diff options
33 files changed, 587 insertions, 275 deletions
diff --git a/MAINTAINERS b/MAINTAINERS index 82db3e6722bf..2c67ee25ffe6 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -24798,6 +24798,7 @@ SOFTWARE RAID (Multiple Disks) SUPPORT M: Song Liu <song@kernel.org> M: Yu Kuai <yukuai@fnnas.com> R: Li Nan <linan122@huawei.com> +R: Xiao Ni <xiao@kernel.org> L: linux-raid@vger.kernel.org S: Supported Q: https://patchwork.kernel.org/project/linux-raid/list/ diff --git a/drivers/cdrom/cdrom.c b/drivers/cdrom/cdrom.c index fc049612d6dc..62934cf4b10d 100644 --- a/drivers/cdrom/cdrom.c +++ b/drivers/cdrom/cdrom.c @@ -631,6 +631,16 @@ int register_cdrom(struct gendisk *disk, struct cdrom_device_info *cdi) WARN_ON(!cdo->generic_packet); + /* + * Propagate the drive's write support to the block layer so BLKROGET + * reflects actual write capability. Drivers that use GET CONFIGURATION + * features (CDC_MRW_W, CDC_RAM) must have called + * cdrom_probe_write_features() before register_cdrom() so the mask is + * complete here. + */ + set_disk_ro(disk, !CDROM_CAN(CDC_DVD_RAM | CDC_MRW_W | CDC_RAM | + CDC_CD_RW)); + cd_dbg(CD_REG_UNREG, "drive \"/dev/%s\" registered\n", cdi->name); mutex_lock(&cdrom_mutex); list_add(&cdi->list, &cdrom_list); @@ -742,6 +752,44 @@ static int cdrom_is_random_writable(struct cdrom_device_info *cdi, int *write) return 0; } +/* + * Probe write-related MMC features via GET CONFIGURATION and update + * cdi->mask accordingly. Drivers that populate cdi->mask from the MODE SENSE + * capabilities page (e.g. sr) should call this after those MODE SENSE bits + * have been set but before register_cdrom(), so that the full set of + * write-capability bits is known by the time register_cdrom() decides on the + * initial read-only state of the disk. + */ +void cdrom_probe_write_features(struct cdrom_device_info *cdi) +{ + int mrw, mrw_write, ram_write; + + mrw = 0; + if (!cdrom_is_mrw(cdi, &mrw_write)) + mrw = 1; + + if (CDROM_CAN(CDC_MO_DRIVE)) + ram_write = 1; + else + (void) cdrom_is_random_writable(cdi, &ram_write); + + if (mrw) + cdi->mask &= ~CDC_MRW; + else + cdi->mask |= CDC_MRW; + + if (mrw_write) + cdi->mask &= ~CDC_MRW_W; + else + cdi->mask |= CDC_MRW_W; + + if (ram_write) + cdi->mask &= ~CDC_RAM; + else + cdi->mask |= CDC_RAM; +} +EXPORT_SYMBOL(cdrom_probe_write_features); + static int cdrom_media_erasable(struct cdrom_device_info *cdi) { disc_information di; @@ -894,33 +942,8 @@ static int cdrom_is_dvd_rw(struct cdrom_device_info *cdi) */ static int cdrom_open_write(struct cdrom_device_info *cdi) { - int mrw, mrw_write, ram_write; int ret = 1; - mrw = 0; - if (!cdrom_is_mrw(cdi, &mrw_write)) - mrw = 1; - - if (CDROM_CAN(CDC_MO_DRIVE)) - ram_write = 1; - else - (void) cdrom_is_random_writable(cdi, &ram_write); - - if (mrw) - cdi->mask &= ~CDC_MRW; - else - cdi->mask |= CDC_MRW; - - if (mrw_write) - cdi->mask &= ~CDC_MRW_W; - else - cdi->mask |= CDC_MRW_W; - - if (ram_write) - cdi->mask &= ~CDC_RAM; - else - cdi->mask |= CDC_RAM; - if (CDROM_CAN(CDC_MRW_W)) ret = cdrom_mrw_open_write(cdi); else if (CDROM_CAN(CDC_DVD_RAM)) diff --git a/drivers/md/md-bitmap.c b/drivers/md/md-bitmap.c index 83378c033c72..028b9ca8ce52 100644 --- a/drivers/md/md-bitmap.c +++ b/drivers/md/md-bitmap.c @@ -216,6 +216,7 @@ struct bitmap { }; static struct workqueue_struct *md_bitmap_wq; +static struct attribute_group md_bitmap_internal_group; static int __bitmap_resize(struct bitmap *bitmap, sector_t blocks, int chunksize, bool init); @@ -2580,6 +2581,30 @@ static int bitmap_resize(struct mddev *mddev, sector_t blocks, int chunksize) return __bitmap_resize(bitmap, blocks, chunksize, false); } +static bool bitmap_none_enabled(void *data, bool flush) +{ + return false; +} + +static int bitmap_none_create(struct mddev *mddev) +{ + return 0; +} + +static int bitmap_none_load(struct mddev *mddev) +{ + return 0; +} + +static void bitmap_none_destroy(struct mddev *mddev) +{ +} + +static int bitmap_none_get_stats(void *data, struct md_bitmap_stats *stats) +{ + return -ENOENT; +} + static ssize_t location_show(struct mddev *mddev, char *page) { @@ -2618,7 +2643,11 @@ location_store(struct mddev *mddev, const char *buf, size_t len) goto out; } - bitmap_destroy(mddev); + sysfs_unmerge_group(&mddev->kobj, &md_bitmap_internal_group); + md_bitmap_destroy_nosysfs(mddev); + mddev->bitmap_id = ID_BITMAP_NONE; + if (!mddev_set_bitmap_ops_nosysfs(mddev)) + goto none_err; mddev->bitmap_info.offset = 0; if (mddev->bitmap_info.file) { struct file *f = mddev->bitmap_info.file; @@ -2654,16 +2683,25 @@ location_store(struct mddev *mddev, const char *buf, size_t len) } mddev->bitmap_info.offset = offset; - rv = bitmap_create(mddev); + md_bitmap_destroy_nosysfs(mddev); + mddev->bitmap_id = ID_BITMAP; + if (!mddev_set_bitmap_ops_nosysfs(mddev)) + goto bitmap_err; + + rv = md_bitmap_create_nosysfs(mddev); if (rv) - goto out; + goto create_err; - rv = bitmap_load(mddev); + rv = mddev->bitmap_ops->load(mddev); if (rv) { mddev->bitmap_info.offset = 0; - bitmap_destroy(mddev); - goto out; + goto load_err; } + + rv = sysfs_merge_group(&mddev->kobj, + &md_bitmap_internal_group); + if (rv) + goto merge_err; } } if (!mddev->external) { @@ -2679,6 +2717,22 @@ out: if (rv) return rv; return len; + +merge_err: + mddev->bitmap_info.offset = 0; +load_err: + md_bitmap_destroy_nosysfs(mddev); +create_err: + mddev->bitmap_info.offset = 0; + mddev->bitmap_id = ID_BITMAP_NONE; + if (!mddev_set_bitmap_ops_nosysfs(mddev)) + rv = -ENOENT; + goto out; +bitmap_err: + rv = -ENOENT; +none_err: + mddev->bitmap_info.offset = 0; + goto out; } static struct md_sysfs_entry bitmap_location = @@ -2955,8 +3009,12 @@ static struct md_sysfs_entry max_backlog_used = __ATTR(max_backlog_used, S_IRUGO | S_IWUSR, behind_writes_used_show, behind_writes_used_reset); -static struct attribute *md_bitmap_attrs[] = { +static struct attribute *md_bitmap_common_attrs[] = { &bitmap_location.attr, + NULL +}; + +static struct attribute *md_bitmap_internal_attrs[] = { &bitmap_space.attr, &bitmap_timeout.attr, &bitmap_backlog.attr, @@ -2967,9 +3025,41 @@ static struct attribute *md_bitmap_attrs[] = { NULL }; -static struct attribute_group md_bitmap_group = { +static struct attribute_group md_bitmap_common_group = { .name = "bitmap", - .attrs = md_bitmap_attrs, + .attrs = md_bitmap_common_attrs, +}; + +static struct attribute_group md_bitmap_internal_group = { + .name = "bitmap", + .attrs = md_bitmap_internal_attrs, +}; + +static const struct attribute_group *bitmap_groups[] = { + &md_bitmap_common_group, + &md_bitmap_internal_group, + NULL, +}; + +static const struct attribute_group *bitmap_none_groups[] = { + &md_bitmap_common_group, + NULL, +}; + +static struct bitmap_operations bitmap_none_ops = { + .head = { + .type = MD_BITMAP, + .id = ID_BITMAP_NONE, + .name = "none", + }, + + .enabled = bitmap_none_enabled, + .create = bitmap_none_create, + .load = bitmap_none_load, + .destroy = bitmap_none_destroy, + .get_stats = bitmap_none_get_stats, + + .groups = bitmap_none_groups, }; static struct bitmap_operations