_LEN;
default:
/* Skip unknown types */
return cur->nidl;
@ -1097,10 +1136,9 @@ static int nvme_identify_ns_descs(struct nvme_ctrl *ctrl, unsigned nsid,
struct nvme_ns_ids *ids)
{
struct nvme_command c = { };
int status;
bool csi_seen = false;
int status, pos, len;
void *data;
int pos;
int len;
c.identify.opcode = nvme_admin_identify;
c.identify.nsid = cpu_to_le32(nsid);
@ -1125,7 +1163,7 @@ static int nvme_identify_ns_descs(struct nvme_ctrl *ctrl, unsigned nsid,
* device just because of a temporal retry-able error (such
* as path of transport errors).
*/
if (status > 0 && (status & NVME_SC_DNR))
if (status > 0 && (status & NVME_SC_DNR) && !nvme_multi_css(ctrl))
status = 0;
goto free_data;
}
@ -1136,12 +1174,19 @@ static int nvme_identify_ns_descs(struct nvme_ctrl *ctrl, unsigned nsid,
if (cur->nidl == 0)
break;
len = nvme_process_ns_desc(ctrl, ids, cur);
len = nvme_process_ns_desc(ctrl, ids, cur, &csi_seen);
if (len < 0)
goto free_data;
break;
len += sizeof(*cur);
}
if (nvme_multi_css(ctrl) && !csi_seen) {
dev_warn(ctrl->device, "Command set not reported for nsid:%d\n",
nsid);
status = -EINVAL;
}
free_data:
kfree(data);
return status;
@ -1350,8 +1395,8 @@ static u32 nvme_passthru_start(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
u32 effects = 0;
if (ns) {
if (ctrl->effects)
effects = le32_to_cpu(ctrl->effects->iocs[opcode]);
if (ns->head->effects)
effects = le32_to_cpu(ns->head->effects->iocs[opcode]);
if (effects & ~(NVME_CMD_EFFECTS_CSUPP | NVME_CMD_EFFECTS_LBCC))
dev_warn(ctrl->device,
"IO command:%02x has unhandled effects:%08x\n",
@ -1378,14 +1423,23 @@ static u32 nvme_passthru_start(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
return effects;
}
static void nvme_update_formats(struct nvme_ctrl *ctrl)
static void nvme_update_formats(struct nvme_ctrl *ctrl, u32 *effects)
{
struct nvme_ns *ns;
down_read(&ctrl->namespaces_rwsem);
list_for_each_entry(ns, &ctrl->namespaces, list)
if (ns->disk && nvme_revalidate_disk(ns->disk))
if (_nvme_revalidate_disk(ns->disk))
nvme_set_queue_dying(ns);
else if (blk_queue_is_zoned(ns->disk->queue)) {
/*
* IO commands are required to fully revalidate a zoned
* device. Force the command effects to trigger rescan
* work so report zones can run in a context with
* unfrozen IO queues.
*/
*effects |= NVME_CMD_EFFECTS_NCC;
}
up_read(&ctrl->namespaces_rwsem);
}
@ -1397,7 +1451,7 @@ static void nvme_passthru_end(struct nvme_ctrl *ctrl, u32 effects)
* this command.
*/
if (effects & NVME_CMD_EFFECTS_LBCC)
nvme_update_formats(ctrl);
nvme_update_formats(ctrl, &effects);
if (effects & (NVME_CMD_EFFECTS_LBCC | NVME_CMD_EFFECTS_CSE_MASK)) {
nvme_unfreeze(ctrl);
nvme_mpath_unfreeze(ctrl->subsys);
@ -1512,7 +1566,7 @@ static int nvme_user_cmd64(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
* Issue ioctl requests on the first available path. Note that unlike normal
* block layer requests we will not retry failed request on another controller.
*/
static struct nvme_ns *nvme_get_ns_from_disk(struct gendisk *disk,
struct nvme_ns *nvme_get_ns_from_disk(struct gendisk *disk,
struct nvme_ns_head **head, int *srcu_idx)
{
#ifdef CONFIG_NVME_MULTIPATH
@ -1532,7 +1586,7 @@ static struct nvme_ns *nvme_get_ns_from_disk(struct gendisk *disk,
return disk->private_data;
}
static void nvme_put_ns_from_disk(struct nvme_ns_head *head, int idx)
void nvme_put_ns_from_disk(struct nvme_ns_head *head, int idx)
{
if (head)
srcu_read_unlock(&head->srcu, idx);
@ -1798,7 +1852,7 @@ static int nvme_report_ns_ids(struct nvme_ctrl *ctrl, unsigned int nsid,
memcpy(ids->eui64, id->eui64, sizeof(id->eui64));
if (ctrl->vs >= NVME_VS(1, 2, 0))
memcpy(ids->nguid, id->nguid, sizeof(id->nguid));
if (ctrl->vs >= NVME_VS(1, 3, 0))
if (ctrl->vs >= NVME_VS(1, 3, 0) || nvme_multi_css(ctrl))
return nvme_identify_ns_descs(ctrl, nsid, ids);
return 0;
}
@ -1814,7 +1868,8 @@ static bool nvme_ns_ids_equal(struct nvme_ns_ids *a, struct nvme_ns_ids *b)
{
return uuid_equal(&a->uuid, &b->uuid) &&
memcmp(&a->nguid, &b->nguid, sizeof(a->nguid)) == 0 &&
memcmp(&a->eui64, &b->eui64, sizeof(a->eui64)) == 0;
memcmp(&a->eui64, &b->eui64, sizeof(a->eui64)) == 0 &&
a->csi == b->csi;
}
static int nvme_setup_streams_ns(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
@ -1924,18 +1979,38 @@ static void nvme_update_disk_info(struct gendisk *disk,
static int __nvme_revalidate_disk(struct gendisk *disk, struct nvme_id_ns *id)
{
unsigned lbaf = id->flbas & NVME_NS_FLBAS_LBA_MASK;
struct nvme_ns *ns = disk->private_data;
struct nvme_ctrl *ctrl = ns->ctrl;
int ret;
u32 iob;
/*
* If identify namespace failed, use default 512 byte block size so
* block layer can use before failing read/write for 0 capacity.
*/
ns->lba_shift = id->lbaf[id->flbas & NVME_NS_FLBAS_LBA_MASK].ds;
ns->lba_shift = id->lbaf[lbaf].ds;
if (ns->lba_shift == 0)
ns->lba_shift = 9;
switch (ns->head->ids.csi) {
case NVME_CSI_NVM:
break;
case NVME_CSI_ZNS:
ret = nvme_update_zone_info(disk, ns, lbaf);
if (ret) {
dev_warn(ctrl->device,
"failed to add zoned namespace:%u ret:%d\n",
ns->head->ns_id, ret);
return ret;
}
break;
default:
dev_warn(ctrl->device, "unknown csi:%u ns:%u\n",
ns->head->ids.csi, ns->head->ns_id);
return -ENODEV;
}
if ((ctrl->quirks & NVME_QUIRK_STRIPE_SIZE) &&
is_power_of_2(ctrl->max_hw_sectors))
iob = ctrl->max_hw_sectors;
@ -1943,7 +2018,7 @@ static int __nvme_revalidate_disk(struct gendisk *disk, struct nvme_id_ns *id)
iob = nvme_lba_to_sect(ns, le16_to_cpu(id->noiob));
ns->features = 0;
ns->ms = le16_to_cpu(id->lbaf[id->flbas & NVME_NS_FLBAS_LBA_MASK].ms);
ns->ms = le16_to_cpu(id->lbaf[lbaf].ms);
/* the PI implementation requires metadata equal t10 pi tuple size */
if (ns->ms == sizeof(struct t10_pi_tuple))
ns->pi_type = id->dps & NVME_NS_DPS_PI_MASK;
@ -1986,7 +2061,7 @@ static int __nvme_revalidate_disk(struct gendisk *disk, struct nvme_id_ns *id)
return 0;
}
static int nvme_revalidate_disk(struct gendisk *disk)
static int _nvme_revalidate_disk(struct gendisk *disk)
{
struct nvme_ns *ns = disk->private_data;
struct nvme_ctrl *ctrl = ns->ctrl;
@ -2034,6 +2109,28 @@ out:
return ret;
}
static int nvme_revalidate_disk(struct gendisk *disk)
{
int ret;
ret = _nvme_revalidate_disk(disk);
if (ret)
return ret;
#ifdef CONFIG_BLK_DEV_ZONED
if (blk_queue_is_zoned(disk->queue)) {
struct nvme_ns *ns = disk->private_data;
struct nvme_ctrl *ctrl = ns->ctrl;
ret = blk_revalidate_disk_zones(disk, NULL);
if (!ret)
blk_queue_max_zone_append_sectors(disk->queue,
ctrl->max_zone_append);
}
#endif
return ret;
}
static char nvme_pr_type(enum pr_type type)
{
switch (type) {
@ -2164,6 +2261,7 @@ static const struct block_device_operations nvme_fops = {
.release = nvme_release,
.getgeo = nvme_getgeo,
.revalidate_disk= nvme_revalidate_disk,
.report_zones = nvme_report_zones,
.pr_ops = &nvme_pr_ops,
};
@ -2190,6 +2288,7 @@ const struct block_device_operations nvme_ns_head_ops = {
.ioctl = nvme_ioctl,
.compat_ioctl = nvme_compat_ioctl,
.getgeo = nvme_getgeo,
.report_zones = nvme_report_zones,
.pr_ops = &nvme_pr_ops,
};
#endif /* CONFIG_NVME_MULTIPATH */
@ -2271,7 +2370,10 @@ int nvme_enable_ctrl(struct nvme_ctrl *ctrl)
ctrl->page_size = 1 << page_shift;
ctrl->ctrl_config = NVME_CC_CSS_NVM;
if (NVME_CAP_CSS(ctrl->cap) & NVME_CAP_CSS_CSI)
ctrl->ctrl_config = NVME_CC_CSS_CSI;
else
ctrl->ctrl_config = NVME_CC_CSS_NVM;
ctrl->ctrl_config |= (page_shift - 12) << NVME_CC_MPS_SHIFT;
ctrl->ctrl_config |= NVME_CC_AMS_RR | NVME_CC_SHN_NONE;
ctrl->ctrl_config |= NVME_CC_IOSQES | NVME_CC_IOCQES;
@ -2819,7 +2921,7 @@ out_unlock:
return ret;
}
int nvme_get_log(struct nvme_ctrl *ctrl, u32 nsid, u8 log_page, u8 lsp,
