diff options
109 files changed, 2224 insertions, 1599 deletions
diff --git a/Documentation/ABI/stable/sysfs-block b/Documentation/ABI/stable/sysfs-block index cd14ecb3c9a5..ac1e519272aa 100644 --- a/Documentation/ABI/stable/sysfs-block +++ b/Documentation/ABI/stable/sysfs-block @@ -432,7 +432,8 @@ Contact: linux-block@vger.kernel.org Description: [RW] This is the maximum number of kilobytes that the block layer will allow for a filesystem request. Must be smaller than - or equal to the maximum size allowed by the hardware. + or equal to the maximum size allowed by the hardware. Write 0 + to use default kernel settings. What: /sys/block/<disk>/queue/max_segment_size diff --git a/Documentation/block/capability.rst b/Documentation/block/capability.rst deleted file mode 100644 index 2ae7f064736a..000000000000 --- a/Documentation/block/capability.rst +++ /dev/null @@ -1,10 +0,0 @@ -=============================== -Generic Block Device Capability -=============================== - -This file documents the sysfs file ``block/<disk>/capability``. - -``capability`` is a bitfield, printed in hexadecimal, indicating which -capabilities a specific block device supports: - -.. kernel-doc:: include/linux/blkdev.h diff --git a/Documentation/block/index.rst b/Documentation/block/index.rst index c4c73db748a8..102953166429 100644 --- a/Documentation/block/index.rst +++ b/Documentation/block/index.rst @@ -10,7 +10,6 @@ Block bfq-iosched biovecs blk-mq - capability cmdline-partition data-integrity deadline-iosched diff --git a/Documentation/block/ublk.rst b/Documentation/block/ublk.rst index ba45c46cc0da..1713b2890abb 100644 --- a/Documentation/block/ublk.rst +++ b/Documentation/block/ublk.rst @@ -144,6 +144,43 @@ managing and controlling ublk devices with help of several control commands: For retrieving device info via ``ublksrv_ctrl_dev_info``. It is the server's responsibility to save IO target specific info in userspace. +- ``UBLK_CMD_GET_DEV_INFO2`` + Same purpose with ``UBLK_CMD_GET_DEV_INFO``, but ublk server has to + provide path of the char device of ``/dev/ublkc*`` for kernel to run + permission check, and this command is added for supporting unprivileged + ublk device, and introduced with ``UBLK_F_UNPRIVILEGED_DEV`` together. + Only the user owning the requested device can retrieve the device info. + + How to deal with userspace/kernel compatibility: + + 1) if kernel is capable of handling ``UBLK_F_UNPRIVILEGED_DEV`` + + If ublk server supports ``UBLK_F_UNPRIVILEGED_DEV``: + + ublk server should send ``UBLK_CMD_GET_DEV_INFO2``, given anytime + unprivileged application needs to query devices the current user owns, + when the application has no idea if ``UBLK_F_UNPRIVILEGED_DEV`` is set + given the capability info is stateless, and application should always + retrieve it via ``UBLK_CMD_GET_DEV_INFO2`` + + If ublk server doesn't support ``UBLK_F_UNPRIVILEGED_DEV``: + + ``UBLK_CMD_GET_DEV_INFO`` is always sent to kernel, and the feature of + UBLK_F_UNPRIVILEGED_DEV isn't available for user + + 2) if kernel isn't capable of handling ``UBLK_F_UNPRIVILEGED_DEV`` + + If ublk server supports ``UBLK_F_UNPRIVILEGED_DEV``: + + ``UBLK_CMD_GET_DEV_INFO2`` is tried first, and will be failed, then + ``UBLK_CMD_GET_DEV_INFO`` needs to be retried given + ``UBLK_F_UNPRIVILEGED_DEV`` can't be set + + If ublk server doesn't support ``UBLK_F_UNPRIVILEGED_DEV``: + + ``UBLK_CMD_GET_DEV_INFO`` is always sent to kernel, and the feature of + ``UBLK_F_UNPRIVILEGED_DEV`` isn't available for user + - ``UBLK_CMD_START_USER_RECOVERY`` This command is valid if ``UBLK_F_USER_RECOVERY`` feature is enabled. This @@ -180,6 +217,15 @@ managing and controlling ublk devices with help of several control commands: double-write since the driver may issue the same I/O request twice. It might be useful to a read-only FS or a VM backend. +Unprivileged ublk device is supported by passing ``UBLK_F_UNPRIVILEGED_DEV``. +Once the flag is set, all control commands can be sent by unprivileged +user. Except for command of ``UBLK_CMD_ADD_DEV``, permission check on +the specified char device(``/dev/ublkc*``) is done for all other control +commands by ublk driver, for doing that, path of the char device has to +be provided in these commands' payload from ublk server. With this way, +ublk device becomes container-ware, and device created in one container +can be controlled/accessed just inside this container. + Data plane ---------- @@ -254,15 +300,6 @@ with specified IO tag in the command data: Future development ================== -Container-aware ublk deivice ----------------------------- - -ublk driver doesn't handle any IO logic. Its function is well defined -for now and very limited userspace interfaces are needed, which is also -well defined too. It is possible to make ublk devices container-aware block -devices in future as Stefan Hajnoczi suggested [#stefan]_, by removing -ADMIN privilege. - Zero copy --------- diff --git a/MAINTAINERS b/MAINTAINERS index 82938ca70466..23a8b5cde775 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -6425,6 +6425,7 @@ T: git git://git.linbit.com/linux-drbd.git T: git git://git.linbit.com/drbd-8.4.git F: Documentation/admin-guide/blockdev/ F: drivers/block/drbd/ +F: include/linux/drbd* F: lib/lru_cache.c DRIVER COMPONENT FRAMEWORK diff --git a/block/Kconfig.iosched b/block/Kconfig.iosched index 615516146086..27f11320b8d1 100644 --- a/block/Kconfig.iosched +++ b/block/Kconfig.iosched @@ -30,6 +30,7 @@ config IOSCHED_BFQ config BFQ_GROUP_IOSCHED bool "BFQ hierarchical scheduling support" depends on IOSCHED_BFQ && BLK_CGROUP + default y select BLK_CGROUP_RWSTAT help diff --git a/block/bfq-cgroup.c b/block/bfq-cgroup.c index 0fbde0fc0628..89ffb3aa992c 100644 --- a/block/bfq-cgroup.c +++ b/block/bfq-cgroup.c @@ -513,12 +513,12 @@ static void bfq_cpd_free(struct blkcg_policy_data *cpd) kfree(cpd_to_bfqgd(cpd)); } -static struct blkg_policy_data *bfq_pd_alloc(gfp_t gfp, struct request_queue *q, - struct blkcg *blkcg) +static struct blkg_policy_data *bfq_pd_alloc(struct gendisk *disk, + struct blkcg *blkcg, gfp_t gfp) { struct bfq_group *bfqg; - bfqg = kzalloc_node(sizeof(*bfqg), gfp, q->node); + bfqg = kzalloc_node(sizeof(*bfqg), gfp, disk->node_id); if (!bfqg) return NULL; @@ -551,7 +551,6 @@ static void bfq_pd_init(struct blkg_policy_data *pd) bfqg->bfqd = bfqd; bfqg->active_entities = 0; bfqg->num_queues_with_pending_reqs = 0; - bfqg->online = true; bfqg->rq_pos_tree = RB_ROOT; } @@ -614,7 +613,7 @@ struct bfq_group *bfq_bio_bfqg(struct bfq_data *bfqd, struct bio *bio) continue; } bfqg = blkg_to_bfqg(blkg); - if (bfqg->online) { + if (bfqg->pd.online) { bio_associate_blkg_from_css(bio, &blkg->blkcg->css); return bfqg; } @@ -706,12 +705,52 @@ void bfq_bfqq_move(struct bfq_data *bfqd, struct bfq_queue *bfqq, bfq_activate_bfqq(bfqd, bfqq); } - if (!bfqd->in_service_queue && !bfqd->rq_in_driver) + if (!bfqd->in_service_queue && !bfqd->tot_rq_in_driver) bfq_schedule_dispatch(bfqd); /* release extra ref taken above, bfqq may happen to be freed now */ bfq_put_queue(bfqq); } +static void bfq_sync_bfqq_move(struct bfq_data *bfqd, + struct bfq_queue *sync_bfqq, + struct bfq_io_cq *bic, + struct bfq_group *bfqg, + unsigned int act_idx) +{ + struct bfq_queue *bfqq; + + if (!sync_bfqq->new_bfqq && !bfq_bfqq_coop(sync_bfqq)) { + /* We are the only user of this bfqq, just move it */ + if (sync_bfqq->entity.sched_data != &bfqg->sched_data) + bfq_bfqq_move(bfqd, sync_bfqq, bfqg); + return; + } + + /* + * The queue was merged to a different queue. Check + * that the merge chain still belongs to the same + * cgroup. + */ + for (bfqq = sync_bfqq; bfqq; bfqq = bfqq->new_bfqq) + if (bfqq->entity.sched_data != &bfqg->sched_data) + break; + if (bfqq) { + /* + * Some queue changed cgroup so the merge is not valid + * anymore. We cannot easily just cancel the merge (by + * clearing new_bfqq) as there may be other processes + * using this queue and holding refs to all queues + * below sync_bfqq->new_bfqq. Similarly if the merge + * already happened, we need to detach from bfqq now + * so that we cannot merge bio to a request from the + * old cgroup. + */ + bfq_put_cooperator(sync_bfqq); + bic_set_bfqq(bic, NULL, true, act_idx); + bfq_release_process_ref(bfqd, sync_bfqq); + } +} + /** * __bfq_bic_change_cgroup - move @bic to @bfqg. * @bfqd: the queue descriptor. @@ -726,53 +765,20 @@ static void __bfq_bic_change_cgroup(struct bfq_data *bfqd, struct bfq_io_cq *bic, struct bfq_group *bfqg) { - struct bfq_queue *async_bfqq = bic_to_bfqq(bic, false); - struct bfq_queue *sync_bfqq = bic_to_bfqq(bic, true); - struct bfq_entity *entity; + unsigned int act_idx; - if (async_bfqq) { - entity = &async_bfqq->entity; + for (act_idx = 0; act_idx < bfqd->num_actuators; act_idx++) { + struct bfq_queue *async_bfqq = bic_to_bfqq(bic, false, act_idx); + struct bfq_queue *sync_bfqq = bic_to_bfqq(bic, true, act_idx); - if (entity->sched_data != &bfqg->sched_data) { - bic_set_bfqq(bic, NULL, false); + if (async_bfqq && + async_bfqq->entity.sched_data != &bfqg->sched_data) { + bic_set_bfqq(bic, NULL, false, act_idx); bfq_release_process_ref(bfqd, async_bfqq); } - } - if (sync_bfqq) { - if (!sync_bfqq->new_bfqq && !bfq_bfqq_coop(sync_bfqq)) { - /* We are the only user of this bfqq, just move it */ - if (sync_bfqq->entity.sched_data != &bfqg->sched_data) - bfq_bfqq_move(bfqd, sync_bfqq, bfqg); - } else { - struct bfq_queue *bfqq; - - /* - * The queue was merged to a different queue. Check - * that the merge chain still belongs to the same - * cgroup. - */ - for (bfqq = sync_bfqq; bfqq; bfqq = bfqq->new_bfqq) - if (bfqq->entity.sched_data != - &bfqg->sched_data) - break; - if (bfqq) { - /* - * Some queue changed cgroup so the merge is - * not valid anymore. We cannot easily just - * cancel the merge (by clearing new_bfqq) as - * there may be other processes using this - * queue and holding refs to all queues below - * sync_bfqq->new_bfqq. Similarly if the merge - * already happened, we need to detach from - * bfqq now so that we cannot merge bio to a - * request from the old cgroup. - */ - bfq_put_cooperator(sync_bfqq); - bic_set_bfqq(bic, NULL, true); - bfq_release_process_ref(bfqd, sync_bfqq); - } - } + if (sync_bfqq) + bfq_sync_bfqq_move(bfqd, sync_bfqq, bic, bfqg, act_idx); } } @@ -978,7 +984,6 @@ static void bfq_pd_offline(struct blkg_policy_data *pd) put_async_queues: bfq_put_async_queues(bfqd, bfqg); - bfqg->online = false; spin_unlock_irqrestore(&bfqd->lock, flags); /* @@ -1284,7 +1289,7 @@ struct bfq_group *bfq_create_group_hierarchy(struct bfq_data *bfqd, int node) { int ret; - ret = blkcg_activate_policy(bfqd->queue, &blkcg_policy_bfq); + ret = blkcg_activate_policy(bfqd->queue->disk, &blkcg_policy_bfq); if (ret) return NULL; diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c index 380e9bda2e57..8a8d4441519c 100644 --- a/block/bfq-iosched.c +++ b/block/bfq-iosched.c @@ -377,20 +377,23 @@ static const unsigned long bfq_late_stable_merging = 600; #define RQ_BIC(rq) ((struct bfq_io_cq *)((rq)->elv.priv[0])) #define RQ_BFQQ(rq) ((rq)->elv.priv[1]) -struct bfq_queue *bic_to_bfqq(struct bfq_io_cq *bic, bool is_sync) +struct bfq_queue *bic_to_bfqq(struct bfq_io_cq *bic, bool is_sync, + unsigned int actuator_idx) { - return bic->bfqq[is_sync]; + if (is_sync) + return bic->bfqq[1][actuator_idx]; + + return bic->bfqq[0][actuator_idx]; } static void bfq_put_stable_ref(struct bfq_queue *bfqq); -void bic_set_bfqq(struct bfq_io_cq *bic, struct bfq_queue *bfqq, bool is_sync) +void bic_set_bfqq(struct bfq_io_cq *bic, + struct bfq_queue *bfqq, + bool is_sync, + unsigned int actuator_idx) { - struct bfq_queue *old_bfqq = bic->bfqq[is_sync]; - - /* Clear bic pointer if bfqq is detached from this bic */ - if (old_bfqq && old_bfqq->bic == bic) - old_bfqq->bic = NULL; + struct bfq_queue *old_bfqq = bic->bfqq[is_sync][actuator_idx]; /* * If bfqq != NULL, then a non-stable queue merge between @@ -405,9 +408,18 @@ void bic_set_bfqq(struct bfq_io_cq *bic, struct bfq_queue *bfqq, bool is_sync) * we cancel the stable merge if * bic->stable_merge_bfqq == bfqq. */ - bic->bfqq[is_sync] = bfqq; + struct bfq_iocq_bfqq_data *bfqq_data = &bic->bfqq_data[actuator_idx]; + + /* Clear bic pointer if bfqq is detached from this bic */ + if (old_bfqq && old_bfqq->bic == bic) + old_bfqq->bic = NULL; - if (bfqq && bic->stable_merge_bfqq == bfqq) { + if (is_sync) + bic->bfqq[1][actuator_idx] = bfqq; + else + bic->bfqq[0][actuator_idx] = bfqq; + + if (bfqq && bfqq_data->stable_merge_bfqq == bfqq) { /* * Actually, these same instructions are executed also * in bfq_setup_cooperator, in case of abort or actual @@ -416,9 +428,9 @@ void bic_set_bfqq(struct bfq_io_cq *bic, struct bfq_queue *bfqq, bool is_sync) * did so, we would nest even more complexity in this * function. */ - bfq_put_stable_ref(bic->stable_merge_bfqq); + bfq_put_stable_ref(bfqq_data->stable_merge_bfqq); - bic->stable_merge_bfqq = NULL; + bfqq_data->stable_merge_bfqq = NULL; } } @@ -678,9 +690,9 @@ static void bfq_limit_depth(blk_opf_t opf, struct blk_mq_alloc_data *data) { struct bfq_data *bfqd = data->q->elevator->elevator_data; struct bfq_io_cq *bic = bfq_bic_lookup(data->q); - struct bfq_queue *bfqq = bic ? bic_to_bfqq(bic, op_is_sync(opf)) : NULL; int depth; unsigned limit = data->q->nr_requests; + unsigned int act_idx; /* Sync reads have full depth available */ if (op_is_sync(opf) && !op_is_write(opf)) { @@ -690,14 +702,21 @@ static void bfq_limit_depth(blk_opf_t opf, struct blk_mq_alloc_data *data) limit = (limit * depth) >> bfqd->full_depth_shift; } - /* - * Does queue (or any parent entity) exceed number of requests that - * should be available to it? Heavily limit depth so that it cannot - * consume more available requests and thus starve other entities. - */ - if (bfqq && bfqq_request_over_limit(bfqq, limit)) - depth = 1; + for (act_idx = 0; bic && act_idx < bfqd->num_actuators; act_idx++) { + struct bfq_queue *bfqq = + bic_to_bfqq(bic, op_is_sync(opf), act_idx); + /* + * Does queue (or any parent entity) exceed number of + * requests that should be available to it? Heavily + * limit depth so that it cannot consume more + * available requests and thus starve other entities. + */ + if (bfqq && bfqq_request_over_limit(bfqq, limit)) { + depth = 1; + break; + } + } bfq_log(bfqd, "[%s] wr_busy %d sync %d depth %u", __func__, bfqd->wr_busy_queues, op_is_sync(opf), depth); if (depth) @@ -1074,9 +1093,6 @@ static unsigned int bfq_wr_duration(struct bfq_data *bfqd) { u64 dur; - if (bfqd->bfq_wr_max_time > 0) - return bfqd->bfq_wr_max_time; - dur = bfqd->rate_dur_prod; do_div(dur, bfqd->peak_rate); @@ -1118,36 +1134,39 @@ bfq_bfqq_resume_state(struct bfq_queue *bfqq, struct bfq_data *bfqd, { unsigned int old_wr_coeff = 1; bool busy = bfq_already_existing && bfq_bfqq_busy(bfqq); + unsigned int a_idx = bfqq->actuator_idx; + struct bfq_iocq_bfqq_data *bfqq_data = &bic->bfqq_data[a_idx]; - if (bic->saved_has_short_ttime) + if (bfqq_data->saved_has_short_ttime) bfq_mark_bfqq_has_short_ttime(bfqq); else bfq_clear_bfqq_has_short_ttime(bfqq); - if (bic->saved_IO_bound) + if (bfqq_data->saved_IO_bound) bfq_mark_bfqq_IO_bound(bfqq); else bfq_clear_bfqq_IO_bound(bfqq); - bfqq->last_serv_time_ns = bic->saved_last_serv_time_ns; - bfqq->inject_limit = bic->saved_inject_limit; - bfqq->decrease_time_jif = bic->saved_decrease_time_jif; + bfqq->last_serv_time_ns = bfqq_data->saved_last_serv_time_ns; + bfqq->inject_limit = bfqq_data->saved_inject_limit; + bfqq->decrease_time_jif = bfqq_data->saved_decrease_time_jif; - bfqq->entity.new_weight = bic->saved_weight; - bfqq->ttime = bic->saved_ttime; - bfqq->io_start_time = bic->saved_io_start_time; - bfqq->tot_idle_time = bic->saved_tot_idle_time; + bfqq->entity.new_weight = bfqq_data->saved_weight; + bfqq->ttime = bfqq_data->saved_ttime; + bfqq->io_start_time = bfqq_data->saved_io_start_time; + bfqq->tot_idle_time = bfqq_data->saved_tot_idle_time; /* * Restore weight coefficient only if low_latency is on */ if (bfqd->low_latency) { old_wr_coeff = bfqq->wr_coeff; - bfqq->wr_coeff = bic->saved_wr_coeff; + bfqq->wr_coeff = bfqq_data->saved_wr_coeff; } - bfqq->service_from_wr = bic->saved_service_from_wr; - bfqq->wr_start_at_switch_to_srt = bic->saved_wr_start_at_switch_to_srt; - bfqq->last_wr_start_finish = bic->saved_last_wr_start_finish; - bfqq->wr_cur_max_time = bic->saved_wr_cur_max_time; + bfqq->service_from_wr = bfqq_data->saved_service_from_wr; + bfqq->wr_start_at_switch_to_srt = + bfqq_data->saved_wr_start_at_switch_to_srt; + bfqq->last_wr_start_finish = bfqq_data->saved_last_wr_start_finish; + bfqq->wr_cur_max_time = bfqq_data->saved_wr_cur_max_time; if (bfqq->wr_coeff > 1 && (bfq_bfqq_in_large_burst(bfqq) || time_is_before_jiffies(bfqq->last_wr_start_finish + @@ -1766,6 +1785,33 @@ static bool bfq_bfqq_higher_class_or_weight(struct bfq_queue *bfqq, return bfqq_weight > in_serv_weight; } +/* + * Get the index of the actuator that will serve bio. + */ +static unsigned int bfq_actuator_index(struct bfq_data *bfqd, struct bio *bio) +{ + unsigned int i; + sector_t end; + + /* no search needed if one or zero ranges present */ + if (bfqd->num_actuators == 1) + return 0; + + /* bio_end_sector(bio) gives the sector after the last one */ + end = bio_end_sector(bio) - 1; + + for (i = 0; i < bfqd->num_actuators; i++) { + if (end >= bfqd->sector[i] && + end < bfqd->sector[i] + bfqd->nr_sectors[i]) + return i; + } + + WARN_ONCE(true, + "bfq_actuator_index: bio sector out of ranges: end=%llu\n", + end); + return 0; +} + static bool bfq_better_to_idle(struct bfq_queue *bfqq); static void bfq_bfqq_handle_idle_busy_switch(struct bfq_data *bfqd, @@ -1785,7 +1831,9 @@ static void bfq_bfqq_handle_idle_busy_switch(struct bfq_data *bfqd, arrived_in_time = ktime_get_ns() <= bfqq->ttime.last_end_request + bfqd->bfq_slice_idle * 3; - + unsigned int act_idx = bfq_actuator_index(bfqd, rq->bio); + bool bfqq_non_merged_or_stably_merged = + bfqq->bic || RQ_BIC(rq)->bfqq_data[act_idx].stably_merged; /* * bfqq deserves to be weight-raised if: @@ -1819,9 +1867,8 @@ static void bfq_bfqq_handle_idle_busy_switch(struct bfq_data *bfqd, */ wr_or_deserves_wr = bfqd->low_latency && (bfqq->wr_coeff > 1 || - (bfq_bfqq_sync(bfqq) && - (bfqq->bic || RQ_BIC(rq)->stably_merged) && - (*interactive || soft_rt))); + (bfq_bfqq_sync(bfqq) && bfqq_non_merged_or_stably_merged && + (*interactive || soft_rt))); /* * Using the last flag, update budget and check whether bfqq @@ -2098,7 +2145,7 @@ static void bfq_check_waker(struct bfq_data *bfqd, struct bfq_queue *bfqq, * We reset waker detection logic also if too much time has passed * since the first detection. If wakeups are rare, pointless idling * doesn't hurt throughput that much. The condition below makes sure - * we do not uselessly idle blocking waker in more than 1/64 cases. + * we do not uselessly idle blocking waker in more than 1/64 cases. */ if (bfqd->last_completed_rq_bfqq != bfqq->tentative_waker_bfqq || @@ -2209,9 +2256,9 @@ static void bfq_add_request(struct request *rq) * elapsed. */ if (bfqq == bfqd->in_service_queue && - (bfqd->rq_in_driver == 0 || + (bfqd->tot_rq_in_driver == 0 || (bfqq->last_serv_time_ns > 0 && - bfqd->rqs_injected && bfqd->rq_in_driver > 0)) && + bfqd->rqs_injected && bfqd->tot_rq_in_driver > 0)) && time_is_before_eq_jiffies(bfqq->decrease_time_jif + msecs_to_jiffies(10))) { bfqd->last_empty_occupied_ns = ktime_get_ns(); @@ -2235,7 +2282,7 @@ static void bfq_add_request(struct request *rq) * will be set in case injection is performed * on bfqq before rq is completed). */ - if (bfqd->rq_in_driver == 0) + if (bfqd->tot_rq_in_driver == 0) bfqd->rqs_injected = false; } } @@ -2418,7 +2465,8 @@ static bool bfq_bio_merge(struct request_queue *q, struct bio *bio, */ bfq_bic_update_cgroup(bic, bio); - bfqd->bio_bfqq = bic_to_bfqq(bic, op_is_sync(bio->bi_opf)); + bfqd->bio_bfqq = bic_to_bfqq(bic, op_is_sync(bio->bi_opf), + bfq_actuator_index(bfqd, bio)); } else { bfqd->bio_bfqq = NULL; } @@ -2584,24 +2632,29 @@ static void bfq_bfqq_end_wr(struct bfq_queue *bfqq) void bfq_end_wr_async_queues(struct bfq_data *bfqd, struct bfq_group *bfqg) { - int i, j; + int i, j, k; - for (i = 0; i < 2; i++) - for (j = 0; j < IOPRIO_NR_LEVELS; j++) - if (bfqg->async_bfqq[i][j]) - bfq_bfqq_end_wr(bfqg->async_bfqq[i][j]); - if (bfqg->async_idle_bfqq) - bfq_bfqq_end_wr(bfqg->async_idle_bfqq); + for (k = 0; k < bfqd->num_actuators; k++) { + for (i = 0; i < 2; i++) + for (j = 0; j < IOPRIO_NR_LEVELS; j++) + if (bfqg->async_bfqq[i][j][k]) + bfq_bfqq_end_wr(bfqg->async_bfqq[i][j][k]); + if (bfqg->async_idle_bfqq[k]) + bfq_bfqq_end_wr(bfqg->async_idle_bfqq[k]); + } } static void bfq_end_wr(struct bfq_data *bfqd) { struct bfq_queue *bfqq; + int i; spin_lock_irq(&bfqd->lock); - list_for_each_entry(bfqq, &bfqd->active_list, bfqq_list) - bfq_bfqq_end_wr(bfqq); + for (i = 0; i < bfqd->num_actuators; i++) { + list_for_each_entry(bfqq, &bfqd->active_list[i], bfqq_list) + bfq_bfqq_end_wr(bfqq); + } list_for_each_entry(bfqq, &bfqd->idle_list, bfqq_list) bfq_bfqq_end_wr(bfqq); bfq_end_wr_async(bfqd); @@ -2794,6 +2847,35 @@ static bool bfq_may_be_close_cooperator(struct bfq_queue *bfqq, static bool idling_boosts_thr_without_issues(struct bfq_data *bfqd, struct bfq_queue *bfqq); +static struct bfq_queue * +bfq_setup_stable_merge(struct bfq_data *bfqd, struct bfq_queue *bfqq, + struct bfq_queue *stable_merge_bfqq, + struct bfq_iocq_bfqq_data *bfqq_data) +{ + int proc_ref = min(bfqq_process_refs(bfqq), + bfqq_process_refs(stable_merge_bfqq)); + struct bfq_queue *new_bfqq; + + if (idling_boosts_thr_without_issues(bfqd, bfqq) || + proc_ref == 0) + return NULL; + + /* next function will take at least one ref */ + new_bfqq = bfq_setup_merge(bfqq, stable_merge_bfqq); + + if (new_bfqq) { + bfqq_data->stably_merged = true; + if (new_bfqq->bic) { + unsigned int new_a_idx = new_bfqq->actuator_idx; + struct bfq_iocq_bfqq_data *new_bfqq_data = + &new_bfqq->bic->bfqq_data[new_a_idx]; + + new_bfqq_data->stably_merged = true; + } + } + return new_bfqq; +} + /* * Attempt to schedule a merge of bfqq with the currently in-service * queue or with a close queue among the scheduled queues. Return @@ -2819,6 +2901,8 @@ bfq_setup_cooperator(struct bfq_data *bfqd, struct bfq_queue *bfqq, void *io_struct, bool request, struct bfq_io_cq *bic) { struct bfq_queue *in_service_bfqq, *new_bfqq; + unsigned int a_idx = bfqq->actuator_idx; + struct bfq_iocq_bfqq_data *bfqq_data = &bic->bfqq_data[a_idx]; /* if a merge has already been setup, then proceed with that first */ if (bfqq->new_bfqq) @@ -2840,37 +2924,23 @@ bfq_setup_cooperator(struct bfq_data *bfqd, struct bfq_queue *bfqq, * stable merging) also if bic is associated with a * sync queue, but this bfqq is async */ - if (bfq_bfqq_sync(bfqq) && bic->stable_merge_bfqq && + if (bfq_bfqq_sync(bfqq) && bfqq_data->stable_merge_bfqq && !bfq_bfqq_just_created(bfqq) && time_is_before_jiffies(bfqq->split_time + msecs_to_jiffies(bfq_late_stable_merging)) && time_is_before_jiffies(bfqq->creation_time + msecs_to_jiffies(bfq_late_stable_merging))) { struct bfq_queue *stable_merge_bfqq = - bic->stable_merge_bfqq; - int proc_ref = min(bfqq_process_refs(bfqq), - bfqq_process_refs(stable_merge_bfqq)); + bfqq_data->stable_merge_bfqq; /* deschedule stable merge, because done or aborted here */ bfq_put_stable_ref(stable_merge_bfqq); - bic->stable_merge_bfqq = NULL; - - if (!idling_boosts_thr_without_issues(bfqd, bfqq) && - proc_ref > 0) { - /* next function will take at least one ref */ - struct bfq_queue *new_bfqq = - bfq_setup_merge(bfqq, stable_merge_bfqq); - - if (new_bfqq) { - bic->stably_merged = true; - if (new_bfqq->bic) - new_bfqq->bic->stably_merged = - true; - } - return new_bfqq; - } else - return NULL; + bfqq_data->stable_merge_bfqq = NULL; + + return bfq_setup_stable_merge(bfqd, bfqq, + stable_merge_bfqq, + bfqq_data); } } @@ -2965,6 +3035,8 @@ bfq_setup_cooperator(struct bfq_data *bfqd, struct bfq_queue *bfqq, static void bfq_bfqq_save_state(struct bfq_queue *bfqq) { struct bfq_io_cq *bic = bfqq->bic; + unsigned int a_idx = bfqq->actuator_idx; + struct bfq_iocq_bfqq_data *bfqq_data = &bic->bfqq_data[a_idx]; /* * If !bfqq->bic, the queue is already shared or its requests @@ -2974,18 +3046,21 @@ static void bfq_bfqq_save_state(struct bfq_queue *bfqq) if (!bic) return; - bic->saved_last_serv_time_ns = bfqq->last_serv_time_ns; - bic->saved_inject_limit = bfqq->inject_limit; - bic->saved_decrease_time_jif = bfqq->decrease_time_jif; - - bic->saved_weight = bfqq->entity.orig_weight; - bic->saved_ttime = bfqq->ttime; - bic->saved_has_short_ttime = bfq_bfqq_has_short_ttime(bfqq); - bic->saved_IO_bound = bfq_bfqq_IO_bound(bfqq); - bic->saved_io_start_time = bfqq->io_start_time; - bic->saved_tot_idle_time = bfqq->tot_idle_time; - bic->saved_in_large_burst = bfq_bfqq_in_large_burst(bfqq); - bic->was_in_burst_list = !hlist_unhashed(&bfqq->burst_list_node); + bfqq_data->saved_last_serv_time_ns = bfqq->last_serv_time_ns; + bfqq_data->saved_inject_limit = bfqq->inject_limit; + bfqq_data->saved_decrease_time_jif = bfqq->decrease_time_jif; + + bfqq_data->saved_weight = bfqq->entity.orig_weight; + bfqq_data->saved_ttime = bfqq->ttime; + bfqq_data->saved_has_short_ttime = + bfq_bfqq_has_short_ttime(bfqq); + bfqq_data->saved_IO_bound = bfq_bfqq_IO_bound(bfqq); + bfqq_data->saved_io_start_time = bfqq->io_start_time; + bfqq_data->saved_tot_idle_time = bfqq->tot_idle_time; + bfqq_data->saved_in_large_burst = bfq_bfqq_in_large_burst(bfqq); + bfqq_data->was_in_burst_list = + !hlist_unhashed(&bfqq->burst_list_node); + if (unlikely(bfq_bfqq_just_created(bfqq) && !bfq_bfqq_in_large_burst(bfqq) && bfqq->bfqd->low_latency)) { @@ -2998,17 +3073,21 @@ static void bfq_bfqq_save_state(struct bfq_queue *bfqq) * to bfqq, so that to avoid that bfqq unjustly fails * to enjoy weight raising if split soon. */ - bic->saved_wr_coeff = bfqq->bfqd->bfq_wr_coeff; - bic->saved_wr_start_at_switch_to_srt = bfq_smallest_from_now(); - bic->saved_wr_cur_max_time = bfq_wr_duration(bfqq->bfqd); - bic->saved_last_wr_start_finish = jiffies; + bfqq_data->saved_wr_coeff = bfqq->bfqd->bfq_wr_coeff; + bfqq_data->saved_wr_start_at_switch_to_srt = + bfq_smallest_from_now(); + bfqq_data->saved_wr_cur_max_time = + bfq_wr_duration(bfqq->bfqd); + bfqq_data->saved_last_wr_start_finish = jiffies; } else { - bic->saved_wr_coeff = bfqq->wr_coeff; - bic->saved_wr_start_at_switch_to_srt = + bfqq_data->saved_wr_coeff = bfqq->wr_coeff; + bfqq_data->saved_wr_start_at_switch_to_srt = bfqq->wr_start_at_switch_to_srt; - bic->saved_service_from_wr = bfqq->service_from_wr; - bic->saved_last_wr_start_finish = bfqq->last_wr_start_finish; - bic->saved_wr_cur_max_time = bfqq->wr_cur_max_time; + bfqq_data->saved_service_from_wr = + bfqq->service_from_wr; + bfqq_data->saved_last_wr_start_finish = + bfqq->last_wr_start_finish; + bfqq_data->saved_wr_cur_max_time = bfqq->wr_cur_max_time; } } @@ -3114,7 +3193,7 @@ bfq_merge_bfqqs(struct bfq_data *bfqd, struct bfq_io_cq *bic, /* * Merge queues (that is, let bic redirect its requests to new_bfqq) */ - bic_set_bfqq(bic, new_bfqq, true); + bic_set_bfqq(bic, new_bfqq, true, bfqq->actuator_idx); bfq_mark_bfqq_coop(new_bfqq); /* * new_bfqq now belongs to at least two bics (it is a shared queue): @@ -3532,13 +3611,13 @@ static void bfq_update_peak_rate(struct bfq_data *bfqd, struct request *rq) * - start a new observation interval with this dispatch */ if (now_ns - bfqd->last_dispatch > 100*NSEC_PER_MSEC && - bfqd->rq_in_driver == 0) + bfqd->tot_rq_in_driver == 0) goto update_rate_and_reset; /* Update sampling information */ bfqd->peak_rate_samples++; - if ((bfqd->rq_in_driver > 0 || + if ((bfqd->tot_rq_in_driver > 0 || now_ns - bfqd->last_completion < BFQ_MIN_TT) && !BFQ_RQ_SEEKY(bfqd, bfqd->last_position, rq)) bfqd->sequential_samples++; @@ -3803,10 +3882,8 @@ static bool idling_needed_for_service_guarantees(struct bfq_data *bfqd, return false; return (bfqq->wr_coeff > 1 && - (bfqd->wr_busy_queues < - tot_busy_queues || - bfqd->rq_in_driver >= - bfqq->dispatched + 4)) || + (bfqd->wr_busy_queues < tot_busy_queues || + bfqd->tot_rq_in_driver >= bfqq->dispatched + 4)) || bfq_asymmetric_scenario(bfqd, bfqq) || tot_busy_queues == 1; } @@ -4072,8 +4149,7 @@ static void __bfq_bfqq_recalc_budget(struct bfq_data *bfqd, * function to evaluate the I/O speed of a process. */ static bool bfq_bfqq_is_slow(struct bfq_data *bfqd, struct bfq_queue *bfqq, - bool compensate, enum bfqq_expiration reason, - unsigned long *delta_ms) + bool compensate, unsigned long *delta_ms) { ktime_t delta_ktime; u32 delta_usecs; @@ -4269,7 +4345,7 @@ void bfq_bfqq_expire(struct bfq_data *bfqd, /* * Check whether the process is slow (see bfq_bfqq_is_slow). */ - slow = bfq_bfqq_is_slow(bfqd, bfqq, compensate, reason, &delta); + slow = bfq_bfqq_is_slow(bfqd, bfqq, compensate, &delta); /* * As above explained, charge slow (typically seeky) and @@ -4577,6 +4653,8 @@ bfq_choose_bfqq_for_injection(struct bfq_data *bfqd) { struct bfq_queue *bfqq, *in_serv_bfqq = bfqd->in_service_queue; unsigned int limit = in_serv_bfqq->inject_limit; + int i; + /* * If * - bfqq is not weight-raised and therefore does not carry @@ -4608,7 +4686,7 @@ bfq_choose_bfqq_for_injection(struct bfq_data *bfqd) ) limit = 1; - if (bfqd->rq_in_driver >= limit) + if (bfqd->tot_rq_in_driver >= limit) return NULL; /* @@ -4623,11 +4701,12 @@ bfq_choose_bfqq_for_injection(struct bfq_data *bfqd) * (and re-added only if it gets new requests, but then it * is assigned again enough budget for its new backlog). */ - list_for_each_entry(bfqq, &bfqd->active_list, bfqq_list) - if (!RB_EMPTY_ROOT(&bfqq->sort_list) && - (in_serv_always_inject || bfqq->wr_coeff > 1) && - bfq_serv_to_charge(bfqq->next_rq, bfqq) <= - bfq_bfqq_budget_left(bfqq)) { + for (i = 0; i < bfqd->num_actuators; i++) { + list_for_each_entry(bfqq, &bfqd->active_list[i], bfqq_list) + if (!RB_EMPTY_ROOT(&bfqq->sort_list) && + (in_serv_always_inject || bfqq->wr_coeff > 1) && + bfq_serv_to_charge(bfqq->next_rq, bfqq) <= + bfq_bfqq_budget_left(bfqq)) { /* * Allow for only one large in-flight request * on non-rotational devices, for the @@ -4647,27 +4726,80 @@ bfq_choose_bfqq_for_injection(struct bfq_data *bfqd) */ if (blk_queue_nonrot(bfqd->queue) && blk_rq_sectors(bfqq->next_rq) >= - BFQQ_SECT_THR_NONROT) - limit = min_t(unsigned int, 1, limit); - else - limit = in_serv_bfqq->inject_limit; - - if (bfqd->rq_in_driver < limit) { + BFQQ_SECT_THR_NONROT && + bfqd->tot_rq_in_driver >= 1) + continue; + else { bfqd->rqs_injected = true; return bfqq; } } + } return NULL; } +static struct bfq_queue * +bfq_find_active_bfqq_for_actuator(struct bfq_data *bfqd, int idx) +{ + struct bfq_queue *bfqq; + + if (bfqd->in_service_queue && + bfqd->in_service_queue->actuator_idx == idx) + return bfqd->in_service_queue; + + list_for_each_entry(bfqq, &bfqd->active_list[idx], bfqq_list) { + if (!RB_EMPTY_ROOT(&bfqq->sort_list) && + bfq_serv_to_charge(bfqq->next_rq, bfqq) <= + bfq_bfqq_budget_left(bfqq)) { + return bfqq; + } + } + + return NULL; +} + +/* + * Perform a linear scan of each actuator, until an actuator is found + * for which the following three conditions hold: the load of the + * actuator is below the threshold (see comments on + * actuator_load_threshold for details) and lower than that of the + * next actuator (comments on this extra condition below), and there + * is a queue that contains I/O for that actuator. On success, return + * that queue. + * + * Performing a plain linear scan entails a prioritization among + * actuators. The extra condition above breaks this prioritization and + * tends to distribute injection uniformly across actuators. + */ +static struct bfq_queue * +bfq_find_bfqq_for_underused_actuator(struct bfq_data *bfqd) +{ + int i; + + for (i = 0 ; i < bfqd->num_actuators; i++) { + if (bfqd->rq_in_driver[i] < bfqd->actuator_load_threshold && + (i == bfqd->num_actuators - 1 || + bfqd->rq_in_driver[i] < bfqd->rq_in_driver[i+1])) { + struct bfq_queue *bfqq = + bfq_find_active_bfqq_for_actuator(bfqd, i); + + if (bfqq) + return bfqq; + } + } + + return NULL; +} + + /* * Select a queue for service. If we have a current queue in service, * check whether to continue servicing it, or retrieve and set a new one. */ static struct bfq_queue *bfq_select_queue(struct bfq_data *bfqd) { - struct bfq_queue *bfqq; + struct bfq_queue *bfqq, *inject_bfqq; struct request *next_rq; enum bfqq_expiration reason = BFQQE_BUDGET_TIMEOUT; @@ -4690,6 +4822,15 @@ static struct bfq_queue *bfq_select_queue(struct bfq_data *bfqd) check_queue: /* + * If some actuator is underutilized, but the in-service + * queue does not contain I/O for that actuator, then try to + * inject I/O for that actuator. + */ + inject_bfqq = bfq_find_bfqq_for_underused_actuator(bfqd); + if (inject_bfqq && inject_bfqq != bfqq) + return inject_bfqq; + + /* * This loop is rarely executed more than once. Even when it * happens, it is much more convenient to re-execute this loop * than to return NULL and trigger a new dispatch to get a @@ -4748,11 +4889,8 @@ check_queue: */ if (bfq_bfqq_wait_request(bfqq) || (bfqq->dispatched != 0 && bfq_better_to_idle(bfqq))) { - struct bfq_queue *async_bfqq = - bfqq->bic && bfqq->bic->bfqq[0] && - bfq_bfqq_busy(bfqq->bic->bfqq[0]) && - bfqq->bic->bfqq[0]->next_rq ? - bfqq->bic->bfqq[0] : NULL; + unsigned int act_idx = bfqq->actuator_idx; + struct bfq_queue *async_bfqq = NULL; struct bfq_queue *blocked_bfqq = !hlist_empty(&bfqq->woken_list) ? container_of(bfqq->woken_list.first, @@ -4760,6 +4898,10 @@ check_queue: woken_list_node) : NULL; + if (bfqq->bic && bfqq->bic->bfqq[0][act_idx] && + bfq_bfqq_busy(bfqq->bic->bfqq[0][act_idx]) && + bfqq->bic->bfqq[0][act_idx]->next_rq) + async_bfqq = bfqq->bic->bfqq[0][act_idx]; /* * The next four mutually-exclusive ifs decide * whether to try injection, and choose the queue to @@ -4844,7 +4986,7 @@ check_queue: icq_to_bic(async_bfqq->next_rq->elv.icq) == bfqq->bic && bfq_serv_to_charge(async_bfqq->next_rq, async_bfqq) <= bfq_bfqq_budget_left(async_bfqq)) - bfqq = bfqq->bic->bfqq[0]; + bfqq = async_bfqq; else if (bfqq->waker_bfqq && bfq_bfqq_busy(bfqq->waker_bfqq) && bfqq->waker_bfqq->next_rq && @@ -4975,7 +5117,7 @@ static struct request *bfq_dispatch_rq_from_bfqq(struct bfq_data *bfqd, bfq_dispatch_remove(bfqd->queue, rq); if (bfqq != bfqd->in_service_queue) - goto return_rq; + return rq; /* * If weight raising has to terminate for bfqq, then next @@ -4995,12 +5137,9 @@ static struct request *bfq_dispatch_rq_from_bfqq(struct bfq_data *bfqd, * belongs to CLASS_IDLE and other queues are waiting for * service. */ - if (!