diff --git a/Documentation/block/cfq-iosched.txt b/Documentation/block/cfq-iosched.txt new file mode 100644 index 0000000000000000000000000000000000000000..e578feed6d818f13b148f16cba3dbca8505362fc --- /dev/null +++ b/Documentation/block/cfq-iosched.txt @@ -0,0 +1,45 @@ +CFQ ioscheduler tunables +======================== + +slice_idle +---------- +This specifies how long CFQ should idle for next request on certain cfq queues +(for sequential workloads) and service trees (for random workloads) before +queue is expired and CFQ selects next queue to dispatch from. + +By default slice_idle is a non-zero value. That means by default we idle on +queues/service trees. This can be very helpful on highly seeky media like +single spindle SATA/SAS disks where we can cut down on overall number of +seeks and see improved throughput. + +Setting slice_idle to 0 will remove all the idling on queues/service tree +level and one should see an overall improved throughput on faster storage +devices like multiple SATA/SAS disks in hardware RAID configuration. The down +side is that isolation provided from WRITES also goes down and notion of +IO priority becomes weaker. + +So depending on storage and workload, it might be useful to set slice_idle=0. +In general I think for SATA/SAS disks and software RAID of SATA/SAS disks +keeping slice_idle enabled should be useful. For any configurations where +there are multiple spindles behind single LUN (Host based hardware RAID +controller or for storage arrays), setting slice_idle=0 might end up in better +throughput and acceptable latencies. + +CFQ IOPS Mode for group scheduling +=================================== +Basic CFQ design is to provide priority based time slices. Higher priority +process gets bigger time slice and lower priority process gets smaller time +slice. Measuring time becomes harder if storage is fast and supports NCQ and +it would be better to dispatch multiple requests from multiple cfq queues in +request queue at a time. In such scenario, it is not possible to measure time +consumed by single queue accurately. + +What is possible though is to measure number of requests dispatched from a +single queue and also allow dispatch from multiple cfq queue at the same time. +This effectively becomes the fairness in terms of IOPS (IO operations per +second). + +If one sets slice_idle=0 and if storage supports NCQ, CFQ internally switches +to IOPS mode and starts providing fairness in terms of number of requests +dispatched. Note that this mode switching takes effect only for group +scheduling. For non-cgroup users nothing should change. diff --git a/Documentation/cgroups/blkio-controller.txt b/Documentation/cgroups/blkio-controller.txt index 48e0b21b00594dac1971472bef9105e04d2bfa77..6919d62591d97580d3132f539e0edd50d9985449 100644 --- a/Documentation/cgroups/blkio-controller.txt +++ b/Documentation/cgroups/blkio-controller.txt @@ -217,6 +217,7 @@ Details of cgroup files CFQ sysfs tunable ================= /sys/block//queue/iosched/group_isolation +----------------------------------------------- If group_isolation=1, it provides stronger isolation between groups at the