int nvme_get_log(struct nvme_ctrl *ctrl, u32 nsid, u8 log_page, u8 lsp, u8 csi,
void *log, size_t size, u64 offset)
{
struct nvme_command c = { };
@ -2833,27 +2935,55 @@ int nvme_get_log(struct nvme_ctrl *ctrl, u32 nsid, u8 log_page, u8 lsp,
c.get_log_page.numdu = cpu_to_le16(dwlen >> 16);
c.get_log_page.lpol = cpu_to_le32(lower_32_bits(offset));
c.get_log_page.lpou = cpu_to_le32(upper_32_bits(offset));
c.get_log_page.csi = csi;
return nvme_submit_sync_cmd(ctrl->admin_q, &c, log, size);
}
static int nvme_get_effects_log(struct nvme_ctrl *ctrl)
static struct nvme_cel *nvme_find_cel(struct nvme_ctrl *ctrl, u8 csi)
{
struct nvme_cel *cel, *ret = NULL;
spin_lock(&ctrl->lock);
list_for_each_entry(cel, &ctrl->cels, entry) {
if (cel->csi == csi) {
ret = cel;
break;
}
}
spin_unlock(&ctrl->lock);
return ret;
}
static int nvme_get_effects_log(struct nvme_ctrl *ctrl, u8 csi,
struct nvme_effects_log **log)
{
struct nvme_cel *cel = nvme_find_cel(ctrl, csi);
int ret;
if (!ctrl->effects)
ctrl->effects = kzalloc(sizeof(*ctrl->effects), GFP_KERNEL);
if (cel)
goto out;
if (!ctrl->effects)
return 0;
cel = kzalloc(sizeof(*cel), GFP_KERNEL);
if (!cel)
return -ENOMEM;
ret = nvme_get_log(ctrl, NVME_NSID_ALL, NVME_LOG_CMD_EFFECTS, 0,
ctrl->effects, sizeof(*ctrl->effects), 0);
ret = nvme_get_log(ctrl, NVME_NSID_ALL, NVME_LOG_CMD_EFFECTS, 0, csi,
&cel->log, sizeof(cel->log), 0);
if (ret) {
kfree(ctrl->effects);
ctrl->effects = NULL;
kfree(cel);
return ret;
}
return ret;
cel->csi = csi;
spin_lock(&ctrl->lock);
list_add_tail(&cel->entry, &ctrl->cels);
spin_unlock(&ctrl->lock);
out:
*log = &cel->log;
return 0;
}
/*
@ -2874,7 +3004,7 @@ int nvme_init_identify(struct nvme_ctrl *ctrl)
return ret;
}
page_shift = NVME_CAP_MPSMIN(ctrl->cap) + 12;
ctrl->sqsize = min_t(int, NVME_CAP_MQES(ctrl->cap), ctrl->sqsize);
ctrl->sqsize = min_t(u16, NVME_CAP_MQES(ctrl->cap), ctrl->sqsize);
if (ctrl->vs >= NVME_VS(1, 1, 0))
ctrl->subsystem = NVME_CAP_NSSRC(ctrl->cap);
@ -2886,7 +3016,7 @@ int nvme_init_identify(struct nvme_ctrl *ctrl)
}
if (id->lpa & NVME_CTRL_LPA_CMD_EFFECTS_LOG) {
ret = nvme_get_effects_log(ctrl);
ret = nvme_get_effects_log(ctrl, NVME_CSI_NVM, &ctrl->effects);
if (ret < 0)
goto out_free;
}
@ -2948,7 +3078,7 @@ int nvme_init_identify(struct nvme_ctrl *ctrl)
if (id->rtd3e) {
/* us -> s */
u32 transition_time = le32_to_cpu(id->rtd3e) / 1000000;
u32 transition_time = le32_to_cpu(id->rtd3e) / USEC_PER_SEC;
ctrl->shutdown_timeout = clamp_t(unsigned int, transition_time,
shutdown_timeout, 60);
@ -3406,6 +3536,66 @@ static ssize_t nvme_sysfs_show_address(struct device *dev,
}
static DEVICE_ATTR(address, S_IRUGO, nvme_sysfs_show_address, NULL);
static ssize_t nvme_ctrl_loss_tmo_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
struct nvme_ctrl *ctrl = dev_get_drvdata(dev);
struct nvmf_ctrl_options *opts = ctrl->opts;
if (ctrl->opts->max_reconnects == -1)
return sprintf(buf, "off\n");
return sprintf(buf, "%d\n",
opts->max_reconnects * opts->reconnect_delay);
}
static ssize_t nvme_ctrl_loss_tmo_store(struct device *dev,
struct device_attribute *attr, const char *buf, size_t count)
{
struct nvme_ctrl *ctrl = dev_get_drvdata(dev);
struct nvmf_ctrl_options *opts = ctrl->opts;
int ctrl_loss_tmo, err;
err = kstrtoint(buf, 10, &ctrl_loss_tmo);
if (err)
return -EINVAL;
else if (ctrl_loss_tmo < 0)
opts->max_reconnects = -1;
else
opts->max_reconnects = DIV_ROUND_UP(ctrl_loss_tmo,
opts->reconnect_delay);
return count;
}
static DEVICE_ATTR(ctrl_loss_tmo, S_IRUGO | S_IWUSR,
nvme_ctrl_loss_tmo_show, nvme_ctrl_loss_tmo_store);
static ssize_t nvme_ctrl_reconnect_delay_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
struct nvme_ctrl *ctrl = dev_get_drvdata(dev);
if (ctrl->opts->reconnect_delay == -1)
return sprintf(buf, "off\n");
return sprintf(buf, "%d\n", ctrl->opts->reconnect_delay);
}
static ssize_t nvme_ctrl_reconnect_delay_store(struct device *dev,
struct device_attribute *attr, const char *buf, size_t count)
{
struct nvme_ctrl *ctrl = dev_get_drvdata(dev);
unsigned int v;
int err;
err = kstrtou32(buf, 10, &v);
if (err || v > UINT_MAX)
return -EINVAL;
ctrl->opts->reconnect_delay = v;
return count;
}
static DEVICE_ATTR(reconnect_delay, S_IRUGO | S_IWUSR,
nvme_ctrl_reconnect_delay_show, nvme_ctrl_reconnect_delay_store);
static struct attribute *nvme_dev_attrs[] = {
&dev_attr_reset_controller.attr,
&dev_attr_rescan_controller.attr,
@ -3423,6 +3613,8 @@ static struct attribute *nvme_dev_attrs[] = {
&dev_attr_sqsize.attr,
&dev_attr_hostnqn.attr,
&dev_attr_hostid.attr,
&dev_attr_ctrl_loss_tmo.attr,
&dev_attr_reconnect_delay.attr,
NULL
};
@ -3519,6 +3711,13 @@ static struct nvme_ns_head *nvme_alloc_ns_head(struct nvme_ctrl *ctrl,
goto out_cleanup_srcu;
}
if (head->ids.csi) {
ret = nvme_get_effects_log(ctrl, head->ids.csi, &head->effects);
if (ret)
goto out_cleanup_srcu;
} else
head->effects = ctrl->effects;
ret = nvme_mpath_alloc_disk(ctrl, head);
if (ret)
goto out_cleanup_srcu;
@ -3735,7 +3934,7 @@ static void nvme_ns_remove(struct nvme_ns *ns)
nvme_mpath_clear_current_path(ns);
synchronize_srcu(&ns->head->srcu); /* wait for concurrent submissions */
if (ns->disk && ns->disk->flags & GENHD_FL_UP) {
if (ns->disk->flags & GENHD_FL_UP) {
del_gendisk(ns->disk);
blk_cleanup_queue(ns->queue);
if (blk_get_integrity(ns->disk))
@ -3766,7 +3965,7 @@ static void nvme_validate_ns(struct nvme_ctrl *ctrl, unsigned nsid)
ns = nvme_find_get_ns(ctrl, nsid);
if (ns) {
if (ns->disk && revalidate_disk(ns->disk))
if (revalidate_disk(ns->disk))
nvme_ns_remove(ns);
nvme_put_ns(ns);
} else
@ -3859,8 +4058,8 @@ static void nvme_clear_changed_ns_log(struct nvme_ctrl *ctrl)
* raced with us in reading the log page, which could cause us to miss
* updates.
*/
error = nvme_get_log(ctrl, NVME_NSID_ALL, NVME_LOG_CHANGED_NS, 0, log,
log_size, 0);
error = nvme_get_log(ctrl, NVME_NSID_ALL, NVME_LOG_CHANGED_NS, 0,
NVME_CSI_NVM, log, log_size, 0);
if (error)
dev_warn(ctrl->device,
"reading changed ns log failed: %d\n", error);
@ -4004,8 +4203,8 @@ static void nvme_get_fw_slot_info(struct nvme_ctrl *ctrl)
if (!log)
return;
if (nvme_get_log(ctrl, NVME_NSID_ALL, NVME_LOG_FW_SLOT, 0, log,
sizeof(*log), 0))
if (nvme_get_log(ctrl, NVME_NSID_ALL, NVME_LOG_FW_SLOT, 0, NVME_CSI_NVM,
log, sizeof(*log), 0))
dev_warn(ctrl->device, "Get FW SLOT INFO log error\n");
kfree(log);
}
@ -4142,11 +4341,16 @@ static void nvme_free_ctrl(struct device *dev)
struct nvme_ctrl *ctrl =
container_of(dev, struct nvme_ctrl, ctrl_device);
struct nvme_subsystem *subsys = ctrl->subsys;
struct nvme_cel *cel, *next;
if (subsys && ctrl->instance != subsys->instance)
ida_simple_remove(&nvme_instance_ida, ctrl->instance);
kfree(ctrl->effects);
list_for_each_entry_safe(cel, next, &ctrl->cels, entry) {
list_del(&cel->entry);
kfree(cel);
}
nvme_mpath_uninit(ctrl);
__free_page(ctrl->discard_page);
@ -4177,6 +4381,7 @@ int nvme_init_ctrl(struct nvme_ctrl *ctrl, struct device *dev,
spin_lock_init(&ctrl->lock);
mutex_init(&ctrl->scan_lock);
INIT_LIST_HEAD(&ctrl->namespaces);
INIT_LIST_HEAD(&ctrl->cels);
init_rwsem(&ctrl->namespaces_rwsem);
ctrl->dev = dev;
ctrl->ops = ops;
@ -4373,6 +4578,8 @@ static inline void _nvme_check_size(void)
BUILD_BUG_ON(sizeof(struct nvme_command) != 64);
BUILD_BUG_ON(sizeof(struct nvme_id_ctrl) != NVME_IDENTIFY_DATA_SIZE);
BUILD_BUG_ON(sizeof(struct nvme_id_ns) != NVME_IDENTIFY_DATA_SIZE);
BUILD_BUG_ON(sizeof(struct nvme_id_ns_zns) != NVME_IDENTIFY_DATA_SIZE);
BUILD_BUG_ON(sizeof(struct nvme_id_ctrl_zns) != NVME_IDENTIFY_DATA_SIZE);
BUILD_BUG_ON(sizeof(struct nvme_lba_range_type) != 64);
BUILD_BUG_ON(sizeof(struct nvme_smart_log) != 512);
BUILD_BUG_ON(sizeof(struct nvme_dbbuf) != 64);