(bfq_tot_busy_queues(bfqd) > 1 && bfq_class_idle(bfqq))) - goto return_rq; - - bfq_bfqq_expire(bfqd, bfqq, false, BFQQE_BUDGET_EXHAUSTED); + if (bfq_tot_busy_queues(bfqd) > 1 && bfq_class_idle(bfqq)) + bfq_bfqq_expire(bfqd, bfqq, false, BFQQE_BUDGET_EXHAUSTED); -return_rq: return rq; } @@ -5043,11 +5182,11 @@ static struct request *__bfq_dispatch_request(struct blk_mq_hw_ctx *hctx) /* * We exploit the bfq_finish_requeue_request hook to - * decrement rq_in_driver, but + * decrement tot_rq_in_driver, but * bfq_finish_requeue_request will not be invoked on * this request. So, to avoid unbalance, just start - * this request, without incrementing rq_in_driver. As - * a negative consequence, rq_in_driver is deceptively + * this request, without incrementing tot_rq_in_driver. As + * a negative consequence, tot_rq_in_driver is deceptively * lower than it should be while this request is in * service. This may cause bfq_schedule_dispatch to be * invoked uselessly. @@ -5056,7 +5195,7 @@ static struct request *__bfq_dispatch_request(struct blk_mq_hw_ctx *hctx) * bfq_finish_requeue_request hook, if defined, is * probably invoked also on this request. So, by * exploiting this hook, we could 1) increment - * rq_in_driver here, and 2) decrement it in + * tot_rq_in_driver here, and 2) decrement it in * bfq_finish_requeue_request. Such a solution would * let the value of the counter be always accurate, * but it would entail using an extra interface @@ -5085,7 +5224,7 @@ static struct request *__bfq_dispatch_request(struct blk_mq_hw_ctx *hctx) * Of course, serving one request at a time may cause loss of * throughput. */ - if (bfqd->strict_guarantees && bfqd->rq_in_driver > 0) + if (bfqd->strict_guarantees && bfqd->tot_rq_in_driver > 0) goto exit; bfqq = bfq_select_queue(bfqd); @@ -5096,7 +5235,8 @@ static struct request *__bfq_dispatch_request(struct blk_mq_hw_ctx *hctx) if (rq) { inc_in_driver_start_rq: - bfqd->rq_in_driver++; + bfqd->rq_in_driver[bfqq->actuator_idx]++; + bfqd->tot_rq_in_driver++; start_rq: rq->rq_flags |= RQF_STARTED; } @@ -5283,8 +5423,6 @@ void bfq_put_cooperator(struct bfq_queue *bfqq) */ __bfqq = bfqq->new_bfqq; while (__bfqq) { - if (__bfqq == bfqq) - break; next = __bfqq->new_bfqq; bfq_put_queue(__bfqq); __bfqq = next; @@ -5305,48 +5443,55 @@ static void bfq_exit_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq) bfq_release_process_ref(bfqd, bfqq); } -static void bfq_exit_icq_bfqq(struct bfq_io_cq *bic, bool is_sync) +static void bfq_exit_icq_bfqq(struct bfq_io_cq *bic, bool is_sync, + unsigned int actuator_idx) { - struct bfq_queue *bfqq = bic_to_bfqq(bic, is_sync); + struct bfq_queue *bfqq = bic_to_bfqq(bic, is_sync, actuator_idx); struct bfq_data *bfqd; if (bfqq) bfqd = bfqq->bfqd; /* NULL if scheduler already exited */ if (bfqq && bfqd) { - unsigned long flags; - - spin_lock_irqsave(&bfqd->lock, flags); - bic_set_bfqq(bic, NULL, is_sync); + bic_set_bfqq(bic, NULL, is_sync, actuator_idx); bfq_exit_bfqq(bfqd, bfqq); - spin_unlock_irqrestore(&bfqd->lock, flags); } } static void bfq_exit_icq(struct io_cq *icq) { struct bfq_io_cq *bic = icq_to_bic(icq); + struct bfq_data *bfqd = bic_to_bfqd(bic); + unsigned long flags; + unsigned int act_idx; + /* + * If bfqd and thus bfqd->num_actuators is not available any + * longer, then cycle over all possible per-actuator bfqqs in + * next loop. We rely on bic being zeroed on creation, and + * therefore on its unused per-actuator fields being NULL. + */ + unsigned int num_actuators = BFQ_MAX_ACTUATORS; + struct bfq_iocq_bfqq_data *bfqq_data = bic->bfqq_data; - if (bic->stable_merge_bfqq) { - struct bfq_data *bfqd = bic->stable_merge_bfqq->bfqd; + /* + * bfqd is NULL if scheduler already exited, and in that case + * this is the last time these queues are accessed. + */ + if (bfqd) { + spin_lock_irqsave(&bfqd->lock, flags); + num_actuators = bfqd->num_actuators; + } - /* - * bfqd is NULL if scheduler already exited, and in - * that case this is the last time bfqq is accessed. - */ - if (bfqd) { - unsigned long flags; + for (act_idx = 0; act_idx < num_actuators; act_idx++) { + if (bfqq_data[act_idx].stable_merge_bfqq) + bfq_put_stable_ref(bfqq_data[act_idx].stable_merge_bfqq); - spin_lock_irqsave(&bfqd->lock, flags); - bfq_put_stable_ref(bic->stable_merge_bfqq); - spin_unlock_irqrestore(&bfqd->lock, flags); - } else { - bfq_put_stable_ref(bic->stable_merge_bfqq); - } + bfq_exit_icq_bfqq(bic, true, act_idx); + bfq_exit_icq_bfqq(bic, false, act_idx); } - bfq_exit_icq_bfqq(bic, true); - bfq_exit_icq_bfqq(bic, false); + if (bfqd) + spin_unlock_irqrestore(&bfqd->lock, flags); } /* @@ -5423,25 +5568,27 @@ static void bfq_check_ioprio_change(struct bfq_io_cq *bic, struct bio *bio) bic->ioprio = ioprio; - bfqq = bic_to_bfqq(bic, false); + bfqq = bic_to_bfqq(bic, false, bfq_actuator_index(bfqd, bio)); if (bfqq) { struct bfq_queue *old_bfqq = bfqq; bfqq = bfq_get_queue(bfqd, bio, false, bic, true); - bic_set_bfqq(bic, bfqq, false); + bic_set_bfqq(bic, bfqq, false, bfq_actuator_index(bfqd, bio)); bfq_release_process_ref(bfqd, old_bfqq); } - bfqq = bic_to_bfqq(bic, true); + bfqq = bic_to_bfqq(bic, true, bfq_actuator_index(bfqd, bio)); if (bfqq) bfq_set_next_ioprio_data(bfqq, bic); } static void bfq_init_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq, - struct bfq_io_cq *bic, pid_t pid, int is_sync) + struct bfq_io_cq *bic, pid_t pid, int is_sync, + unsigned int act_idx) { u64 now_ns = ktime_get_ns(); + bfqq->actuator_idx = act_idx; RB_CLEAR_NODE(&bfqq->entity.rb_node); INIT_LIST_HEAD(&bfqq->fifo); INIT_HLIST_NODE(&bfqq->burst_list_node); @@ -5501,22 +5648,24 @@ static void bfq_init_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq, /* first request is almost certainly seeky */ bfqq->seek_history = 1; + + bfqq->decrease_time_jif = jiffies; } static struct bfq_queue **bfq_async_queue_prio(struct bfq_data *bfqd, struct bfq_group *bfqg, - int ioprio_class, int ioprio) + int ioprio_class, int ioprio, int act_idx) { switch (ioprio_class) { case IOPRIO_CLASS_RT: - return &bfqg->async_bfqq[0][ioprio]; + return &bfqg->async_bfqq[0][ioprio][act_idx]; case IOPRIO_CLASS_NONE: ioprio = IOPRIO_BE_NORM; fallthrough; case IOPRIO_CLASS_BE: - return &bfqg->async_bfqq[1][ioprio]; + return &bfqg->async_bfqq[1][ioprio][act_idx]; case IOPRIO_CLASS_IDLE: - return &bfqg->async_idle_bfqq; + return &bfqg->async_idle_bfqq[act_idx]; default: return NULL; } @@ -5527,6 +5676,7 @@ bfq_do_early_stable_merge(struct bfq_data *bfqd, struct bfq_queue *bfqq, struct bfq_io_cq *bic, struct bfq_queue *last_bfqq_created) { + unsigned int a_idx = last_bfqq_created->actuator_idx; struct bfq_queue *new_bfqq = bfq_setup_merge(bfqq, last_bfqq_created); @@ -5534,8 +5684,8 @@ bfq_do_early_stable_merge(struct bfq_data *bfqd, struct bfq_queue *bfqq, return bfqq; if (new_bfqq->bic) - new_bfqq->bic->stably_merged = true; - bic->stably_merged = true; + new_bfqq->bic->bfqq_data[a_idx].stably_merged = true; + bic->bfqq_data[a_idx].stably_merged = true; /* * Reusing merge functions. This implies that @@ -5610,9 +5760,13 @@ static struct bfq_queue *bfq_do_or_sched_stable_merge(struct bfq_data *bfqd, * it has been set already, but too long ago, then move it * forward to bfqq. Finally, move also if bfqq belongs to a * different group than last_bfqq_created, or if bfqq has a - * different ioprio or ioprio_class. If none of these - * conditions holds true, then try an early stable merge or - * schedule a delayed stable merge. + * different ioprio, ioprio_class or actuator_idx. If none of + * these conditions holds true, then try an early stable merge + * or schedule a delayed stable merge. As for the condition on + * actuator_idx, the reason is that, if queues associated with + * different actuators are merged, then control is lost on + * each actuator. Therefore some actuator may be + * underutilized, and throughput may decrease. * * A delayed merge is scheduled (instead of performing an * early merge), in case bfqq might soon prove to be more @@ -5630,7 +5784,8 @@ static struct bfq_queue *bfq_do_or_sched_stable_merge(struct bfq_data *bfqd, bfqq->creation_time) || bfqq->entity.parent != last_bfqq_created->entity.parent || bfqq->ioprio != last_bfqq_created->ioprio || - bfqq->ioprio_class != last_bfqq_created->ioprio_class) + bfqq->ioprio_class != last_bfqq_created->ioprio_class || + bfqq->actuator_idx != last_bfqq_created->actuator_idx) *source_bfqq = bfqq; else if (time_after_eq(last_bfqq_created->creation_time + bfqd->bfq_burst_interval, @@ -5660,7 +5815,8 @@ static struct bfq_queue *bfq_do_or_sched_stable_merge(struct bfq_data *bfqd, /* * Record the bfqq to merge to. */ - bic->stable_merge_bfqq = last_bfqq_created; + bic->bfqq_data[last_bfqq_created->actuator_idx].stable_merge_bfqq = + last_bfqq_created; } } @@ -5682,7 +5838,8 @@ static struct bfq_queue *bfq_get_queue(struct bfq_data *bfqd, bfqg = bfq_bio_bfqg(bfqd, bio); if (!is_sync) { async_bfqq = bfq_async_queue_prio(bfqd, bfqg, ioprio_class, - ioprio); + ioprio, + bfq_actuator_index(bfqd, bio)); bfqq = *async_bfqq; if (bfqq) goto out; @@ -5694,7 +5851,7 @@ static struct bfq_queue *bfq_get_queue(struct bfq_data *bfqd, if (bfqq) { bfq_init_bfqq(bfqd, bfqq, bic, current->pid, - is_sync); + is_sync, bfq_actuator_index(bfqd, bio)); bfq_init_entity(&bfqq->entity, bfqg); bfq_log_bfqq(bfqd, bfqq, "allocated"); } else { @@ -6009,7 +6166,8 @@ static bool __bfq_insert_request(struct bfq_data *bfqd, struct request *rq) * then complete the merge and redirect it to * new_bfqq. */ - if (bic_to_bfqq(RQ_BIC(rq), 1) == bfqq) + if (bic_to_bfqq(RQ_BIC(rq), true, + bfq_actuator_index(bfqd, rq->bio)) == bfqq) bfq_merge_bfqqs(bfqd, RQ_BIC(rq), bfqq, new_bfqq); @@ -6147,7 +6305,7 @@ static void bfq_update_hw_tag(struct bfq_data *bfqd) struct bfq_queue *bfqq = bfqd->in_service_queue; bfqd->max_rq_in_driver = max_t(int, bfqd->max_rq_in_driver, - bfqd->rq_in_driver); + bfqd->tot_rq_in_driver); if (bfqd->hw_tag == 1) return; @@ -6158,7 +6316,7 @@ static void bfq_update_hw_tag(struct bfq_data *bfqd) * sum is not exact, as it's not taking into account deactivated * requests. */ - if (bfqd->rq_in_driver + bfqd->queued <= BFQ_HW_QUEUE_THRESHOLD) + if (bfqd->tot_rq_in_driver + bfqd->queued <= BFQ_HW_QUEUE_THRESHOLD) return; /* @@ -6169,7 +6327,7 @@ static void bfq_update_hw_tag(struct bfq_data *bfqd) if (bfqq && bfq_bfqq_has_short_ttime(bfqq) && bfqq->dispatched + bfqq->queued[0] + bfqq->queued[1] < BFQ_HW_QUEUE_THRESHOLD && - bfqd->rq_in_driver < BFQ_HW_QUEUE_THRESHOLD) + bfqd->tot_rq_in_driver < BFQ_HW_QUEUE_THRESHOLD) return; if (bfqd->hw_tag_samples++ < BFQ_HW_QUEUE_SAMPLES) @@ -6190,7 +6348,8 @@ static void bfq_completed_request(struct bfq_queue *bfqq, struct bfq_data *bfqd) bfq_update_hw_tag(bfqd); - bfqd->rq_in_driver--; + bfqd->rq_in_driver[bfqq->actuator_idx]--; + bfqd->tot_rq_in_driver--; bfqq->dispatched--; if (!bfqq->dispatched && !bfq_bfqq_busy(bfqq)) { @@ -6310,7 +6469,7 @@ static void bfq_completed_request(struct bfq_queue *bfqq, struct bfq_data *bfqd) BFQQE_NO_MORE_REQUESTS); } - if (!bfqd->rq_in_driver) + if (!bfqd->tot_rq_in_driver) bfq_schedule_dispatch(bfqd); } @@ -6441,13 +6600,13 @@ static void bfq_update_inject_limit(struct bfq_data *bfqd, * conditions to do it, or we can lower the last base value * computed. * - * NOTE: (bfqd->rq_in_driver == 1) means that there is no I/O + * NOTE: (bfqd->tot_rq_in_driver == 1) means that there is no I/O * request in flight, because this function is in the code * path that handles the completion of a request of bfqq, and, * in particular, this function is executed before - * bfqd->rq_in_driver is decremented in such a code path. + * bfqd->tot_rq_in_driver is decremented in such a code path. */ - if ((bfqq->last_serv_time_ns == 0 && bfqd->rq_in_driver == 1) || + if ((bfqq->last_serv_time_ns == 0 && bfqd->tot_rq_in_driver == 1) || tot_time_ns < bfqq->last_serv_time_ns) { if (bfqq->last_serv_time_ns == 0) { /* @@ -6457,7 +6616,7 @@ static void bfq_update_inject_limit(struct bfq_data *bfqd, bfqq->inject_limit = max_t(unsigned int, 1, old_limit); } bfqq->last_serv_time_ns = tot_time_ns; - } else if (!bfqd->rqs_injected && bfqd->rq_in_driver == 1) + } else if (!bfqd->rqs_injected && bfqd->tot_rq_in_driver == 1) /* * No I/O injected and no request still in service in * the drive: these are the exact conditions for @@ -6564,7 +6723,7 @@ bfq_split_bfqq(struct bfq_io_cq *bic, struct bfq_queue *bfqq) return bfqq; } - bic_set_bfqq(bic, NULL, true); + bic_set_bfqq(bic, NULL, true, bfqq->actuator_idx); bfq_put_cooperator(bfqq); @@ -6578,7 +6737,9 @@ static struct bfq_queue *bfq_get_bfqq_handle_split(struct bfq_data *bfqd, bool split, bool is_sync, bool *new_queue) { - struct bfq_queue *bfqq = bic_to_bfqq(bic, is_sync); + unsigned int act_idx = bfq_actuator_index(bfqd, bio); + struct bfq_queue *bfqq = bic_to_bfqq(bic, is_sync, act_idx); + struct bfq_iocq_bfqq_data *bfqq_data = &bic->bfqq_data[act_idx]; if (likely(bfqq && bfqq != &bfqd->oom_bfqq)) return bfqq; @@ -6590,14 +6751,14 @@ static struct bfq_queue *bfq_get_bfqq_handle_split(struct bfq_data *bfqd, bfq_put_queue(bfqq); bfqq = bfq_get_queue(bfqd, bio, is_sync, bic, split); - bic_set_bfqq(bic, bfqq, is_sync); + bic_set_bfqq(bic, bfqq, is_sync, act_idx); if (split && is_sync) { - if ((bic->was_in_burst_list && bfqd->large_burst) || - bic->saved_in_large_burst) + if ((bfqq_data->was_in_burst_list && bfqd->large_burst) || + bfqq_data->saved_in_large_burst) bfq_mark_bfqq_in_large_burst(bfqq); else { bfq_clear_bfqq_in_large_burst(bfqq); - if (bic->was_in_burst_list) + if (bfqq_data->was_in_burst_list) /* * If bfqq was in the current * burst list before being @@ -6686,19 +6847,20 @@ static struct bfq_queue *bfq_init_rq(struct request *rq) struct bfq_queue *bfqq; bool new_queue = false; bool bfqq_already_existing = false, split = false; + unsigned int a_idx = bfq_actuator_index(bfqd, bio); if (unlikely(!rq->elv.icq)) return NULL; /* - * Assuming that elv.priv[1] is set only if everything is set + * Assuming that RQ_BFQQ(rq) is set only if everything is set * for this rq. This holds true, because this function is * invoked only for insertion or merging, and, after such * events, a request cannot be manipulated any longer before * being removed from bfq. */ - if (rq->elv.priv[1]) - return rq->elv.priv[1]; + if (RQ_BFQQ(rq)) + return RQ_BFQQ(rq); bic = icq_to_bic(rq->elv.icq); @@ -6712,12 +6874,13 @@ static struct bfq_queue *bfq_init_rq(struct request *rq) if (likely(!new_queue)) { /* If the queue was seeky for too long, break it apart. */ if (bfq_bfqq_coop(bfqq) && bfq_bfqq_split_coop(bfqq) && - !bic->stably_merged) { + !bic->bfqq_data[a_idx].stably_merged) { struct bfq_queue *old_bfqq = bfqq; /* Update bic before losing reference to bfqq */ if (bfq_bfqq_in_large_burst(bfqq)) - bic->saved_in_large_burst = true; + bic->bfqq_data[a_idx].saved_in_large_burst = + true; bfqq = bfq_split_bfqq(bic, bfqq); split = true; @@ -6900,13 +7063,15 @@ static void __bfq_put_async_bfqq(struct bfq_data *bfqd, */ void bfq_put_async_queues(struct bfq_data *bfqd, struct bfq_group *bfqg) { - int i, j; + int i, j, k; - for (i = 0; i < 2; i++) - for (j = 0; j < IOPRIO_NR_LEVELS; j++) - __bfq_put_async_bfqq(bfqd, &bfqg->async_bfqq[i][j]); + for (k = 0; k < bfqd->num_actuators; k++) { + for (i = 0; i < 2; i++) + for (j = 0; j < IOPRIO_NR_LEVELS; j++) + __bfq_put_async_bfqq(bfqd, &bfqg->async_bfqq[i][j][k]); - __bfq_put_async_bfqq(bfqd, &bfqg->async_idle_bfqq); + __bfq_put_async_bfqq(bfqd, &bfqg->async_idle_bfqq[k]); + } } /* @@ -6983,7 +7148,7 @@ static void bfq_exit_queue(struct elevator_queue *e) bfqg_and_blkg_put(bfqd->root_group); #ifdef CONFIG_BFQ_GROUP_IOSCHED - blkcg_deactivate_policy(bfqd->queue, &blkcg_policy_bfq); + blkcg_deactivate_policy(bfqd->queue->disk, &blkcg_policy_bfq); #else spin_lock_irq(&bfqd->lock); bfq_put_async_queues(bfqd, bfqd->root_group); @@ -6993,7 +7158,7 @@ static void bfq_exit_queue(struct elevator_queue *e) blk_stat_disable_accounting(bfqd->queue); clear_bit(ELEVATOR_FLAG_DISABLE_WBT, &e->flags); - wbt_enable_default(bfqd->queue); + wbt_enable_default(bfqd->queue->disk); kfree(bfqd); } @@ -7018,6 +7183,8 @@ static int bfq_init_queue(struct request_queue *q, struct elevator_type *e) { struct bfq_data *bfqd; struct elevator_queue *eq; + unsigned int i; + struct blk_independent_access_ranges *ia_ranges = q->disk->ia_ranges; eq = elevator_alloc(q, e); if (!eq) @@ -7038,8 +7205,10 @@ static int bfq_init_queue(struct request_queue *q, struct elevator_type *e) * Our fallback bfqq if bfq_find_alloc_queue() runs into OOM issues. * Grab a permanent reference to it, so that the normal code flow * will not attempt to free it. + * Set zero as actuator index: we will pretend that + * all I/O requests are for the same actuator. */ - bfq_init_bfqq(bfqd, &bfqd->oom_bfqq, NULL, 1, 0); + bfq_init_bfqq(bfqd, &bfqd->oom_bfqq, NULL, 1, 0, 0); bfqd->oom_bfqq.ref++; bfqd->oom_bfqq.new_ioprio = BFQ_DEFAULT_QUEUE_IOPRIO; bfqd->oom_bfqq.new_ioprio_class = IOPRIO_CLASS_BE; @@ -7058,6 +7227,39 @@ static int bfq_init_queue(struct request_queue *q, struct elevator_type *e) bfqd->queue = q; + bfqd->num_actuators = 1; + /* + * If the disk supports multiple actuators, copy independent + * access ranges from the request queue structure. + */ + spin_lock_irq(&q->queue_lock); + if (ia_ranges) { + /* + * Check if the disk ia_ranges size exceeds the current bfq + * actuator limit. + */ + if (ia_ranges->nr_ia_ranges > BFQ_MAX_ACTUATORS) { + pr_crit("nr_ia_ranges higher than act limit: iars=%d, max=%d.\n", + ia_ranges->nr_ia_ranges, BFQ_MAX_ACTUATORS); + pr_crit("Falling back to single actuator mode.\n"); + } else { + bfqd->num_actuators = ia_ranges->nr_ia_ranges; + + for (i = 0; i < bfqd->num_actuators; i++) { + bfqd->sector[i] = ia_ranges->ia_range[i].sector; + bfqd->nr_sectors[i] = + ia_ranges->ia_range[i].nr_sectors; + } + } + } + + /* Otherwise use single-actuator dev info */ + if (bfqd->num_actuators == 1) { + bfqd->sector[0] = 0; + bfqd->nr_sectors[0] = get_capacity(q->disk); + } + spin_unlock_irq(&q->queue_lock); + INIT_LIST_HEAD(&bfqd->dispatch); hrtimer_init(&bfqd->idle_slice_timer, CLOCK_MONOTONIC, @@ -7069,7 +7271,8 @@ static int bfq_init_queue(struct request_queue *q, struct elevator_type *e) bfqd->num_groups_with_pending_reqs = 0; #endif - INIT_LIST_HEAD(&bfqd->active_list); + INIT_LIST_HEAD(&bfqd->active_list[0]); + INIT_LIST_HEAD(&bfqd->active_list[1]); INIT_LIST_HEAD(&bfqd->idle_list); INIT_HLIST_HEAD(&bfqd->burst_list); @@ -7095,7 +7298,6 @@ static int bfq_init_queue(struct request_queue *q, struct elevator_type *e) */ bfqd->bfq_wr_coeff = 30; bfqd->bfq_wr_rt_max_time = msecs_to_jiffies(300); - bfqd->bfq_wr_max_time = 0; bfqd->bfq_wr_min_idle_time = msecs_to_jiffies(2000); bfqd->bfq_wr_min_inter_arr_async = msecs_to_jiffies(500); bfqd->bfq_wr_max_softrt_rate = 7000; /* @@ -7114,6 +7316,9 @@ static int bfq_init_queue(struct request_queue *q, struct elevator_type *e) ref_wr_duration[blk_queue_nonrot(bfqd->queue)]; bfqd->peak_rate = ref_rate[blk_queue_nonrot(bfqd->queue)] * 2 / 3; + /* see comments on the definition of next field inside bfq_data */ + bfqd->actuator_load_threshold = 4; + spin_lock_init(&bfqd->lock); /* @@ -7141,7 +7346,7 @@ static int bfq_init_queue(struct request_queue *q, struct elevator_type *e) blk_queue_flag_set(QUEUE_FLAG_SQ_SCHED, q); set_bit(ELEVATOR_FLAG_DISABLE_WBT, &eq->flags); - wbt_disable_default(q); + wbt_disable_default(q->disk); blk_stat_enable_accounting(q); return 0; diff --git a/block/bfq-iosched.h b/block/bfq-iosched.h index 466e4865ace6..69aaee52285a 100644 --- a/block/bfq-iosched.h +++ b/block/bfq-iosched.h @@ -33,6 +33,14 @@ */ #define BFQ_SOFTRT_WEIGHT_FACTOR 100 +/* + * Maximum number of actuators supported. This constant is used simply + * to define the size of the static array that will contain + * per-actuator data. The current value is hopefully a good upper + * bound to the possible number of actuators of any actual drive. + */ +#define BFQ_MAX_ACTUATORS 8 + struct bfq_entity; /** @@ -227,12 +235,14 @@ struct bfq_ttime { * struct bfq_queue - leaf schedulable entity. * * A bfq_queue is a leaf request queue; it can be associated with an - * io_context or more, if it is async or shared between cooperating - * processes. @cgroup holds a reference to the cgroup, to be sure that it - * does not disappear while a bfqq still references it (mostly to avoid - * races between request issuing and task migration followed by cgroup - * destruction). - * All the fields are protected by the queue lock of the containing bfqd. + * io_context or more, if it is async or shared between cooperating + * processes. Besides, it contains I/O requests for only one actuator + * (an io_context is associated with a different bfq_queue for each + * actuator it generates I/O for). @cgroup holds a reference to the + * cgroup, to be sure that it does not disappear while a bfqq still + * references it (mostly to avoid races between request issuing and + * task migration followed by cgroup destruction). All the fields are + * protected by the queue lock of the containing bfqd. */ struct bfq_queue { /* reference counter */ @@ -397,24 +407,18 @@ struct bfq_queue { * the woken queues when this queue exits. */ struct hlist_head woken_list; + + /* index of the actuator this queue is associated with */ + unsigned int actuator_idx; }; /** - * struct bfq_io_cq - per (request_queue, io_context) structure. - */ -struct bfq_io_cq { - /* associated io_cq structure */ - struct io_cq icq; /* must be the first member */ - /* array of two process queues, the sync and the async */ - struct bfq_queue *bfqq[2]; - /* per (request_queue, blkcg) ioprio */ - int ioprio; -#ifdef CONFIG_BFQ_GROUP_IOSCHED - uint64_t blkcg_serial_nr; /* the current blkcg serial */ -#endif +* struct bfq_data - bfqq data unique and persistent for associated bfq_io_cq +*/ +struct bfq_iocq_bfqq_data { /* * Snapshot of the has_short_time flag before merging; taken - * to remember its value while the queue is merged, so as to + * to remember its values while the queue is merged, so as to * be able to restore it in case of split. */ bool saved_has_short_ttime; @@ -428,7 +432,7 @@ struct bfq_io_cq { u64 saved_tot_idle_time; /* - * Same purpose as the previous fields for the value of the + * Same purpose as the previous fields for the values of the * field keeping the queue's belonging to a large burst */ bool saved_in_large_burst; @@ -466,6 +470,38 @@ struct bfq_io_cq { struct bfq_queue *stable_merge_bfqq; bool stably_merged; /* non splittable if true */ +}; + +/** + * struct bfq_io_cq - per (request_queue, io_context) structure. + */ +struct bfq_io_cq { + /* associated io_cq structure */ + struct io_cq icq; /* must be the first member */ + /* + * Matrix of associated process queues: first row for async + * queues, second row sync queues. Each row contains one + * column for each actuator. An I/O request generated by the + * process is inserted into the queue pointed by bfqq[i][j] if + * the request is to be served by the j-th actuator of the + * drive, where i==0 or i==1, depending on whether the request + * is async or sync. So there is a distinct queue for each + * actuator. + */ + struct bfq_queue *bfqq[2][BFQ_MAX_ACTUATORS]; + /* per (request_queue, blkcg) ioprio */ + int ioprio; +#ifdef CONFIG_BFQ_GROUP_IOSCHED + uint64_t blkcg_serial_nr; /* the current blkcg serial */ +#endif + + /* + * Persistent data for associated synchronous process queues + * (one queue per actuator, see field bfqq above). In + * particular, each of these queues may undergo a merge. + */ + struct bfq_iocq_bfqq_data bfqq_data[BFQ_MAX_ACTUATORS]; + unsigned int requests; /* Number of requests this process has in flight */ }; @@ -554,7 +590,12 @@ struct bfq_data { /* number of queued requests */ int queued; /* number of requests dispatched and waiting for completion */ - int rq_in_driver; + int tot_rq_in_driver; + /* + * number of requests dispatched and waiting for completion + * for each actuator + */ + int rq_in_driver[BFQ_MAX_ACTUATORS]; /* true if the device is non rotational and performs queueing */ bool nonrot_with_queueing; @@ -648,8 +689,13 @@ struct bfq_data { /* maximum budget allotted to a bfq_queue before rescheduling */ int bfq_max_budget; - /* list of all the bfq_queues active on the device */ - struct list_head active_list; + /* + * List of all the bfq_queues active for a specific actuator + * on the device. Keeping active queues separate on a + * per-actuator basis helps implementing per-actuator + * injection more efficiently. + */ + struct list_head active_list[BFQ_MAX_ACTUATORS]; /* list of all the bfq_queues idle on the device */ struct list_head idle_list; @@ -723,8 +769,6 @@ struct bfq_data { * is multiplied. */ unsigned int bfq_wr_coeff; - /* maximum duration of a weight-raising period (jiffies) */ - unsigned int bfq_wr_max_time; /* Maximum weight-raising duration for soft real-time processes */ unsigned int bfq_wr_rt_max_time; @@ -772,6 +816,42 @@ struct bfq_data { */ unsigned int word_depths[2][2]; unsigned int full_depth_shift; + + /* + * Number of independent actuators. This is equal to 1 in + * case of single-actuator drives. + */ + unsigned int num_actuators; + /* + * Disk independent access ranges for each actuator + * in this device. + */ + sector_t sector[BFQ_MAX_ACTUATORS]; + sector_t nr_sectors[BFQ_MAX_ACTUATORS]; + struct blk_independent_access_range ia_ranges[BFQ_MAX_ACTUATORS]; + + /* + * If the number of I/O requests queued in the device for a + * given actuator is below next threshold, then the actuator + * is deemed as underutilized. If this condition is found to + * hold for some actuator upon a dispatch, but (i) the + * in-service queue does not contain I/O for that actuator, + * while (ii) some other queue does contain I/O for that + * actuator, then the head I/O request of the latter queue is + * returned (injected), instead of the head request of the + * currently in-service queue. + * + * We set the threshold, empirically, to the minimum possible + * value for which an actuator is fully utilized, or close to + * be fully utilized. By doing so, injected I/O 'steals' as + * few drive-queue slots as possibile to the in-service + * queue. This reduces as much as possible the probability + * that the service of I/O from the in-service bfq_queue gets + * delayed because of slot exhaustion, i.e., because all the + * slots of the drive queue are filled with I/O injected from + * other queues (NCQ provides for 32 slots). + */ + unsigned int actuator_load_threshold; }; enum bfqq_state_flags { @@ -929,16 +1009,14 @@ struct bfq_group { /* reference counter (see comments in bfq_bic_update_cgroup) */ refcount_t ref; - /* Is bfq_group still online? */ - bool online; struct bfq_entity entity; struct bfq_sched_data sched_data; struct bfq_data *bfqd; - struct bfq_queue *async_bfqq[2][IOPRIO_NR_LEVELS]; - struct bfq_queue *async_idle_bfqq; + struct bfq_queue *async_bfqq[2][IOPRIO_NR_LEVELS][BFQ_MAX_ACTUATORS]; + struct bfq_queue *async_idle_bfqq[BFQ_MAX_ACTUATORS]; struct bfq_entity *my_entity; @@ -955,8 +1033,8 @@ struct bfq_group { struct bfq_entity entity; struct bfq_sched_data sched_data; - struct bfq_queue *async_bfqq[2][IOPRIO_NR_LEVELS]; - struct bfq_queue *async_idle_bfqq; + struct bfq_queue *async_bfqq[2][IOPRIO_NR_LEVELS][BFQ_MAX_ACTUATORS]; + struct bfq_queue *async_idle_bfqq[BFQ_MAX_ACTUATORS]; struct rb_root rq_pos_tree; }; @@ -969,8 +1047,10 @@ struct bfq_group { extern const int bfq_timeout; -struct bfq_queue *bic_to_bfqq(struct bfq_io_cq *bic, bool is_sync); -void bic_set_bfqq(struct bfq_io_cq *bic, struct bfq_queue *bfqq, bool is_sync); +struct bfq_queue *bic_to_bfqq(struct bfq_io_cq *bic, bool is_sync, + unsigned int actuator_idx); +void bic_set_bfqq(struct bfq_io_cq *bic, struct bfq_queue *bfqq, bool is_sync, + unsigned int actuator_idx); struct bfq_data *bic_to_bfqd(struct bfq_io_cq *bic); void bfq_pos_tree_add_move(struct bfq_data *bfqd, struct bfq_queue *bfqq); void bfq_weights_tree_add(struct bfq_queue *bfqq); diff --git a/block/bfq-wf2q.c b/block/bfq-wf2q.c index ea4c3d757fdd..7941b6f07391 100644 --- a/block/bfq-wf2q.c +++ b/block/bfq-wf2q.c @@ -493,7 +493,7 @@ static void bfq_active_insert(struct bfq_service_tree *st, bfq_update_active_tree(node); if (bfqq) - list_add(&bfqq->bfqq_list, &bfqq->bfqd->active_list); + list_add(&bfqq->bfqq_list, &bfqq->bfqd->active_list[bfqq->actuator_idx]); bfq_inc_active_entities(entity); } diff --git a/block/bio-integrity.c b/block/bio-integrity.c index 3f5685c00e36..4533eb491661 100644 --- a/block/bio-integrity.c +++ b/block/bio-integrity.c @@ -124,23 +124,18 @@ int bio_integrity_add_page(struct bio *bio, struct page *page, unsigned int len, unsigned int offset) { struct bio_integrity_payload *bip = bio_integrity(bio); - struct bio_vec *iv; if (bip->bip_vcnt >= bip->bip_max_vcnt) { printk(KERN_ERR "%s: bip_vec full\n", __func__); return 0; } - iv = bip->bip_vec + bip->bip_vcnt; - if (bip->bip_vcnt && bvec_gap_to_prev(&bdev_get_queue(bio->bi_bdev)->limits, &bip->bip_vec[bip->bip_vcnt - 1], offset)) return 0; - iv->bv_page = page; - iv->bv_len = len; - iv->bv_offset = offset; + bvec_set_page(&bip->bip_vec[bip->bip_vcnt], page, len, offset); bip->bip_vcnt++; return len; @@ -418,6 +413,7 @@ int bio_integrity_clone(struct bio *bio, struct bio *bio_src, bip->bip_vcnt = bip_src->bip_vcnt; bip->bip_iter = bip_src->bip_iter; + bip->bip_flags = bip_src->bip_flags & ~BIP_BLOCK_INTEGRITY; return 0; } diff --git a/block/bio.c b/block/bio.c index ab59a491a883..2693f34afb7e 100644 --- a/block/bio.c +++ b/block/bio.c @@ -26,7 +26,6 @@ #include "blk-cgroup.h" #define ALLOC_CACHE_THRESHOLD 16 -#define ALLOC_CACHE_SLACK 64 #define ALLOC_CACHE_MAX 256 struct bio_alloc_cache { @@ -1029,10 +1028,7 @@ int bio_add_hw_page(struct request_queue *q, struct bio *bio, if (bio->bi_vcnt >= queue_max_segments(q)) return 0; - bvec = &bio->bi_io_vec[bio->bi_vcnt]; - bvec->bv_page = page; - bvec->bv_len = len; - bvec->bv_offset = offset; + bvec_set_page(&bio->bi_io_vec[bio->bi_vcnt], page, len, offset); bio->bi_vcnt++; bio->bi_iter.bi_size += len; return len; @@ -1108,15 +1104,10 @@ EXPORT_SYMBOL_GPL(bio_add_zone_append_page); void __bio_add_page(struct bio *bio, struct page *page, unsigned int len, unsigned int off) { - struct bio_vec *bv = &bio->bi_io_vec[bio->bi_vcnt]; - WARN_ON_ONCE(bio_flagged(bio, BIO_CLONED)); WARN_ON_ONCE(bio_full(bio, len)); - bv->bv_page = page; - bv->bv_offset = off; - bv->bv_len = len; - + bvec_set_page(&bio->bi_io_vec[bio->bi_vcnt], page, len, off); bio->bi_iter.bi_size += len; bio->bi_vcnt++; } @@ -1792,6 +1783,8 @@ static int __init init_bio(void) { int i; + BUILD_BUG_ON(BIO_FLAG_LAST > 8 * sizeof_field(struct bio, bi_flags)); + bio_integrity_init(); for (i = 0; i < ARRAY_SIZE(bvec_slabs); i++) { diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c index 9ac1efb053e0..bd50b55bdb61 100644 --- a/block/blk-cgroup.c +++ b/block/blk-cgroup.c @@ -118,14 +118,26 @@ static void blkg_free_workfn(struct work_struct *work) { struct blkcg_gq *blkg = container_of(work, struct blkcg_gq, free_work); + struct request_queue *q = blkg->q; int i; + /* + * pd_free_fn() can also be called from blkcg_deactivate_policy(), + * in order to make sure pd_free_fn() is called in order, the deletion + * of the list blkg->q_node is delayed to here from blkg_destroy(), and + * blkcg_mutex is used to synchronize blkg_free_workfn() and + * blkcg_deactivate_policy(). + */ + mutex_lock(&q->blkcg_mutex); for (i = 0; i < BLKCG_MAX_POLS; i++) if (blkg->pd[i]) blkcg_policy[i]->pd_free_fn(blkg->pd[i]); + if (blkg->parent) + blkg_put(blkg->parent); + list_del_init(&blkg->q_node); + mutex_unlock(&q->blkcg_mutex); - if (blkg->q) - blk_put_queue(blkg->q); + blk_put_queue(q); free_percpu(blkg->iostat_cpu); percpu_ref_exit(&blkg->refcnt); kfree(blkg); @@ -158,8 +170,6 @@ static void __blkg_release(struct rcu_head *rcu) /* release the blkcg and parent blkg refs this blkg has been holding */ css_put(&blkg->blkcg->css); - if (blkg->parent) - blkg_put(blkg->parent); blkg_free(blkg); } @@ -249,16 +259,13 @@ static struct blkcg_gq *blkg_alloc(struct blkcg *blkcg, struct gendisk *disk, blkg = kzalloc_node(sizeof(*blkg), gfp_mask, disk->queue->node); if (!blkg) return NULL; - if (percpu_ref_init(&blkg->refcnt, blkg_release, 0, gfp_mask)) - goto err_free; - + goto out_free_blkg; blkg->iostat_cpu = alloc_percpu_gfp(struct blkg_iostat_set, gfp_mask); if (!blkg->iostat_cpu) - goto err_free; - + goto out_exit_refcnt; if (!blk_get_queue(disk->queue)) - goto err_free; + goto out_free_iostat; blkg->q = disk->queue; INIT_LIST_HEAD(&blkg->q_node); @@ -281,19 +288,28 @@ static struct blkcg_gq *blkg_alloc(struct blkcg *blkcg, struct gendisk *disk, continue; /* alloc per-policy data and attach it to blkg */ - pd = pol->pd_alloc_fn(gfp_mask, disk->queue, blkcg); + pd = pol->pd_alloc_fn(disk, blkcg, gfp_mask); if (!pd) - goto err_free; - + goto out_free_pds; blkg->pd[i] = pd; pd->blkg = blkg; pd->plid = i; + pd->online = false; } return blkg; -err_free: - blkg_free(blkg); +out_free_pds: + while (--i >= 0) + if (blkg->pd[i]) + blkcg_policy[i]->pd_free_fn(blkg->pd[i]); + blk_put_queue(disk->queue); +out_free_iostat: + free_percpu(blkg->iostat_cpu); +out_exit_refcnt: + percpu_ref_exit(&blkg->refcnt); +out_free_blkg: + kfree(blkg); return NULL; } @@ -359,8 +375,11 @@ static struct blkcg_gq *blkg_create(struct blkcg *blkcg, struct gendisk *disk, for (i = 0; i < BLKCG_MAX_POLS; i++) { struct blkcg_policy *pol = blkcg_policy[i]; - if (blkg->pd[i] && pol->pd_online_fn) - pol->pd_online_fn(blkg->pd[i]); + if (blkg->pd[i]) { + if (pol->pd_online_fn) + pol->pd_online_fn(blkg->pd[i]); + blkg->pd[i]->online = true; + } } } blkg->online = true; @@ -376,7 +395,8 @@ static struct blkcg_gq *blkg_create(struct blkcg *blkcg, struct gendisk *disk, err_put_css: css_put(&blkcg->css); err_free_blkg: - blkg_free(new_blkg); + if (new_blkg) + blkg_free(new_blkg); return ERR_PTR(ret); } @@ -458,21 +478,28 @@ static void blkg_destroy(struct blkcg_gq *blkg) lockdep_assert_held(&blkg->q->queue_lock); lockdep_assert_held(&blkcg->lock); - /* Something wrong if we are trying to remove same group twice */ - WARN_ON_ONCE(list_empty(&blkg->q_node)); - WARN_ON_ONCE(hlist_unhashed(&blkg->blkcg_node)); + /* + * blkg stays on the queue list until blkg_free_workfn(), see details in + * blkg_free_workfn(), hence this function can be called from + * blkcg_destroy_blkgs() first and again from blkg_destroy_all() before + * blkg_free_workfn(). + */ + if (hlist_unhashed(&blkg->blkcg_node)) + return; for (i = 0; i < BLKCG_MAX_POLS; i++) { struct blkcg_policy *pol = blkcg_policy[i]; - if (blkg->pd[i] && pol->pd_offline_fn) - pol->pd_offline_fn(blkg->pd[i]); + if (blkg->pd[i] && blkg->pd[i]->online) { + blkg->pd[i]->online = false; + if (pol->pd_offline_fn) + pol->pd_offline_fn(blkg->pd[i]); + } } blkg->online = false; radix_tree_delete(&blkcg->blkg_tree, blkg->q->id); - list_del_init(&blkg->q_node); hlist_del_init_rcu(&blkg->blkcg_node); /* @@ -559,7 +586,7 @@ static int blkcg_reset_stats(struct cgroup_subsys_state *css, const char *blkg_dev_name(struct blkcg_gq *blkg) { - if (!blkg->q->disk || !blkg->q->disk->bdi->dev) + if (!blkg->q->disk) return NULL; return bdi_dev_name(blkg->q->disk->bdi); } @@ -1273,6 +1300,7 @@ int blkcg_init_disk(struct gendisk *disk) int ret; INIT_LIST_HEAD(&q->blkg_list); + mutex_init(&q->blkcg_mutex); new_blkg = blkg_alloc(&blkcg_root, disk, GFP_KERNEL); if (!new_blkg) @@ -1349,9 +1377,9 @@ static void blkcg_bind(struct cgroup_subsys_state *root_css) static void blkcg_exit(struct task_struct *tsk) { - if (tsk->throttle_queue) - blk_put_queue(tsk->throttle_queue); - tsk->throttle_queue = NULL; + if (tsk->throttle_disk) + put_disk(tsk->throttle_disk); + tsk->throttle_disk = NULL; } struct cgroup_subsys io_cgrp_subsys = { @@ -1377,14 +1405,14 @@ struct cgroup_subsys io_cgrp_subsys = { EXPORT_SYMBOL_GPL(io_cgrp_subsys); /** - * blkcg_activate_policy - activate a blkcg policy on a request_queue - * @q: request_queue of interest + * blkcg_activate_policy - activate a blkcg policy on a gendisk + * @disk: gendisk of interest * @pol: blkcg policy to activate * - * Activate @pol on @q. Requires %GFP_KERNEL context. @q goes through + * Activate @pol on @disk. Requires %GFP_KERNEL context. @disk goes through * bypass mode to populate its blkgs with policy_data for @pol. * - * Activation happens with @q bypassed, so nobody would be accessing blkgs + * Activation happens with @disk bypassed, so nobody would be accessing blkgs * from IO path. Update of each blkg is protected by both queue and blkcg * locks so that holding either lock and testing blkcg_policy_enabled() is * always enough for dereferencing policy data. @@ -1392,9 +1420,9 @@ EXPORT_SYMBOL_GPL(io_cgrp_subsys); * The caller is responsible for synchronizing [de]activations and policy * [un]registerations. Returns 0 on success, -errno on failure. */ -int blkcg_activate_policy(struct request_queue *q, - const struct blkcg_policy *pol) +int blkcg_activate_policy(struct gendisk *disk, const struct blkcg_policy *pol) { + struct request_queue *q = disk->queue; struct blkg_policy_data *pd_prealloc = NULL; struct blkcg_gq *blkg, *pinned_blkg = NULL; int ret; @@ -1419,8 +1447,8 @@ retry: pd = pd_prealloc; pd_prealloc = NULL; } else { - pd = pol->pd_alloc_fn(GFP_NOWAIT | __GFP_NOWARN, q, - blkg->blkcg); + pd = pol->pd_alloc_fn(disk, blkg->blkcg, + GFP_NOWAIT | __GFP_NOWARN); } if (!pd) { @@ -1437,8 +1465,8 @@ retry: if (pd_prealloc) pol->pd_free_fn(pd_prealloc); - pd_prealloc = pol->pd_alloc_fn(GFP_KERNEL, q, - blkg->blkcg); + pd_prealloc = pol->pd_alloc_fn(disk, blkg->blkcg, + GFP_KERNEL); if (pd_prealloc) goto retry; else @@ -1448,6 +1476,7 @@ retry: blkg->pd[pol->plid] = pd; pd->blkg = blkg; pd->plid = pol->plid; + pd->online = false; } /* all allocated, init in the same order */ @@ -1455,9 +1484,11 @@ retry: list_for_each_entry_reverse(blkg, &q->blkg_list, q_node) pol->pd_init_fn(blkg->pd[pol->plid]); - if (pol->pd_online_fn) - list_for_each_entry_reverse(blkg, &q->blkg_list, q_node) + list_for_each_entry_reverse(blkg, &q->blkg_list, q_node) { + if (pol->pd_online_fn) pol->pd_online_fn(blkg->pd[pol->plid]); + blkg->pd[pol->plid]->online = true; + } __set_bit(pol->plid, q->blkcg_pols); ret = 0; @@ -1492,16 +1523,17 @@ enomem: EXPORT_SYMBOL_GPL(blkcg_activate_policy); /** - * blkcg_deactivate_policy - deactivate a blkcg policy on a request_queue - * @q: request_queue of interest + * blkcg_deactivate_policy - deactivate a blkcg policy on a gendisk + * @disk: gendisk of interest * @pol: blkcg policy to deactivate * - * Deactivate @pol on @q. Follows the same synchronization rules as + * Deactivate @pol on @disk. Follows the same synchronization rules as * blkcg_activate_policy(). */ -void blkcg_deactivate_policy(struct request_queue *q, +void blkcg_deactivate_policy(struct gendisk *disk, const struct blkcg_policy *pol) { + struct request_queue *q = disk->queue; struct blkcg_gq *blkg; if (!blkcg_policy_enabled(q, pol)) @@ -1510,6 +1542,7 @@ void blkcg_deactivate_policy(struct request_queue *q, if (queue_is_mq(q)) blk_mq_freeze_queue(q); + mutex_lock(&q->blkcg_mutex); spin_lock_irq(&q->queue_lock); __clear_bit(pol->plid, q->blkcg_pols); @@ -1519,7 +1552,7 @@ void blkcg_deactivate_policy(struct request_queue *q, spin_lock(&blkcg->lock); if (blkg->pd[pol->plid]) { - if (pol->pd_offline_fn) + if (blkg->pd[pol->plid]->online && pol->pd_offline_fn) pol->pd_offline_fn(blkg->pd[pol->plid]); pol->pd_free_fn(blkg->pd[pol->plid]); blkg->pd[pol->plid] = NULL; @@ -1528,6 +1561,7 @@ void blkcg_deactivate_policy(struct request_queue *q, } spin_unlock_irq(&q->queue_lock); + mutex_unlock(&q->blkcg_mutex); if (queue_is_mq(q)) blk_mq_unfreeze_queue(q); @@ -1797,29 +1831,29 @@ static void blkcg_maybe_throttle_blkg(struct blkcg_gq *blkg, bool use_memdelay) * * This is only called if we've been marked with set_notify_resume(). Obviously * we can be set_notify_resume() for reasons other than blkcg throttling, so we - * check to see if current->throttle_queue is set and if not this doesn't do + * check to see if current->throttle_disk is set and if not this doesn't do * anything. This should only ever be called by the resume code, it's not meant * to be called by people willy-nilly as it will actually do the work to * throttle the task if it is setup for throttling. */ void blkcg_maybe_throttle_current(void) { - struct request_queue *q = current->throttle_queue; + struct gendisk *disk = current->throttle_disk; struct blkcg *blkcg; struct blkcg_gq *blkg; bool use_memdelay = current->use_memdelay; - if (!q) + if (!disk) return; - current->throttle_queue = NULL; + current->throttle_disk = NULL; current->use_memdelay = false; rcu_read_lock(); blkcg = css_to_blkcg(blkcg_css()); if (!blkcg) goto out; - blkg = blkg_lookup(blkcg, q); + blkg = blkg_lookup(blkcg, disk->queue); if (!blkg) goto out; if (!blkg_tryget(blkg)) @@ -1828,11 +1862,10 @@ void blkcg_maybe_throttle_current(void) blkcg_maybe_throttle_blkg(blkg, use_memdelay); blkg_put(blkg); - blk_put_queue(q); + put_disk(disk); return; out: rcu_read_unlock(); - blk_put_queue(q); } /** @@ -1854,18 +1887,17 @@ out: */ void blkcg_schedule_throttle(struct gendisk *disk, bool use_memdelay) { - struct request_queue *q = disk->queue; - if (unlikely(current->flags & PF_KTHREAD)) return; - if (current->throttle_queue != q) { - if (!blk_get_queue(q)) + if (current->throttle_disk != disk) { + if (test_bit(GD_DEAD, &disk->state)) return; + get_device(disk_to_dev(disk)); - if (current->throttle_queue) - blk_put_queue(current->throttle_queue); - current->throttle_queue = q; + if (current->throttle_disk) + put_disk(current->throttle_disk); + current->throttle_disk = disk; } if (use_memdelay) diff --git a/block/blk-cgroup.h b/block/blk-cgroup.h index 1e94e404eaa8..9c5078755e5e 100644 --- a/block/blk-cgroup.h +++ b/block/blk-cgroup.h @@ -135,6 +135,7 @@ struct blkg_policy_data { /* the blkg and policy id this per-policy data belongs to */ struct blkcg_gq *blkg; int plid; + bool online; }; /* @@ -154,8 +155,8 @@ typedef struct blkcg_policy_data *(blkcg_pol_alloc_cpd_fn)(gfp_t gfp); typedef void (blkcg_pol_init_cpd_fn)(struct blkcg_policy_data *cpd); typedef void (blkcg_pol_free_cpd_fn)(struct blkcg_policy_data *cpd); typedef void (blkcg_pol_bind_cpd_fn)(struct blkcg_policy_data *cpd); -typedef struct blkg_policy_data *(blkcg_pol_alloc_pd_fn)(gfp_t gfp, - struct request_queue *q, struct blkcg *blkcg); +typedef struct blkg_policy_data *(blkcg_pol_alloc_pd_fn)(struct gendisk *disk, + struct blkcg *blkcg, gfp_t gfp); typedef void (blkcg_pol_init_pd_fn)(struct blkg_policy_data *pd); typedef void (blkcg_pol_online_pd_fn)(struct blkg_policy_data *pd); typedef void (blkcg_pol_offline_pd_fn)(struct blkg_policy_data *pd); @@ -194,9 +195,8 @@ void blkcg_exit_disk(struct gendisk *disk); /* Blkio controller policy registration */ int blkcg_policy_register(struct blkcg_policy *pol); void blkcg_policy_unregister(struct blkcg_policy *pol); -int blkcg_activate_policy(struct request_queue *q, - const struct blkcg_policy *pol); -void blkcg_deactivate_policy(struct request_queue *q, +int blkcg_activate_policy(struct gendisk *disk, const struct blkcg_policy *pol); +void blkcg_deactivate_policy(struct gendisk *disk, const struct blkcg_policy *pol); const char *blkg_dev_name(struct blkcg_gq *blkg); @@ -495,9 +495,9 @@ static inline int blkcg_init_disk(struct gendisk *disk) { return 0; } static inline void blkcg_exit_disk(struct gendisk *disk) { } static inline int blkcg_policy_register(struct blkcg_policy *pol) { return 0; } static inline void blkcg_policy_unregister(struct blkcg_policy *pol) { } -static inline int blkcg_activate_policy(struct request_queue *q, +static inline int blkcg_activate_policy(struct gendisk *disk, const struct blkcg_policy *pol) { return 0; } -static inline void blkcg_deactivate_policy(struct request_queue *q, +static inline void blkcg_deactivate_policy(struct gendisk *disk, const struct blkcg_policy *pol) { } static inline struct blkg_policy_data *blkg_to_pd(struct blkcg_gq *blkg, diff --git a/block/blk-core.c b/block/blk-core.c index b5098355d8b2..5fb6856745b4 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -570,7 +570,7 @@ static inline blk_status_t blk_check_zone_append(struct request_queue *q, return BLK_STS_NOTSUPP; /* The bio sector must point to the start of a sequential zone */ - if (bio->bi_iter.bi_sector & (bdev_zone_sectors(bio->bi_bdev) - 1) || + if (!bdev_is_zone_start(bio->bi_bdev, bio->bi_iter.bi_sector) || !bio_zone_is_seq(bio)) return BLK_STS_IOERR; @@ -684,6 +684,18 @@ static void __submit_bio_noacct_mq(struct bio *bio) void submit_bio_noacct_nocheck(struct bio *bio) { + blk_cgroup_bio_start(bio); + blkcg_bio_issue_init(bio); + + if (!bio_flagged(bio, BIO_TRACE_COMPLETION)) { + trace_block_bio_queue(bio); + /* + * Now that enqueuing has been traced, we need to trace + * completion as well. + */ + bio_set_flag(bio, BIO_TRACE_COMPLETION); + } + /* * We only want one ->submit_bio to be active at a time, else stack * usage with stacked devices could be a problem. Use current->bio_list @@ -788,17 +800,6 @@ void submit_bio_noacct(struct bio *bio) if (blk_throtl_bio(bio)) return; - - blk_cgroup_bio_start(bio); - blkcg_bio_issue_init(bio); - - if (!bio_flagged(bio, BIO_TRACE_COMPLETION)) { - trace_block_bio_queue(bio); - /* Now that enqueuing has been traced, we need to trace - * completion as well. - */ - bio_set_flag(bio, BIO_TRACE_COMPLETION); - } submit_bio_noacct_nocheck(bio); return; @@ -869,7 +870,16 @@ int bio_poll(struct bio *bio, struct io_comp_batch *iob, unsigned int flags) */ blk_flush_plug(current->plug, false); - if (bio_queue_enter(bio)) + /* + * We need to be able to enter a frozen queue, similar to how + * timeouts also need to do that. If that is blocked, then we can + * have pending IO when a queue freeze is started, and then the + * wait for the freeze to finish will wait for polled requests to + * timeout as the poller is preventer from entering the queue and + * completing them. As long as we prevent new IO from being queued, + * that should be all that matters. + */ + if (!percpu_ref_tryget(&q->q_usage_counter)) return 0; if (queue_is_mq(q)) { ret = blk_mq_poll(q, cookie, iob, flags); diff --git a/block/blk-crypto-sysfs.c b/block/blk-crypto-sysfs.c index 55268edc0625..a304434489ba 100644 --- a/block/blk-crypto-sysfs.c +++ b/block/blk-crypto-sysfs.c @@ -116,7 +116,7 @@ static void blk_crypto_release(struct kobject *kobj) kfree(container_of(kobj, struct blk_crypto_kobj, kobj)); } -static struct kobj_type blk_crypto_ktype = { +static const struct kobj_type blk_crypto_ktype = { .default_groups = blk_crypto_attr_groups, .sysfs_ops = &blk_crypto_attr_ops, .release = blk_crypto_release, diff --git a/block/blk-ia-ranges.c b/block/blk-ia-ranges.c index 2141931ddd37..c9eb4241e048 100644 --- a/block/blk-ia-ranges.c +++ b/block/blk-ia-ranges.c @@ -75,7 +75,7 @@ static void blk_ia_range_sysfs_nop_release(struct kobject *kobj) { } -static struct kobj_type blk_ia_range_ktype = { +static const struct kobj_type blk_ia_range_ktype = { .sysfs_ops = &blk_ia_range_sysfs_ops, .default_groups = blk_ia_range_groups, .release = blk_ia_range_sysfs_nop_release, @@ -94,7 +94,7 @@ static void blk_ia_ranges_sysfs_release(struct kobject *kobj) kfree(iars); } -static struct kobj_type blk_ia_ranges_ktype = { +static const struct kobj_type blk_ia_ranges_ktype = { .release = blk_ia_ranges_sysfs_release, }; diff --git a/block/blk-integrity.c b/block/blk-integrity.c index 69eed260a823..8f01d786f5cb 100644 --- a/block/blk-integrity.c +++ b/block/blk-integrity.c @@ -356,7 +356,7 @@ static const struct sysfs_ops integrity_ops = { .store = &integrity_attr_store, }; -static struct kobj_type integrity_ktype = { +static const struct kobj_type integrity_ktype = { .default_groups = integrity_groups, .sysfs_ops = &integrity_ops, }; diff --git a/block/blk-iocost.c b/block/blk-iocost.c index 6955605629e4..ff534e9d92dc 100644 --- a/block/blk-iocost.c +++ b/block/blk-iocost.c @@ -258,6 +258,11 @@ enum { VRATE_MIN = VTIME_PER_USEC * VRATE_MIN_PPM / MILLION, VRATE_CLAMP_ADJ_PCT = 4, + /* switch iff the conditions are met for longer than this */ + AUTOP_CYCLE_NSEC = 10LLU * NSEC_PER_SEC, +}; + +enum { /* if IOs end up waiting for requests, issue less */ RQ_WAIT_BUSY_PCT = 5, @@ -296,9 +301,6 @@ enum { /* don't let cmds which take a very long time pin lagging for too long */ MAX_LAGGING_PERIODS = 10, - /* switch iff the conditions are met for longer than this */ - AUTOP_CYCLE_NSEC = 10LLU * NSEC_PER_SEC, - /* * Count IO size in 4k pages. The 12bit shift helps keeping * size-proportional components of cost calculation in closer @@ -667,7 +669,7 @@ static struct ioc *q_to_ioc(struct request_queue *q) static const char __maybe_unused *ioc_name(struct ioc *ioc) { - struct gendisk *disk = ioc->rqos.q->disk; + struct gendisk *disk = ioc->rqos.disk; if (!disk) return "<unknown>"; @@ -806,11 +808,11 @@ static int ioc_autop_idx(struct ioc *ioc) u64 now_ns; /* rotational? */ - if (!blk_queue_nonrot(ioc->rqos.q)) + if (!blk_queue_nonrot(ioc->rqos.disk->queue)) return AUTOP_HDD; /* handle SATA SSDs w/ broken NCQ */ - if (blk_queue_depth(ioc->rqos.q) == 1) + if (blk_queue_depth(ioc->rqos.disk->queue) == 1) return AUTOP_SSD_QD1; /* use one of the normal ssd sets */ @@ -866,9 +868,14 @@ static void calc_lcoefs(u64 bps, u64 seqiops, u64 randiops, *page = *seqio = *randio = 0; - if (bps) - *page = DIV64_U64_ROUND_UP(VTIME_PER_SEC, - DIV_ROUND_UP_ULL(bps, IOC_PAGE_SIZE)); + if (bps) { + u64 bps_pages = DIV_ROUND_UP_ULL(bps, IOC_PAGE_SIZE); + + if (bps_pages) + *page = DIV64_U64_ROUND_UP(VTIME_PER_SEC, bps_pages); + else + *page = 1; + } if (seqiops) { v = DIV64_U64_ROUND_UP(VTIME_PER_SEC, seqiops); @@ -926,8 +933,8 @@ static bool ioc_refresh_params(struct ioc *ioc, bool force) ioc->vrate_min = DIV64_U64_ROUND_UP((u64)ioc->params.qos[QOS_MIN] * VTIME_PER_USEC, MILLION); - ioc->vrate_max = div64_u64((u64)ioc->params.qos[QOS_MAX] * - VTIME_PER_USEC, MILLION); + ioc->vrate_max = DIV64_U64_ROUND_UP((u64)ioc->params.qos[QOS_MAX] * + VTIME_PER_USEC, MILLION); return true; } @@ -2642,7 +2649,7 @@ retry_lock: if (use_debt) { iocg_incur_debt(iocg, abs_cost, &now); if (iocg_kick_delay(iocg, &now)) - blkcg_schedule_throttle(rqos->q->disk, + blkcg_schedule_throttle(rqos->disk, (bio->bi_opf & REQ_SWAP) == REQ_SWAP); iocg_unlock(iocg, ioc_locked, &flags); return; @@ -2743,7 +2750,7 @@ static void ioc_rqos_merge(struct rq_qos *rqos, struct request *rq, if (likely(!list_empty(&iocg->active_list))) { iocg_incur_debt(iocg, abs_cost, &now); if (iocg_kick_delay(iocg, &now)) - blkcg_schedule_throttle(rqos->q->disk, + blkcg_schedule_throttle(rqos->disk, (bio->bi_opf & REQ_SWAP) == REQ_SWAP); } else { iocg_commit_bio(iocg, bio, abs_cost, cost); @@ -2814,7 +2821,7 @@ static void ioc_rqos_exit(struct rq_qos *rqos) { struct ioc *ioc = rqos_to_ioc(rqos); - blkcg_deactivate_policy(rqos->q, &blkcg_policy_iocost); + blkcg_deactivate_policy(rqos->disk, &blkcg_policy_iocost); spin_lock_irq(&ioc->lock); ioc->running = IOC_STOP; @@ -2825,7 +2832,7 @@ static void ioc_rqos_exit(struct rq_qos *rqos) kfree(ioc); } -static struct rq_qos_ops ioc_rqos_ops = { +static const struct rq_qos_ops ioc_rqos_ops = { .throttle = ioc_rqos_throttle, .merge = ioc_rqos_merge, .done_bio = ioc_rqos_done_bio, @@ -2836,9 +2843,7 @@ static struct rq_qos_ops ioc_rqos_ops = { static int blk_iocost_init(struct gendisk *disk) { - struct request_queue *q = disk->queue; struct ioc *ioc; - struct rq_qos *rqos; int i, cpu, ret; ioc = kzalloc(sizeof(*ioc), GFP_KERNEL); @@ -2861,11 +2866,6 @@ static int blk_iocost_init(struct gendisk *disk) local64_set(&ccs->rq_wait_ns, 0); } - rqos = &ioc->rqos; - rqos->id = RQ_QOS_COST; - rqos->ops = &ioc_rqos_ops; - rqos->q = q; - spin_lock_init(&ioc->lock); timer_setup(&ioc->timer, ioc_timer_fn, 0); INIT_LIST_HEAD(&ioc->active_iocgs); @@ -2889,17 +2889,17 @@ static int blk_iocost_init(struct gendisk *disk) * called before policy activation completion, can't assume that the * target bio has an iocg associated and need to test for NULL iocg. */ - ret = rq_qos_add(q, rqos); + ret = rq_qos_add(&ioc->rqos, disk, RQ_QOS_COST, &ioc_rqos_ops); if (ret) goto err_free_ioc; - ret = blkcg_activate_policy(q, &blkcg_policy_iocost); + ret = blkcg_activate_policy(disk, &blkcg_policy_iocost); if (ret) goto err_del_qos; return 0; err_del_qos: - rq_qos_del(q, rqos); + rq_qos_del(&ioc->rqos); err_free_ioc: free_percpu(ioc->pcpu_stat); kfree(ioc); @@ -2923,13 +2923,14 @@ static void ioc_cpd_free(struct blkcg_policy_data *cpd) kfree(container_of(cpd, struct ioc_cgrp, cpd)); } -static struct blkg_policy_data *ioc_pd_alloc(gfp_t gfp, struct request_queue *q, - struct blkcg *blkcg) +static struct blkg_policy_data *ioc_pd_alloc(struct gendisk *disk, + struct blkcg *blkcg, gfp_t gfp) { int levels = blkcg->css.cgroup->level + 1; struct ioc_gq *iocg; - iocg = kzalloc_node(struct_size(iocg, ancestors, levels), gfp, q->node); + iocg = kzalloc_node(struct_size(iocg, ancestors, levels), gfp, + disk->node_id); if (!iocg) return NULL; @@ -3129,6 +3130,7 @@ static u64 ioc_qos_prfill(struct seq_file *sf, struct blkg_policy_data *pd, if (!dname) return 0; + spin_lock_irq(&ioc->lock); seq_printf(sf, "%s enable=%d ctrl=%s rpct=%u.%02u rlat=%u wpct=%u.%02u wlat=%u min=%u.%02u max=%u.%02u\n", dname, ioc->enabled, ioc->user_qos_params ? "user" : "auto", ioc->params.qos[QOS_RPPM] / 10000, @@ -3141,6 +3143,7 @@ static u64 ioc_qos_prfill(struct seq_file *sf, struct blkg_policy_data *pd, ioc->params.qos[QOS_MIN] % 10000 / 100, ioc->params.qos[QOS_MAX] / 10000, ioc->params.qos[QOS_MAX] % 10000 / 100); + spin_unlock_irq(&ioc->lock); return 0; } @@ -3185,6 +3188,11 @@ static ssize_t ioc_qos_write(struct kernfs_open_file *of, char *input, return PTR_ERR(bdev); disk = bdev->bd_disk; + if (!queue_is_mq(disk->queue)) { + ret = -EOPNOTSUPP; + goto err; + } + ioc = q_to_ioc(disk->queue); if (!ioc) { ret = blk_iocost_init(disk); @@ -3212,7 +3220,8 @@ static ssize_t ioc_qos_write(struct kernfs_open_file *of, char *input, switch (match_token(p, qos_ctrl_tokens, args)) { case QOS_ENABLE: - match_u64(&args[0], &v); + if (match_u64(&args[0], &v)) + goto einval; enable = v; continue; case QOS_CTRL: @@ -3270,11 +3279,11 @@ static ssize_t ioc_qos_write(struct kernfs_open_file *of, char *input, blk_stat_enable_accounting(disk->queue); blk_queue_flag_set(QUEUE_FLAG_RQ_ALLOC_TIME, disk->queue); ioc->enabled = true; - wbt_disable_default(disk->queue); + wbt_disable_default(disk); } else { blk_queue_flag_clear(QUEUE_FLAG_RQ_ALLOC_TIME, disk->queue); ioc->enabled = false; - wbt_enable_default(disk->queue); + wbt_enable_default(disk); } if (user) { @@ -3314,12 +3323,14 @@ static u64 ioc_cost_model_prfill(struct seq_file *sf, if (!dname) return 0; + spin_lock_irq(&ioc->lock); seq_printf(sf, "%s ctrl=%s model=linear " "rbps=%llu rseqiops=%llu rrandiops=%llu " "wbps=%llu wseqiops=%llu wrandiops=%llu\n", dname, ioc->user_cost_model ? "user" : "auto", u[I_LCOEF_RBPS], u[I_LCOEF_RSEQIOPS], u[I_LCOEF_RRANDIOPS], u[I_LCOEF_WBPS], u[I_LCOEF_WSEQIOPS], u[I_LCOEF_WRANDIOPS]); + spin_unlock_irq(&ioc->lock); return 0; } @@ -3364,6 +3375,11 @@ static ssize_t ioc_cost_model_write(struct kernfs_open_file *of, char *input, return PTR_ERR(bdev); q = bdev_get_queue(bdev); + if (!queue_is_mq(q)) { + ret = -EOPNOTSUPP; + goto err; + } + ioc = q_to_ioc(q); if (!ioc) { ret = blk_iocost_init(bdev->bd_disk); diff --git a/block/blk-iolatency.c b/block/blk-iolatency.c index ecdc10741836..0dc910568b31 100644 --- a/block/blk-iolatency.c +++ b/block/blk-iolatency.c @@ -292,7 +292,7 @@ static void __blkcg_iolatency_throttle(struct rq_qos *rqos, unsigned use_delay = atomic_read(&lat_to_blkg(iolat)->use_delay); if (use_delay) - blkcg_schedule_throttle(rqos->q->disk, use_memdelay); + blkcg_schedule_throttle(rqos->disk, use_memdelay); /* * To avoid priority inversions we want to just take a slot if we are @@ -330,7 +330,7 @@ static void scale_cookie_change(struct blk_iolatency *blkiolat, struct child_latency_info *lat_info, bool up) { - unsigned long qd = blkiolat->rqos.q->nr_requests; + unsigned long qd = blkiolat->rqos.disk->queue->nr_requests; unsigned long scale = scale_amount(qd, up); unsigned long old = atomic_read(&lat_info->scale_cookie); unsigned long max_scale = qd << 1; @@ -372,7 +372,7 @@ static void scale_cookie_change(struct blk_iolatency *blkiolat, */ static void scale_change(struct iolatency_grp *iolat, bool up) { - unsigned long qd = iolat->blkiolat->rqos.q->nr_requests; + unsigned long qd = iolat->blkiolat->rqos.disk->queue->nr_requests; unsigned long scale = scale_amount(qd, up); unsigned long old = iolat->max_depth; @@ -646,11 +646,11 @@ static void blkcg_iolatency_exit(struct rq_qos *rqos) timer_shutdown_sync(&blkiolat->timer); flush_work(&blkiolat->enable_work); - blkcg_deactivate_policy(rqos->q, &blkcg_policy_iolatency); + blkcg_deactivate_policy(rqos->disk, &blkcg_policy_iolatency); kfree(blkiolat); } -static struct rq_qos_ops blkcg_iolatency_ops = { +static const struct rq_qos_ops blkcg_iolatency_ops = { .throttle = blkcg_iolatency_throttle, .done_bio = blkcg_iolatency_done_bio, .exit = blkcg_iolatency_exit, @@ -665,7 +665,7 @@ static void blkiolatency_timer_fn(struct timer_list *t) rcu_read_lock(); blkg_for_each_descendant_pre(blkg, pos_css, - blkiolat->rqos.q->root_blkg) { + blkiolat->rqos.disk->queue->root_blkg) { struct iolatency_grp *iolat; struct child_latency_info *lat_info; unsigned long flags; @@ -749,32 +749,26 @@ static void blkiolatency_enable_work_fn(struct work_struct *work) */ enabled = atomic_read(&blkiolat->enable_cnt); if (enabled != blkiolat->enabled) { - blk_mq_freeze_queue(blkiolat->rqos.q); + blk_mq_freeze_queue(blkiolat->rqos.disk->queue); blkiolat->enabled = enabled; - blk_mq_unfreeze_queue(blkiolat->rqos.q); + blk_mq_unfreeze_queue(blkiolat->rqos.disk->queue); } } int blk_iolatency_init(struct gendisk *disk) { - struct request_queue *q = disk->queue; struct blk_iolatency *blkiolat; - struct rq_qos *rqos; int ret; blkiolat = kzalloc(sizeof(*blkiolat), GFP_KERNEL); if (!blkiolat) return -ENOMEM; - rqos = &blkiolat->rqos; - rqos->id = RQ_QOS_LATENCY; - rqos->ops = &blkcg_iolatency_ops; - rqos->q = q; - - ret = rq_qos_add(q, rqos); + ret = rq_qos_add(&blkiolat->rqos, disk, RQ_QOS_LATENCY, + &blkcg_iolatency_ops); if (ret) goto err_free; - ret = blkcg_activate_policy(q, &blkcg_policy_iolatency); + ret = blkcg_activate_policy(disk, &blkcg_policy_iolatency); if (ret) goto err_qos_del; @@ -784,7 +778,7 @@ int blk_iolatency_init(struct gendisk *disk) return 0; err_qos_del: - rq_qos_del(q, rqos); + rq_qos_del(&blkiolat->rqos); err_free: kfree(blkiolat); return ret; @@ -952,13 +946,12 @@ static void iolatency_pd_stat(struct blkg_policy_data *pd, struct seq_file *s) iolat->max_depth, avg_lat, cur_win); } -static struct blkg_policy_data *iolatency_pd_alloc(gfp_t gfp, - struct request_queue *q, - struct blkcg *blkcg) +static struct blkg_policy_data *iolatency_pd_alloc(struct gendisk *disk, + struct blkcg *blkcg, gfp_t gfp) { struct iolatency_grp *iolat; - iolat = kzalloc_node(sizeof(*iolat), gfp, q->node); + iolat = kzalloc_node(sizeof(*iolat), gfp, disk->node_id); if (!iolat) return NULL; iolat->stats = __alloc_percpu_gfp(sizeof(struct latency_stat), diff --git a/block/blk-ioprio.c b/block/blk-ioprio.c index 8bb6b8eba4ce..055529b9b92b 100644 --- a/block/blk-ioprio.c +++ b/block/blk-ioprio.c @@ -116,7 +116,7 @@ static ssize_t ioprio_set_prio_policy(struct kernfs_open_file *of, char *buf, } static struct blkg_policy_data * -ioprio_alloc_pd(gfp_t gfp, struct request_queue *q, struct blkcg *blkcg) +ioprio_alloc_pd(struct gendisk *disk, struct blkcg *blkcg, gfp_t gfp) { struct ioprio_blkg *ioprio_blkg; @@ -204,12 +204,12 @@ void blkcg_set_ioprio(struct bio *bio) void blk_ioprio_exit(struct gendisk *disk) { - blkcg_deactivate_policy(disk->queue, &ioprio_policy); + blkcg_deactivate_policy(disk, &ioprio_policy); } int blk_ioprio_init(struct gendisk *disk) { - return blkcg_activate_policy(disk->queue, &ioprio_policy); + return blkcg_activate_policy(disk, &ioprio_policy); } static int __init ioprio_init(void) diff --git a/block/blk-map.c b/block/blk-map.c index f2135e6ee8f6..9ee4be4ba2f1 100644 --- a/block/blk-map.c +++ b/block/blk-map.c @@ -247,10 +247,8 @@ static struct bio *blk_rq_map_bio_alloc(struct request *rq, { struct bio *bio; - if (rq->cmd_flags & REQ_POLLED) { - blk_opf_t opf = rq->cmd_flags | REQ_ALLOC_CACHE; - - bio = bio_alloc_bioset(NULL, nr_vecs, opf, gfp_mask, + if (rq->cmd_flags & REQ_ALLOC_CACHE) { + bio = bio_alloc_bioset(NULL, nr_vecs, rq->cmd_flags, gfp_mask, &fs_bio_set); if (!bio) return NULL; diff --git a/block/blk-merge.c b/block/blk-merge.c index 64bf7d9dd8e8..1ac782fdc55c 100644 --- a/block/blk-merge.c +++ b/block/blk-merge.c @@ -758,6 +758,33 @@ void blk_rq_set_mixed_merge(struct request *rq) rq->rq_flags |= RQF_MIXED_MERGE; } +static inline blk_opf_t bio_failfast(const struct bio *bio) +{ + if (bio->bi_opf & REQ_RAHEAD) + return REQ_FAILFAST_MASK; + + return bio->bi_opf & REQ_FAILFAST_MASK; +} + +/* + * After we are marked as MIXED_MERGE, any new RA bio has to be updated + * as failfast, and request's failfast has to be updated in case of + * front merge. + */ +static inline void blk_update_mixed_merge(struct request *req, + struct bio *bio, bool front_merge) +{ + if (req->rq_flags & RQF_MIXED_MERGE) { + if (bio->bi_opf & REQ_RAHEAD) + bio->bi_opf |= REQ_FAILFAST_MASK; + + if (front_merge) { + req->cmd_flags &= ~REQ_FAILFAST_MASK; + req->cmd_flags |= bio->bi_opf & REQ_FAILFAST_MASK; + } + } +} + static void blk_account_io_merge_request(struct request *req) { if (blk_do_io_stat(req)) { @@ -955,7 +982,7 @@ enum bio_merge_status { static enum bio_merge_status bio_attempt_back_merge(struct request *req, struct bio *bio, unsigned int nr_segs) { - const blk_opf_t ff = bio->bi_opf & REQ_FAILFAST_MASK; + const blk_opf_t ff = bio_failfast(bio); if (!ll_back_merge_fn(req, bio, nr_segs)) return BIO_MERGE_FAILED; @@ -966,6 +993,8 @@ static enum bio_merge_status bio_attempt_back_merge(struct request *req, if ((req->cmd_flags & REQ_FAILFAST_MASK) != ff) blk_rq_set_mixed_merge(req); + blk_update_mixed_merge(req, bio, false); + req->biotail->bi_next = bio; req->biotail = bio; req->__data_len += bio->bi_iter.bi_size; @@ -979,7 +1008,7 @@ static enum bio_merge_status bio_attempt_back_merge(struct request *req, static enum bio_merge_status bio_attempt_front_merge(struct request *req, struct bio *bio, unsigned int nr_segs) { - const blk_opf_t ff = bio->bi_opf & REQ_FAILFAST_MASK; + const blk_opf_t ff = bio_failfast(bio); if (!ll_front_merge_fn(req, bio, nr_segs)) return BIO_MERGE_FAILED; @@ -990,6 +1019,8 @@ static enum bio_merge_status bio_attempt_front_merge(struct request *req, if ((req->cmd_flags & REQ_FAILFAST_MASK) != ff) blk_rq_set_mixed_merge(req); + blk_update_mixed_merge(req, bio, true); + bio->bi_next = req->bio; req->bio = bio; diff --git a/block/blk-mq-debugfs.c b/block/blk-mq-debugfs.c index bd942341b638..b01818f8e216 100644 --- a/block/blk-mq-debugfs.c +++ b/block/blk-mq-debugfs.c @@ -813,9 +813,9 @@ static const char *rq_qos_id_to_name(enum rq_qos_id id) void blk_mq_debugfs_unregister_rqos(struct rq_qos *rqos) { - lockdep_assert_held(&rqos->q->debugfs_mutex); + lockdep_assert_held(&rqos->disk->queue->debugfs_mutex); - if (!rqos->q->debugfs_dir) + if (!rqos->disk->queue->debugfs_dir) return; debugfs_remove_recursive(rqos->debugfs_dir); rqos->debugfs_dir = NULL; @@ -823,7 +823,7 @@ void blk_mq_debugfs_unregister_rqos(struct rq_qos *rqos) void blk_mq_debugfs_register_rqos(struct rq_qos *rqos) { - struct request_queue *q = rqos->q; + struct request_queue *q = rqos->disk->queue; const char *dir_name = rq_qos_id_to_name(rqos->id); lockdep_assert_held(&q->debugfs_mutex); @@ -835,9 +835,7 @@ void blk_mq_debugfs_register_rqos(struct rq_qos *rqos) q->rqos_debugfs_dir = debugfs_create_dir("rqos", q->debugfs_dir); - rqos->debugfs_dir = debugfs_create_dir(dir_name, - rqos->q->rqos_debugfs_dir); - + rqos->debugfs_dir = debugfs_create_dir(dir_name, q->rqos_debugfs_dir); debugfs_create_files(rqos->debugfs_dir, rqos, rqos->ops->debugfs_attrs); } diff --git a/block/blk-mq-sched.c b/block/blk-mq-sched.c index 23d1a90fec42..06b312c69114 100644 --- a/block/blk-mq-sched.c +++ b/block/blk-mq-sched.c @@ -19,8 +19,7 @@ #include "blk-wbt.h" /* - * Mark a hardware queue as needing a restart. For shared queues, maintain - * a count of how many hardware queues are marked for restart. + * Mark a hardware queue as needing a restart. */ void blk_mq_sched_mark_restart_hctx(struct blk_mq_hw_ctx *hctx) { @@ -82,7 +81,7 @@ dispatch: /* * Only SCSI implements .get_budget and .put_budget, and SCSI restarts * its queue by itself in its completion handler, so we don't need to - * restart queue if .get_budget() returns BLK_STS_NO_RESOURCE. + * restart queue if .get_budget() fails to get the budget. * * Returns -EAGAIN if hctx->dispatch was found non-empty and run_work has to * be run again. This is necessary to avoid starving flushes. @@ -210,7 +209,7 @@ static struct blk_mq_ctx *blk_mq_next_ctx(struct blk_mq_hw_ctx *hctx, /* * Only SCSI implements .get_budget and .put_budget, and SCSI restarts * its queue by itself in its completion handler, so we don't need to - * restart queue if .get_budget() returns BLK_STS_NO_RESOURCE. + * restart queue if .get_budget() fails to get the budget. * * Returns -EAGAIN if hctx->dispatch was found non-empty and run_work has to * be run again. This is necessary to avoid starving flushes. diff --git a/block/blk-mq-sysfs.c b/block/blk-mq-sysfs.c index 4515288fbe35..1b2b0d258e46 100644 --- a/block/blk-mq-sysfs.c +++ b/block/blk-mq-sysfs.c @@ -46,7 +46,6 @@ static void blk_mq_hw_sysfs_release(struct kobject *kobj) struct blk_mq_hw_ctx_sysfs_entry { struct attribute attr; ssize_t (*show)(struct blk_mq_hw_ctx *, char *); - ssize_t (*store)(struct blk_mq_hw_ctx *, const char *, size_t); }; static ssize_t blk_mq_hw_sysfs_show(struct kobject *kobj, @@ -70,28 +69,6 @@ static ssize_t blk_mq_hw_sysfs_show(struct kobject *kobj, return res; } -static ssize_t blk_mq_hw_sysfs_store(struct kobject *kobj, - struct attribute *attr, const char *page, - size_t length) -{ - struct blk_mq_hw_ctx_sysfs_entry *entry; - struct blk_mq_hw_ctx *hctx; - struct request_queue *q; - ssize_t res; - - entry = container_of(attr, struct blk_mq_hw_ctx_sysfs_entry, attr); - hctx = container_of(kobj, struct blk_mq_hw_ctx, kobj); - q = hctx->queue; - - if (!entry->store) - return -EIO; - - mutex_lock(&q->sysfs_lock); - res = entry->store(hctx, page, length); - mutex_unlock(&q->sysfs_lock); - return res; -} - static ssize_t blk_mq_hw_sysfs_nr_tags_show(struct blk_mq_hw_ctx *hctx, char *page) { @@ -150,18 +127,17 @@ ATTRIBUTE_GROUPS(default_hw_ctx); static const struct sysfs_ops blk_mq_hw_sysfs_ops = { .show = blk_mq_hw_sysfs_show, - .store = blk_mq_hw_sysfs_store, }; -static struct kobj_type blk_mq_ktype = { +static const struct kobj_type blk_mq_ktype = { .release = blk_mq_sysfs_release, }; -static struct kobj_type blk_mq_ctx_ktype = { +static const struct kobj_type blk_mq_ctx_ktype = { .release = blk_mq_ctx_sysfs_release, }; -static struct kobj_type blk_mq_hw_ktype = { +static const struct kobj_type blk_mq_hw_ktype = { .sysfs_ops = &blk_mq_hw_sysfs_ops, .default_groups = default_hw_ctx_groups, .release = blk_mq_hw_sysfs_release, diff --git a/block/blk-mq.c b/block/blk-mq.c index 9c8dc70020bc..d3494a796ba8 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -658,7 +658,8 @@ struct request *blk_mq_alloc_request_hctx(struct request_queue *q, * allocator for this for the rare use case of a command tied to * a specific queue. */ - if (WARN_ON_ONCE(!