expense of throughput. By default group_isolation is 0. In general that @@ -243,6 +244,33 @@ By default one should run with group_isolation=0. If that is not sufficient and one wants stronger isolation between groups, then set group_isolation=1 but this will come at cost of reduced throughput. +/sys/block//queue/iosched/slice_idle +------------------------------------------ +On a faster hardware CFQ can be slow, especially with sequential workload. +This happens because CFQ idles on a single queue and single queue might not +drive deeper request queue depths to keep the storage busy. In such scenarios +one can try setting slice_idle=0 and that would switch CFQ to IOPS +(IO operations per second) mode on NCQ supporting hardware. + +That means CFQ will not idle between cfq queues of a cfq group and hence be +able to driver higher queue depth and achieve better throughput. That also +means that cfq provides fairness among groups in terms of IOPS and not in +terms of disk time. + +/sys/block//queue/iosched/group_idle +------------------------------------------ +If one disables idling on individual cfq queues and cfq service trees by +setting slice_idle=0, group_idle kicks in. That means CFQ will still idle +on the group in an attempt to provide fairness among groups. + +By default group_idle is same as slice_idle and does not do anything if +slice_idle is enabled. + +One can experience an overall throughput drop if you have created multiple +groups and put applications in that group which are not driving enough +IO to keep disk busy. In that case set group_idle=0, and CFQ will not idle +on individual groups and throughput should improve. + What works ========== - Currently only sync IO queues are support. All the buffered writes are diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c index a6809645d212d9cf970b85473e3d9c05bc4ba652..2fef1ef931a06756d364707c28d97e6c440aa484 100644 --- a/block/blk-cgroup.c +++ b/block/blk-cgroup.c @@ -966,7 +966,7 @@ blkiocg_create(struct cgroup_subsys *subsys, struct cgroup *cgroup) /* Currently we do not support hierarchy deeper than two level (0,1) */ if (parent != cgroup->top_cgroup) - return ERR_PTR(-EINVAL); + return ERR_PTR(-EPERM); blkcg = kzalloc(sizeof(*blkcg), GFP_KERNEL); if (!blkcg) diff --git a/block/blk-core.c b/block/blk-core.c index ee1a1e7e63ccfc3e735566e3725febee1890bb2e..32a1c123dfb36a5fff24857221a9a4d1b79131bf 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -1198,9 +1198,9 @@ static int __make_request(struct request_queue *q, struct bio *bio) int el_ret; unsigned int bytes = bio->bi_size; const unsigned short prio = bio_prio(bio); - const bool sync = (bio->bi_rw & REQ_SYNC); - const bool unplug = (bio->bi_rw & REQ_UNPLUG); - const unsigned int ff = bio->bi_rw & REQ_FAILFAST_MASK; + const bool sync = !!(bio->bi_rw & REQ_SYNC); + const bool unplug = !!