2
drivers/nvme/host/hwmon.c
View File

@ -62,7 +62,7 @@ static int nvme_hwmon_get_smart_log(struct nvme_hwmon_data *data)
int ret;
ret = nvme_get_log(data->ctrl, NVME_NSID_ALL, NVME_LOG_SMART, 0,
&data->log, sizeof(data->log), 0);
NVME_CSI_NVM, &data->log, sizeof(data->log), 0);
return ret <= 0 ? ret : -EIO;
}

4
drivers/nvme/host/lightnvm.c
View File

@ -593,8 +593,8 @@ static int nvme_nvm_get_chk_meta(struct nvm_dev *ndev,
dev_meta_off = dev_meta;
ret = nvme_get_log(ctrl, ns->head->ns_id,
NVME_NVM_LOG_REPORT_CHUNK, 0, dev_meta, len,
offset);
NVME_NVM_LOG_REPORT_CHUNK, 0, NVME_CSI_NVM,
dev_meta, len, offset);
if (ret) {
dev_err(ctrl->device, "Get REPORT CHUNK log error\n");
break;

2
drivers/nvme/host/multipath.c
View File

@ -527,7 +527,7 @@ static int nvme_read_ana_log(struct nvme_ctrl *ctrl)
int error;
mutex_lock(&ctrl->ana_lock);
error = nvme_get_log(ctrl, NVME_NSID_ALL, NVME_LOG_ANA, 0,
error = nvme_get_log(ctrl, NVME_NSID_ALL, NVME_LOG_ANA, 0, NVME_CSI_NVM,
ctrl->ana_log_buf, ctrl->ana_log_size, 0);
if (error) {
dev_warn(ctrl->device, "Failed to get ANA log: %d\n", error);

50
drivers/nvme/host/nvme.h
View File

@ -191,6 +191,12 @@ struct nvme_fault_inject {
#endif
};
struct nvme_cel {
struct list_head entry;
struct nvme_effects_log log;
u8 csi;
};
struct nvme_ctrl {
bool comp_seen;
enum nvme_ctrl_state state;
@ -232,6 +238,9 @@ struct nvme_ctrl {
u32 max_hw_sectors;
u32 max_segments;
u32 max_integrity_segments;
#ifdef CONFIG_BLK_DEV_ZONED
u32 max_zone_append;
#endif
u16 crdt[3];
u16 oncs;
u16 oacs;
@ -257,6 +266,7 @@ struct nvme_ctrl {
unsigned long quirks;
struct nvme_id_power_state psd[32];
struct nvme_effects_log *effects;
struct list_head cels;
struct work_struct scan_work;
struct work_struct async_event_work;
struct delayed_work ka_work;
@ -339,6 +349,7 @@ struct nvme_ns_ids {
u8 eui64[8];
u8 nguid[16];
uuid_t uuid;
u8 csi;
};
/*
@ -358,6 +369,7 @@ struct nvme_ns_head {
struct kref ref;
bool shared;
int instance;
struct nvme_effects_log *effects;
#ifdef CONFIG_NVME_MULTIPATH
struct gendisk *disk;
struct bio_list requeue_list;
@ -395,6 +407,9 @@ struct nvme_ns {
u16 sgs;
u32 sws;
u8 pi_type;
#ifdef CONFIG_BLK_DEV_ZONED
u64 zsze;
#endif
unsigned long features;
unsigned long flags;
#define NVME_NS_REMOVING 0
@ -560,8 +575,11 @@ int nvme_reset_ctrl_sync(struct nvme_ctrl *ctrl);
int nvme_try_sched_reset(struct nvme_ctrl *ctrl);
int nvme_delete_ctrl(struct nvme_ctrl *ctrl);
int nvme_get_log(struct nvme_ctrl *ctrl, u32 nsid, u8 log_page, u8 lsp,
int nvme_get_log(struct nvme_ctrl *ctrl, u32 nsid, u8 log_page, u8 lsp, u8 csi,
void *log, size_t size, u64 offset);
struct nvme_ns *nvme_get_ns_from_disk(struct gendisk *disk,
struct nvme_ns_head **head, int *srcu_idx);
void nvme_put_ns_from_disk(struct nvme_ns_head *head, int idx);
extern const struct attribute_group *nvme_ns_id_attr_groups[];
extern const struct block_device_operations nvme_ns_head_ops;
@ -697,6 +715,36 @@ static inline void nvme_mpath_update_disk_size(struct gendisk *disk)
}
#endif /* CONFIG_NVME_MULTIPATH */
#ifdef CONFIG_BLK_DEV_ZONED
int nvme_update_zone_info(struct gendisk *disk, struct nvme_ns *ns,
unsigned lbaf);
int nvme_report_zones(struct gendisk *disk, sector_t sector,
unsigned int nr_zones, report_zones_cb cb, void *data);
blk_status_t nvme_setup_zone_mgmt_send(struct nvme_ns *ns, struct request *req,
struct nvme_command *cmnd,
enum nvme_zone_mgmt_action action);
#else
#define nvme_report_zones NULL
static inline blk_status_t nvme_setup_zone_mgmt_send(struct nvme_ns *ns,
struct request *req, struct nvme_command *cmnd,
enum nvme_zone_mgmt_action action)
{
return BLK_STS_NOTSUPP;
}
static inline int nvme_update_zone_info(struct gendisk *disk,
struct nvme_ns *ns,
unsigned lbaf)
{
dev_warn(ns->ctrl->device,
"Please enable CONFIG_BLK_DEV_ZONED to support ZNS devices\n");
return -EPROTONOSUPPORT;
}
#endif
#ifdef CONFIG_NVM
int nvme_nvm_register(struct nvme_ns *ns, char *disk_name, int node);
void nvme_nvm_unregister(struct nvme_ns *ns);

