diff options
31 files changed, 94 insertions, 125 deletions
diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c index e17da947f6bd..0ac817b750db 100644 --- a/block/blk-cgroup.c +++ b/block/blk-cgroup.c @@ -822,7 +822,6 @@ static void blkcg_css_free(struct cgroup_subsys_state *css) static struct cgroup_subsys_state * blkcg_css_alloc(struct cgroup_subsys_state *parent_css) { - static atomic64_t id_seq = ATOMIC64_INIT(0); struct blkcg *blkcg; if (!parent_css) { @@ -836,7 +835,6 @@ blkcg_css_alloc(struct cgroup_subsys_state *parent_css) blkcg->cfq_weight = CFQ_WEIGHT_DEFAULT; blkcg->cfq_leaf_weight = CFQ_WEIGHT_DEFAULT; - blkcg->id = atomic64_inc_return(&id_seq); /* root is 0, start from 1 */ done: spin_lock_init(&blkcg->lock); INIT_RADIX_TREE(&blkcg->blkg_tree, GFP_ATOMIC); diff --git a/block/blk-cgroup.h b/block/blk-cgroup.h index d3fd7aa3d2a3..c567865b5f1d 100644 --- a/block/blk-cgroup.h +++ b/block/blk-cgroup.h @@ -50,9 +50,6 @@ struct blkcg { struct blkcg_gq *blkg_hint; struct hlist_head blkg_list; - /* for policies to test whether associated blkcg has changed */ - uint64_t id; - /* TODO: per-policy storage in blkcg */ unsigned int cfq_weight; /* belongs to cfq */ unsigned int cfq_leaf_weight; diff --git a/block/blk-core.c b/block/blk-core.c index bf930f481d43..6946a4275e6f 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -83,18 +83,14 @@ void blk_queue_congestion_threshold(struct request_queue *q) * @bdev: device * * Locates the passed device's request queue and returns the address of its - * backing_dev_info - * - * Will return NULL if the request queue cannot be located. + * backing_dev_info. This function can only be called if @bdev is opened + * and the return value is never NULL. */ struct backing_dev_info *blk_get_backing_dev_info(struct block_device *bdev) { - struct backing_dev_info *ret = NULL; struct request_queue *q = bdev_get_queue(bdev); - if (q) - ret = &q->backing_dev_info; - return ret; + return &q->backing_dev_info; } EXPORT_SYMBOL(blk_get_backing_dev_info); @@ -933,9 +929,9 @@ static struct io_context *rq_ioc(struct bio *bio) * Get a free request from @q. This function may fail under memory * pressure or if @q is dead. * - * Must be callled with @q->queue_lock held and, - * Returns %NULL on failure, with @q->queue_lock held. - * Returns !%NULL on success, with @q->queue_lock *not held*. + * Must be called with @q->queue_lock held and, + * Returns ERR_PTR on failure, with @q->queue_lock held. + * Returns request pointer on success, with @q->queue_lock *not held*. */ static struct request *__get_request(struct request_list *rl, int rw_flags, struct bio *bio, gfp_t gfp_mask) @@ -949,7 +945,7 @@ static struct request *__get_request(struct request_list *rl, int rw_flags, int may_queue; if (unlikely(blk_queue_dying(q))) - return NULL; + return ERR_PTR(-ENODEV); may_queue = elv_may_queue(q, rw_flags); if (may_queue == ELV_MQUEUE_NO) @@ -974,7 +970,7 @@ static struct request *__get_request(struct request_list *rl, int rw_flags, * process is not a "batcher", and not * exempted by the IO scheduler */ - return NULL; + return ERR_PTR(-ENOMEM); } } } @@ -992,7 +988,7 @@ static struct request *__get_request(struct request_list *rl, int rw_flags, * allocated with any setting of ->nr_requests */ if (rl->count[is_sync] >= (3 * q->nr_requests / 2)) - return NULL; + return ERR_PTR(-ENOMEM); q->nr_rqs[is_sync]++; rl->count[is_sync]++; @@ -1097,7 +1093,7 @@ fail_alloc: rq_starved: if (unlikely(rl->count[is_sync] == 0)) rl->starved[is_sync] = 1; - return NULL; + return ERR_PTR(-ENOMEM); } /** @@ -1110,9 +1106,9 @@ rq_starved: * Get a free request from @q. If %__GFP_WAIT is set in @gfp_mask, this * function keeps retrying under memory pressure and fails iff @q is dead. * - * Must be callled with @q->queue_lock held and, - * Returns %NULL on failure, with @q->queue_lock held. - * Returns !%NULL on success, with @q->queue_lock *not held*. + * Must be called with @q->queue_lock held and, + * Returns ERR_PTR on failure, with @q->queue_lock held. + * Returns request pointer on success, with @q->queue_lock *not held*. */ static struct request *get_request(struct request_queue *q, int rw_flags, struct bio *bio, gfp_t gfp_mask) @@ -1125,12 +1121,12 @@ static struct request *get_request(struct request_queue *q, int rw_flags, rl = blk_get_rl(q, bio); /* transferred to @rq on success */ retry: rq = __get_request(rl, rw_flags, bio, gfp_mask); - if (rq) + if (!IS_ERR(rq)) return rq; if (!(gfp_mask & __GFP_WAIT) || unlikely(blk_queue_dying(q))) { blk_put_rl(rl); - return NULL; + return rq; } /* wait on @rl and retry */ @@ -1167,7 +1163,7 @@ static struct request *blk_old_get_request(struct request_queue *q, int rw, spin_lock_irq(q->queue_lock); rq = get_request(q, rw, NULL, gfp_mask); - if (!rq) + if (IS_ERR(rq)) spin_unlock_irq(q->queue_lock); /* q->queue_lock is unlocked at this point */ @@ -1219,8 +1215,8 @@ struct request *blk_make_request(struct request_queue *q, struct bio *bio, { struct request *rq = blk_get_request(q, bio_data_dir(bio), gfp_mask); - if (unlikely(!rq)) - return ERR_PTR(-ENOMEM); + if (IS_ERR(rq)) + return rq; blk_rq_set_block_pc(rq); @@ -1614,8 +1610,8 @@ get_rq: * Returns with the queue unlocked. */ req = get_request(q, rw_flags, bio, GFP_NOIO); - if (unlikely(!req)) { - bio_endio(bio, -ENODEV); /* @q is dead */ + if (IS_ERR(req)) { + bio_endio(bio, PTR_ERR(req)); /* @q is dead */ goto out_unlock; } diff --git a/block/blk-mq.c b/block/blk-mq.c index c88e6089746d..e743d28620b2 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -223,9 +223,11 @@ struct request *blk_mq_alloc_request(struct request_queue *q, int rw, gfp_t gfp, struct blk_mq_hw_ctx *hctx; struct request *rq; struct blk_mq_alloc_data alloc_data; + int ret; - if (blk_mq_queue_enter(q)) - return NULL; + ret = blk_mq_queue_enter(q); + if (ret) + return ERR_PTR(ret); ctx = blk_mq_get_ctx(q); hctx = q->mq_ops->map_queue(q, ctx->cpu); @@ -245,6 +247,8 @@ struct request *blk_mq_alloc_request(struct request_queue *q, int rw, gfp_t gfp, ctx = alloc_data.ctx; } blk_mq_put_ctx(ctx); + if (!rq) + return ERR_PTR(-EWOULDBLOCK); return rq; } EXPORT_SYMBOL(blk_mq_alloc_request); diff --git a/block/bsg.c b/block/bsg.c index ff46addde5d8..276e869e686c 100644 --- a/block/bsg.c +++ b/block/bsg.c @@ -270,8 +270,8 @@ bsg_map_hdr(struct bsg_device *bd, struct sg_io_v4 *hdr, fmode_t has_write_perm, * map scatter-gather elements separately and string them to request */ rq = blk_get_request(q, rw, GFP_KERNEL); - if (!rq) - return ERR_PTR(-ENOMEM); + if (IS_ERR(rq)) + return rq; blk_rq_set_block_pc(rq); ret = blk_fill_sgv4_hdr_rq(q, rq, hdr, bd, has_write_perm); @@ -285,8 +285,9 @@ bsg_map_hdr(struct bsg_device *bd, struct sg_io_v4 *hdr, fmode_t has_write_perm, } next_rq = blk_get_request(q, READ, GFP_KERNEL); - if (!next_rq) { - ret = -ENOMEM; + if (IS_ERR(next_rq)) { + ret = PTR_ERR(next_rq); + next_rq = NULL; goto out; } rq->next_rq = next_rq; diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c index 3f31cf9508e6..6f2751d305de 100644 --- a/block/cfq-iosched.c +++ b/block/cfq-iosched.c @@ -299,7 +299,7 @@ struct cfq_io_cq { struct cfq_ttime ttime; int ioprio; /* the current ioprio */ #ifdef CONFIG_CFQ_GROUP_IOSCHED - uint64_t blkcg_id; /* the current blkcg ID */ + uint64_t blkcg_serial_nr; /* the current blkcg serial */ #endif }; @@ -3547,17 +3547,17 @@ static void check_blkcg_changed(struct cfq_io_cq *cic, struct bio *bio) { struct cfq_data *cfqd = cic_to_cfqd(cic); struct cfq_queue *sync_cfqq; - uint64_t id; + uint64_t serial_nr; rcu_read_lock(); - id = bio_blkcg(bio)->id; + serial_nr = bio_blkcg(bio)->css.serial_nr; rcu_read_unlock(); /* * Check whether blkcg has changed. The condition may trigger * spuriously on a newly created cic but there's no harm. */ - if (unlikely(!cfqd) || likely(cic->blkcg_id == id)) + if (unlikely(!cfqd) || likely(cic->blkcg_serial_nr == serial_nr)) return; sync_cfqq = cic_to_cfqq(cic, 1); @@ -3571,7 +3571,7 @@ static void check_blkcg_changed(struct cfq_io_cq *cic, struct bio *bio) cfq_put_queue(sync_cfqq); } - cic->blkcg_id = id; + cic->blkcg_serial_nr = serial_nr; } #else static inline void check_blkcg_changed(struct cfq_io_cq *cic, struct bio *bio) { } diff --git a/block/compat_ioctl.c b/block/compat_ioctl.c index 18b282ce361e..f678c733df40 100644 --- a/block/compat_ioctl.c +++ b/block/compat_ioctl.c @@ -709,8 +709,6 @@ long compat_blkdev_ioctl(struct file *file, unsigned cmd, unsigned long arg) if (!arg) return -EINVAL; bdi = blk_get_backing_dev_info(bdev); - if (bdi == NULL) - return -ENOTTY; return compat_put_long(arg, (bdi->ra_pages * PAGE_CACHE_SIZE) / 512); case BLKROGET: /* compatible */ @@ -731,8 +729,6 @@ long compat_blkdev_ioctl(struct file *file, unsigned cmd, unsigned long arg) if (!capable(CAP_SYS_ADMIN)) return -EACCES; bdi = blk_get_backing_dev_info(bdev); - if (bdi == NULL) - return -ENOTTY; bdi->ra_pages = (arg * 512) / PAGE_CACHE_SIZE; return 0; case BLKGETSIZE: diff --git a/block/ioctl.c b/block/ioctl.c index d6cda8147c91..6c7bf903742f 100644 --- a/block/ioctl.c +++ b/block/ioctl.c @@ -356,8 +356,6 @@ int blkdev_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd, if (!arg) return -EINVAL; bdi = blk_get_backing_dev_info(bdev); - if (bdi == NULL) - return -ENOTTY; return put_long(arg, (bdi->ra_pages * PAGE_CACHE_SIZE) / 512); case BLKROGET: return put_int(arg, bdev_read_only(bdev) != 0); @@ -386,8 +384,6 @@ int