(bio->bi_rw & REQ_UNPLUG); + const unsigned long ff = bio->bi_rw & REQ_FAILFAST_MASK; int rw_flags; if ((bio->bi_rw & REQ_HARDBARRIER) && diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c index 001ab18078f5ba1b8c6f34e021cc02ef401d98b6..0749b89c68852fc824e4afa862d871814c56ddd8 100644 --- a/block/blk-sysfs.c +++ b/block/blk-sysfs.c @@ -511,6 +511,7 @@ int blk_register_queue(struct gendisk *disk) kobject_uevent(&q->kobj, KOBJ_REMOVE); kobject_del(&q->kobj); blk_trace_remove_sysfs(disk_to_dev(disk)); + kobject_put(&dev->kobj); return ret; } diff --git a/block/blk.h b/block/blk.h index 6e7dc87141e48230d0eb82c2bdcf770b0ac581a9..d6b911ac002cd9ef14c76535a6b3b6814243079b 100644 --- a/block/blk.h +++ b/block/blk.h @@ -142,14 +142,18 @@ static inline int queue_congestion_off_threshold(struct request_queue *q) static inline int blk_cpu_to_group(int cpu) { + int group = NR_CPUS; #ifdef CONFIG_SCHED_MC const struct cpumask *mask = cpu_coregroup_mask(cpu); - return cpumask_first(mask); + group = cpumask_first(mask); #elif defined(CONFIG_SCHED_SMT) - return cpumask_first(topology_thread_cpumask(cpu)); + group = cpumask_first(topology_thread_cpumask(cpu)); #else return cpu; #endif + if (likely(group < NR_CPUS)) + return group; + return cpu; } /* diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c index eb4086f7dfef9eb7efc6d202fb7a979919a551b8..f65c6f01c47580b7e24e7fc6bda1764668cf4d21 100644 --- a/block/cfq-iosched.c +++ b/block/cfq-iosched.c @@ -30,6 +30,7 @@ static const int cfq_slice_sync = HZ / 10; static int cfq_slice_async = HZ / 25; static const int cfq_slice_async_rq = 2; static int cfq_slice_idle = HZ / 125; +static int cfq_group_idle = HZ / 125; static const int cfq_target_latency = HZ * 3/10; /* 300 ms */ static const int cfq_hist_divisor = 4; @@ -147,6 +148,8 @@ struct cfq_queue { struct cfq_queue *new_cfqq; struct cfq_group *cfqg; struct cfq_group *orig_cfqg; + /* Number of sectors dispatched from queue in single dispatch round */ + unsigned long nr_sectors; }; /* @@ -198,6 +201,8 @@ struct cfq_group { struct hlist_node cfqd_node; atomic_t ref; #endif + /* number of requests that are on the dispatch list or inside driver */ + int dispatched; }; /* @@ -271,6 +276,7 @@ struct cfq_data { unsigned int cfq_slice[2]; unsigned int cfq_slice_async_rq; unsigned int cfq_slice_idle; + unsigned int cfq_group_idle; unsigned int cfq_latency; unsigned int cfq_group_isolation; @@ -378,6 +384,21 @@ CFQ_CFQQ_FNS(wait_busy); &cfqg->service_trees[i][j]: NULL) \ +static inline bool iops_mode(struct cfq_data *cfqd) +{ + /* + * If we are not idling on queues and it is a NCQ drive, parallel + * execution of requests is on and measuring time is not possible + * in most of the cases until and unless we drive shallower queue + * depths and that becomes a performance bottleneck. In such cases + * switch to start providing fairness in terms of number of IOs. + */ + if (!cfqd->cfq_slice_idle && cfqd->hw_tag) + return true; + else + return false; +} + static inline enum wl_prio_t cfqq_prio(struct cfq_queue *cfqq) { if (cfq_class_idle(cfqq)) @@ -906,7 +927,6 @@ static inline unsigned int cfq_cfqq_slice_usage(struct cfq_queue *cfqq) slice_used = cfqq->allocated_slice; } - cfq_log_cfqq(cfqq->cfqd, cfqq, "sl_used=%u", slice_used); return slice_used; } @@ -914,19 +934,21 @@ static void cfq_group_served(struct cfq_data *cfqd, struct cfq_group *cfqg, struct cfq_queue *cfqq) { struct cfq_rb_root *st = &cfqd->grp_service_tree; - unsigned