(flags & (BLK_MQ_REQ_NOWAIT | BLK_MQ_REQ_RESERVED)))) + if (WARN_ON_ONCE(!(flags & BLK_MQ_REQ_NOWAIT)) || + WARN_ON_ONCE(!(flags & BLK_MQ_REQ_RESERVED))) return ERR_PTR(-EINVAL); if (hctx_idx >= q->nr_hw_queues) @@ -1825,12 +1826,13 @@ static int blk_mq_dispatch_wake(wait_queue_entry_t *wait, unsigned mode, static bool blk_mq_mark_tag_wait(struct blk_mq_hw_ctx *hctx, struct request *rq) { - struct sbitmap_queue *sbq = &hctx->tags->bitmap_tags; + struct sbitmap_queue *sbq; struct wait_queue_head *wq; wait_queue_entry_t *wait; bool ret; - if (!(hctx->flags & BLK_MQ_F_TAG_QUEUE_SHARED)) { + if (!(hctx->flags & BLK_MQ_F_TAG_QUEUE_SHARED) && + !(blk_mq_is_shared_tags(hctx->flags))) { blk_mq_sched_mark_restart_hctx(hctx); /* @@ -1848,6 +1850,10 @@ static bool blk_mq_mark_tag_wait(struct blk_mq_hw_ctx *hctx, if (!list_empty_careful(&wait->entry)) return false; + if (blk_mq_tag_is_reserved(rq->mq_hctx->sched_tags, rq->internal_tag)) + sbq = &hctx->tags->breserved_tags; + else + sbq = &hctx->tags->bitmap_tags; wq = &bt_wait_ptr(sbq, hctx)->wait; spin_lock_irq(&wq->lock); @@ -1917,16 +1923,6 @@ static void blk_mq_update_dispatch_busy(struct blk_mq_hw_ctx *hctx, bool busy) static void blk_mq_handle_dev_resource(struct request *rq, struct list_head *list) { - struct request *next = - list_first_entry_or_null(list, struct request, queuelist); - - /* - * If an I/O scheduler has been configured and we got a driver tag for - * the next request already, free it. - */ - if (next) - blk_mq_put_driver_tag(next); - list_add(&rq->queuelist, list); __blk_mq_requeue_request(rq); } @@ -2002,6 +1998,23 @@ static void blk_mq_release_budgets(struct request_queue *q, } /* + * blk_mq_commit_rqs will notify driver using bd->last that there is no + * more requests. (See comment in struct blk_mq_ops for commit_rqs for + * details) + * Attention, we should explicitly call this in unusual cases: + * 1) did not queue everything initially scheduled to queue + * 2) the last attempt to queue a request failed + */ +static void blk_mq_commit_rqs(struct blk_mq_hw_ctx *hctx, int queued, + bool from_schedule) +{ + if (hctx->queue->mq_ops->commit_rqs && queued) { + trace_block_unplug(hctx->queue, queued, !from_schedule); + hctx->queue->mq_ops->commit_rqs(hctx); + } +} + +/* * Returns true if we did some work AND can potentially do more. */ bool blk_mq_dispatch_rq_list(struct blk_mq_hw_ctx *hctx, struct list_head *list, @@ -2009,8 +2022,8 @@ bool blk_mq_dispatch_rq_list(struct blk_mq_hw_ctx *hctx, struct list_head *list, { enum prep_dispatch prep; struct request_queue *q = hctx->queue; - struct request *rq, *nxt; - int errors, queued; + struct request *rq; + int queued; blk_status_t ret = BLK_STS_OK; LIST_HEAD(zone_list); bool needs_resource = false; @@ -2021,7 +2034,7 @@ bool blk_mq_dispatch_rq_list(struct blk_mq_hw_ctx *hctx, struct list_head *list, /* * Now process all the entries, sending them to the driver. */ - errors = queued = 0; + queued = 0; do { struct blk_mq_queue_data bd; @@ -2035,17 +2048,7 @@ bool blk_mq_dispatch_rq_list(struct blk_mq_hw_ctx *hctx, struct list_head *list, list_del_init(&rq->queuelist); bd.rq = rq; - - /* - * Flag last if we have no more requests, or if we have more - * but can't assign a driver tag to it. - */ - if (list_empty(list)) - bd.last = true; - else { - nxt = list_first_entry(list, struct request, queuelist); - bd.last = !blk_mq_get_driver_tag(nxt); - } + bd.last = list_empty(list); /* * once the request is queued to lld, no need to cover the @@ -2074,7 +2077,6 @@ bool blk_mq_dispatch_rq_list(struct blk_mq_hw_ctx *hctx, struct list_head *list, needs_resource = true; break; default: - errors++; blk_mq_end_request(rq, ret); } } while (!list_empty(list)); @@ -2085,9 +2087,9 @@ out: /* If we didn't flush the entire list, we could have told the driver * there was more coming, but that turned out to be a lie. */ - if ((!list_empty(list) || errors || needs_resource || - ret == BLK_STS_DEV_RESOURCE) && q->mq_ops->commit_rqs && queued) - q->mq_ops->commit_rqs(hctx); + if (!list_empty(list) || ret != BLK_STS_OK) + blk_mq_commit_rqs(hctx, queued, false); + /* * Any items that need requeuing? Stuff them into hctx->dispatch, * that is where we will continue on next queue run. @@ -2096,7 +2098,8 @@ out: bool needs_restart; /* For non-shared tags, the RESTART check will suffice */ bool no_tag = prep == PREP_DISPATCH_NO_TAG && - (hctx->flags & BLK_MQ_F_TAG_QUEUE_SHARED); + ((hctx->flags & BLK_MQ_F_TAG_QUEUE_SHARED) || + blk_mq_is_shared_tags(hctx->flags)); if (nr_budgets) blk_mq_release_budgets(q, list); @@ -2151,10 +2154,10 @@ out: blk_mq_update_dispatch_busy(hctx, true); return false; - } else - blk_mq_update_dispatch_busy(hctx, false); + } - return (queued + errors) != 0; + blk_mq_update_dispatch_busy(hctx, false); + return true; } /** @@ -2548,16 +2551,6 @@ void blk_mq_insert_requests(struct blk_mq_hw_ctx *hctx, struct blk_mq_ctx *ctx, spin_unlock(&ctx->lock); } -static void blk_mq_commit_rqs(struct blk_mq_hw_ctx *hctx, int *queued, - bool from_schedule) -{ - if (hctx->queue->mq_ops->commit_rqs) { - trace_block_unplug(hctx->queue, *queued, !from_schedule); - hctx->queue->mq_ops->commit_rqs(hctx); - } - *queued = 0; -} - static void blk_mq_bio_to_request(struct request *rq, struct bio *bio, unsigned int nr_segs) { @@ -2681,20 +2674,21 @@ static blk_status_t blk_mq_request_issue_directly(struct request *rq, bool last) return __blk_mq_try_issue_directly(rq->mq_hctx, rq, true, last); } -static void blk_mq_plug_issue_direct(struct blk_plug *plug, bool from_schedule) +static void blk_mq_plug_issue_direct(struct blk_plug *plug) { struct blk_mq_hw_ctx *hctx = NULL; struct request *rq; int queued = 0; - int errors = 0; + blk_status_t ret = BLK_STS_OK; while ((rq = rq_list_pop(&plug->mq_list))) { bool last = rq_list_empty(plug->mq_list); - blk_status_t ret; if (hctx != rq->mq_hctx) { - if (hctx) - blk_mq_commit_rqs(hctx, &queued, from_schedule); + if (hctx) { + blk_mq_commit_rqs(hctx, queued, false); + queued = 0; + } hctx = rq->mq_hctx; } @@ -2706,21 +2700,16 @@ static void blk_mq_plug_issue_direct(struct blk_plug *plug, bool from_schedule) case BLK_STS_RESOURCE: case BLK_STS_DEV_RESOURCE: blk_mq_request_bypass_insert(rq, false, true); - blk_mq_commit_rqs(hctx, &queued, from_schedule); - return; + goto out; default: blk_mq_end_request(rq, ret); - errors++; break; } } - /* - * If we didn't flush the entire list, we could have told the driver - * there was more coming, but that turned out to be a lie. - */ - if (errors) - blk_mq_commit_rqs(hctx, &queued, from_schedule); +out: + if (ret != BLK_STS_OK) + blk_mq_commit_rqs(hctx, queued, false); } static void __blk_mq_flush_plug_list(struct request_queue *q, @@ -2791,7 +2780,7 @@ void blk_mq_flush_plug_list(struct blk_plug *plug, bool from_schedule) } blk_mq_run_dispatch_ops(q, - blk_mq_plug_issue_direct(plug, false)); + blk_mq_plug_issue_direct(plug)); if (rq_list_empty(plug->mq_list)) return; } @@ -2805,36 +2794,32 @@ void blk_mq_try_issue_list_directly(struct blk_mq_hw_ctx *hctx, struct list_head *list) { int queued = 0; - int errors = 0; + blk_status_t ret = BLK_STS_OK; while (!list_empty(list)) { - blk_status_t ret; struct request *rq = list_first_entry(list, struct request, queuelist); list_del_init(&rq->queuelist); ret = blk_mq_request_issue_directly(rq, list_empty(list)); - if (ret != BLK_STS_OK) { - errors++; - if (ret == BLK_STS_RESOURCE || - ret == BLK_STS_DEV_RESOURCE) { - blk_mq_request_bypass_insert(rq, false, - list_empty(list)); - break; - } - blk_mq_end_request(rq, ret); - } else + switch (ret) { + case BLK_STS_OK: queued++; + break; + case BLK_STS_RESOURCE: + case BLK_STS_DEV_RESOURCE: + blk_mq_request_bypass_insert(rq, false, + list_empty(list)); + goto out; + default: + blk_mq_end_request(rq, ret); + break; + } } - /* - * If we didn't flush the entire list, we could have told - * the driver there was more coming, but that turned out to - * be a lie. - */ - if ((!list_empty(list) || errors) && - hctx->queue->mq_ops->commit_rqs && queued) - hctx->queue->mq_ops->commit_rqs(hctx); +out: + if (ret != BLK_STS_OK) + blk_mq_commit_rqs(hctx, queued, false); } static bool blk_mq_attempt_bio_merge(struct request_queue *q, @@ -2894,15 +2879,16 @@ static inline struct request *blk_mq_get_cached_request(struct request_queue *q, if (!plug) return NULL; - rq = rq_list_peek(&plug->cached_rq); - if (!rq || rq->q != q) - return NULL; if (blk_mq_attempt_bio_merge(q, *bio, nsegs)) { *bio = NULL; return NULL; } + rq = rq_list_peek(&plug->cached_rq); + if (!rq || rq->q != q) + return NULL; + type = blk_mq_get_hctx_type((*bio)->bi_opf); hctx_type = rq->mq_hctx->type; if (type != hctx_type && diff --git a/block/blk-rq-qos.c b/block/blk-rq-qos.c index 88f0fe7dcf54..d8cc820a365e 100644 --- a/block/blk-rq-qos.c +++ b/block/blk-rq-qos.c @@ -294,3 +294,70 @@ void rq_qos_exit(struct request_queue *q) rqos->ops->exit(rqos); } } + +int rq_qos_add(struct rq_qos *rqos, struct gendisk *disk, enum rq_qos_id id, + const struct rq_qos_ops *ops) +{ + struct request_queue *q = disk->queue; + + rqos->disk = disk; + rqos->id = id; + rqos->ops = ops; + + /* + * No IO can be in-flight when adding rqos, so freeze queue, which + * is fine since we only support rq_qos for blk-mq queue. + * + * Reuse ->queue_lock for protecting against other concurrent + * rq_qos adding/deleting + */ + blk_mq_freeze_queue(q); + + spin_lock_irq(&q->queue_lock); + if (rq_qos_id(q, rqos->id)) + goto ebusy; + rqos->next = q->rq_qos; + q->rq_qos = rqos; + spin_unlock_irq(&q->queue_lock); + + blk_mq_unfreeze_queue(q); + + if (rqos->ops->debugfs_attrs) { + mutex_lock(&q->debugfs_mutex); + blk_mq_debugfs_register_rqos(rqos); + mutex_unlock(&q->debugfs_mutex); + } + + return 0; +ebusy: + spin_unlock_irq(&q->queue_lock); + blk_mq_unfreeze_queue(q); + return -EBUSY; +} + +void rq_qos_del(struct rq_qos *rqos) +{ + struct request_queue *q = rqos->disk->queue; + struct rq_qos **cur; + + /* + * See comment in rq_qos_add() about freezing queue & using + * ->queue_lock. + */ + blk_mq_freeze_queue(q); + + spin_lock_irq(&q->queue_lock); + for (cur = &q->rq_qos; *cur; cur = &(*cur)->next) { + if (*cur == rqos) { + *cur = rqos->next; + break; + } + } + spin_unlock_irq(&q->queue_lock); + + blk_mq_unfreeze_queue(q); + + mutex_lock(&q->debugfs_mutex); + blk_mq_debugfs_unregister_rqos(rqos); + mutex_unlock(&q->debugfs_mutex); +} diff --git a/block/blk-rq-qos.h b/block/blk-rq-qos.h index 1ef1f7d4bc3c..b02a1a3d33a8 100644 --- a/block/blk-rq-qos.h +++ b/block/blk-rq-qos.h @@ -25,8 +25,8 @@ struct rq_wait { }; struct rq_qos { - struct rq_qos_ops *ops; - struct request_queue *q; + const struct rq_qos_ops *ops; + struct gendisk *disk; enum rq_qos_id id; struct rq_qos *next; #ifdef CONFIG_BLK_DEBUG_FS @@ -85,65 +85,9 @@ static inline void rq_wait_init(struct rq_wait *rq_wait) init_waitqueue_head(&rq_wait->wait); } -static inline int rq_qos_add(struct request_queue *q, struct rq_qos *rqos) -{ - /* - * No IO can be in-flight when adding rqos, so freeze queue, which - * is fine since we only support rq_qos for blk-mq queue. - * - * Reuse ->queue_lock for protecting against other concurrent - * rq_qos adding/deleting - */ - blk_mq_freeze_queue(q); - - spin_lock_irq(&q->queue_lock); - if (rq_qos_id(q, rqos->id)) - goto ebusy; - rqos->next = q->rq_qos; - q->rq_qos = rqos; - spin_unlock_irq(&q->queue_lock); - - blk_mq_unfreeze_queue(q); - - if (rqos->ops->debugfs_attrs) { - mutex_lock(&q->debugfs_mutex); - blk_mq_debugfs_register_rqos(rqos); - mutex_unlock(&q->debugfs_mutex); - } - - return 0; -ebusy: - spin_unlock_irq(&q->queue_lock); - blk_mq_unfreeze_queue(q); - return -EBUSY; - -} - -static inline void rq_qos_del(struct request_queue *q, struct rq_qos *rqos) -{ - struct rq_qos **cur; - - /* - * See comment in rq_qos_add() about freezing queue & using - * ->queue_lock. - */ - blk_mq_freeze_queue(q); - - spin_lock_irq(&q->queue_lock); - for (cur = &q->rq_qos; *cur; cur = &(*cur)->next) { - if (*cur == rqos) { - *cur = rqos->next; - break; - } - } - spin_unlock_irq(&q->queue_lock); - - blk_mq_unfreeze_queue(q); - - mutex_lock(&q->debugfs_mutex); - blk_mq_debugfs_unregister_rqos(rqos); - mutex_unlock(&q->debugfs_mutex); -} +int rq_qos_add(struct rq_qos *rqos, struct gendisk *disk, enum rq_qos_id id, + const struct rq_qos_ops *ops); +void rq_qos_del(struct rq_qos *rqos); typedef bool (acquire_inflight_cb_t)(struct rq_wait *rqw, void *private_data); typedef void (cleanup_cb_t)(struct rq_wait *rqw, void *private_data); diff --git a/block/blk-settings.c b/block/blk-settings.c index 0477c4d527fe..896b4654ab00 100644 --- a/block/blk-settings.c +++ b/block/blk-settings.c @@ -16,6 +16,7 @@ #include <linux/dma-mapping.h> #include "blk.h" +#include "blk-rq-qos.h" #include "blk-wbt.h" void blk_queue_rq_timeout(struct request_queue *q, unsigned int timeout) @@ -40,7 +41,7 @@ void blk_set_default_limits(struct queue_limits *lim) lim->virt_boundary_mask = 0; lim->max_segment_size = BLK_MAX_SEGMENT_SIZE; lim->max_sectors = lim->max_hw_sectors = BLK_SAFE_MAX_SECTORS; - lim->max_dev_sectors = 0; + lim->max_user_sectors = lim->max_dev_sectors = 0; lim->chunk_sectors = 0; lim->max_write_zeroes_sectors = 0; lim->max_zone_append_sectors = 0; @@ -135,7 +136,12 @@ void blk_queue_max_hw_sectors(struct request_queue *q, unsigned int max_hw_secto limits->max_hw_sectors = max_hw_sectors; max_sectors = min_not_zero(max_hw_sectors, limits->max_dev_sectors); - max_sectors = min_t(unsigned int, max_sectors, BLK_DEF_MAX_SECTORS); + + if (limits->max_user_sectors) + max_sectors = min(max_sectors, limits->max_user_sectors); + else + max_sectors = min(max_sectors, BLK_DEF_MAX_SECTORS); + max_sectors = round_down(max_sectors, limits->logical_block_size >> SECTOR_SHIFT); limits->max_sectors = max_sectors; diff --git a/block/blk-stat.c b/block/blk-stat.c index 2ea01b5c1aca..c6ca16abf911 100644 --- a/block/blk-stat.c +++ b/block/blk-stat.c @@ -58,7 +58,8 @@ void blk_stat_add(struct request *rq, u64 now) value = (now >= rq->io_start_time_ns) ? now - rq->io_start_time_ns : 0; - blk_throtl_stat_add(rq, value); + if (req_op(rq) == REQ_OP_READ || req_op(rq) == REQ_OP_WRITE) + blk_throtl_stat_add(rq, value); rcu_read_lock(); cpu = get_cpu(); diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c index 93d9e9c9a6ea..f1fce1c7fa44 100644 --- a/block/blk-sysfs.c +++ b/block/blk-sysfs.c @@ -16,6 +16,7 @@ #include "blk-mq.h" #include "blk-mq-debugfs.h" #include "blk-mq-sched.h" +#include "blk-rq-qos.h" #include "blk-wbt.h" #include "blk-cgroup.h" #include "blk-throttle.h" @@ -239,19 +240,28 @@ static ssize_t queue_zone_append_max_show(struct request_queue *q, char *page) static ssize_t queue_max_sectors_store(struct request_queue *q, const char *page, size_t count) { - unsigned long max_sectors_kb, + unsigned long var; + unsigned int max_sectors_kb, max_hw_sectors_kb = queue_max_hw_sectors(q) >> 1, page_kb = 1 << (PAGE_SHIFT - 10); - ssize_t ret = queue_var_store(&max_sectors_kb, page, count); + ssize_t ret = queue_var_store(&var, page, count); if (ret < 0) return ret; - max_hw_sectors_kb = min_not_zero(max_hw_sectors_kb, (unsigned long) + max_sectors_kb = (unsigned int)var; + max_hw_sectors_kb = min_not_zero(max_hw_sectors_kb, q->limits.max_dev_sectors >> 1); - - if (max_sectors_kb > max_hw_sectors_kb || max_sectors_kb < page_kb) - return -EINVAL; + if (max_sectors_kb == 0) { + q->limits.max_user_sectors = 0; + max_sectors_kb = min(max_hw_sectors_kb, + BLK_DEF_MAX_SECTORS >> 1); + } else { + if (max_sectors_kb > max_hw_sectors_kb || + max_sectors_kb < page_kb) + return -EINVAL; + q->limits.max_user_sectors = max_sectors_kb << 1; + } spin_lock_irq(&q->queue_lock); q->limits.max_sectors = max_sectors_kb << 1; @@ -491,7 +501,7 @@ static ssize_t queue_wb_lat_store(struct request_queue *q, const char *page, rqos = wbt_rq_qos(q); if (!rqos) { - ret = wbt_init(q); + ret = wbt_init(q->disk); if (ret) return ret; } @@ -755,7 +765,7 @@ static void blk_queue_release(struct kobject *kobj) /* nothing to do here, all data is associated with the parent gendisk */ } -static struct kobj_type blk_queue_ktype = { +static const struct kobj_type blk_queue_ktype = { .default_groups = blk_queue_attr_groups, .sysfs_ops = &queue_sysfs_ops, .release = blk_queue_release, @@ -817,7 +827,7 @@ int blk_register_queue(struct gendisk *disk) goto out_elv_unregister; blk_queue_flag_set(QUEUE_FLAG_REGISTERED, q); - wbt_enable_default(q); + wbt_enable_default(disk); blk_throtl_register(disk); /* Now everything is ready and send out KOBJ_ADD uevent */ diff --git a/block/blk-throttle.c b/block/blk-throttle.c index 6fb5a2f9e1ee..47e9d8be68f3 100644 --- a/block/blk-throttle.c +++ b/block/blk-throttle.c @@ -335,14 +335,13 @@ static void throtl_service_queue_init(struct throtl_service_queue *sq) timer_setup(&sq->pending_timer, throtl_pending_timer_fn, 0); } -static struct blkg_policy_data *throtl_pd_alloc(gfp_t gfp, - struct request_queue *q, - struct blkcg *blkcg) +static struct blkg_policy_data *throtl_pd_alloc(struct gendisk *disk, + struct blkcg *blkcg, gfp_t gfp) { struct throtl_grp *tg; int rw; - tg = kzalloc_node(sizeof(*tg), gfp, q->node); + tg = kzalloc_node(sizeof(*tg), gfp, disk->node_id); if (!tg) return NULL; @@ -2395,7 +2394,7 @@ int blk_throtl_init(struct gendisk *disk) td->low_downgrade_time = jiffies; /* activate policy */ - ret = blkcg_activate_policy(q, &blkcg_policy_throtl); + ret = blkcg_activate_policy(disk, &blkcg_policy_throtl); if (ret) { free_percpu(td->latency_buckets[READ]); free_percpu(td->latency_buckets[WRITE]); @@ -2411,7 +2410,7 @@ void blk_throtl_exit(struct gendisk *disk) BUG_ON(!q->td); del_timer_sync(&q->td->service_queue.pending_timer); throtl_shutdown_wq(q); - blkcg_deactivate_policy(q, &blkcg_policy_throtl); + blkcg_deactivate_policy(disk, &blkcg_policy_throtl); free_percpu(q->td->latency_buckets[READ]); free_percpu(q->td->latency_buckets[WRITE]); kfree(q->td); diff --git a/block/blk-wbt.c b/block/blk-wbt.c index 68a774d7a7c9..e49a48684532 100644 --- a/block/blk-wbt.c +++ b/block/blk-wbt.c @@ -25,6 +25,7 @@ #include <linux/backing-dev.h> #include <linux/swap.h> +#include "blk-stat.h" #include "blk-wbt.h" #include "blk-rq-qos.h" #include "elevator.h" @@ -32,6 +33,72 @@ #define CREATE_TRACE_POINTS #include <trace/events/wbt.h> +enum wbt_flags { + WBT_TRACKED = 1, /* write, tracked for throttling */ + WBT_READ = 2, /* read */ + WBT_KSWAPD = 4, /* write, from kswapd */ + WBT_DISCARD = 8, /* discard */ + + WBT_NR_BITS = 4, /* number of bits */ +}; + +enum { + WBT_RWQ_BG = 0, + WBT_RWQ_KSWAPD, + WBT_RWQ_DISCARD, + WBT_NUM_RWQ, +}; + +/* + * If current state is WBT_STATE_ON/OFF_DEFAULT, it can be covered to any other + * state, if current state is WBT_STATE_ON/OFF_MANUAL, it can only be covered + * to WBT_STATE_OFF/ON_MANUAL. + */ +enum { + WBT_STATE_ON_DEFAULT = 1, /* on by default */ + WBT_STATE_ON_MANUAL = 2, /* on manually by sysfs */ + WBT_STATE_OFF_DEFAULT = 3, /* off by default */ + WBT_STATE_OFF_MANUAL = 4, /* off manually by sysfs */ +}; + +struct rq_wb { + /* + * Settings that govern how we throttle + */ + unsigned int wb_background; /* background writeback */ + unsigned int wb_normal; /* normal writeback */ + + short enable_state; /* WBT_STATE_* */ + + /* + * Number of consecutive periods where we don't have enough + * information to make a firm scale up/down decision. + */ + unsigned int unknown_cnt; + + u64 win_nsec; /* default window size */ + u64 cur_win_nsec; /* current window size */ + + struct blk_stat_callback *cb; + + u64 sync_issue; + void *sync_cookie; + + unsigned int wc; + + unsigned long last_issue; /* last non-throttled issue */ + unsigned long last_comp; /* last non-throttled comp */ + unsigned long min_lat_nsec; + struct rq_qos rqos; + struct rq_wait rq_wait[WBT_NUM_RWQ]; + struct rq_depth rq_depth; +}; + +static inline struct rq_wb *RQWB(struct rq_qos *rqos) +{ + return container_of(rqos, struct rq_wb, rqos); +} + static inline void wbt_clear_state(struct request *rq) { rq->wbt_flags = 0; @@ -98,7 +165,7 @@ static void wb_timestamp(struct rq_wb *rwb, unsigned long *var) */ static bool wb_recent_wait(struct rq_wb *rwb) { - struct bdi_writeback *wb = &rwb->rqos.q->disk->bdi->wb; + struct bdi_writeback *wb = &rwb->rqos.disk->bdi->wb; return time_before(jiffies, wb->dirty_sleep + HZ); } @@ -226,6 +293,16 @@ static u64 rwb_sync_issue_lat(struct rq_wb *rwb) return now - issue; } +static inline unsigned int wbt_inflight(struct rq_wb *rwb) +{ + unsigned int i, ret = 0; + + for (i = 0; i < WBT_NUM_RWQ; i++) + ret += atomic_read(&rwb->rq_wait[i].inflight); + + return ret; +} + enum { LAT_OK = 1, LAT_UNKNOWN, @@ -235,7 +312,7 @@ enum { static int latency_exceeded(struct rq_wb *rwb, struct blk_rq_stat *stat) { - struct backing_dev_info *bdi = rwb->rqos.q->disk->bdi; + struct backing_dev_info *bdi = rwb->rqos.disk->bdi; struct rq_depth *rqd = &rwb->rq_depth; u64 thislat; @@ -288,7 +365,7 @@ static int latency_exceeded(struct rq_wb *rwb, struct blk_rq_stat *stat) static void rwb_trace_step(struct rq_wb *rwb, const char *msg) { - struct backing_dev_info *bdi = rwb->rqos.q->disk->bdi; + struct backing_dev_info *bdi = rwb->rqos.disk->bdi; struct rq_depth *rqd = &rwb->rq_depth; trace_wbt_step(bdi, msg, rqd->scale_step, rwb->cur_win_nsec, @@ -358,13 +435,12 @@ static void wb_timer_fn(struct blk_stat_callback *cb) unsigned int inflight = wbt_inflight(rwb); int status; - if (!rwb->rqos.q->disk) + if (!rwb->rqos.disk) return; status = latency_exceeded(rwb, cb->stat); - trace_wbt_timer(rwb->rqos.q->disk->bdi, status, rqd->scale_step, - inflight); + trace_wbt_timer(rwb->rqos.disk->bdi, status, rqd->scale_step, inflight); /* * If we exceeded the latency target, step down. If we did not, @@ -650,8 +726,9 @@ void wbt_set_write_cache(struct request_queue *q, bool write_cache_on) /* * Enable wbt if defaults are configured that way */ -void wbt_enable_default(struct request_queue *q) +void wbt_enable_default(struct gendisk *disk) { + struct request_queue *q = disk->queue; struct rq_qos *rqos; bool disable_flag = q->elevator && test_bit(ELEVATOR_FLAG_DISABLE_WBT, &q->elevator->flags); @@ -670,7 +747,7 @@ void wbt_enable_default(struct request_queue *q) return; if (queue_is_mq(q) && !disable_flag) - wbt_init(q); + wbt_init(disk); } EXPORT_SYMBOL_GPL(wbt_enable_default); @@ -701,16 +778,15 @@ static int wbt_data_dir(const struct request *rq) static void wbt_queue_depth_changed(struct rq_qos *rqos) { - RQWB(rqos)->rq_depth.queue_depth = blk_queue_depth(rqos->q); + RQWB(rqos)->rq_depth.queue_depth = blk_queue_depth(rqos->disk->queue); wbt_update_limits(RQWB(rqos)); } static void wbt_exit(struct rq_qos *rqos) { struct rq_wb *rwb = RQWB(rqos); - struct request_queue *q = rqos->q; - blk_stat_remove_callback(q, rwb->cb); + blk_stat_remove_callback(rqos->disk->queue, rwb->cb); blk_stat_free_callback(rwb->cb); kfree(rwb); } @@ -718,9 +794,9 @@ static void wbt_exit(struct rq_qos *rqos) /* * Disable wbt, if enabled by default. */ -void wbt_disable_default(struct request_queue *q) +void wbt_disable_default(struct gendisk *disk) { - struct rq_qos *rqos = wbt_rq_qos(q); + struct rq_qos *rqos = wbt_rq_qos(disk->queue); struct rq_wb *rwb; if (!rqos) return; @@ -820,7 +896,7 @@ static const struct blk_mq_debugfs_attr wbt_debugfs_attrs[] = { }; #endif -static struct rq_qos_ops wbt_rqos_ops = { +static const struct rq_qos_ops wbt_rqos_ops = { .throttle = wbt_wait, .issue = wbt_issue, .track = wbt_track, @@ -834,8 +910,9 @@ static struct rq_qos_ops wbt_rqos_ops = { #endif }; -int wbt_init(struct request_queue *q) +int wbt_init(struct gendisk *disk) { + struct request_queue *q = disk->queue; struct rq_wb *rwb; int i; int ret; @@ -853,22 +930,19 @@ int wbt_init(struct request_queue *q) for (i = 0; i < WBT_NUM_RWQ; i++) rq_wait_init(&rwb->rq_wait[i]); - rwb->rqos.id = RQ_QOS_WBT; - rwb->rqos.ops = &wbt_rqos_ops; - rwb->rqos.q = q; rwb->last_comp = rwb->last_issue = jiffies; rwb->win_nsec = RWB_WINDOW_NSEC; rwb->enable_state = WBT_STATE_ON_DEFAULT; rwb->wc = test_bit(QUEUE_FLAG_WC, &q->queue_flags); rwb->rq_depth.default_depth = RWB_DEF_DEPTH; rwb->min_lat_nsec = wbt_default_latency_nsec(q); - - wbt_queue_depth_changed(&rwb->rqos); + rwb->rq_depth.queue_depth = blk_queue_depth(q); + wbt_update_limits(rwb); /* * Assign rwb and add the stats callback. */ - ret = rq_qos_add(q, &rwb->rqos); + ret = rq_qos_add(&rwb->rqos, disk, RQ_QOS_WBT, &wbt_rqos_ops); if (ret) goto err_free; diff --git a/block/blk-wbt.h b/block/blk-wbt.h index e3ea6e7e2900..ba6cca5849a6 100644 --- a/block/blk-wbt.h +++ b/block/blk-wbt.h @@ -2,97 +2,11 @@ #ifndef WB_THROTTLE_H #define WB_THROTTLE_H -#include <linux/kernel.h> -#include <linux/atomic.h> -#include <linux/wait.h> -#include <linux/timer.h> -#include <linux/ktime.h> - -#include "blk-stat.h" -#include "blk-rq-qos.h" - -enum wbt_flags { - WBT_TRACKED = 1, /* write, tracked for throttling */ - WBT_READ = 2, /* read */ - WBT_KSWAPD = 4, /* write, from kswapd */ - WBT_DISCARD = 8, /* discard */ - - WBT_NR_BITS = 4, /* number of bits */ -}; - -enum { - WBT_RWQ_BG = 0, - WBT_RWQ_KSWAPD, - WBT_RWQ_DISCARD, - WBT_NUM_RWQ, -}; - -/* - * If current state is WBT_STATE_ON/OFF_DEFAULT, it can be covered to any other - * state, if current state is WBT_STATE_ON/OFF_MANUAL, it can only be covered - * to WBT_STATE_OFF/ON_MANUAL. - */ -enum { - WBT_STATE_ON_DEFAULT = 1, /* on by default */ - WBT_STATE_ON_MANUAL = 2, /* on manually by sysfs */ - WBT_STATE_OFF_DEFAULT = 3, /* off by default */ - WBT_STATE_OFF_MANUAL = 4, /* off manually by sysfs */ -}; - -struct rq_wb { - /* - * Settings that govern how we throttle - */ - unsigned int wb_background; /* background writeback */ - unsigned int wb_normal; /* normal writeback */ - - short enable_state; /* WBT_STATE_* */ - - /* - * Number of consecutive periods where we don't have enough - * information to make a firm scale up/down decision. - */ - unsigned int unknown_cnt; - - u64 win_nsec; /* default window size */ - u64 cur_win_nsec; /* current window size */ - - struct blk_stat_callback *cb; - - u64 sync_issue; - void *sync_cookie; - - unsigned int wc; - - unsigned long last_issue; /* last non-throttled issue */ - unsigned long last_comp; /* last non-throttled comp */ - unsigned long min_lat_nsec; - struct rq_qos rqos; - struct rq_wait rq_wait[WBT_NUM_RWQ]; - struct rq_depth rq_depth; -}; - -static inline struct rq_wb *RQWB(struct rq_qos *rqos) -{ - return container_of(rqos, struct rq_wb, rqos); -} - -static inline unsigned int wbt_inflight(struct rq_wb *rwb) -{ - unsigned int i, ret = 0; - - for (i = 0; i < WBT_NUM_RWQ; i++) - ret += atomic_read(&rwb->rq_wait[i].inflight); - - return ret; -} - - #ifdef CONFIG_BLK_WBT -int wbt_init(struct request_queue *); -void wbt_disable_default(struct request_queue *); -void wbt_enable_default(struct request_queue *); +int wbt_init(struct gendisk *disk); +void wbt_disable_default(struct gendisk *disk); +void wbt_enable_default(struct gendisk *disk); u64 wbt_get_min_lat(struct request_queue *q); void wbt_set_min_lat(struct request_queue *q, u64 val); @@ -104,14 +18,14 @@ u64 wbt_default_latency_nsec(struct request_queue *); #else -static inline int wbt_init(struct request_queue *q) +static inline int wbt_init(struct gendisk *disk) { return -EINVAL; } -static inline void wbt_disable_default(struct request_queue *q) +static inline void wbt_disable_default(struct gendisk *disk) { } -static inline void wbt_enable_default(struct request_queue *q) +static inline void wbt_enable_default(struct gendisk *disk) { } static inline void wbt_set_write_cache(struct request_queue *q, bool wc) diff --git a/block/blk-zoned.c b/block/blk-zoned.c index db829401d8d0..614b575be899 100644 --- a/block/blk-zoned.c +++ b/block/blk-zoned.c @@ -277,10 +277,10 @@ int blkdev_zone_mgmt(struct block_device *bdev, enum req_op op, return -EINVAL; /* Check alignment (handle eventual smaller last zone) */ - if (sector & (zone_sectors - 1)) + if (!bdev_is_zone_start(bdev, sector)) return -EINVAL; - if ((nr_sectors & (zone_sectors - 1)) && end_sector != capacity) + if (!bdev_is_zone_start(bdev, nr_sectors) && end_sector != capacity) return -EINVAL; /* diff --git a/block/elevator.c b/block/elevator.c index adee58e48e2d..24909069f872 100644 --- a/block/elevator.c +++ b/block/elevator.c @@ -126,7 +126,7 @@ static struct elevator_type *elevator_find_get(struct request_queue *q, return e; } -static struct kobj_type elv_ktype; +static const struct kobj_type elv_ktype; struct elevator_queue *elevator_alloc(struct request_queue *q, struct elevator_type *e) @@ -455,7 +455,7 @@ static const struct sysfs_ops elv_sysfs_ops = { .store = elv_attr_store, }; -static struct kobj_type elv_ktype = { +static const struct kobj_type elv_ktype = { .sysfs_ops = &elv_sysfs_ops, .release = elevator_release, }; diff --git a/block/fops.c b/block/fops.c index 50d245e8c913..d2e6be4e3d1c 100644 --- a/block/fops.c +++ b/block/fops.c @@ -221,6 +221,24 @@ static ssize_t __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, bio_endio(bio); break; } + if (iocb->ki_flags & IOCB_NOWAIT) { + /* + * This is nonblocking IO, and we need to allocate + * another bio if we have data left to map. As we + * cannot guarantee that one of the sub bios will not + * fail getting issued FOR NOWAIT and as error results + * are coalesced across all of them, be safe and ask for + * a retry of this from blocking context. + */ + if (unlikely(iov_iter_count(iter))) { + bio_release_pages(bio, false); + bio_clear_flag(bio, BIO_REFFED); + bio_put(bio); + blk_finish_plug(&plug); + return -EAGAIN; + } + bio->bi_opf |= REQ_NOWAIT; + } if (is_read) { if (dio->flags & DIO_SHOULD_DIRTY) @@ -228,9 +246,6 @@ static ssize_t __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, } else { task_io_account_write(bio->bi_iter.bi_size); } - if (iocb->ki_flags & IOCB_NOWAIT) - bio->bi_opf |= REQ_NOWAIT; - dio->size += bio->bi_iter.bi_size; pos += bio->bi_iter.bi_size; diff --git a/block/genhd.c b/block/genhd.c index 23cf83b3331c..093ef292e98f 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -1016,9 +1016,8 @@ ssize_t part_inflight_show(struct device *dev, struct device_attribute *attr, static ssize_t disk_capability_show(struct device *dev, struct device_attribute *attr, char *buf) { - struct gendisk *disk = dev_to_disk(dev); - - return sprintf(buf, "%x\n", disk->flags); + dev_warn_once(dev, "the capability attribute has been deprecated.