blkdev_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd, if(!capable(CAP_SYS_ADMIN)) return -EACCES; bdi = blk_get_backing_dev_info(bdev); - if (bdi == NULL) - return -ENOTTY; bdi->ra_pages = (arg * 512) / PAGE_CACHE_SIZE; return 0; case BLKBSZSET: diff --git a/block/scsi_ioctl.c b/block/scsi_ioctl.c index 9b8eaeca6a79..abb2e65b24cc 100644 --- a/block/scsi_ioctl.c +++ b/block/scsi_ioctl.c @@ -316,8 +316,8 @@ static int sg_io(struct request_queue *q, struct gendisk *bd_disk, ret = -ENOMEM; rq = blk_get_request(q, writing ? WRITE : READ, GFP_KERNEL); - if (!rq) - goto out; + if (IS_ERR(rq)) + return PTR_ERR(rq); blk_rq_set_block_pc(rq); if (hdr->cmd_len > BLK_MAX_CDB) { @@ -387,7 +387,6 @@ out_free_cdb: kfree(rq->cmd); out_put_request: blk_put_request(rq); -out: return ret; } @@ -457,8 +456,8 @@ int sg_scsi_ioctl(struct request_queue *q, struct gendisk *disk, fmode_t mode, } rq = blk_get_request(q, in_len ? WRITE : READ, __GFP_WAIT); - if (!rq) { - err = -ENOMEM; + if (IS_ERR(rq)) { + err = PTR_ERR(rq); goto error; } blk_rq_set_block_pc(rq); @@ -548,6 +547,8 @@ static int __blk_send_generic(struct request_queue *q, struct gendisk *bd_disk, int err; rq = blk_get_request(q, WRITE, __GFP_WAIT); + if (IS_ERR(rq)) + return PTR_ERR(rq); blk_rq_set_block_pc(rq); rq->timeout = BLK_DEFAULT_SG_TIMEOUT; rq->cmd[0] = cmd; diff --git a/drivers/block/paride/pd.c b/drivers/block/paride/pd.c index fea7e76a00de..d48715b287e6 100644 --- a/drivers/block/paride/pd.c +++ b/drivers/block/paride/pd.c @@ -722,6 +722,8 @@ static int pd_special_command(struct pd_unit *disk, int err = 0; rq = blk_get_request(disk->gd->queue, READ, __GFP_WAIT); + if (IS_ERR(rq)) + return PTR_ERR(rq); rq->cmd_type = REQ_TYPE_SPECIAL; rq->special = func; diff --git a/drivers/block/pktcdvd.c b/drivers/block/pktcdvd.c index 758ac442c5b5..09e628dafd9d 100644 --- a/drivers/block/pktcdvd.c +++ b/drivers/block/pktcdvd.c @@ -704,6 +704,8 @@ static int pkt_generic_packet(struct pktcdvd_device *pd, struct packet_command * rq = blk_get_request(q, (cgc->data_direction == CGC_DATA_WRITE) ? WRITE : READ, __GFP_WAIT); + if (IS_ERR(rq)) + return PTR_ERR(rq); blk_rq_set_block_pc(rq); if (cgc->buflen) { diff --git a/drivers/block/sx8.c b/drivers/block/sx8.c index d5e2d12b9d9e..5d552857de41 100644 --- a/drivers/block/sx8.c +++ b/drivers/block/sx8.c @@ -568,7 +568,7 @@ static struct carm_request *carm_get_special(struct carm_host *host) return NULL; rq = blk_get_request(host->oob_q, WRITE /* bogus */, GFP_KERNEL); - if (!rq) { + if (IS_ERR(rq)) { spin_lock_irqsave(&host->lock, flags); carm_put_request(host, crq); spin_unlock_irqrestore(&host->lock, flags); diff --git a/drivers/cdrom/cdrom.c b/drivers/cdrom/cdrom.c index 898b84bba28a..5d28a45d2960 100644 --- a/drivers/cdrom/cdrom.c +++ b/drivers/cdrom/cdrom.c @@ -2180,8 +2180,8 @@ static int cdrom_read_cdda_bpc(struct cdrom_device_info *cdi, __u8 __user *ubuf, len = nr * CD_FRAMESIZE_RAW; rq = blk_get_request(q, READ, GFP_KERNEL); - if (!rq) { - ret = -ENOMEM; + if (IS_ERR(rq)) { + ret = PTR_ERR(rq); break; } blk_rq_set_block_pc(rq); diff --git a/drivers/ide/ide-park.c b/drivers/ide/ide-park.c