diff options
Diffstat (limited to 'drivers/block')
29 files changed, 483 insertions, 585 deletions
diff --git a/drivers/block/aoe/aoe.h b/drivers/block/aoe/aoe.h index 84d0fcebd6af..749ae1246f4c 100644 --- a/drivers/block/aoe/aoe.h +++ b/drivers/block/aoe/aoe.h @@ -244,3 +244,5 @@ void aoenet_exit(void); void aoenet_xmit(struct sk_buff_head *); int is_aoe_netif(struct net_device *ifp); int set_aoe_iflist(const char __user *str, size_t size); + +extern struct workqueue_struct *aoe_wq; diff --git a/drivers/block/aoe/aoeblk.c b/drivers/block/aoe/aoeblk.c index 8a91fcac6f82..348adf335217 100644 --- a/drivers/block/aoe/aoeblk.c +++ b/drivers/block/aoe/aoeblk.c @@ -435,7 +435,7 @@ err_mempool: err: spin_lock_irqsave(&d->lock, flags); d->flags &= ~DEVFL_GD_NOW; - schedule_work(&d->work); + queue_work(aoe_wq, &d->work); spin_unlock_irqrestore(&d->lock, flags); } diff --git a/drivers/block/aoe/aoecmd.c b/drivers/block/aoe/aoecmd.c index 384073ef2323..d7317425be51 100644 --- a/drivers/block/aoe/aoecmd.c +++ b/drivers/block/aoe/aoecmd.c @@ -968,7 +968,7 @@ ataid_complete(struct aoedev *d, struct aoetgt *t, unsigned char *id) d->flags |= DEVFL_NEWSIZE; else d->flags |= DEVFL_GDALLOC; - schedule_work(&d->work); + queue_work(aoe_wq, &d->work); } static void diff --git a/drivers/block/aoe/aoedev.c b/drivers/block/aoe/aoedev.c index c5753c6bfe80..b381d1c3ef32 100644 --- a/drivers/block/aoe/aoedev.c +++ b/drivers/block/aoe/aoedev.c @@ -321,7 +321,7 @@ flush(const char __user *str, size_t cnt, int exiting) specified = 1; } - flush_scheduled_work(); + flush_workqueue(aoe_wq); /* pass one: do aoedev_downdev, which might sleep */ restart1: spin_lock_irqsave(&devlist_lock, flags); @@ -520,7 +520,7 @@ freetgt(struct aoedev *d, struct aoetgt *t) void aoedev_exit(void) { - flush_scheduled_work(); + flush_workqueue(aoe_wq); flush(NULL, 0, EXITING); } diff --git a/drivers/block/aoe/aoemain.c b/drivers/block/aoe/aoemain.c index 1e4e2971171c..6238c4c87cfc 100644 --- a/drivers/block/aoe/aoemain.c +++ b/drivers/block/aoe/aoemain.c @@ -16,6 +16,7 @@ MODULE_DESCRIPTION("AoE block/char driver for 2.6.2 and newer 2.6 kernels"); MODULE_VERSION(VERSION); static struct timer_list timer; +struct workqueue_struct *aoe_wq; static void discover_timer(struct timer_list *t) { @@ -35,6 +36,7 @@ aoe_exit(void) aoechr_exit(); aoedev_exit(); aoeblk_exit(); /* free cache after de-allocating bufs */ + destroy_workqueue(aoe_wq); } static int __init @@ -42,9 +44,13 @@ aoe_init(void) { int ret; + aoe_wq = alloc_workqueue("aoe_wq", 0, 0); + if (!aoe_wq) + return -ENOMEM; + ret = aoedev_init(); if (ret) - return ret; + goto dev_fail; ret = aoechr_init(); if (ret) goto chr_fail; @@ -77,6 +83,8 @@ aoe_init(void) aoechr_exit(); chr_fail: aoedev_exit(); + dev_fail: + destroy_workqueue(aoe_wq); printk(KERN_INFO "aoe: initialisation failure.\n"); return ret; diff --git a/drivers/block/drbd/drbd_bitmap.c b/drivers/block/drbd/drbd_bitmap.c index df25eecf80af..9e060e49b3f8 100644 --- a/drivers/block/drbd/drbd_bitmap.c +++ b/drivers/block/drbd/drbd_bitmap.c @@ -683,7 +683,7 @@ int drbd_bm_resize(struct drbd_device *device, sector_t capacity, int set_new_bi } } - want = ALIGN(words*sizeof(long), PAGE_SIZE) >> PAGE_SHIFT; + want = PFN_UP(words*sizeof(long)); have = b->bm_number_of_pages; if (want == have) { D_ASSERT(device, b->bm_pages != NULL); diff --git a/drivers/block/drbd/drbd_main.c b/drivers/block/drbd/drbd_main.c index 4b0b25cc916e..2887350ae010 100644 --- a/drivers/block/drbd/drbd_main.c +++ b/drivers/block/drbd/drbd_main.c @@ -903,31 +903,6 @@ void drbd_gen_and_send_sync_uuid(struct drbd_peer_device *peer_device) } } -/* communicated if (agreed_features & DRBD_FF_WSAME) */ -static void -assign_p_sizes_qlim(struct drbd_device *device, struct p_sizes *p, - struct request_queue *q) -{ - if (q) { - p->qlim->physical_block_size = cpu_to_be32(queue_physical_block_size(q)); - p->qlim->logical_block_size = cpu_to_be32(queue_logical_block_size(q)); - p->qlim->alignment_offset = cpu_to_be32(queue_alignment_offset(q)); - p->qlim->io_min = cpu_to_be32(queue_io_min(q)); - p->qlim->io_opt = cpu_to_be32(queue_io_opt(q)); - p->qlim->discard_enabled = blk_queue_discard(q); - p->qlim->write_same_capable = 0; - } else { - q = device->rq_queue; - p->qlim->physical_block_size = cpu_to_be32(queue_physical_block_size(q)); - p->qlim->logical_block_size = cpu_to_be32(queue_logical_block_size(q)); - p->qlim->alignment_offset = 0; - p->qlim->io_min = cpu_to_be32(queue_io_min(q)); - p->qlim->io_opt = cpu_to_be32(queue_io_opt(q)); - p->qlim->discard_enabled = 0; - p->qlim->write_same_capable = 0; - } -} - int drbd_send_sizes(struct drbd_peer_device *peer_device, int trigger_reply, enum dds_flags flags) { struct drbd_device *device = peer_device->device; @@ -949,7 +924,9 @@ int drbd_send_sizes(struct drbd_peer_device *peer_device, int trigger_reply, enu memset(p, 0, packet_size); if (get_ldev_if_state(device, D_NEGOTIATING)) { - struct request_queue *q = bdev_get_queue(device->ldev->backing_bdev); + struct block_device *bdev = device->ldev->backing_bdev; + struct request_queue *q = bdev_get_queue(bdev); + d_size = drbd_get_max_capacity(device->ldev); rcu_read_lock(); u_size = rcu_dereference(device->ldev->disk_conf)->disk_size; @@ -957,14 +934,32 @@ int drbd_send_sizes(struct drbd_peer_device *peer_device, int trigger_reply, enu q_order_type = drbd_queue_order_type(device); max_bio_size = queue_max_hw_sectors(q) << 9; max_bio_size = min(max_bio_size, DRBD_MAX_BIO_SIZE); - assign_p_sizes_qlim(device, p, q); + p->qlim->physical_block_size = + cpu_to_be32(bdev_physical_block_size(bdev)); + p->qlim->logical_block_size = + cpu_to_be32(bdev_logical_block_size(bdev)); + p->qlim->alignment_offset = + cpu_to_be32(bdev_alignment_offset(bdev)); + p->qlim->io_min = cpu_to_be32(bdev_io_min(bdev)); + p->qlim->io_opt = cpu_to_be32(bdev_io_opt(bdev)); + p->qlim->discard_enabled = !!bdev_max_discard_sectors(bdev); put_ldev(device); } else { + struct request_queue *q = device->rq_queue; + + p->qlim->physical_block_size = + cpu_to_be32(queue_physical_block_size(q)); + p->qlim->logical_block_size = + cpu_to_be32(queue_logical_block_size(q)); + p->qlim->alignment_offset = 0; + p->qlim->io_min = cpu_to_be32(queue_io_min(q)); + p->qlim->io_opt = cpu_to_be32(queue_io_opt(q)); + p->qlim->discard_enabled = 0; + d_size = 0; u_size = 0; q_order_type = QUEUE_ORDERED_NONE; max_bio_size = DRBD_MAX_BIO_SIZE; /* ... multiple BIOs per peer_request */ - assign_p_sizes_qlim(device, p, NULL); } if (peer_device->connection->agreed_pro_version <= 94) @@ -3586,9 +3581,8 @@ const char *cmdname(enum drbd_packet cmd) * when we want to support more than * one PRO_VERSION */ static const char *cmdnames[] = { + [P_DATA] = "Data", - [P_WSAME] = "WriteSame", - [P_TRIM] = "Trim", [P_DATA_REPLY] = "DataReply", [P_RS_DATA_REPLY] = "RSDataReply", [P_BARRIER] = "Barrier", @@ -3599,7 +3593,6 @@ const char *cmdname(enum drbd_packet cmd) [P_DATA_REQUEST] = "DataRequest", [P_RS_DATA_REQUEST] = "RSDataRequest", [P_SYNC_PARAM] = "SyncParam", - [P_SYNC_PARAM89] = "SyncParam89", [P_PROTOCOL] = "ReportProtocol", [P_UUIDS] = "ReportUUIDs", [P_SIZES] = "ReportSizes", @@ -3607,6 +3600,7 @@ const char *cmdname(enum drbd_packet cmd) [P_SYNC_UUID] = "ReportSyncUUID", [P_AUTH_CHALLENGE] = "AuthChallenge", [P_AUTH_RESPONSE] = "AuthResponse", + [P_STATE_CHG_REQ] = "StateChgRequest", [P_PING] = "Ping", [P_PING_ACK] = "PingAck", [P_RECV_ACK] = "RecvAck", @@ -3617,23 +3611,25 @@ const char *cmdname(enum drbd_packet cmd) [P_NEG_DREPLY] = "NegDReply", [P_NEG_RS_DREPLY] = "NegRSDReply", [P_BARRIER_ACK] = "BarrierAck", - [P_STATE_CHG_REQ] = "StateChgRequest", [P_STATE_CHG_REPLY] = "StateChgReply", [P_OV_REQUEST] = "OVRequest", [P_OV_REPLY] = "OVReply", [P_OV_RESULT] = "OVResult", [P_CSUM_RS_REQUEST] = "CsumRSRequest", [P_RS_IS_IN_SYNC] = "CsumRSIsInSync", + [P_SYNC_PARAM89] = "SyncParam89", [P_COMPRESSED_BITMAP] = "CBitmap", [P_DELAY_PROBE] = "DelayProbe", [P_OUT_OF_SYNC] = "OutOfSync", - [P_RETRY_WRITE] = "RetryWrite", [P_RS_CANCEL] = "RSCancel", [P_CONN_ST_CHG_REQ] = "conn_st_chg_req", [P_CONN_ST_CHG_REPLY] = "conn_st_chg_reply", [P_PROTOCOL_UPDATE] = "protocol_update", + [P_TRIM] = "Trim", [P_RS_THIN_REQ] = "rs_thin_req", [P_RS_DEALLOCATED] = "rs_deallocated", + [P_WSAME] = "WriteSame", + [P_ZEROES] = "Zeroes", /* enum drbd_packet, but not commands - obsoleted flags: * P_MAY_IGNORE diff --git a/drivers/block/drbd/drbd_nl.c b/drivers/block/drbd/drbd_nl.c index b7216c186ba4..013d355a2033 100644 --- a/drivers/block/drbd/drbd_nl.c +++ b/drivers/block/drbd/drbd_nl.c @@ -770,6 +770,7 @@ int drbd_adm_set_role(struct sk_buff *skb, struct genl_info *info) struct set_role_parms parms; int err; enum drbd_ret_code retcode; + enum drbd_state_rv rv; retcode = drbd_adm_prepare(&adm_ctx, skb, info, DRBD_ADM_NEED_MINOR); if (!adm_ctx.reply_skb) @@ -790,14 +791,14 @@ int drbd_adm_set_role(struct sk_buff *skb, struct genl_info *info) mutex_lock(&adm_ctx.resource->adm_mutex); if (info->genlhdr->cmd == DRBD_ADM_PRIMARY) - retcode = (enum drbd_ret_code)drbd_set_role(adm_ctx.device, - R_PRIMARY, parms.assume_uptodate); + rv = drbd_set_role(adm_ctx.device, R_PRIMARY, parms.assume_uptodate); else - retcode = (enum drbd_ret_code)drbd_set_role(adm_ctx.device, - R_SECONDARY, 0); + rv = drbd_set_role(adm_ctx.device, R_SECONDARY, 0); mutex_unlock(&adm_ctx.resource->adm_mutex); genl_lock(); + drbd_adm_finish(&adm_ctx, info, rv); + return 0; out: drbd_adm_finish(&adm_ctx, info, retcode); return 0; @@ -1204,50 +1205,40 @@ static unsigned int drbd_max_discard_sectors(struct drbd_connection *connection) } static void decide_on_discard_support(struct drbd_device *device, - struct request_queue *q, - struct request_queue *b, - bool discard_zeroes_if_aligned) + struct drbd_backing_dev *bdev) { - /* q = drbd device queue (device->rq_queue) - * b = backing device queue (device->ldev->backing_bdev->bd_disk->queue), - * or NULL if diskless - */ - struct drbd_connection *connection = first_peer_device(device)->connection; - bool can_do = b ? blk_queue_discard(b) : true; - - if (can_do && connection->cstate >= C_CONNECTED && !