int used_sl, charge_sl; + unsigned int used_sl, charge; int nr_sync = cfqg->nr_cfqq - cfqg_busy_async_queues(cfqd, cfqg) - cfqg->service_tree_idle.count; BUG_ON(nr_sync < 0); - used_sl = charge_sl = cfq_cfqq_slice_usage(cfqq); + used_sl = charge = cfq_cfqq_slice_usage(cfqq); - if (!cfq_cfqq_sync(cfqq) && !nr_sync) - charge_sl = cfqq->allocated_slice; + if (iops_mode(cfqd)) + charge = cfqq->slice_dispatch; + else if (!cfq_cfqq_sync(cfqq) && !nr_sync) + charge = cfqq->allocated_slice; /* Can't update vdisktime while group is on service tree */ cfq_rb_erase(&cfqg->rb_node, st); - cfqg->vdisktime += cfq_scale_slice(charge_sl, cfqg); + cfqg->vdisktime += cfq_scale_slice(charge, cfqg); __cfq_group_service_tree_add(st, cfqg); /* This group is being expired. Save the context */ @@ -940,6 +962,9 @@ static void cfq_group_served(struct cfq_data *cfqd, struct cfq_group *cfqg, cfq_log_cfqg(cfqd, cfqg, "served: vt=%llu min_vt=%llu", cfqg->vdisktime, st->min_vdisktime); + cfq_log_cfqq(cfqq->cfqd, cfqq, "sl_used=%u disp=%u charge=%u iops=%u" + " sect=%u", used_sl, cfqq->slice_dispatch, charge, + iops_mode(cfqd), cfqq->nr_sectors); cfq_blkiocg_update_timeslice_used(&cfqg->blkg, used_sl); cfq_blkiocg_set_start_empty_time(&cfqg->blkg); } @@ -1587,6 +1612,7 @@ static void __cfq_set_active_queue(struct cfq_data *cfqd, cfqq->allocated_slice = 0; cfqq->slice_end = 0; cfqq->slice_dispatch = 0; + cfqq->nr_sectors = 0; cfq_clear_cfqq_wait_request(cfqq); cfq_clear_cfqq_must_dispatch(cfqq); @@ -1839,6 +1865,9 @@ static bool cfq_should_idle(struct cfq_data *cfqd, struct cfq_queue *cfqq) BUG_ON(!service_tree); BUG_ON(!service_tree->count); + if (!cfqd->cfq_slice_idle) + return false; + /* We never do for idle class queues. */ if (prio == IDLE_WORKLOAD) return false; @@ -1863,7 +1892,7 @@ static void cfq_arm_slice_timer(struct cfq_data *cfqd) { struct cfq_queue *cfqq = cfqd->active_queue; struct cfq_io_context *cic; - unsigned long sl; + unsigned long sl, group_idle = 0; /* * SSD device without seek penalty, disable idling. But only do so @@ -1879,8 +1908,13 @@ static void cfq_arm_slice_timer(struct cfq_data *cfqd) /* * idle is disabled, either manually or by past process history */ - if (!cfqd->cfq_slice_idle || !cfq_should_idle(cfqd, cfqq)) - return; + if (!cfq_should_idle(cfqd, cfqq)) { + /* no queue idling. Check for group idling */ + if (cfqd->cfq_group_idle) + group_idle = cfqd->cfq_group_idle; + else + return; + } /* * still active requests from this queue, don't idle @@ -1907,13 +1941,21 @@ static void cfq_arm_slice_timer(struct cfq_data *cfqd) return; } + /* There are other queues in the group, don't do group idle */ + if (group_idle && cfqq->cfqg->nr_cfqq > 1) + return; + cfq_mark_cfqq_wait_request(cfqq); - sl = cfqd->cfq_slice_idle; + if (group_idle) + sl = cfqd->cfq_group_idle; + else + sl = cfqd->cfq_slice_idle; mod_timer(&cfqd->idle_slice_timer, jiffies + sl); cfq_blkiocg_update_set_idle_time_stats(&cfqq->cfqg->blkg); - cfq_log_cfqq(cfqd, cfqq, "arm_idle: %lu", sl); + cfq_log_cfqq(cfqd, cfqq, "arm_idle: %lu group_idle: %d", sl, + group_idle ? 