bitmap_ops = { @@ -3013,21 +3103,38 @@ static struct bitmap_operations bitmap_ops = { .set_pages = bitmap_set_pages, .free = md_bitmap_free, - .group = &md_bitmap_group, + .groups = bitmap_groups, }; int md_bitmap_init(void) { + int err; + md_bitmap_wq = alloc_workqueue("md_bitmap", WQ_MEM_RECLAIM | WQ_UNBOUND, 0); if (!md_bitmap_wq) return -ENOMEM; - return register_md_submodule(&bitmap_ops.head); + err = register_md_submodule(&bitmap_none_ops.head); + if (err) + goto err_wq; + + err = register_md_submodule(&bitmap_ops.head); + if (err) + goto err_none; + + return 0; + +err_none: + unregister_md_submodule(&bitmap_none_ops.head); +err_wq: + destroy_workqueue(md_bitmap_wq); + return err; } void md_bitmap_exit(void) { - destroy_workqueue(md_bitmap_wq); unregister_md_submodule(&bitmap_ops.head); + unregister_md_submodule(&bitmap_none_ops.head); + destroy_workqueue(md_bitmap_wq); } diff --git a/drivers/md/md-bitmap.h b/drivers/md/md-bitmap.h index b42a28fa83a0..214f623c7e79 100644 --- a/drivers/md/md-bitmap.h +++ b/drivers/md/md-bitmap.h @@ -125,7 +125,7 @@ struct bitmap_operations { void (*set_pages)(void *data, unsigned long pages); void (*free)(void *data); - struct attribute_group *group; + const struct attribute_group **groups; }; /* the bitmap API */ diff --git a/drivers/md/md-llbitmap.c b/drivers/md/md-llbitmap.c index 9e7e6b1a6f15..1adc5b117821 100644 --- a/drivers/md/md-llbitmap.c +++ b/drivers/md/md-llbitmap.c @@ -1738,6 +1738,11 @@ static struct attribute_group md_llbitmap_group = { .attrs = md_llbitmap_attrs, }; +static const struct attribute_group *md_llbitmap_groups[] = { + &md_llbitmap_group, + NULL, +}; + static struct bitmap_operations llbitmap_ops = { .head = { .type = MD_BITMAP, @@ -1774,7 +1779,7 @@ static struct bitmap_operations llbitmap_ops = { .dirty_bits = llbitmap_dirty_bits, .write_all = llbitmap_write_all, - .group = &md_llbitmap_group, + .groups = md_llbitmap_groups, }; int md_llbitmap_init(void) diff --git a/drivers/md/md.c b/drivers/md/md.c index 5fb5ae8368ba..8b568eee8743 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -396,27 +396,19 @@ bool md_handle_request(struct mddev *mddev, struct bio *bio) { check_suspended: if (is_suspended(mddev, bio)) { - DEFINE_WAIT(__wait); /* Bail out if REQ_NOWAIT is set for the bio */ if (bio->bi_opf & REQ_NOWAIT) { bio_wouldblock_error(bio); return true; } - for (;;) { - prepare_to_wait(&mddev->sb_wait, &__wait, - TASK_UNINTERRUPTIBLE); - if (!is_suspended(mddev, bio)) - break; - schedule(); - } - finish_wait(&mddev->sb_wait, &__wait); + wait_event(mddev->sb_wait, !is_suspended(mddev, bio)); } if (!percpu_ref_tryget_live(&mddev->active_io)) goto check_suspended; if (!mddev->pers->make_request(mddev, bio)) { percpu_ref_put(&mddev->active_io); - if (!mddev->gendisk && mddev->pers->prepare_suspend) + if (mddev_is_dm(mddev) && mddev->pers->prepare_suspend) return false; goto check_suspended; } @@ -687,13 +679,38 @@ static void active_io_release(struct percpu_ref *ref) static void no_op(struct percpu_ref *r) {} -static bool mddev_set_bitmap_ops(struct mddev *mddev) +static void md_bitmap_sysfs_add(struct mddev *mddev) +{ + if (sysfs_update_groups(&mddev->kobj, mddev->bitmap_ops->groups)) + pr_warn("md: cannot register extra bitmap attributes for %s\n", + mdname(mddev)); + else + /* + * Inform user with KOBJ_CHANGE about new bitmap + * attributes. + */ + kobject_uevent(&mddev->kobj, KOBJ_CHANGE); +} + +static void md_bitmap_sysfs_del(struct mddev *mddev) +{ + int nr_groups = 0; + + for (nr_groups = 0; mddev->bitmap_ops->groups[nr_groups]; nr_groups++) + ; + + while (--nr_groups >= 1) + sysfs_unmerge_group(&mddev->kobj, + mddev->bitmap_ops->groups[nr_groups]); + sysfs_remove_group(&mddev->kobj, mddev->bitmap_ops->groups[0]); +} + +bool mddev_set_bitmap_ops_nosysfs(struct mddev *mddev) { - struct bitmap_operations *old = mddev->bitmap_ops; struct md_submodule_head *head; - if (mddev->bitmap_id == ID_BITMAP_NONE || - (old && old->head.id == mddev->bitmap_id)) + if (mddev->bitmap_ops && + mddev->bitmap_ops->head.id == mddev->bitmap_id) return true; xa_lock(&md_submodule); @@ -711,18 +728,6 @@ static bool mddev_set_bitmap_ops(struct mddev *mddev) mddev->bitmap_ops = (void *)head; xa_unlock(&md_submodule); - - if (!mddev_is_dm(mddev) && mddev->bitmap_ops->group) { - if (sysfs_create_group(&mddev->kobj, mddev->bitmap_ops->group)) - pr_warn("md: cannot register extra bitmap attributes for %s\n", - mdname(mddev)); - else - /* - * Inform user with KOBJ_CHANGE about new bitmap - * attributes. - */ - kobject_uevent(&mddev->kobj, KOBJ_CHANGE); - } return true; err: @@ -730,15 +735,6 @@ err: return false; } -static void mddev_clear_bitmap_ops(struct mddev *mddev) -{ - if (!mddev_is_dm(mddev) && mddev->bitmap_ops && - mddev->bitmap_ops->group) - sysfs_remove_group(&mddev->kobj, mddev->bitmap_ops->group); - - mddev->bitmap_ops = NULL; -} - int mddev_init(struct mddev *mddev) { int err = 0; @@ -4279,7 +4275,7 @@ bitmap_type_show(struct mddev *mddev, char *page) xa_lock(&md_submodule); xa_for_each(&md_submodule, i, head) { - if (head->type != MD_BITMAP) + if (head->type != MD_BITMAP || head->id == ID_BITMAP_NONE) continue; if (mddev->bitmap_id == head->id) @@ -6059,10 +6055,7 @@ static struct attribute *md_default_attrs[] = { &md_logical_block_size.attr, NULL, }; - -static const struct attribute_group md_default_group = { - .attrs = md_default_attrs, -}; +ATTRIBUTE_GROUPS(md_default); static struct attribute *md_redundancy_attrs[] = { &md_scan_mode.attr, @@ -6087,11 +6080,6 @@ static const struct attribute_group md_redundancy_group = { .attrs = md_redundancy_attrs, }; -static const struct attribute_group *md_attr_groups[] = { - &md_default_group, - NULL, -}; - static ssize_t md_attr_show(struct kobject *kobj, struct attribute *attr, char *page) { @@ -6174,7 +6162,7 @@ static const struct sysfs_ops md_sysfs_ops = { static const struct kobj_type md_ktype = { .release = md_kobj_release, .sysfs_ops = &md_sysfs_ops, - .default_groups = md_attr_groups, + .default_groups = md_default_groups, }; int mdp_major = 0; @@ -6539,7 +6527,7 @@ out: return id; } -static int md_bitmap_create(struct mddev *mddev) +int md_bitmap_create_nosysfs(struct mddev *mddev) { enum md_submodule_id orig_id = mddev->bitmap_id; enum md_submodule_id sb_id; @@ -6548,8 +6536,10 @@ static int md_bitmap_create(struct mddev *mddev) if (mddev->bitmap_id == ID_BITMAP_NONE) return -EINVAL; - if (!mddev_set_bitmap_ops(mddev)) + if (!mddev_set_bitmap_ops_nosysfs(mddev)) { + mddev->bitmap_id = orig_id; return -ENOENT; + } err = mddev->bitmap_ops->create(mddev); if (!err) @@ -6560,37 +6550,72 @@ static int md_bitmap_create(struct mddev *mddev) * doesn't match, and mdadm is not the latest version to set * bitmap_type, set bitmap_ops based on the disk version. */ - mddev_clear_bitmap_ops(mddev); + mddev->bitmap_ops = NULL; sb_id = md_bitmap_get_id_from_sb(mddev); - if (sb_id == ID_BITMAP_NONE || sb_id == orig_id) + if (sb_id == ID_BITMAP_NONE || sb_id == orig_id) { + mddev->bitmap_id = orig_id; return err; + } pr_info("md: %s: bitmap version