(connection->agreed_features & DRBD_FF_TRIM)) { - can_do = false; - drbd_info(connection, "peer DRBD too old, does not support TRIM: disabling discards\n"); - } - if (can_do) { - /* We don't care for the granularity, really. - * Stacking limits below should fix it for the local - * device. Whether or not it is a suitable granularity - * on the remote device is not our problem, really. If - * you care, you need to use devices with similar - * topology on all peers. */ - blk_queue_discard_granularity(q, 512); - q->limits.max_discard_sectors = drbd_max_discard_sectors(connection); - blk_queue_flag_set(QUEUE_FLAG_DISCARD, q); - q->limits.max_write_zeroes_sectors = drbd_max_discard_sectors(connection); - } else { - blk_queue_flag_clear(QUEUE_FLAG_DISCARD, q); - blk_queue_discard_granularity(q, 0); - q->limits.max_discard_sectors = 0; - q->limits.max_write_zeroes_sectors = 0; - } -} + struct drbd_connection *connection = + first_peer_device(device)->connection; + struct request_queue *q = device->rq_queue; -static void fixup_discard_if_not_supported(struct request_queue *q) -{ - /* To avoid confusion, if this queue does not support discard, clear - * max_discard_sectors, which is what lsblk -D reports to the user. - * Older kernels got this wrong in "stack limits". - * */ - if (!blk_queue_discard(q)) { - blk_queue_max_discard_sectors(q, 0); - blk_queue_discard_granularity(q, 0); + if (bdev && !bdev_max_discard_sectors(bdev->backing_bdev)) + goto not_supported; + + if (connection->cstate >= C_CONNECTED && + !(connection->agreed_features & DRBD_FF_TRIM)) { + drbd_info(connection, + "peer DRBD too old, does not support TRIM: disabling discards\n"); + goto not_supported; } + + /* + * We don't care for the granularity, really. + * + * Stacking limits below should fix it for the local device. Whether or + * not it is a suitable granularity on the remote device is not our + * problem, really. If you care, you need to use devices with similar + * topology on all peers. + */ + blk_queue_discard_granularity(q, 512); + q->limits.max_discard_sectors = drbd_max_discard_sectors(connection); + q->limits.max_write_zeroes_sectors = + drbd_max_discard_sectors(connection); + return; + +not_supported: + blk_queue_discard_granularity(q, 0); + q->limits.max_discard_sectors = 0; + q->limits.max_write_zeroes_sectors = 0; } static void fixup_write_zeroes(struct drbd_device *device, struct request_queue *q) @@ -1273,7 +1264,6 @@ static void drbd_setup_queue_param(struct drbd_device *device, struct drbd_backi unsigned int max_segments = 0; struct request_queue *b = NULL; struct disk_conf *dc; - bool discard_zeroes_if_aligned = true; if (bdev) { b = bdev->backing_bdev->bd_disk->queue; @@ -1282,7 +1272,6 @@ static void drbd_setup_queue_param(struct drbd_device *device, struct drbd_backi rcu_read_lock(); dc = rcu_dereference(device->ldev->disk_conf); max_segments = dc->max_bio_bvecs; - discard_zeroes_if_aligned = dc->discard_zeroes_if_aligned; rcu_read_unlock(); blk_set_stacking_limits(&q->limits); @@ -1292,13 +1281,12 @@ static void drbd_setup_queue_param(struct drbd_device *device, struct drbd_backi /* This is the workaround for "bio would need to, but cannot, be split" */ blk_queue_max_segments(q, max_segments ? max_segments : BLK_MAX_SEGMENTS); blk_queue_segment_boundary(q, PAGE_SIZE-1); - decide_on_discard_support(device, q, b, discard_zeroes_if_aligned); + decide_on_discard_support(device, bdev); if (b) { blk_stack_limits(&q->limits, &b->limits, 0); disk_update_readahead(device->vdisk); } - fixup_discard_if_not_supported(q); fixup_write_zeroes(device, q); } @@ -1437,14 +1425,14 @@ static bool write_ordering_changed(struct disk_conf *a, struct disk_conf *b) static void sanitize_disk_conf(struct drbd_device *device, struct disk_conf *disk_conf, struct drbd_backing_dev *nbc) { - struct request_queue * const q = nbc->backing_bdev->bd_disk->queue; + struct block_device *bdev = nbc->backing_bdev; if (disk_conf->al_extents < DRBD_AL_EXTENTS_MIN) disk_conf->al_extents = DRBD_AL_EXTENTS_MIN; if (disk_conf->al_extents > drbd_al_extents_max(nbc)) disk_conf->al_extents = drbd_al_extents_max(nbc); - if (!blk_queue_discard(q)) { + if (!bdev_max_discard_sectors(bdev)) { if (disk_conf->rs_discard_granularity) { disk_conf->rs_discard_granularity = 0; /* disable feature */ drbd_info(device, "rs_discard_granularity feature disabled\n"); @@ -1453,16 +1441,19 @@ static void sanitize_disk_conf(struct drbd_device *device, struct disk_conf *dis if (disk_conf->rs_discard_granularity) { int orig_value = disk_conf->rs_discard_granularity; + sector_t discard_size = bdev_max_discard_sectors(bdev) << 9; + unsigned int discard_granularity = bdev_discard_granularity(bdev); int remainder; - if (q->limits.discard_granularity > disk_conf->rs_discard_granularity) - disk_conf->rs_discard_granularity = q->limits.discard_granularity; + if (discard_granularity > disk_conf->rs_discard_granularity) + disk_conf->rs_discard_granularity = discard_granularity; - remainder = disk_conf->rs_discard_granularity % q->limits.discard_granularity; + remainder = disk_conf->rs_discard_granularity % + discard_granularity; disk_conf->rs_discard_granularity += remainder; - if (disk_conf->rs_discard_granularity > q->limits.max_discard_sectors << 9) - disk_conf->rs_discard_granularity = q->limits.max_discard_sectors << 9; + if (disk_conf->rs_discard_granularity > discard_size) + disk_conf->rs_discard_granularity = discard_size; if (disk_conf->rs_discard_granularity != orig_value) drbd_info(device, "rs_discard_granularity changed to %d\n", @@ -1611,8 +1602,7 @@ int drbd_adm_disk_opts(struct sk_buff *skb, struct genl_info *info) drbd_send_sync_param(peer_device); } - synchronize_rcu(); - kfree(old_disk_conf); + kvfree_rcu(old_disk_conf); kfree(old_plan); mod_timer(&device->request_timer, jiffies + HZ); goto success; @@ -2443,8 +2433,7 @@ int drbd_adm_net_opts(struct sk_buff *skb, struct genl_info *info) mutex_unlock(&connection->resource->conf_update); mutex_unlock(&connection->data.mutex); - synchronize_rcu(); - kfree(old_net_conf); + kvfree_rcu(old_net_conf); if (connection->cstate >= C_WF_REPORT_PARAMS) { struct drbd_peer_device *peer_device; @@ -2502,6 +2491,7 @@ int drbd_adm_connect(struct sk_buff *skb, struct genl_info *info) struct drbd_resource *resource; struct drbd_connection *connection; enum drbd_ret_code retcode; + enum drbd_state_rv rv; int i; int err; @@ -2621,12 +2611,11 @@ int drbd_adm_connect(struct sk_buff *skb, struct genl_info *info) } rcu_read_unlock(); - retcode = (enum drbd_ret_code)conn_request_state(connection, - NS(conn, C_UNCONNECTED), CS_VERBOSE); + rv = conn_request_state(connection, NS(conn, C_UNCONNECTED), CS_VERBOSE); conn_reconfig_done(connection); mutex_unlock(&adm_ctx.resource->adm_mutex); - drbd_adm_finish(&adm_ctx, info, retcode); + drbd_adm_finish(&adm_ctx, info, rv); return 0; fail: @@ -2734,11 +2723,12 @@ int drbd_adm_disconnect(struct sk_buff *skb, struct genl_info *info) mutex_lock(&adm_ctx.resource->adm_mutex); rv = conn_try_disconnect(connection, parms.force_disconnect); - if (rv < SS_SUCCESS) - retcode = (enum drbd_ret_code)rv; - else - retcode = NO_ERROR; mutex_unlock(&adm_ctx.resource->adm_mutex); + if (rv < SS_SUCCESS) { + drbd_adm_finish(&adm_ctx, info, rv); + return 0; + } + retcode = NO_ERROR; fail: drbd_adm_finish(&adm_ctx, info, retcode); return 0; @@ -2857,8 +2847,7 @@ int drbd_adm_resize(struct sk_buff *skb, struct genl_info *info) new_disk_conf->disk_size = (sector_t)rs.resize_size; rcu_assign_pointer(device->ldev->disk_conf, new_disk_conf); mutex_unlock(&device->resource->conf_update); - synchronize_rcu(); - kfree(old_disk_conf); + kvfree_rcu(old_disk_conf); new_disk_conf = NULL; } diff --git a/drivers/block/drbd/drbd_receiver.c b/drivers/block/drbd/drbd_receiver.c index 08da922f81d1..6762be53f409 100644 --- a/drivers/block/drbd/drbd_receiver.c +++ b/drivers/block/drbd/drbd_receiver.c @@ -364,7 +364,7 @@ drbd_alloc_peer_req(struct drbd_peer_device *peer_device, u64 id, sector_t secto struct drbd_device *device = peer_device->device; struct drbd_peer_request *peer_req; struct page *page = NULL; - unsigned nr_pages = (payload_size + PAGE_SIZE -1) >> PAGE_SHIFT; + unsigned int nr_pages = PFN_UP(payload_size); if (drbd_insert_fault(device, DRBD_FAULT_AL_EE)) return NULL; @@ -1511,7 +1511,6 @@ void drbd_bump_write_ordering(struct drbd_resource *resource, struct drbd_backin int drbd_issue_discard_or_zero_out(struct drbd_device *device, sector_t start, unsigned int nr_sectors, int flags) { struct block_device *bdev = device->ldev->backing_bdev; - struct request_queue *q = bdev_get_queue(bdev); sector_t tmp, nr; unsigned int max_discard_sectors, granularity; int alignment; @@ -1521,10 +1520,10 @@ int drbd_issue_discard_or_zero_out(struct drbd_device *device, sector_t start, u goto zero_out; /* Zero-sector (unknown) and one-sector granularities are the same. */ - granularity = max(q->limits.discard_granularity >> 9, 1U); + granularity = max(bdev_discard_granularity(bdev) >> 