index f41558a0bcd1..ca958604cda2 100644 --- a/drivers/ide/ide-park.c +++ b/drivers/ide/ide-park.c @@ -46,7 +46,7 @@ static void issue_park_cmd(ide_drive_t *drive, unsigned long timeout) * timeout has expired, so power management will be reenabled. */ rq = blk_get_request(q, READ, GFP_NOWAIT); - if (unlikely(!rq)) + if (IS_ERR(rq)) goto out; rq->cmd[0] = REQ_UNPARK_HEADS; diff --git a/drivers/scsi/device_handler/scsi_dh_alua.c b/drivers/scsi/device_handler/scsi_dh_alua.c index 7bcf67eec921..e99507ed0e3c 100644 --- a/drivers/scsi/device_handler/scsi_dh_alua.c +++ b/drivers/scsi/device_handler/scsi_dh_alua.c @@ -115,7 +115,7 @@ static struct request *get_alua_req(struct scsi_device *sdev, rq = blk_get_request(q, rw, GFP_NOIO); - if (!rq) { + if (IS_ERR(rq)) { sdev_printk(KERN_INFO, sdev, "%s: blk_get_request failed\n", __func__); return NULL; diff --git a/drivers/scsi/device_handler/scsi_dh_emc.c b/drivers/scsi/device_handler/scsi_dh_emc.c index 6f07f7fe3aa1..84765384c47c 100644 --- a/drivers/scsi/device_handler/scsi_dh_emc.c +++ b/drivers/scsi/device_handler/scsi_dh_emc.c @@ -275,7 +275,7 @@ static struct request *get_req(struct scsi_device *sdev, int cmd, rq = blk_get_request(sdev->request_queue, (cmd != INQUIRY) ? WRITE : READ, GFP_NOIO); - if (!rq) { + if (IS_ERR(rq)) { sdev_printk(KERN_INFO, sdev, "get_req: blk_get_request failed"); return NULL; } diff --git a/drivers/scsi/device_handler/scsi_dh_hp_sw.c b/drivers/scsi/device_handler/scsi_dh_hp_sw.c index e9d9fea9e272..4ee2759f5299 100644 --- a/drivers/scsi/device_handler/scsi_dh_hp_sw.c +++ b/drivers/scsi/device_handler/scsi_dh_hp_sw.c @@ -117,7 +117,7 @@ static int hp_sw_tur(struct scsi_device *sdev, struct hp_sw_dh_data *h) retry: req = blk_get_request(sdev->request_queue, WRITE, GFP_NOIO); - if (!req) + if (IS_ERR(req)) return SCSI_DH_RES_TEMP_UNAVAIL; blk_rq_set_block_pc(req); @@ -247,7 +247,7 @@ static int hp_sw_start_stop(struct hp_sw_dh_data *h) struct request *req; req = blk_get_request(h->sdev->request_queue, WRITE, GFP_ATOMIC); - if (!req) + if (IS_ERR(req)) return SCSI_DH_RES_TEMP_UNAVAIL; blk_rq_set_block_pc(req); diff --git a/drivers/scsi/device_handler/scsi_dh_rdac.c b/drivers/scsi/device_handler/scsi_dh_rdac.c index 826069db9848..1b5bc9293e37 100644 --- a/drivers/scsi/device_handler/scsi_dh_rdac.c +++ b/drivers/scsi/device_handler/scsi_dh_rdac.c @@ -274,7 +274,7 @@ static struct request *get_rdac_req(struct scsi_device *sdev, rq = blk_get_request(q, rw, GFP_NOIO); - if (!rq) { + if (IS_ERR(rq)) { sdev_printk(KERN_INFO, sdev, "get_rdac_req: blk_get_request failed.\n"); return NULL; diff --git a/drivers/scsi/osd/osd_initiator.c b/drivers/scsi/osd/osd_initiator.c index 5f4cbf0c4759..fd19fd8468ac 100644 --- a/drivers/scsi/osd/osd_initiator.c +++ b/drivers/scsi/osd/osd_initiator.c @@ -1567,8 +1567,8 @@ static struct request *_make_request(struct request_queue *q, bool has_write, struct request *req; req = blk_get_request(q, has_write ? WRITE : READ, flags); - if (unlikely(!req)) - return ERR_PTR(-ENOMEM); + if (IS_ERR(req)) + return req; blk_rq_set_block_pc(req); return req; diff --git a/drivers/scsi/osst.c