\n"); + return sprintf(buf, "0\n"); } static ssize_t disk_alignment_offset_show(struct device *dev, diff --git a/drivers/block/brd.c b/drivers/block/brd.c index 20acc4a1fd6d..a8a77a1efe1e 100644 --- a/drivers/block/brd.c +++ b/drivers/block/brd.c @@ -78,32 +78,25 @@ static struct page *brd_lookup_page(struct brd_device *brd, sector_t sector) } /* - * Look up and return a brd's page for a given sector. - * If one does not exist, allocate an empty page, and insert that. Then - * return it. + * Insert a new page for a given sector, if one does not already exist. */ -static struct page *brd_insert_page(struct brd_device *brd, sector_t sector) +static int brd_insert_page(struct brd_device *brd, sector_t sector, gfp_t gfp) { pgoff_t idx; struct page *page; - gfp_t gfp_flags; + int ret = 0; page = brd_lookup_page(brd, sector); if (page) - return page; + return 0; - /* - * Must use NOIO because we don't want to recurse back into the - * block or filesystem layers from page reclaim. - */ - gfp_flags = GFP_NOIO | __GFP_ZERO | __GFP_HIGHMEM; - page = alloc_page(gfp_flags); + page = alloc_page(gfp | __GFP_ZERO | __GFP_HIGHMEM); if (!page) - return NULL; + return -ENOMEM; - if (radix_tree_preload(GFP_NOIO)) { + if (radix_tree_maybe_preload(gfp)) { __free_page(page); - return NULL; + return -ENOMEM; } spin_lock(&brd->brd_lock); @@ -112,16 +105,17 @@ static struct page *brd_insert_page(struct brd_device *brd, sector_t sector) if (radix_tree_insert(&brd->brd_pages, idx, page)) { __free_page(page); page = radix_tree_lookup(&brd->brd_pages, idx); - BUG_ON(!page); - BUG_ON(page->index != idx); + if (!page) + ret = -ENOMEM; + else if (page->index != idx) + ret = -EIO; } else { brd->brd_nr_pages++; } spin_unlock(&brd->brd_lock); radix_tree_preload_end(); - - return page; + return ret; } /* @@ -170,20 +164,22 @@ static void brd_free_pages(struct brd_device *brd) /* * copy_to_brd_setup must be called before copy_to_brd. It may sleep. */ -static int copy_to_brd_setup(struct brd_device *brd, sector_t sector, size_t n) +static int copy_to_brd_setup(struct brd_device *brd, sector_t sector, size_t n, + gfp_t gfp) { unsigned int offset = (sector & (PAGE_SECTORS-1)) << SECTOR_SHIFT; size_t copy; + int ret; copy = min_t(size_t, n, PAGE_SIZE - offset); - if (!brd_insert_page(brd, sector)) - return -ENOSPC; + ret = brd_insert_page(brd, sector, gfp); + if (ret) + return ret; if (copy < n) { sector += copy >> SECTOR_SHIFT; - if (!brd_insert_page(brd, sector)) - return -ENOSPC; + ret = brd_insert_page(brd, sector, gfp); } - return 0; + return ret; } /* @@ -256,20 +252,26 @@ static void copy_from_brd(void *dst, struct brd_device *brd, * Process a single bvec of a bio. */ static int brd_do_bvec(struct brd_device *brd, struct page *page, - unsigned int len, unsigned int off, enum req_op op, + unsigned int len, unsigned int off, blk_opf_t opf, sector_t sector) { void *mem; int err = 0; - if (op_is_write(op)) { - err = copy_to_brd_setup(brd, sector, len); + if (op_is_write(opf)) { + /* + * Must use NOIO because we don't want to recurse back into the + * block or filesystem layers from page reclaim. + */ + gfp_t gfp = opf & REQ_NOWAIT ? GFP_NOWAIT : GFP_NOIO; + + err = copy_to_brd_setup(brd, sector, len, gfp); if (err) goto out; } mem = kmap_atomic(page); - if (!op_is_write(op)) { + if (!op_is_write(opf)) { copy_from_brd(mem + off, brd, sector, len); flush_dcache_page(page); } else { @@ -298,8 +300,12 @@ static void brd_submit_bio(struct bio *bio) (len & (SECTOR_SIZE - 1))); err = brd_do_bvec(brd, bvec.bv_page, len, bvec.bv_offset, - bio_op(bio), sector); + bio->bi_opf, sector); if (err) { + if (err == -ENOMEM && bio->bi_opf & REQ_NOWAIT) { + bio_wouldblock_error(bio); + return; + } bio_io_error(bio); return; } @@ -412,6 +418,7 @@ static int brd_alloc(int i) /* Tell the block layer that this is not a rotational device */ blk_queue_flag_set(QUEUE_FLAG_NONROT, disk->queue); blk_queue_flag_clear(QUEUE_FLAG_ADD_RANDOM, disk->queue); + blk_queue_flag_set(QUEUE_FLAG_NOWAIT, disk->queue); err = add_disk(disk); if (err) goto out_cleanup_disk; diff --git a/drivers/block/drbd/Makefile b/drivers/block/drbd/Makefile index c93e462130ff..67a8b352a1d5 100644 --- a/drivers/block/drbd/Makefile +++ b/drivers/block/drbd/Makefile @@ -1,5 +1,5 @@ # SPDX-License-Identifier: GPL-2.0-only -drbd-y := drbd_bitmap.o drbd_proc.o +drbd-y := drbd_buildtag.o drbd_bitmap.o drbd_proc.o drbd-y += drbd_worker.o drbd_receiver.o drbd_req.o drbd_actlog.o drbd-y += drbd_main.o drbd_strings.o drbd_nl.o drbd-y += drbd_interval.o drbd_state.o diff --git a/drivers/block/drbd/drbd_buildtag.c b/drivers/block/drbd/drbd_buildtag.c new file mode 100644 index 000000000000..cb1aa66d7d5d --- /dev/null +++ b/drivers/block/drbd/drbd_buildtag.c @@ -0,0 +1,22 @@ +// SPDX-License-Identifier: GPL-2.0-only +#include <linux/drbd_config.h> +#include <linux/module.h> + +const char *drbd_buildtag(void) +{ + /* DRBD built from external sources has here a reference to the + * git hash of the source code. + */ + + static char buildtag[38] = "\0uilt-in"; + + if (buildtag[0] == 0) { +#ifdef MODULE + sprintf(buildtag, "srcversion: %-24s", THIS_MODULE->srcversion); +#else + buildtag[0] = 'b'; +#endif + } + + return buildtag; +} diff --git a/drivers/block/drbd/drbd_debugfs.c b/drivers/block/drbd/drbd_debugfs.c index a72c096aa5b1..12460b584bcb 100644 --- a/drivers/block/drbd/drbd_debugfs.c +++ b/drivers/block/drbd/drbd_debugfs.c @@ -844,7 +844,7 @@ static int drbd_version_show(struct seq_file *m, void *ignored) { seq_printf(m, "# %s\n", drbd_buildtag()); seq_printf(m, "VERSION=%s\n", REL_VERSION); - seq_printf(m, "API_VERSION=%u\n", API_VERSION); + seq_printf(m, "API_VERSION=%u\n", GENL_MAGIC_VERSION); seq_printf(m, "PRO_VERSION_MIN=%u\n", PRO_VERSION_MIN); seq_printf(m, "PRO_VERSION_MAX=%u\n", PRO_VERSION_MAX); return 0; diff --git a/drivers/block/drbd/drbd_int.h b/drivers/block/drbd/drbd_int.h index ae713338aa46..d89b7d03d4c8 100644 --- a/drivers/block/drbd/drbd_int.h +++ b/drivers/block/drbd/drbd_int.h @@ -34,21 +34,12 @@ #include <linux/prefetch.h> #include <linux/drbd_genl_api.h> #include <linux/drbd.h> +#include <linux/drbd_config.h> #include "drbd_strings.h" #include "drbd_state.h" #include "drbd_protocol.h" #include "drbd_polymorph_printk.h" -#ifdef __CHECKER__ -# define __protected_by(x) __attribute__((require_context(x,1,999,"rdwr"))) -# define __protected_read_by(x) __attribute__((require_context(x,1,999,"read"))) -# define __protected_write_by(x) __attribute__((require_context(x,1,999,"write"))) -#else -# define __protected_by(x) -# define __protected_read_by(x) -# define __protected_write_by(x) -#endif - /* shared module parameters, defined in drbd_main.c */ #ifdef CONFIG_DRBD_FAULT_INJECTION extern int drbd_enable_faults; @@ -774,7 +765,7 @@ struct drbd_device { unsigned long flags; /* configured by drbdsetup */ - struct drbd_backing_dev *ldev __protected_by(local); + struct drbd_backing_dev *ldev; sector_t p_size; /* partner's disk size */ struct request_queue *rq_queue; diff --git a/drivers/block/drbd/drbd_interval.c b/drivers/block/drbd/drbd_interval.c index 5024ffd6143d..873beda6de24 100644 --- a/drivers/block/drbd/drbd_interval.c +++ b/drivers/block/drbd/drbd_interval.c @@ -58,7 +58,7 @@ drbd_insert_interval(struct rb_root *root, struct drbd_interval *this) * drbd_contains_interval - check if a tree contains a given interval * @root: red black tree root * @sector: start sector of @interval - * @interval: may not be a valid pointer + * @interval: may be an invalid pointer * * Returns if the tree contains the node @interval with start sector @start. * Does not dereference @interval until @interval is known to be a valid object @@ -95,6 +95,10 @@ drbd_contains_interval(struct rb_root *root, sector_t sector, void drbd_remove_interval(struct rb_root *root, struct drbd_interval *this) { + /* avoid endless loop */ + if (drbd_interval_empty(this)) + return; + rb_erase_augmented(&this->rb, root, &augment_callbacks); } diff --git a/drivers/block/drbd/drbd_main.c b/drivers/block/drbd/drbd_main.c index e43dfb9eb6ad..2c764f7ee4a7 100644 --- a/drivers/block/drbd/drbd_main.c +++ b/drivers/block/drbd/drbd_main.c @@ -2899,7 +2899,7 @@ static int __init drbd_init(void) pr_info("initialized. " "Version: " REL_VERSION " (api:%d/proto:%d-%d)\n", - API_VERSION, PRO_VERSION_MIN, PRO_VERSION_MAX); + GENL_MAGIC_VERSION, PRO_VERSION_MIN, PRO_VERSION_MAX); pr_info("%s\n", drbd_buildtag()); pr_info("registered as block device major %d\n", DRBD_MAJOR); return 0; /* Success! */ @@ -3776,24 +3776,6 @@ _drbd_insert_fault(struct drbd_device *device, unsigned int type) } #endif -const char *drbd_buildtag(void) -{ - /* DRBD built from external sources has here a reference to the - git hash of the source code. */ - - static char buildtag[38] = "\0uilt-in"; - - if (buildtag[0] == 0) { -#ifdef MODULE - sprintf(buildtag, "srcversion: %-24s", THIS_MODULE->srcversion); -#else - buildtag[0] = 'b'; -#endif - } - - return buildtag; -} - module_init(drbd_init) module_exit(drbd_cleanup) diff --git a/drivers/block/drbd/drbd_proc.c b/drivers/block/drbd/drbd_proc.c index 2227fb0db1ce..1d0feafceadc 100644 --- a/drivers/block/drbd/drbd_proc.c +++ b/drivers/block/drbd/drbd_proc.c @@ -228,7 +228,7 @@ int drbd_seq_show(struct seq_file *seq, void *v) }; seq_printf(seq, "version: " REL_VERSION " (api:%d/proto:%d-%d)\n%s\n", - API_VERSION, PRO_VERSION_MIN, PRO_VERSION_MAX, drbd_buildtag()); + GENL_MAGIC_VERSION, PRO_VERSION_MIN, PRO_VERSION_MAX, drbd_buildtag()); /* cs .. connection state diff --git a/drivers/block/drbd/drbd_vli.h b/drivers/block/drbd/drbd_vli.h index 1ee81e3c2152..941c511cc4da 100644 --- a/drivers/block/drbd/drbd_vli.h +++ b/drivers/block/drbd/drbd_vli.h @@ -327,7 +327,7 @@ static inline int bitstream_get_bits(struct bitstream *bs, u64 *out, int bits) */ static inline int vli_encode_bits(struct bitstream *bs, u64 in) { - u64 code = code; + u64 code; int bits = __vli_encode_bits(&code, in); if (bits <= 0) diff --git a/drivers/block/loop.c b/drivers/block/loop.c index 1518a6423279..5f04235e4ff7 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -90,7 +90,7 @@ struct loop_cmd { }; #define LOOP_IDLE_WORKER_TIMEOUT (60 * HZ) -#define LOOP_DEFAULT_HW_Q_DEPTH (128) +#define LOOP_DEFAULT_HW_Q_DEPTH 128 static DEFINE_IDR(loop_index_idr); static DEFINE_MUTEX(loop_ctl_mutex); @@ -1792,9 +1792,15 @@ static int hw_queue_depth = LOOP_DEFAULT_HW_Q_DEPTH; static int loop_set_hw_queue_depth(const char *s, const struct kernel_param *p) { - int ret = kstrtoint(s, 10, &hw_queue_depth); + int qd, ret; - return (ret || (hw_queue_depth < 1)) ? -EINVAL : 0; + ret = kstrtoint(s, 0, &qd); + if (ret < 0) + return ret; + if (qd < 1) + return -EINVAL; + hw_queue_depth = qd; + return 0; } static const struct kernel_param_ops loop_hw_qdepth_param_ops = { @@ -1803,7 +1809,7 @@ static const struct kernel_param_ops loop_hw_qdepth_param_ops = { }; device_param_cb(hw_queue_depth, &loop_hw_qdepth_param_ops, &hw_queue_depth, 0444); -MODULE_PARM_DESC(hw_queue_depth, "Queue depth for each hardware queue. Default: 128"); +MODULE_PARM_DESC(hw_queue_depth, "Queue depth for each hardware queue. Default: " __stringify(LOOP_DEFAULT_HW_Q_DEPTH)); MODULE_LICENSE("GPL"); MODULE_ALIAS_BLOCKDEV_MAJOR(LOOP_MAJOR); diff --git a/drivers/block/null_blk/main.c b/drivers/block/null_blk/main.c index 7d28e3aa406c..4c601ca9552a 100644 --- a/drivers/block/null_blk/main.c +++ b/drivers/block/null_blk/main.c @@ -2123,8 +2123,7 @@ static int null_add_dev(struct nullb_device *dev) blk_queue_physical_block_size(nullb->q, dev->blocksize); if (!dev->max_sectors) dev->max_sectors = queue_max_hw_sectors(nullb->q); - dev->max_sectors = min_t(unsigned int, dev->max_sectors, - BLK_DEF_MAX_SECTORS); + dev->max_sectors = min(dev->max_sectors, BLK_DEF_MAX_SECTORS); blk_queue_max_hw_sectors(nullb->q, dev->max_sectors); if (dev->virt_boundary) diff --git a/drivers/block/ps3vram.c b/drivers/block/ps3vram.c index 574e470b220b..38d42af01b25 100644 --- a/drivers/block/ps3vram.c +++ b/drivers/block/ps3vram.c @@ -586,10 +586,6 @@ static void ps3vram_submit_bio(struct bio *bio) dev_dbg(&dev->core, "%s\n", __func__); - bio = bio_split_to_limits(bio); - if (!bio) - return; - spin_lock_irq(&priv->lock); busy = !bio_list_empty(&priv->list); bio_list_add(&priv->list, bio); @@ -749,9 +745,6 @@ static int ps3vram_probe(struct ps3_system_bus_device *dev) gendisk->private_data = dev; strscpy(gendisk->disk_name, DEVICE_NAME, sizeof(gendisk->disk_name)); set_capacity(gendisk, priv->size >> 9); - blk_queue_max_segments(gendisk->queue, BLK_MAX_SEGMENTS); - blk_queue_max_segment_size(gendisk->queue, BLK_MAX_SEGMENT_SIZE); - blk_queue_max_hw_sectors(gendisk->queue, BLK_SAFE_MAX_SECTORS); dev_info(&dev->core, "%s: Using %llu MiB of GPU memory\n", gendisk->disk_name, get_capacity(gendisk) >> 11); diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c index 04453f4a319c..1faca7e07a4d 100644 --- a/drivers/block/rbd.c +++ b/drivers/block/rbd.c @@ -3068,13 +3068,12 @@ static int setup_copyup_bvecs(struct rbd_obj_request *obj_req, u64 obj_overlap) for (i = 0; i < obj_req->copyup_bvec_count; i++) { unsigned int len = min(obj_overlap, (u64)PAGE_SIZE); + struct page *page = alloc_page(GFP_NOIO); - obj_req->copyup_bvecs[i].bv_page = alloc_page(GFP_NOIO); - if (!obj_req->copyup_bvecs[i].bv_page) + if (!page) return -ENOMEM; - obj_req->copyup_bvecs[i].bv_offset = 0; - obj_req->copyup_bvecs[i].bv_len = len; + bvec_set_page(&obj_req->copyup_bvecs[i], page, len, 0); obj_overlap -= len; } diff --git a/drivers/block/ublk_drv.c b/drivers/block/ublk_drv.c index 6368b56eacf1..b9c759cef00e 100644 --- a/drivers/block/ublk_drv.c +++ b/drivers/block/ublk_drv.c @@ -42,6 +42,7 @@ #include <linux/mm.h> #include <asm/page.h> #include <linux/task_work.h> +#include <linux/namei.h> #include <uapi/linux/ublk_cmd.h> #define UBLK_MINORS (1U << MINORBITS) @@ -51,10 +52,12 @@ | UBLK_F_URING_CMD_COMP_IN_TASK \ | UBLK_F_NEED_GET_DATA \ | UBLK_F_USER_RECOVERY \ - | UBLK_F_USER_RECOVERY_REISSUE) + | UBLK_F_USER_RECOVERY_REISSUE \ + | UBLK_F_UNPRIVILEGED_DEV) /* All UBLK_PARAM_TYPE_* should be included here */ -#define UBLK_PARAM_TYPE_ALL (UBLK_PARAM_TYPE_BASIC | UBLK_PARAM_TYPE_DISCARD) +#define UBLK_PARAM_TYPE_ALL (UBLK_PARAM_TYPE_BASIC | \ + UBLK_PARAM_TYPE_DISCARD | UBLK_PARAM_TYPE_DEVT) struct ublk_rq_data { struct llist_node node; @@ -147,6 +150,7 @@ struct ublk_device { #define UB_STATE_OPEN 0 #define UB_STATE_USED 1 +#define UB_STATE_DELETED 2 unsigned long state; int ub_number; @@ -159,7 +163,7 @@ struct ublk_device { struct completion completion; unsigned int nr_queues_ready; - atomic_t nr_aborted_queues; + unsigned int nr_privileged_daemon; /* * Our ubq->daemon may be killed without any notification, so @@ -185,6 +189,15 @@ static wait_queue_head_t ublk_idr_wq; /* wait until one idr is freed */ static DEFINE_MUTEX(ublk_ctl_mutex); +/* + * Max ublk devices allowed to add + * + * It can be extended to one per-user limit in future or even controlled + * by cgroup. + */ +static unsigned int ublks_max = 64; +static unsigned int ublks_added; /* protected by ublk_ctl_mutex */ + static struct miscdevice ublk_misc; static void ublk_dev_param_basic_apply(struct ublk_device *ub) @@ -255,6 +268,10 @@ static int ublk_validate_params(const struct ublk_device *ub) return -EINVAL; } + /* dev_t is read-only */ + if (ub->params.types & UBLK_PARAM_TYPE_DEVT) + return -EINVAL; + return 0; } @@ -306,7 +323,7 @@ static inline struct ublk_queue *ublk_get_queue(struct ublk_device *dev, static inline bool ublk_rq_has_data(const struct request *rq) { - return rq->bio && bio_has_data(rq->bio); + return bio_has_data(rq->bio); } static inline struct ublksrv_io_desc *ublk_get_iod(struct ublk_queue *ubq, @@ -361,8 +378,50 @@ static void ublk_free_disk(struct gendisk *disk) put_device(&ub->cdev_dev); } +static void ublk_store_owner_uid_gid(unsigned int *owner_uid, + unsigned int *owner_gid) +{ + kuid_t uid; + kgid_t gid; + + current_uid_gid(&uid, &gid); + + *owner_uid = from_kuid(&init_user_ns, uid); + *owner_gid = from_kgid(&init_user_ns, gid); +} + +static int ublk_open(struct block_device *bdev, fmode_t mode) +{ + struct ublk_device *ub = bdev->bd_disk->private_data; + + if (capable(CAP_SYS_ADMIN)) + return 0; + + /* + * If it is one unprivileged device, only owner can open + * the disk. Otherwise it could be one trap made by one + * evil user who grants this disk's privileges to other + * users deliberately. + * + * This way is reasonable too given anyone can create + * unprivileged device, and no need other's grant. + */ + if (ub->dev_info.flags & UBLK_F_UNPRIVILEGED_DEV) { + unsigned int curr_uid, curr_gid; + + ublk_store_owner_uid_gid(&curr_uid, &curr_gid); + + if (curr_uid != ub->dev_info.owner_uid || curr_gid != + ub->dev_info.owner_gid) + return -EPERM; + } + + return 0; +} + static const struct block_device_operations ub_fops = { .owner = THIS_MODULE, + .open = ublk_open, .free_disk = ublk_free_disk, }; @@ -607,7 +666,7 @@ static void ublk_complete_rq(struct request *req) } /* - * FLUSH or DISCARD usually won't return bytes returned, so end them + * FLUSH, DISCARD or WRITE_ZEROES usually won't return bytes returned, so end them * directly. * * Both the two needn't unmap. @@ -1179,6 +1238,9 @@ static void ublk_mark_io_ready(struct ublk_device *ub, struct ublk_queue *ubq) ubq->ubq_daemon = current; get_task_struct(ubq->ubq_daemon); ub->nr_queues_ready++; + + if (capable(CAP_SYS_ADMIN)) + ub->nr_privileged_daemon++; } if (ub->nr_queues_ready == ub->dev_info.nr_hw_queues) complete_all(&ub->completion); @@ -1203,6 +1265,7 @@ static int ublk_ch_uring_cmd(struct io_uring_cmd *cmd, unsigned int issue_flags) u32 cmd_op = cmd->cmd_op; unsigned tag = ub_cmd->tag; int ret = -EINVAL; + struct request *req; pr_devel("%s: received: cmd op %d queue %d tag %d result %d\n", __func__, cmd->cmd_op, ub_cmd->q_id, tag, @@ -1253,8 +1316,8 @@ static int ublk_ch_uring_cmd(struct io_uring_cmd *cmd, unsigned int issue_flags) */ if (io->flags & UBLK_IO_FLAG_OWNED_BY_SRV) goto out; - /* FETCH_RQ has to provide IO buffer */ - if (!ub_cmd->addr) + /* FETCH_RQ has to provide IO buffer if NEED GET DATA is not enabled */ + if (!ub_cmd->addr && !ublk_need_get_data(ubq)) goto out; io->cmd = cmd; io->flags |= UBLK_IO_FLAG_ACTIVE; @@ -1263,8 +1326,12 @@ static int ublk_ch_uring_cmd(struct io_uring_cmd *cmd, unsigned int issue_flags) ublk_mark_io_ready(ub, ubq); break; case UBLK_IO_COMMIT_AND_FETCH_REQ: - /* FETCH_RQ has to provide IO buffer */ - if (!ub_cmd->addr) + req = blk_mq_tag_to_rq(ub->tag_set.tags[ub_cmd->q_id], tag); + /* + * COMMIT_AND_FETCH_REQ has to provide IO buffer if NEED GET DATA is + * not enabled or it is Read IO. + */ + if (!ub_cmd->addr && (!ublk_need_get_data(ubq) || req_op(req) == REQ_OP_READ)) goto out; if (!(io->flags & UBLK_IO_FLAG_OWNED_BY_SRV)) goto out; @@ -1433,6 +1500,8 @@ static int ublk_add_chdev(struct ublk_device *ub) ret = cdev_device_add(&ub->cdev, dev); if (ret) goto fail; + + ublks_added++; return 0; fail: put_device(dev); @@ -1475,6 +1544,7 @@ static void ublk_remove(struct ublk_device *ub) cancel_work_sync(&ub->quiesce_work); cdev_device_del(&ub->cdev, &ub->cdev_dev); put_device(&ub->cdev_dev); + ublks_added--; } static struct ublk_device *ublk_get_device_from_id(int idx) @@ -1493,21 +1563,16 @@ static struct ublk_device *ublk_get_device_from_id(int idx) return ub; } -static int ublk_ctrl_start_dev(struct io_uring_cmd *cmd) +static int ublk_ctrl_start_dev(struct ublk_device *ub, struct io_uring_cmd *cmd) { struct ublksrv_ctrl_cmd *header = (struct ublksrv_ctrl_cmd *)cmd->cmd; int ublksrv_pid = (int)header->data[0]; - struct ublk_device *ub; struct gendisk *disk; int ret = -EINVAL; if (ublksrv_pid <= 0) return -EINVAL; - ub = ublk_get_device_from_id(header->dev_id); - if (!ub) - return -EINVAL; - wait_for_completion_interruptible(&ub->completion); schedule_delayed_work(&ub->monitor_work, UBLK_DAEMON_MONITOR_PERIOD); @@ -1519,7 +1584,7 @@ static int ublk_ctrl_start_dev(struct io_uring_cmd *cmd) goto out_unlock; } - disk = blk_mq_alloc_disk(&ub->tag_set, ub); + disk = blk_mq_alloc_disk(&ub->tag_set, NULL); if (IS_ERR(disk)) { ret = PTR_ERR(disk); goto out_unlock; @@ -1535,6 +1600,10 @@ static int ublk_ctrl_start_dev(struct io_uring_cmd *cmd) if (ret) goto out_put_disk; + /* don't probe partitions if any one ubq daemon is un-trusted */ + if (ub->nr_privileged_daemon != ub->nr_queues_ready) + set_bit(GD_SUPPRESS_PART_SCAN, &disk->state); + get_device(&ub->cdev_dev); ret = add_disk(disk); if (ret) { @@ -1552,21 +1621,20 @@ out_put_disk: put_disk(disk); out_unlock: mutex_unlock(&ub->mutex); - ublk_put_device(ub); return ret; } -static int ublk_ctrl_get_queue_affinity(struct io_uring_cmd *cmd) +static int ublk_ctrl_get_queue_affinity(struct ublk_device *ub, + struct io_uring_cmd *cmd) { struct ublksrv_ctrl_cmd *header = (struct ublksrv_ctrl_cmd *)cmd->cmd; void __user *argp = (void __user *)(unsigned long)header->addr; - struct ublk_device *ub; cpumask_var_t cpumask; unsigned long queue; unsigned int retlen; unsigned int i; - int ret = -EINVAL; - + int ret; + if (header->len * BITS_PER_BYTE < nr_cpu_ids) return -EINVAL; if (header->len & (sizeof(unsigned long)-1)) @@ -1574,17 +1642,12 @@ static int ublk_ctrl_get_queue_affinity(struct io_uring_cmd *cmd) if (!header->addr) return -EINVAL; - ub = ublk_get_device_from_id(header->dev_id); - if (!ub) - return -EINVAL; - queue = header->data[0]; if (queue >= ub->dev_info.nr_hw_queues) - goto out_put_device; + return -EINVAL; - ret = -ENOMEM; if (!zalloc_cpumask_var(&cpumask, GFP_KERNEL)) - goto out_put_device; + return -ENOMEM; for_each_possible_cpu(i) { if (ub->tag_set.map[HCTX_TYPE_DEFAULT].mq_map[i] == queue) @@ -1602,8 +1665,6 @@ static int ublk_ctrl_get_queue_affinity(struct io_uring_cmd *cmd) ret = 0; out_free_cpumask: free_cpumask_var(cpumask); -out_put_device: - ublk_put_device(ub); return ret; } @@ -1630,19 +1691,34 @@ static int ublk_ctrl_add_dev(struct io_uring_cmd *cmd) __func__, header->queue_id); return -EINVAL; } + if (copy_from_user(&info, argp, sizeof(info))) return -EFAULT; - ublk_dump_dev_info(&info); + + if (capable(CAP_SYS_ADMIN)) + info.flags &= ~UBLK_F_UNPRIVILEGED_DEV; + else if (!(info.flags & UBLK_F_UNPRIVILEGED_DEV)) + return -EPERM; + + /* the created device is always owned by current user */ + ublk_store_owner_uid_gid(&info.owner_uid, &info.owner_gid); + if (header->dev_id != info.dev_id) { pr_warn("%s: dev id not match %u %u\n", __func__, header->dev_id, info.dev_id); return -EINVAL; } + ublk_dump_dev_info(&info); + ret = mutex_lock_killable(&ublk_ctl_mutex); if (ret) return ret; + ret = -EACCES; + if (ublks_added >= ublks_max) + goto out_unlock; + ret = -ENOMEM; ub = kzalloc(sizeof(*ub), GFP_KERNEL); if (!ub) @@ -1724,33 +1800,43 @@ static inline bool ublk_idr_freed(int id) return ptr == NULL; } -static int ublk_ctrl_del_dev(int idx) +static int ublk_ctrl_del_dev(struct ublk_device **p_ub) { - struct ublk_device *ub; + struct ublk_device *ub = *p_ub; + int idx = ub->ub_number; int ret; ret = mutex_lock_killable(&ublk_ctl_mutex); if (ret) return ret; - ub = ublk_get_device_from_id(idx); - if (ub) { + if (!test_bit(UB_STATE_DELETED, &ub->state)) { ublk_remove(ub); - ublk_put_device(ub); - ret = 0; - } else { - ret = -ENODEV; + set_bit(UB_STATE_DELETED, &ub->state); } + /* Mark the reference as consumed */ + *p_ub = NULL; + ublk_put_device(ub); + mutex_unlock(&ublk_ctl_mutex); + /* * Wait until the idr is removed, then it can be reused after * DEL_DEV command is returned. + * + * If we returns because of user interrupt, future delete command + * may come: + * + * - the device number isn't freed, this device won't or needn't + * be deleted again, since UB_STATE_DELETED is set, and device + * will be released after the last reference is dropped + * + * - the device number is freed already, we will not find this + * device via ublk_get_device_from_id() */ - if (!ret) - wait_event(ublk_idr_wq, ublk_idr_freed(idx)); - mutex_unlock(&ublk_ctl_mutex); + wait_event_interruptible(ublk_idr_wq, ublk_idr_freed(idx)); - return ret; + return 0; } static inline void ublk_ctrl_cmd_dump(struct io_uring_cmd *cmd) @@ -1762,50 +1848,52 @@ static inline void ublk_ctrl_cmd_dump(struct io_uring_cmd *cmd) header->data[0], header->addr, header->len); } -static int ublk_ctrl_stop_dev(struct io_uring_cmd *cmd) +static int ublk_ctrl_stop_dev(struct ublk_device *ub) { - struct ublksrv_ctrl_cmd *header = (struct ublksrv_ctrl_cmd *)cmd->cmd; - struct ublk_device *ub; - - ub = ublk_get_device_from_id(header->dev_id); - if (!ub) - return -EINVAL; - ublk_stop_dev(ub); cancel_work_sync(&ub->stop_work); cancel_work_sync(&ub->quiesce_work); - ublk_put_device(ub); return 0; } -static int ublk_ctrl_get_dev_info(struct io_uring_cmd *cmd) +static int ublk_ctrl_get_dev_info(struct ublk_device *ub, + struct io_uring_cmd *cmd) { struct ublksrv_ctrl_cmd *header = (struct ublksrv_ctrl_cmd *)cmd->cmd; void __user *argp = (void __user *)(unsigned long)header->addr; - struct ublk_device *ub; - int ret = 0; if (header->len < sizeof(struct ublksrv_ctrl_dev_info) || !header->addr) return -EINVAL; - ub = ublk_get_device_from_id(header->dev_id); - if (!ub) - return -EINVAL; - if (copy_to_user(argp, &ub->dev_info, sizeof(ub->dev_info))) - ret = -EFAULT; - ublk_put_device(ub); + return -EFAULT; - return ret; + return 0; +} + +/* TYPE_DEVT is readonly, so fill it up before returning to userspace */ +static void ublk_ctrl_fill_params_devt(struct ublk_device *ub) +{ + ub->params.devt.char_major = MAJOR(ub->cdev_dev.devt); + ub->params.devt.char_minor = MINOR(ub->cdev_dev.devt); + + if (ub->ub_disk) { + ub->params.devt.disk_major = MAJOR(disk_devt(ub->ub_disk)); + ub->params.devt.disk_minor = MINOR(disk_devt(ub->ub_disk)); + } else { + ub->params.devt.disk_major = 0; + ub->params.devt.disk_minor = 0; + } + ub->params.types |= UBLK_PARAM_TYPE_DEVT; } -static int ublk_ctrl_get_params(struct io_uring_cmd *cmd) +static int ublk_ctrl_get_params(struct ublk_device *ub, + struct io_uring_cmd *cmd) { struct ublksrv_ctrl_cmd *header = (struct ublksrv_ctrl_cmd *)cmd->cmd; void __user *argp = (void __user *)(unsigned long)header->addr; struct ublk_params_header ph; - struct ublk_device *ub; int ret; if (header->len <= sizeof(ph) || !header->addr) @@ -1820,27 +1908,23 @@ static int ublk_ctrl_get_params(struct io_uring_cmd *cmd) if (ph.len > sizeof(struct ublk_params)) ph.len = sizeof(struct ublk_params); - ub = ublk_get_device_from_id(header->dev_id); - if (!ub) - return -EINVAL; - mutex_lock(&ub->mutex); + ublk_ctrl_fill_params_devt(ub); if (copy_to_user(argp, &ub->params, ph.len)) ret = -EFAULT; else ret = 0; mutex_unlock(&ub->mutex); - ublk_put_device(ub); return ret; } -static int ublk_ctrl_set_params(struct io_uring_cmd *cmd) +static int ublk_ctrl_set_params(struct ublk_device *ub, + struct io_uring_cmd *cmd) { struct ublksrv_ctrl_cmd *header = (struct ublksrv_ctrl_cmd *)cmd->cmd; void __user *argp = (void __user *)(unsigned long)header->addr; struct ublk_params_header ph; - struct ublk_device *ub; int ret = -EFAULT; if (header->len <= sizeof(ph) || !header->addr) @@ -1855,10 +1939,6 @@ static int ublk_ctrl_set_params(struct io_uring_cmd *cmd) if (ph.len > sizeof(struct ublk_params)) ph.len = sizeof(struct ublk_params); - ub = ublk_get_device_from_id(header->dev_id); - if (!ub) - return -EINVAL; - /* parameters can only be changed when device isn't live */ mutex_lock(&ub->mutex); if (ub->dev_info.state == UBLK_S_DEV_LIVE) { @@ -1871,7 +1951,6 @@ static int ublk_ctrl_set_params(struct io_uring_cmd *cmd) ret = ublk_validate_params(ub); } mutex_unlock(&ub->mutex); - ublk_put_device(ub); return ret; } @@ -1898,17 +1977,13 @@ static void ublk_queue_reinit(struct ublk_device *ub, struct ublk_queue *ubq) } } -static int ublk_ctrl_start_recovery(struct io_uring_cmd *cmd) +static int ublk_ctrl_start_recovery(struct ublk_device *ub, + struct io_uring_cmd *cmd) { struct ublksrv_ctrl_cmd *header = (struct ublksrv_ctrl_cmd *)cmd->cmd; - struct ublk_device *ub; int ret = -EINVAL; int i; - ub = ublk_get_device_from_id(header->dev_id); - if (!ub) - return ret; - mutex_lock(&ub->mutex); if (!ublk_can_use_recovery(ub)) goto out_unlock; @@ -1936,25 +2011,21 @@ static int ublk_ctrl_start_recovery(struct io_uring_cmd *cmd) /* set to NULL, otherwise new ubq_daemon cannot mmap the io_cmd_buf */ ub->mm = NULL; ub->nr_queues_ready = 0; + ub->nr_privileged_daemon = 0; init_completion(&ub->completion); ret = 0; out_unlock: mutex_unlock(&ub->mutex); - ublk_put_device(ub); return ret; } -static int ublk_ctrl_end_recovery(struct io_uring_cmd *cmd) +static int ublk_ctrl_end_recovery(struct ublk_device *ub, + struct io_uring_cmd *cmd) { struct ublksrv_ctrl_cmd *header = (struct ublksrv_ctrl_cmd *)cmd->cmd; int ublksrv_pid = (int)header->data[0]; - struct ublk_device *ub; int ret = -EINVAL; - ub = ublk_get_device_from_id(header->dev_id); - if (!ub) - return ret; - pr_devel("%s: Waiting for new ubq_daemons(nr: %d) are ready, dev id %d...\n", __func__, ub->dev_info.nr_hw_queues, header->dev_id); /* wait until new ubq_daemon sending all FETCH_REQ */ @@ -1982,7 +2053,115 @@ static int ublk_ctrl_end_recovery(struct io_uring_cmd *cmd) ret = 0; out_unlock: mutex_unlock(&ub->mutex); - ublk_put_device(ub); + return ret; +} + +/* + * All control commands are sent via /dev/ublk-control, so we have to check + * the destination device's permission + */ +static int ublk_char_dev_permission(struct ublk_device *ub, + const char *dev_path, int mask) +{ + int err; + struct path path; + struct kstat stat; + + err = kern_path(dev_path, LOOKUP_FOLLOW, &path); + if (err) + return err; + + err = vfs_getattr(&path, &stat, STATX_TYPE, AT_STATX_SYNC_AS_STAT); + if (err) + goto exit; + + err = -EPERM; + if (stat.rdev != ub->cdev_dev.devt || !S_ISCHR(stat.mode)) + goto exit; + + err = inode_permission(&nop_mnt_idmap, + d_backing_inode(path.dentry), mask); +exit: + path_put(&path); + return err; +} + +static int ublk_ctrl_uring_cmd_permission(struct ublk_device *ub, + struct io_uring_cmd *cmd) +{ + struct ublksrv_ctrl_cmd *header = (struct ublksrv_ctrl_cmd *)cmd->cmd; + bool unprivileged = ub->dev_info.flags & UBLK_F_UNPRIVILEGED_DEV; + void __user *argp = (void __user *)(unsigned long)header->addr; + char *dev_path = NULL; + int ret = 0; + int mask; + + if (!unprivileged) { + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + /* + * The new added command of UBLK_CMD_GET_DEV_INFO2 includes + * char_dev_path in payload too, since userspace may not + * know if the specified device is created as unprivileged + * mode. + */ + if (cmd->cmd_op != UBLK_CMD_GET_DEV_INFO2) + return 0; + } + + /* + * User has to provide the char device path for unprivileged ublk + * + * header->addr always points to the dev path buffer, and + * header->dev_path_len records length of dev path buffer. + */ + if (!header->dev_path_len || header->dev_path_len > PATH_MAX) + return -EINVAL; + + if (header->len < header->dev_path_len) + return -EINVAL; + + dev_path = kmalloc(header->dev_path_len + 1, GFP_KERNEL); + if (!dev_path) + return -ENOMEM; + + ret = -EFAULT; + if (copy_from_user(dev_path, argp, header->dev_path_len)) + goto exit; + dev_path[header->dev_path_len] = 0; + + ret = -EINVAL; + switch (cmd->cmd_op) { + case UBLK_CMD_GET_DEV_INFO: + case UBLK_CMD_GET_DEV_INFO2: + case UBLK_CMD_GET_QUEUE_AFFINITY: + case UBLK_CMD_GET_PARAMS: + mask = MAY_READ; + break; + case UBLK_CMD_START_DEV: + case UBLK_CMD_STOP_DEV: + case UBLK_CMD_ADD_DEV: + case UBLK_CMD_DEL_DEV: + case UBLK_CMD_SET_PARAMS: + case UBLK_CMD_START_USER_RECOVERY: + case UBLK_CMD_END_USER_RECOVERY: + mask = MAY_READ | MAY_WRITE; + break; + default: + goto exit; + } + + ret = ublk_char_dev_permission(ub, dev_path, mask); + if (!ret) { + header->len -= header->dev_path_len; + header->addr += header->dev_path_len; + } + pr_devel("%s: dev id %d cmd_op %x uid %d gid %d path %s ret %d\n", + __func__, ub->ub_number, cmd->cmd_op, + ub->dev_info.owner_uid, ub->dev_info.owner_gid, + dev_path, ret); +exit: + kfree(dev_path); return ret; } @@ -1990,6 +2169,7 @@ static int ublk_ctrl_uring_cmd(struct io_uring_cmd *cmd, unsigned int issue_flags) { struct ublksrv_ctrl_cmd *header = (struct ublksrv_ctrl_cmd *)cmd->cmd; + struct ublk_device *ub = NULL; int ret = -EINVAL; if (issue_flags & IO_URING_F_NONBLOCK) @@ -2000,45 +2180,61 @@ static int ublk_ctrl_uring_cmd(struct io_uring_cmd *cmd, if (!