9, 1U); alignment = (bdev_discard_alignment(bdev) >> 9) % granularity; - max_discard_sectors = min(q->limits.max_discard_sectors, (1U << 22)); + max_discard_sectors = min(bdev_max_discard_sectors(bdev), (1U << 22)); max_discard_sectors -= max_discard_sectors % granularity; if (unlikely(!max_discard_sectors)) goto zero_out; @@ -1548,7 +1547,8 @@ int drbd_issue_discard_or_zero_out(struct drbd_device *device, sector_t start, u start = tmp; } while (nr_sectors >= max_discard_sectors) { - err |= blkdev_issue_discard(bdev, start, max_discard_sectors, GFP_NOIO, 0); + err |= blkdev_issue_discard(bdev, start, max_discard_sectors, + GFP_NOIO); nr_sectors -= max_discard_sectors; start += max_discard_sectors; } @@ -1560,7 +1560,7 @@ int drbd_issue_discard_or_zero_out(struct drbd_device *device, sector_t start, u nr = nr_sectors; nr -= (unsigned int)nr % granularity; if (nr) { - err |= blkdev_issue_discard(bdev, start, nr, GFP_NOIO, 0); + err |= blkdev_issue_discard(bdev, start, nr, GFP_NOIO); nr_sectors -= nr; start += nr; } @@ -1575,11 +1575,10 @@ int drbd_issue_discard_or_zero_out(struct drbd_device *device, sector_t start, u static bool can_do_reliable_discards(struct drbd_device *device) { - struct request_queue *q = bdev_get_queue(device->ldev->backing_bdev); struct disk_conf *dc; bool can_do; - if (!blk_queue_discard(q)) + if (!bdev_max_discard_sectors(device->ldev->backing_bdev)) return false; rcu_read_lock(); @@ -1629,9 +1628,9 @@ int drbd_submit_peer_request(struct drbd_device *device, struct bio *bio; struct page *page = peer_req->pages; sector_t sector = peer_req->i.sector; - unsigned data_size = peer_req->i.size; - unsigned n_bios = 0; - unsigned nr_pages = (data_size + PAGE_SIZE -1) >> PAGE_SHIFT; + unsigned int data_size = peer_req->i.size; + unsigned int n_bios = 0; + unsigned int nr_pages = PFN_UP(data_size); /* TRIM/DISCARD: for now, always use the helper function * blkdev_issue_zeroout(..., discard=true). @@ -3751,8 +3750,7 @@ static int receive_protocol(struct drbd_connection *connection, struct packet_in drbd_info(connection, "peer data-integrity-alg: %s\n", integrity_alg[0] ? integrity_alg : "(none)"); - synchronize_rcu(); - kfree(old_net_conf); + kvfree_rcu(old_net_conf); return 0; disconnect_rcu_unlock: @@ -3903,7 +3901,6 @@ static int receive_SyncParam(struct drbd_connection *connection, struct packet_i drbd_err(device, "verify-alg of wrong size, " "peer wants %u, accepting only up to %u byte\n", data_size, SHARED_SECRET_MAX); - err = -EIO; goto reconnect; } @@ -4121,8 +4118,7 @@ static int receive_sizes(struct drbd_connection *connection, struct packet_info rcu_assign_pointer(device->ldev->disk_conf, new_disk_conf); mutex_unlock(&connection->resource->conf_update); - synchronize_rcu(); - kfree(old_disk_conf); + kvfree_rcu(old_disk_conf); drbd_info(device, "Peer sets u_size to %lu sectors (old: %lu)\n", (unsigned long)p_usize, (unsigned long)my_usize); diff --git a/drivers/block/drbd/drbd_req.c b/drivers/block/drbd/drbd_req.c index 75be0e16770a..e64bcfba30ef 100644 --- a/drivers/block/drbd/drbd_req.c +++ b/drivers/block/drbd/drbd_req.c @@ -922,7 +922,7 @@ static bool remote_due_to_read_balancing(struct drbd_device *device, sector_t se switch (rbm) { case RB_CONGESTED_REMOTE: - return 0; + return false; case RB_LEAST_PENDING: return atomic_read(&device->local_cnt) > atomic_read(&device->ap_pending_cnt) + atomic_read(&device->rs_pending_cnt); diff --git a/drivers/block/drbd/drbd_state.c b/drivers/block/drbd/drbd_state.c index 4ee11aef6672..3f7bf9f2d874 100644 --- a/drivers/block/drbd/drbd_state.c +++ b/drivers/block/drbd/drbd_state.c @@ -2071,8 +2071,7 @@ static int w_after_conn_state_ch(struct drbd_work *w, int unused) conn_free_crypto(connection); mutex_unlock(&connection->resource->conf_update); - synchronize_rcu(); - kfree(old_conf); + kvfree_rcu(old_conf); } if (ns_max.susp_fen) { diff --git a/drivers/block/drbd/drbd_worker.c b/drivers/block/drbd/drbd_worker.c index 0f9956f4e9c4..af3051dd8912 100644 --- a/drivers/block/drbd/drbd_worker.c +++ b/drivers/block/drbd/drbd_worker.c @@ -1030,7 +1030,7 @@ static void move_to_net_ee_or_free(struct drbd_device *device, struct drbd_peer_ { if (drbd_peer_req_has_active_page(peer_req)) { /* This might happen if sendpage() has not finished */ - int i = (peer_req->i.size + PAGE_SIZE -1) >> PAGE_SHIFT; + int i = PFN_UP(peer_req->i.size); atomic_add(i, &device->pp_in_use_by_net); atomic_sub(i, &device->pp_in_use); spin_lock_irq(&device->resource->req_lock); diff --git a/drivers/block/loop.c b/drivers/block/loop.c index a58595f5ee2c..e2cb51810e89 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -1,54 +1,7 @@ +// SPDX-License-Identifier: GPL-2.0-only /* - * linux/drivers/block/loop.c - * - * Written by Theodore Ts'o, 3/29/93 - * - * Copyright 1993 by Theodore Ts'o. Redistribution of this file is - * permitted under the GNU General Public License. - * - * DES encryption plus some minor changes by Werner Almesberger, 30-MAY-1993 - * more DES encryption plus IDEA encryption by Nicholas J. Leon, June 20, 1996 - * - * Modularized and updated for 1.1.16 kernel - Mitch Dsouza 28th May 1994 - * Adapted for 1.3.59 kernel - Andries Brouwer, 1 Feb 1996 - * - * Fixed do_loop_request() re-entrancy - Vincent.Renardias@waw.com Mar 20, 1997 - * - * Added devfs support - Richard Gooch <rgooch@atnf.csiro.au> 16-Jan-1998 - * - * Handle sparse backing files correctly - Kenn Humborg, Jun 28, 1998 - * - * Loadable modules and other fixes by AK, 1998 - * - * Make real block number available to downstream transfer functions, enables - * CBC (and relatives) mode encryption requiring unique IVs per data block. - * Reed H. Petty, rhp@draper.net - * - * Maximum number of loop devices now dynamic via max_loop module parameter. - * Russell Kroll <rkroll@exploits.org> 19990701 - * - * Maximum number of loop devices when compiled-in now selectable by passing - * max_loop=<1-255> to the kernel on boot. - * Erik I. Bolsø, <eriki@himolde.no>, Oct 31, 1999 - * - * Completely rewrite request handling to be make_request_fn style and - * non blocking, pushing work to a helper thread. Lots of fixes from - * Al Viro too. - * Jens Axboe <axboe@suse.de>, Nov 2000 - * - * Support up to 256 loop devices - * Heinz Mauelshagen <mge@sistina.com>, Feb 2002 - * - * Support for falling back on the write file operation when the address space - * operations write_begin is not available on the backing filesystem. - * Anton Altaparmakov, 16 Feb 2005 - * - * Still To Fix: - * - Advisory locking is ignored here. - * - Should use an own CAP_* category instead of CAP_SYS_ADMIN - * + * Copyright 1993 by Theodore Ts'o. */ - #include <linux/module.h> #include <linux/moduleparam.h> #include <linux/sched.h> @@ -59,7 +12,6 @@ #include <linux/errno.h> #include <linux/major.h> #include <linux/wait.h> -#include <linux/blkdev.h> #include <linux/blkpg.h> #include <linux/init.h> #include <linux/swap.h> @@ -80,10 +32,62 @@ #include <linux/blk-cgroup.h> #include <linux/sched/mm.h> #include <linux/statfs.h> +#include <linux/uaccess.h> +#include <linux/blk-mq.h> +#include <linux/spinlock.h> +#include <uapi/linux/loop.h> + +/* Possible states of device */ +enum { + Lo_unbound, + Lo_bound, + Lo_rundown, + Lo_deleting, +}; -#include "loop.h" +struct loop_func_table; + +struct loop_device { + int lo_number; + loff_t lo_offset; + loff_t lo_sizelimit; + int lo_flags; + char lo_file_name[LO_NAME_SIZE]; + + struct file * lo_backing_file; + struct block_device *lo_device; + + gfp_t old_gfp_mask; + + spinlock_t lo_lock; + int lo_state; + spinlock_t lo_work_lock; + struct workqueue_struct *workqueue; + struct work_struct rootcg_work; + struct list_head rootcg_cmd_list; + struct list_head idle_worker_list; + struct rb_root worker_tree; + struct timer_list timer; + bool use_dio; + bool sysfs_inited; + + struct request_queue *lo_queue; + struct blk_mq_tag_set tag_set; + struct gendisk *lo_disk; + struct mutex lo_mutex; + bool idr_visible; +}; -#include <linux/uaccess.h> +struct loop_cmd { + struct list_head list_entry; + bool use_aio; /* use AIO interface to handle I/O */ + atomic_t ref; /* only for aio */ + long ret; + struct kiocb iocb; + struct bio_vec *bvec; + struct cgroup_subsys_state *blkcg_css; + struct cgroup_subsys_state *memcg_css; +}; #define LOOP_IDLE_WORKER_TIMEOUT (60 * HZ) #define LOOP_DEFAULT_HW_Q_DEPTH (128) @@ -314,15 +318,12 @@ static int lo_fallocate(struct loop_device *lo, struct request *rq, loff_t pos, mode |= FALLOC_FL_KEEP_SIZE; - if (!blk_queue_discard(lo->lo_queue)) { - ret = -EOPNOTSUPP; - goto out; - } + if (!bdev_max_discard_sectors(lo->lo_device)) + return -EOPNOTSUPP; ret = file->f_op->fallocate(file, mode, pos, blk_rq_bytes(rq)); if (unlikely(ret && ret != -EINVAL && ret != -EOPNOTSUPP)) - ret = -EIO; - out: + return -EIO; return ret; } @@ -572,6 +573,10 @@ static int loop_change_fd(struct loop_device *lo, struct block_device *bdev, if (!file) return -EBADF; + + /* suppress uevents while reconfiguring the device */ + dev_set_uevent_suppress(disk_to_dev(lo->lo_disk), 1); + is_loop = is_loop_device(file); error = loop_global_lock_killable(lo, is_loop); if (error) @@ -626,13 +631,18 @@ static int loop_change_fd(struct loop_device *lo, struct block_device *bdev, fput(old_file); if (partscan) loop_reread_partitions(lo); - return 0; + + error = 0; +done: + /* enable and uncork uevent now that we are done */ + dev_set_uevent_suppress(disk_to_dev(lo->lo_disk), 0); + return error; out_err: loop_global_unlock(lo, is_loop); out_putf: fput(file); - return error; + goto