From 85e6c775762aa4067d2c2b8121e59a06564d0dc4 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 4 Mar 2022 18:55:55 +0100 Subject: nvme: remove support or stream based temperature hint This support was added for RocksDB, but RocksDB ended up not using it. At the same time drives on the open marked (vs those build for OEMs for non-Linux support) that actually support streams are extremly rare. Don't bloat the nvme driver for it. Signed-off-by: Christoph Hellwig Acked-by: Jens Axboe Reviewed-by: Keith Busch Link: https://lore.kernel.org/r/20220304175556.407719-1-hch@lst.de [axboe: fold in ctrl->nr_streams removal from Keith] Signed-off-by: Jens Axboe --- drivers/nvme/host/core.c | 143 ----------------------------------------------- drivers/nvme/host/nvme.h | 1 - 2 files changed, 144 deletions(-) diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index ace8c61850b1..bcbe12fd4984 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -77,10 +77,6 @@ module_param(apst_secondary_latency_tol_us, ulong, 0644); MODULE_PARM_DESC(apst_secondary_latency_tol_us, "secondary APST latency tolerance in us"); -static bool streams; -module_param(streams, bool, 0644); -MODULE_PARM_DESC(streams, "turn on support for Streams write directives"); - /* * nvme_wq - hosts nvme related works that are not reset or delete * nvme_reset_wq - hosts nvme reset works @@ -748,108 +744,6 @@ bool __nvme_check_ready(struct nvme_ctrl *ctrl, struct request *rq, } EXPORT_SYMBOL_GPL(__nvme_check_ready); -static int nvme_toggle_streams(struct nvme_ctrl *ctrl, bool enable) -{ - struct nvme_command c = { }; - - c.directive.opcode = nvme_admin_directive_send; - c.directive.nsid = cpu_to_le32(NVME_NSID_ALL); - c.directive.doper = NVME_DIR_SND_ID_OP_ENABLE; - c.directive.dtype = NVME_DIR_IDENTIFY; - c.directive.tdtype = NVME_DIR_STREAMS; - c.directive.endir = enable ? NVME_DIR_ENDIR : 0; - - return nvme_submit_sync_cmd(ctrl->admin_q, &c, NULL, 0); -} - -static int nvme_disable_streams(struct nvme_ctrl *ctrl) -{ - return nvme_toggle_streams(ctrl, false); -} - -static int nvme_enable_streams(struct nvme_ctrl *ctrl) -{ - return nvme_toggle_streams(ctrl, true); -} - -static int nvme_get_stream_params(struct nvme_ctrl *ctrl, - struct streams_directive_params *s, u32 nsid) -{ - struct nvme_command c = { }; - - memset(s, 0, sizeof(*s)); - - c.directive.opcode = nvme_admin_directive_recv; - c.directive.nsid = cpu_to_le32(nsid); - c.directive.numd = cpu_to_le32(nvme_bytes_to_numd(sizeof(*s))); - c.directive.doper = NVME_DIR_RCV_ST_OP_PARAM; - c.directive.dtype = NVME_DIR_STREAMS; - - return nvme_submit_sync_cmd(ctrl->admin_q, &c, s, sizeof(*s)); -} - -static int nvme_configure_directives(struct nvme_ctrl *ctrl) -{ - struct streams_directive_params s; - u16 nssa; - int ret; - - if (!