(issue_flags & IO_URING_F_SQE128)) goto out; - ret = -EPERM; - if (!capable(CAP_SYS_ADMIN)) - goto out; + if (cmd->cmd_op != UBLK_CMD_ADD_DEV) { + ret = -ENODEV; + ub = ublk_get_device_from_id(header->dev_id); + if (!ub) + goto out; + + ret = ublk_ctrl_uring_cmd_permission(ub, cmd); + } else { + /* ADD_DEV permission check is done in command handler */ + ret = 0; + } + + if (ret) + goto put_dev; - ret = -ENODEV; switch (cmd->cmd_op) { case UBLK_CMD_START_DEV: - ret = ublk_ctrl_start_dev(cmd); + ret = ublk_ctrl_start_dev(ub, cmd); break; case UBLK_CMD_STOP_DEV: - ret = ublk_ctrl_stop_dev(cmd); + ret = ublk_ctrl_stop_dev(ub); break; case UBLK_CMD_GET_DEV_INFO: - ret = ublk_ctrl_get_dev_info(cmd); + case UBLK_CMD_GET_DEV_INFO2: + ret = ublk_ctrl_get_dev_info(ub, cmd); break; case UBLK_CMD_ADD_DEV: ret = ublk_ctrl_add_dev(cmd); break; case UBLK_CMD_DEL_DEV: - ret = ublk_ctrl_del_dev(header->dev_id); + ret = ublk_ctrl_del_dev(&ub); break; case UBLK_CMD_GET_QUEUE_AFFINITY: - ret = ublk_ctrl_get_queue_affinity(cmd); + ret = ublk_ctrl_get_queue_affinity(ub, cmd); break; case UBLK_CMD_GET_PARAMS: - ret = ublk_ctrl_get_params(cmd); + ret = ublk_ctrl_get_params(ub, cmd); break; case UBLK_CMD_SET_PARAMS: - ret = ublk_ctrl_set_params(cmd); + ret = ublk_ctrl_set_params(ub, cmd); break; case UBLK_CMD_START_USER_RECOVERY: - ret = ublk_ctrl_start_recovery(cmd); + ret = ublk_ctrl_start_recovery(ub, cmd); break; case UBLK_CMD_END_USER_RECOVERY: - ret = ublk_ctrl_end_recovery(cmd); + ret = ublk_ctrl_end_recovery(ub, cmd); break; default: + ret = -ENOTSUPP; break; } + + put_dev: + if (ub) + ublk_put_device(ub); out: io_uring_cmd_done(cmd, ret, 0); pr_devel("%s: cmd done ret %d cmd_op %x, dev id %d qid %d\n", @@ -2105,5 +2301,8 @@ static void __exit ublk_exit(void) module_init(ublk_init); module_exit(ublk_exit); +module_param(ublks_max, int, 0444); +MODULE_PARM_DESC(ublks_max, "max number of ublk devices allowed to add(default: 64)"); + MODULE_AUTHOR("Ming Lei <ming.lei@redhat.com>"); MODULE_LICENSE("GPL"); diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c index 6a77fa917428..dc6e9b989910 100644 --- a/drivers/block/virtio_blk.c +++ b/drivers/block/virtio_blk.c @@ -170,9 +170,7 @@ static int virtblk_setup_discard_write_zeroes_erase(struct request *req, bool un WARN_ON_ONCE(n != segments); - req->special_vec.bv_page = virt_to_page(range); - req->special_vec.bv_offset = offset_in_page(range); - req->special_vec.bv_len = sizeof(*range) * segments; + bvec_set_virt(&req->special_vec, range, sizeof(*range) * segments); req->rq_flags |= RQF_SPECIAL_PAYLOAD; return 0; diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c index e290d6d97047..bd8ae4822dc3 100644 --- a/drivers/block/zram/zram_drv.c +++ b/drivers/block/zram/zram_drv.c @@ -703,9 +703,7 @@ static ssize_t writeback_store(struct device *dev, for (; nr_pages != 0; index++, nr_pages--) { struct bio_vec bvec; - bvec.bv_page = page; - bvec.bv_len = PAGE_SIZE; - bvec.bv_offset = 0; + bvec_set_page(&bvec, page, PAGE_SIZE, 0); spin_lock(&zram->wb_limit_lock); if (zram->wb_limit_enable && !zram->bd_wb_limit) { @@ -1380,12 +1378,9 @@ out: static int zram_bvec_read_from_bdev(struct zram *zram, struct page *page, u32 index, struct bio *bio, bool partial_io) { - struct bio_vec bvec = { - .bv_page = page, - .bv_len = PAGE_SIZE, - .bv_offset = 0, - }; + struct bio_vec bvec; + bvec_set_page(&bvec, page, PAGE_SIZE, 0); return read_from_bdev(zram, &bvec, zram_get_element(zram, index), bio, partial_io); } @@ -1652,9 +1647,7 @@ static int zram_bvec_write(struct zram *zram, struct bio_vec *bvec, memcpy_from_bvec(dst + offset, bvec); kunmap_atomic(dst); - vec.bv_page = page; - vec.bv_len = PAGE_SIZE; - vec.bv_offset = 0; + bvec_set_page(&vec, page, PAGE_SIZE, 0); } ret = __zram_bvec_write(zram, &vec, index, bio); diff --git a/drivers/md/md.c b/drivers/md/md.c index 02b0240e7c71..927a43db5dfb 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -380,6 +380,10 @@ EXPORT_SYMBOL_GPL(md_new_event); static LIST_HEAD(all_mddevs); static DEFINE_SPINLOCK(all_mddevs_lock); +static bool is_md_suspended(struct mddev *mddev) +{ + return percpu_ref_is_dying(&mddev->active_io); +} /* Rather than calling directly into the personality make_request function, * IO requests come here first so that we can check if the device is * being suspended pending a reconfiguration. @@ -389,7 +393,7 @@ static DEFINE_SPINLOCK(all_mddevs_lock); */ static bool is_suspended(struct mddev *mddev, struct bio *bio) { - if (mddev->suspended) + if (is_md_suspended(mddev)) return true; if (bio_data_dir(bio) != WRITE) return false; @@ -405,12 +409,10 @@ static bool is_suspended(struct mddev *mddev, struct bio *bio) void md_handle_request(struct mddev *mddev, struct bio *bio) { check_suspended: - rcu_read_lock(); if (is_suspended(mddev, bio)) { DEFINE_WAIT(__wait); /* Bail out if REQ_NOWAIT is set for the bio */ if (bio->bi_opf & REQ_NOWAIT) { - rcu_read_unlock(); bio_wouldblock_error(bio); return; } @@ -419,23 +421,19 @@ check_suspended: TASK_UNINTERRUPTIBLE); if (!is_suspended(mddev, bio)) break; - rcu_read_unlock(); schedule(); - rcu_read_lock(); } finish_wait(&mddev->sb_wait, &__wait); } - atomic_inc(&mddev->active_io); - rcu_read_unlock(); + if (!percpu_ref_tryget_live(&mddev->active_io)) + goto check_suspended; if (!mddev->pers->make_request(mddev, bio)) { - atomic_dec(&mddev->active_io); - wake_up(&mddev->sb_wait); + percpu_ref_put(&mddev->active_io); goto check_suspended; } - if (atomic_dec_and_test(&mddev->active_io) && mddev->suspended) - wake_up(&mddev->sb_wait); + percpu_ref_put(&mddev->active_io); } EXPORT_SYMBOL(md_handle_request); @@ -483,11 +481,10 @@ void mddev_suspend(struct mddev *mddev) lockdep_assert_held(&mddev->reconfig_mutex); if (mddev->suspended++) return; - synchronize_rcu(); wake_up(&mddev->sb_wait); set_bit(MD_ALLOW_SB_UPDATE, &mddev->flags); - smp_mb__after_atomic(); - wait_event(mddev->sb_wait, atomic_read(&mddev->active_io) == 0); + percpu_ref_kill(&mddev->active_io); + wait_event(mddev->sb_wait, percpu_ref_is_zero(&mddev->active_io)); mddev->pers->quiesce(mddev, 1); clear_bit_unlock(MD_ALLOW_SB_UPDATE, &mddev->flags); wait_event(mddev->sb_wait, !test_bit(MD_UPDATING_SB, &mddev->flags)); @@ -505,6 +502,7 @@ void mddev_resume(struct mddev *mddev) lockdep_assert_held(&mddev->reconfig_mutex); if (--mddev->suspended) return; + percpu_ref_resurrect(&mddev->active_io); wake_up(&mddev->sb_wait); mddev->pers->quiesce(mddev, 0); @@ -683,7 +681,6 @@ void mddev_init(struct mddev *mddev) timer_setup(&mddev->safemode_timer, md_safemode_timeout, 0); atomic_set(&mddev->active, 1); atomic_set(&mddev->openers, 0); - atomic_set(&mddev->active_io, 0); spin_lock_init(&mddev->lock); atomic_set(&mddev->flush_pending, 0); init_waitqueue_head(&mddev->sb_wait); @@ -5760,6 +5757,12 @@ static void md_safemode_timeout(struct timer_list *t) } static int start_dirty_degraded; +static void active_io_release(struct percpu_ref *ref) +{ + struct mddev *mddev = container_of(ref, struct mddev, active_io); + + wake_up(&mddev->sb_wait); +} int md_run(struct mddev *mddev) { @@ -5840,10 +5843,15 @@ int md_run(struct mddev *mddev) nowait = nowait && bdev_nowait(rdev->bdev); } + err = percpu_ref_init(&mddev->active_io, active_io_release, + PERCPU_REF_ALLOW_REINIT, GFP_KERNEL); + if (err) + return err; + if (!bioset_initialized(&mddev->bio_set)) { err = bioset_init(&mddev->bio_set, BIO_POOL_SIZE, 0, BIOSET_NEED_BVECS); if (err) - return err; + goto exit_active_io; } if (!bioset_initialized(&mddev->sync_set)) { err = bioset_init(&mddev->sync_set, BIO_POOL_SIZE, 0, BIOSET_NEED_BVECS); @@ -6031,6 +6039,8 @@ abort: bioset_exit(&mddev->sync_set); exit_bio_set: bioset_exit(&mddev->bio_set); +exit_active_io: + percpu_ref_exit(&mddev->active_io); return err; } EXPORT_SYMBOL_GPL(md_run); @@ -6156,7 +6166,7 @@ static void md_clean(struct mddev *mddev) mddev->new_level = LEVEL_NONE; mddev->new_layout = 0; mddev->new_chunk_sectors = 0; - mddev->curr_resync = 0; + mddev->curr_resync = MD_RESYNC_NONE; atomic64_set(&mddev->resync_mismatches, 0); mddev->suspend_lo = mddev->suspend_hi = 0; mddev->sync_speed_min = mddev->sync_speed_max = 0; @@ -6219,7 +6229,7 @@ EXPORT_SYMBOL_GPL(md_stop_writes); static void mddev_detach(struct mddev *mddev) { md_bitmap_wait_behind_writes(mddev); - if (mddev->pers && mddev->pers->quiesce && !mddev->suspended) { + if (mddev->pers && mddev->pers->quiesce && !is_md_suspended(mddev)) { mddev->pers->quiesce(mddev, 1); mddev->pers->quiesce(mddev, 0); } @@ -6255,6 +6265,8 @@ void md_stop(struct mddev *mddev) */ __md_stop_writes(mddev); __md_stop(mddev); + percpu_ref_exit(&mddev->writes_pending); + percpu_ref_exit(&mddev->active_io); bioset_exit(&mddev->bio_set); bioset_exit(&mddev->sync_set); } @@ -7828,6 +7840,7 @@ static void md_free_disk(struct gendisk *disk) struct mddev *mddev = disk->private_data; percpu_ref_exit(&mddev->writes_pending); + percpu_ref_exit(&mddev->active_io); bioset_exit(&mddev->bio_set); bioset_exit(&mddev->sync_set); @@ -8531,7 +8544,7 @@ bool md_write_start(struct mddev *mddev, struct bio *bi) return true; wait_event(mddev->sb_wait, !test_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags) || - mddev->suspended); + is_md_suspended(mddev)); if (test_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags)) { percpu_ref_put(&mddev->writes_pending); return false; @@ -8615,12 +8628,15 @@ static void md_end_io_acct(struct bio *bio) { struct md_io_acct *md_io_acct = bio->bi_private; struct bio *orig_bio = md_io_acct->orig_bio; + struct mddev *mddev = md_io_acct->mddev; orig_bio->bi_status = bio->bi_status; bio_end_io_acct(orig_bio, md_io_acct->start_time); bio_put(bio); bio_endio(orig_bio); + + percpu_ref_put(&mddev->active_io); } /* @@ -8636,10 +8652,13 @@ void md_account_bio(struct mddev *mddev, struct bio **bio) if (!blk_queue_io_stat(bdev->bd_disk->queue)) return; + percpu_ref_get(&mddev->active_io); + clone = bio_alloc_clone(bdev, *bio, GFP_NOIO, &mddev->io_acct_set); md_io_acct = container_of(clone, struct md_io_acct, bio_clone); md_io_acct->orig_bio = *bio; md_io_acct->start_time = bio_start_io_acct(*bio); + md_io_acct->mddev = mddev; clone->bi_end_io = md_end_io_acct; clone->bi_private = md_io_acct; @@ -8883,7 +8902,7 @@ void md_do_sync(struct md_thread *thread) atomic_set(&mddev->recovery_active, 0); last_check = 0; - if (j>2) { + if (j >= MD_RESYNC_ACTIVE) { pr_debug("md: resuming %s of %s from checkpoint.\n", desc, mdname(mddev)); mddev->curr_resync = j; @@ -8955,7 +8974,7 @@ void md_do_sync(struct md_thread *thread) if (j > max_sectors) /* when skipping, extra large numbers can be returned. */ j = max_sectors; - if (j > 2) + if (j >= MD_RESYNC_ACTIVE) mddev->curr_resync = j; mddev->curr_mark_cnt = io_sectors; if (last_check == 0) @@ -9030,7 +9049,7 @@ void md_do_sync(struct md_thread *thread) mddev->pers->sync_request(mddev, max_sectors, &skipped); if (!test_bit(MD_RECOVERY_CHECK, &mddev->recovery) && - mddev->curr_resync >= MD_RESYNC_ACTIVE) { + mddev->curr_resync > MD_RESYNC_ACTIVE) { if (test_bit(MD_RECOVERY_SYNC, &mddev->recovery)) { if (test_bit(MD_RECOVERY_INTR, &mddev->recovery)) { if (mddev->curr_resync >= mddev->recovery_cp) { @@ -9259,7 +9278,7 @@ void md_check_recovery(struct mddev *mddev) wake_up(&mddev->sb_wait); } - if (mddev->suspended) + if (is_md_suspended(mddev)) return; if (mddev->bitmap) diff --git a/drivers/md/md.h b/drivers/md/md.h index 554a9026669a..e148e3c83b0d 100644 --- a/drivers/md/md.h +++ b/drivers/md/md.h @@ -315,7 +315,7 @@ struct mddev { unsigned long sb_flags; int suspended; - atomic_t active_io; + struct percpu_ref active_io; int ro; int sysfs_active; /* set when sysfs deletes * are happening, so run/ @@ -710,9 +710,10 @@ struct md_thread { }; struct md_io_acct { - struct bio *orig_bio; - unsigned long start_time; - struct bio bio_clone; + struct mddev *mddev; + struct bio *orig_bio; + unsigned long start_time; + struct bio bio_clone; }; #define THREAD_WAKEUP 0 diff --git a/drivers/nvme/host/auth.c b/drivers/nvme/host/auth.c index bdb97496ba2d..901c59145811 100644 --- a/drivers/nvme/host/auth.c +++ b/drivers/nvme/host/auth.c @@ -160,7 +160,7 @@ static int nvme_auth_process_dhchap_challenge(struct nvme_ctrl *ctrl, if (size > CHAP_BUF_SIZE) { chap->status = NVME_AUTH_DHCHAP_FAILURE_INCORRECT_PAYLOAD; - return NVME_SC_INVALID_FIELD; + return -EINVAL; } hmac_name = nvme_auth_hmac_name(data->hashid); @@ -169,7 +169,7 @@ static int nvme_auth_process_dhchap_challenge(struct nvme_ctrl *ctrl, "qid %d: invalid HASH ID %d\n", chap->qid, data->hashid); chap->status = NVME_AUTH_DHCHAP_FAILURE_HASH_UNUSABLE; - return NVME_SC_INVALID_FIELD; + return -EPROTO; } if (chap->hash_id == data->hashid && chap->shash_tfm && @@ -195,7 +195,7 @@ static int nvme_auth_process_dhchap_challenge(struct nvme_ctrl *ctrl, chap->qid, hmac_name, PTR_ERR(chap->shash_tfm)); chap->shash_tfm = NULL; chap->status = NVME_AUTH_DHCHAP_FAILURE_FAILED; - return NVME_SC_AUTH_REQUIRED; + return -ENOMEM; } if (crypto_shash_digestsize(chap->shash_tfm) != data->hl) { @@ -205,7 +205,7 @@ static int nvme_auth_process_dhchap_challenge(struct nvme_ctrl *ctrl, crypto_free_shash(chap->shash_tfm); chap->shash_tfm = NULL; chap->status = NVME_AUTH_DHCHAP_FAILURE_HASH_UNUSABLE; - return NVME_SC_AUTH_REQUIRED; + return -EPROTO; } chap->hash_id = data->hashid; @@ -221,7 +221,7 @@ select_kpp: chap->qid, data->dhgid); chap->status = NVME_AUTH_DHCHAP_FAILURE_DHGROUP_UNUSABLE; /* Leave previous dh_tfm intact */ - return NVME_SC_AUTH_REQUIRED; + return -EPROTO; } if (chap->dhgroup_id == data->dhgid && @@ -244,7 +244,7 @@ select_kpp: "qid %d: empty DH value\n", chap->qid); chap->status = NVME_AUTH_DHCHAP_FAILURE_DHGROUP_UNUSABLE; - return NVME_SC_INVALID_FIELD; + return -EPROTO; } chap->dh_tfm = crypto_alloc_kpp(kpp_name, 0, 0); @@ -256,7 +256,7 @@ select_kpp: chap->qid, ret, gid_name); chap->status = NVME_AUTH_DHCHAP_FAILURE_DHGROUP_UNUSABLE; chap->dh_tfm = NULL; - return NVME_SC_AUTH_REQUIRED; + return -ret; } dev_dbg(ctrl->device, "qid %d: selected DH group %s\n", chap->qid, gid_name); @@ -265,7 +265,7 @@ select_kpp: "qid %d: invalid DH value for NULL DH\n", chap->qid); chap->status = NVME_AUTH_DHCHAP_FAILURE_INCORRECT_PAYLOAD; - return NVME_SC_INVALID_FIELD; + return -EPROTO; } chap->dhgroup_id = data->dhgid; @@ -276,7 +276,7 @@ skip_kpp: chap->ctrl_key = kmalloc(dhvlen, GFP_KERNEL); if (!chap->ctrl_key) { chap->status = NVME_AUTH_DHCHAP_FAILURE_FAILED; - return NVME_SC_AUTH_REQUIRED; + return -ENOMEM; } chap->ctrl_key_len = dhvlen; memcpy(chap->ctrl_key, data->cval + chap->hash_len, @@ -346,7 +346,7 @@ static int nvme_auth_process_dhchap_success1(struct nvme_ctrl *ctrl, if (size > CHAP_BUF_SIZE) { chap->status = NVME_AUTH_DHCHAP_FAILURE_INCORRECT_PAYLOAD; - return NVME_SC_INVALID_FIELD; + return -EINVAL; } if (data->hl != chap->hash_len) { @@ -354,7 +354,7 @@ static int nvme_auth_process_dhchap_success1(struct nvme_ctrl *ctrl, "qid %d: invalid hash length %u\n", chap->qid, data->hl); chap->status = NVME_AUTH_DHCHAP_FAILURE_HASH_UNUSABLE; - return NVME_SC_INVALID_FIELD; + return -EPROTO; } /* Just print out information for the admin queue */ @@ -378,7 +378,7 @@ static int nvme_auth_process_dhchap_success1(struct nvme_ctrl *ctrl, "qid %d: controller authentication failed\n", chap->qid); chap->status = NVME_AUTH_DHCHAP_FAILURE_FAILED; - return NVME_SC_AUTH_REQUIRED; + return -ECONNREFUSED; } /* Just print out information for the admin queue */ @@ -732,7 +732,7 @@ static void nvme_queue_auth_work(struct work_struct *work) NVME_AUTH_DHCHAP_MESSAGE_CHALLENGE); if (ret) { chap->status = ret; - chap->error = NVME_SC_AUTH_REQUIRED; + chap->error = -ECONNREFUSED; return; } @@ -800,7 +800,7 @@ static void nvme_queue_auth_work(struct work_struct *work) NVME_AUTH_DHCHAP_MESSAGE_SUCCESS1); if (ret) { chap->status = ret; - chap->error = NVME_SC_AUTH_REQUIRED; + chap->error = -ECONNREFUSED; return; } @@ -821,7 +821,7 @@ static void nvme_queue_auth_work(struct work_struct *work) ret = nvme_auth_process_dhchap_success1(ctrl, chap); if (ret) { /* Controller authentication failed */ - chap->error = NVME_SC_AUTH_REQUIRED; + chap->error = -ECONNREFUSED; goto fail2; } diff --git a/drivers/nvme/host/constants.c b/drivers/nvme/host/constants.c index e958d5015585..bc523ca02254 100644 --- a/drivers/nvme/host/constants.c +++ b/drivers/nvme/host/constants.c @@ -54,6 +54,14 @@ static const char * const nvme_admin_ops[] = { [nvme_admin_get_lba_status] = "Get LBA Status", }; +static const char * const nvme_fabrics_ops[] = { + [nvme_fabrics_type_property_set] = "Property Set", + [nvme_fabrics_type_property_get] = "Property Get", + [nvme_fabrics_type_connect] = "Connect", + [nvme_fabrics_type_auth_send] = "Authentication Send", + [nvme_fabrics_type_auth_receive] = "Authentication Receive", +}; + static const char * const nvme_statuses[] = { [NVME_SC_SUCCESS] = "Success", [NVME_SC_INVALID_OPCODE] = "Invalid Command Opcode", @@ -185,3 +193,11 @@ const unsigned char *nvme_get_admin_opcode_str(u8 opcode) return nvme_admin_ops[opcode]; return "Unknown"; } +EXPORT_SYMBOL_GPL(nvme_get_admin_opcode_str); + +const unsigned char *nvme_get_fabrics_opcode_str(u8 opcode) { + if (opcode < ARRAY_SIZE(nvme_fabrics_ops) && nvme_fabrics_ops[opcode]) + return nvme_fabrics_ops[opcode]; + return "Unknown"; +} +EXPORT_SYMBOL_GPL(nvme_get_fabrics_opcode_str); diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 8b6421141162..8698410aeb84 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -806,9 +806,7 @@ static blk_status_t nvme_setup_discard(struct nvme_ns *ns, struct request *req, cmnd->dsm.nr = cpu_to_le32(segments - 1); cmnd->dsm.attributes = cpu_to_le32(NVME_DSMGMT_AD); - req->special_vec.bv_page = virt_to_page(range); - req->special_vec.bv_offset = offset_in_page(range); - req->special_vec.bv_len = alloc_size; + bvec_set_virt(&req->special_vec, range, alloc_size); req->rq_flags |= RQF_SPECIAL_PAYLOAD; return BLK_STS_OK; @@ -1004,7 +1002,7 @@ EXPORT_SYMBOL_GPL(nvme_setup_cmd); * >0: nvme controller's cqe status response * <0: kernel error in lieu of controller response */ -static int nvme_execute_rq(struct request *rq, bool at_head) +int nvme_execute_rq(struct request *rq, bool at_head) { blk_status_t status; @@ -1015,6 +1013,7 @@ static int nvme_execute_rq(struct request *rq, bool at_head) return nvme_req(rq)->status; return blk_status_to_errno(status); } +EXPORT_SYMBOL_NS_GPL(nvme_execute_rq, NVME_TARGET_PASSTHRU); /* * Returns 0 on success. If the result is negative, it's a Linux error code; @@ -1060,41 +1059,12 @@ int nvme_submit_sync_cmd(struct request_queue *q, struct nvme_command *cmd, } EXPORT_SYMBOL_GPL(nvme_submit_sync_cmd); -static u32 nvme_known_admin_effects(u8 opcode) -{ - switch (opcode) { - case nvme_admin_format_nvm: - return NVME_CMD_EFFECTS_LBCC | NVME_CMD_EFFECTS_NCC | - NVME_CMD_EFFECTS_CSE_MASK; - case nvme_admin_sanitize_nvm: - return NVME_CMD_EFFECTS_LBCC | NVME_CMD_EFFECTS_CSE_MASK; - default: - break; - } - return 0; -} - -static u32 nvme_known_nvm_effects(u8 opcode) -{ - switch (opcode) { - case nvme_cmd_write: - case nvme_cmd_write_zeroes: - case nvme_cmd_write_uncor: - return NVME_CMD_EFFECTS_LBCC; - default: - return 0; - } -} - u32 nvme_command_effects(struct nvme_ctrl *ctrl, struct nvme_ns *ns, u8 opcode) { u32 effects = 0; if (ns) { - if (ns->head->effects) - effects = le32_to_cpu(ns->head->effects->iocs[opcode]); - if (ns->head->ids.csi == NVME_CSI_NVM) - effects |= nvme_known_nvm_effects(opcode); + effects = le32_to_cpu(ns->head->effects->iocs[opcode]); if (effects & ~(NVME_CMD_EFFECTS_CSUPP | NVME_CMD_EFFECTS_LBCC)) dev_warn_once(ctrl->device, "IO command:%02x has unusual effects:%08x\n", @@ -1107,17 +1077,14 @@ u32 nvme_command_effects(struct nvme_ctrl *ctrl, struct nvme_ns *ns, u8 opcode) */ effects &= ~NVME_CMD_EFFECTS_CSE_MASK; } else { - if (ctrl->effects) - effects = le32_to_cpu(ctrl->effects->acs[opcode]); - effects |= nvme_known_admin_effects(opcode); + effects = le32_to_cpu(ctrl->effects->acs[opcode]); } return effects; } EXPORT_SYMBOL_NS_GPL(nvme_command_effects, NVME_TARGET_PASSTHRU); -static u32 nvme_passthru_start(struct nvme_ctrl *ctrl, struct nvme_ns *ns, - u8 opcode) +u32 nvme_passthru_start(struct nvme_ctrl *ctrl, struct nvme_ns *ns, u8 opcode) { u32 effects = nvme_command_effects(ctrl, ns, opcode); @@ -1135,6 +1102,7 @@ static u32 nvme_passthru_start(struct nvme_ctrl *ctrl, struct nvme_ns *ns, } return effects; } +EXPORT_SYMBOL_NS_GPL(nvme_passthru_start, NVME_TARGET_PASSTHRU); void nvme_passthru_end(struct nvme_ctrl *ctrl, u32 effects, struct nvme_command *cmd, int status) @@ -1176,17 +1144,6 @@ void nvme_passthru_end(struct nvme_ctrl *ctrl, u32 effects, } EXPORT_SYMBOL_NS_GPL(nvme_passthru_end, NVME_TARGET_PASSTHRU); -int nvme_execute_passthru_rq(struct request *rq, u32 *effects) -{ - struct nvme_command *cmd = nvme_req(rq)->cmd; - struct nvme_ctrl *ctrl = nvme_req(rq)->ctrl; - struct nvme_ns *ns = rq->q->queuedata; - - *effects = nvme_passthru_start(ctrl, ns, cmd->common.opcode); - return nvme_execute_rq(rq, false); -} -EXPORT_SYMBOL_NS_GPL(nvme_execute_passthru_rq, NVME_TARGET_PASSTHRU); - /* * Recommended frequency for KATO commands per NVMe 1.4 section 7.12.1: * @@ -3122,6 +3079,62 @@ free_data: return ret; } +static void nvme_init_known_nvm_effects(struct nvme_ctrl *ctrl) +{ + struct nvme_effects_log *log = ctrl->effects; + + log->acs[nvme_admin_format_nvm] |= cpu_to_le32(NVME_CMD_EFFECTS_LBCC | + NVME_CMD_EFFECTS_NCC | + NVME_CMD_EFFECTS_CSE_MASK); + log->acs[nvme_admin_sanitize_nvm] |= cpu_to_le32(NVME_CMD_EFFECTS_LBCC | + NVME_CMD_EFFECTS_CSE_MASK); + + /* + * The spec says the result of a security receive command depends on + * the previous security send command. As such, many vendors log this + * command as one to submitted only when no other commands to the same + * namespace are outstanding. The intention is to tell the host to + * prevent mixing security send and receive. + * + * This driver can only enforce such exclusive access against IO + * queues, though. We are not readily able to enforce such a rule for + * two commands to the admin queue, which is the only queue that + * matters for this command. + * + * Rather than blindly freezing the IO queues for this effect that + * doesn't even apply to IO, mask it off. + */ + log->acs[nvme_admin_security_recv] &= ~NVME_CMD_EFFECTS_CSE_MASK; + + log->iocs[nvme_cmd_write] |= cpu_to_le32(NVME_CMD_EFFECTS_LBCC); + log->iocs[nvme_cmd_write_zeroes] |= cpu_to_le32(NVME_CMD_EFFECTS_LBCC); + log->iocs[nvme_cmd_write_uncor] |= cpu_to_le32(NVME_CMD_EFFECTS_LBCC); +} + +static int nvme_init_effects(struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id) +{ + int ret = 0; + + if (ctrl->effects) + return 0; + + if (id->lpa & NVME_CTRL_LPA_CMD_EFFECTS_LOG) { + ret = nvme_get_effects_log(ctrl, NVME_CSI_NVM, &ctrl->effects); + if (ret < 0) + return ret; + } + + if (!ctrl->effects) { + ctrl->effects = kzalloc(sizeof(*ctrl->effects), GFP_KERNEL); + if (!ctrl->effects) + return -ENOMEM; + xa_store(&ctrl->cels, NVME_CSI_NVM, ctrl->effects, GFP_KERNEL); + } + + nvme_init_known_nvm_effects(ctrl); + return 0; +} + static int nvme_init_identify(struct nvme_ctrl *ctrl) { struct nvme_id_ctrl *id; @@ -3135,12 +3148,6 @@ static int nvme_init_identify(struct nvme_ctrl *ctrl) return -EIO; } - if (id->lpa & NVME_CTRL_LPA_CMD_EFFECTS_LOG) { - ret = nvme_get_effects_log(ctrl, NVME_CSI_NVM, &ctrl->effects); - if (ret < 0) - goto out_free; - } - if (!(ctrl->ops->flags & NVME_F_FABRICS)) ctrl->cntlid = le16_to_cpu(id->cntlid); @@ -3163,6 +3170,10 @@ static int nvme_init_identify(struct nvme_ctrl *ctrl) ret = nvme_init_subsystem(ctrl, id); if (ret) goto out_free; + + ret = nvme_init_effects(ctrl, id); + if (ret) + goto out_free; } memcpy(ctrl->subsys->firmware_rev, id->fr, sizeof(ctrl->subsys->firmware_rev)); diff --git a/drivers/nvme/host/fabrics.c b/drivers/nvme/host/fabrics.c index ce27276f552d..bbaa04a0c502 100644 --- a/drivers/nvme/host/fabrics.c +++ b/drivers/nvme/host/fabrics.c @@ -410,7 +410,14 @@ int nvmf_connect_admin_queue(struct nvme_ctrl *ctrl) result = le32_to_cpu(res.u32); ctrl->cntlid = result & 0xFFFF; - if ((result >> 16) & 0x3) { + if (result & (NVME_CONNECT_AUTHREQ_ATR | NVME_CONNECT_AUTHREQ_ASCR)) { + /* Secure concatenation is not implemented */ + if (result & NVME_CONNECT_AUTHREQ_ASCR) { + dev_warn(ctrl->device, + "qid 0: secure concatenation is not supported\n"); + ret = NVME_SC_AUTH_REQUIRED; + goto out_free_data; + } /* Authentication required */ ret = nvme_auth_negotiate(ctrl, 0); if (ret) { @@ -486,7 +493,14 @@ int nvmf_connect_io_queue(struct nvme_ctrl *ctrl, u16 qid) &cmd, data); } result = le32_to_cpu(res.u32); - if ((result >> 16) & 2) { + if (result & (NVME_CONNECT_AUTHREQ_ATR | NVME_CONNECT_AUTHREQ_ASCR)) { + /* Secure concatenation is not implemented */ + if (result & NVME_CONNECT_AUTHREQ_ASCR) { + dev_warn(ctrl->device, + "qid 0: secure concatenation is not supported\n"); + ret = NVME_SC_AUTH_REQUIRED; + goto out_free_data; + } /* Authentication required */ ret = nvme_auth_negotiate(ctrl, qid); if (ret) { @@ -500,6 +514,7 @@ int nvmf_connect_io_queue(struct nvme_ctrl *ctrl, u16 qid) "qid %u: authentication failed\n", qid); } } +out_free_data: kfree(data); return ret; } diff --git a/drivers/nvme/host/ioctl.c b/drivers/nvme/host/ioctl.c index 06f52db34be9..723e7d5b778f 100644 --- a/drivers/nvme/host/ioctl.c +++ b/drivers/nvme/host/ioctl.c @@ -219,6 +219,7 @@ static int nvme_submit_user_cmd(struct request_queue *q, void __user *meta_buffer, unsigned meta_len, u32 meta_seed, u64 *result, unsigned timeout, unsigned int flags) { + struct nvme_ns *ns = q->queuedata; struct nvme_ctrl *ctrl; struct request *req; void *meta = NULL; @@ -241,8 +242,8 @@ static int nvme_submit_user_cmd(struct request_queue *q, bio = req->bio; ctrl = nvme_req(req)->ctrl; - ret = nvme_execute_passthru_rq(req, &effects); - + effects = nvme_passthru_start(ctrl, ns, cmd->common.opcode); + ret = nvme_execute_rq(req, false); if (result) *result = le64_to_cpu(nvme_req(req)->result.u64); if (meta) @@ -554,7 +555,7 @@ static int nvme_uring_cmd_io(struct nvme_ctrl *ctrl, struct nvme_ns *ns, struct nvme_uring_data d; struct nvme_command c; struct request *req; - blk_opf_t rq_flags = 0; + blk_opf_t rq_flags = REQ_ALLOC_CACHE; blk_mq_req_flags_t blk_flags = 0; void *meta = NULL; int ret; @@ -590,7 +591,7 @@ static int nvme_uring_cmd_io(struct nvme_ctrl *ctrl, struct nvme_ns *ns, d.timeout_ms = READ_ONCE(cmd->timeout_ms); if (issue_flags & IO_URING_F_NONBLOCK) { - rq_flags = REQ_NOWAIT; + rq_flags |= REQ_NOWAIT; blk_flags = BLK_MQ_REQ_NOWAIT; } if (issue_flags & IO_URING_F_IOPOLL) diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h index 424c8a467a0c..bf46f122e9e1 100644 --- a/drivers/nvme/host/nvme.h +++ b/drivers/nvme/host/nvme.h @@ -1070,7 +1070,8 @@ static inline void nvme_auth_free(struct nvme_ctrl *ctrl) {}; u32 nvme_command_effects(struct nvme_ctrl *ctrl, struct nvme_ns *ns, u8 opcode); -int nvme_execute_passthru_rq(struct request *rq, u32 *effects); +u32 nvme_passthru_start(struct nvme_ctrl *ctrl, struct nvme_ns *ns, u8 opcode); +int nvme_execute_rq(struct request *rq, bool at_head); void nvme_passthru_end(struct nvme_ctrl *ctrl, u32 effects, struct nvme_command *cmd, int status); struct nvme_ctrl *nvme_ctrl_from_file(struct file *file); @@ -1086,6 +1087,7 @@ static inline bool nvme_multi_css(struct nvme_ctrl *ctrl) const unsigned char *nvme_get_error_status_str(u16 status); const unsigned char *nvme_get_opcode_str(u8 opcode); const unsigned char *nvme_get_admin_opcode_str(u8 opcode); +const unsigned char *nvme_get_fabrics_opcode_str(u8 opcode); #else /* CONFIG_NVME_VERBOSE_ERRORS */ static inline const unsigned char *nvme_get_error_status_str(u16 status) { @@ -1099,6 +1101,18 @@ static inline const unsigned char *nvme_get_admin_opcode_str(u8 opcode) { return "Admin Cmd"; } + +static inline const unsigned char *nvme_get_fabrics_opcode_str(u8 opcode) +{ + return "Fabrics Cmd"; +} #endif /* CONFIG_NVME_VERBOSE_ERRORS */ +static inline const unsigned char *nvme_opcode_str(int qid, u8 opcode, u8 fctype) +{ + if (opcode == nvme_fabrics_command) + return nvme_get_fabrics_opcode_str(fctype); + return qid ? nvme_get_opcode_str(opcode) : + nvme_get_admin_opcode_str(opcode); +} #endif /* _NVME_H */ diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index c11e0cfeef0f..5b95c94ee40f 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -42,8 +42,9 @@ * These can be higher, but we need to ensure that any command doesn't * require an sg allocation that needs more than a page of data. */ -#define NVME_MAX_KB_SZ 4096 -#define NVME_MAX_SEGS 127 +#define NVME_MAX_KB_SZ 8192 +#define NVME_MAX_SEGS 128 +#define NVME_MAX_NR_ALLOCATIONS 5 static int use_threaded_interrupts; module_param(use_threaded_interrupts, int, 0444); @@ -216,6 +217,11 @@ struct nvme_queue { struct completion delete_done; }; +union nvme_descriptor { + struct nvme_sgl_desc *sg_list; + __le64 *prp_list; +}; + /* * The nvme_iod describes the data in an I/O. * @@ -225,7 +231,6 @@ struct nvme_queue { struct nvme_iod { struct nvme_request req; struct nvme_command cmd; - bool use_sgl; bool aborted; s8 nr_allocations; /* PRP list pool allocations. 0 means small pool in use */ @@ -233,6 +238,7 @@ struct nvme_iod { dma_addr_t first_dma; dma_addr_t meta_dma; struct sg_table sgt; + union nvme_descriptor list[NVME_MAX_NR_ALLOCATIONS]; }; static inline unsigned int nvme_dbbuf_size(struct nvme_dev *dev) @@ -387,16 +393,6 @@ static int nvme_pci_npages_prp(void) return DIV_ROUND_UP(8 * nprps, NVME_CTRL_PAGE_SIZE - 8); } -/* - * Calculates the number of pages needed for the SGL segments. For example a 4k - * page can accommodate 256 SGL descriptors. - */ -static int nvme_pci_npages_sgl(void) -{ - return DIV_ROUND_UP(NVME_MAX_SEGS * sizeof(struct nvme_sgl_desc), - NVME_CTRL_PAGE_SIZE); -} - static int nvme_admin_init_hctx(struct blk_mq_hw_ctx *hctx, void *data, unsigned int hctx_idx) { @@ -510,16 +506,10 @@ static void nvme_commit_rqs(struct blk_mq_hw_ctx *hctx) spin_unlock(&nvmeq->sq_lock); } -static void **nvme_pci_iod_list(struct request *req) -{ - struct nvme_iod *iod = blk_mq_rq_to_pdu(req); - return (void **)(iod->sgt.sgl + blk_rq_nr_phys_segments(req)); -} - -static inline bool nvme_pci_use_sgls(struct nvme_dev *dev, struct request *req) +static inline bool nvme_pci_use_sgls(struct nvme_dev *dev, struct request *req, + int nseg) { struct nvme_queue *nvmeq = req->mq_hctx->driver_data; - int nseg = blk_rq_nr_phys_segments(req); unsigned int avg_seg_size; avg_seg_size = DIV_ROUND_UP(blk_rq_payload_bytes(req), nseg); @@ -541,7 +531,7 @@ static void nvme_free_prps(struct nvme_dev *dev, struct request *req) int i; for (i = 0; i < iod->nr_allocations; i++) { - __le64 *prp_list = nvme_pci_iod_list(req)[i]; + __le64 *prp_list = iod->list[i].prp_list; dma_addr_t next_dma_addr = le64_to_cpu(prp_list[last_prp]); dma_pool_free(dev->prp_page_pool, prp_list, dma_addr); @@ -549,22 +539,6 @@ static void nvme_free_prps(struct nvme_dev *dev, struct request *req) } } -static void nvme_free_sgls(struct nvme_dev *dev, struct request *req) -{ - const int last_sg = SGES_PER_PAGE - 1; - struct nvme_iod *iod = blk_mq_rq_to_pdu(req); - dma_addr_t dma_addr = iod->first_dma; - int i; - - for (i = 0; i < iod->nr_allocations; i++) { - struct nvme_sgl_desc *sg_list = nvme_pci_iod_list(req)[i]; - dma_addr_t next_dma_addr = le64_to_cpu((sg_list[last_sg]).addr); - - dma_pool_free(dev->prp_page_pool, sg_list, dma_addr); - dma_addr = next_dma_addr; - } -} - static void nvme_unmap_data(struct nvme_dev *dev, struct request *req) { struct nvme_iod *iod = blk_mq_rq_to_pdu(req); @@ -580,10 +554,11 @@ static void nvme_unmap_data(struct nvme_dev *dev, struct request *req) dma_unmap_sgtable(dev->dev, &iod->sgt, rq_dma_dir(req), 0); if (iod->nr_allocations == 0) - dma_pool_free(dev->prp_small_pool, nvme_pci_iod_list(req)[0], + dma_pool_free(dev->prp_small_pool, iod->list[0].sg_list, + iod->first_dma); + else if (iod->nr_allocations == 1) + dma_pool_free(dev->prp_page_pool, iod->list[0].sg_list, iod->first_dma); - else if (iod->use_sgl) - nvme_free_sgls(dev, req); else nvme_free_prps(dev, req); mempool_free(iod->sgt.sgl, dev->iod_mempool); @@ -614,7 +589,6 @@ static blk_status_t nvme_pci_setup_prps(struct nvme_dev *dev, u64 dma_addr = sg_dma_address(sg); int offset = dma_addr & (NVME_CTRL_PAGE_SIZE - 1); __le64 *prp_list; - void **list = nvme_pci_iod_list(req); dma_addr_t prp_dma; int nprps, i; @@ -652,7 +626,7 @@ static blk_status_t nvme_pci_setup_prps(struct nvme_dev *dev, iod->nr_allocations = -1; return BLK_STS_RESOURCE; } - list[0] = prp_list; + iod->list[0].prp_list = prp_list; iod->first_dma = prp_dma; i = 0; for (;;) { @@ -661,7 +635,7 @@ static blk_status_t nvme_pci_setup_prps(struct nvme_dev *dev, prp_list = dma_pool_alloc(pool, GFP_ATOMIC, &prp_dma); if (!prp_list) goto free_prps; - list[iod->nr_allocations++] = prp_list; + iod->list[iod->nr_allocations++].prp_list = prp_list; prp_list[0] = old_prp_list[i - 1]; old_prp_list[i - 1] = cpu_to_le64(prp_dma); i = 1; @@ -706,13 +680,8 @@ static void nvme_pci_sgl_set_seg(struct nvme_sgl_desc *sge, dma_addr_t dma_addr, int entries) { sge->addr = cpu_to_le64(dma_addr); - if (entries < SGES_PER_PAGE) { - sge->length = cpu_to_le32(entries * sizeof(*sge)); - sge->type = NVME_SGL_FMT_LAST_SEG_DESC << 4; - } else { - sge->length = cpu_to_le32(NVME_CTRL_PAGE_SIZE); - sge->type = NVME_SGL_FMT_SEG_DESC << 4; - } + sge->length = cpu_to_le32(entries * sizeof(*sge)); + sge->type = NVME_SGL_FMT_LAST_SEG_DESC << 4; } static blk_status_t nvme_pci_setup_sgls(struct nvme_dev *dev, @@ -748,34 +717,16 @@ static blk_status_t nvme_pci_setup_sgls(struct nvme_dev *dev, return BLK_STS_RESOURCE; } - nvme_pci_iod_list(req)[0] = sg_list; + iod->list[0].sg_list = sg_list; iod->first_dma = sgl_dma; nvme_pci_sgl_set_seg(&cmd->dptr.sgl, sgl_dma, entries); - do { - if (i == SGES_PER_PAGE) { - struct nvme_sgl_desc *old_sg_desc = sg_list; - struct nvme_sgl_desc *link = &old_sg_desc[i - 1]; - - sg_list = dma_pool_alloc(pool, GFP_ATOMIC, &sgl_dma); - if (!sg_list) - goto free_sgls; - - i = 0; - nvme_pci_iod_list(req)[iod->nr_allocations++] = sg_list; - sg_list[i++] = *link; - nvme_pci_sgl_set_seg(link, sgl_dma, entries); - } - nvme_pci_sgl_set_data(&sg_list[i++], sg); sg = sg_next(sg); } while (--entries > 0); return BLK_STS_OK; -free_sgls: - nvme_free_sgls(dev, req); - return BLK_STS_RESOURCE; } static blk_status_t nvme_setup_prp_simple(struct nvme_dev *dev, @@ -857,8 +808,7 @@ static blk_status_t nvme_map_data(struct nvme_dev *dev, struct request *req, goto out_free_sg; } - iod->use_sgl = nvme_pci_use_sgls(dev, req); - if (iod->use_sgl) + if (nvme_pci_use_sgls(dev, req, iod->sgt.nents)) ret = nvme_pci_setup_sgls(dev, req, &cmnd->rw); else ret = nvme_pci_setup_prps(dev, req, &cmnd->rw); @@ -2706,11 +2656,8 @@ static void nvme_release_prp_pools(struct nvme_dev *dev) static int nvme_pci_alloc_iod_mempool(struct nvme_dev *dev) { - size_t npages = max(nvme_pci_npages_prp(), nvme_pci_npages_sgl()); - size_t alloc_size = sizeof(__le64 *) * npages + - sizeof(struct scatterlist) * NVME_MAX_SEGS; + size_t alloc_size = sizeof(struct scatterlist) * NVME_MAX_SEGS; - WARN_ON_ONCE(alloc_size > PAGE_SIZE); dev->iod_mempool = mempool_create_node(1, mempool_kmalloc, mempool_kfree, (void *)alloc_size, GFP_KERNEL, @@ -3538,8 +3485,9 @@ static int __init nvme_init(void) BUILD_BUG_ON(sizeof(struct nvme_create_sq) != 64); BUILD_BUG_ON(sizeof(struct nvme_delete_queue) != 64); BUILD_BUG_ON(IRQ_AFFINITY_MAX_SETS < 2); - BUILD_BUG_ON(DIV_ROUND_UP(nvme_pci_npages_prp(), NVME_CTRL_PAGE_SIZE) > - S8_MAX); + BUILD_BUG_ON(NVME_MAX_SEGS > SGES_PER_PAGE); + BUILD_BUG_ON(sizeof(struct scatterlist) * NVME_MAX_SEGS > PAGE_SIZE); + BUILD_BUG_ON(nvme_pci_npages_prp() > NVME_MAX_NR_ALLOCATIONS); return pci_register_driver(&nvme_driver); } diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c index 8cedc1ef496c..d6100a787d39 100644 --- a/drivers/nvme/host/tcp.c +++ b/drivers/nvme/host/tcp.c @@ -2282,10 +2282,13 @@ static enum blk_eh_timer_return nvme_tcp_timeout(struct request *rq) struct nvme_tcp_request *req = blk_mq_rq_to_pdu(rq); struct nvme_ctrl *ctrl = &req->queue->ctrl->ctrl; struct nvme_tcp_cmd_pdu *pdu = req->pdu; + u8 opc = pdu->cmd.common.opcode, fctype = pdu->cmd.fabrics.fctype; + int qid = nvme_tcp_queue_id(req->queue); dev_warn(ctrl->device, - "queue %d: timeout request %#x type %d\n", - nvme_tcp_queue_id(req->queue), rq->tag, pdu->hdr.type); + "queue %d: timeout cid %#x type %d opcode %#x (%s)\n", + nvme_tcp_queue_id(req->queue), nvme_cid(rq), pdu->hdr.type, + opc, nvme_opcode_str(qid, opc, fctype)); if (ctrl->state != NVME_CTRL_LIVE) { /* diff --git a/drivers/nvme/target/admin-cmd.c b/drivers/nvme/target/admin-cmd.c index 6a54ed6fb121..80099df37314 100644 --- a/drivers/nvme/target/admin-cmd.c +++ b/drivers/nvme/target/admin-cmd.c @@ -840,7 +840,7 @@ void nvmet_execute_set_features(struct nvmet_req *req) u16 nsqr; u16 ncqr; - if (!nvmet_check_transfer_len(req, 0)) + if (!nvmet_check_data_len_lte(req, 0)) return; switch (cdw10 & 0xff) { diff --git a/drivers/nvme/target/io-cmd-file.c b/drivers/nvme/target/io-cmd-file.c index 871c4f32f443..2d068439b129 100644 --- a/drivers/nvme/target/io-cmd-file.c +++ b/drivers/nvme/target/io-cmd-file.c @@ -73,13 +73,6 @@ err: return ret; } -static void nvmet_file_init_bvec(struct bio_vec *bv, struct scatterlist *sg) -{ - bv->bv_page = sg_page(sg); - bv->bv_offset = sg->offset; - bv->bv_len = sg->length; -} - static ssize_t nvmet_file_submit_bvec(struct nvmet_req *req, loff_t pos, unsigned long nr_segs, size_t count, int ki_flags) { @@ -146,7 +139,8 @@ static bool nvmet_file_execute_io(struct nvmet_req *req, int ki_flags) memset(&req->f.iocb, 0, sizeof(struct kiocb)); for_each_sg(req->sg, sg, req->sg_cnt, i) { - nvmet_file_init_bvec(&req->f.bvec[bv_cnt], sg); + bvec_set_page(&req->f.bvec[bv_cnt], sg_page(sg), sg->length, + sg->offset); len += req->f.bvec[bv_cnt].bv_len; total_len += req->f.bvec[bv_cnt].bv_len; bv_cnt++; diff --git a/drivers/nvme/target/passthru.c b/drivers/nvme/target/passthru.c index adc0958755d6..511c980d538d 100644 --- a/drivers/nvme/target/passthru.c +++ b/drivers/nvme/target/passthru.c @@ -216,11 +216,12 @@ static void nvmet_passthru_execute_cmd_work(struct work_struct *w) struct nvmet_req *req = container_of(w, struct nvmet_req, p.work); struct request *rq = req->p.rq; struct nvme_ctrl *ctrl = nvme_req(rq)->ctrl; + struct nvme_ns *ns = rq->q->queuedata; u32 effects; int status; - status = nvme_execute_passthru_rq(rq, &effects); - + effects = nvme_passthru_start(ctrl, ns, req->cmd->common.opcode); + status = nvme_execute_rq(rq, false); if (status == NVME_SC_SUCCESS && req->cmd->common.opcode == nvme_admin_identify) { switch (req->cmd->identify.cns) { diff --git a/drivers/nvme/target/tcp.c b/drivers/nvme/target/tcp.c index cc05c094de22..c5759eb503d0 100644 --- a/drivers/nvme/target/tcp.c +++ b/drivers/nvme/target/tcp.c @@ -321,9 +321,8 @@ static void nvmet_tcp_build_pdu_iovec(struct nvmet_tcp_cmd *cmd) while (length) { u32 iov_len = min_t(u32, length, sg->length - sg_offset); - iov->bv_page = sg_page(sg); - iov->bv_len = sg->length; - iov->bv_offset = sg->offset + sg_offset; + bvec_set_page(iov, sg_page(sg), sg->length, + sg->offset + sg_offset); length -= iov_len; sg = sg_next(sg); diff --git a/drivers/nvme/target/zns.c b/drivers/nvme/target/zns.c index 1254cf57e008..7e4292d88016 100644 --- a/drivers/nvme/target/zns.c +++ b/drivers/nvme/target/zns.c @@ -254,8 +254,7 @@ static unsigned long nvmet_req_nr_zones_from_slba(struct nvmet_req *req) { unsigned int sect = nvmet_lba_to_sect(req->ns, req->cmd->zmr.slba); - return bdev_nr_zones(req->ns->bdev) - - (sect >> ilog2(bdev_zone_sectors(req->ns->bdev))); + return bdev_nr_zones(req->ns->bdev) - bdev_zone_no(req->ns->bdev, sect); } static unsigned long get_nr_zones_from_buf(struct nvmet_req *req, u32 bufsize) diff --git a/drivers/s390/block/dasd.c b/drivers/s390/block/dasd.c index 5a6d9c15395f..a9c2a8d76c45 100644 --- a/drivers/s390/block/dasd.c +++ b/drivers/s390/block/dasd.c @@ -3978,7 +3978,7 @@ static struct dasd_ccw_req *dasd_generic_build_rdc(struct dasd_device *device, ccw = cqr->cpaddr; ccw->cmd_code = CCW_CMD_RDC; - ccw->cda = (__u32)(addr_t) cqr->data; + ccw->cda = (__u32)virt_to_phys(cqr->data); ccw->flags = 0; ccw->count = rdc_buffer_size; cqr->startdev = device; @@ -4022,8 +4022,7 @@ char *dasd_get_sense(struct irb *irb) if (scsw_is_tm(&irb->scsw) && (irb->scsw.tm.fcxs == 0x01)) { if (irb->scsw.tm.tcw) - tsb = tcw_get_tsb((struct tcw *)(unsigned long) - irb->scsw.tm.tcw); + tsb = tcw_get_tsb(phys_to_virt(irb->scsw.tm.tcw)); if (tsb && tsb->length == 64 && tsb->flags) switch (tsb->flags & 0x07) { case 1: /* tsa_iostat */ diff --git a/drivers/s390/block/dasd_3990_erp.c b/drivers/s390/block/dasd_3990_erp.c index 81d283b3cd3b..9fd36c468706 100644 --- a/drivers/s390/block/dasd_3990_erp.c +++ b/drivers/s390/block/dasd_3990_erp.c @@ -220,7 +220,7 @@ dasd_3990_erp_DCTL(struct dasd_ccw_req * erp, char modifier) memset(ccw, 0, sizeof(struct ccw1)); ccw->cmd_code = CCW_CMD_DCTL; ccw->count = 4; - ccw->cda = (__u32)(addr_t) DCTL_data; + ccw->cda = (__u32)virt_to_phys(DCTL_data); dctl_cqr->flags = erp->flags; dctl_cqr->function = dasd_3990_erp_DCTL; dctl_cqr->refers = erp; @@ -1714,7 +1714,7 @@ dasd_3990_erp_action_1B_32(struct dasd_ccw_req * default_erp, char *sense) ccw->cmd_code = DASD_ECKD_CCW_DEFINE_EXTENT; ccw->flags = CCW_FLAG_CC; ccw->count = 16; - ccw->cda = (__u32)(addr_t) DE_data; + ccw->cda = (__u32)virt_to_phys(DE_data); /* create LO ccw */ ccw++; @@ -1722,7 +1722,7 @@ dasd_3990_erp_action_1B_32(struct dasd_ccw_req * default_erp, char *sense) ccw->cmd_code = DASD_ECKD_CCW_LOCATE_RECORD; ccw->flags = CCW_FLAG_CC; ccw->count = 16; - ccw->cda = (__u32)(addr_t) LO_data; + ccw->cda = (__u32)virt_to_phys(LO_data); /* TIC to the failed ccw */ ccw++; @@ -2419,7 +2419,7 @@ static struct dasd_ccw_req *dasd_3990_erp_add_erp(struct dasd_ccw_req *cqr) tcw = erp->cpaddr; tsb = (struct tsb *) &tcw[1]; *tcw = *((struct tcw *)cqr->cpaddr); - tcw->tsb = (long)tsb; + tcw->tsb = virt_to_phys(tsb); } else if (ccw->cmd_code == DASD_ECKD_CCW_PSF) { /* PSF cannot be chained from NOOP/TIC */ erp->cpaddr = cqr->cpaddr; @@ -2430,7 +2430,7 @@ static struct dasd_ccw_req *dasd_3990_erp_add_erp(struct dasd_ccw_req *cqr) ccw->flags = CCW_FLAG_CC; ccw++; ccw->cmd_code = CCW_CMD_TIC; - ccw->cda = (long)(cqr->cpaddr); + ccw->cda = (__u32)virt_to_phys(cqr->cpaddr); } erp->flags = cqr->flags; diff --git a/drivers/s390/block/dasd_alias.c b/drivers/s390/block/dasd_alias.c index b6b938aa6615..c9740ae88d1a 100644 --- a/drivers/s390/block/dasd_alias.c +++ b/drivers/s390/block/dasd_alias.c @@ -443,7 +443,7 @@ static int read_unit_address_configuration(struct dasd_device *device, ccw->cmd_code = DASD_ECKD_CCW_PSF; ccw->count = sizeof(struct dasd_psf_prssd_data); ccw->flags |= CCW_FLAG_CC; - ccw->cda = (__u32)(addr_t) prssdp; + ccw->cda = (__u32)virt_to_phys(prssdp); /* Read Subsystem Data - feature codes */ memset(lcu->uac, 0, sizeof(*(lcu->uac))); @@ -451,7 +451,7 @@ static int read_unit_address_configuration(struct dasd_device *device, ccw++; ccw->cmd_code = DASD_ECKD_CCW_RSSD; ccw->count = sizeof(*(lcu->uac)); - ccw->cda = (__u32)(addr_t) lcu->uac; + ccw->cda = (__u32)virt_to_phys(lcu->uac); cqr->buildclk = get_tod_clock(); cqr->status = DASD_CQR_FILLED; @@ -747,7 +747,7 @@ static int reset_summary_unit_check(struct alias_lcu *lcu, ccw->cmd_code = DASD_ECKD_CCW_RSCK; ccw->flags = CCW_FLAG_SLI; ccw->count = 16; - ccw->cda = (__u32)(addr_t) cqr->data; + ccw->cda = (__u32)virt_to_phys(cqr->data); ((char *)cqr->data)[0] = reason; clear_bit(DASD_CQR_FLAGS_USE_ERP, &cqr->flags); diff --git a/drivers/s390/block/dasd_eckd.c b/drivers/s390/block/dasd_eckd.c index 5d0b9991e91a..1a69f97e88fb 100644 --- a/drivers/s390/block/dasd_eckd.c +++ b/drivers/s390/block/dasd_eckd.c @@ -288,7 +288,7 @@ define_extent(struct ccw1 *ccw, struct DE_eckd_data *data, unsigned int trk, ccw->cmd_code = DASD_ECKD_CCW_DEFINE_EXTENT; ccw->flags = 0; ccw->count = 16; - ccw->cda = (__u32)__pa(data); + ccw->cda = (__u32)virt_to_phys(data); } memset(data, 0, sizeof(struct DE_eckd_data)); @@ -398,7 +398,7 @@ static void locate_record_ext(struct ccw1 *ccw, struct LRE_eckd_data *data, ccw->count = 22; else ccw->count = 20; - ccw->cda = (__u32)__pa(data); + ccw->cda = (__u32)virt_to_phys(data); } memset(data, 0, sizeof(*data)); @@ -544,11 +544,11 @@ static int prefix_LRE(struct ccw1 *ccw, struct PFX_eckd_data *pfxdata, ccw->flags = 0; if (cmd == DASD_ECKD_CCW_WRITE_FULL_TRACK) { ccw->count = sizeof(*pfxdata) + 2; - ccw->cda = (__u32) __pa(pfxdata); + ccw->cda = (__u32)virt_to_phys(pfxdata); memset(pfxdata, 0, sizeof(*pfxdata) + 2); } else { ccw->count = sizeof(*pfxdata); - ccw->cda = (__u32) __pa(pfxdata); + ccw->cda = (__u32)virt_to_phys(pfxdata); memset(pfxdata, 0, sizeof(*pfxdata)); } @@ -615,7 +615,7 @@ locate_record(struct ccw1 *ccw, struct LO_eckd_data *data, unsigned int trk, ccw->cmd_code = DASD_ECKD_CCW_LOCATE_RECORD; ccw->flags = 0; ccw->count = 16; - ccw->cda = (__u32) __pa(data); + ccw->cda = (__u32)virt_to_phys(data); memset(data, 0, sizeof(struct LO_eckd_data)); sector = 0; @@ -830,7 +830,7 @@ static void dasd_eckd_fill_rcd_cqr(struct dasd_device *device, ccw = cqr->cpaddr; ccw->cmd_code = DASD_ECKD_CCW_RCD; ccw->flags = 0; - ccw->cda = (__u32)(addr_t)rcd_buffer; + ccw->cda = (__u32)virt_to_phys(rcd_buffer); ccw->count = DASD_ECKD_RCD_DATA_SIZE; cqr->magic = DASD_ECKD_MAGIC; @@ -858,7 +858,7 @@ static void read_conf_cb(struct dasd_ccw_req *cqr, void *data) if (cqr->status != DASD_CQR_DONE) { ccw = cqr->cpaddr; - rcd_buffer = (__u8 *)((addr_t) ccw->cda); + rcd_buffer = phys_to_virt(ccw->cda); memset(rcd_buffer, 0, sizeof(*rcd_buffer)); rcd_buffer[0] = 0xE5; @@ -1547,7 +1547,7 @@ static int dasd_eckd_read_features(struct dasd_device *device) ccw->cmd_code = DASD_ECKD_CCW_PSF; ccw->count = sizeof(struct dasd_psf_prssd_data); ccw->flags |= CCW_FLAG_CC; - ccw->cda = (__u32)(addr_t) prssdp; + ccw->cda = (__u32)virt_to_phys(prssdp); /* Read Subsystem Data - feature codes */ features = (struct dasd_rssd_features *) (prssdp + 1); @@ -1556,7 +1556,7 @@ static int dasd_eckd_read_features(struct dasd_device *device) ccw++; ccw->cmd_code = DASD_ECKD_CCW_RSSD; ccw->count = sizeof(struct dasd_rssd_features); - ccw->cda = (__u32)(addr_t) features; + ccw->cda = (__u32)virt_to_phys(features); cqr->buildclk = get_tod_clock(); cqr->status = DASD_CQR_FILLED; @@ -1616,7 +1616,7 @@ static int dasd_eckd_read_vol_info(struct dasd_device *device) ccw->cmd_code = DASD_ECKD_CCW_PSF; ccw->count = sizeof(*prssdp); ccw->flags |= CCW_FLAG_CC; - ccw->cda = (__u32)(addr_t)prssdp; + ccw->cda = (__u32)virt_to_phys(prssdp); /* Read Subsystem Data - Volume Storage Query */ vsq = (struct dasd_rssd_vsq *)(prssdp + 1); @@ -1626,7 +1626,7 @@ static int dasd_eckd_read_vol_info(struct dasd_device *device) ccw->cmd_code = DASD_ECKD_CCW_RSSD; ccw->count = sizeof(*vsq); ccw->flags |= CCW_FLAG_SLI; - ccw->cda = (__u32)(addr_t)vsq; + ccw->cda = (__u32)virt_to_phys(vsq); cqr->buildclk = get_tod_clock(); cqr->status = DASD_CQR_FILLED; @@ -1801,7 +1801,7 @@ static int dasd_eckd_read_ext_pool_info(struct dasd_device *device) ccw->cmd_code = DASD_ECKD_CCW_PSF; ccw->count = sizeof(*prssdp); ccw->flags |= CCW_FLAG_CC; - ccw->cda = (__u32)(addr_t)prssdp; + ccw->cda = (__u32)virt_to_phys(prssdp); lcq = (struct dasd_rssd_lcq *)(prssdp + 1); memset(lcq, 0, sizeof(*lcq)); @@ -1810,7 +1810,7 @@ static int dasd_eckd_read_ext_pool_info(struct dasd_device *device) ccw->cmd_code = DASD_ECKD_CCW_RSSD; ccw->count = sizeof(*lcq); ccw->flags |= CCW_FLAG_SLI; - ccw->cda = (__u32)(addr_t)lcq; + ccw->cda = (__u32)virt_to_phys(lcq); cqr->buildclk = get_tod_clock(); cqr->status = DASD_CQR_FILLED; @@ -1907,7 +1907,7 @@ static struct dasd_ccw_req *dasd_eckd_build_psf_ssc(struct dasd_device *device, } ccw = cqr->cpaddr; ccw->cmd_code = DASD_ECKD_CCW_PSF; - ccw->cda = (__u32)(addr_t)psf_ssc_data; + ccw->cda = (__u32)virt_to_phys(psf_ssc_data); ccw->count = 66; cqr->startdev = device; @@ -2262,7 +2262,7 @@ dasd_eckd_analysis_ccw(struct dasd_device *device) ccw->cmd_code = DASD_ECKD_CCW_READ_COUNT; ccw->flags = 0; ccw->count = 8; - ccw->cda = (__u32)(addr_t) count_data; + ccw->cda = (__u32)virt_to_phys(count_data); ccw++; count_data++; } @@ -2276,7 +2276,7 @@ dasd_eckd_analysis_ccw(struct dasd_device *device) ccw->cmd_code = DASD_ECKD_CCW_READ_COUNT; ccw->flags = 0; ccw->count = 8; - ccw->cda = (__u32)(addr_t) count_data; + ccw->cda = (__u32)virt_to_phys(count_data); cqr->block = NULL; cqr->startdev = device; @@ -2647,7 +2647,7 @@ dasd_eckd_build_check(struct dasd_device *base, struct format_data_t *fdata, ccw->cmd_code = DASD_ECKD_CCW_READ_COUNT; ccw->flags = CCW_FLAG_SLI; ccw->count = 8; - ccw->cda = (__u32)(addr_t) fmt_buffer; + ccw->cda = (__u32)virt_to_phys(fmt_buffer); ccw++; fmt_buffer++; } @@ -2857,7 +2857,7 @@ dasd_eckd_build_format(struct dasd_device *base, struct dasd_device *startdev, ccw->cmd_code = DASD_ECKD_CCW_WRITE_RECORD_ZERO; ccw->flags = CCW_FLAG_SLI; ccw->count = 8; - ccw->cda = (__u32)(addr_t) ect; + ccw->cda = (__u32)virt_to_phys(ect); ccw++; } if ((intensity & ~0x08) & 0x04) { /* erase track */ @@ -2872,7 +2872,7 @@ dasd_eckd_build_format(struct dasd_device *base, struct dasd_device *startdev, ccw->cmd_code = DASD_ECKD_CCW_WRITE_CKD; ccw->flags = CCW_FLAG_SLI; ccw->count = 8; - ccw->cda = (__u32)(addr_t) ect; + ccw->cda = (__u32)virt_to_phys(ect); } else { /* write remaining records */ for (i = 0; i < rpt; i++) { ect = (struct eckd_count *) data; @@ -2907,7 +2907,7 @@ dasd_eckd_build_format(struct dasd_device *base, struct dasd_device *startdev, DASD_ECKD_CCW_WRITE_CKD_MT; ccw->flags = CCW_FLAG_SLI; ccw->count = 8; - ccw->cda = (__u32)(addr_t) ect; + ccw->cda = (__u32)virt_to_phys(ect); ccw++; } } @@ -3821,7 +3821,7 @@ dasd_eckd_dso_ras(struct dasd_device *device, struct dasd_block *block, } ccw = cqr->cpaddr; - ccw->cda = (__u32)(addr_t)cqr->data; + ccw->cda = (__u32)virt_to_phys(cqr->data); ccw->cmd_code = DASD_ECKD_CCW_DSO; ccw->count = size; @@ -4090,11 +4090,11 @@ static struct dasd_ccw_req *dasd_eckd_build_cp_cmd_single( ccw->cmd_code = rcmd; ccw->count = count; if (idal_is_needed(dst, blksize)) { - ccw->cda = (__u32)(addr_t) idaws; + ccw->cda = (__u32)virt_to_phys(idaws); ccw->flags = CCW_FLAG_IDA; idaws = idal_create_words(idaws, dst, blksize); } else { - ccw->cda = (__u32)(addr_t) dst; + ccw->cda = (__u32)virt_to_phys(dst); ccw->flags = 0; } ccw++; @@ -4228,7 +4228,7 @@ static struct dasd_ccw_req *dasd_eckd_build_cp_cmd_track( ccw[-1].flags |= CCW_FLAG_CC; ccw->cmd_code = cmd; ccw->count = len_to_track_end; - ccw->cda = (__u32)(addr_t)idaws; + ccw->cda = (__u32)virt_to_phys(idaws); ccw->flags = CCW_FLAG_IDA; ccw++; recid += count; @@ -4244,7 +4244,7 @@ static struct dasd_ccw_req *dasd_eckd_build_cp_cmd_track( * idaw ends */ if (!idaw_dst) { - if (__pa(dst) & (IDA_BLOCK_SIZE-1)) { + if ((__u32)virt_to_phys(dst) & (IDA_BLOCK_SIZE - 1)) { dasd_sfree_request(cqr, startdev); return ERR_PTR(-ERANGE); } else @@ -4264,7 +4264,7 @@ static struct dasd_ccw_req *dasd_eckd_build_cp_cmd_track( * idal_create_words will handle cases where idaw_len * is larger then IDA_BLOCK_SIZE */ - if (!(__pa(idaw_dst + idaw_len) & (IDA_BLOCK_SIZE-1))) + if (!((__u32)virt_to_phys(idaw_dst + idaw_len) & (IDA_BLOCK_SIZE - 1))) end_idaw = 1; /* We also need to end the idaw at track end */ if (!len_to_track_end) { @@ -4817,7 +4817,7 @@ static struct dasd_ccw_req *dasd_eckd_build_cp_raw(struct dasd_device *startdev, ccw->count = 57326; /* 64k map to one track */ len_to_track_end = 65536 - start_padding_sectors * 512; - ccw->cda = (__u32)(addr_t)idaws; + ccw->cda = (__u32)virt_to_phys(idaws); ccw->flags |= CCW_FLAG_IDA; ccw->flags |= CCW_FLAG_SLI; ccw++; @@ -4836,7 +4836,7 @@ static struct dasd_ccw_req *dasd_eckd_build_cp_raw(struct dasd_device *startdev, ccw->count = 57326; /* 64k map to one track */ len_to_track_end = 65536; - ccw->cda = (__u32)(addr_t)idaws; + ccw->cda = (__u32)virt_to_phys(idaws); ccw->flags |= CCW_FLAG_IDA; ccw->flags |= CCW_FLAG_SLI; ccw++; @@ -4893,9 +4893,9 @@ dasd_eckd_free_cp(struct dasd_ccw_req *cqr, struct request *req) ccw++; if (dst) { if (ccw->flags & CCW_FLAG_IDA) - cda = *((char **)((addr_t) ccw->cda)); + cda = *((char **)phys_to_virt(ccw->cda)); else - cda = (char *)((addr_t) ccw->cda); + cda = phys_to_virt(ccw->cda); if (dst != cda) { if (rq_data_dir(req) == READ) memcpy(dst, cda, bv.bv_len); @@ -5045,7 +5045,7 @@ dasd_eckd_release(struct dasd_device *device) ccw->cmd_code = DASD_ECKD_CCW_RELEASE; ccw->flags |= CCW_FLAG_SLI; ccw->count = 32; - ccw->cda = (__u32)(addr_t) cqr->data; + ccw->cda = (__u32)virt_to_phys(cqr->data); cqr->startdev = device; cqr->memdev = device; clear_bit(DASD_CQR_FLAGS_USE_ERP, &cqr->flags); @@ -5100,7 +5100,7 @@ dasd_eckd_reserve(struct dasd_device *device) ccw->cmd_code = DASD_ECKD_CCW_RESERVE; ccw->flags |= CCW_FLAG_SLI; ccw->count = 32; - ccw->cda = (__u32)(addr_t) cqr->data; + ccw->cda = (__u32)virt_to_phys(cqr->data); cqr->startdev = device; cqr->memdev = device; clear_bit(DASD_CQR_FLAGS_USE_ERP, &cqr->flags); @@ -5154,7 +5154,7 @@ dasd_eckd_steal_lock(struct dasd_device *device) ccw->cmd_code = DASD_ECKD_CCW_SLCK; ccw->flags |= CCW_FLAG_SLI; ccw->count = 32; - ccw->cda = (__u32)(addr_t) cqr->data; + ccw->cda = (__u32)virt_to_phys(cqr->data); cqr->startdev = device; cqr->memdev = device; clear_bit(DASD_CQR_FLAGS_USE_ERP, &cqr->flags); @@ -5215,7 +5215,7 @@ static int dasd_eckd_snid(struct dasd_device *device, ccw->cmd_code = DASD_ECKD_CCW_SNID; ccw->flags |= CCW_FLAG_SLI; ccw->count = 12; - ccw->cda = (__u32)(addr_t) cqr->data; + ccw->cda = (__u32)virt_to_phys(cqr->data); cqr->startdev = device; cqr->memdev = device; clear_bit(DASD_CQR_FLAGS_USE_ERP, &cqr->flags); @@ -5282,7 +5282,7 @@ dasd_eckd_performance(struct dasd_device *device, void __user *argp) ccw->cmd_code = DASD_ECKD_CCW_PSF; ccw->count = sizeof(struct dasd_psf_prssd_data); ccw->flags |= CCW_FLAG_CC; - ccw->cda = (__u32)(addr_t) prssdp; + ccw->cda = (__u32)virt_to_phys(prssdp); /* Read Subsystem Data - Performance Statistics */ stats = (struct dasd_rssd_perf_stats_t *) (prssdp + 1); @@ -5291,7 +5291,7 @@ dasd_eckd_performance(struct dasd_device *device, void __user *argp) ccw++; ccw->cmd_code = DASD_ECKD_CCW_RSSD; ccw->count = sizeof(struct dasd_rssd_perf_stats_t); - ccw->cda = (__u32)(addr_t) stats; + ccw->cda = (__u32)virt_to_phys(stats); cqr->buildclk = get_tod_clock(); cqr->status = DASD_CQR_FILLED; @@ -5435,7 +5435,7 @@ static int dasd_symm_io(struct dasd_device *device, void __user *argp) ccw->cmd_code = DASD_ECKD_CCW_PSF; ccw->count = usrparm.psf_data_len; ccw->flags |= CCW_FLAG_CC; - ccw->cda = (__u32)(addr_t) psf_data; + ccw->cda = (__u32)virt_to_phys(psf_data); ccw++; @@ -5443,7 +5443,7 @@ static int dasd_symm_io(struct dasd_device *device, void __user *argp) ccw->cmd_code = DASD_ECKD_CCW_RSSD; ccw->count = usrparm.rssd_result_len; ccw->flags = CCW_FLAG_SLI ; - ccw->cda = (__u32)(addr_t) rssd_result; + ccw->cda = (__u32)virt_to_phys(rssd_result); rc = dasd_sleep_on(cqr); if (rc) @@ -5512,9 +5512,9 @@ dasd_eckd_dump_ccw_range(struct ccw1 *from, struct ccw1 *to, char *page) /* get pointer to data (consider IDALs) */ if (from->flags & CCW_FLAG_IDA) - datap = (char *) *((addr_t *) (addr_t) from->cda); + datap = (char *)*((addr_t *)phys_to_virt(from->cda)); else - datap = (char *) ((addr_t) from->cda); + datap = phys_to_virt(from->cda); /* dump data (max 128 bytes) */ for (count = 0; count < from->count && count < 128; count++) { @@ -5585,7 +5585,7 @@ static void dasd_eckd_dump_sense_ccw(struct dasd_device *device, len += sprintf(page + len, PRINTK_HEADER " device %s: Failing CCW: %p\n", dev_name(&device->cdev->dev), - (void *) (addr_t) irb->scsw.cmd.cpa); + phys_to_virt(irb->scsw.cmd.cpa)); if (irb->esw.esw0.erw.cons) { for (sl = 0; sl < 4; sl++) { len += sprintf(page + len, PRINTK_HEADER @@ -5632,8 +5632,7 @@ static void dasd_eckd_dump_sense_ccw(struct dasd_device *device, /* print failing CCW area (maximum 4) */ /* scsw->cda is either valid or zero */ from = ++to; - fail = (struct ccw1 *)(addr_t) - irb->scsw.cmd.cpa; /* failing CCW */ + fail = phys_to_virt(irb->scsw.cmd.cpa); /* failing CCW */ if (from < fail - 2) { from = fail - 2; /* there is a gap - print header */ printk(KERN_ERR PRINTK_HEADER "......\n"); @@ -5687,13 +5686,12 @@ static void dasd_eckd_dump_sense_tcw(struct dasd_device *device, len += sprintf(page + len, PRINTK_HEADER " device %s: Failing TCW: %p\n", dev_name(&device->cdev->dev), - (void *) (addr_t) irb->scsw.tm.tcw); + phys_to_virt(irb->scsw.tm.tcw)); tsb = NULL; sense = NULL; if (irb->scsw.tm.tcw && (irb->scsw.tm.fcxs & 0x01)) - tsb = tcw_get_tsb( - (struct tcw *)(unsigned long)irb->scsw.tm.tcw); + tsb = tcw_get_tsb(phys_to_virt(irb->scsw.tm.tcw)); if (tsb) { len += sprintf(page + len, PRINTK_HEADER @@ -5917,7 +5915,7 @@ retry: ccw->count = sizeof(struct dasd_psf_prssd_data); ccw->flags |= CCW_FLAG_CC; ccw->flags |= CCW_FLAG_SLI; - ccw->cda = (__u32)(addr_t) prssdp; + ccw->cda = (__u32)virt_to_phys(prssdp); /* Read Subsystem Data - message buffer */ message_buf = (struct dasd_rssd_messages *) (prssdp + 1); @@ -5927,7 +5925,7 @@ retry: ccw->cmd_code = DASD_ECKD_CCW_RSSD; ccw->count = sizeof(struct dasd_rssd_messages); ccw->flags |= CCW_FLAG_SLI; - ccw->cda = (__u32)(addr_t) message_buf; + ccw->cda = (__u32)virt_to_phys(message_buf); cqr->buildclk = get_tod_clock(); cqr->status = DASD_CQR_FILLED; @@ -6008,14 +6006,14 @@ static int dasd_eckd_query_host_access(struct dasd_device *device, ccw->count = sizeof(struct dasd_psf_prssd_data); ccw->flags |= CCW_FLAG_CC; ccw->flags |= CCW_FLAG_SLI; - ccw->cda = (__u32)(addr_t) prssdp; + ccw->cda = (__u32)virt_to_phys(prssdp); /* Read Subsystem Data - query host access */ ccw++; ccw->cmd_code = DASD_ECKD_CCW_RSSD; ccw->count = sizeof(struct dasd_psf_query_host_access); ccw->flags |= CCW_FLAG_SLI; - ccw->cda = (__u32)(addr_t) host_access; + ccw->cda = (__u32)virt_to_phys(host_access); cqr->buildclk = get_tod_clock(); cqr->status = DASD_CQR_FILLED; @@ -6351,7 +6349,7 @@ dasd_eckd_psf_cuir_response(struct dasd_device *device, int response, psf_cuir->ssid = device->path[pos].ssid; ccw = cqr->cpaddr; ccw->cmd_code = DASD_ECKD_CCW_PSF; - ccw->cda = (__u32)(addr_t)psf_cuir; + ccw->cda = (__u32)virt_to_phys(psf_cuir); ccw->flags = CCW_FLAG_SLI; ccw->count = sizeof(struct dasd_psf_cuir_response); @@ -6956,8 +6954,10 @@ dasd_eckd_init(void) return -ENOMEM; dasd_vol_info_req = kmalloc(sizeof(*dasd_vol_info_req), GFP_KERNEL | GFP_DMA); - if (!dasd_vol_info_req) + if (!dasd_vol_info_req) { + kfree(dasd_reserve_req); return -ENOMEM; + } pe_handler_worker = kmalloc(sizeof(*pe_handler_worker), GFP_KERNEL | GFP_DMA); if (!pe_handler_worker) { diff --git a/drivers/s390/block/dasd_eer.c b/drivers/s390/block/dasd_eer.c index d4d31cd11d26..a4cc772208a6 100644 --- a/drivers/s390/block/dasd_eer.c +++ b/drivers/s390/block/dasd_eer.c @@ -491,7 +491,7 @@ int dasd_eer_enable(struct dasd_device *device) ccw->cmd_code = DASD_ECKD_CCW_SNSS; ccw->count = SNSS_DATA_SIZE; ccw->flags = 0; - ccw->cda = (__u32)(addr_t) cqr->data; + ccw->cda = (__u32)virt_to_phys(cqr->data); cqr->buildclk = get_tod_clock(); cqr->status = DASD_CQR_FILLED; diff --git a/drivers/s390/block/dasd_fba.c b/drivers/s390/block/dasd_fba.c index cddfb01a3dca..bcb67fa747a7 100644 --- a/drivers/s390/block/dasd_fba.c +++ b/drivers/s390/block/dasd_fba.c @@ -83,7 +83,7 @@ define_extent(struct ccw1 * ccw, struct DE_fba_data *data, int rw, ccw->cmd_code = DASD_FBA_CCW_DEFINE_EXTENT; ccw->flags = 0; ccw->count = 16; - ccw->cda = (__u32) __pa(data); + ccw->cda = (__u32)virt_to_phys(data); memset(data, 0, sizeof (struct DE_fba_data)); if (rw == WRITE) (data->mask).perm = 0x0; @@ -103,7 +103,7 @@ locate_record(struct ccw1 * ccw, struct LO_fba_data *data, int rw, ccw->cmd_code = DASD_FBA_CCW_LOCATE; ccw->flags = 0; ccw->count = 8; - ccw->cda = (__u32) __pa(data); + ccw->cda = (__u32)virt_to_phys(data); memset(data, 0, sizeof (struct LO_fba_data)); if (rw == WRITE) data->operation.cmd = 0x5; @@ -262,7 +262,7 @@ static void ccw_write_zero(struct ccw1 *ccw, int count) ccw->cmd_code = DASD_FBA_CCW_WRITE; ccw->flags |= CCW_FLAG_SLI; ccw->count = count; - ccw->cda = (__u32) (addr_t) dasd_fba_zero_page; + ccw->cda = (__u32)virt_to_phys(dasd_fba_zero_page); } /* @@ -528,11 +528,11 @@ static struct dasd_ccw_req *dasd_fba_build_cp_regular( ccw->cmd_code = cmd; ccw->count = block->bp_block; if (idal_is_needed(dst, blksize)) { - ccw->cda = (__u32)(addr_t) idaws; + ccw->cda = (__u32)virt_to_phys(idaws); ccw->flags = CCW_FLAG_IDA; idaws = idal_create_words(idaws, dst, blksize); } else { - ccw->cda = (__u32)(addr_t) dst; + ccw->cda = (__u32)virt_to_phys(dst); ccw->flags = 0; } ccw++; @@ -590,9 +590,9 @@ dasd_fba_free_cp(struct dasd_ccw_req *cqr, struct request *req) ccw++; if (dst) { if (ccw->flags & CCW_FLAG_IDA) - cda = *((char **)((addr_t) ccw->cda)); + cda = *((char **)phys_to_virt(ccw->cda)); else - cda = (char *)((addr_t) ccw->cda); + cda = phys_to_virt(ccw->cda); if (dst != cda) { if (rq_data_dir(req) == READ) memcpy(dst, cda, bv.bv_len); diff --git a/drivers/s390/block/dcssblk.c b/drivers/s390/block/dcssblk.c index c0f85ffb2b62..c09f2e053bf8 100644 --- a/drivers/s390/block/dcssblk.c +++ b/drivers/s390/block/dcssblk.c @@ -864,10 +864,6 @@ dcssblk_submit_bio(struct bio *bio) unsigned long source_addr; unsigned long bytes_done; - bio = bio_split_to_limits(bio); - if (!bio) - return; - bytes_done = 0; dev_info = bio->bi_bdev->bd_disk->private_data; if (dev_info == NULL) diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c index 47dafe6b8a66..277960decc10 100644 --- a/drivers/scsi/sd.c +++ b/drivers/scsi/sd.c @@ -831,6 +831,19 @@ static void sd_config_discard(struct scsi_disk *sdkp, unsigned int mode) blk_queue_max_discard_sectors(q, max_blocks * (logical_block_size >> 9)); } +static void *sd_set_special_bvec(struct request *rq, unsigned int data_len) +{ + struct page *page; + + page = mempool_alloc(sd_page_pool, GFP_ATOMIC); + if (!page) + return NULL; + clear_highpage(page); + bvec_set_page(&rq->special_vec, page, data_len, 0); + rq->rq_flags |= RQF_SPECIAL_PAYLOAD; + return bvec_virt(&rq->special_vec); +} + static blk_status_t sd_setup_unmap_cmnd(struct scsi_cmnd *cmd) { struct scsi_device *sdp = cmd->device; @@ -841,19 +854,14 @@ static blk_status_t sd_setup_unmap_cmnd(struct scsi_cmnd *cmd) unsigned int data_len = 24; char *buf; - rq->special_vec.bv_page = mempool_alloc(sd_page_pool, GFP_ATOMIC); - if (!rq->special_vec.bv_page) + buf = sd_set_special_bvec(rq, data_len); + if (!buf) return BLK_STS_RESOURCE; - clear_highpage(rq->special_vec.bv_page); - rq->special_vec.bv_offset = 0; - rq->special_vec.bv_len = data_len; - rq->rq_flags |= RQF_SPECIAL_PAYLOAD; cmd->cmd_len = 10; cmd->cmnd[0] = UNMAP; cmd->cmnd[8] = 24; - buf = bvec_virt(&rq->special_vec); put_unaligned_be16(6 + 16, &buf[0]); put_unaligned_be16(16, &buf[2]); put_unaligned_be64(lba, &buf[8]); @@ -876,13 +884,8 @@ static blk_status_t sd_setup_write_same16_cmnd(struct scsi_cmnd *cmd, u32 nr_blocks = sectors_to_logical(sdp, blk_rq_sectors(rq)); u32 data_len = sdp->sector_size; - rq->special_vec.bv_page = mempool_alloc(sd_page_pool, GFP_ATOMIC); - if (!rq->special_vec.bv_page) + if (!sd_set_special_bvec(rq, data_len)) return BLK_STS_RESOURCE; - clear_highpage(rq->special_vec.bv_page); - rq->special_vec.bv_offset = 0; - rq->special_vec.bv_len = data_len; - rq->rq_flags |= RQF_SPECIAL_PAYLOAD; cmd->cmd_len = 16; cmd->cmnd[0] = WRITE_SAME_16; @@ -908,13 +911,8 @@ static blk_status_t sd_setup_write_same10_cmnd(struct scsi_cmnd *cmd, u32 nr_blocks = sectors_to_logical(sdp, blk_rq_sectors(rq)); u32 data_len = sdp->sector_size; - rq->special_vec.bv_page = mempool_alloc(sd_page_pool, GFP_ATOMIC); - if (!rq->special_vec.bv_page) + if (!sd_set_special_bvec(rq, data_len)) return BLK_STS_RESOURCE; - clear_highpage(rq->special_vec.bv_page); - rq->special_vec.bv_offset = 0; - rq->special_vec.bv_len = data_len; - rq->rq_flags |= RQF_SPECIAL_PAYLOAD; cmd->cmd_len = 10; cmd->cmnd[0] = WRITE_SAME; diff --git a/drivers/target/target_core_file.c b/drivers/target/target_core_file.c index fd584111da45..ce0e000b74fc 100644 --- a/drivers/target/target_core_file.c +++ b/drivers/target/target_core_file.c @@ -281,10 +281,8 @@ fd_execute_rw_aio(struct se_cmd *cmd, struct scatterlist *sgl, u32 sgl_nents, return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE; for_each_sg(sgl, sg, sgl_nents, i) { - aio_cmd->bvecs[i].bv_page = sg_page(sg); - aio_cmd->bvecs[i].bv_len = sg->length; - aio_cmd->bvecs[i].bv_offset = sg->offset; - + bvec_set_page(&aio_cmd->bvecs[i], sg_page(sg), sg->length, + sg->offset); len += sg->length; } @@ -329,10 +327,7 @@ static int fd_do_rw(struct se_cmd *cmd, struct file *fd, } for_each_sg(sgl, sg, sgl_nents, i) { - bvec[i].bv_page = sg_page(sg); - bvec[i].bv_len = sg->length; - bvec[i].bv_offset = sg->offset; - + bvec_set_page(&bvec[i], sg_page(sg), sg->length, sg->offset); len += sg->length; } @@ -465,10 +460,9 @@ fd_execute_write_same(struct se_cmd *cmd) return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE; for (i = 0; i < nolb; i++) { - bvec[i].bv_page = sg_page(&cmd->t_data_sg[0]); - bvec[i].bv_len = cmd->t_data_sg[0].length; - bvec[i].bv_offset = cmd->t_data_sg[0].offset; - + bvec_set_page(&bvec[i], sg_page(&cmd->t_data_sg[0]), + cmd->t_data_sg[0].length, + cmd->t_data_sg[0].offset); len += se_dev->dev_attrib.block_size; } diff --git a/drivers/vhost/vringh.c b/drivers/vhost/vringh.c index 33eb941fcf15..a1e27da54481 100644 --- a/drivers/vhost/vringh.c +++ b/drivers/vhost/vringh.c @@ -1126,9 +1126,8 @@ static int iotlb_translate(const struct vringh *vrh, size = map->size - addr + map->start; pa = map->addr + addr - map->start; pfn = pa >> PAGE_SHIFT; - iov[ret].bv_page = pfn_to_page(pfn); - iov[ret].bv_len = min(len - s, size); - iov[ret].bv_offset = pa & (PAGE_SIZE - 1); + bvec_set_page(&iov[ret], pfn_to_page(pfn), min(len - s, size), + pa & (PAGE_SIZE - 1)); s += size; addr += size; ++ret; diff --git a/fs/afs/write.c b/fs/afs/write.c index 19df10d63323..2d17891b618e 100644 --- a/fs/afs/write.c +++ b/fs/afs/write.c @@ -992,7 +992,7 @@ int afs_launder_folio(struct folio *folio) { struct afs_vnode *vnode = AFS_FS_I(folio_inode(folio)); struct iov_iter iter; - struct bio_vec bv[1]; + struct bio_vec bv; unsigned long priv; unsigned int f, t; int ret = 0; @@ -1008,10 +1008,8 @@ int afs_launder_folio(struct folio *folio) t = afs_folio_dirty_to(folio, priv); } - bv[0].bv_page = &folio->page; - bv[0].bv_offset = f; - bv[0].bv_len = t - f; - iov_iter_bvec(&iter, ITER_SOURCE, bv, 1, bv[0].bv_len); + bvec_set_folio(&bv, folio, t - f, f); + iov_iter_bvec(&iter, ITER_SOURCE, &bv, 1, bv.bv_len); trace_afs_folio_dirty(vnode, tracepoint_string("launder"), folio); ret = afs_store_data(vnode, &iter, folio_pos(folio) + f, true); diff --git a/fs/ceph/file.c b/fs/ceph/file.c index b5cff85925a1..5dcc62e678c4 100644 --- a/fs/ceph/file.c +++ b/fs/ceph/file.c @@ -103,14 +103,10 @@ static ssize_t __iter_get_bvecs(struct iov_iter *iter, size_t maxsize, size += bytes; for ( ; bytes; idx++, bvec_idx++) { - struct bio_vec bv = { - .bv_page = pages[idx], - .bv_len = min_t(int, bytes, PAGE_SIZE - start), - .bv_offset = start, - }; - - bvecs[bvec_idx] = bv; - bytes -= bv.bv_len; + int len = min_t(int, bytes, PAGE_SIZE - start); + + bvec_set_page(&bvecs[bvec_idx], pages[idx], len, start); + bytes -= len; start = 0; } } diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index b2a04b4e89a5..e6088d96eb04 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -759,8 +759,9 @@ cifs_read_page_from_socket(struct TCP_Server_Info *server, struct page *page, unsigned int page_offset, unsigned int to_read) { struct msghdr smb_msg = {}; - struct bio_vec bv = { - .bv_page = page, .bv_len = to_read, .bv_offset = page_offset}; + struct bio_vec bv; + + bvec_set_page(&bv, page, to_read, page_offset); iov_iter_bvec(&smb_msg.msg_iter, ITER_DEST, &bv, 1, to_read); return cifs_readv_from_socket(server, &smb_msg); } diff --git a/fs/cifs/fscache.c b/fs/cifs/fscache.c index f6f3a6b75601..0911327ebfde 100644 --- a/fs/cifs/fscache.c +++ b/fs/cifs/fscache.c @@ -143,14 +143,12 @@ static int fscache_fallback_read_page(struct inode *inode, struct page *page) struct netfs_cache_resources cres; struct fscache_cookie *cookie = cifs_inode_cookie(inode); struct iov_iter iter; - struct bio_vec bvec[1]; + struct bio_vec bvec; int ret; memset(&cres, 0, sizeof(cres)); - bvec[0].bv_page = page; - bvec[0].bv_offset = 0; - bvec[0].bv_len = PAGE_SIZE; - iov_iter_bvec(&iter, ITER_DEST, bvec, ARRAY_SIZE(bvec), PAGE_SIZE); + bvec_set_page(&bvec, page, PAGE_SIZE, 0); + iov_iter_bvec(&iter, ITER_DEST, &bvec, 1, PAGE_SIZE); ret = fscache_begin_read_operation(&cres, cookie); if (ret < 0) @@ -171,16 +169,14 @@ static int fscache_fallback_write_page(struct inode *inode, struct page *page, struct netfs_cache_resources cres; struct fscache_cookie *cookie = cifs_inode_cookie(inode); struct iov_iter iter; - struct bio_vec bvec[1]; + struct bio_vec bvec; loff_t start = page_offset(page); size_t len = PAGE_SIZE; int ret; memset(&cres, 0, sizeof(cres)); - bvec[0].bv_page = page; - bvec[0].bv_offset = 0; - bvec[0].bv_len = PAGE_SIZE; - iov_iter_bvec(&iter, ITER_SOURCE, bvec, ARRAY_SIZE(bvec), PAGE_SIZE); + bvec_set_page(&bvec, page, PAGE_SIZE, 0); + iov_iter_bvec(&iter, ITER_SOURCE, &bvec, 1, PAGE_SIZE); ret = fscache_begin_write_operation(&cres, cookie); if (ret < 0) diff --git a/fs/cifs/misc.c b/fs/cifs/misc.c index 2a19c7987c5b..95cc4d7dd806 100644 --- a/fs/cifs/misc.c +++ b/fs/cifs/misc.c @@ -1054,9 +1054,8 @@ setup_aio_ctx_iter(struct cifs_aio_ctx *ctx, struct iov_iter *iter, int rw) for (i = 0; i < cur_npages; i++) { len = rc > PAGE_SIZE ? PAGE_SIZE : rc; - bv[npages + i].bv_page = pages[i]; - bv[npages + i].bv_offset = start; - bv[npages + i].bv_len = len - start; + bvec_set_page(&bv[npages + i], pages[i], len - start, + start); rc -= len; start = 0; } diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c index e6bcd2baf446..cb2deac6b2d7 100644 --- a/fs/cifs/smb2ops.c +++ b/fs/cifs/smb2ops.c @@ -4598,9 +4598,9 @@ init_read_bvec(struct page **pages, unsigned int npages, unsigned int data_size, return -ENOMEM; for (i = 0; i < npages; i++) { - bvec[i].bv_page = pages[i]; - bvec[i].bv_offset = (i == 0) ? cur_off : 0; - bvec[i].bv_len = min_t(unsigned int, PAGE_SIZE, data_size); + bvec_set_page(&bvec[i], pages[i], + min_t(unsigned int, PAGE_SIZE, data_size), + i == 0 ? cur_off : 0); data_size -= bvec[i].bv_len; } diff --git a/fs/coredump.c b/fs/coredump.c index 68619329ec65..a141dca68165 100644 --- a/fs/coredump.c +++ b/fs/coredump.c @@ -864,11 +864,7 @@ EXPORT_SYMBOL(dump_skip); #ifdef CONFIG_ELF_CORE static int dump_emit_page(struct coredump_params *cprm, struct page *page) { - struct bio_vec bvec = { - .bv_page = page, - .bv_offset = 0, - .bv_len = PAGE_SIZE, - }; + struct bio_vec bvec; struct iov_iter iter; struct file *file = cprm->file; loff_t pos; @@ -884,6 +880,7 @@ static int dump_emit_page(struct coredump_params *cprm, struct page *page) if (dump_interrupted()) return 0; pos = file->f_pos; + bvec_set_page(&bvec, page, PAGE_SIZE, 0); iov_iter_bvec(&iter, ITER_SOURCE, &bvec, 1, PAGE_SIZE); n = __kernel_write_iter(cprm->file, &iter, &pos); if (n != PAGE_SIZE) diff --git a/fs/nfs/fscache.c b/fs/nfs/fscache.c index e731c00a9fcb..ea5f2976dfab 100644 --- a/fs/nfs/fscache.c +++ b/fs/nfs/fscache.c @@ -245,14 +245,12 @@ static int fscache_fallback_read_page(struct inode *inode, struct page *page) struct netfs_cache_resources cres; struct fscache_cookie *cookie = nfs_i_fscache(inode); struct iov_iter iter; - struct bio_vec bvec[1]; + struct bio_vec bvec; int ret; memset(&cres, 0, sizeof(cres)); - bvec[0].bv_page = page; - bvec[0].bv_offset = 0; - bvec[0].bv_len = PAGE_SIZE; - iov_iter_bvec(&iter, ITER_DEST, bvec, ARRAY_SIZE(bvec), PAGE_SIZE); + bvec_set_page(&bvec, page, PAGE_SIZE, 0); + iov_iter_bvec(&iter, ITER_DEST, &bvec, 1, PAGE_SIZE); ret = fscache_begin_read_operation(&cres, cookie); if (ret < 0) @@ -273,16 +271,14 @@ static int fscache_fallback_write_page(struct inode *inode, struct page *page, struct netfs_cache_resources cres; struct fscache_cookie *cookie = nfs_i_fscache(inode); struct iov_iter iter; - struct bio_vec bvec[1]; + struct bio_vec bvec; loff_t start = page_offset(page); size_t