b/drivers/scsi/osst.c index 0727ea7cc387..dff37a250d79 100644 --- a/drivers/scsi/osst.c +++ b/drivers/scsi/osst.c @@ -362,7 +362,7 @@ static int osst_execute(struct osst_request *SRpnt, const unsigned char *cmd, int write = (data_direction == DMA_TO_DEVICE); req = blk_get_request(SRpnt->stp->device->request_queue, write, GFP_KERNEL); - if (!req) + if (IS_ERR(req)) return DRIVER_ERROR << 24; blk_rq_set_block_pc(req); diff --git a/drivers/scsi/scsi_error.c b/drivers/scsi/scsi_error.c index 5db8454474ee..a2c3d3d255a1 100644 --- a/drivers/scsi/scsi_error.c +++ b/drivers/scsi/scsi_error.c @@ -1960,6 +1960,8 @@ static void scsi_eh_lock_door(struct scsi_device *sdev) * request becomes available */ req = blk_get_request(sdev->request_queue, READ, GFP_KERNEL); + if (IS_ERR(req)) + return; blk_rq_set_block_pc(req); diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c index d837dc180522..1f2bae475cb7 100644 --- a/drivers/scsi/scsi_lib.c +++ b/drivers/scsi/scsi_lib.c @@ -221,7 +221,7 @@ int scsi_execute(struct scsi_device *sdev, const unsigned char *cmd, int ret = DRIVER_ERROR << 24; req = blk_get_request(sdev->request_queue, write, __GFP_WAIT); - if (!req) + if (IS_ERR(req)) return ret; blk_rq_set_block_pc(req); diff --git a/drivers/scsi/sg.c b/drivers/scsi/sg.c index 01cf88888797..60354449d9ed 100644 --- a/drivers/scsi/sg.c +++ b/drivers/scsi/sg.c @@ -1711,9 +1711,9 @@ sg_start_req(Sg_request *srp, unsigned char *cmd) } rq = blk_get_request(q, rw, GFP_ATOMIC); - if (!rq) { + if (IS_ERR(rq)) { kfree(long_cmdp); - return -ENOMEM; + return PTR_ERR(rq); } blk_rq_set_block_pc(rq); diff --git a/drivers/scsi/st.c b/drivers/scsi/st.c index aff9689de0f7..59db5bfc11db 100644 --- a/drivers/scsi/st.c +++ b/drivers/scsi/st.c @@ -490,7 +490,7 @@ static int st_scsi_execute(struct st_request *SRpnt, const unsigned char *cmd, req = blk_get_request(SRpnt->stp->device->request_queue, write, GFP_KERNEL); - if (!req) + if (IS_ERR(req)) return DRIVER_ERROR << 24; blk_rq_set_block_pc(req); diff --git a/drivers/target/target_core_pscsi.c b/drivers/target/target_core_pscsi.c index 943b1dbe859a..70d9f6dabba0 100644 --- a/drivers/target/target_core_pscsi.c +++ b/drivers/target/target_core_pscsi.c @@ -1050,7 +1050,7 @@ pscsi_execute_cmd(struct se_cmd *cmd) req = blk_get_request(pdv->pdv_sd->request_queue, (data_direction == DMA_TO_DEVICE), GFP_KERNEL); - if (!req) { + if (IS_ERR(req)) { pr_err("PSCSI: blk_get_request() failed\n"); ret = TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE; goto fail; diff --git a/fs/block_dev.c b/fs/block_dev.c index 6d7274619bf9..cc8d68ac29aa 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -50,32 +50,22 @@ inline struct block_device *I_BDEV(struct inode *inode) EXPORT_SYMBOL(I_BDEV); /* - * Move the inode from its current bdi to a new bdi. If the inode is dirty we - * need to move it onto the dirty list of @dst so that the inode is always on - * the right list. + * Move the inode from its current bdi to a new bdi. Make sure the inode + * is clean before moving so that it doesn't linger on the old bdi. */ static void bdev_inode_switch_bdi(struct inode *inode, struct backing_dev_info *dst) { - struct backing_dev_info *old = inode->i_data.backing_dev_info; - bool wakeup_bdi = false; - - if (unlikely(dst == old)) /* deadlock avoidance */ - return; - bdi_lock_two(&old->wb, &dst->wb); - spin_lock(&inode->i_lock); - inode->i_data.backing_dev_info = dst; - if (inode->i_state & I_DIRTY) { - if (bdi_cap_writeback_dirty(dst) && !wb_has_dirty_io(&dst->wb)) - wakeup_bdi = true; - list_move(&inode->i_wb_list, &dst->wb.b_dirty); + while (true) { + spin_lock(&inode->i_lock); + if (!(inode->i_state & I_DIRTY)) { + inode->i_data.backing_dev_info = dst; + spin_unlock(&inode->i_lock); + return; + } + spin_unlock(&inode->i_lock); + WARN_ON_ONCE(write_inode_now(inode, true)); } - spin_unlock(&inode->i_lock); - spin_unlock(&old->wb.list_lock); - spin_unlock(&dst->wb.list_lock); - - if (wakeup_bdi) - bdi_wakeup_thread_delayed(dst); } /* Kill _all_ buffers and pagecache , dirty or not.. */ @@ -1173,8 +1163,6 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part) if (!ret) { bd_set_size(bdev,(loff_t)get_capacity(disk)<<9); bdi = blk_get_backing_dev_info(bdev); - if (bdi == NULL) - bdi = &default_backing_dev_info; bdev_inode_switch_bdi(bdev->bd_inode, bdi); } diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index a1d36e62179c..7e221b090308 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -1699,7 +1699,7 @@ static int btrfs_congested_fn(void *congested_data, int bdi_bits) if (!device->bdev) continue; bdi = blk_get_backing_dev_info(device->bdev); - if (bdi && bdi_congested(bdi, bdi_bits)) { + if (bdi_congested(bdi, bdi_bits)) { ret = 1; break; } diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c index cd7b8ca9b064..497fcde381d7 100644 --- a/fs/xfs/xfs_buf.c +++ b/fs/xfs/xfs_buf.c @@ -1678,8 +1678,6 @@ xfs_alloc_buftarg( btp->bt_dev = bdev->bd_dev; btp->bt_bdev = bdev; btp->bt_bdi = blk_get_backing_dev_info(bdev); - if (!btp->bt_bdi) - goto error; if (xfs_setsize_buftarg_early(btp, bdev)) goto error; diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index e488e9459a93..5da6012b7a14 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -28,12 +28,10 @@ struct dentry; * Bits in backing_dev_info.state */ enum bdi_state { - BDI_wb_alloc, /* Default embedded wb allocated */ BDI_async_congested, /* The async (write) queue is getting full */ BDI_sync_congested, /* The sync queue is getting full */ BDI_registered, /* bdi_register() was done */ BDI_writeback_running, /* Writeback is in progress */ - BDI_unused, /* Available bits start here */ }; typedef int (congested_fn)(void *, int); @@ -50,7 +48,6 @@ enum bdi_stat_item { struct bdi_writeback { struct backing_dev_info *bdi; /* our parent bdi */ - unsigned int nr; unsigned long last_old_flush; /* last old data flush */ @@ -124,7 +121,6 @@ void bdi_start_background_writeback(struct backing_dev_info *bdi); void bdi_writeback_workfn(struct work_struct *work); int bdi_has_dirty_io(struct backing_dev_info *bdi); void bdi_wakeup_thread_delayed(struct backing_dev_info *bdi); -void bdi_lock_two(struct bdi_writeback *wb1, struct bdi_writeback *wb2); extern spinlock_t bdi_lock; extern struct list_head