59
drivers/nvme/host/pci.c
View File

@ -61,10 +61,10 @@ MODULE_PARM_DESC(sgl_threshold,
static int io_queue_depth_set(const char *val, const struct kernel_param *kp);
static const struct kernel_param_ops io_queue_depth_ops = {
.set = io_queue_depth_set,
.get = param_get_int,
.get = param_get_uint,
};
static int io_queue_depth = 1024;
static unsigned int io_queue_depth = 1024;
module_param_cb(io_queue_depth, &io_queue_depth_ops, &io_queue_depth, 0644);
MODULE_PARM_DESC(io_queue_depth, "set io queue depth, should >= 2");
@ -115,7 +115,7 @@ struct nvme_dev {
unsigned max_qid;
unsigned io_queues[HCTX_MAX_TYPES];
unsigned int num_vecs;
int q_depth;
u16 q_depth;
int io_sqes;
u32 db_stride;
void __iomem *bar;
@ -151,13 +151,14 @@ struct nvme_dev {
static int io_queue_depth_set(const char *val, const struct kernel_param *kp)
{
int n = 0, ret;
int ret;
u16 n;
ret = kstrtoint(val, 10, &n);
ret = kstrtou16(val, 10, &n);
if (ret != 0 || n < 2)
return -EINVAL;
return param_set_int(val, kp);
return param_set_ushort(val, kp);
}
static inline unsigned int sq_idx(unsigned int qid, u32 stride)
@ -361,7 +362,7 @@ static int nvme_pci_npages_sgl(unsigned int num_seg)
return DIV_ROUND_UP(num_seg * sizeof(struct nvme_sgl_desc), PAGE_SIZE);
}
static unsigned int nvme_pci_iod_alloc_size(struct nvme_dev *dev,
static size_t nvme_pci_iod_alloc_size(struct nvme_dev *dev,
unsigned int size, unsigned int nseg, bool use_sgl)
{
size_t alloc_size;
@ -500,9 +501,6 @@ static inline bool nvme_pci_use_sgls(struct nvme_dev *dev, struct request *req)
int nseg = blk_rq_nr_phys_segments(req);
unsigned int avg_seg_size;
if (nseg == 0)
return false;
avg_seg_size = DIV_ROUND_UP(blk_rq_payload_bytes(req), nseg);
if (!(dev->ctrl.sgls & ((1 << 0) | (1 << 1))))
@ -764,7 +762,7 @@ static blk_status_t nvme_setup_prp_simple(struct nvme_dev *dev,
cmnd->dptr.prp1 = cpu_to_le64(iod->first_dma);
if (bv->bv_len > first_prp_len)
cmnd->dptr.prp2 = cpu_to_le64(iod->first_dma + first_prp_len);
return 0;
return BLK_STS_OK;
}
static blk_status_t nvme_setup_sgl_simple(struct nvme_dev *dev,
@ -782,7 +780,7 @@ static blk_status_t nvme_setup_sgl_simple(struct nvme_dev *dev,
cmnd->dptr.sgl.addr = cpu_to_le64(iod->first_dma);
cmnd->dptr.sgl.length = cpu_to_le32(iod->dma_len);
cmnd->dptr.sgl.type = NVME_SGL_FMT_DATA_DESC << 4;
return 0;
return BLK_STS_OK;
}
static blk_status_t nvme_map_data(struct nvme_dev *dev, struct request *req,
@ -846,7 +844,7 @@ static blk_status_t nvme_map_metadata(struct nvme_dev *dev, struct request *req,
if (dma_mapping_error(dev->dev, iod->meta_dma))
return BLK_STS_IOERR;
cmnd->rw.metadata = cpu_to_le64(iod->meta_dma);
return 0;
return BLK_STS_OK;
}
/*
@ -1019,6 +1017,7 @@ static irqreturn_t nvme_irq(int irq, void *data)
static irqreturn_t nvme_irq_check(int irq, void *data)
{
struct nvme_queue *nvmeq = data;
if (nvme_cqe_pending(nvmeq))
return IRQ_WAKE_THREAD;
return IRQ_NONE;
@ -1154,7 +1153,6 @@ static void abort_endio(struct request *req, blk_status_t error)
static bool nvme_should_reset(struct nvme_dev *dev, u32 csts)
{
/* If true, indicates loss of adapter communication, possibly by a
* NVMe Subsystem reset.
*/
@ -1261,9 +1259,9 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req, bool reserved)
}
/*
* Shutdown the controller immediately and schedule a reset if the
* command was already aborted once before and still hasn't been
* returned to the driver, or if this is the admin queue.
* Shutdown the controller immediately and schedule a reset if the
* command was already aborted once before and still hasn't been
* returned to the driver, or if this is the admin queue.
*/
if (!nvmeq->qid || iod->aborted) {
dev_warn(dev->ctrl.device,
@ -1402,6 +1400,7 @@ static int nvme_cmb_qdepth(struct nvme_dev *dev, int nr_io_queues,
if (q_size_aligned * nr_io_queues > dev->cmb_size) {
u64 mem_per_q = div_u64(dev->cmb_size, nr_io_queues);
mem_per_q = round_down(mem_per_q, dev->ctrl.page_size);
q_depth = div_u64(mem_per_q, entry_size);
@ -1932,12 +1931,12 @@ out:
static int nvme_alloc_host_mem(struct nvme_dev *dev, u64 min, u64 preferred)
{
u32 chunk_size;
u64 min_chunk = min_t(u64, preferred, PAGE_SIZE * MAX_ORDER_NR_PAGES);
u64 hmminds = max_t(u32, dev->ctrl.hmminds * 4096, PAGE_SIZE * 2);
u64 chunk_size;
/* start big and work our way down */
for (chunk_size = min_t(u64, preferred, PAGE_SIZE * MAX_ORDER_NR_PAGES);
chunk_size >= max_t(u32, dev->ctrl.hmminds * 4096, PAGE_SIZE * 2);
chunk_size /= 2) {
for (chunk_size = min_chunk; chunk_size >= hmminds; chunk_size /= 2) {
if (!__nvme_alloc_host_mem(dev, preferred, chunk_size)) {
if (!min || dev->host_mem_size >= min)
return 0;
@ -2003,7 +2002,7 @@ static void nvme_calc_irq_sets(struct irq_affinity *affd, unsigned int nrirqs)
unsigned int nr_read_queues, nr_write_queues = dev->nr_write_queues;
/*
* If there is no interupt available for queues, ensure that
* If there is no interrupt available for queues, ensure that
* the default queue is set to 1. The affinity set size is
* also set to one, but the irq core ignores it for this case.
*
@ -2261,8 +2260,8 @@ static void nvme_dev_add(struct nvme_dev *dev)
dev->tagset.nr_maps++;
dev->tagset.timeout = NVME_IO_TIMEOUT;
dev->tagset.numa_node = dev->ctrl.numa_node;
dev->tagset.queue_depth =
min_t(int, dev->q_depth, BLK_MQ_MAX_DEPTH) - 1;
dev->tagset.queue_depth = min_t(unsigned int, dev->q_depth,
BLK_MQ_MAX_DEPTH) - 1;
dev->tagset.cmd_size = sizeof(struct nvme_iod);
dev->tagset.flags = BLK_MQ_F_SHOULD_MERGE;
dev->tagset.driver_data = dev;
@ -2321,7 +2320,7 @@ static int nvme_pci_enable(struct nvme_dev *dev)
dev->ctrl.cap = lo_hi_readq(dev->bar + NVME_REG_CAP);
dev->q_depth = min_t(int, NVME_CAP_MQES(dev->ctrl.cap) + 1,
dev->q_depth = min_t(u16, NVME_CAP_MQES(dev->ctrl.cap) + 1,
io_queue_depth);
dev->ctrl.sqsize = dev->q_depth - 1; /* 0's based queue depth */
dev->db_stride = 1 << NVME_CAP_STRIDE(dev->ctrl.cap);
@ -2876,6 +2875,7 @@ static void nvme_reset_done(struct pci_dev *pdev)
static void nvme_shutdown(struct pci_dev *pdev)
{
struct nvme_dev *dev = pci_get_drvdata(pdev);
nvme_disable_prepare_reset(dev, true);
}
@ -3006,6 +3006,7 @@ unfreeze:
static int nvme_simple_suspend(struct device *dev)
{
struct nvme_dev *ndev = pci_get_drvdata(to_pci_dev(dev));
return nvme_disable_prepare_reset(ndev, true);
}
@ -3079,16 +3080,16 @@ static const struct pci_error_handlers nvme_err_handler = {
};
static const struct pci_device_id nvme_id_table[] = {
{ PCI_VDEVICE(INTEL, 0x0953),
{ PCI_VDEVICE(INTEL, 0x0953), /* Intel 750/P3500/P3600/P3700 */
.driver_data = NVME_QUIRK_STRIPE_SIZE |
NVME_QUIRK_DEALLOCATE_ZEROES, },
{ PCI_VDEVICE(INTEL, 0x0a53),
{ PCI_VDEVICE(INTEL, 0x0a53), /* Intel P3520 */
.driver_data = NVME_QUIRK_STRIPE_SIZE |
NVME_QUIRK_DEALLOCATE_ZEROES, },
{ PCI_VDEVICE(INTEL, 0x0a54),
{ PCI_VDEVICE(INTEL, 0x0a54), /* Intel P4500/P4600 */
.driver_data = NVME_QUIRK_STRIPE_SIZE |
NVME_QUIRK_DEALLOCATE_ZEROES, },
{ PCI_VDEVICE(INTEL, 0x0a55),
{ PCI_VDEVICE(INTEL, 0x0a55), /* Dell Express Flash P4600 */
.driver_data = NVME_QUIRK_STRIPE_SIZE |
NVME_QUIRK_DEALLOCATE_ZEROES, },
{ PCI_VDEVICE(INTEL, 0xf1a5), /* Intel 600P/P3100 */