len = PAGE_SIZE; int ret; memset(&cres, 0, sizeof(cres)); - bvec[0].bv_page = page; - bvec[0].bv_offset = 0; - bvec[0].bv_len = PAGE_SIZE; - iov_iter_bvec(&iter, ITER_SOURCE, bvec, ARRAY_SIZE(bvec), PAGE_SIZE); + bvec_set_page(&bvec, page, PAGE_SIZE, 0); + iov_iter_bvec(&iter, ITER_SOURCE, &bvec, 1, PAGE_SIZE); ret = fscache_begin_write_operation(&cres, cookie); if (ret < 0) diff --git a/fs/orangefs/inode.c b/fs/orangefs/inode.c index 11e21a0e65ce..c036851a6efe 100644 --- a/fs/orangefs/inode.c +++ b/fs/orangefs/inode.c @@ -49,10 +49,8 @@ static int orangefs_writepage_locked(struct page *page, /* Should've been handled in orangefs_invalidate_folio. */ WARN_ON(off == len || off + wlen > len); - bv.bv_page = page; - bv.bv_len = wlen; - bv.bv_offset = off % PAGE_SIZE; WARN_ON(wlen == 0); + bvec_set_page(&bv, page, wlen, off % PAGE_SIZE); iov_iter_bvec(&iter, ITER_SOURCE, &bv, 1, wlen); ret = wait_for_direct_io(ORANGEFS_IO_WRITE, inode, &off, &iter, wlen, @@ -102,15 +100,11 @@ static int orangefs_writepages_work(struct orangefs_writepages *ow, for (i = 0; i < ow->npages; i++) { set_page_writeback(ow->pages[i]); - ow->bv[i].bv_page = ow->pages[i]; - ow->bv[i].bv_len = min(page_offset(ow->pages[i]) + PAGE_SIZE, - ow->off + ow->len) - - max(ow->off, page_offset(ow->pages[i])); - if (i == 0) - ow->bv[i].bv_offset = ow->off - - page_offset(ow->pages[i]); - else - ow->bv[i].bv_offset = 0; + bvec_set_page(&ow->bv[i], ow->pages[i], + min(page_offset(ow->pages[i]) + PAGE_SIZE, + ow->off + ow->len) - + max(ow->off, page_offset(ow->pages[i])), + i == 0 ? ow->off - page_offset(ow->pages[i]) : 0); } iov_iter_bvec(&iter, ITER_SOURCE, ow->bv, ow->npages, ow->len); @@ -300,9 +294,7 @@ static int orangefs_read_folio(struct file *file, struct folio *folio) orangefs_launder_folio(folio); off = folio_pos(folio); - bv.bv_page = &folio->page; - bv.bv_len = folio_size(folio); - bv.bv_offset = 0; + bvec_set_folio(&bv, folio, folio_size(folio), 0); iov_iter_bvec(&iter, ITER_DEST, &bv, 1, folio_size(folio)); ret = wait_for_direct_io(ORANGEFS_IO_READ, inode, &off, &iter, diff --git a/fs/splice.c b/fs/splice.c index 5969b7a1d353..87d9b19349de 100644 --- a/fs/splice.c +++ b/fs/splice.c @@ -675,9 +675,8 @@ iter_file_splice_write(struct pipe_inode_info *pipe, struct file *out, goto done; } - array[n].bv_page = buf->page; - array[n].bv_len = this_len; - array[n].bv_offset = buf->offset; + bvec_set_page(&array[n], buf->page, this_len, + buf->offset); left -= this_len; n++; } diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 43d4e073b111..b9637d63e6f0 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -288,6 +288,7 @@ struct queue_limits { unsigned int max_dev_sectors; unsigned int chunk_sectors; unsigned int max_sectors; + unsigned int max_user_sectors; unsigned int max_segment_size; unsigned int physical_block_size; unsigned int logical_block_size; @@ -484,6 +485,7 @@ struct request_queue { DECLARE_BITMAP (blkcg_pols, BLKCG_MAX_POLS); struct blkcg_gq *root_blkg; struct list_head blkg_list; + struct mutex blkcg_mutex; #endif struct queue_limits limits; @@ -1095,11 +1097,12 @@ static inline bool bdev_is_partition(struct block_device *bdev) enum blk_default_limits { BLK_MAX_SEGMENTS = 128, BLK_SAFE_MAX_SECTORS = 255, - BLK_DEF_MAX_SECTORS = 2560, BLK_MAX_SEGMENT_SIZE = 65536, BLK_SEG_BOUNDARY_MASK = 0xFFFFFFFFUL, }; +#define BLK_DEF_MAX_SECTORS 2560u + static inline unsigned long queue_segment_boundary(const struct request_queue *q) { return q->limits.seg_boundary_mask; @@ -1283,12 +1286,12 @@ static inline enum blk_zoned_model bdev_zoned_model(struct block_device *bdev) static inline bool bdev_is_zoned(struct block_device *bdev) { - struct request_queue *q = bdev_get_queue(bdev); - - if (q) - return blk_queue_is_zoned(q); + return blk_queue_is_zoned(bdev_get_queue(bdev)); +} - return false; +static inline unsigned int bdev_zone_no(struct block_device *bdev, sector_t sec) +{ + return disk_zone_no(bdev->bd_disk, sec); } static inline bool bdev_op_is_zoned_write(struct block_device *bdev, @@ -1309,6 +1312,18 @@ static inline sector_t bdev_zone_sectors(struct block_device *bdev) return q->limits.chunk_sectors; } +static inline sector_t bdev_offset_from_zone_start(struct block_device *bdev, + sector_t sector) +{ + return sector & (bdev_zone_sectors(bdev) - 1); +} + +static inline bool bdev_is_zone_start(struct block_device *bdev, + sector_t sector) +{ + return bdev_offset_from_zone_start(bdev, sector) == 0; +} + static inline int queue_dma_alignment(const struct request_queue *q) { return q ? q->limits.dma_alignment : 511; diff --git a/include/linux/bvec.h b/include/linux/bvec.h index 35c25dff651a..555aae5448ae 100644 --- a/include/linux/bvec.h +++ b/include/linux/bvec.h @@ -12,7 +12,6 @@ #include <linux/errno.h> #include <linux/limits.h> #include <linux/minmax.h> -#include <linux/mm.h> #include <linux/types.h> struct page; @@ -35,6 +34,46 @@ struct bio_vec { unsigned int bv_offset; }; +/** + * bvec_set_page - initialize a bvec based off a struct page + * @bv: bvec to initialize + * @page: page the bvec should point to + * @len: length of the bvec + * @offset: offset into the page + */ +static inline void bvec_set_page(struct bio_vec *bv, struct page *page, + unsigned int len, unsigned int offset) +{ + bv->bv_page = page; + bv->bv_len = len; + bv->bv_offset = offset; +} + +/** + * bvec_set_folio - initialize a bvec based off a struct folio + * @bv: bvec to initialize + * @folio: folio the bvec should point to + * @len: length of the bvec + * @offset: offset into the folio + */ +static inline void bvec_set_folio(struct bio_vec *bv, struct folio *folio, + unsigned int len, unsigned int offset) +{ + bvec_set_page(bv, &folio->page, len, offset); +} + +/** + * bvec_set_virt - initialize a bvec based on a virtual address + * @bv: bvec to initialize + * @vaddr: virtual address to set the bvec to + * @len: length of the bvec + */ +static inline void bvec_set_virt(struct bio_vec *bv, void *vaddr, + unsigned int len) +{ + bvec_set_page(bv, virt_to_page(vaddr), len, offset_in_page(vaddr)); +} + struct bvec_iter { sector_t bi_sector; /* device address in 512 byte sectors */ diff --git a/include/linux/drbd.h b/include/linux/drbd.h index 5755537b51b1..5468a2399d48 100644 --- a/include/linux/drbd.h +++ b/include/linux/drbd.h @@ -38,13 +38,6 @@ #endif -extern const char *drbd_buildtag(void); -#define REL_VERSION "8.4.11" -#define API_VERSION 1 -#define PRO_VERSION_MIN 86 -#define PRO_VERSION_MAX 101 - - enum drbd_io_error_p { EP_PASS_ON, /* FIXME should the better be named "Ignore"? */ EP_CALL_HELPER, diff --git a/include/linux/drbd_config.h b/include/linux/drbd_config.h new file mode 100644 index 000000000000..d215365c6bb1 --- /dev/null +++ b/include/linux/drbd_config.h @@ -0,0 +1,16 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * drbd_config.h + * DRBD's compile time configuration. + */ + +#ifndef DRBD_CONFIG_H +#define DRBD_CONFIG_H + +extern const char *drbd_buildtag(void); + +#define REL_VERSION "8.4.11" +#define PRO_VERSION_MIN 86 +#define PRO_VERSION_MAX 101 + +#endif diff --git a/include/linux/drbd_genl_api.h b/include/linux/drbd_genl_api.h index bd62efc29002..70682c058027 100644 --- a/include/linux/drbd_genl_api.h +++ b/include/linux/drbd_genl_api.h @@ -47,7 +47,7 @@ enum drbd_state_info_bcast_reason { #undef linux #include <linux/drbd.h> -#define GENL_MAGIC_VERSION API_VERSION +#define GENL_MAGIC_VERSION 1 #define GENL_MAGIC_FAMILY drbd #define GENL_MAGIC_FAMILY_HDRSZ sizeof(struct drbd_genlmsghdr) #define GENL_MAGIC_INCLUDE_FILE <linux/drbd_genl.h> diff --git a/include/linux/drbd_limits.h b/include/linux/drbd_limits.h index 9e33f7038bea..5b042fb427e9 100644 --- a/include/linux/drbd_limits.h +++ b/include/linux/drbd_limits.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: GPL-2.0 */ +/* SPDX-License-Identifier: GPL-2.0-only */ /* drbd_limits.h This file is part of DRBD by Philipp Reisner and Lars Ellenberg. @@ -16,123 +16,123 @@ #define DEBUG_RANGE_CHECK 0 -#define DRBD_MINOR_COUNT_MIN 1 -#define DRBD_MINOR_COUNT_MAX 255 -#define DRBD_MINOR_COUNT_DEF 32 +#define DRBD_MINOR_COUNT_MIN 1U +#define DRBD_MINOR_COUNT_MAX 255U +#define DRBD_MINOR_COUNT_DEF 32U #define DRBD_MINOR_COUNT_SCALE '1' -#define DRBD_VOLUME_MAX 65535 +#define DRBD_VOLUME_MAX 65534U -#define DRBD_DIALOG_REFRESH_MIN 0 -#define DRBD_DIALOG_REFRESH_MAX 600 +#define DRBD_DIALOG_REFRESH_MIN 0U +#define DRBD_DIALOG_REFRESH_MAX 600U #define DRBD_DIALOG_REFRESH_SCALE '1' /* valid port number */ -#define DRBD_PORT_MIN 1 -#define DRBD_PORT_MAX 0xffff +#define DRBD_PORT_MIN 1U +#define DRBD_PORT_MAX 0xffffU #define DRBD_PORT_SCALE '1' /* startup { */ /* if you want more than 3.4 days, disable */ -#define DRBD_WFC_TIMEOUT_MIN 0 -#define DRBD_WFC_TIMEOUT_MAX 300000 -#define DRBD_WFC_TIMEOUT_DEF 0 +#define DRBD_WFC_TIMEOUT_MIN 0U +#define DRBD_WFC_TIMEOUT_MAX 300000U +#define DRBD_WFC_TIMEOUT_DEF 0U #define DRBD_WFC_TIMEOUT_SCALE '1' -#define DRBD_DEGR_WFC_TIMEOUT_MIN 0 -#define DRBD_DEGR_WFC_TIMEOUT_MAX 300000 -#define DRBD_DEGR_WFC_TIMEOUT_DEF 0 +#define DRBD_DEGR_WFC_TIMEOUT_MIN 0U +#define DRBD_DEGR_WFC_TIMEOUT_MAX 300000U +#define DRBD_DEGR_WFC_TIMEOUT_DEF 0U #define DRBD_DEGR_WFC_TIMEOUT_SCALE '1' -#define DRBD_OUTDATED_WFC_TIMEOUT_MIN 0 -#define DRBD_OUTDATED_WFC_TIMEOUT_MAX 300000 -#define DRBD_OUTDATED_WFC_TIMEOUT_DEF 0 +#define DRBD_OUTDATED_WFC_TIMEOUT_MIN 0U +#define DRBD_OUTDATED_WFC_TIMEOUT_MAX 300000U +#define DRBD_OUTDATED_WFC_TIMEOUT_DEF 0U #define DRBD_OUTDATED_WFC_TIMEOUT_SCALE '1' /* }*/ /* net { */ /* timeout, unit centi seconds * more than one minute timeout is not useful */ -#define DRBD_TIMEOUT_MIN 1 -#define DRBD_TIMEOUT_MAX 600 -#define DRBD_TIMEOUT_DEF 60 /* 6 seconds */ +#define DRBD_TIMEOUT_MIN 1U +#define DRBD_TIMEOUT_MAX 600U +#define DRBD_TIMEOUT_DEF 60U /* 6 seconds */ #define DRBD_TIMEOUT_SCALE '1' /* If backing disk takes longer than disk_timeout, mark the disk as failed */ -#define DRBD_DISK_TIMEOUT_MIN 0 /* 0 = disabled */ -#define DRBD_DISK_TIMEOUT_MAX 6000 /* 10 Minutes */ -#define DRBD_DISK_TIMEOUT_DEF 0 /* disabled */ +#define DRBD_DISK_TIMEOUT_MIN 0U /* 0 = disabled */ +#define DRBD_DISK_TIMEOUT_MAX 6000U /* 10 Minutes */ +#define DRBD_DISK_TIMEOUT_DEF 0U /* disabled */ #define DRBD_DISK_TIMEOUT_SCALE '1' /* active connection retries when C_WF_CONNECTION */ -#define DRBD_CONNECT_INT_MIN 1 -#define DRBD_CONNECT_INT_MAX 120 -#define DRBD_CONNECT_INT_DEF 10 /* seconds */ +#define DRBD_CONNECT_INT_MIN 1U +#define DRBD_CONNECT_INT_MAX 120U +#define DRBD_CONNECT_INT_DEF 10U /* seconds */ #define DRBD_CONNECT_INT_SCALE '1' /* keep-alive probes when idle */ -#define DRBD_PING_INT_MIN 1 -#define DRBD_PING_INT_MAX 120 -#define DRBD_PING_INT_DEF 10 +#define DRBD_PING_INT_MIN 1U +#define DRBD_PING_INT_MAX 120U +#define DRBD_PING_INT_DEF 10U #define DRBD_PING_INT_SCALE '1' /* timeout for the ping packets.*/ -#define DRBD_PING_TIMEO_MIN 1 -#define DRBD_PING_TIMEO_MAX 300 -#define DRBD_PING_TIMEO_DEF 5 +#define DRBD_PING_TIMEO_MIN 1U +#define DRBD_PING_TIMEO_MAX 300U +#define DRBD_PING_TIMEO_DEF 5U #define DRBD_PING_TIMEO_SCALE '1' /* max number of write requests between write barriers */ -#define DRBD_MAX_EPOCH_SIZE_MIN 1 -#define DRBD_MAX_EPOCH_SIZE_MAX 20000 -#define DRBD_MAX_EPOCH_SIZE_DEF 2048 +#define DRBD_MAX_EPOCH_SIZE_MIN 1U +#define DRBD_MAX_EPOCH_SIZE_MAX 20000U +#define DRBD_MAX_EPOCH_SIZE_DEF 2048U #define DRBD_MAX_EPOCH_SIZE_SCALE '1' /* I don't think that a tcp send buffer of more than 10M is useful */ -#define DRBD_SNDBUF_SIZE_MIN 0 -#define DRBD_SNDBUF_SIZE_MAX (10<<20) -#define DRBD_SNDBUF_SIZE_DEF 0 +#define DRBD_SNDBUF_SIZE_MIN 0U +#define DRBD_SNDBUF_SIZE_MAX (10U<<20) +#define DRBD_SNDBUF_SIZE_DEF 0U #define DRBD_SNDBUF_SIZE_SCALE '1' -#define DRBD_RCVBUF_SIZE_MIN 0 -#define DRBD_RCVBUF_SIZE_MAX (10<<20) -#define DRBD_RCVBUF_SIZE_DEF 0 +#define DRBD_RCVBUF_SIZE_MIN 0U +#define DRBD_RCVBUF_SIZE_MAX (10U<<20) +#define DRBD_RCVBUF_SIZE_DEF 0U #define DRBD_RCVBUF_SIZE_SCALE '1' /* @4k PageSize -> 128kB - 512MB */ -#define DRBD_MAX_BUFFERS_MIN 32 -#define DRBD_MAX_BUFFERS_MAX 131072 -#define DRBD_MAX_BUFFERS_DEF 2048 +#define DRBD_MAX_BUFFERS_MIN 32U +#define DRBD_MAX_BUFFERS_MAX 131072U +#define DRBD_MAX_BUFFERS_DEF 2048U #define DRBD_MAX_BUFFERS_SCALE '1' /* @4k PageSize -> 4kB - 512MB */ -#define DRBD_UNPLUG_WATERMARK_MIN 1 -#define DRBD_UNPLUG_WATERMARK_MAX 131072 +#define DRBD_UNPLUG_WATERMARK_MIN 1U +#define DRBD_UNPLUG_WATERMARK_MAX 131072U #define DRBD_UNPLUG_WATERMARK_DEF (DRBD_MAX_BUFFERS_DEF/16) #define DRBD_UNPLUG_WATERMARK_SCALE '1' /* 0 is disabled. * 200 should be more than enough even for very short timeouts */ -#define DRBD_KO_COUNT_MIN 0 -#define DRBD_KO_COUNT_MAX 200 -#define DRBD_KO_COUNT_DEF 7 +#define DRBD_KO_COUNT_MIN 0U +#define DRBD_KO_COUNT_MAX 200U +#define DRBD_KO_COUNT_DEF 7U #define DRBD_KO_COUNT_SCALE '1' /* } */ /* syncer { */ /* FIXME allow rate to be zero? */ -#define DRBD_RESYNC_RATE_MIN 1 +#define DRBD_RESYNC_RATE_MIN 1U /* channel bonding 10 GbE, or other hardware */ #define DRBD_RESYNC_RATE_MAX (4 << 20) -#define DRBD_RESYNC_RATE_DEF 250 +#define DRBD_RESYNC_RATE_DEF 250U #define DRBD_RESYNC_RATE_SCALE 'k' /* kilobytes */ -#define DRBD_AL_EXTENTS_MIN 67 +#define DRBD_AL_EXTENTS_MIN 67U /* we use u16 as "slot number", (u16)~0 is "FREE". * If you use >= 292 kB on-disk ring buffer, * this is the maximum you can use: */ -#define DRBD_AL_EXTENTS_MAX 0xfffe -#define DRBD_AL_EXTENTS_DEF 1237 +#define DRBD_AL_EXTENTS_MAX 0xfffeU +#define DRBD_AL_EXTENTS_DEF 1237U #define DRBD_AL_EXTENTS_SCALE '1' #define DRBD_MINOR_NUMBER_MIN -1 @@ -147,9 +147,9 @@ * the upper limit with 64bit kernel, enough ram and flexible meta data * is 1 PiB, currently. */ /* DRBD_MAX_SECTORS */ -#define DRBD_DISK_SIZE_MIN 0 -#define DRBD_DISK_SIZE_MAX (1 * (2LLU << 40)) -#define DRBD_DISK_SIZE_DEF 0 /* = disabled = no user size... */ +#define DRBD_DISK_SIZE_MIN 0LLU +#define DRBD_DISK_SIZE_MAX (1LLU * (2LLU << 40)) +#define DRBD_DISK_SIZE_DEF 0LLU /* = disabled = no user size... */ #define DRBD_DISK_SIZE_SCALE 's' /* sectors */ #define DRBD_ON_IO_ERROR_DEF EP_DETACH @@ -162,39 +162,39 @@ #define DRBD_ON_CONGESTION_DEF OC_BLOCK #define DRBD_READ_BALANCING_DEF RB_PREFER_LOCAL -#define DRBD_MAX_BIO_BVECS_MIN 0 -#define DRBD_MAX_BIO_BVECS_MAX 128 -#define DRBD_MAX_BIO_BVECS_DEF 0 +#define DRBD_MAX_BIO_BVECS_MIN 0U +#define DRBD_MAX_BIO_BVECS_MAX 128U +#define DRBD_MAX_BIO_BVECS_DEF 0U #define DRBD_MAX_BIO_BVECS_SCALE '1' -#define DRBD_C_PLAN_AHEAD_MIN 0 -#define DRBD_C_PLAN_AHEAD_MAX 300 -#define DRBD_C_PLAN_AHEAD_DEF 20 +#define DRBD_C_PLAN_AHEAD_MIN 0U +#define DRBD_C_PLAN_AHEAD_MAX 300U +#define DRBD_C_PLAN_AHEAD_DEF 20U #define DRBD_C_PLAN_AHEAD_SCALE '1' -#define DRBD_C_DELAY_TARGET_MIN 1 -#define DRBD_C_DELAY_TARGET_MAX 100 -#define DRBD_C_DELAY_TARGET_DEF 10 +#define DRBD_C_DELAY_TARGET_MIN 1U +#define DRBD_C_DELAY_TARGET_MAX 100U +#define DRBD_C_DELAY_TARGET_DEF 10U #define DRBD_C_DELAY_TARGET_SCALE '1' -#define DRBD_C_FILL_TARGET_MIN 0 -#define DRBD_C_FILL_TARGET_MAX (1<<20) /* 500MByte in sec */ -#define DRBD_C_FILL_TARGET_DEF 100 /* Try to place 50KiB in socket send buffer during resync */ +#define DRBD_C_FILL_TARGET_MIN 0U +#define DRBD_C_FILL_TARGET_MAX (1U<<20) /* 500MByte in sec */ +#define DRBD_C_FILL_TARGET_DEF 100U /* Try to place 50KiB in socket send buffer during resync */ #define DRBD_C_FILL_TARGET_SCALE 's' /* sectors */ -#define DRBD_C_MAX_RATE_MIN 250 -#define DRBD_C_MAX_RATE_MAX (4 << 20) -#define DRBD_C_MAX_RATE_DEF 102400 +#define DRBD_C_MAX_RATE_MIN 250U +#define DRBD_C_MAX_RATE_MAX (4U << 20) +#define DRBD_C_MAX_RATE_DEF 102400U #define DRBD_C_MAX_RATE_SCALE 'k' /* kilobytes */ -#define DRBD_C_MIN_RATE_MIN 0 -#define DRBD_C_MIN_RATE_MAX (4 << 20) -#define DRBD_C_MIN_RATE_DEF 250 +#define DRBD_C_MIN_RATE_MIN 0U +#define DRBD_C_MIN_RATE_MAX (4U << 20) +#define DRBD_C_MIN_RATE_DEF 250U #define DRBD_C_MIN_RATE_SCALE 'k' /* kilobytes */ -#define DRBD_CONG_FILL_MIN 0 -#define DRBD_CONG_FILL_MAX (10<<21) /* 10GByte in sectors */ -#define DRBD_CONG_FILL_DEF 0 +#define DRBD_CONG_FILL_MIN 0U +#define DRBD_CONG_FILL_MAX (10U<<21) /* 10GByte in sectors */ +#define DRBD_CONG_FILL_DEF 0U #define DRBD_CONG_FILL_SCALE 's' /* sectors */ #define DRBD_CONG_EXTENTS_MIN DRBD_AL_EXTENTS_MIN @@ -204,48 +204,48 @@ #define DRBD_PROTOCOL_DEF DRBD_PROT_C -#define DRBD_DISK_BARRIER_DEF 0 -#define DRBD_DISK_FLUSHES_DEF 1 -#define DRBD_DISK_DRAIN_DEF 1 -#define DRBD_MD_FLUSHES_DEF 1 -#define DRBD_TCP_CORK_DEF 1 -#define DRBD_AL_UPDATES_DEF 1 +#define DRBD_DISK_BARRIER_DEF 0U +#define DRBD_DISK_FLUSHES_DEF 1U +#define DRBD_DISK_DRAIN_DEF 1U +#define DRBD_MD_FLUSHES_DEF 1U +#define DRBD_TCP_CORK_DEF 1U +#define DRBD_AL_UPDATES_DEF 1U /* We used to ignore the discard_zeroes_data setting. * To not change established (and expected) behaviour, * by default assume that, for discard_zeroes_data=0, * we can make that an effective discard_zeroes_data=1, * if we only explicitly zero-out unaligned partial chunks. */ -#define DRBD_DISCARD_ZEROES_IF_ALIGNED_DEF 1 +#define DRBD_DISCARD_ZEROES_IF_ALIGNED_DEF 1U /* Some backends pretend to support WRITE SAME, * but fail such requests when they are actually submitted. * This is to tell DRBD to not even try. */ -#define DRBD_DISABLE_WRITE_SAME_DEF 0 +#define DRBD_DISABLE_WRITE_SAME_DEF 0U -#define DRBD_ALLOW_TWO_PRIMARIES_DEF 0 -#define DRBD_ALWAYS_ASBP_DEF 0 -#define DRBD_USE_RLE_DEF 1 -#define DRBD_CSUMS_AFTER_CRASH_ONLY_DEF 0 +#define DRBD_ALLOW_TWO_PRIMARIES_DEF 0U +#define DRBD_ALWAYS_ASBP_DEF 0U +#define DRBD_USE_RLE_DEF 1U +#define DRBD_CSUMS_AFTER_CRASH_ONLY_DEF 0U -#define DRBD_AL_STRIPES_MIN 1 -#define DRBD_AL_STRIPES_MAX 1024 -#define DRBD_AL_STRIPES_DEF 1 +#define DRBD_AL_STRIPES_MIN 1U +#define DRBD_AL_STRIPES_MAX 1024U +#define DRBD_AL_STRIPES_DEF 1U #define DRBD_AL_STRIPES_SCALE '1' -#define DRBD_AL_STRIPE_SIZE_MIN 4 -#define DRBD_AL_STRIPE_SIZE_MAX 16777216 -#define DRBD_AL_STRIPE_SIZE_DEF 32 +#define DRBD_AL_STRIPE_SIZE_MIN 4U +#define DRBD_AL_STRIPE_SIZE_MAX 16777216U +#define DRBD_AL_STRIPE_SIZE_DEF 32U #define DRBD_AL_STRIPE_SIZE_SCALE 'k' /* kilobytes */ -#define DRBD_SOCKET_CHECK_TIMEO_MIN 0 +#define DRBD_SOCKET_CHECK_TIMEO_MIN 0U #define DRBD_SOCKET_CHECK_TIMEO_MAX DRBD_PING_TIMEO_MAX -#define DRBD_SOCKET_CHECK_TIMEO_DEF 0 +#define DRBD_SOCKET_CHECK_TIMEO_DEF 0U #define DRBD_SOCKET_CHECK_TIMEO_SCALE '1' -#define DRBD_RS_DISCARD_GRANULARITY_MIN 0 -#define DRBD_RS_DISCARD_GRANULARITY_MAX (1<<20) /* 1MiByte */ -#define DRBD_RS_DISCARD_GRANULARITY_DEF 0 /* disabled by default */ +#define DRBD_RS_DISCARD_GRANULARITY_MIN 0U +#define DRBD_RS_DISCARD_GRANULARITY_MAX (1U<<20) /* 1MiByte */ +#define DRBD_RS_DISCARD_GRANULARITY_DEF 0U /* disabled by default */ #define DRBD_RS_DISCARD_GRANULARITY_SCALE '1' /* bytes */ #endif diff --git a/include/linux/sched.h b/include/linux/sched.h index 853d08f7562b..6f6ce9ca7097 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1436,7 +1436,7 @@ struct task_struct { #endif #ifdef CONFIG_BLK_CGROUP - struct request_queue *throttle_queue; + struct gendisk *throttle_disk; #endif #ifdef CONFIG_UPROBES diff --git a/include/uapi/linux/ublk_cmd.h b/include/uapi/linux/ublk_cmd.h index 8f88e3a29998..f6238ccc7800 100644 --- a/include/uapi/linux/ublk_cmd.h +++ b/include/uapi/linux/ublk_cmd.h @@ -19,6 +19,8 @@ #define UBLK_CMD_GET_PARAMS 0x09 #define UBLK_CMD_START_USER_RECOVERY 0x10 #define UBLK_CMD_END_USER_RECOVERY 0x11 +#define UBLK_CMD_GET_DEV_INFO2 0x12 + /* * IO commands, issued by ublk server, and handled by ublk driver. * @@ -79,6 +81,27 @@ #define UBLK_F_USER_RECOVERY_REISSUE (1UL << 4) +/* + * Unprivileged user can create /dev/ublkcN and /dev/ublkbN. + * + * /dev/ublk-control needs to be available for unprivileged user, and it + * can be done via udev rule to make all control commands available to + * unprivileged user. Except for the command of UBLK_CMD_ADD_DEV, all + * other commands are only allowed for the owner of the specified device. + * + * When userspace sends UBLK_CMD_ADD_DEV, the device pair's owner_uid and + * owner_gid are stored to ublksrv_ctrl_dev_info by kernel, so far only + * the current user's uid/gid is stored, that said owner of the created + * device is always the current user. + * + * We still need udev rule to apply OWNER/GROUP with the stored owner_uid + * and owner_gid. + * + * Then ublk server can be run as unprivileged user, and /dev/ublkbN can + * be accessed and managed by its owner represented by owner_uid/owner_gid. + */ +#define UBLK_F_UNPRIVILEGED_DEV (1UL << 5) + /* device state */ #define UBLK_S_DEV_DEAD 0 #define UBLK_S_DEV_LIVE 1 @@ -98,7 +121,15 @@ struct ublksrv_ctrl_cmd { __u64 addr; /* inline data */ - __u64 data[2]; + __u64 data[1]; + + /* + * Used for UBLK_F_UNPRIVILEGED_DEV and UBLK_CMD_GET_DEV_INFO2 + * only, include null char + */ + __u16 dev_path_len; + __u16 pad; + __u32 reserved; }; struct ublksrv_ctrl_dev_info { @@ -118,7 +149,8 @@ struct ublksrv_ctrl_dev_info { /* For ublksrv internal use, invisible to ublk driver */ __u64 ublksrv_flags; - __u64 reserved0; + __u32 owner_uid; /* store by kernel */ + __u32 owner_gid; /* store by kernel */ __u64 reserved1; __u64 reserved2; }; @@ -214,6 +246,17 @@ struct ublk_param_discard { __u16 reserved0; }; +/* + * read-only, can't set via UBLK_CMD_SET_PARAMS, disk_devt is available + * after device is started + */ +struct ublk_param_devt { + __u32 char_major; + __u32 char_minor; + __u32 disk_major; + __u32 disk_minor; +}; + struct ublk_params { /* * Total length of parameters, userspace has to set 'len' for both @@ -224,10 +267,12 @@ struct ublk_params { __u32 len; #define UBLK_PARAM_TYPE_BASIC (1 << 0) #define UBLK_PARAM_TYPE_DISCARD (1 << 1) +#define UBLK_PARAM_TYPE_DEVT (1 << 2) __u32 types; /* types of parameter included */ struct ublk_param_basic basic; struct ublk_param_discard discard; + struct ublk_param_devt devt; }; #endif diff --git a/io_uring/rsrc.c b/io_uring/rsrc.c index 18de10c68a15..a59fc02de598 100644 --- a/io_uring/rsrc.c +++ b/io_uring/rsrc.c @@ -1237,9 +1237,7 @@ static int io_sqe_buffer_register(struct io_ring_ctx *ctx, struct iovec *iov, size_t vec_len; vec_len = min_t(size_t, size, PAGE_SIZE - off); - imu->bvec[i].bv_page = pages[i]; - imu->bvec[i].bv_len = vec_len; - imu->bvec[i].bv_offset = off; + bvec_set_page(&imu->bvec[i], pages[i], vec_len, off); off = 0; size -= vec_len; } diff --git a/kernel/fork.c b/kernel/fork.c index 9f7fe3541897..d9c97704b7c9 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1044,7 +1044,7 @@ static struct task_struct *dup_task_struct(struct task_struct *orig, int node) #endif #ifdef CONFIG_BLK_CGROUP - tsk->throttle_queue = NULL; + tsk->throttle_disk = NULL; tsk->use_memdelay = 0; #endif diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c index 918a7d12df8f..5743be559415 100644 --- a/kernel/trace/blktrace.c +++ b/kernel/trace/blktrace.c @@ -320,8 +320,8 @@ static void blk_trace_free(struct request_queue *q, struct blk_trace *bt) * under 'q->debugfs_dir', thus lookup and remove them. */ if (!bt->dir) { - debugfs_remove(debugfs_lookup("dropped", q->debugfs_dir)); - debugfs_remove(debugfs_lookup("msg", q->debugfs_dir)); + debugfs_lookup_and_remove("dropped", q->debugfs_dir); + debugfs_lookup_and_remove("msg", q->debugfs_dir); } else { debugfs_remove(bt->dir); } diff --git a/lib/sbitmap.c b/lib/sbitmap.c index 1fcede228fa2..eff4e42c425a 100644 --- a/lib/sbitmap.c +++ b/lib/sbitmap.c @@ -167,15 +167,16 @@ static int __sbitmap_get_word(unsigned long *word, unsigned long depth, return nr; } -static int sbitmap_find_bit_in_index(struct sbitmap *sb, int index, - unsigned int alloc_hint) +static int sbitmap_find_bit_in_word(struct sbitmap_word *map, + unsigned int depth, + unsigned int alloc_hint, + bool wrap) { - struct sbitmap_word *map = &sb->map[index]; int nr; do { - nr = __sbitmap_get_word(&map->word, __map_depth(sb, index), - alloc_hint, !sb->round_robin); + nr = __sbitmap_get_word(&map->word, depth, + alloc_hint, wrap); if (nr != -1) break; if (!sbitmap_deferred_clear(map)) @@ -185,25 +186,22 @@ static int sbitmap_find_bit_in_index(struct sbitmap *sb, int index, return nr; } -static int __sbitmap_get(struct sbitmap *sb, unsigned int alloc_hint) +static int sbitmap_find_bit(struct sbitmap *sb, + unsigned int depth, + unsigned int index, + unsigned int alloc_hint, + bool wrap) { - unsigned int i, index; + unsigned int i; int nr = -1; - index = SB_NR_TO_INDEX(sb, alloc_hint); - - /* - * Unless we're doing round robin tag allocation, just use the - * alloc_hint to find the right word index. No point in looping - * twice in find_next_zero_bit() for that case. - */ - if (sb->round_robin) - alloc_hint = SB_NR_TO_BIT(sb, alloc_hint); - else - alloc_hint = 0; - for (i = 0; i < sb->map_nr; i++) { - nr = sbitmap_find_bit_in_index(sb, index, alloc_hint); + nr = sbitmap_find_bit_in_word(&sb->map[index], + min_t(unsigned int, + __map_depth(sb, index), + depth), + alloc_hint, wrap); + if (nr != -1) { nr += index << sb->shift; break; @@ -218,6 +216,26 @@ static int __sbitmap_get(struct sbitmap *sb, unsigned int alloc_hint) return nr; } +static int __sbitmap_get(struct sbitmap *sb, unsigned int alloc_hint) +{ + unsigned int index; + + index = SB_NR_TO_INDEX(sb, alloc_hint); + + /* + * Unless we're doing round robin tag allocation, just use the + * alloc_hint to find the right word index. No point in looping + * twice in find_next_zero_bit() for that case. + */ + if (sb->round_robin) + alloc_hint = SB_NR_TO_BIT(sb, alloc_hint); + else + alloc_hint = 0; + + return sbitmap_find_bit(sb, UINT_MAX, index, alloc_hint, + !sb->round_robin); +} + int sbitmap_get(struct sbitmap *sb) { int nr; @@ -239,37 +257,12 @@ static int __sbitmap_get_shallow(struct sbitmap *sb, unsigned int alloc_hint, unsigned long shallow_depth) { - unsigned int i, index; - int nr = -1; + unsigned int index; index = SB_NR_TO_INDEX(sb, alloc_hint); + alloc_hint = SB_NR_TO_BIT(sb, alloc_hint); - for (i = 0; i < sb->map_nr; i++) { -again: - nr = __sbitmap_get_word(&sb->map[index].word, - min_t(unsigned int, - __map_depth(sb, index), - shallow_depth), - SB_NR_TO_BIT(sb, alloc_hint), true); - if (nr != -1) { - nr += index << sb->shift; - break; - } - - if (sbitmap_deferred_clear(&sb->map[index])) - goto again; - - /* Jump to next index. */ - index++; - alloc_hint = index << sb->shift; - - if (index >= sb->map_nr) { - index = 0; - alloc_hint = 0; - } - } - - return nr; + return sbitmap_find_bit(sb, shallow_depth, index, alloc_hint, true); } int sbitmap_get_shallow(struct sbitmap *sb, unsigned long shallow_depth) @@ -464,13 +457,10 @@ void sbitmap_queue_recalculate_wake_batch(struct sbitmap_queue *sbq, unsigned int users) { unsigned int wake_batch; - unsigned int min_batch; unsigned int depth = (sbq->sb.depth + users - 1) / users; - min_batch = sbq->sb.depth >= (4 * SBQ_WAIT_QUEUES) ? 4 : 1; - wake_batch = clamp_val(depth / SBQ_WAIT_QUEUES, - min_batch, SBQ_WAKE_BATCH); + 1, SBQ_WAKE_BATCH); WRITE_ONCE(sbq->wake_batch, wake_batch); } @@ -521,11 +511,9 @@ unsigned long __sbitmap_queue_get_batch(struct sbitmap_queue *sbq, int nr_tags, get_mask = ((1UL << nr_tags) - 1) << nr; val = READ_ONCE(map->word); - do { - if ((val & ~get_mask) != val) - goto next; - } while (!atomic_long_try_cmpxchg(ptr, &val, - get_mask | val)); + while (!atomic_long_try_cmpxchg(ptr, &val, + get_mask | val)) + ; get_mask = (get_mask & ~val) >> nr; if (get_mask) { *offset = nr + (index << sb->shift); diff --git a/mm/page_io.c b/mm/page_io.c index 3a5f921b932e..233f6e6eb1c5 100644 --- a/mm/page_io.c +++ b/mm/page_io.c @@ -318,9 +318,7 @@ static int swap_writepage_fs(struct page *page, struct writeback_control *wbc) sio->pages = 0; sio->len = 0; } - sio->bvec[sio->pages].bv_page = page; - sio->bvec[sio->pages].bv_len = thp_size(page); - sio->bvec[sio->pages].bv_offset = 0; + bvec_set_page(&sio->bvec[sio->pages], page, thp_size(page), 0); sio->len += thp_size(page); sio->pages += 1; if (sio->pages == ARRAY_SIZE(sio->bvec) || !wbc->swap_plug) { @@ -432,9 +430,7 @@ static void swap_readpage_fs(struct page *page, sio->pages = 0; sio->len = 0; } - sio->bvec[sio->pages].bv_page = page; - sio->bvec[sio->pages].bv_len = thp_size(page); - sio->bvec[sio->pages].bv_offset = 0; + bvec_set_page(&sio->bvec[sio->pages], page, thp_size(page), 0); sio->len += thp_size(page); sio->pages += 1; if (sio->pages == ARRAY_SIZE(sio->bvec) || !plug) { diff --git a/mm/swapfile.c b/mm/swapfile.c index eb9b0bf1fcdd..0ab52d16bde6 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -3651,7 +3651,7 @@ void __cgroup_throttle_swaprate(struct page *page, gfp_t gfp_mask) * We've already scheduled a throttle, avoid taking the global swap * lock. */ - if (current->throttle_queue) + if (current->throttle_disk) return; spin_lock(&swap_avail_lock); diff --git a/net/ceph/messenger_v1.c b/net/ceph/messenger_v1.c index d1787d7d33ef..d664cb1593a7 100644 --- a/net/ceph/messenger_v1.c +++ b/net/ceph/messenger_v1.c @@ -40,15 +40,12 @@ static int ceph_tcp_recvmsg(struct socket *sock, void *buf, size_t len) static int ceph_tcp_recvpage(struct socket *sock, struct page *page, int page_offset, size_t length) { - struct bio_vec bvec = { - .bv_page = page, - .bv_offset = page_offset, - .bv_len = length - }; + struct bio_vec bvec; struct msghdr msg = { .msg_flags = MSG_DONTWAIT | MSG_NOSIGNAL }; int r; BUG_ON(page_offset + length > PAGE_SIZE); + bvec_set_page(&bvec, page, length, page_offset); iov_iter_bvec(&msg.msg_iter, ITER_DEST, &bvec, 1, length); r = sock_recvmsg(sock, &msg, msg.msg_flags); if (r == -EAGAIN) diff --git a/net/ceph/messenger_v2.c b/net/ceph/messenger_v2.c index 3009028c4fa2..301a991dc6a6 100644 --- a/net/ceph/messenger_v2.c +++ b/net/ceph/messenger_v2.c @@ -149,10 +149,10 @@ static int do_try_sendpage(struct socket *sock, struct iov_iter *it) while (iov_iter_count(it)) { /* iov_iter_iovec() for ITER_BVEC */ - bv.bv_page = it->bvec->bv_page; - bv.bv_offset = it->bvec->bv_offset + it->iov_offset; - bv.bv_len = min(iov_iter_count(it), - it->bvec->bv_len - it->iov_offset); + bvec_set_page(&bv, it->bvec->bv_page, + min(iov_iter_count(it), + it->bvec->bv_len - it->iov_offset), + it->bvec->bv_offset + it->iov_offset); /* * sendpage cannot properly handle pages with @@ -286,9 +286,8 @@ static void set_out_bvec_zero(struct ceph_connection *con) WARN_ON(iov_iter_count(&con->v2.out_iter)); WARN_ON(!con->v2.out_zero); - con->v2.out_bvec.bv_page = ceph_zero_page; - con->v2.out_bvec.bv_offset = 0; - con->v2.out_bvec.bv_len = min(con->v2.out_zero, (int)PAGE_SIZE); + bvec_set_page(&con->v2.out_bvec, ceph_zero_page, + min(con->v2.out_zero, (int)PAGE_SIZE), 0); con->v2.out_iter_sendpage = true; iov_iter_bvec(&con->v2.out_iter, ITER_SOURCE, &con->v2.out_bvec, 1, con->v2.out_bvec.bv_len); @@ -863,10 +862,7 @@ static void get_bvec_at(struct ceph_msg_data_cursor *cursor, /* get a piece of data, cursor isn't advanced */ page = ceph_msg_data_next(cursor, &off, &len); - - bv->bv_page = page; - bv->bv_offset = off; - bv->bv_len = len; + bvec_set_page(bv, page, len, off); } static int calc_sg_cnt(void *buf, int buf_len) @@ -1855,9 +1851,8 @@ static void prepare_read_enc_page(struct ceph_connection *con) con->v2.in_enc_resid); WARN_ON(!con->v2.in_enc_resid); - bv.bv_page = con->v2.in_enc_pages[con->v2.in_enc_i]; - bv.bv_offset = 0; - bv.bv_len = min(con->v2.in_enc_resid, (int)PAGE_SIZE); + bvec_set_page(&bv, con->v2.in_enc_pages[con->v2.in_enc_i], + min(con->v2.in_enc_resid, (int)PAGE_SIZE), 0); set_in_bvec(con, &bv); con->v2.in_enc_i++; @@ -2998,9 +2993,8 @@ static void queue_enc_page(struct ceph_connection *con) con->v2.out_enc_resid); WARN_ON(!con->v2.out_enc_resid); - bv.bv_page = con->v2.out_enc_pages[con->v2.out_enc_i]; - bv.bv_offset = 0; - bv.bv_len = min(con->v2.out_enc_resid, (int)PAGE_SIZE); + bvec_set_page(&bv, con->v2.out_enc_pages[con->v2.out_enc_i], + min(con->v2.out_enc_resid, (int)PAGE_SIZE), 0); set_out_bvec(con, &bv, false); con->v2.out_enc_i++; diff --git a/net/rxrpc/rxperf.c b/net/rxrpc/rxperf.c index 16dcabb71ebe..4a2e90015ca7 100644 --- a/net/rxrpc/rxperf.c +++ b/net/rxrpc/rxperf.c @@ -493,7 +493,7 @@ static int rxperf_deliver_request(struct rxperf_call *call) static int rxperf_process_call(struct rxperf_call *call) { struct msghdr msg = {}; - struct bio_vec bv[1]; + struct bio_vec bv; struct kvec iov[1]; ssize_t n; size_t reply_len = call->reply_len, len; @@ -503,10 +503,8 @@ static int rxperf_process_call(struct rxperf_call *call) while (reply_len > 0) { len = min_t(size_t, reply_len, PAGE_SIZE); - bv[0].bv_page = ZERO_PAGE(0); - bv[0].bv_offset = 0; - bv[0].bv_len = len; - iov_iter_bvec(&msg.msg_iter, WRITE, bv, 1, len); + bvec_set_page(&bv, ZERO_PAGE(0), len, 0); + iov_iter_bvec(&msg.msg_iter, WRITE, &bv, 1, len); msg.msg_flags = MSG_MORE; n = rxrpc_kernel_send_data(rxperf_socket, call->rxcall, &msg, len, rxperf_notify_end_reply_tx); diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c index 815baf308236..91252adcae46 100644 --- a/net/sunrpc/svcsock.c +++ b/net/sunrpc/svcsock.c @@ -252,11 +252,8 @@ static ssize_t svc_tcp_read_msg(struct svc_rqst *rqstp, size_t buflen, clear_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags); - for (i = 0, t = 0; t < buflen; i++, t += PAGE_SIZE) { - bvec[i].bv_page = rqstp->rq_pages[i]; - bvec[i].bv_len = PAGE_SIZE; - bvec[i].bv_offset = 0; - } + for (i = 0, t = 0; t < buflen; i++, t += PAGE_SIZE) + bvec_set_page(&bvec[i], rqstp->rq_pages[i], PAGE_SIZE, 0); rqstp->rq_respages = &rqstp->rq_pages[i]; rqstp->rq_next_page = rqstp->rq_respages + 1; diff --git a/net/sunrpc/xdr.c b/net/sunrpc/xdr.c index f7767bf22406..afe7ec02d232 100644 --- a/net/sunrpc/xdr.c +++ b/net/sunrpc/xdr.c @@ -150,9 +150,8 @@ xdr_alloc_bvec(struct xdr_buf *buf, gfp_t gfp) if (!buf->bvec) return -ENOMEM; for (i = 0; i < n; i++) { - buf->bvec[i].bv_page = buf->pages[i]; - buf->bvec[i].bv_len = PAGE_SIZE; - buf->bvec[i].bv_offset = 0; + bvec_set_page(&buf->bvec[i], buf->pages[i], PAGE_SIZE, + 0); } } return 0; |