1 : 0); } /* @@ -1929,9 +1971,11 @@ static void cfq_dispatch_insert(struct request_queue *q, struct request *rq) cfqq->next_rq = cfq_find_next_rq(cfqd, cfqq, rq); cfq_remove_request(rq); cfqq->dispatched++; + (RQ_CFQG(rq))->dispatched++; elv_dispatch_sort(q, rq); cfqd->rq_in_flight[cfq_cfqq_sync(cfqq)]++; + cfqq->nr_sectors += blk_rq_sectors(rq); cfq_blkiocg_update_dispatch_stats(&cfqq->cfqg->blkg, blk_rq_bytes(rq), rq_data_dir(rq), rq_is_sync(rq)); } @@ -2198,7 +2242,7 @@ static struct cfq_queue *cfq_select_queue(struct cfq_data *cfqd) cfqq = NULL; goto keep_queue; } else - goto expire; + goto check_group_idle; } /* @@ -2226,8 +2270,23 @@ static struct cfq_queue *cfq_select_queue(struct cfq_data *cfqd) * flight or is idling for a new request, allow either of these * conditions to happen (or time out) before selecting a new queue. */ - if (timer_pending(&cfqd->idle_slice_timer) || - (cfqq->dispatched && cfq_should_idle(cfqd, cfqq))) { + if (timer_pending(&cfqd->idle_slice_timer)) { + cfqq = NULL; + goto keep_queue; + } + + if (cfqq->dispatched && cfq_should_idle(cfqd, cfqq)) { + cfqq = NULL; + goto keep_queue; + } + + /* + * If group idle is enabled and there are requests dispatched from + * this group, wait for requests to complete. + */ +check_group_idle: + if (cfqd->cfq_group_idle && cfqq->cfqg->nr_cfqq == 1 + && cfqq->cfqg->dispatched) { cfqq = NULL; goto keep_queue; } @@ -3375,6 +3434,7 @@ static void cfq_completed_request(struct request_queue *q, struct request *rq) WARN_ON(!cfqq->dispatched); cfqd->rq_in_driver--; cfqq->dispatched--; + (RQ_CFQG(rq))->dispatched--; cfq_blkiocg_update_completion_stats(&cfqq->cfqg->blkg, rq_start_time_ns(rq), rq_io_start_time_ns(rq), rq_data_dir(rq), rq_is_sync(rq)); @@ -3404,7 +3464,10 @@ static void cfq_completed_request(struct request_queue *q, struct request *rq) * the queue. */ if (cfq_should_wait_busy(cfqd, cfqq)) { - cfqq->slice_end = jiffies + cfqd->cfq_slice_idle; + unsigned long extend_sl = cfqd->cfq_slice_idle; + if (!cfqd->cfq_slice_idle) + extend_sl = cfqd->cfq_group_idle; + cfqq->slice_end = jiffies + extend_sl; cfq_mark_cfqq_wait_busy(cfqq); cfq_log_cfqq(cfqd, cfqq, "will busy wait"); } @@ -3850,6 +3913,7 @@ static void *cfq_init_queue(struct request_queue *q) cfqd->cfq_slice[1] = cfq_slice_sync; cfqd->cfq_slice_async_rq = cfq_slice_async_rq; cfqd->cfq_slice_idle = cfq_slice_idle; + cfqd->cfq_group_idle = cfq_group_idle; cfqd->cfq_latency = 1; cfqd->cfq_group_isolation = 0; cfqd->hw_tag = -1; @@ -3922,6 +3986,7 @@ SHOW_FUNCTION(cfq_fifo_expire_async_show, cfqd->cfq_fifo_expire[0], 1); SHOW_FUNCTION(cfq_back_seek_max_show, cfqd->cfq_back_max, 0); SHOW_FUNCTION(cfq_back_seek_penalty_show, cfqd->cfq_back_penalty, 0); SHOW_FUNCTION(cfq_slice_idle_show, cfqd->cfq_slice_idle, 1); +SHOW_FUNCTION(cfq_group_idle_show, cfqd->cfq_group_idle, 1); SHOW_FUNCTION(cfq_slice_sync_show, cfqd->cfq_slice[1], 1); SHOW_FUNCTION(cfq_slice_async_show, cfqd->cfq_slice[0], 1); SHOW_FUNCTION(cfq_slice_async_rq_show, cfqd->cfq_slice_async_rq, 0); @@ -3954,6 +4019,7 @@ STORE_FUNCTION(cfq_back_seek_max_store, &cfqd->cfq_back_max, 0, UINT_MAX, 0); STORE_FUNCTION(cfq_back_seek_penalty_store, &cfqd->cfq_back_penalty, 1, UINT_MAX, 