73
drivers/nvme/host/tcp.c
View File

@ -46,6 +46,7 @@ struct nvme_tcp_request {
u32 pdu_sent;
u16 ttag;
struct list_head entry;
struct llist_node lentry;
__le32 ddgst;
struct bio *curr_bio;
@ -75,9 +76,10 @@ struct nvme_tcp_queue {
struct work_struct io_work;
int io_cpu;
spinlock_t lock;
struct mutex send_mutex;
struct llist_head req_list;
struct list_head send_list;
bool more_requests;
/* recv state */
void *pdu;
@ -261,15 +263,13 @@ static inline void nvme_tcp_advance_req(struct nvme_tcp_request *req,
}
static inline void nvme_tcp_queue_request(struct nvme_tcp_request *req,
bool sync)
bool sync, bool last)
{
struct nvme_tcp_queue *queue = req->queue;
bool empty;
spin_lock(&queue->lock);
empty = list_empty(&queue->send_list) && !queue->request;
list_add_tail(&req->entry, &queue->send_list);
spin_unlock(&queue->lock);
empty = llist_add(&req->lentry, &queue->req_list) &&
list_empty(&queue->send_list) && !queue->request;
/*
* if we're the first on the send_list and we can try to send
@ -278,25 +278,42 @@ static inline void nvme_tcp_queue_request(struct nvme_tcp_request *req,
*/
if (queue->io_cpu == smp_processor_id() &&
sync && empty && mutex_trylock(&queue->send_mutex)) {
queue->more_requests = !last;
nvme_tcp_try_send(queue);
queue->more_requests = false;
mutex_unlock(&queue->send_mutex);
} else {
} else if (last) {
queue_work_on(queue->io_cpu, nvme_tcp_wq, &queue->io_work);
}
}
static void nvme_tcp_process_req_list(struct nvme_tcp_queue *queue)
{
struct nvme_tcp_request *req;
struct llist_node *node;
for (node = llist_del_all(&queue->req_list); node; node = node->next) {
req = llist_entry(node, struct nvme_tcp_request, lentry);
list_add(&req->entry, &queue->send_list);
}
}
static inline struct nvme_tcp_request *
nvme_tcp_fetch_request(struct nvme_tcp_queue *queue)
{
struct nvme_tcp_request *req;
spin_lock(&queue->lock);
req = list_first_entry_or_null(&queue->send_list,
struct nvme_tcp_request, entry);
if (req)
list_del(&req->entry);
spin_unlock(&queue->lock);
if (!req) {
nvme_tcp_process_req_list(queue);
req = list_first_entry_or_null(&queue->send_list,
struct nvme_tcp_request, entry);
if (unlikely(!req))
return NULL;
}
list_del(&req->entry);
return req;
}
@ -596,7 +613,7 @@ static int nvme_tcp_handle_r2t(struct nvme_tcp_queue *queue,
req->state = NVME_TCP_SEND_H2C_PDU;
req->offset = 0;
nvme_tcp_queue_request(req, false);
nvme_tcp_queue_request(req, false, true);
return 0;
}
@ -863,6 +880,12 @@ done:
read_unlock(&sk->sk_callback_lock);
}
static inline bool nvme_tcp_queue_more(struct nvme_tcp_queue *queue)
{
return !list_empty(&queue->send_list) ||
!llist_empty(&queue->req_list) || queue->more_requests;
}
static inline void nvme_tcp_done_send_req(struct nvme_tcp_queue *queue)
{
queue->request = NULL;
@ -884,7 +907,7 @@ static int nvme_tcp_try_send_data(struct nvme_tcp_request *req)
bool last = nvme_tcp_pdu_last_send(req, len);
int ret, flags = MSG_DONTWAIT;
if (last && !queue->data_digest)
if (last && !queue->data_digest && !nvme_tcp_queue_more(queue))
flags |= MSG_EOR;
else
flags |= MSG_MORE | MSG_SENDPAGE_NOTLAST;
@ -931,7 +954,7 @@ static int nvme_tcp_try_send_cmd_pdu(struct nvme_tcp_request *req)
int flags = MSG_DONTWAIT;
int ret;
if (inline_data)
if (inline_data || nvme_tcp_queue_more(queue))
flags |= MSG_MORE | MSG_SENDPAGE_NOTLAST;
else
flags |= MSG_EOR;
@ -996,12 +1019,17 @@ static int nvme_tcp_try_send_ddgst(struct nvme_tcp_request *req)
{
struct nvme_tcp_queue *queue = req->queue;
int ret;
struct msghdr msg = { .msg_flags = MSG_DONTWAIT | MSG_EOR };
struct msghdr msg = { .msg_flags = MSG_DONTWAIT };
struct kvec iov = {
.iov_base = &req->ddgst + req->offset,
.iov_len = NVME_TCP_DIGEST_LENGTH - req->offset
};
if (nvme_tcp_queue_more(queue))
msg.msg_flags |= MSG_MORE;
else
msg.msg_flags |= MSG_EOR;
ret = kernel_sendmsg(queue->sock, &msg, &iov, 1, iov.iov_len);
if (unlikely(ret <= 0))
return ret;
@ -1344,8 +1372,8 @@ static int nvme_tcp_alloc_queue(struct nvme_ctrl *nctrl,
int ret, rcv_pdu_size;
queue->ctrl = ctrl;
init_llist_head(&queue->req_list);
INIT_LIST_HEAD(&queue->send_list);
spin_lock_init(&queue->lock);
mutex_init(&queue->send_mutex);
INIT_WORK(&queue->io_work, nvme_tcp_io_work);
queue->queue_size = queue_size;
@ -2106,7 +2134,7 @@ static void nvme_tcp_submit_async_event(struct nvme_ctrl *arg)
ctrl->async_req.curr_bio = NULL;
ctrl->async_req.data_len = 0;
nvme_tcp_queue_request(&ctrl->async_req, true);
nvme_tcp_queue_request(&ctrl->async_req, true, true);
}
static enum blk_eh_timer_return
@ -2218,6 +2246,14 @@ static blk_status_t nvme_tcp_setup_cmd_pdu(struct nvme_ns *ns,
return 0;
}
static void nvme_tcp_commit_rqs(struct blk_mq_hw_ctx *hctx)
{
struct nvme_tcp_queue *queue = hctx->driver_data;
if (!llist_empty(&queue->req_list))
queue_work_on(queue->io_cpu, nvme_tcp_wq, &queue->io_work);
}
static blk_status_t nvme_tcp_queue_rq(struct blk_mq_hw_ctx *hctx,
const struct blk_mq_queue_data *bd)
{
@ -2237,7 +2273,7 @@ static blk_status_t nvme_tcp_queue_rq(struct blk_mq_hw_ctx *hctx,
blk_mq_start_request(rq);
nvme_tcp_queue_request(req, true);
nvme_tcp_queue_request(req, true, bd->last);
return BLK_STS_OK;
}
@ -2305,6 +2341,7 @@ static int nvme_tcp_poll(struct blk_mq_hw_ctx *hctx)
static const struct blk_mq_ops nvme_tcp_mq_ops = {
.queue_rq = nvme_tcp_queue_rq,
.commit_rqs = nvme_tcp_commit_rqs,
.complete = nvme_complete_rq,
.init_request = nvme_tcp_init_request,
.exit_request = nvme_tcp_exit_request,

256
drivers/nvme/host/zns.c Normal file
View File

@ -0,0 +1,256 @@
// SPDX-License-Identifier: GPL-2.0
/*
* Copyright (C) 2020 Western Digital Corporation or its affiliates.
*/
#include <linux/blkdev.h>
#include <linux/vmalloc.h>
#include "nvme.h"
static int nvme_set_max_append(struct nvme_ctrl *ctrl)
{
struct nvme_command c = { };
struct nvme_id_ctrl_zns *id;
int status;
id = kzalloc(sizeof(*id), GFP_KERNEL);
if (!id)
return -ENOMEM;
c.identify.opcode = nvme_admin_identify;
c.identify.cns = NVME_ID_CNS_CS_CTRL;
c.identify.csi = NVME_CSI_ZNS;
status = nvme_submit_sync_cmd(ctrl->admin_q, &c, id, sizeof(*id));
if (status) {
kfree(id);
return status;
}
if (id->zasl)
ctrl->max_zone_append = 1 << (id->zasl + 3);
else
ctrl->max_zone_append = ctrl->max_hw_sectors;
kfree(id);
return 0;
}
int nvme_update_zone_info(struct gendisk *disk, struct nvme_ns *ns,
unsigned lbaf)
{
struct nvme_effects_log *log = ns->head->effects;
struct request_queue *q = disk->queue;
struct nvme_command c = { };
struct nvme_id_ns_zns *id;
int status;
/* Driver requires zone append support */
if (!(le32_to_cpu(log->iocs[nvme_cmd_zone_append]) &
NVME_CMD_EFFECTS_CSUPP)) {
dev_warn(ns->ctrl->device,
"append not supported for zoned namespace:%d\n",
ns->head->ns_id);
return -EINVAL;
}
/* Lazily query controller append limit for the first zoned namespace */
if (!ns->ctrl->max_zone_append) {
status = nvme_set_max_append(ns->ctrl);
if (status)
return status;
}
id = kzalloc(sizeof(*id), GFP_KERNEL);
if (!id)
return -ENOMEM;
c.identify.opcode = nvme_admin_identify;
c.identify.nsid = cpu_to_le32(ns->head->ns_id);
c.identify.cns = NVME_ID_CNS_CS_NS;
c.identify.csi = NVME_CSI_ZNS;
status = nvme_submit_sync_cmd(ns->ctrl->admin_q, &c, id, sizeof(*id));
if (status)
goto free_data;
/*
* We currently do not handle devices requiring any of the zoned
* operation characteristics.
*/
if (id->zoc) {
dev_warn(ns->ctrl->device,
"zone operations:%x not supported for namespace:%u\n",
le16_to_cpu(id->zoc), ns->head->ns_id);
status = -EINVAL;
goto free_data;
}
ns->zsze = nvme_lba_to_sect(ns, le64_to_cpu(id->lbafe[lbaf].zsze));
if (!is_power_of_2(ns->zsze)) {
dev_warn(ns->ctrl->device,
"invalid zone size:%llu for namespace:%u\n",
ns->zsze, ns->head->ns_id);
status = -EINVAL;
goto free_data;
}
q->limits.zoned = BLK_ZONED_HM;
blk_queue_flag_set(QUEUE_FLAG_ZONE_RESETALL, q);
blk_queue_max_open_zones(q, le32_to_cpu(id->mor) + 1);
blk_queue_max_active_zones(q, le32_to_cpu(id->mar) + 1);
free_data:
kfree(id);
return status;
}
static void *nvme_zns_alloc_report_buffer(struct nvme_ns *ns,
unsigned int nr_zones, size_t *buflen)
{
struct request_queue *q = ns->disk->queue;
size_t bufsize;
void *buf;
const size_t min_bufsize = sizeof(struct nvme_zone_report) +
sizeof(struct nvme_zone_descriptor);
nr_zones = min_t(unsigned int, nr_zones,
get_capacity(ns->disk) >> ilog2(ns->zsze));
bufsize = sizeof(struct nvme_zone_report) +
nr_zones * sizeof(struct nvme_zone_descriptor);
bufsize = min_t(size_t, bufsize,
queue_max_hw_sectors(q) << SECTOR_SHIFT);
bufsize = min_t(size_t, bufsize, queue_max_segments(q) << PAGE_SHIFT);
while (bufsize >= min_bufsize) {
buf = __vmalloc(bufsize, GFP_KERNEL | __GFP_NORETRY);
if (buf) {
*buflen = bufsize;
return buf;
}
bufsize >>= 1;
}
return NULL;
}
static int __nvme_ns_report_zones(struct nvme_ns *ns, sector_t sector,
struct nvme_zone_report *report,
size_t buflen)
{
struct nvme_command c = { };
int ret;
c.zmr.opcode = nvme_cmd_zone_mgmt_recv;
c.zmr.nsid = cpu_to_le32(ns->head->ns_id);
c.zmr.slba = cpu_to_le64(nvme_sect_to_lba(ns, sector));
c.zmr.numd = cpu_to_le32(nvme_bytes_to_numd(buflen));
c.zmr.zra = NVME_ZRA_ZONE_REPORT;
c.zmr.zrasf = NVME_ZRASF_ZONE_REPORT_ALL;
c.zmr.pr = NVME_REPORT_ZONE_PARTIAL;
ret = nvme_submit_sync_cmd(ns->queue, &c, report, buflen);
if (ret)
return ret;
return le64_to_cpu(report->nr_zones);
}
static int nvme_zone_parse_entry(struct nvme_ns *ns,
struct nvme_zone_descriptor *entry,
unsigned int idx, report_zones_cb cb,
void *data)
{
struct blk_zone zone = { };
if ((entry->zt & 0xf) != NVME_ZONE_TYPE_SEQWRITE_REQ) {
dev_err(ns->ctrl->device, "invalid zone type %#x\n",
entry->zt);
return -EINVAL;
}
zone.type = BLK_ZONE_TYPE_SEQWRITE_REQ;
zone.cond = entry->zs >> 4;
zone.len = ns->zsze;
zone.capacity = nvme_lba_to_sect(ns, le64_to_cpu(entry->zcap));
zone.start = nvme_lba_to_sect(ns, le64_to_cpu(entry->zslba));
zone.wp = nvme_lba_to_sect(ns, le64_to_cpu(entry->wp));
return cb(&zone, idx, data);
}
static int nvme_ns_report_zones(struct nvme_ns *ns, sector_t sector,
unsigned int nr_zones, report_zones_cb cb, void *data)
{
struct nvme_zone_report *report;
int ret, zone_idx = 0;
unsigned int nz, i;
size_t buflen;
report = nvme_zns_alloc_report_buffer(ns, nr_zones, &buflen);
if (!report)
return -ENOMEM;
sector &= ~(ns->zsze - 1);
while (zone_idx < nr_zones && sector < get_capacity(ns->disk)) {
memset(report, 0, buflen);
ret = __nvme_ns_report_zones(ns, sector, report, buflen);
if (ret < 0)
goto out_free;
nz = min_t(unsigned int, ret, nr_zones);
if (!nz)
break;
for (i = 0; i < nz && zone_idx < nr_zones; i++) {
ret = nvme_zone_parse_entry(ns, &report->entries[i],
zone_idx, cb, data);
if (ret)
goto out_free;
zone_idx++;
}
sector += ns->zsze * nz;
}
if (zone_idx > 0)
ret = zone_idx;
else
ret = -EINVAL;
out_free:
kvfree(report);
return ret;
}
int nvme_report_zones(struct gendisk *disk, sector_t sector,
unsigned int nr_zones, report_zones_cb cb, void *data)
{
struct nvme_ns_head *head = NULL;
struct nvme_ns *ns;
int srcu_idx, ret;
ns = nvme_get_ns_from_disk(disk, &head, &srcu_idx);
if (unlikely(!ns))
return -EWOULDBLOCK;
if (ns->head->ids.csi == NVME_CSI_ZNS)
ret = nvme_ns_report_zones(ns, sector, nr_zones, cb, data);
else
ret = -EINVAL;
nvme_put_ns_from_disk(head, srcu_idx);
return ret;
}
blk_status_t nvme_setup_zone_mgmt_send(struct nvme_ns *ns, struct request *req,
struct nvme_command *c, enum nvme_zone_mgmt_action action)
{
c->zms.opcode = nvme_cmd_zone_mgmt_send;
c->zms.nsid = cpu_to_le32(ns->head->ns_id);
c->zms.slba = cpu_to_le64(nvme_sect_to_lba(ns, blk_rq_pos(req)));
c->zms.zsa = action;
if (req_op(req) == REQ_OP_ZONE_RESET_ALL)
c->zms.select_all = 1;
return BLK_STS_OK;
}