bdi_list; diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 518b46555b80..e267bf0db559 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -865,7 +865,7 @@ extern void blk_execute_rq_nowait(struct request_queue *, struct gendisk *, static inline struct request_queue *bdev_get_queue(struct block_device *bdev) { - return bdev->bd_disk->queue; + return bdev->bd_disk->queue; /* this is never NULL */ } /* diff --git a/mm/backing-dev.c b/mm/backing-dev.c index 1706cbbdf5f0..7d63d5e9d3de 100644 --- a/mm/backing-dev.c +++ b/mm/backing-dev.c @@ -40,7 +40,7 @@ LIST_HEAD(bdi_list); /* bdi_wq serves all asynchronous writeback tasks */ struct workqueue_struct *bdi_wq; -void bdi_lock_two(struct bdi_writeback *wb1, struct bdi_writeback *wb2) +static void bdi_lock_two(struct bdi_writeback *wb1, struct bdi_writeback *wb2) { if (wb1 < wb2) { spin_lock(&wb1->list_lock); @@ -376,13 +376,7 @@ static void bdi_wb_shutdown(struct backing_dev_info *bdi) mod_delayed_work(bdi_wq, &bdi->wb.dwork, 0); flush_delayed_work(&bdi->wb.dwork); WARN_ON(!list_empty(&bdi->work_list)); - - /* - * This shouldn't be necessary unless @bdi for some reason has - * unflushed dirty IO after work_list is drained. Do it anyway - * just in case. - */ - cancel_delayed_work_sync(&bdi->wb.dwork); + WARN_ON(delayed_work_pending(&bdi->wb.dwork)); } /* @@ -402,21 +396,15 @@ static void bdi_prune_sb(struct backing_dev_info *bdi) void bdi_unregister(struct backing_dev_info *bdi) { - struct device *dev = bdi->dev; - - if (dev) { + if (bdi->dev) { bdi_set_min_ratio(bdi, 0); trace_writeback_bdi_unregister(bdi); bdi_prune_sb(bdi); bdi_wb_shutdown(bdi); bdi_debug_unregister(bdi); - - spin_lock_bh(&bdi->wb_lock); + device_unregister(bdi->dev); bdi->dev = NULL; - spin_unlock_bh(&bdi->wb_lock); - - device_unregister(dev); } } EXPORT_SYMBOL(bdi_unregister); @@ -487,8 +475,17 @@ void bdi_destroy(struct backing_dev_info *bdi) int i; /* - * Splice our entries to the default_backing_dev_info, if this - * bdi disappears + * Splice our entries to the default_backing_dev_info. This + * condition shouldn't happen. @wb must be empty at this point and + * dirty inodes on it might cause other issues. This workaround is + * added by ce5f8e779519 ("writeback: splice dirty inode entries to + * default bdi on bdi_destroy()") without root-causing the issue. + * + * http://lkml.kernel.org/g/1253038617-30204-11-git-send-email-jens.axboe@oracle.com + * http://thread.gmane.org/gmane.linux.file-systems/35341/focus=35350 + * + * We should probably add WARN_ON() to find out whether it still + * happens and track it down if so. */ if (bdi_has_dirty_io(bdi)) { struct bdi_writeback *dst = &default_backing_dev_info.wb; @@ -503,12 +500,7 @@ void bdi_destroy(struct backing_dev_info *bdi) bdi_unregister(bdi); - /* - * If bdi_unregister() had already been called earlier, the dwork - * could still be pending because bdi_prune_sb() can race with the - * bdi_wakeup_thread_delayed() calls from __mark_inode_dirty(). - */ - cancel_delayed_work_sync(&bdi->wb.dwork); + WARN_ON(delayed_work_pending(&bdi->wb.dwork)); for (i = 0; i < NR_BDI_STAT_ITEMS; i++) percpu_counter_destroy(&bdi->bdi_stat[i]); |