mismatch, switching from %d to %d\n", mdname(mddev), orig_id, sb_id); mddev->bitmap_id = sb_id; - if (!mddev_set_bitmap_ops(mddev)) { + if (!mddev_set_bitmap_ops_nosysfs(mddev)) { mddev->bitmap_id = orig_id; return -ENOENT; } err = mddev->bitmap_ops->create(mddev); if (err) { - mddev_clear_bitmap_ops(mddev); + mddev->bitmap_ops = NULL; mddev->bitmap_id = orig_id; } return err; } -static void md_bitmap_destroy(struct mddev *mddev) +static int md_bitmap_create(struct mddev *mddev) +{ + int err; + + err = md_bitmap_create_nosysfs(mddev); + if (err) + return err; + + if (!mddev_is_dm(mddev) && mddev->bitmap_ops->groups) + md_bitmap_sysfs_add(mddev); + + return 0; +} + +void md_bitmap_destroy_nosysfs(struct mddev *mddev) { if (!md_bitmap_registered(mddev)) return; mddev->bitmap_ops->destroy(mddev); - mddev_clear_bitmap_ops(mddev); + mddev->bitmap_ops = NULL; +} + +static void md_bitmap_destroy(struct mddev *mddev) +{ + if (!mddev_is_dm(mddev) && mddev->bitmap_ops && + mddev->bitmap_ops->groups) + md_bitmap_sysfs_del(mddev); + + md_bitmap_destroy_nosysfs(mddev); +} + +static void md_bitmap_set_none(struct mddev *mddev) +{ + mddev->bitmap_id = ID_BITMAP_NONE; + if (!mddev_set_bitmap_ops_nosysfs(mddev)) + return; + + if (!mddev_is_dm(mddev) && mddev->bitmap_ops->groups) + md_bitmap_sysfs_add(mddev); } int md_run(struct mddev *mddev) @@ -6713,7 +6738,7 @@ int md_run(struct mddev *mddev) } /* dm-raid expect sync_thread to be frozen until resume */ - if (mddev->gendisk) + if (!mddev_is_dm(mddev)) mddev->recovery = 0; /* may be over-ridden by personality */ @@ -6802,6 +6827,10 @@ int md_run(struct mddev *mddev) if (mddev->sb_flags) md_update_sb(mddev, 0); + if (IS_ENABLED(CONFIG_MD_BITMAP) && !mddev->bitmap_info.file && + !mddev->bitmap_info.offset) + md_bitmap_set_none(mddev); + md_new_event(); return 0; @@ -7747,7 +7776,8 @@ static int set_bitmap_file(struct mddev *mddev, int fd) { int err = 0; - if (!md_bitmap_registered(mddev)) + if (!md_bitmap_registered(mddev) || + mddev->bitmap_id == ID_BITMAP_NONE) return -EINVAL; if (mddev->pers) { @@ -7812,10 +7842,12 @@ static int set_bitmap_file(struct mddev *mddev, int fd) if (err) { md_bitmap_destroy(mddev); + md_bitmap_set_none(mddev); fd = -1; } } else if (fd < 0) { md_bitmap_destroy(mddev); + md_bitmap_set_none(mddev); } } @@ -8122,12 +8154,16 @@ static int update_array_info(struct mddev *mddev, mdu_array_info_t *info) mddev->bitmap_info.default_offset; mddev->bitmap_info.space = mddev->bitmap_info.default_space; + mddev->bitmap_id = ID_BITMAP; rv = md_bitmap_create(mddev); if (!rv) rv = mddev->bitmap_ops->load(mddev); - if (rv) + if (rv) { md_bitmap_destroy(mddev); + mddev->bitmap_info.offset = 0; + md_bitmap_set_none(mddev); + } } else { struct md_bitmap_stats stats; @@ -8155,6 +8191,7 @@ static int update_array_info(struct mddev *mddev, mdu_array_info_t *info) } md_bitmap_destroy(mddev); mddev->bitmap_info.offset = 0; + md_bitmap_set_none(mddev); } } md_update_sb(mddev, 1); @@ -9341,9 +9378,11 @@ static void md_bitmap_end(struct mddev *mddev, struct md_io_clone *md_io_clone) static void md_end_clone_io(struct bio *bio) { - struct md_io_clone *md_io_clone = bio->bi_private; + struct md_io_clone *md_io_clone = container_of(bio, struct md_io_clone, + bio_clone); struct bio *orig_bio = md_io_clone->orig_bio; struct mddev *mddev = md_io_clone->mddev; + struct completion *reshape_completion = bio->bi_private; if (bio_data_dir(orig_bio) == WRITE && md_bitmap_enabled(mddev, false)) md_bitmap_end(mddev, md_io_clone); @@ -9355,7 +9394,10 @@ static void md_end_clone_io(struct bio *bio) bio_end_io_acct(orig_bio, md_io_clone->start_time); bio_put(bio); - bio_endio(orig_bio); + if (unlikely(reshape_completion)) + complete(reshape_completion); + else + bio_endio(orig_bio); percpu_ref_put(&mddev->active_io); } @@ -9380,7 +9422,7 @@ static void md_clone_bio(struct mddev *mddev, struct bio **bio) } clone->bi_end_io = md_end_clone_io; - clone->bi_private = md_io_clone; + clone->bi_private = NULL; *bio = clone; } @@ -9391,26 +9433,6 @@ void md_account_bio(struct mddev *mddev, struct bio **bio) } EXPORT_SYMBOL_GPL(md_account_bio); -void md_free_cloned_bio(struct bio *bio) -{ - struct md_io_clone *md_io_clone = bio->bi_private; - struct bio *orig_bio = md_io_clone->orig_bio; - struct mddev *mddev = md_io_clone->mddev; - - if (bio_data_dir(orig_bio) == WRITE && md_bitmap_enabled(mddev, false)) - md_bitmap_end(mddev, md_io_clone); - - if (bio->bi_status && !orig_bio->bi_status) - orig_bio->bi_status = bio->bi_status; - - if (md_io_clone->start_time) - bio_end_io_acct(orig_bio, md_io_clone->start_time); - - bio_put(bio); - percpu_ref_put(&mddev->active_io); -} -EXPORT_SYMBOL_GPL(md_free_cloned_bio); - /* md_allow_write(mddev) * Calling this ensures that the array is marked 'active' so that writes * may proceed without blocking. It is important to call this before diff --git a/drivers/md/md.h b/drivers/md/md.h index d6f5482e2479..52c378086046 100644 --- a/drivers/md/md.h +++ b/drivers/md/md.h @@ -920,7 +920,6 @@ extern void md_finish_reshape(struct mddev *mddev); void md_submit_discard_bio(struct mddev *mddev, struct md_rdev *rdev, struct bio *bio, sector_t start, sector_t size); void md_account_bio(struct mddev *mddev, struct bio **bio); -void md_free_cloned_bio(struct bio *bio); extern bool __must_check md_flush_request(struct mddev *mddev, struct bio *bio); void md_write_metadata(struct mddev *mddev, struct md_rdev *rdev, @@ -935,6 +934,9 @@ extern void md_allow_write(struct mddev *mddev); extern void md_wait_for_blocked_rdev(struct md_rdev *rdev, struct mddev *mddev); extern void md_set_array_sectors(struct mddev *mddev, sector_t array_sectors); extern int md_check_no_bitmap(struct mddev *mddev); +bool mddev_set_bitmap_ops_nosysfs(struct mddev *mddev); +int md_bitmap_create_nosysfs(struct mddev *mddev); +void md_bitmap_destroy_nosysfs(struct mddev *mddev); extern int md_integrity_register(struct mddev *mddev); extern int strict_strtoul_scaled(const char *cp, unsigned long *res, int scale); @@ -1015,7 +1017,7 @@ static inline int mddev_suspend_and_lock(struct mddev *mddev) static inline void mddev_suspend_and_lock_nointr(struct mddev *mddev) { mddev_suspend(mddev, false); - mutex_lock(&mddev->reconfig_mutex); + mddev_lock_nointr(mddev); } static inline void mddev_unlock_and_resume(struct mddev *mddev) diff --git a/drivers/md/raid1-10.c b/drivers/md/raid1-10.c index c33099925f23..56a56a4da4f8 100644 --- a/drivers/md/raid1-10.c +++ b/drivers/md/raid1-10.c @@ -293,8 +293,13 @@ static inline bool raid1_should_read_first(struct mddev *mddev, * bio with REQ_RAHEAD or REQ_NOWAIT can fail at anytime, before such IO is * submitted to the underlying disks, hence don't record badblocks or retry * in this case. + * + * BLK_STS_INVAL means the bio was not valid for the underlying device. This + * is a user error, not a device failure, so retrying or recording bad blocks + * would be wrong. */ static inline bool raid1_should_handle_error(struct bio *bio) { - return !(bio->bi_opf & (REQ_RAHEAD | REQ_NOWAIT)); + return !