2
drivers/nvme/target/admin-cmd.c
View File

@ -427,7 +427,7 @@ static void nvmet_execute_identify_ctrl(struct nvmet_req *req)
id->awupf = 0;
id->sgls = cpu_to_le32(1 << 0); /* we always support SGLs */
if (ctrl->ops->has_keyed_sgls)
if (ctrl->ops->flags & NVMF_KEYED_SGLS)
id->sgls |= cpu_to_le32(1 << 2);
if (req->port->inline_data_size)
id->sgls |= cpu_to_le32(1 << 20);

14
drivers/nvme/target/configfs.c
View File

@ -862,14 +862,14 @@ static ssize_t nvmet_subsys_attr_version_show(struct config_item *item,
struct nvmet_subsys *subsys = to_subsys(item);
if (NVME_TERTIARY(subsys->ver))
return snprintf(page, PAGE_SIZE, "%d.%d.%d\n",
(int)NVME_MAJOR(subsys->ver),
(int)NVME_MINOR(subsys->ver),
(int)NVME_TERTIARY(subsys->ver));
return snprintf(page, PAGE_SIZE, "%llu.%llu.%llu\n",
NVME_MAJOR(subsys->ver),
NVME_MINOR(subsys->ver),
NVME_TERTIARY(subsys->ver));
return snprintf(page, PAGE_SIZE, "%d.%d\n",
(int)NVME_MAJOR(subsys->ver),
(int)NVME_MINOR(subsys->ver));
return snprintf(page, PAGE_SIZE, "%llu.%llu\n",
NVME_MAJOR(subsys->ver),
NVME_MINOR(subsys->ver));
}
static ssize_t nvmet_subsys_attr_version_store(struct config_item *item,

2
drivers/nvme/target/core.c
View File

@ -336,7 +336,7 @@ int nvmet_enable_port(struct nvmet_port *port)
* If the user requested PI support and the transport isn't pi capable,
* don't enable the port.
*/
if (port->pi_enable && !ops->metadata_support) {
if (port->pi_enable && !(ops->flags & NVMF_METADATA_SUPPORTED)) {
pr_err("T10-PI is not supported by transport type %d\n",
port->disc_addr.trtype);
ret = -EINVAL;

2
drivers/nvme/target/discovery.c
View File

@ -277,7 +277,7 @@ static void nvmet_execute_disc_identify(struct nvmet_req *req)
id->maxcmd = cpu_to_le16(NVMET_MAX_CMD);
id->sgls = cpu_to_le32(1 << 0); /* we always support SGLs */
if (ctrl->ops->has_keyed_sgls)
if (ctrl->ops->flags & NVMF_KEYED_SGLS)
id->sgls |= cpu_to_le32(1 << 2);
if (req->port->inline_data_size)
id->sgls |= cpu_to_le32(1 << 20);

29
drivers/nvme/target/fcloop.c
View File

@ -43,6 +43,17 @@ static const match_table_t opt_tokens = {
{ NVMF_OPT_ERR, NULL }
};
static int fcloop_verify_addr(substring_t *s)
{
size_t blen = s->to - s->from + 1;
if (strnlen(s->from, blen) != NVME_FC_TRADDR_HEXNAMELEN + 2 ||
strncmp(s->from, "0x", 2))
return -EINVAL;
return 0;
}
static int
fcloop_parse_options(struct fcloop_ctrl_options *opts,
const char *buf)
@ -64,14 +75,16 @@ fcloop_parse_options(struct fcloop_ctrl_options *opts,
opts->mask |= token;
switch (token) {
case NVMF_OPT_WWNN:
if (match_u64(args, &token64)) {
if (fcloop_verify_addr(args) ||
match_u64(args, &token64)) {
ret = -EINVAL;
goto out_free_options;
}
opts->wwnn = token64;
break;
case NVMF_OPT_WWPN:
if (match_u64(args, &token64)) {
if (fcloop_verify_addr(args) ||
match_u64(args, &token64)) {
ret = -EINVAL;
goto out_free_options;
}
@ -92,14 +105,16 @@ fcloop_parse_options(struct fcloop_ctrl_options *opts,
opts->fcaddr = token;
break;
case NVMF_OPT_LPWWNN:
if (match_u64(args, &token64)) {
if (fcloop_verify_addr(args) ||
match_u64(args, &token64)) {
ret = -EINVAL;
goto out_free_options;
}
opts->lpwwnn = token64;
break;
case NVMF_OPT_LPWWPN:
if (match_u64(args, &token64)) {
if (fcloop_verify_addr(args) ||
match_u64(args, &token64)) {
ret = -EINVAL;
goto out_free_options;
}
@ -141,14 +156,16 @@ fcloop_parse_nm_options(struct device *dev, u64 *nname, u64 *pname,
token = match_token(p, opt_tokens, args);
switch (token) {
case NVMF_OPT_WWNN:
if (match_u64(args, &token64)) {
if (fcloop_verify_addr(args) ||
match_u64(args, &token64)) {
ret = -EINVAL;
goto out_free_options;
}
*nname = token64;
break;
case NVMF_OPT_WWPN:
if (match_u64(args, &token64)) {
if (fcloop_verify_addr(args) ||
match_u64(args, &token64)) {
ret = -EINVAL;
goto out_free_options;
}

1
drivers/nvme/target/loop.c
View File

@ -36,7 +36,6 @@ struct nvme_loop_ctrl {
struct nvme_loop_iod async_event_iod;
struct nvme_ctrl ctrl;
struct nvmet_ctrl *target_ctrl;
struct nvmet_port *port;
};

5
drivers/nvme/target/nvmet.h
View File

@ -286,8 +286,9 @@ struct nvmet_fabrics_ops {
struct module *owner;
unsigned int type;
unsigned int msdbd;
bool has_keyed_sgls : 1;
bool metadata_support : 1;
unsigned int flags;
#define NVMF_KEYED_SGLS (1 << 0)
#define NVMF_METADATA_SUPPORTED (1 << 1)
void (*queue_response)(struct nvmet_req *req);
int (*add_port)(struct nvmet_port *port);
void (*remove_port)(struct nvmet_port *port);