0); STORE_FUNCTION(cfq_slice_idle_store, &cfqd->cfq_slice_idle, 0, UINT_MAX, 1); +STORE_FUNCTION(cfq_group_idle_store, &cfqd->cfq_group_idle, 0, UINT_MAX, 1); STORE_FUNCTION(cfq_slice_sync_store, &cfqd->cfq_slice[1], 1, UINT_MAX, 1); STORE_FUNCTION(cfq_slice_async_store, &cfqd->cfq_slice[0], 1, UINT_MAX, 1); STORE_FUNCTION(cfq_slice_async_rq_store, &cfqd->cfq_slice_async_rq, 1, @@ -3975,6 +4041,7 @@ static struct elv_fs_entry cfq_attrs[] = { CFQ_ATTR(slice_async), CFQ_ATTR(slice_async_rq), CFQ_ATTR(slice_idle), + CFQ_ATTR(group_idle), CFQ_ATTR(low_latency), CFQ_ATTR(group_isolation), __ATTR_NULL @@ -4028,6 +4095,12 @@ static int __init cfq_init(void) if (!cfq_slice_idle) cfq_slice_idle = 1; +#ifdef CONFIG_CFQ_GROUP_IOSCHED + if (!cfq_group_idle) + cfq_group_idle = 1; +#else + cfq_group_idle = 0; +#endif if (cfq_slab_setup()) return -ENOMEM; diff --git a/block/elevator.c b/block/elevator.c index ec585c9554d33c04b973537f9ac3216e332afa50..205b09a5bd9ead9e64d7bcfb60cec924f1a22cbd 100644 --- a/block/elevator.c +++ b/block/elevator.c @@ -1009,18 +1009,19 @@ static int elevator_switch(struct request_queue *q, struct elevator_type *new_e) { struct elevator_queue *old_elevator, *e; void *data; + int err; /* * Allocate new elevator */ e = elevator_alloc(q, new_e); if (!e) - return 0; + return -ENOMEM; data = elevator_init_queue(q, e); if (!data) { kobject_put(&e->kobj); - return 0; + return -ENOMEM; } /* @@ -1043,7 +1044,8 @@ static int elevator_switch(struct request_queue *q, struct elevator_type *new_e) __elv_unregister_queue(old_elevator); - if (elv_register_queue(q)) + err = elv_register_queue(q); + if (err) goto fail_register; /* @@ -1056,7 +1058,7 @@ static int elevator_switch(struct request_queue *q, struct elevator_type *new_e) blk_add_trace_msg(q, "elv switch: %s", e->elevator_type->elevator_name); - return 1; + return 0; fail_register: /* @@ -1071,17 +1073,19 @@ static int elevator_switch(struct request_queue *q, struct elevator_type *new_e) queue_flag_clear(QUEUE_FLAG_ELVSWITCH, q); spin_unlock_irq(q->queue_lock); - return 0; + return err; } -ssize_t elv_iosched_store(struct request_queue *q, const char *name, - size_t count) +/* + * Switch this queue to the given IO scheduler. + */ +int elevator_change(struct request_queue *q, const char *name) { char elevator_name[ELV_NAME_MAX]; struct elevator_type *e; if (!q->elevator) - return count; + return -ENXIO; strlcpy(elevator_name, name, sizeof(elevator_name)); e = elevator_get(strstrip(elevator_name)); @@ -1092,13 +1096,27 @@ ssize_t elv_iosched_store(struct request_queue *q, const char *name, if (!strcmp(elevator_name, q->elevator->elevator_type->elevator_name)) { elevator_put(e); - return count; + return 0; } - if (!elevator_switch(q, e)) - printk(KERN_ERR "elevator: switch to %s failed\n", - elevator_name); - return count; + return elevator_switch(q, e); +} +EXPORT_SYMBOL(elevator_change); + +ssize_t elv_iosched_store(struct request_queue *q, const char *name, + size_t count) +{ + int ret; + + if (!q->elevator) + return count; + + ret = elevator_change(q, name); + if (!ret) + return count; + + printk(KERN_ERR "elevator: switch to %s failed\n", name); + return ret; } ssize_t