(bio->bi_opf & (REQ_RAHEAD | REQ_NOWAIT)) && + bio->bi_status != BLK_STS_INVAL; } diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c index ba91f7e61920..64d970e2ef50 100644 --- a/drivers/md/raid1.c +++ b/drivers/md/raid1.c @@ -1510,21 +1510,14 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio, mddev->cluster_ops->area_resyncing(mddev, WRITE, bio->bi_iter.bi_sector, bio_end_sector(bio))) { - DEFINE_WAIT(w); if (bio->bi_opf & REQ_NOWAIT) { bio_wouldblock_error(bio); return; } - for (;;) { - prepare_to_wait(&conf->wait_barrier, - &w, TASK_IDLE); - if (!mddev->cluster_ops->area_resyncing(mddev, WRITE, - bio->bi_iter.bi_sector, - bio_end_sector(bio))) - break; - schedule(); - } - finish_wait(&conf->wait_barrier, &w); + wait_event_idle(conf->wait_barrier, + !mddev->cluster_ops->area_resyncing(mddev, WRITE, + bio->bi_iter.bi_sector, + bio_end_sector(bio))); } /* diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c index 4901ebe45c87..39085e7dd6d2 100644 --- a/drivers/md/raid10.c +++ b/drivers/md/raid10.c @@ -3791,6 +3791,8 @@ static int setup_geo(struct geom *geo, struct mddev *mddev, enum geo_type new) nc = layout & 255; fc = (layout >> 8) & 255; fo = layout & (1<<16); + if (!nc || !fc) + return -1; geo->raid_disks = disks; geo->near_copies = nc; geo->far_copies = fc; diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index 6e79829c5acb..0d76e82f4506 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -6217,7 +6217,12 @@ static bool raid5_make_request(struct mddev *mddev, struct bio * bi) mempool_free(ctx, conf->ctx_pool); if (res == STRIPE_WAIT_RESHAPE) { - md_free_cloned_bio(bi); + DECLARE_COMPLETION_ONSTACK(done); + WRITE_ONCE(bi->bi_private, &done); + + bio_endio(bi); + + wait_for_completion(&done); return false; } diff --git a/drivers/nvme/common/auth.c b/drivers/nvme/common/auth.c index 2d325fb93083..77f1d22512f8 100644 --- a/drivers/nvme/common/auth.c +++ b/drivers/nvme/common/auth.c @@ -351,18 +351,29 @@ struct nvme_dhchap_key *nvme_auth_transform_key( } EXPORT_SYMBOL_GPL(nvme_auth_transform_key); +/** + * nvme_auth_augmented_challenge() - Compute the augmented DH-HMAC-CHAP challenge + * @hmac_id: Hash algorithm identifier + * @skey: Session key + * @skey_len: Length of @skey + * @challenge: Challenge value + * @aug: Output buffer for the augmented challenge + * @hlen: Hash output length (length of @challenge and @aug) + * + * NVMe base specification 8.3.5.5.4: The augmented challenge is computed + * applying the HMAC function using the hash function H() selected by the + * HashID parameter ... with the hash of the ephemeral DH key ... as HMAC key + * to the challenge C (i.e., Ca = HMAC(H(g^xy mod p), C)). + * + * As the session key skey is already H(g^xy mod p) per section 8.3.5.5.9, use + * it directly as the HMAC key without additional hashing. + * + * Return: 0 on success, negative errno on failure. + */ int nvme_auth_augmented_challenge(u8 hmac_id, const u8 *skey, size_t skey_len, const u8 *challenge, u8 *aug, size_t hlen) { - u8 hashed_key[NVME_AUTH_MAX_DIGEST_SIZE]; - int ret; - - ret = nvme_auth_hash(hmac_id, skey, skey_len, hashed_key); - if (ret) - return ret; - ret = nvme_auth_hmac(hmac_id, hashed_key, hlen, challenge, hlen, aug); - memzero_explicit(hashed_key, sizeof(hashed_key)); - return ret; + return nvme_auth_hmac(hmac_id, skey, skey_len, challenge, hlen, aug); } EXPORT_SYMBOL_GPL(nvme_auth_augmented_challenge); @@ -403,33 +414,76 @@ int nvme_auth_gen_pubkey(struct crypto_kpp *dh_tfm, } EXPORT_SYMBOL_GPL(nvme_auth_gen_pubkey); -int nvme_auth_gen_shared_secret(struct crypto_kpp *dh_tfm, - const u8 *ctrl_key, size_t ctrl_key_len, - u8 *sess_key, size_t sess_key_len) +/** + * nvme_auth_gen_session_key() - Generate an ephemeral session key + * @dh_tfm: Diffie-Hellman transform with local private key already set + * @public_key: Peer's public key + * @public_key_len: Length of @public_key + * @sess_key: Output buffer for the session key + * @sess_key_len: Size of @sess_key buffer + * @hash_id: Hash algorithm identifier + * + * NVMe base specification 8.3.5.5.9: The session key Ks shall be computed from + * the ephemeral DH key (i.e., g^xy mod p) ... by applying the hash function + * H() selected by the HashID parameter ... (i.e., Ks = H(g^xy mod p)). + * + * Return: 0 on success, negative errno on failure. + */ +int nvme_auth_gen_session_key(struct crypto_kpp *dh_tfm, + const u8 *public_key, size_t public_key_len, + u8 *sess_key, size_t sess_key_len, u8 hash_id) { struct kpp_request *req; struct crypto_wait wait; struct scatterlist src, dst; + u8 *dh_secret; + size_t dh_secret_len, hash_len; int ret; - req = kpp_request_alloc(dh_tfm, GFP_KERNEL); - if (!req) + hash_len = nvme_auth_hmac_hash_len(hash_id); + if (!hash_len) { + pr_warn("%s: invalid hash algorithm %d\n", __func__, hash_id); + return -EINVAL; + } + + if (sess_key_len != hash_len) { + pr_warn("%s: sess_key buffer missized (%zu != %zu)\n", + __func__, sess_key_len, hash_len); + return -EINVAL; + } + + dh_secret_len = crypto_kpp_maxsize(dh_tfm); + dh_secret = kzalloc(dh_secret_len, GFP_KERNEL); + if (!dh_secret) return -ENOMEM; + req = kpp_request_alloc(dh_tfm, GFP_KERNEL); + if (!req) { + ret = -ENOMEM; + goto out_free_secret; + } + crypto_init_wait(&wait); - sg_init_one(&src, ctrl_key, ctrl_key_len); - kpp_request_set_input(req, &src, ctrl_key_len); - sg_init_one(&dst, sess_key, sess_key_len); - kpp_request_set_output(req, &dst, sess_key_len); + sg_init_one(&src, public_key, public_key_len); + kpp_request_set_input(req, &src, public_key_len); + sg_init_one(&dst, dh_secret, dh_secret_len); + kpp_request_set_output(req, &dst, dh_secret_len); kpp_request_set_callback(req, CRYPTO_TFM_REQ_MAY_BACKLOG, crypto_req_done, &wait); ret = crypto_wait_req(crypto_kpp_compute_shared_secret(req), &wait); - kpp_request_free(req); + + if (ret) + goto out_free_secret; + + ret = nvme_auth_hash(hash_id, dh_secret, dh_secret_len, sess_key); + +out_free_secret: + kfree_sensitive(dh_secret); return ret; } -EXPORT_SYMBOL_GPL(nvme_auth_gen_shared_secret); +EXPORT_SYMBOL_GPL(nvme_auth_gen_session_key); int nvme_auth_parse_key(const char *secret, struct nvme_dhchap_key **ret_key) { diff --git a/drivers/nvme/host/apple.c b/drivers/nvme/host/apple.c index ed61b97fde59..423c9c628e7b 100644 --- a/drivers/nvme/host/apple.c +++ b/drivers/nvme/host/apple.c @@ -1267,11 +1267,7 @@ static int apple_nvme_get_address(struct nvme_ctrl *ctrl, char *buf, int size) static void apple_nvme_free_ctrl(struct nvme_ctrl *ctrl) { - struct apple_nvme *anv = ctrl_to_apple_nvme(ctrl); - - if (anv->ctrl.admin_q) - blk_put_queue(anv->ctrl.admin_q); - put_device(anv->dev); + put_device(ctrl->dev); } static const struct nvme_ctrl_ops nvme_ctrl_ops = { diff --git a/drivers/nvme/host/auth.c b/drivers/nvme/host/auth.c index bbedbe181c8a..16de4499a8e7 100644 --- a/drivers/nvme/host/auth.c +++ b/drivers/nvme/host/auth.c @@ -535,11 +535,12 @@ static int nvme_auth_dhchap_setup_ctrl_response(struct nvme_ctrl *ctrl, put_unaligned_le16(chap->transaction, buf); nvme_auth_hmac_update(&hmac, buf, 