done; } /* loop sysfs attributes */ @@ -762,7 +772,7 @@ static void loop_config_discard(struct loop_device *lo) struct request_queue *backingq = bdev_get_queue(I_BDEV(inode)); max_discard_sectors = backingq->limits.max_write_zeroes_sectors; - granularity = backingq->limits.discard_granularity ?: + granularity = bdev_discard_granularity(I_BDEV(inode)) ?: queue_physical_block_size(backingq); /* @@ -787,14 +797,11 @@ static void loop_config_discard(struct loop_device *lo) q->limits.discard_granularity = granularity; blk_queue_max_discard_sectors(q, max_discard_sectors); blk_queue_max_write_zeroes_sectors(q, max_discard_sectors); - blk_queue_flag_set(QUEUE_FLAG_DISCARD, q); } else { q->limits.discard_granularity = 0; blk_queue_max_discard_sectors(q, 0); blk_queue_max_write_zeroes_sectors(q, 0); - blk_queue_flag_clear(QUEUE_FLAG_DISCARD, q); } - q->limits.discard_alignment = 0; } struct loop_worker { @@ -808,8 +815,6 @@ struct loop_worker { }; static void loop_workfn(struct work_struct *work); -static void loop_rootcg_workfn(struct work_struct *work); -static void loop_free_idle_workers(struct timer_list *timer); #ifdef CONFIG_BLK_CGROUP static inline int queue_on_root_worker(struct cgroup_subsys_state *css) @@ -893,6 +898,39 @@ queue_work: spin_unlock_irq(&lo->lo_work_lock); } +static void loop_set_timer(struct loop_device *lo) +{ + timer_reduce(&lo->timer, jiffies + LOOP_IDLE_WORKER_TIMEOUT); +} + +static void loop_free_idle_workers(struct loop_device *lo, bool delete_all) +{ + struct loop_worker *pos, *worker; + + spin_lock_irq(&lo->lo_work_lock); + list_for_each_entry_safe(worker, pos, &lo->idle_worker_list, + idle_list) { + if (!delete_all && + time_is_after_jiffies(worker->last_ran_at + + LOOP_IDLE_WORKER_TIMEOUT)) + break; + list_del(&worker->idle_list); + rb_erase(&worker->rb_node, &lo->worker_tree); + css_put(worker->blkcg_css); + kfree(worker); + } + if (!list_empty(&lo->idle_worker_list)) + loop_set_timer(lo); + spin_unlock_irq(&lo->lo_work_lock); +} + +static void loop_free_idle_workers_timer(struct timer_list *timer) +{ + struct loop_device *lo = container_of(timer, struct loop_device, timer); + + return loop_free_idle_workers(lo, false); +} + static void loop_update_rotational(struct loop_device *lo) { struct file *file = lo->lo_backing_file; @@ -903,7 +941,7 @@ static void loop_update_rotational(struct loop_device *lo) /* not all filesystems (e.g. tmpfs) have a sb->s_bdev */ if (file_bdev) - nonrot = blk_queue_nonrot(bdev_get_queue(file_bdev)); + nonrot = bdev_nonrot(file_bdev); if (nonrot) blk_queue_flag_set(QUEUE_FLAG_NONROT, q); @@ -967,6 +1005,9 @@ static int loop_configure(struct loop_device *lo, fmode_t mode, /* This is safe, since we have a reference from open(). */ __module_get(THIS_MODULE); + /* suppress uevents while reconfiguring the device */ + dev_set_uevent_suppress(disk_to_dev(lo->lo_disk), 1); + /* * If we don't hold exclusive handle for the device, upgrade to it * here to avoid changing device under exclusive owner. @@ -1011,24 +1052,19 @@ static int loop_configure(struct loop_device *lo, fmode_t mode, !file->f_op->write_iter) lo->lo_flags |= LO_FLAGS_READ_ONLY; - lo->workqueue = alloc_workqueue("loop%d", - WQ_UNBOUND | WQ_FREEZABLE, - 0, - lo->lo_number); if (!lo->workqueue) { - error = -ENOMEM; - goto out_unlock; + lo->workqueue = alloc_workqueue("loop%d", + WQ_UNBOUND | WQ_FREEZABLE, + 0, lo->lo_number); + if (!lo->workqueue) { + error = -ENOMEM; + goto out_unlock; + } } disk_force_media_change(lo->lo_disk, DISK_EVENT_MEDIA_CHANGE); set_disk_ro(lo->lo_disk, (lo->lo_flags & LO_FLAGS_READ_ONLY) != 0); - INIT_WORK(&lo->rootcg_work, loop_rootcg_workfn); - INIT_LIST_HEAD(&lo->rootcg_cmd_list); - INIT_LIST_HEAD(&lo->idle_worker_list); - lo->worker_tree = RB_ROOT; - timer_setup(&lo->timer, loop_free_idle_workers, - TIMER_DEFERRABLE); lo->use_dio = lo->lo_flags & LO_FLAGS_DIRECT_IO; lo->lo_device = bdev; lo->lo_backing_file = file; @@ -1073,7 +1109,12 @@ static int loop_configure(struct loop_device *lo, fmode_t mode, loop_reread_partitions(lo); if (!(mode & FMODE_EXCL)) bd_abort_claiming(bdev, loop_configure); - return 0; + + error = 0; +done: + /* enable and uncork uevent now that we are done */ + dev_set_uevent_suppress(disk_to_dev(lo->lo_disk), 0); + return error; out_unlock: loop_global_unlock(lo, is_loop); @@ -1084,53 +1125,24 @@ out_putf: fput(file); /* This is safe: open() is still holding a reference. */ module_put(THIS_MODULE); - return error; + goto done; } static void __loop_clr_fd(struct loop_device *lo, bool release) { struct file *filp; gfp_t gfp = lo->old_gfp_mask; - struct loop_worker *pos, *worker; - - /* - * Flush loop_configure() and loop_change_fd(). It is acceptable for - * loop_validate_file() to succeed, for actual clear operation has not - * started yet. - */ - mutex_lock(&loop_validate_mutex); - mutex_unlock(&loop_validate_mutex); - /* - * loop_validate_file() now fails because l->lo_state != Lo_bound - * became visible. - */ - - /* - * Since this function is called upon "ioctl(LOOP_CLR_FD)" xor "close() - * after ioctl(LOOP_CLR_FD)", it is a sign of something going wrong if - * lo->lo_state has changed while waiting for lo->lo_mutex. - */ - mutex_lock(&lo->lo_mutex); - BUG_ON(lo->lo_state != Lo_rundown); - mutex_unlock(&lo->lo_mutex); if (test_bit(QUEUE_FLAG_WC, &lo->lo_queue->queue_flags)) blk_queue_write_cache(lo->lo_queue, false, false); - /* freeze request queue during the transition */ - blk_mq_freeze_queue(lo->lo_queue); - - destroy_workqueue(lo->workqueue); - spin_lock_irq(&lo->lo_work_lock); - list_for_each_entry_safe(worker, pos, &lo->idle_worker_list, - idle_list) { - list_del(&worker->idle_list); - rb_erase(&worker->rb_node, &lo->worker_tree); - css_put(worker->blkcg_css); - kfree(worker); - } - spin_unlock_irq(&lo->lo_work_lock); - del_timer_sync(&lo->timer); + /* + * Freeze the request queue when unbinding on a live file descriptor and + * thus an open device. When called from ->release we are guaranteed + * that there is no I/O in progress already. + */ + if (!release) + blk_mq_freeze_queue(lo->lo_queue); spin_lock_irq(&lo->lo_lock); filp = lo->lo_backing_file; @@ -1151,7 +1163,8 @@ static void __loop_clr_fd(struct loop_device *lo, bool release) mapping_set_gfp_mask(filp->f_mapping, gfp); /* This is safe: open() is still holding a reference. */ module_put(THIS_MODULE); - blk_mq_unfreeze_queue(lo->lo_queue); + if (!release) + blk_mq_unfreeze_queue(lo->lo_queue); disk_force_media_change(lo->lo_disk, DISK_EVENT_MEDIA_CHANGE); @@ -1202,11 +1215,20 @@ static int loop_clr_fd(struct loop_device *lo) { int err; - err = mutex_lock_killable(&lo->lo_mutex); + /* + * Since lo_ioctl() is called without locks held, it is possible that + * loop_configure()/loop_change_fd() and loop_clr_fd() run in parallel. + * + * Therefore, use global lock when setting Lo_rundown state in order to + * make sure that loop_validate_file() will fail if the "struct file" + * which loop_configure()/loop_change_fd() found via fget() was this + * loop device. + */ + err = loop_global_lock_killable(lo, true); if (err) return err; if (lo->lo_state != Lo_bound) { - mutex_unlock(&lo->lo_mutex); + loop_global_unlock(lo, true); return -ENXIO; } /* @@ -1219,13 +1241,13 @@ static int loop_clr_fd(struct loop_device *lo) * <dev>/do something like mkfs/losetup -d <dev> causing the losetup -d * command to fail with EBUSY. */ - if (atomic_read(&lo->lo_refcnt) > 1) { + if (disk_openers(lo->lo_disk) > 1) { lo->lo_flags |= LO_FLAGS_AUTOCLEAR; - mutex_unlock(&lo->lo_mutex); + loop_global_unlock(lo, true); return 0; } lo->lo_state = Lo_rundown; - mutex_unlock(&lo->lo_mutex); + loop_global_unlock(lo, true); __loop_clr_fd(lo, false); return 0; @@ -1257,15 +1279,6 @@ loop_set_status(struct loop_device *lo, const struct loop_info64 *info) /* I/O need to be drained during transfer transition */ blk_mq_freeze_queue(lo->lo_queue); - if (size_changed && lo->lo_device->bd_inode->i_mapping->nrpages) { - /* If any pages were dirtied after invalidate_bdev(), try again */ - err = -EAGAIN; - pr_warn("%s: loop%d (%s) still has dirty pages (nrpages=%lu)\n", - __func__, lo->lo_number, lo->lo_file_name, - lo->lo_device->bd_inode->i_mapping->nrpages); - goto out_unfreeze; - } - prev_lo_flags = lo->lo_flags; err = loop_set_status_from_info(lo, info); @@ -1476,21 +1489,10 @@ static int loop_set_block_size(struct loop_device *lo, unsigned long arg) invalidate_bdev(lo->lo_device); blk_mq_freeze_queue(lo->lo_queue); - - /* invalidate_bdev should have truncated all the pages */ - if (lo->lo_device->bd_inode->i_mapping->nrpages) { - err = -EAGAIN; - pr_warn("%s: loop%d (%s) still has dirty pages (nrpages=%lu)\n", - __func__, lo->lo_number, lo->lo_file_name, - lo->lo_device->bd_inode->i_mapping->nrpages); - goto out_unfreeze; - } - blk_queue_logical_block_size(lo->lo_queue, arg); blk_queue_physical_block_size(lo->lo_queue, arg); blk_queue_io_min(lo->lo_queue, arg); loop_update_dio(lo); -out_unfreeze: blk_mq_unfreeze_queue(lo->lo_queue); return err; @@ -1720,33 +1722,15 @@ static int lo_compat_ioctl(struct block_device *bdev, fmode_t mode, } #endif -static int lo_open(struct block_device *bdev, fmode_t mode) -{ - struct loop_device *lo = bdev->bd_disk->private_data; - int err; - - err = mutex_lock_killable(&lo->lo_mutex); - if (err) - return err; - if (lo->lo_state == Lo_deleting) - err = -ENXIO; - else - atomic_inc(&lo->lo_refcnt); - mutex_unlock(&lo->lo_mutex); - return err; -} - static void lo_release(struct gendisk *disk, fmode_t mode) { struct loop_device *lo = disk->private_data; - mutex_lock(&lo->lo_mutex); - if (atomic_dec_return(&lo->lo_refcnt)) - goto out_unlock; + if (disk_openers(disk) > 0) + return; - if (lo->lo_flags & LO_FLAGS_AUTOCLEAR) { - if (lo->lo_state != Lo_bound) - goto out_unlock; + mutex_lock(&lo->lo_mutex); + if (lo->lo_state == Lo_bound && (lo->lo_flags & LO_FLAGS_AUTOCLEAR)) { lo->lo_state = Lo_rundown; mutex_unlock(&lo->lo_mutex); /* @@ -1755,27 +1739,30 @@ static void lo_release(struct gendisk *disk, fmode_t mode) */ __loop_clr_fd(lo, true); return; - } else if (lo->lo_state == Lo_bound) { - /* - * Otherwise keep thread (if running) and config, - * but flush possible ongoing bios in thread. - */ - blk_mq_freeze_queue(lo->lo_queue); - blk_mq_unfreeze_queue(lo->lo_queue); } - -out_unlock: mutex_unlock(&lo->lo_mutex); } +static void lo_free_disk(struct gendisk *disk) +{ + struct loop_device *lo = disk->private_data; + + if (lo->workqueue) + destroy_workqueue(lo->workqueue); + loop_free_idle_workers(lo, true); + del_timer_sync(&lo->timer); + mutex_destroy(&lo->lo_mutex); + kfree(lo); +} + static const struct block_device_operations lo_fops = { .owner = THIS_MODULE, - .open = lo_open, .release = lo_release, .ioctl = lo_ioctl, #ifdef CONFIG_COMPAT .compat_ioctl = lo_compat_ioctl, #endif + .free_disk = lo_free_disk, }; /* @@ -1834,12 +1821,14 @@ static blk_status_t loop_queue_rq(struct blk_mq_hw_ctx *hctx, cmd->blkcg_css = NULL; cmd->memcg_css = NULL; #ifdef CONFIG_BLK_CGROUP - if (rq->bio && rq->bio->bi_blkg) { - cmd->blkcg_css = &bio_blkcg(rq->bio)->css; + if (rq->bio) { + cmd->blkcg_css = bio_blkcg_css(rq->bio); #ifdef CONFIG_MEMCG - cmd->memcg_css = - cgroup_get_e_css(cmd->blkcg_css->cgroup, - &memory_cgrp_subsys); + if (cmd->blkcg_css) { + cmd->memcg_css = + cgroup_get_e_css(cmd->blkcg_css->cgroup, + &memory_cgrp_subsys); + } #endif } #endif @@ -1888,11 +1877,6 @@ static void loop_handle_cmd(struct loop_cmd *cmd) } } -static void loop_set_timer(struct loop_device *lo) -{ - timer_reduce(&lo->timer, jiffies + LOOP_IDLE_WORKER_TIMEOUT); -} - static void loop_process_work(struct loop_worker *worker, struct list_head *cmd_list, struct loop_device *lo) { @@ -1941,27 +1925,6 @@ static void loop_rootcg_workfn(struct work_struct *work) loop_process_work(NULL, &lo->rootcg_cmd_list, lo); } -static void loop_free_idle_workers(struct timer_list *timer) -{ - struct loop_device *lo = container_of(timer, struct loop_device, timer); - struct loop_worker *pos, *worker; - - spin_lock_irq(&lo->lo_work_lock); - list_for_each_entry_safe(worker, pos, &lo->idle_worker_list, - idle_list) { - if (time_is_after_jiffies(worker->last_ran_at + - LOOP_IDLE_WORKER_TIMEOUT)) - break; - list_del(&worker->idle_list); - rb_erase(&worker->rb_node, &lo->worker_tree); - css_put(worker->blkcg_css); - kfree(worker); - } - if (!list_empty(&lo->idle_worker_list)) - loop_set_timer(lo); - spin_unlock_irq(&lo->lo_work_lock); -} - static const struct blk_mq_ops loop_mq_ops = { .queue_rq = loop_queue_rq, .complete = lo_complete_rq, @@ -1977,6 +1940,9 @@ static int loop_add(int i) lo = kzalloc(sizeof(*lo), GFP_KERNEL); if (!lo) goto out; + lo->worker_tree = RB_ROOT; + INIT_LIST_HEAD(&lo->idle_worker_list); + timer_setup(&lo->timer, loop_free_idle_workers_timer, TIMER_DEFERRABLE); lo->lo_state = Lo_unbound; err = mutex_lock_killable(&loop_ctl_mutex); @@ -2046,11 +2012,12 @@ static int loop_add(int i) */ if (!part_shift) disk->flags |= GENHD_FL_NO_PART; - atomic_set(&lo->lo_refcnt, 0); mutex_init(&lo->lo_mutex); lo->lo_number = i; spin_lock_init(&lo->lo_lock); spin_lock_init(&lo->lo_work_lock); + INIT_WORK(&lo->rootcg_work, loop_rootcg_workfn); + INIT_LIST_HEAD(&lo->rootcg_cmd_list); disk->major = LOOP_MAJOR; disk->first_minor = i << part_shift; disk->minors = 1 << part_shift; @@ -2090,15 +2057,14 @@ static void loop_remove(struct loop_device *lo) { /* Make this loop device unreachable from pathname. */ del_gendisk(lo->lo_disk); - blk_cleanup_disk(lo->lo_disk); + blk_cleanup_queue(lo->lo_disk->queue); blk_mq_free_tag_set(&lo->tag_set); mutex_lock(&loop_ctl_mutex); idr_remove(&loop_index_idr, lo->lo_number); mutex_unlock(&loop_ctl_mutex); - /* There is no route which can find this loop device. */ - mutex_destroy(&lo->lo_mutex); - kfree(lo); + + put_disk(lo->lo_disk); } static void loop_probe(dev_t dev) @@ -2137,13 +2103,12 @@ static int loop_control_remove(int idx) ret = mutex_lock_killable(&lo->lo_mutex); if (ret) goto mark_visible; - if (lo->lo_state != Lo_unbound || - atomic_read(&lo->lo_refcnt) > 0) { + if (lo->lo_state != Lo_unbound || disk_openers(lo->lo_disk) > 0) { mutex_unlock(&lo->lo_mutex); ret = -EBUSY; goto mark_visible; } - /* Mark this loop device no longer open()-able. */ + /* Mark this loop device as no more bound, but not quite unbound yet */ lo->lo_state = Lo_deleting; mutex_unlock(&lo->lo_mutex); diff --git a/drivers/block/loop.h b/drivers/block/loop.h deleted file mode 100644 index 082d4b6bfc6a..000000000000 --- a/drivers/block/loop.h +++ /dev/null @@ -1,72 +0,0 @@ -/* - * loop.h - * - * Written by Theodore Ts'o, 3/29/93. - * - * Copyright 1993 by Theodore Ts'o. Redistribution of this file is - * permitted under the GNU General Public License. - */ -#ifndef _LINUX_LOOP_H -#define _LINUX_LOOP_H - -#include <linux/bio.h> -#include <linux/blkdev.h> -#include <linux/blk-mq.h> -#include <linux/spinlock.h> -#include <linux/mutex.h> -#include <uapi/linux/loop.h> - -/* Possible states of device */ -enum { - Lo_unbound, - Lo_bound, - Lo_rundown, - Lo_deleting, -}; - -struct loop_func_table; - -struct loop_device { - int lo_number; - atomic_t lo_refcnt; - loff_t lo_offset; - loff_t lo_sizelimit; - int lo_flags; - char lo_file_name[LO_NAME_SIZE]; - - struct file * lo_backing_file; - struct block_device *lo_device; - - gfp_t old_gfp_mask; - - spinlock_t lo_lock; - int lo_state; - spinlock_t lo_work_lock; - struct workqueue_struct *workqueue; - struct work_struct rootcg_work; - struct list_head rootcg_cmd_list; - struct list_head idle_worker_list; - struct rb_root worker_tree; - struct timer_list timer; - bool use_dio; - bool sysfs_inited; - - struct request_queue *lo_queue; - struct blk_mq_tag_set tag_set; - struct gendisk *lo_disk; - struct mutex lo_mutex; - bool idr_visible; -}; - -struct loop_cmd { - struct list_head list_entry; - bool use_aio; /* use AIO interface to handle I/O */ - atomic_t ref; /* only for aio */ - long ret; - struct kiocb iocb; - struct bio_vec *bvec; - struct cgroup_subsys_state *blkcg_css; - struct cgroup_subsys_state *memcg_css; -}; - -#endif diff --git a/drivers/block/mtip32xx/mtip32xx.c b/drivers/block/mtip32xx/mtip32xx.c index 4fbaf0b4958b..27386a572ba4 100644 --- a/drivers/block/mtip32xx/mtip32xx.c +++ b/drivers/block/mtip32xx/mtip32xx.c @@ -2729,7 +2729,7 @@ static int mtip_dma_alloc(struct driver_data *dd) { struct mtip_port *port = dd->port; - /* Allocate dma memory for RX Fis, Identify, and Sector Bufffer */ + /* Allocate dma memory for RX Fis, Identify, and Sector Buffer */ port->block1 = dma_alloc_coherent(&dd->pdev->dev, BLOCK_DMA_ALLOC_SZ, &port->block1_dma, GFP_KERNEL); diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c index 5a1f98494ddd..ac8b045c777c 100644 --- a/drivers/block/nbd.c +++ b/drivers/block/nbd.c @@ -333,7 +333,6 @@ static int nbd_set_size(struct nbd_device *nbd, loff_t bytesize, if (nbd->config->flags & NBD_FLAG_SEND_TRIM) { nbd->disk->queue->limits.discard_granularity = blksize; - nbd->disk->queue->limits.discard_alignment = blksize; blk_queue_max_discard_sectors(nbd->disk->queue, UINT_MAX); } blk_queue_logical_block_size(nbd->disk->queue, blksize); @@ -947,11 +946,15 @@ static int wait_for_reconnect(struct nbd_device *nbd) struct nbd_config *config = nbd->config; if (!config->dead_conn_timeout) return 0; - if (test_bit(NBD_RT_DISCONNECTED, &config->runtime_flags)) + + if (!wait_event_timeout(config->conn_wait, + test_bit(NBD_RT_DISCONNECTED, + &config->runtime_flags) || + atomic_read(&config->live_connections) > 0, + config->dead_conn_timeout)) return 0; - return wait_event_timeout(config->conn_wait, - atomic_read(&config->live_connections) > 0, - config->dead_conn_timeout) > 0; + + return !test_bit(NBD_RT_DISCONNECTED, &config->runtime_flags); } static int nbd_handle_cmd(struct nbd_cmd *cmd, int index) @@ -1217,11 +1220,11 @@ static int nbd_reconnect_socket(struct nbd_device *nbd, unsigned long arg) return -ENOSPC; } -static void nbd_bdev_reset(struct block_device *bdev) +static void nbd_bdev_reset(struct nbd_device *nbd) { - if (bdev->bd_openers > 1) + if (disk_openers(nbd->disk) > 1) return; - set_capacity(bdev->bd_disk, 0); + set_capacity(nbd->disk, 0); } static void nbd_parse_flags(struct nbd_device *nbd) @@ -1231,8 +1234,6 @@ static void nbd_parse_flags(struct nbd_device *nbd) set_disk_ro(nbd->disk, true); else set_disk_ro(nbd->disk, false); - if (config->flags & NBD_FLAG_SEND_TRIM) - blk_queue_flag_set(QUEUE_FLAG_DISCARD, nbd->disk->queue); if (config->flags & NBD_FLAG_SEND_FLUSH) { if (config->flags & NBD_FLAG_SEND_FUA) blk_queue_write_cache(nbd->disk->queue, true, true); @@ -1318,9 +1319,7 @@ static void nbd_config_put(struct nbd_device *nbd) nbd->tag_set.timeout = 0; nbd->disk->queue->limits.discard_granularity = 0; - nbd->disk->queue->limits.discard_alignment = 0; - blk_queue_max_discard_sectors(nbd->disk->queue, UINT_MAX); - blk_queue_flag_clear(QUEUE_FLAG_DISCARD, nbd->disk->queue); + blk_queue_max_discard_sectors(nbd->disk->queue, 0); mutex_unlock(&nbd->config_lock); nbd_put(nbd); @@ -1389,7 +1388,7 @@ static int nbd_start_device(struct nbd_device *nbd) return nbd_set_size(nbd, config->bytesize, nbd_blksize(config)); } -static