(ctrl->oacs & NVME_CTRL_OACS_DIRECTIVES)) - return 0; - if (!streams) - return 0; - - ret = nvme_enable_streams(ctrl); - if (ret) - return ret; - - ret = nvme_get_stream_params(ctrl, &s, NVME_NSID_ALL); - if (ret) - goto out_disable_stream; - - nssa = le16_to_cpu(s.nssa); - if (nssa < BLK_MAX_WRITE_HINTS - 1) { - dev_info(ctrl->device, "too few streams (%u) available\n", - nssa); - /* this condition is not an error: streams are optional */ - ret = 0; - goto out_disable_stream; - } - - ctrl->nr_streams = min_t(u16, nssa, BLK_MAX_WRITE_HINTS - 1); - dev_info(ctrl->device, "Using %u streams\n", ctrl->nr_streams); - return 0; - -out_disable_stream: - nvme_disable_streams(ctrl); - return ret; -} - -/* - * Check if 'req' has a write hint associated with it. If it does, assign - * a valid namespace stream to the write. - */ -static void nvme_assign_write_stream(struct nvme_ctrl *ctrl, - struct request *req, u16 *control, - u32 *dsmgmt) -{ - enum rw_hint streamid = req->write_hint; - - if (streamid == WRITE_LIFE_NOT_SET || streamid == WRITE_LIFE_NONE) - streamid = 0; - else { - streamid--; - if (WARN_ON_ONCE(streamid > ctrl->nr_streams)) - return; - - *control |= NVME_RW_DTYPE_STREAMS; - *dsmgmt |= streamid << 16; - } - - if (streamid < ARRAY_SIZE(req->q->write_hints)) - req->q->write_hints[streamid] += blk_rq_bytes(req) >> 9; -} - static inline void nvme_setup_flush(struct nvme_ns *ns, struct nvme_command *cmnd) { @@ -953,7 +847,6 @@ static inline blk_status_t nvme_setup_rw(struct nvme_ns *ns, struct request *req, struct nvme_command *cmnd, enum nvme_opcode op) { - struct nvme_ctrl *ctrl = ns->ctrl; u16 control = 0; u32 dsmgmt = 0; @@ -976,9 +869,6 @@ static inline blk_status_t nvme_setup_rw(struct nvme_ns *ns, cmnd->rw.apptag = 0; cmnd->rw.appmask = 0; - if (req_op(req) == REQ_OP_WRITE && ctrl->nr_streams) - nvme_assign_write_stream(ctrl, req, &control, &dsmgmt); - if (ns->ms) { /* * If formated with metadata, the block layer always provides a @@ -1697,9 +1587,6 @@ static void nvme_config_discard(struct gendisk *disk, struct nvme_ns *ns) return; } - if (ctrl->nr_streams && ns->sws && ns->sgs) - size *= ns->sws * ns->sgs; - BUILD_BUG_ON(PAGE_SIZE / sizeof(struct nvme_dsm_range) < NVME_DSM_MAX_RANGES); @@ -1725,31 +1612,6 @@ static bool nvme_ns_ids_equal(struct nvme_ns_ids *a, struct nvme_ns_ids *b) a->csi == b->csi; } -static int nvme_setup_streams_ns(struct nvme_ctrl *ctrl, struct nvme_ns *ns, - u32 *phys_bs, u32 *io_opt) -{ - struct streams_directive_params s; - int ret; - - if (!ctrl->nr_streams) - return 0; - - ret = nvme_get_stream_params(ctrl, &s, ns->head->ns_id); - if (ret) - return ret; - - ns->sws = le32_to_cpu(s.sws); - ns->sgs = le16_to_cpu(s.sgs); - - if (ns->sws) { - *phys_bs = ns->sws * (1 << ns->lba_shift); - if (ns->sgs) - *io_opt = *phys_bs * ns->sgs; - } - - return 0; -} - static void nvme_configure_metadata(struct nvme_ns *ns, struct nvme_id_ns *id) { struct nvme_ctrl *ctrl = ns->ctrl; @@ -1841,7 +1703,6 @@ static void nvme_update_disk_info(struct gendisk *disk, blk_integrity_unregister(disk); atomic_bs = phys_bs = bs; - nvme_setup_streams_ns(ns->ctrl, ns, &phys_bs, &io_opt); if (id->nabo == 0) { /* * Bit 1 indicates whether NAWUPF is defined for this namespace @@ -3131,10 +2992,6 @@ int nvme_init_ctrl_finish(struct nvme_ctrl *ctrl) if (ret < 0) return ret; - ret = nvme_configure_directives(ctrl); - if (ret < 0) - return