2); - memset(buf, 0, 4); + *buf = chap->sc_c; nvme_auth_hmac_update(&hmac, buf, 1); nvme_auth_hmac_update(&hmac, "Controller", 10); nvme_auth_hmac_update(&hmac, ctrl->opts->subsysnqn, strlen(ctrl->opts->subsysnqn)); + memset(buf, 0, 4); nvme_auth_hmac_update(&hmac, buf, 1); nvme_auth_hmac_update(&hmac, ctrl->opts->host->nqn, strlen(ctrl->opts->host->nqn)); @@ -587,7 +588,7 @@ static int nvme_auth_dhchap_exponential(struct nvme_ctrl *ctrl, } gen_sesskey: - chap->sess_key_len = chap->host_key_len; + chap->sess_key_len = chap->hash_len; chap->sess_key = kmalloc(chap->sess_key_len, GFP_KERNEL); if (!chap->sess_key) { chap->sess_key_len = 0; @@ -595,16 +596,17 @@ gen_sesskey: return -ENOMEM; } - ret = nvme_auth_gen_shared_secret(chap->dh_tfm, - chap->ctrl_key, chap->ctrl_key_len, - chap->sess_key, chap->sess_key_len); + ret = nvme_auth_gen_session_key(chap->dh_tfm, + chap->ctrl_key, chap->ctrl_key_len, + chap->sess_key, chap->sess_key_len, + chap->hash_id); if (ret) { dev_dbg(ctrl->device, - "failed to generate shared secret, error %d\n", ret); + "failed to generate session key, error %d\n", ret); chap->status = NVME_AUTH_DHCHAP_FAILURE_INCORRECT_PAYLOAD; return ret; } - dev_dbg(ctrl->device, "shared secret %*ph\n", + dev_dbg(ctrl->device, "session key %*ph\n", (int)chap->sess_key_len, chap->sess_key); return 0; } diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 1e33af94c24b..dc388e24caad 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -454,11 +454,10 @@ void nvme_end_req(struct request *req) blk_mq_end_request(req, status); } -void nvme_complete_rq(struct request *req) +static void __nvme_complete_rq(struct request *req) { struct nvme_ctrl *ctrl = nvme_req(req)->ctrl; - trace_nvme_complete_rq(req); nvme_cleanup_cmd(req); /* @@ -493,6 +492,12 @@ void nvme_complete_rq(struct request *req) return; } } + +void nvme_complete_rq(struct request *req) +{ + trace_nvme_complete_rq(req); + __nvme_complete_rq(req); +} EXPORT_SYMBOL_GPL(nvme_complete_rq); void nvme_complete_batch_req(struct request *req) @@ -513,7 +518,7 @@ blk_status_t nvme_host_path_error(struct request *req) { nvme_req(req)->status = NVME_SC_HOST_PATH_ERROR; blk_mq_set_request_complete(req); - nvme_complete_rq(req); + __nvme_complete_rq(req); return BLK_STS_OK; } EXPORT_SYMBOL_GPL(nvme_host_path_error); @@ -3044,7 +3049,7 @@ static const struct nvme_core_quirk_entry core_quirks[] = { * * The device is left in a state where it is also not possible * to use "nvme set-feature" to disable APST, but booting with - * nvme_core.default_ps_max_latency=0 works. + * nvme_core.default_ps_max_latency_us=0 works. */ .vid = 0x1e0f, .mn = "KCD6XVUL6T40", @@ -4083,7 +4088,8 @@ static int nvme_init_ns_head(struct nvme_ns *ns, struct nvme_ns_info *info) mutex_unlock(&ctrl->subsys->lock); #ifdef CONFIG_NVME_MULTIPATH - cancel_delayed_work(&head->remove_work); + if (cancel_delayed_work(&head->remove_work)) + module_put(THIS_MODULE); #endif return 0; diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c index e1bb4707183c..e4f4528fe2a2 100644 --- a/drivers/nvme/host/fc.c +++ b/drivers/nvme/host/fc.c @@ -3968,3 +3968,4 @@ module_exit(nvme_fc_exit_module); MODULE_DESCRIPTION("NVMe host FC transport driver"); MODULE_LICENSE("GPL v2"); +MODULE_ALIAS("nvme-fc"); diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c index ba00f0b72b85..263161cb8ac0 100644 --- a/drivers/nvme/host/multipath.c +++ b/drivers/nvme/host/multipath.c @@ -231,16 +231,12 @@ bool nvme_mpath_clear_current_path(struct nvme_ns *ns) bool changed = false; int node; - if (!head) - goto out; - for_each_node(node) { if (ns == rcu_access_pointer(head->current_path[node])) { rcu_assign_pointer(head->current_path[node], NULL); changed = true; } } -out: return changed; } diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index db5fc9bf6627..9fd04cd7c5cb 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -2241,6 +2241,7 @@ release_cq: static const struct blk_mq_ops nvme_mq_admin_ops = { .queue_rq = nvme_queue_rq, .complete = nvme_pci_complete_rq, + .commit_rqs = nvme_commit_rqs, .init_hctx = nvme_admin_init_hctx, .init_request = nvme_pci_init_request, .timeout = nvme_timeout, @@ -4104,6 +4105,10 @@ static const struct pci_device_id nvme_id_table[] = { .driver_data = NVME_QUIRK_DELAY_BEFORE_CHK_RDY, }, { PCI_DEVICE(0x1c5f, 0x0540), /* Memblaze Pblaze4 adapter */ .driver_data = NVME_QUIRK_DELAY_BEFORE_CHK_RDY, }, + { PCI_DEVICE(0x1c5f, 0x0555), /* Memblaze Pblaze5 adapter */ + .driver_data = NVME_QUIRK_NO_NS_DESC_LIST, }, + { PCI_DEVICE(0x144d, 0xa808), /* Samsung PM981/983 */ + .driver_data = NVME_QUIRK_IGNORE_DEV_SUBNQN, }, { PCI_DEVICE(0x144d, 0xa821), /* Samsung PM1725 */ .driver_data = NVME_QUIRK_DELAY_BEFORE_CHK_RDY, }, { PCI_DEVICE(0x144d, 0xa822), /* Samsung PM1725a */ diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c index 57111139e84f..f77c960f7632 100644 --- a/drivers/nvme/host/rdma.c +++ b/drivers/nvme/host/rdma.c @@ -2189,6 +2189,13 @@ out_fail: nvme_rdma_reconnect_or_remove(ctrl, ret); } +static bool nvme_rdma_supports_pci_p2pdma(struct nvme_ctrl *ctrl) +{ + struct nvme_rdma_ctrl *r_ctrl = to_rdma_ctrl(ctrl); + + return ib_dma_pci_p2p_dma_supported(r_ctrl->device->dev); +} + static const struct nvme_ctrl_ops nvme_rdma_ctrl_ops = { .name = "rdma", .module = THIS_MODULE, @@ -2203,6 +2210,7 @@ static const struct nvme_ctrl_ops nvme_rdma_ctrl_ops = { .get_address = nvmf_get_address, .stop_ctrl = nvme_rdma_stop_ctrl, .get_virt_boundary = nvme_get_virt_boundary, + .supports_pci_p2pdma = nvme_rdma_supports_pci_p2pdma, }; /* @@ -2432,3 +2440,4 @@ module_exit(nvme_rdma_cleanup_module); MODULE_DESCRIPTION("NVMe host RDMA transport driver"); MODULE_LICENSE("GPL v2"); +MODULE_ALIAS("nvme-rdma"); diff --git a/drivers/nvme/host/sysfs.c b/drivers/nvme/host/sysfs.c index 7bf2e972126b..e59758616f27 100644 --- a/drivers/nvme/host/sysfs.c +++ b/drivers/nvme/host/sysfs.c @@ -883,10 +883,26 @@ static ssize_t tls_keyring_show(struct device *dev, } static DEVICE_ATTR_RO(tls_keyring); +static ssize_t tls_mode_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct nvme_ctrl *ctrl = dev_get_drvdata(dev); + const char *mode; + + if (ctrl->opts->tls) + mode = "tls"; + else + mode = "concat"; + + return sysfs_emit(buf, "%s\n", mode); +} +static DEVICE_ATTR_RO(tls_mode); + static struct attribute *nvme_tls_attrs[] = { &dev_attr_tls_key.attr, &dev_attr_tls_configured_key.attr, &dev_attr_tls_keyring.attr, + &dev_attr_tls_mode.attr, NULL, }; @@ -908,6 +924,9 @@ static umode_t nvme_tls_attrs_are_visible(struct kobject *kobj, if (a == &dev_attr_tls_keyring.attr && !ctrl->opts->keyring) return 0; + if (a == &dev_attr_tls_mode.attr && + !ctrl->opts->tls && !ctrl->opts->concat) + return 0; return a->mode; } diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c index 243dab830dc8..15d36d6a728e 100644 --- a/drivers/nvme/host/tcp.c +++ b/drivers/nvme/host/tcp.c @@ -1438,18 +1438,32 @@ static void nvme_tcp_free_queue(struct nvme_ctrl *nctrl, int qid) { struct nvme_tcp_ctrl *ctrl = to_tcp_ctrl(nctrl); struct nvme_tcp_queue *queue = &ctrl->queues[qid]; - unsigned