int nbd_start_device_ioctl(struct nbd_device *nbd, struct block_device *bdev) +static int nbd_start_device_ioctl(struct nbd_device *nbd) { struct nbd_config *config = nbd->config; int ret; @@ -1408,7 +1407,7 @@ static int nbd_start_device_ioctl(struct nbd_device *nbd, struct block_device *b flush_workqueue(nbd->recv_workq); mutex_lock(&nbd->config_lock); - nbd_bdev_reset(bdev); + nbd_bdev_reset(nbd); /* user requested, ignore socket errors */ if (test_bit(NBD_RT_DISCONNECT_REQUESTED, &config->runtime_flags)) ret = 0; @@ -1422,7 +1421,7 @@ static void nbd_clear_sock_ioctl(struct nbd_device *nbd, { sock_shutdown(nbd); __invalidate_device(bdev, true); - nbd_bdev_reset(bdev); + nbd_bdev_reset(nbd); if (test_and_clear_bit(NBD_RT_HAS_CONFIG_REF, &nbd->config->runtime_flags)) nbd_config_put(nbd); @@ -1468,7 +1467,7 @@ static int __nbd_ioctl(struct block_device *bdev, struct nbd_device *nbd, config->flags = arg; return 0; case NBD_DO_IT: - return nbd_start_device_ioctl(nbd, bdev); + return nbd_start_device_ioctl(nbd); case NBD_CLEAR_QUE: /* * This is for compatibility only. The queue is always cleared @@ -1579,7 +1578,7 @@ static void nbd_release(struct gendisk *disk, fmode_t mode) struct nbd_device *nbd = disk->private_data; if (test_bit(NBD_RT_DISCONNECT_ON_CLOSE, &nbd->config->runtime_flags) && - disk->part0->bd_openers == 0) + disk_openers(disk) == 0) nbd_disconnect_and_put(nbd); nbd_config_put(nbd); @@ -1784,7 +1783,6 @@ static struct nbd_device *nbd_dev_add(int index, unsigned int refs) blk_queue_flag_set(QUEUE_FLAG_NONROT, disk->queue); blk_queue_flag_clear(QUEUE_FLAG_ADD_RANDOM, disk->queue); disk->queue->limits.discard_granularity = 0; - disk->queue->limits.discard_alignment = 0; blk_queue_max_discard_sectors(disk->queue, 0); blk_queue_max_segment_size(disk->queue, UINT_MAX); blk_queue_max_segments(disk->queue, USHRT_MAX); @@ -2082,6 +2080,7 @@ static void nbd_disconnect_and_put(struct nbd_device *nbd) mutex_lock(&nbd->config_lock); nbd_disconnect(nbd); sock_shutdown(nbd); + wake_up(&nbd->config->conn_wait); /* * Make sure recv thread has finished, we can safely call nbd_clear_que() * to cancel the inflight I/Os. diff --git a/drivers/block/null_blk/main.c b/drivers/block/null_blk/main.c index c441a4972064..539cfeac263d 100644 --- a/drivers/block/null_blk/main.c +++ b/drivers/block/null_blk/main.c @@ -11,6 +11,9 @@ #include <linux/init.h> #include "null_blk.h" +#undef pr_fmt +#define pr_fmt(fmt) "null_blk: " fmt + #define FREE_BATCH 16 #define TICKS_PER_SEC 50ULL @@ -232,6 +235,7 @@ static struct nullb_device *null_alloc_dev(void); static void null_free_dev(struct nullb_device *dev); static void null_del_dev(struct nullb *nullb); static int null_add_dev(struct nullb_device *dev); +static struct nullb *null_find_dev_by_name(const char *name); static void null_free_device_storage(struct nullb_device *dev, bool is_cache); static inline struct nullb_device *to_nullb_device(struct config_item *item) @@ -560,6 +564,9 @@ config_item *nullb_group_make_item(struct config_group *group, const char *name) { struct nullb_device *dev; + if (null_find_dev_by_name(name)) + return ERR_PTR(-EEXIST); + dev = null_alloc_dev(); if (!dev) return ERR_PTR(-ENOMEM); @@ -1765,9 +1772,7 @@ static void null_config_discard(struct nullb *nullb) } nullb->q->limits.discard_granularity = nullb->dev->blocksize; - nullb->q->limits.discard_alignment = nullb->dev->blocksize; blk_queue_max_discard_sectors(nullb->q, UINT_MAX >> 9); - blk_queue_flag_set(QUEUE_FLAG_DISCARD, nullb->q); } static const struct block_device_operations null_bio_ops = { @@ -2061,7 +2066,13 @@ static int null_add_dev(struct nullb_device *dev) null_config_discard(nullb); - sprintf(nullb->disk_name, "nullb%d", nullb->index); + if (config_item_name(&dev->item)) { + /* Use configfs dir name as the device name */ + snprintf(nullb->disk_name, sizeof(nullb->disk_name), + "%s", config_item_name(&dev->item)); + } else { + sprintf(nullb->disk_name, "nullb%d", nullb->index); + } rv = null_gendisk_register(nullb); if (rv) @@ -2071,6 +2082,8 @@ static int null_add_dev(struct nullb_device *dev) list_add_tail(&nullb->list, &nullb_list); mutex_unlock(&lock); + pr_info("disk %s created\n", nullb->disk_name); + return 0; out_cleanup_zone: null_free_zoned_dev(dev); @@ -2088,12 +2101,53 @@ out: return rv; } +static struct nullb *null_find_dev_by_name(const char *name) +{ + struct nullb *nullb = NULL, *nb; + + mutex_lock(&lock); + list_for_each_entry(nb, &nullb_list, list) { + if (strcmp(nb->disk_name, name) == 0) { + nullb = nb; + break; + } + } + mutex_unlock(&lock); + + return nullb; +} + +static int null_create_dev(void) +{ + struct nullb_device *dev; + int ret; + + dev = null_alloc_dev(); + if (!dev) + return -ENOMEM; + + ret = null_add_dev(dev); + if (ret) { + null_free_dev(dev); + return ret; + } + + return 0; +} + +static void null_destroy_dev(struct nullb *nullb) +{ + struct nullb_device *dev = nullb->dev; + + null_del_dev(nullb); + null_free_dev(dev); +} + static int __init null_init(void) { int ret = 0; unsigned int i; struct nullb *nullb; - struct nullb_device *dev; if (g_bs > PAGE_SIZE) { pr_warn("invalid block size\n"); @@ -2113,19 +2167,21 @@ static int __init null_init(void) } if (g_queue_mode == NULL_Q_RQ) { - pr_err("legacy IO path no longer available\n"); + pr_err("legacy IO path is no longer available\n"); return -EINVAL; } + if (g_queue_mode == NULL_Q_MQ && g_use_per_node_hctx) { if (g_submit_queues != nr_online_nodes) { pr_warn("submit_queues param is set to %u.\n", - nr_online_nodes); + nr_online_nodes); g_submit_queues = nr_online_nodes; } - } else if (g_submit_queues > nr_cpu_ids) + } else if (g_submit_queues > nr_cpu_ids) { g_submit_queues = nr_cpu_ids; - else if (g_submit_queues <= 0) + } else if (g_submit_queues <= 0) { g_submit_queues = 1; + } if (g_queue_mode == NULL_Q_MQ && shared_tags) { ret = null_init_tag_set(NULL, &tag_set); @@ -2149,16 +2205,9 @@ static int __init null_init(void) } for (i = 0; i < nr_devices; i++) { - dev = null_alloc_dev(); - if (!dev) { - ret = -ENOMEM; - goto err_dev; - } - ret = null_add_dev(dev); - if (ret) { - null_free_dev(dev); + ret = null_create_dev(); + if (ret) goto err_dev; - } } pr_info("module loaded\n"); @@ -2167,9 +2216,7 @@ static int __init null_init(void) err_dev: while (!list_empty(&nullb_list)) { nullb = list_entry(nullb_list.next, struct nullb, list); - dev = nullb->dev; - null_del_dev(nullb); - null_free_dev(dev); + null_destroy_dev(nullb); } unregister_blkdev(null_major, "nullb"); err_conf: @@ -2190,12 +2237,8 @@ static void __exit null_exit(void) mutex_lock(&lock); while (!list_empty(&nullb_list)) { - struct nullb_device *dev; - nullb = list_entry(nullb_list.next, struct nullb, list); - dev = nullb->dev; - null_del_dev(nullb); - null_free_dev(dev); + null_destroy_dev(nullb); } mutex_unlock(&lock); diff --git a/drivers/block/null_blk/null_blk.h b/drivers/block/null_blk/null_blk.h index 78eb56b0ca55..4525a65e1b23 100644 --- a/drivers/block/null_blk/null_blk.h +++ b/drivers/block/null_blk/null_blk.h @@ -16,13 +16,15 @@ #include <linux/mutex.h> struct nullb_cmd { - struct request *rq; - struct bio *bio; + union { + struct request *rq; + struct bio *bio; + }; unsigned int tag; blk_status_t error; + bool fake_timeout; struct nullb_queue *nq; struct hrtimer timer; - bool fake_timeout; }; struct nullb_queue { diff --git a/drivers/block/null_blk/zoned.c b/drivers/block/null_blk/zoned.c index dae54dd1aeac..ed158ea4fdd1 100644 --- a/drivers/block/null_blk/zoned.c +++ b/drivers/block/null_blk/zoned.c @@ -6,6 +6,9 @@ #define CREATE_TRACE_POINTS #include "trace.h" +#undef pr_fmt +#define pr_fmt(fmt) "null_blk: " fmt + static inline sector_t mb_to_sects(unsigned long mb) { return ((sector_t)mb * SZ_1M) >> SECTOR_SHIFT; @@ -75,8 +78,8 @@ int null_init_zoned_dev(struct nullb_device *dev, struct request_queue *q) 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); + pr_err("zone capacity (%lu MB) larger than zone size (%lu MB)\n", + dev->zone_capacity, dev->zone_size); return -EINVAL; } diff --git a/drivers/block/pktcdvd.c b/drivers/block/pktcdvd.c index 86c8794ede41..789093375344 100644 --- a/drivers/block/pktcdvd.c +++ b/drivers/block/pktcdvd.c @@ -12,7 +12,7 @@ * Theory of operation: * * At the lowest level, there is the standard driver for the CD/DVD device, - * typically ide-cd.c or sr.c. This driver can handle read and write requests, + * such as drivers/scsi/sr.c. This driver can handle read and write requests, * but it doesn't know anything about the special restrictions that apply to * packet writing. One restriction is that write requests must be aligned to * packet boundaries on the physical media, and the size of a write request @@ -522,7 +522,7 @@ static struct packet_data *pkt_alloc_packet_data(int frames) goto no_pkt; pkt->frames = frames; - pkt->w_bio = bio_kmalloc(GFP_KERNEL, frames); + pkt->w_bio = bio_kmalloc(frames, GFP_KERNEL); if (!pkt->w_bio) goto no_bio; @@ -536,27 +536,21 @@ static struct packet_data *pkt_alloc_packet_data(int frames) bio_list_init(&pkt->orig_bios); for (i = 0; i < frames; i++) { - struct bio *bio = bio_kmalloc(GFP_KERNEL, 1); - if (!bio) + pkt->r_bios[i] = bio_kmalloc(1, GFP_KERNEL); + if (!pkt->r_bios[i]) goto no_rd_bio; - - pkt->r_bios[i] = bio; } return pkt; no_rd_bio: - for (i = 0; i < frames; i++) { - struct bio *bio = pkt->r_bios[i]; - if (bio) - bio_put(bio); - } - + for (i = 0; i < frames; i++) + kfree(pkt->r_bios[i]); no_page: for (i = 0; i < frames / FRAMES_PER_PAGE; i++) if (pkt->pages[i]) __free_page(pkt->pages[i]); - bio_put(pkt->w_bio); + kfree(pkt->w_bio); no_bio: kfree(pkt); no_pkt: @@ -570,14 +564,11 @@ static void pkt_free_packet_data(struct packet_data *pkt) { int i; - for (i = 0; i < pkt->frames; i++) { - struct bio *bio = pkt->r_bios[i]; - if (bio) - bio_put(bio); - } + for (i = 0; i < pkt->frames; i++) + kfree(pkt->r_bios[i]); for (i = 0; i < pkt->frames / FRAMES_PER_PAGE; i++) __free_page(pkt->pages[i]); - bio_put(pkt->w_bio); + kfree(pkt->w_bio); kfree(pkt); } @@ -951,6 +942,7 @@ static void pkt_end_io_read(struct bio *bio) if (bio->bi_status) atomic_inc(&pkt->io_errors); + bio_uninit(bio); if (atomic_dec_and_test(&pkt->io_wait)) { atomic_inc(&pkt->run_sm); wake_up(&pd->wqueue); @@ -968,6 +960,7 @@ static void pkt_end_io_packet_write(struct bio *bio) pd->stats.pkt_ended++; + bio_uninit(bio); pkt_bio_finished(pd); atomic_dec(&pkt->io_wait); atomic_inc(&pkt->run_sm); @@ -1022,7 +1015,7 @@ static void pkt_gather_data(struct pktcdvd_device *pd, struct packet_data *pkt) continue; bio = pkt->r_bios[f]; - bio_reset(bio, pd->bdev, REQ_OP_READ); + bio_init(bio, pd->bdev, bio->bi_inline_vecs, 1, REQ_OP_READ); bio->bi_iter.bi_sector = pkt->sector + f * (CD_FRAMESIZE >> 9); bio->bi_end_io = pkt_end_io_read; bio->bi_private = pkt; @@ -1235,7 +1228,8 @@ static void pkt_start_write(struct pktcdvd_device *pd, struct packet_data *pkt) { int f; - bio_reset(pkt->w_bio, pd->bdev, REQ_OP_WRITE); + bio_init(pkt->w_bio, pd->bdev, pkt->w_bio->bi_inline_vecs, pkt->frames, + REQ_OP_WRITE); pkt->w_bio->bi_iter.bi_sector = pkt->sector; pkt->w_bio->bi_end_io = pkt_end_io_packet_write; pkt->w_bio->bi_private = pkt; diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c index b844432bad20..2b21f717cce1 100644 --- a/drivers/block/rbd.c +++ b/drivers/block/rbd.c @@ -4942,7 +4942,6 @@ static int rbd_init_disk(struct rbd_device *rbd_dev) blk_queue_io_opt(q, rbd_dev->opts->alloc_size); if (rbd_dev->opts->trim) { - blk_queue_flag_set(QUEUE_FLAG_DISCARD, q); q->limits.discard_granularity = rbd_dev->opts->alloc_size; blk_queue_max_discard_sectors(q, objset_bytes >> SECTOR_SHIFT); blk_queue_max_write_zeroes_sectors(q, objset_bytes >> SECTOR_SHIFT); diff --git a/drivers/block/rnbd/rnbd-clt.c b/drivers/block/rnbd/rnbd-clt.c index b66e8840b94b..409c76b81aed 100644 --- a/drivers/block/rnbd/rnbd-clt.c +++ b/drivers/block/rnbd/rnbd-clt.c @@ -25,6 +25,7 @@ static int rnbd_client_major; static DEFINE_IDA(index_ida); static DEFINE_MUTEX(sess_lock); static LIST_HEAD(sess_list); +static struct workqueue_struct *rnbd_clt_wq; /* * Maximum number of partitions an instance can have. @@ -1364,11 +1365,9 @@ static void setup_request_queue(struct rnbd_clt_dev *dev) blk_queue_max_discard_sectors(dev->queue, dev->max_discard_sectors); dev->queue->limits.discard_granularity = dev->discard_granularity; dev->queue->limits.discard_alignment = dev->discard_alignment; - if (dev->max_discard_sectors) - blk_queue_flag_set(QUEUE_FLAG_DISCARD, dev->queue); if (dev->secure_discard) - blk_queue_flag_set(QUEUE_FLAG_SECERASE, dev->queue); - + blk_queue_max_secure_erase_sectors(dev->queue, + dev->max_discard_sectors); blk_queue_flag_set(QUEUE_FLAG_SAME_COMP, dev->queue); blk_queue_flag_set(QUEUE_FLAG_SAME_FORCE, dev->queue); blk_queue_max_segments(dev->queue, dev->max_segments); @@ -1761,12 +1760,12 @@ static void rnbd_destroy_sessions(void) * procedure takes minutes. */ INIT_WORK(&dev->unmap_on_rmmod_work, unmap_device_work); - queue_work(system_long_wq, &dev->unmap_on_rmmod_work); + queue_work(rnbd_clt_wq, &dev->unmap_on_rmmod_work); } rnbd_clt_put_sess(sess); } /* Wait for all scheduled unmap works */ - flush_workqueue(system_long_wq); + flush_workqueue(rnbd_clt_wq); WARN_ON(!list_empty(&sess_list)); } @@ -1791,6 +1790,14 @@ static int __init rnbd_client_init(void) pr_err("Failed to load module, creating sysfs device files failed, err: %d\n", err); unregister_blkdev(rnbd_client_major, "rnbd"); + return err; + } + rnbd_clt_wq = alloc_workqueue("rnbd_clt_wq", 0, 0); + if (!rnbd_clt_wq) { + pr_err("Failed to load module, alloc_workqueue failed.\n"); + rnbd_clt_destroy_sysfs_files(); + unregister_blkdev(rnbd_client_major, "rnbd"); + err = -ENOMEM; } return err; @@ -1801,6 +1808,7 @@ static void __exit rnbd_client_exit(void) rnbd_destroy_sessions(); unregister_blkdev(rnbd_client_major, "rnbd"); ida_destroy(&index_ida); + destroy_workqueue(rnbd_clt_wq); } module_init(rnbd_client_init); diff --git a/drivers/block/rnbd/rnbd-srv-dev.h b/drivers/block/rnbd/rnbd-srv-dev.h index 2c3df02b5e8e..4309e5252469 100644 --- a/drivers/block/rnbd/rnbd-srv-dev.h +++ b/drivers/block/rnbd/rnbd-srv-dev.h @@ -44,16 +44,12 @@ static inline int rnbd_dev_get_max_hw_sects(const struct rnbd_dev *dev) static inline int rnbd_dev_get_secure_discard(const struct rnbd_dev *dev) { - return blk_queue_secure_erase(bdev_get_queue(dev->bdev)); + return bdev_max_secure_erase_sectors(dev->bdev); } static inline int rnbd_dev_get_max_discard_sects(const struct rnbd_dev *dev) { - if (!blk_queue_discard(bdev_get_queue(dev->bdev))) - return 0; - - return blk_queue_get_max_sectors(bdev_get_queue(dev->bdev), - REQ_OP_DISCARD); + return bdev_max_discard_sectors(dev->bdev); } static inline int rnbd_dev_get_discard_granularity(const struct rnbd_dev *dev) @@ -63,7 +59,7 @@ static inline int rnbd_dev_get_discard_granularity(const struct rnbd_dev *dev) static inline int rnbd_dev_get_discard_alignment(const struct rnbd_dev *dev) { - return bdev_get_queue(dev->bdev)->limits.discard_alignment; + return bdev_discard_alignment(dev->bdev); } #endif /* RNBD_SRV_DEV_H */ diff --git a/drivers/block/rnbd/rnbd-srv.c b/drivers/block/rnbd/rnbd-srv.c index f04df6294650..beaef43a67b9 100644 --- a/drivers/block/rnbd/rnbd-srv.c +++ b/drivers/block/rnbd/rnbd-srv.c @@ -533,7 +533,6 @@ static void rnbd_srv_fill_msg_open_rsp(struct rnbd_msg_open_rsp *rsp, struct rnbd_srv_sess_dev *sess_dev) { struct rnbd_dev *rnbd_dev = sess_dev->rnbd_dev; - struct request_queue *q = bdev_get_queue(rnbd_dev->bdev); rsp->hdr.type = cpu_to_le16(RNBD_MSG_OPEN_RSP); rsp->device_id = @@ -558,9 +557,9 @@ static void rnbd_srv_fill_msg_open_rsp(struct rnbd_msg_open_rsp *rsp, rsp->secure_discard = cpu_to_le16(rnbd_dev_get_secure_discard(rnbd_dev)); rsp->cache_policy = 0; - if (test_bit(QUEUE_FLAG_WC, &q->queue_flags)) + if (bdev_write_cache(rnbd_dev->bdev)) rsp->cache_policy |= RNBD_WRITEBACK; - if (blk_queue_fua(q)) + if (bdev_fua(rnbd_dev->bdev)) rsp->cache_policy |= RNBD_FUA; } diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c index a8bcf3f664af..d624cc8eddc3 100644 --- a/drivers/block/virtio_blk.c +++ b/drivers/block/virtio_blk.c @@ -867,11 +867,12 @@ static int virtblk_probe(struct virtio_device *vdev) blk_queue_io_opt(q, blk_size * opt_io_size); if (virtio_has_feature(vdev, VIRTIO_BLK_F_DISCARD)) { - q->limits.discard_granularity = blk_size; - virtio_cread(vdev, struct virtio_blk_config, discard_sector_alignment, &v); - q->limits.discard_alignment = v ? v << SECTOR_SHIFT : 0; + if (v) + q->limits.discard_granularity = v << SECTOR_SHIFT; + else + q->limits.discard_granularity = blk_size; virtio_cread(vdev, struct virtio_blk_config, max_discard_sectors, &v); @@ -888,8 +889,6 @@ static int virtblk_probe(struct virtio_device *vdev) v = sg_elems; blk_queue_max_discard_segments(q, min(v, MAX_DISCARD_SEGMENTS)); - - blk_queue_flag_set(QUEUE_FLAG_DISCARD, q); } if (virtio_has_feature(vdev, VIRTIO_BLK_F_WRITE_ZEROES)) { diff --git a/drivers/block/xen-blkback/blkback.c b/drivers/block/xen-blkback/blkback.c index de42458195bc..a97f2bf5b01b 100644 --- a/drivers/block/xen-blkback/blkback.c +++ b/drivers/block/xen-blkback/blkback.c @@ -970,7 +970,6 @@ static int dispatch_discard_io(struct xen_blkif_ring *ring, int status = BLKIF_RSP_OKAY; struct xen_blkif *blkif = ring->blkif; struct block_device *bdev = blkif->vbd.bdev; - unsigned long secure; struct phys_req preq; xen_blkif_get(blkif); @@ -987,13 +986,15 @@ static int dispatch_discard_io(struct xen_blkif_ring *ring, } ring->st_ds_req++; - secure = (blkif->vbd.discard_secure && - (req->u.discard.flag & BLKIF_DISCARD_SECURE)) ? - BLKDEV_DISCARD_SECURE : 0; + if (blkif->vbd.discard_secure && + (req->u.discard.flag & BLKIF_DISCARD_SECURE)) + err = blkdev_issue_secure_erase(bdev, + req->u.discard.sector_number, + req->u.discard.nr_sectors, GFP_KERNEL); + else + err = blkdev_issue_discard(bdev, req->u.discard.sector_number, + req->u.discard.nr_sectors, GFP_KERNEL); - err = blkdev_issue_discard(bdev, req->u.discard.sector_number, - req->u.discard.nr_sectors, - GFP_KERNEL, secure); fail_response: if (err == -EOPNOTSUPP) { pr_debug("discard op failed, not supported\n"); diff --git a/drivers/block/xen-blkback/xenbus.c b/drivers/block/xen-blkback/xenbus.c index f09040435e2e..97de13b14175 100644 --- a/drivers/block/xen-blkback/xenbus.c +++ b/drivers/block/xen-blkback/xenbus.c @@ -484,7 +484,6 @@ static int xen_vbd_create(struct xen_blkif *blkif, blkif_vdev_t handle, { struct xen_vbd *vbd; struct block_device *bdev; - struct request_queue *q; vbd = &blkif->vbd; vbd->handle = handle; @@ -516,11 +515,9 @@ static int xen_vbd_create(struct xen_blkif *blkif, blkif_vdev_t handle, if (vbd->bdev->bd_disk->flags & GENHD_FL_REMOVABLE) vbd->type |= VDISK_REMOVABLE; - q = bdev_get_queue(bdev); - if (q && test_bit(QUEUE_FLAG_WC, &q->queue_flags)) + if (bdev_write_cache(bdev)) vbd->flush_support = true; - - if (q && blk_queue_secure_erase(q)) + if (bdev_max_secure_erase_sectors(bdev)) vbd->discard_secure = true; vbd->feature_gnt_persistent = feature_persistent; @@ -578,22 +575,21 @@ static void xen_blkbk_discard(struct