3
drivers/nvme/target/rdma.c
View File

@ -1970,8 +1970,7 @@ static const struct nvmet_fabrics_ops nvmet_rdma_ops = {
.owner = THIS_MODULE,
.type = NVMF_TRTYPE_RDMA,
.msdbd = 1,
.has_keyed_sgls = 1,
.metadata_support = 1,
.flags = NVMF_KEYED_SGLS | NVMF_METADATA_SUPPORTED,
.add_port = nvmet_rdma_add_port,
.remove_port = nvmet_rdma_remove_port,
.queue_response = nvmet_rdma_queue_response,

13
drivers/nvme/target/tcp.c
View File

@ -459,17 +459,11 @@ static void nvmet_setup_response_pdu(struct nvmet_tcp_cmd *cmd)
static void nvmet_tcp_process_resp_list(struct nvmet_tcp_queue *queue)
{
struct llist_node *node;
struct nvmet_tcp_cmd *cmd;
node = llist_del_all(&queue->resp_list);
if (!node)
return;
while (node) {
struct nvmet_tcp_cmd *cmd = llist_entry(node,
struct nvmet_tcp_cmd, lentry);
for (node = llist_del_all(&queue->resp_list); node; node = node->next) {
cmd = llist_entry(node, struct nvmet_tcp_cmd, lentry);
list_add(&cmd->entry, &queue->resp_send_list);
node = node->next;
queue->send_list_len++;
}
}
@ -1717,7 +1711,6 @@ static const struct nvmet_fabrics_ops nvmet_tcp_ops = {
.owner = THIS_MODULE,
.type = NVMF_TRTYPE_TCP,
.msdbd = 1,
.has_keyed_sgls = 0,
.add_port = nvmet_tcp_add_port,
.remove_port = nvmet_tcp_remove_port,
.queue_response = nvmet_tcp_queue_response,

33
drivers/s390/block/dasd_diag.c
View File

@ -319,7 +319,7 @@ dasd_diag_check_device(struct dasd_device *device)
struct dasd_diag_characteristics *rdc_data;
struct vtoc_cms_label *label;
struct dasd_block *block;
struct dasd_diag_bio bio;
struct dasd_diag_bio *bio;
unsigned int sb, bsize;
blocknum_t end_block;
int rc;
@ -395,29 +395,36 @@ dasd_diag_check_device(struct dasd_device *device)
rc = -ENOMEM;
goto out;
}
bio = kzalloc(sizeof(*bio), GFP_KERNEL);
if (bio == NULL) {
DBF_DEV_EVENT(DBF_WARNING, device, "%s",
"No memory to allocate initialization bio");
rc = -ENOMEM;
goto out_label;
}
rc = 0;
end_block = 0;
/* try all sizes - needed for ECKD devices */
for (bsize = 512; bsize <= PAGE_SIZE; bsize <<= 1) {
mdsk_init_io(device, bsize, 0, &end_block);
memset(&bio, 0, sizeof (struct dasd_diag_bio));
bio.type = MDSK_READ_REQ;
bio.block_number = private->pt_block + 1;
bio.buffer = label;
memset(bio, 0, sizeof(*bio));
bio->type = MDSK_READ_REQ;
bio->block_number = private->pt_block + 1;
bio->buffer = label;
memset(&private->iob, 0, sizeof (struct dasd_diag_rw_io));
private->iob.dev_nr = rdc_data->dev_nr;
private->iob.key = 0;
private->iob.flags = 0; /* do synchronous io */
private->iob.block_count = 1;
private->iob.interrupt_params = 0;
private->iob.bio_list = &bio;
private->iob.bio_list = bio;
private->iob.flaga = DASD_DIAG_FLAGA_DEFAULT;
rc = dia250(&private->iob, RW_BIO);
if (rc == 3) {
pr_warn("%s: A 64-bit DIAG call failed\n",
dev_name(&device->cdev->dev));
rc = -EOPNOTSUPP;
goto out_label;
goto out_bio;
}
mdsk_term_io(device);
if (rc == 0)
@ -427,7 +434,7 @@ dasd_diag_check_device(struct dasd_device *device)
pr_warn("%s: Accessing the DASD failed because of an incorrect format (rc=%d)\n",
dev_name(&device->cdev->dev), rc);
rc = -EIO;
goto out_label;
goto out_bio;
}
/* check for label block */
if (memcmp(label->label_id, DASD_DIAG_CMS1,
@ -457,6 +464,8 @@ dasd_diag_check_device(struct dasd_device *device)
(rc == 4) ? ", read-only device" : "");
rc = 0;
}
out_bio:
kfree(bio);
out_label:
free_page((long) label);
out:
@ -506,7 +515,7 @@ static struct dasd_ccw_req *dasd_diag_build_cp(struct dasd_device *memdev,
struct req_iterator iter;
struct bio_vec bv;
char *dst;
unsigned int count, datasize;
unsigned int count;
sector_t recid, first_rec, last_rec;
unsigned int blksize, off;
unsigned char rw_cmd;
@ -534,10 +543,8 @@ static struct dasd_ccw_req *dasd_diag_build_cp(struct dasd_device *memdev,
if (count != last_rec - first_rec + 1)
return ERR_PTR(-EINVAL);
/* Build the request */
datasize = sizeof(struct dasd_diag_req) +
count*sizeof(struct dasd_diag_bio);
cqr = dasd_smalloc_request(DASD_DIAG_MAGIC, 0, datasize, memdev,
blk_mq_rq_to_pdu(req));
cqr = dasd_smalloc_request(DASD_DIAG_MAGIC, 0, struct_size(dreq, bio, count),
memdev, blk_mq_rq_to_pdu(req));
if (IS_ERR(cqr))
return cqr;

6
drivers/scsi/sd_zbc.c
View File

@ -59,6 +59,7 @@ static int sd_zbc_parse_report(struct scsi_disk *sdkp, u8 *buf,
zone.non_seq = 1;
zone.len = logical_to_sectors(sdp, get_unaligned_be64(&buf[8]));
zone.capacity = zone.len;
zone.start = logical_to_sectors(sdp, get_unaligned_be64(&buf[16]));
zone.wp = logical_to_sectors(sdp, get_unaligned_be64(&buf[24]));
if (zone.type != ZBC_ZONE_TYPE_CONV &&
@ -716,6 +717,11 @@ int sd_zbc_read_zones(struct scsi_disk *sdkp, unsigned char *buf)
/* The drive satisfies the kernel restrictions: set it up */
blk_queue_flag_set(QUEUE_FLAG_ZONE_RESETALL, q);
blk_queue_required_elevator_features(q, ELEVATOR_F_ZBD_SEQ_WRITE);
if (sdkp->zones_max_open == U32_MAX)
blk_queue_max_open_zones(q, 0);
else
blk_queue_max_open_zones(q, sdkp->zones_max_open);
blk_queue_max_active_zones(q, 0);
nr_zones = round_up(sdkp->capacity, zone_blocks) >> ilog2(zone_blocks);
/* READ16/WRITE16 is mandatory for ZBC disks */

50
include/linux/blkdev.h
View File

@ -513,6 +513,8 @@ struct request_queue {
unsigned int nr_zones;
unsigned long *conv_zones_bitmap;
unsigned long *seq_zones_wlock;
unsigned int max_open_zones;
unsigned int max_active_zones;
#endif /* CONFIG_BLK_DEV_ZONED */
/*
@ -722,6 +724,28 @@ static inline bool blk_queue_zone_is_seq(struct request_queue *q,
return true;
return !test_bit(blk_queue_zone_no(q, sector), q->conv_zones_bitmap);
}
static inline void blk_queue_max_open_zones(struct request_queue *q,
unsigned int max_open_zones)
{
q->max_open_zones = max_open_zones;
}
static inline unsigned int queue_max_open_zones(const struct request_queue *q)
{
return q->max_open_zones;
}
static inline void blk_queue_max_active_zones(struct request_queue *q,
unsigned int max_active_zones)
{
q->max_active_zones = max_active_zones;
}
static inline unsigned int queue_max_active_zones(const struct request_queue *q)
{
return q->max_active_zones;
}
#else /* CONFIG_BLK_DEV_ZONED */
static inline unsigned int blk_queue_nr_zones(struct request_queue *q)
{
@ -737,6 +761,14 @@ static inline unsigned int blk_queue_zone_no(struct request_queue *q,
{
return 0;
}
static inline unsigned int queue_max_open_zones(const struct request_queue *q)
{
return 0;
}
static inline unsigned int queue_max_active_zones(const struct request_queue *q)
{
return 0;
}
#endif /* CONFIG_BLK_DEV_ZONED */
static inline bool rq_is_sync(struct request *rq)
@ -1519,6 +1551,24 @@ static inline sector_t bdev_zone_sectors(struct block_device *bdev)
return 0;
}
static inline unsigned int bdev_max_open_zones(struct block_device *bdev)
{
struct request_queue *q = bdev_get_queue(bdev);
if (q)
return queue_max_open_zones(q);
return 0;
}
static inline unsigned int bdev_max_active_zones(struct block_device *bdev)
{
struct request_queue *q = bdev_get_queue(bdev);
if (q)
return queue_max_active_zones(q);
return 0;
}
static inline int queue_dma_alignment(const struct request_queue *q)
{
return q ? q->dma_alignment : 511;