elv_iosched_show(struct request_queue *q, char *name) diff --git a/drivers/block/cciss.c b/drivers/block/cciss.c index 31064df1370a96320f548d1ce5f191eaf2e97051..6124c2fd2d33440f022aa45b369bd7fb7a850c8a 100644 --- a/drivers/block/cciss.c +++ b/drivers/block/cciss.c @@ -297,6 +297,8 @@ static void enqueue_cmd_and_start_io(ctlr_info_t *h, spin_lock_irqsave(&h->lock, flags); addQ(&h->reqQ, c); h->Qdepth++; + if (h->Qdepth > h->maxQsinceinit) + h->maxQsinceinit = h->Qdepth; start_io(h); spin_unlock_irqrestore(&h->lock, flags); } @@ -4519,6 +4521,12 @@ static __devinit int cciss_kdump_hard_reset_controller(struct pci_dev *pdev) misc_fw_support = readl(&cfgtable->misc_fw_support); use_doorbell = misc_fw_support & MISC_FW_DOORBELL_RESET; + /* The doorbell reset seems to cause lockups on some Smart + * Arrays (e.g. P410, P410i, maybe others). Until this is + * fixed or at least isolated, avoid the doorbell reset. + */ + use_doorbell = 0; + rc = cciss_controller_hard_reset(pdev, vaddr, use_doorbell); if (rc) goto unmap_cfgtable; @@ -4712,6 +4720,9 @@ static int __devinit cciss_init_one(struct pci_dev *pdev, h->scatter_list = kmalloc(h->max_commands * sizeof(struct scatterlist *), GFP_KERNEL); + if (!h->scatter_list) + goto clean4; + for (k = 0; k < h->nr_cmds; k++) { h->scatter_list[k] = kmalloc(sizeof(struct scatterlist) * h->maxsgentries, diff --git a/drivers/block/loop.c b/drivers/block/loop.c index f3c636d237187df21879c0e8acc4a4c943e59ad2..91797bbbe702f01afc5770f45618487ab21054da 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -477,7 +477,7 @@ static int do_bio_filebacked(struct loop_device *lo, struct bio *bio) pos = ((loff_t) bio->bi_sector << 9) + lo->lo_offset; if (bio_rw(bio) == WRITE) { - bool barrier = (bio->bi_rw & REQ_HARDBARRIER); + bool barrier = !!(bio->bi_rw & REQ_HARDBARRIER); struct file *file = lo->lo_backing_file; if (barrier) { diff --git a/drivers/block/mg_disk.c b/drivers/block/mg_disk.c index b82c5ce5e9dfaf3bcc1d81b68554de8cdff0493c..76fa3deaee84059d4431f7763981311210f16f06 100644 --- a/drivers/block/mg_disk.c +++ b/drivers/block/mg_disk.c @@ -974,8 +974,7 @@ static int mg_probe(struct platform_device *plat_dev) host->breq->queuedata = host; /* mflash is random device, thanx for the noop */ - elevator_exit(host->breq->elevator); - err = elevator_init(host->breq, "noop"); + err = elevator_change(host->breq, "noop"); if (err) { printk(KERN_ERR "%s:%d (elevator_init) fail\n", __func__, __LINE__); diff --git a/drivers/s390/char/tape_block.c b/drivers/s390/char/tape_block.c index b7de02525ec901ebbee390b2798043eb1938f4bd..85cf607fc78f62d243ae41b20f2df018710be2e0 100644 --- a/drivers/s390/char/tape_block.c +++ b/drivers/s390/char/tape_block.c @@ -217,8 +217,7 @@ tapeblock_setup_device(struct tape_device * device) if (!blkdat->request_queue) return -ENOMEM; - elevator_exit(blkdat->request_queue->elevator); - rc = elevator_init(blkdat->request_queue, "noop"); + rc = elevator_change(blkdat->request_queue, "noop"); if (rc) goto cleanup_queue; diff --git a/fs/bio-integrity.c b/fs/bio-integrity.c index 612a5c38d3c1a5fc49e0d0990e19550c27217650..4d0ff5ee27b86bef6d377b9211694941939999a9 100644 --- a/fs/bio-integrity.c +++ b/fs/bio-integrity.c @@ -413,10 +413,10 @@ int bio_integrity_prep(struct bio *bio) /* Allocate kernel buffer for protection data */ len = sectors * blk_integrity_tuple_size(bi); - buf = kmalloc(len, GFP_NOIO | __GFP_NOFAIL | q->bounce_gfp); + buf = kmalloc(len, GFP_NOIO | q->bounce_gfp); if (unlikely(buf == NULL)) { printk(KERN_ERR "could not allocate integrity buffer\n"); - return -EIO; + return -ENOMEM; } end = (((unsigned long) buf) + len + PAGE_SIZE - 1) >> PAGE_SHIFT; diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index 7d9d06ba184b409e2ae90050ce82ca365cf3ce82..81e086d8aa5733c7a86a966827bf7ea18d29baa4 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -808,7 +808,7 @@ int bdi_writeback_thread(void *data) wb->last_active = jiffies; set_current_state(TASK_INTERRUPTIBLE); - if (!list_empty(&bdi->work_list)) { + if (!list_empty(&bdi->work_list) || kthread_should_stop()) { __set_current_state(TASK_RUNNING); continue; } diff --git a/include/linux/elevator.h b/include/linux/elevator.h index 2c958f4fce1ed6f1d6f4a8c3fc865155cd1eac81..926b50322a469c9d16c48ed35e10c4c12bd695f3 100644 --- a/include/linux/elevator.h +++ b/include/linux/elevator.h @@ -136,6 +136,7 @@ extern ssize_t elv_iosched_store(struct request_queue *, const char *, size_t); extern int elevator_init(struct request_queue *, char *); extern void elevator_exit(struct elevator_queue *); +extern int elevator_change(struct request_queue *, const char *); extern int elv_rq_merge_ok(struct request *, struct bio *); /* diff --git a/lib/scatterlist.c b/lib/scatterlist.c index a5ec42868f99d8d6700f34ca81c061c1ef21d15b..4ceb05d772aed12d392d618358284ea71cb51dd2 100644 --- a/lib/scatterlist.c +++ b/lib/scatterlist.c @@ -248,8 +248,18 @@ int __sg_alloc_table(struct sg_table *table, unsigned int nents, left -= sg_size; sg = alloc_fn(alloc_size, gfp_mask); - if (unlikely(!sg)) - return -ENOMEM; + if (unlikely(!sg)) { + /* + * Adjust entry count to reflect that the last + * entry of the previous table won't be used for + * linkage. Without this, sg_kfree() may get + * confused. + */ + if (prv) + table->nents = ++table->orig_nents; + + return -ENOMEM; + } sg_init_table(sg, alloc_size); table->nents = table->orig_nents += sg_size; diff --git a/mm/backing-dev.c b/mm/backing-dev.c index eaa4a5bbe0634390fc802ebffdbad4291fa3b991..c2bf86f470ed0044ab7366d5e6ea95a4aea2adf2 100644 --- a/mm/backing-dev.c +++ b/mm/backing-dev.c @@ -445,8 +445,8 @@ static int bdi_forker_thread(void *ptr) switch (action) { case FORK_THREAD: __set_current_state(TASK_RUNNING); - task = kthread_run(bdi_writeback_thread, &bdi->wb, "flush-%s", - dev_name(bdi->dev)); + task = kthread_create(bdi_writeback_thread, &bdi->wb, + "flush-%s", dev_name(bdi->dev)); if (IS_ERR(task)) { /* * If thread creation fails, force writeout of @@ -457,10 +457,13 @@ static int bdi_forker_thread(void *ptr) /* * The spinlock makes sure we do not lose * wake-ups when racing with 'bdi_queue_work()'. + * And as soon as the bdi thread is visible, we + * can start it. */ spin_lock_bh(&bdi->wb_lock); bdi->wb.task = task; spin_unlock_bh(&bdi->wb_lock); + wake_up_process(task); } break;