int noreclaim_flag; + unsigned int noio_flag; if (!test_and_clear_bit(NVME_TCP_Q_ALLOCATED, &queue->flags)) return; page_frag_cache_drain(&queue->pf_cache); - noreclaim_flag = memalloc_noreclaim_save(); - /* ->sock will be released by fput() */ - fput(queue->sock->file); + /** + * Prevent memory reclaim from triggering block I/O during socket + * teardown. The socket release path fput -> tcp_close -> + * tcp_disconnect -> tcp_send_active_reset may allocate memory, and + * allowing reclaim to issue I/O could deadlock if we're being called + * from block device teardown (e.g., del_gendisk -> elevator cleanup) + * which holds locks that the I/O completion path needs. + */ + noio_flag = memalloc_noio_save(); + + /** + * Release the socket synchronously. During reset in + * nvme_reset_ctrl_work(), queue teardown is immediately followed by + * re-allocation. fput() defers socket cleanup to delayed_fput_work + * in workqueue context, which can race with new queue setup. + */ + __fput_sync(queue->sock->file); queue->sock = NULL; - memalloc_noreclaim_restore(noreclaim_flag); + memalloc_noio_restore(noio_flag); kfree(queue->pdu); mutex_destroy(&queue->send_mutex); @@ -1901,8 +1915,8 @@ err_init_connect: err_rcv_pdu: kfree(queue->pdu); err_sock: - /* ->sock will be released by fput() */ - fput(queue->sock->file); + /* Use sync variant - see nvme_tcp_free_queue() for explanation */ + __fput_sync(queue->sock->file); queue->sock = NULL; err_destroy_mutex: mutex_destroy(&queue->send_mutex); @@ -3071,3 +3085,4 @@ module_exit(nvme_tcp_cleanup_module); MODULE_DESCRIPTION("NVMe host TCP transport driver"); MODULE_LICENSE("GPL v2"); +MODULE_ALIAS("nvme-tcp"); diff --git a/drivers/nvme/target/admin-cmd.c b/drivers/nvme/target/admin-cmd.c index e4fd1caadfb0..01b799e92ae6 100644 --- a/drivers/nvme/target/admin-cmd.c +++ b/drivers/nvme/target/admin-cmd.c @@ -687,12 +687,8 @@ static void nvmet_execute_identify_ctrl(struct nvmet_req *req) id->cmic = NVME_CTRL_CMIC_MULTI_PORT | NVME_CTRL_CMIC_MULTI_CTRL | NVME_CTRL_CMIC_ANA; - /* Limit MDTS according to transport capability */ - if (ctrl->ops->get_mdts) - id->mdts = ctrl->ops->get_mdts(ctrl); - else - id->mdts = 0; - + /* Limit MDTS according to port config or transport capability */ + id->mdts = nvmet_ctrl_mdts(req); id->cntlid = cpu_to_le16(ctrl->cntlid); id->ver = cpu_to_le32(ctrl->subsys->ver); diff --git a/drivers/nvme/target/auth.c b/drivers/nvme/target/auth.c index b34610e2f19d..9a2eccdc8b13 100644 --- a/drivers/nvme/target/auth.c +++ b/drivers/nvme/target/auth.c @@ -229,9 +229,6 @@ out_unlock: void nvmet_auth_sq_free(struct nvmet_sq *sq) { cancel_delayed_work(&sq->auth_expired_work); -#ifdef CONFIG_NVME_TARGET_TCP_TLS - sq->tls_key = NULL; -#endif kfree(sq->dhchap_c1); sq->dhchap_c1 = NULL; kfree(sq->dhchap_c2); @@ -402,11 +399,12 @@ int nvmet_auth_ctrl_hash(struct nvmet_req *req, u8 *response, put_unaligned_le16(req->sq->dhchap_tid, buf); nvme_auth_hmac_update(&hmac, buf, 2); - memset(buf, 0, 4); + *buf = req->sq->sc_c; nvme_auth_hmac_update(&hmac, buf, 1); nvme_auth_hmac_update(&hmac, "Controller", 10); nvme_auth_hmac_update(&hmac, ctrl->subsys->subsysnqn, strlen(ctrl->subsys->subsysnqn)); + memset(buf, 0, 4); nvme_auth_hmac_update(&hmac, buf, 1); nvme_auth_hmac_update(&hmac, ctrl->hostnqn, strlen(ctrl->hostnqn)); nvme_auth_hmac_final(&hmac, response); @@ -449,18 +447,19 @@ int nvmet_auth_ctrl_sesskey(struct nvmet_req *req, struct nvmet_ctrl *ctrl = req->sq->ctrl; int ret; - req->sq->dhchap_skey_len = ctrl->dh_keysize; + req->sq->dhchap_skey_len = nvme_auth_hmac_hash_len(ctrl->shash_id); req->sq->dhchap_skey = kzalloc(req->sq->dhchap_skey_len, GFP_KERNEL); if (!req->sq->dhchap_skey) return -ENOMEM; - ret = nvme_auth_gen_shared_secret(ctrl->dh_tfm, - pkey, pkey_size, - req->sq->dhchap_skey, - req->sq->dhchap_skey_len); + ret = nvme_auth_gen_session_key(ctrl->dh_tfm, + pkey, pkey_size, + req->sq->dhchap_skey, + req->sq->dhchap_skey_len, + ctrl->shash_id); if (ret) - pr_debug("failed to compute shared secret, err %d\n", ret); + pr_debug("failed to compute session key, err %d\n", ret); else - pr_debug("%s: shared secret %*ph\n", __func__, + pr_debug("%s: session key %*ph\n", __func__, (int)req->sq->dhchap_skey_len, req->sq->dhchap_skey); diff --git a/drivers/nvme/target/configfs.c b/drivers/nvme/target/configfs.c index 463348c7f097..b88f897f06e2 100644 --- a/drivers/nvme/target/configfs.c +++ b/drivers/nvme/target/configfs.c @@ -301,6 +301,31 @@ static ssize_t nvmet_param_max_queue_size_store(struct config_item *item, CONFIGFS_ATTR(nvmet_, param_max_queue_size); +static ssize_t nvmet_param_mdts_show(struct config_item *item, char *page) +{ + struct nvmet_port *port = to_nvmet_port(item); + + return snprintf(page, PAGE_SIZE, "%d\n", port->mdts); +} + +static ssize_t nvmet_param_mdts_store(struct config_item *item, + const char *page, size_t count) +{ + struct nvmet_port *port = to_nvmet_port(item); + int ret; + + if (nvmet_is_port_enabled(port, __func__)) + return -EACCES; + ret = kstrtoint(page, 0, &port->mdts); + if (ret) { + pr_err("Invalid value '%s' for mdts\n", page); + return -EINVAL; + } + return count; +} + +CONFIGFS_ATTR(nvmet_, param_mdts); + #ifdef CONFIG_BLK_DEV_INTEGRITY static ssize_t nvmet_param_pi_enable_show(struct config_item *item, char *page) @@ -1995,6 +2020,7 @@ static struct configfs_attribute *nvmet_port_attrs[] = { &nvmet_attr_addr_tsas, &nvmet_attr_param_inline_data_size, &nvmet_attr_param_max_queue_size, + &nvmet_attr_param_mdts, #ifdef CONFIG_BLK_DEV_INTEGRITY &nvmet_attr_param_pi_enable, #endif @@ -2053,6 +2079,7 @@ static struct config_group *nvmet_ports_make(struct config_group *group, INIT_LIST_HEAD(&port->referrals); port->inline_data_size = -1; /* < 0 == let the transport choose */ port->max_queue_size = -1; /* < 0 == let the transport choose */ + port->mdts = -1; /* < 0 == let the transport choose */ port->disc_addr.trtype = NVMF_TRTYPE_MAX; port->disc_addr.portid = cpu_to_le16(portid); diff --git a/drivers/nvme/target/core.c b/drivers/nvme/target/core.c index 45f686175fea..62dd59b9aa4f 100644 --- a/drivers/nvme/target/core.c +++ b/drivers/nvme/target/core.c @@ -370,6 +370,14 @@ int nvmet_enable_port(struct nvmet_port *port) NVMET_MIN_QUEUE_SIZE, NVMET_MAX_QUEUE_SIZE); + /* + * If the transport didn't set the mdts properly, then clamp it to the + * target limits. Also set default values in case the transport didn't + * set it at all. + */ + if (port->mdts < 0 || port->mdts > NVMET_MAX_MDTS) + port->mdts = 0; + port->enabled = true; port->tr_ops = ops; return 0; @@ -1743,7 +1751,7 @@ static void nvmet_ctrl_free(struct kref *ref) nvmet_stop_keep_alive_timer(ctrl); - flush_work(&ctrl->async_event_work); + cancel_work_sync(&ctrl->async_event_work); cancel_work_sync(&ctrl->fatal_err_work); nvmet_destroy_auth(ctrl); diff --git a/drivers/nvme/target/fabrics-cmd-auth.c b/drivers/nvme/target/fabrics-cmd-auth.c index b9ab80c7a694..f1e613e7c63e 100644 --- a/drivers/nvme/target/fabrics-cmd-auth.c +++ b/drivers/nvme/target/fabrics-cmd-auth.c @@ -395,10 +395,9 @@ done: goto complete; } /* Final states, clear up variables */ - if (req->sq->dhchap_step == NVME_AUTH_DHCHAP_MESSAGE_FAILURE2) { - nvmet_auth_sq_free(req->sq); + nvmet_auth_sq_free(req->sq); + if (req->sq->dhchap_step == NVME_AUTH_DHCHAP_MESSAGE_FAILURE2) nvmet_ctrl_fatal_error(ctrl); - } complete: nvmet_req_complete(req, status); @@ -574,7 +573,9 @@ void nvmet_execute_auth_receive(struct nvmet_req *req) status = nvmet_copy_to_sgl(req, 0, d, al); kfree(d); done: - if (req->sq->dhchap_step == NVME_AUTH_DHCHAP_MESSAGE_FAILURE1) { + if (req->sq->dhchap_step == NVME_AUTH_DHCHAP_MESSAGE_SUCCESS2) + nvmet_auth_sq_free(req->sq); + else if (req->sq->dhchap_step == NVME_AUTH_DHCHAP_MESSAGE_FAILURE1) { nvmet_auth_sq_free(req->sq); nvmet_ctrl_fatal_error(ctrl); } diff --git a/drivers/nvme/target/nvmet.h b/drivers/nvme/target/nvmet.h index 50070cfb782a..3305a88684ec 100644 --- a/drivers/nvme/target/nvmet.h +++ b/drivers/nvme/target/nvmet.h @@ -214,6 +214,7 @@ struct nvmet_port { bool enabled; int inline_data_size; int max_queue_size; + int mdts; const struct nvmet_fabrics_ops *tr_ops; bool pi_enable; }; @@ -673,6 +674,7 @@ void nvmet_add_async_event(struct nvmet_ctrl *ctrl, u8 event_type, #define NVMET_MAX_QUEUE_SIZE 1024 #define NVMET_NR_QUEUES 128 #define NVMET_MAX_CMD(ctrl) (NVME_CAP_MQES(ctrl->cap) + 1) +#define NVMET_MAX_MDTS 255 /* * Nice round number that makes a list of nsids fit into a page. @@ -761,6 +763,17 @@ static inline bool nvmet_is_pci_ctrl(struct nvmet_ctrl *ctrl) return ctrl->port->disc_addr.trtype == NVMF_TRTYPE_PCI; } +/* Limit MDTS according to port config or transport capability */ +static inline u8 nvmet_ctrl_mdts(struct nvmet_req *req) +{ + struct nvmet_ctrl *ctrl = req->sq->ctrl; + u8 mdts = req->port->mdts; + + if (!ctrl->ops->get_mdts) + return mdts; + return min_not_zero(ctrl->ops->get_mdts(ctrl), mdts); +} + #ifdef CONFIG_NVME_TARGET_PASSTHRU void nvmet_passthru_subsys_free(struct nvmet_subsys *subsys); int nvmet_passthru_ctrl_enable(struct nvmet_subsys *subsys); diff --git a/drivers/nvme/target/tcp.c b/drivers/nvme/target/tcp.c index 4b8b02341ddc..164a564ba3b4 100644 --- a/drivers/nvme/target/tcp.c +++ b/drivers/nvme/target/tcp.c @@ -349,9 +349,7 @@ static void nvmet_tcp_free_cmd_buffers(struct nvmet_tcp_cmd *cmd) cmd->req.sg = NULL; } -static void nvmet_tcp_fatal_error(struct nvmet_tcp_queue *queue); - -static void nvmet_tcp_build_pdu_iovec(struct nvmet_tcp_cmd *cmd) +static int nvmet_tcp_build_pdu_iovec(struct nvmet_tcp_cmd *cmd) { struct bio_vec *iov = cmd->iov; struct scatterlist *sg; @@ -364,22 +362,19 @@ static void nvmet_tcp_build_pdu_iovec(struct nvmet_tcp_cmd *cmd) offset = cmd->rbytes_done; cmd->sg_idx = offset / PAGE_SIZE; sg_offset = offset % PAGE_SIZE; - if (!cmd->req.sg_cnt || cmd->sg_idx >= cmd->req.sg_cnt) { - nvmet_tcp_fatal_error(cmd->queue); - return; - } + if (!cmd->req.sg_cnt || cmd->sg_idx >= cmd->req.sg_cnt) + return -EPROTO; + sg = &cmd->req.sg[cmd->sg_idx]; sg_remaining = cmd->req.sg_cnt - cmd->sg_idx; while (length) { - if (!sg_remaining) { - nvmet_tcp_fatal_error(cmd->queue); - return; - } - if (!sg->length || sg->length <= sg_offset) { - nvmet_tcp_fatal_error(cmd->queue); - return; - } + if (!sg_remaining) + return -EPROTO; + + if (!sg->length || sg->length <= sg_offset) + return -EPROTO; + u32 iov_len = min_t(u32, length, sg->length - sg_offset); bvec_set_page(iov, sg_page(sg), iov_len, @@ -394,24 +389,29 @@ static void nvmet_tcp_build_pdu_iovec(struct nvmet_tcp_cmd *cmd) iov_iter_bvec(&cmd->recv_msg.msg_iter, ITER_DEST, cmd->iov, nr_pages, cmd->pdu_len); -} - -static void nvmet_tcp_fatal_error(struct nvmet_tcp_queue *queue) -{ - queue->rcv_state = NVMET_TCP_RECV_ERR; - if (queue->nvme_sq.ctrl) - nvmet_ctrl_fatal_error(queue->nvme_sq.ctrl); - else - kernel_sock_shutdown(queue->sock, SHUT_RDWR); + return 0; } static void nvmet_tcp_socket_error(struct nvmet_tcp_queue *queue, int status) { + /* + * Keep rcv_state at RECV_ERR even for the internal -ESHUTDOWN path. + * nvmet_tcp_handle_icreq() can return -ESHUTDOWN after the ICReq has + * already been consumed and queue teardown has started. + * + * If nvmet_tcp_data_ready() or nvmet_tcp_write_space() queues + * nvmet_tcp_io_work() again before nvmet_tcp_release_queue_work() + * cancels it, the queue must not keep that old receive state. + * Otherwise the next nvmet_tcp_io_work() run can reach + * nvmet_tcp_done_recv_pdu() and try to handle the same ICReq again. + * + * That is why queue->rcv_state needs to be updated before we return. + */ queue->rcv_state = NVMET_TCP_RECV_ERR; - if (status == -EPIPE || status == -ECONNRESET) + if (status == -EPIPE || status == -ECONNRESET || !queue->nvme_sq.ctrl) kernel_sock_shutdown(queue->sock, SHUT_RDWR); else - nvmet_tcp_fatal_error(queue); + nvmet_ctrl_fatal_error(queue->nvme_sq.ctrl); } static int nvmet_tcp_map_data(struct nvmet_tcp_cmd *cmd) @@ -887,7 +887,6 @@ static int nvmet_tcp_handle_icreq(struct nvmet_tcp_queue *queue) if (le32_to_cpu(icreq->hdr.plen) != sizeof(struct nvme_tcp_icreq_pdu)) { pr_err("bad nvme-tcp pdu length (%d)\n", le32_to_cpu(icreq->hdr.plen)); - nvmet_tcp_fatal_error(queue); return -EPROTO; } @@ -922,16 +921,29 @@ static int nvmet_tcp_handle_icreq(struct nvmet_tcp_queue *queue) iov.iov_len = sizeof(*icresp); ret = kernel_sendmsg(queue->sock, &msg, &iov, 1, iov.iov_len); if (ret < 0) { + spin_lock_bh(&queue->state_lock); + if (queue->state == NVMET_TCP_Q_DISCONNECTING) { + spin_unlock_bh(&queue->state_lock); + return -ESHUTDOWN; + } queue->state = NVMET_TCP_Q_FAILED; + spin_unlock_bh(&queue->state_lock); return ret; /* queue removal will cleanup */ } + spin_lock_bh(&queue->state_lock); + if (queue->state == NVMET_TCP_Q_DISCONNECTING) { + spin_unlock_bh(&queue->state_lock); + /* Tell nvmet_tcp_socket_error() teardown is in progress. */ + return -ESHUTDOWN; + } queue->state = NVMET_TCP_Q_LIVE; + spin_unlock_bh(&queue->state_lock); nvmet_prepare_receive_pdu(queue); return 0; } -static void nvmet_tcp_handle_req_failure(struct nvmet_tcp_queue *queue, +static int nvmet_tcp_handle_req_failure(struct nvmet_tcp_queue *queue, struct nvmet_tcp_cmd *cmd, struct nvmet_req *req) { size_t data_len = le32_to_cpu(req->cmd->common.dptr.sgl.length); @@ -947,19 +959,22 @@ static void nvmet_tcp_handle_req_failure(struct nvmet_tcp_queue *queue, if (!nvme_is_write(cmd->req.cmd) || !data_len || data_len > cmd->req.port->inline_data_size) { nvmet_prepare_receive_pdu(queue); - return; + return 0; } ret = nvmet_tcp_map_data(cmd); if (unlikely(ret)) { pr_err("queue %d: failed to map data\n", queue->idx); - nvmet_tcp_fatal_error(queue); - return; + return -EPROTO; } queue->rcv_state = NVMET_TCP_RECV_DATA; - nvmet_tcp_build_pdu_iovec(cmd); cmd->flags |= NVMET_TCP_F_INIT_FAILED; + ret = nvmet_tcp_build_pdu_iovec(cmd); + if (unlikely(ret)) + pr_err("queue %d: failed to build PDU iovec\n", queue->idx); + + return ret; } static int nvmet_tcp_handle_h2c_data_pdu(struct nvmet_tcp_queue *queue) @@ -1011,7 +1026,10 @@ static int nvmet_tcp_handle_h2c_data_pdu(struct nvmet_tcp_queue *queue) goto err_proto; } cmd->pdu_recv = 0; - nvmet_tcp_build_pdu_iovec(cmd); + if (unlikely(nvmet_tcp_build_pdu_iovec(cmd))) { + pr_err("queue %d: failed to build PDU iovec\n", queue->idx); + goto err_proto; + } queue->cmd = cmd; queue->rcv_state = NVMET_TCP_RECV_DATA; @@ -1019,7 +1037,6 @@ static int nvmet_tcp_handle_h2c_data_pdu(struct nvmet_tcp_queue *queue) err_proto: /* FIXME: use proper transport errors */ - nvmet_tcp_fatal_error(queue); return -EPROTO; } @@ -1034,7 +1051,6 @@ static int nvmet_tcp_done_recv_pdu(struct nvmet_tcp_queue *queue) if (hdr->type != nvme_tcp_icreq) { pr_err("unexpected pdu type (%d) before icreq\n", hdr->type); - nvmet_tcp_fatal_error(queue); return -EPROTO; } return nvmet_tcp_handle_icreq(queue); @@ -1043,7 +1059,6 @@ static int nvmet_tcp_done_recv_pdu(struct nvmet_tcp_queue *queue) if (unlikely(hdr->type == nvme_tcp_icreq)) { pr_err("queue %d: received icreq pdu in state %d\n", queue->idx, queue->state); - nvmet_tcp_fatal_error(queue); return -EPROTO; } @@ -1060,7 +1075,6 @@ static int nvmet_tcp_done_recv_pdu(struct nvmet_tcp_queue *queue) pr_err("queue %d: out of commands (%d) send_list_len: %d, opcode: %d", queue->idx, queue->nr_cmds, queue->send_list_len, nvme_cmd->common.opcode); - nvmet_tcp_fatal_error(queue); return -ENOMEM; } @@ -1074,17 +1088,16 @@ static int nvmet_tcp_done_recv_pdu(struct nvmet_tcp_queue *queue) le32_to_cpu(req->cmd->common.dptr.sgl.length), le16_to_cpu(req->cqe->status)); - nvmet_tcp_handle_req_failure(queue, queue->cmd, req); - return 0; + return nvmet_tcp_handle_req_failure(queue, queue->cmd, req); } ret = nvmet_tcp_map_data(queue->cmd); if (unlikely(ret)) { pr_err("queue %d: failed to map data\n", queue->idx); if (nvmet_tcp_has_inline_data(queue->cmd)) - nvmet_tcp_fatal_error(queue); - else - nvmet_req_complete(req, ret); + return -EPROTO; + + nvmet_req_complete(req, ret); ret = -EAGAIN; goto out; } @@ -1092,8 +1105,11 @@ static int nvmet_tcp_done_recv_pdu(struct nvmet_tcp_queue *queue) if (nvmet_tcp_need_data_in(queue->cmd)) { if (nvmet_tcp_has_inline_data(queue->cmd)) { queue->rcv_state = NVMET_TCP_RECV_DATA; - nvmet_tcp_build_pdu_iovec(queue->cmd); - return 0; + ret = nvmet_tcp_build_pdu_iovec(queue->cmd); + if (unlikely(ret)) + pr_err("queue %d: failed to build PDU iovec\n", + queue->idx); + return ret; } /* send back R2T */ nvmet_tcp_queue_response(&queue->cmd->req); @@ -1204,7 +1220,6 @@ recv: if (unlikely(!nvmet_tcp_pdu_valid(hdr->type))) { pr_err("unexpected pdu type %d\n", hdr->type); - nvmet_tcp_fatal_error(queue); return -EIO; } @@ -1218,16 +1233,12 @@ recv: } if (queue->hdr_digest && - nvmet_tcp_verify_hdgst(queue, &queue->pdu, hdr->hlen)) { - nvmet_tcp_fatal_error(queue); /* fatal */ + nvmet_tcp_verify_hdgst(queue, &queue->pdu, hdr->hlen)) return -EPROTO; - } if (queue->data_digest && - nvmet_tcp_check_ddgst(queue, &queue->pdu)) { - nvmet_tcp_fatal_error(queue); /* fatal */ + nvmet_tcp_check_ddgst(queue, &queue->pdu)) return -EPROTO; - } return nvmet_tcp_done_recv_pdu(queue); } @@ -1310,9 +1321,9 @@ static int nvmet_tcp_try_recv_ddgst(struct nvmet_tcp_queue *queue) queue->idx, cmd->req.cmd->common.command_id, queue->pdu.cmd.hdr.type, le32_to_cpu(cmd->recv_ddgst), le32_to_cpu(cmd->exp_ddgst)); - nvmet_req_uninit(&cmd->req); + if (!(cmd->flags & NVMET_TCP_F_INIT_FAILED)) + nvmet_req_uninit(&cmd->req); nvmet_tcp_free_cmd_buffers(cmd); - nvmet_tcp_fatal_error(queue); ret = -EPROTO; goto out; } diff --git a/drivers/nvme/target/zns.c b/drivers/nvme/target/zns.c index aeaf73b54c3a..f00921931eb6 100644 --- a/drivers/nvme/target/zns.c +++ b/drivers/nvme/target/zns.c @@ -69,7 +69,6 @@ bool nvmet_bdev_zns_enable(struct nvmet_ns *ns) void nvmet_execute_identify_ctrl_zns(struct nvmet_req *req) { u8 zasl = req->sq->ctrl->subsys->zasl; - struct nvmet_ctrl *ctrl = req->sq->ctrl; struct nvme_id_ctrl_zns *id; u16 status; @@ -79,10 +78,7 @@ void nvmet_execute_identify_ctrl_zns(struct nvmet_req *req) goto out; } - if (ctrl->ops->get_mdts) - id->zasl = min_t(u8, ctrl->ops->get_mdts(ctrl), zasl); - else - id->zasl = zasl; + id->zasl = min_not_zero(nvmet_ctrl_mdts(req), zasl); status = nvmet_copy_to_sgl(req, 0, id, sizeof(*id)); diff --git a/drivers/scsi/sr.c b/drivers/scsi/sr.c index 7adb2573f50d..c36c54ecd354 100644 --- a/drivers/scsi/sr.c +++ b/drivers/scsi/sr.c @@ -395,7 +395,7 @@ static blk_status_t sr_init_command(struct scsi_cmnd *SCpnt) switch (req_op(rq)) { case REQ_OP_WRITE: - if (!cd->writeable) + if (get_disk_ro(cd->disk)) goto out; SCpnt->cmnd[0] = WRITE_10; cd->cdi.media_written = 1; @@ -681,6 +681,7 @@ static int sr_probe(struct scsi_device *sdev) error = -ENOMEM; if (get_capabilities(cd)) goto fail_minor; + cdrom_probe_write_features(&cd->cdi); sr_vendor_init(cd); set_capacity(disk, cd->capacity); @@ -899,14 +900,6 @@ static int get_capabilities(struct scsi_cd *cd) /*else I don't think it can close its tray cd->cdi.mask |= CDC_CLOSE_TRAY; */ - /* - * if DVD-RAM, MRW-W or CD-RW, we are randomly writable - */ - if ((cd->cdi.mask & (CDC_DVD_RAM | CDC_MRW_W | CDC_RAM | CDC_CD_RW)) != - (CDC_DVD_RAM | CDC_MRW_W | CDC_RAM | CDC_CD_RW)) { - cd->writeable = 1; - } - kfree(buffer); return 0; } diff --git a/drivers/scsi/sr.h b/drivers/scsi/sr.h index dc899277b3a4..2d92f9cb6fec 100644 --- a/drivers/scsi/sr.h +++ b/drivers/scsi/sr.h @@ -35,7 +35,6 @@ typedef struct scsi_cd { struct scsi_device *device; unsigned int vendor; /* vendor code, see sr_vendor.c */ unsigned long ms_offset; /* for reading multisession-CD's */ - unsigned writeable : 1; unsigned use:1; /* is this device still supportable */ unsigned xa_flag:1; /* CD has XA sectors ? */ unsigned readcd_known:1; /* drive supports READ_CD (0xbe) */ diff --git a/include/linux/cdrom.h b/include/linux/cdrom.h index b907e6c2307d..260d7968cf72 100644 --- a/include/linux/cdrom.h +++ b/include/linux/cdrom.h @@ -108,6 +108,7 @@ int cdrom_ioctl(struct cdrom_device_info *cdi, struct block_device *bdev, extern unsigned int cdrom_check_events(struct cdrom_device_info *cdi, unsigned int clearing); +extern void cdrom_probe_write_features(struct cdrom_device_info *cdi); extern int register_cdrom(struct gendisk *disk, struct cdrom_device_info *cdi); extern void unregister_cdrom(struct cdrom_device_info *cdi); diff --git a/include/linux/nvme-auth.h b/include/linux/nvme-auth.h index 682f81046345..d674d8ab26e6 100644 --- a/include/linux/nvme-auth.h +++ b/include/linux/nvme-auth.h @@ -49,9 +49,9 @@ int nvme_auth_augmented_challenge(u8 hmac_id, const u8 *skey, size_t skey_len, int nvme_auth_gen_privkey(struct crypto_kpp *dh_tfm, u8 dh_gid); int nvme_auth_gen_pubkey(struct crypto_kpp *dh_tfm, u8 *host_key, size_t host_key_len); -int nvme_auth_gen_shared_secret(struct crypto_kpp *dh_tfm, - const u8 *ctrl_key, size_t ctrl_key_len, - u8 *sess_key, size_t sess_key_len); +int nvme_auth_gen_session_key(struct crypto_kpp *dh_tfm, + const u8 *public_key, size_t public_key_len, + u8 *sess_key, size_t sess_key_len, u8 hash_id); int nvme_auth_generate_psk(u8 hmac_id, const u8 *skey, size_t skey_len, const u8 *c1, const u8 *c2, size_t hash_len, u8 **ret_psk, size_t *ret_len); |