134
include/linux/nvme.h
View File

@ -132,6 +132,7 @@ enum {
#define NVME_CAP_TIMEOUT(cap) (((cap) >> 24) & 0xff)
#define NVME_CAP_STRIDE(cap) (((cap) >> 32) & 0xf)
#define NVME_CAP_NSSRC(cap) (((cap) >> 36) & 0x1)
#define NVME_CAP_CSS(cap) (((cap) >> 37) & 0xff)
#define NVME_CAP_MPSMIN(cap) (((cap) >> 48) & 0xf)
#define NVME_CAP_MPSMAX(cap) (((cap) >> 52) & 0xf)
@ -162,7 +163,6 @@ enum {
enum {
NVME_CC_ENABLE = 1 << 0,
NVME_CC_CSS_NVM = 0 << 4,
NVME_CC_EN_SHIFT = 0,
NVME_CC_CSS_SHIFT = 4,
NVME_CC_MPS_SHIFT = 7,
@ -170,6 +170,9 @@ enum {
NVME_CC_SHN_SHIFT = 14,
NVME_CC_IOSQES_SHIFT = 16,
NVME_CC_IOCQES_SHIFT = 20,
NVME_CC_CSS_NVM = 0 << NVME_CC_CSS_SHIFT,
NVME_CC_CSS_CSI = 6 << NVME_CC_CSS_SHIFT,
NVME_CC_CSS_MASK = 7 << NVME_CC_CSS_SHIFT,
NVME_CC_AMS_RR = 0 << NVME_CC_AMS_SHIFT,
NVME_CC_AMS_WRRU = 1 << NVME_CC_AMS_SHIFT,
NVME_CC_AMS_VS = 7 << NVME_CC_AMS_SHIFT,
@ -179,6 +182,8 @@ enum {
NVME_CC_SHN_MASK = 3 << NVME_CC_SHN_SHIFT,
NVME_CC_IOSQES = NVME_NVM_IOSQES << NVME_CC_IOSQES_SHIFT,
NVME_CC_IOCQES = NVME_NVM_IOCQES << NVME_CC_IOCQES_SHIFT,
NVME_CAP_CSS_NVM = 1 << 0,
NVME_CAP_CSS_CSI = 1 << 6,
NVME_CSTS_RDY = 1 << 0,
NVME_CSTS_CFS = 1 << 1,
NVME_CSTS_NSSRO = 1 << 4,
@ -369,11 +374,37 @@ struct nvme_id_ns {
__u8 vs[3712];
};
struct nvme_zns_lbafe {
__le64 zsze;
__u8 zdes;
__u8 rsvd9[7];
};
struct nvme_id_ns_zns {
__le16 zoc;
__le16 ozcs;
__le32 mar;
__le32 mor;
__le32 rrl;
__le32 frl;
__u8 rsvd20[2796];
struct nvme_zns_lbafe lbafe[16];
__u8 rsvd3072[768];
__u8 vs[256];
};
struct nvme_id_ctrl_zns {
__u8 zasl;
__u8 rsvd1[4095];
};
enum {
NVME_ID_CNS_NS = 0x00,
NVME_ID_CNS_CTRL = 0x01,
NVME_ID_CNS_NS_ACTIVE_LIST = 0x02,
NVME_ID_CNS_NS_DESC_LIST = 0x03,
NVME_ID_CNS_CS_NS = 0x05,
NVME_ID_CNS_CS_CTRL = 0x06,
NVME_ID_CNS_NS_PRESENT_LIST = 0x10,
NVME_ID_CNS_NS_PRESENT = 0x11,
NVME_ID_CNS_CTRL_NS_LIST = 0x12,
@ -383,6 +414,11 @@ enum {
NVME_ID_CNS_UUID_LIST = 0x17,
};
enum {
NVME_CSI_NVM = 0,
NVME_CSI_ZNS = 2,
};
enum {
NVME_DIR_IDENTIFY = 0x00,
NVME_DIR_STREAMS = 0x01,
@ -435,11 +471,13 @@ struct nvme_ns_id_desc {
#define NVME_NIDT_EUI64_LEN 8
#define NVME_NIDT_NGUID_LEN 16
#define NVME_NIDT_UUID_LEN 16
#define NVME_NIDT_CSI_LEN 1
enum {
NVME_NIDT_EUI64 = 0x01,
NVME_NIDT_NGUID = 0x02,
NVME_NIDT_UUID = 0x03,
NVME_NIDT_CSI = 0x04,
};
struct nvme_smart_log {
@ -519,6 +557,27 @@ struct nvme_ana_rsp_hdr {
__le16 rsvd10[3];
};
struct nvme_zone_descriptor {
__u8 zt;
__u8 zs;
__u8 za;
__u8 rsvd3[5];
__le64 zcap;
__le64 zslba;
__le64 wp;
__u8 rsvd32[32];
};
enum {
NVME_ZONE_TYPE_SEQWRITE_REQ = 0x2,
};
struct nvme_zone_report {
__le64 nr_zones;
__u8 resv8[56];
struct nvme_zone_descriptor entries[];
};
enum {
NVME_SMART_CRIT_SPARE = 1 << 0,
NVME_SMART_CRIT_TEMPERATURE = 1 << 1,
@ -613,6 +672,9 @@ enum nvme_opcode {
nvme_cmd_resv_report = 0x0e,
nvme_cmd_resv_acquire = 0x11,
nvme_cmd_resv_release = 0x15,
nvme_cmd_zone_mgmt_send = 0x79,
nvme_cmd_zone_mgmt_recv = 0x7a,
nvme_cmd_zone_append = 0x7d,
};
#define nvme_opcode_name(opcode) { opcode, #opcode }
@ -751,6 +813,7 @@ struct nvme_rw_command {
enum {
NVME_RW_LR = 1 << 15,
NVME_RW_FUA = 1 << 14,
NVME_RW_APPEND_PIREMAP = 1 << 9,
NVME_RW_DSM_FREQ_UNSPEC = 0,
NVME_RW_DSM_FREQ_TYPICAL = 1,
NVME_RW_DSM_FREQ_RARE = 2,
@ -816,6 +879,53 @@ struct nvme_write_zeroes_cmd {
__le16 appmask;
};
enum nvme_zone_mgmt_action {
NVME_ZONE_CLOSE = 0x1,
NVME_ZONE_FINISH = 0x2,
NVME_ZONE_OPEN = 0x3,
NVME_ZONE_RESET = 0x4,
NVME_ZONE_OFFLINE = 0x5,
NVME_ZONE_SET_DESC_EXT = 0x10,
};
struct nvme_zone_mgmt_send_cmd {
__u8 opcode;
__u8 flags;
__u16 command_id;
__le32 nsid;
__le32 cdw2[2];
__le64 metadata;
union nvme_data_ptr dptr;
__le64 slba;
__le32 cdw12;
__u8 zsa;
__u8 select_all;
__u8 rsvd13[2];
__le32 cdw14[2];
};
struct nvme_zone_mgmt_recv_cmd {
__u8 opcode;
__u8 flags;
__u16 command_id;
__le32 nsid;
__le64 rsvd2[2];
union nvme_data_ptr dptr;
__le64 slba;
__le32 numd;
__u8 zra;
__u8 zrasf;
__u8 pr;
__u8 rsvd13;
__le32 cdw14[2];
};
enum {
NVME_ZRA_ZONE_REPORT = 0,
NVME_ZRASF_ZONE_REPORT_ALL = 0,
NVME_REPORT_ZONE_PARTIAL = 1,
};
/* Features */
enum {
@ -972,7 +1082,9 @@ struct nvme_identify {
__u8 cns;
__u8 rsvd3;
__le16 ctrlid;
__u32 rsvd11[5];
__u8 rsvd11[3];
__u8 csi;
__u32 rsvd12[4];
};
#define NVME_IDENTIFY_DATA_SIZE 4096
@ -1086,7 +1198,9 @@ struct nvme_get_log_page_command {
};
__le64 lpo;
};
__u32 rsvd14[2];
__u8 rsvd14[3];
__u8 csi;
__u32 rsvd15;
};
struct nvme_directive_cmd {
@ -1283,6 +1397,8 @@ struct nvme_command {
struct nvme_format_cmd format;
struct nvme_dsm_cmd dsm;
struct nvme_write_zeroes_cmd write_zeroes;
struct nvme_zone_mgmt_send_cmd zms;
struct nvme_zone_mgmt_recv_cmd zmr;
struct nvme_abort_cmd abort;
struct nvme_get_log_page_command get_log_page;
struct nvmf_common_command fabrics;
@ -1416,6 +1532,18 @@ enum {
NVME_SC_DISCOVERY_RESTART = 0x190,
NVME_SC_AUTH_REQUIRED = 0x191,
/*
* I/O Command Set Specific - Zoned commands:
*/
NVME_SC_ZONE_BOUNDARY_ERROR = 0x1b8,
NVME_SC_ZONE_FULL = 0x1b9,
NVME_SC_ZONE_READ_ONLY = 0x1ba,
NVME_SC_ZONE_OFFLINE = 0x1bb,
NVME_SC_ZONE_INVALID_WRITE = 0x1bc,
NVME_SC_ZONE_TOO_MANY_ACTIVE = 0x1bd,
NVME_SC_ZONE_TOO_MANY_OPEN = 0x1be,
NVME_SC_ZONE_INVALID_TRANSITION = 0x1bf,
/*
* Media and Data Integrity Errors:
*/

15
include/uapi/linux/blkzoned.h
View File

@ -73,6 +73,15 @@ enum blk_zone_cond {
BLK_ZONE_COND_OFFLINE = 0xF,
};
/**
* enum blk_zone_report_flags - Feature flags of reported zone descriptors.
*
* @BLK_ZONE_REP_CAPACITY: Zone descriptor has capacity field.
*/
enum blk_zone_report_flags {
BLK_ZONE_REP_CAPACITY = (1 << 0),
};
/**
* struct blk_zone - Zone descriptor for BLKREPORTZONE ioctl.
*
@ -99,7 +108,9 @@ struct blk_zone {
__u8 cond; /* Zone condition */
__u8 non_seq; /* Non-sequential write resources active */
__u8 reset; /* Reset write pointer recommended */
__u8 reserved[36];
__u8 resv[4];
__u64 capacity; /* Zone capacity in number of sectors */
__u8 reserved[24];
};
/**
@ -115,7 +126,7 @@ struct blk_zone {
struct blk_zone_report {
__u64 sector;
__u32 nr_zones;
__u8 reserved[4];
__u32 flags;
struct blk_zone zones[0];
};