xenbus_transaction xbt, struct backend_info int err; int state = 0; struct block_device *bdev = be->blkif->vbd.bdev; - struct request_queue *q = bdev_get_queue(bdev); if (!xenbus_read_unsigned(dev->nodename, "discard-enable", 1)) return; - if (blk_queue_discard(q)) { + if (bdev_max_discard_sectors(bdev)) { err = xenbus_printf(xbt, dev->nodename, "discard-granularity", "%u", - q->limits.discard_granularity); + bdev_discard_granularity(bdev)); if (err) { dev_warn(&dev->dev, "writing discard-granularity (%d)", err); return; } err = xenbus_printf(xbt, dev->nodename, "discard-alignment", "%u", - q->limits.discard_alignment); + bdev_discard_alignment(bdev)); if (err) { dev_warn(&dev->dev, "writing discard-alignment (%d)", err); return; diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c index 003056d4f7f5..55e004d03ced 100644 --- a/drivers/block/xen-blkfront.c +++ b/drivers/block/xen-blkfront.c @@ -229,8 +229,6 @@ static unsigned int nr_minors; static unsigned long *minors; static DEFINE_SPINLOCK(minor_lock); -#define GRANT_INVALID_REF 0 - #define PARTS_PER_DISK 16 #define PARTS_PER_EXT_DISK 256 @@ -321,7 +319,7 @@ static int fill_grant_buffer(struct blkfront_ring_info *rinfo, int num) gnt_list_entry->page = granted_page; } - gnt_list_entry->gref = GRANT_INVALID_REF; + gnt_list_entry->gref = INVALID_GRANT_REF; list_add(&gnt_list_entry->node, &rinfo->grants); i++; } @@ -350,7 +348,7 @@ static struct grant *get_free_grant(struct blkfront_ring_info *rinfo) node); list_del(&gnt_list_entry->node); - if (gnt_list_entry->gref != GRANT_INVALID_REF) + if (gnt_list_entry->gref != INVALID_GRANT_REF) rinfo->persistent_gnts_c--; return gnt_list_entry; @@ -372,7 +370,7 @@ static struct grant *get_grant(grant_ref_t *gref_head, struct grant *gnt_list_entry = get_free_grant(rinfo); struct blkfront_info *info = rinfo->dev_info; - if (gnt_list_entry->gref != GRANT_INVALID_REF) + if (gnt_list_entry->gref != INVALID_GRANT_REF) return gnt_list_entry; /* Assign a gref to this page */ @@ -396,7 +394,7 @@ static struct grant *get_indirect_grant(grant_ref_t *gref_head, struct grant *gnt_list_entry = get_free_grant(rinfo); struct blkfront_info *info = rinfo->dev_info; - if (gnt_list_entry->gref != GRANT_INVALID_REF) + if (gnt_list_entry->gref != INVALID_GRANT_REF) return gnt_list_entry; /* Assign a gref to this page */ @@ -944,13 +942,13 @@ static void blkif_set_queue_limits(struct blkfront_info *info) blk_queue_flag_set(QUEUE_FLAG_VIRT, rq); if (info->feature_discard) { - blk_queue_flag_set(QUEUE_FLAG_DISCARD, rq); blk_queue_max_discard_sectors(rq, get_capacity(gd)); rq->limits.discard_granularity = info->discard_granularity ?: info->physical_sector_size; rq->limits.discard_alignment = info->discard_alignment; if (info->feature_secdiscard) - blk_queue_flag_set(QUEUE_FLAG_SECERASE, rq); + blk_queue_max_secure_erase_sectors(rq, + get_capacity(gd)); } /* Hard sector size and max sectors impersonate the equiv. hardware. */ @@ -1221,7 +1219,7 @@ static void blkif_free_ring(struct blkfront_ring_info *rinfo) list_for_each_entry_safe(persistent_gnt, n, &rinfo->grants, node) { list_del(&persistent_gnt->node); - if (persistent_gnt->gref != GRANT_INVALID_REF) { + if (persistent_gnt->gref != INVALID_GRANT_REF) { gnttab_end_foreign_access(persistent_gnt->gref, 0UL); rinfo->persistent_gnts_c--; @@ -1282,15 +1280,8 @@ free_shadow: flush_work(&rinfo->work); /* Free resources associated with old device channel. */ - for (i = 0; i < info->nr_ring_pages; i++) { - if (rinfo->ring_ref[i] != GRANT_INVALID_REF) { - gnttab_end_foreign_access(rinfo->ring_ref[i], 0); - rinfo->ring_ref[i] = GRANT_INVALID_REF; - } - } - free_pages_exact(rinfo->ring.sring, - info->nr_ring_pages * XEN_PAGE_SIZE); - rinfo->ring.sring = NULL; + xenbus_teardown_ring((void **)&rinfo->ring.sring, info->nr_ring_pages, + rinfo->ring_ref); if (rinfo->irq) unbind_from_irqhandler(rinfo->irq, rinfo); @@ -1475,7 +1466,7 @@ static int blkif_completion(unsigned long *id, * to the tail of the list, so it will not be picked * again unless we run out of persistent grants. */ - s->grants_used[i]->gref = GRANT_INVALID_REF; + s->grants_used[i]->gref = INVALID_GRANT_REF; list_add_tail(&s->grants_used[i]->node, &rinfo->grants); } } @@ -1500,7 +1491,7 @@ static int blkif_completion(unsigned long *id, indirect_page = s->indirect_grants[i]->page; list_add(&indirect_page->lru, &rinfo->indirect_pages); } - s->indirect_grants[i]->gref = GRANT_INVALID_REF; + s->indirect_grants[i]->gref = INVALID_GRANT_REF; list_add_tail(&s->indirect_grants[i]->node, &rinfo->grants); } } @@ -1606,8 +1597,8 @@ static irqreturn_t blkif_interrupt(int irq, void *dev_id) blkif_req(req)->error = BLK_STS_NOTSUPP; info->feature_discard = 0; info->feature_secdiscard = 0; - blk_queue_flag_clear(QUEUE_FLAG_DISCARD, rq); - blk_queue_flag_clear(QUEUE_FLAG_SECERASE, rq); + blk_queue_max_discard_sectors(rq, 0); + blk_queue_max_secure_erase_sectors(rq, 0); } break; case BLKIF_OP_FLUSH_DISKCACHE: @@ -1681,30 +1672,16 @@ static int setup_blkring(struct xenbus_device *dev, struct blkfront_ring_info *rinfo) { struct blkif_sring *sring; - int err, i; + int err; struct blkfront_info *info = rinfo->dev_info; unsigned long ring_size = info->nr_ring_pages * XEN_PAGE_SIZE; - grant_ref_t gref[XENBUS_MAX_RING_GRANTS]; - - for (i = 0; i < info->nr_ring_pages; i++) - rinfo->ring_ref[i] = GRANT_INVALID_REF; - sring = alloc_pages_exact(ring_size, GFP_NOIO); - if (!sring) { - xenbus_dev_fatal(dev, -ENOMEM, "allocating shared ring"); - return -ENOMEM; - } - SHARED_RING_INIT(sring); - FRONT_RING_INIT(&rinfo->ring, sring, ring_size); - - err = xenbus_grant_ring(dev, rinfo->ring.sring, info->nr_ring_pages, gref); - if (err < 0) { - free_pages_exact(sring, ring_size); - rinfo->ring.sring = NULL; + err = xenbus_setup_ring(dev, GFP_NOIO, (void **)&sring, + info->nr_ring_pages, rinfo->ring_ref); + if (err) goto fail; - } - for (i = 0; i < info->nr_ring_pages; i++) - rinfo->ring_ref[i] = gref[i]; + + XEN_FRONT_RING_INIT(&rinfo->ring, sring, ring_size); err = xenbus_alloc_evtchn(dev, &rinfo->evtchn); if (err) @@ -2544,13 +2521,13 @@ static void purge_persistent_grants(struct blkfront_info *info) list_for_each_entry_safe(gnt_list_entry, tmp, &rinfo->grants, node) { - if (gnt_list_entry->gref == GRANT_INVALID_REF || + if (gnt_list_entry->gref == INVALID_GRANT_REF || !gnttab_try_end_foreign_access(gnt_list_entry->gref)) continue; list_del(&gnt_list_entry->node); rinfo->persistent_gnts_c--; - gnt_list_entry->gref = GRANT_INVALID_REF; + gnt_list_entry->gref = INVALID_GRANT_REF; list_add_tail(&gnt_list_entry->node, &grants); } diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c index e9474b02012d..6853dd3c7d3a 100644 --- a/drivers/block/zram/zram_drv.c +++ b/drivers/block/zram/zram_drv.c @@ -1675,9 +1675,10 @@ static int zram_rw_page(struct block_device *bdev, sector_t sector, bv.bv_len = PAGE_SIZE; bv.bv_offset = 0; - start_time = disk_start_io_acct(bdev->bd_disk, SECTORS_PER_PAGE, op); + start_time = bdev_start_io_acct(bdev->bd_disk->part0, + SECTORS_PER_PAGE, op, jiffies); ret = zram_bvec_rw(zram, &bv, index, offset, op, NULL); - disk_end_io_acct(bdev->bd_disk, op, start_time); + bdev_end_io_acct(bdev->bd_disk->part0, op, start_time); out: /* * If I/O fails, just return error(ie, non-zero) without @@ -1786,7 +1787,7 @@ static ssize_t reset_store(struct device *dev, int ret; unsigned short do_reset; struct zram *zram; - struct block_device *bdev; + struct gendisk *disk; ret = kstrtou16(buf, 10, &do_reset); if (ret) @@ -1796,26 +1797,26 @@ static ssize_t reset_store(struct device *dev, return -EINVAL; zram = dev_to_zram(dev); - bdev = zram->disk->part0; + disk = zram->disk; - mutex_lock(&bdev->bd_disk->open_mutex); + mutex_lock(&disk->open_mutex); /* Do not reset an active device or claimed device */ - if (bdev->bd_openers || zram->claim) { - mutex_unlock(&bdev->bd_disk->open_mutex); + if (disk_openers(disk) || zram->claim) { + mutex_unlock(&disk->open_mutex); return -EBUSY; } /* From now on, anyone can't open /dev/zram[0-9] */ zram->claim = true; - mutex_unlock(&bdev->bd_disk->open_mutex); + mutex_unlock(&disk->open_mutex); /* Make sure all the pending I/O are finished */ - sync_blockdev(bdev); + sync_blockdev(disk->part0); zram_reset_device(zram); - mutex_lock(&bdev->bd_disk->open_mutex); + mutex_lock(&disk->open_mutex); zram->claim = false; - mutex_unlock(&bdev->bd_disk->open_mutex); + mutex_unlock(&disk->open_mutex); return len; } @@ -1952,7 +1953,6 @@ static int zram_add(void) blk_queue_io_opt(zram->disk->queue, PAGE_SIZE); zram->disk->queue->limits.discard_granularity = PAGE_SIZE; blk_queue_max_discard_sectors(zram->disk->queue, UINT_MAX); - blk_queue_flag_set(QUEUE_FLAG_DISCARD, zram->disk->queue); /* * zram_bio_discard() will clear all logical blocks if logical block @@ -1987,19 +1987,18 @@ out_free_dev: static int zram_remove(struct zram *zram) { - struct block_device *bdev = zram->disk->part0; bool claimed; - mutex_lock(&bdev->bd_disk->open_mutex); - if (bdev->bd_openers) { - mutex_unlock(&bdev->bd_disk->open_mutex); + mutex_lock(&zram->disk->open_mutex); + if (disk_openers(zram->disk)) { + mutex_unlock(&zram->disk->open_mutex); return -EBUSY; } claimed = zram->claim; if (!claimed) zram->claim = true; - mutex_unlock(&bdev->bd_disk->open_mutex); + mutex_unlock(&zram->disk->open_mutex); zram_debugfs_unregister(zram); @@ -2011,7 +2010,7 @@ static int zram_remove(struct zram *zram) ; } else { /* Make sure all the pending I/O are finished */ - sync_blockdev(bdev); + sync_blockdev(zram->disk->part0); zram_reset_device(zram); } |