ret; - ret = nvme_configure_acre(ctrl); if (ret < 0) return ret; diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h index 587d92df118b..1bed663322ee 100644 --- a/drivers/nvme/host/nvme.h +++ b/drivers/nvme/host/nvme.h @@ -280,7 +280,6 @@ struct nvme_ctrl { u16 crdt[3]; u16 oncs; u16 oacs; - u16 nr_streams; u16 sqsize; u32 max_namespaces; atomic_t abort_limit; -- cgit From c75e707fe1aab32f1dc8e09845533b6542d9aaa9 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 4 Mar 2022 18:55:56 +0100 Subject: block: remove the per-bio/request write hint With the NVMe support for this gone, there are no consumers of these hints left, so remove them. Signed-off-by: Christoph Hellwig Link: https://lore.kernel.org/r/20220304175556.407719-2-hch@lst.de Signed-off-by: Jens Axboe --- block/bio.c | 2 -- block/blk-crypto-fallback.c | 1 - block/blk-merge.c | 14 -------------- block/blk-mq-debugfs.c | 24 ------------------------ block/blk-mq.c | 1 - block/bounce.c | 1 - block/fops.c | 3 --- drivers/md/raid1.c | 2 -- drivers/md/raid5-ppl.c | 28 +++------------------------- drivers/md/raid5.c | 6 ------ fs/btrfs/extent_io.c | 1 - fs/buffer.c | 13 +++++-------- fs/direct-io.c | 3 --- fs/ext4/page-io.c | 5 +---- fs/f2fs/data.c | 2 -- fs/gfs2/lops.c | 1 - fs/iomap/buffered-io.c | 2 -- fs/iomap/direct-io.c | 1 - fs/mpage.c | 1 - fs/zonefs/super.c | 1 - include/linux/blk_types.h | 1 - include/linux/blkdev.h | 3 --- 22 files changed, 9 insertions(+), 107 deletions(-) diff --git a/block/bio.c b/block/bio.c index 151cace2dbe1..3c57b3ba727d 100644 --- a/block/bio.c +++ b/block/bio.c @@ -257,7 +257,6 @@ void bio_init(struct bio *bio, struct block_device *bdev, struct bio_vec *table, bio->bi_opf = opf; bio->bi_flags = 0; bio->bi_ioprio = 0; - bio->bi_write_hint = 0; bio->bi_status = 0; bio->bi_iter.bi_sector = 0; bio->bi_iter.bi_size = 0; @@ -737,7 +736,6 @@ static int __bio_clone(struct bio *bio, struct bio *bio_src, gfp_t gfp) bio_flagged(bio_src, BIO_REMAPPED)) bio_set_flag(bio, BIO_REMAPPED); bio->bi_ioprio = bio_src->bi_ioprio; - bio->bi_write_hint = bio_src->bi_write_hint; bio->bi_iter = bio_src->bi_iter; bio_clone_blkg_association(bio, bio_src); diff --git a/block/blk-crypto-fallback.c b/block/blk-crypto-fallback.c index 18c8eafe20b9..7c854584b52b 100644 --- a/block/blk-crypto-fallback.c +++ b/block/blk-crypto-fallback.c @@ -170,7 +170,6 @@ static struct bio *blk_crypto_fallback_clone_bio(struct bio *bio_src) bio_set_flag(bio, BIO_REMAPPED); bio->bi_opf = bio_src->bi_opf; bio->bi_ioprio = bio_src->bi_ioprio; - bio->bi_write_hint = bio_src->bi_write_hint; bio->bi_iter.bi_sector = bio_src->bi_iter.bi_sector; bio->bi_iter.bi_size = bio_src->bi_iter.bi_size; diff --git a/block/blk-merge.c b/block/blk-merge.c index f5255991b773..0e871d4e7cb8 100644 --- a/block/blk-merge.c +++ b/block/blk-merge.c @@ -782,13 +782,6 @@ static struct request *attempt_merge(struct request_queue *q, !blk_write_same_mergeable(req->bio, next->bio)) return NULL; - /* - * Don't allow merge of different write hints, or for a hint with - * non-hint IO. - */ - if (req->write_hint != next->write_hint) - return NULL; - if (req->ioprio != next->ioprio) return NULL; @@ -915,13 +908,6 @@ bool blk_rq_merge_ok(struct request *rq, struct bio *bio) !blk_write_same_mergeable(rq->bio, bio)) return false; - /* - * Don't allow merge of different write hints, or for a hint with - * non-hint IO. - */ - if (rq->write_hint != bio->bi_write_hint) - return false; - if (rq->ioprio != bio_prio(bio)) return false; diff --git a/block/blk-mq-debugfs.c b/block/blk-mq-debugfs.c index 3a790eb4995c..c2904c75c160 100644 --- a/block/blk-mq-debugfs.c +++ b/block/blk-mq-debugfs.c @@ -183,35 +183,11 @@ inval: return count; } -static int queue_write_hint_show(void *data, struct seq_file *m) -{ - struct request_queue *q = data; - int i; - - for (i = 0; i < BLK_MAX_WRITE_HINTS; i++) - seq_printf(m, "hint%d: %llu\n", i, q->write_hints[i]); - - return 0; -} - -static ssize_t queue_write_hint_store(void *data, const char __user *buf, - size_t count, loff_t *ppos) -{ - struct request_queue *q = data; - int i; - - for (i = 0; i < BLK_MAX_WRITE_HINTS; i++) - q->write_hints[i] = 0; - - return count; -} - static const struct blk_mq_debugfs_attr blk_mq_debugfs_queue_attrs[] = { { "poll_stat", 0400, queue_poll_stat_show }, { "requeue_list", 0400, .seq_ops = &queue_requeue_list_seq_ops }, { "pm_only", 0600, queue_pm_only_show, NULL }, { "state", 0600, queue_state_show, queue_state_write }, - { "write_hints", 0600, queue_write_hint_show, queue_write_hint_store }, { "zone_wlock", 0400, queue_zone_wlock_show, NULL }, { }, }; diff --git a/block/blk-mq.c b/block/blk-mq.c index f1b067d06ab5..64d5c2edb817 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -2406,7 +2406,6 @@ static void blk_mq_bio_to_request(struct request *rq, struct bio *bio, rq->cmd_flags |= REQ_FAILFAST_MASK; rq->__sector = bio->bi_iter.bi_sector; - rq->write_hint = bio->bi_write_hint; blk_rq_bio_prep(rq, bio, nr_segs); /* This can't fail, since GFP_NOIO includes __GFP_DIRECT_RECLAIM. */ diff --git a/block/bounce.c b/block/bounce.c index 3d50d19cde72..9db1256d57d5 100644 --- a/block/bounce.c +++ b/block/bounce.c @@ -169,7 +169,6 @@ static struct bio *bounce_clone_bio(struct bio *bio_src) if (bio_flagged(bio_src, BIO_REMAPPED)) bio_set_flag(bio, BIO_REMAPPED); bio->bi_ioprio = bio_src->bi_ioprio; - bio->bi_write_hint = bio_src->bi_write_hint; bio->bi_iter.bi_sector = bio_src->bi_iter.bi_sector; bio->bi_iter.bi_size = bio_src->bi_iter.bi_size; diff --git a/block/fops.c b/block/fops.c index 7ccc4ff109ce..1c732b72de72 100644 --- a/block/fops.c +++ b/block/fops.c @@ -83,7 +83,6 @@ static ssize_t __blkdev_direct_IO_simple(struct kiocb *iocb, bio_init(&bio, bdev, vecs, nr_pages, dio_bio_write_op(iocb)); } bio.bi_iter.bi_sector = pos >> SECTOR_SHIFT; - bio.bi_write_hint = iocb->ki_hint; bio.bi_private = current; bio.bi_end_io = blkdev_bio_end_io_simple; bio.bi_ioprio = iocb->ki_ioprio; @@ -225,7 +224,6 @@ static ssize_t __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, for (;;) { bio->bi_iter.bi_sector = pos >> SECTOR_SHIFT; - bio->bi_write_hint = iocb->ki_hint; bio->bi_private = dio; bio->bi_end_io = blkdev_bio_end_io; bio->bi_ioprio = iocb->ki_ioprio; @@ -327,7 +325,6 @@ static ssize_t __blkdev_direct_IO_async(struct kiocb *iocb, dio->flags = 0; dio->iocb = iocb; bio->bi_iter.bi_sector = pos >> SECTOR_SHIFT; - bio->bi_write_hint = iocb->ki_hint; bio->bi_end_io = blkdev_bio_end_io_async; bio->bi_ioprio = iocb->ki_ioprio; diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c index 03477e971699..370ab3218534 100644 --- a/drivers/md/raid1.c +++ b/drivers/md/raid1.c @@ -1137,8 +1137,6 @@ static void alloc_behind_master_bio(struct r1bio *r1_bio, goto skip_copy; } - behind_bio->bi_write_hint = bio->bi_write_hint; - while (i < vcnt && size) { struct page *page; int len = min_t(int, PAGE_SIZE, size); diff --git a/drivers/md/raid5-ppl.c b/drivers/md/raid5-ppl.c index bbb5673104ec..388ab41d1a11 100644 --- a/drivers/md/raid5-ppl.c +++ b/drivers/md/raid5-ppl.c @@ -467,7 +467,6 @@ static void ppl_submit_iounit(struct ppl_io_unit *io) bio_set_dev(bio, log->rdev->bdev); bio->bi_iter.bi_sector = log->next_io_sector; bio_add_page(bio, io->header_page, PAGE_SIZE, 0); - bio->bi_write_hint = ppl_conf->write_hint; pr_debug("%s: log->current_io_sector: %llu\n", __func__, (unsigned long long)log->next_io_sector); @@ -497,7 +496,6 @@ static void ppl_submit_iounit(struct ppl_io_unit *io) bio = bio_alloc_bioset(prev->bi_bdev, BIO_MAX_VECS, prev->bi_opf, GFP_NOIO, &ppl_conf->bs); - bio->bi_write_hint = prev->bi_write_hint; bio->bi_iter.bi_sector = bio_end_sector(prev); bio_add_page(bio, sh->ppl_page, PAGE_SIZE, 0); @@ -1397,7 +1395,6 @@ int ppl_init_log(struct r5conf *conf) atomic64_set(&ppl_conf->seq, 0); INIT_LIST_HEAD(&ppl_conf->no_mem_stripes); spin_lock_init(&ppl_conf->no_mem_stripes_lock); - ppl_conf->write_hint = RWH_WRITE_LIFE_NOT_SET; if (!mddev->external) { ppl_conf->signature = ~crc32c_le(~0, mddev->uuid, sizeof(mddev->uuid)); @@ -1496,25 +1493,13 @@ int ppl_modify_log(struct r5conf *conf, struct md_rdev *rdev, bool add) static ssize_t ppl_write_hint_show(struct mddev *mddev, char *buf) { - size_t ret = 0; - struct r5conf *conf; - struct ppl_conf *ppl_conf = NULL; - - spin_lock(&mddev->lock); - conf = mddev->private; - if (conf && raid5_has_ppl(conf)) - ppl_conf = conf->log_private; - ret = sprintf(buf, "%d\n", ppl_conf ? ppl_conf->write_hint : 0); - spin_unlock(&mddev->lock); - - return ret; + return sprintf(buf, "%d\n", 0); } static ssize_t ppl_write_hint_store(struct mddev *mddev, const char *page, size_t len) { struct r5conf *conf; - struct ppl_conf *ppl_conf; int err = 0; unsigned short new; @@ -1528,17 +1513,10 @@ ppl_write_hint_store(struct mddev *mddev, const char *page, size_t len) return err; conf = mddev->private; - if (!conf) { + if (!conf) err = -ENODEV; - } else if (raid5_has_ppl(conf)) { - ppl_conf = conf->log_private; - if (!ppl_conf) - err = -EINVAL; - else - ppl_conf->write_hint = new; - } else { + else if (!raid5_has_ppl(conf) || !conf->log_private) err = -EINVAL; - } mddev_unlock(mddev); diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index 8891aaba6596..78503db55ca4 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -1210,9 +1210,6 @@ again: bi->bi_io_vec[0].bv_len = RAID5_STRIPE_SIZE(conf); bi->bi_io_vec[0].bv_offset = sh->dev[i].offset; bi->bi_iter.bi_size = RAID5_STRIPE_SIZE(conf); - bi->bi_write_hint = sh->dev[i].write_hint; - if (!rrdev) - sh->dev[i].write_hint = RWH_WRITE_LIFE_NOT_SET; /* * If this is discard request, set bi_vcnt 0. We don't * want to confuse SCSI because SCSI will replace payload @@ -1264,8 +1261,6 @@ again: rbi->bi_io_vec[0].bv_len = RAID5_STRIPE_SIZE(conf); rbi->bi_io_vec[0].bv_offset = sh->dev[i].offset; rbi->bi_iter.bi_size = RAID5_STRIPE_SIZE(conf); - rbi->bi_write_hint = sh->dev[i].write_hint; - sh->dev[i].write_hint = RWH_WRITE_LIFE_NOT_SET; /* * If this is discard request, set bi_vcnt 0. We don't * want to confuse SCSI because SCSI will replace payload @@ -3416,7 +3411,6 @@ static int add_stripe_bio(struct stripe_head *sh, struct bio *bi, int dd_idx, (unsigned long long)sh->sector); spin_lock_irq(&sh->stripe_lock); - sh->dev[dd_idx].write_hint = bi->bi_write_hint; /* Don't allow new IO added to stripes in batch list */ if (sh->batch_head) goto overlap; diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index 5923eec8caa8..3b386bbb85a7 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -3321,7 +3321,6 @@ static int alloc_new_bio(struct btrfs_inode *inode, bio_ctrl->bio_flags = bio_flags; bio->bi_end_io = end_io_func; bio->bi_private = &inode->io_tree; - bio->bi_write_hint = inode->vfs_inode.i_write_hint; bio->bi_opf = opf; ret = calc_bio_boundaries(bio_ctrl, inode, file_offset); if (ret < 0) diff --git a/fs/buffer.c b/fs/buffer.c index a17c386a142c..29c6c60660f6 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -53,7 +53,7 @@ static int fsync_buffers_list(spinlock_t *lock, struct list_head *list); static int submit_bh_wbc(int op, int op_flags, struct buffer_head *bh, - enum rw_hint hint, struct writeback_control *wbc); + struct writeback_control *wbc); #define BH_ENTRY(list) list_entry((list), struct buffer_head, b_assoc_buffers) @@ -1806,8 +1806,7 @@ int __block_write_full_page(struct inode *inode, struct page *page, do { struct buffer_head *next = bh->b_this_page; if (buffer_async_write(bh)) { - submit_bh_wbc(REQ_OP_WRITE, write_flags, bh, - inode->i_write_hint, wbc); + submit_bh_wbc(REQ_OP_WRITE, write_flags, bh, wbc); nr_underway++; } bh = next; @@ -1861,8 +1860,7 @@ recover: struct buffer_head *next = bh->b_this_page; if (buffer_async_write(bh)) { clear_buffer_dirty(bh); - submit_bh_wbc(REQ_OP_WRITE, write_flags, bh, - inode->i_write_hint, wbc); + submit_bh_wbc(REQ_OP_WRITE, write_flags, bh, wbc); nr_underway++; } bh = next; @@ -3008,7 +3006,7 @@ static void end_bio_bh_io_sync(struct bio *bio) } static int submit_bh_wbc(int op, int op_flags, struct buffer_head *bh, - enum rw_hint write_hint, struct writeback_control *wbc) + struct writeback_control *wbc) { struct bio *bio; @@ -3034,7 +3032,6 @@ static int submit_bh_wbc(int op, int op_flags, struct buffer_head *bh, fscrypt_set_bio_crypt_ctx_bh(bio, bh, GFP_NOIO); bio->bi_iter.bi_sector = bh->b_blocknr * (bh->b_size >> 9); - bio->bi_write_hint = write_hint; bio_add_page(bio, bh->b_page, bh->b_size, bh_offset(bh)); BUG_ON(bio->bi_iter.bi_size != bh->b_size); @@ -3056,7 +3053,7 @@ static int submit_bh_wbc(int op, int op_flags, struct buffer_head *bh, int submit_bh(int op, int op_flags, struct buffer_head *bh) { - return submit_bh_wbc(op, op_flags, bh, 0, NULL); + return submit_bh_wbc(op, op_flags, bh, NULL); } EXPORT_SYMBOL(submit_bh); diff --git a/fs/direct-io.c b/fs/direct-io.c index 38bca4980a1c..aef06e607b40 100644 --- a/fs/direct-io.c +++ b/fs/direct-io.c @@ -402,9 +402,6 @@ dio_bio_alloc(struct dio *dio, struct dio_submit *sdio, bio->bi_end_io = dio_bio_end_aio; else bio->bi_end_io = dio_bio_end_io; - - bio->bi_write_hint = dio->iocb->ki_hint; - sdio->bio = bio; sdio->logical_offset_in_bio = sdio->cur_page_fs_offset; } diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c index 17bb78ebd784..495ce59fb4ad 100644 --- a/fs/ext4/page-io.c +++ b/fs/ext4/page-io.c @@ -373,7 +373,6 @@ void ext4_io_submit(struct ext4_io_submit *io) if (bio) { if (io->io_wbc->sync_mode == WB_SYNC_ALL) io->io_bio->bi_opf |= REQ_SYNC; - io->io_bio->bi_write_hint = io->io_end->inode->i_write_hint; submit_bio(io->io_bio); } io->io_bio = NULL; @@ -418,10 +417,8 @@ static void io_submit_add_bh(struct ext4_io_submit *io, submit_and_retry: ext4_io_submit(io); } - if (io->io_bio == NULL) { + if (io->io_bio == NULL) io_submit_init_bio(io, bh); - io->io_bio->bi_write_hint = inode->i_write_hint; - } ret = bio_add_page(io->io_bio, page, bh->b_size, bh_offset(bh)); if (ret != bh->b_size) goto submit_and_retry; diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c index e71dde8de0db..20d65aa6243a 100644 --- a/fs/f2fs/data.c +++ b/fs/f2fs/data.c @@ -403,8 +403,6 @@ static struct bio *__bio_alloc(struct f2fs_io_info *fio, int npages) } else { bio->bi_end_io = f2fs_write_end_io; bio->bi_private = sbi; - bio->bi_write_hint = f2fs_io_type_to_rw_hint(sbi, - fio->type, fio->temp); } iostat_alloc_and_bind_ctx(sbi, bio, NULL); diff --git a/fs/gfs2/lops.c b/fs/gfs2/lops.c index 4ae1eefae616..6ba51cbb94cf 100644 --- a/fs/gfs2/lops.c +++ b/fs/gfs2/lops.c @@ -491,7 +491,6 @@ static struct bio *gfs2_chain_bio(struct bio *prev, unsigned int nr_iovecs) new = bio_alloc(prev->bi_bdev, nr_iovecs, prev->bi_opf, GFP_NOIO); bio_clone_blkg_association(new, prev); new->bi_iter.bi_sector = bio_end_sector(prev); - new->bi_write_hint = prev->bi_write_hint; bio_chain(new, prev); submit_bio(prev); return new; diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c index 4653f3d07a1d..d0bf43f37a64 100644 --- a/fs/iomap/buffered-io.c +++ b/fs/iomap/buffered-io.c @@ -1232,7 +1232,6 @@ iomap_alloc_ioend(struct inode *inode, struct iomap_writepage_ctx *wpc, REQ_OP_WRITE | wbc_to_write_flags(wbc), GFP_NOFS, &iomap_ioend_bioset); bio->bi_iter.bi_sector = sector; - bio->bi_write_hint = inode->i_write_hint; wbc_init_bio(wbc, bio); ioend = container_of(bio, struct iomap_ioend, io_inline_bio); @@ -1263,7 +1262,6 @@ iomap_chain_bio(struct bio *prev) new = bio_alloc(prev->bi_bdev, BIO_MAX_VECS, prev->bi_opf, GFP_NOFS); bio_clone_blkg_association(new, prev); new->bi_iter.bi_sector = bio_end_sector(prev); - new->bi_write_hint = prev->bi_write_hint; bio_chain(prev, new); bio_get(prev); /* for iomap_finish_ioend */ diff --git a/fs/iomap/direct-io.c b/fs/iomap/direct-io.c index e2ba13645ef2..a434b1829545 100644 --- a/fs/iomap/direct-io.c +++ b/fs/iomap/direct-io.c @@ -309,7 +309,6 @@ static loff_t iomap_dio_bio_iter(const struct iomap_iter *iter, bio = bio_alloc(iomap->bdev, nr_pages, bio_opf, GFP_KERNEL); bio->bi_iter.bi_sector = iomap_sector(iomap, pos); - bio->bi_write_hint = dio->iocb->ki_hint; bio->bi_ioprio = dio->iocb->ki_ioprio; bio->bi_private = dio; bio->bi_end_io = iomap_dio_bio_end_io; diff --git a/fs/mpage.c b/fs/mpage.c index 6c4b810a21d0..c6379a81f90f 100644 --- a/fs/mpage.c +++ b/fs/mpage.c @@ -588,7 +588,6 @@ alloc_new: GFP_NOFS); bio->bi_iter.bi_sector = blocks[0] << (blkbits - 9); wbc_init_bio(wbc, bio); - bio->bi_write_hint = inode->i_write_hint; } /* diff --git a/fs/zonefs/super.c b/fs/zonefs/super.c index d331b52592a0..b71a23dd1255 100644 --- a/fs/zonefs/super.c +++ b/fs/zonefs/super.c @@ -695,7 +695,6 @@ static ssize_t zonefs_file_dio_append(struct kiocb *iocb, struct iov_iter *from) bio = bio_alloc(bdev, nr_pages, REQ_OP_ZONE_APPEND | REQ_SYNC | REQ_IDLE, GFP_NOFS); bio->bi_iter.bi_sector = zi->i_zsector; - bio->bi_write_hint = iocb->ki_hint; bio->bi_ioprio = iocb->ki_ioprio; if (iocb->ki_flags & IOCB_DSYNC) bio->bi_opf |= REQ_FUA; diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index 5561e58d158a..ba8cfa57255f 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -250,7 +250,6 @@ struct bio { */ unsigned short bi_flags; /* BIO_* below */ unsigned short bi_ioprio; - unsigned short bi_write_hint; blk_status_t bi_status; atomic_t __bi_remaining; diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index a12c031af887..226836ccd060 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -518,9 +518,6 @@ struct request_queue { bool mq_sysfs_init_done; -#define BLK_MAX_WRITE_HINTS 5 - u64 write_hints[BLK_MAX_WRITE_HINTS]; - /* * Independent sector access ranges. This is always NULL for * devices that do not have multiple independent access ranges. -- cgit From 41d36a9f3e5336f5b48c3adba0777b8e217020d7 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 8 Mar 2022 07:05:28 +0100 Subject: fs: remove kiocb.ki_hint This field is entirely unused now except for a tracepoint in f2fs, so remove it. Signed-off-by: Christoph Hellwig Reviewed-by: Dave Chinner Reviewed-by: Chaitanya Kulkarni Link: https://lore.kernel.org/r/20220308060529.736277-2-hch@lst.de Signed-off-by: Jens Axboe --- fs/aio.c | 1 - fs/cachefiles/io.c | 2 -- fs/f2fs/file.c | 6 ------ fs/io_uring.c | 1 - include/linux/fs.h | 12 ------------ include/trace/events/f2fs.h | 3 +-- 6 files changed, 1 insertion(+), 24 deletions(-) diff --git a/fs/aio.c b/fs/aio.c index 4ceba13a7db0..eb0948bb74f1 100644 --- a/fs/aio.c +++ b/fs/aio.c @@ -1478,7 +1478,6 @@ static int aio_prep_rw(struct kiocb *req, const struct iocb *iocb) req->ki_flags = iocb_flags(req->ki_filp); if (iocb->aio_flags & IOCB_FLAG_RESFD) req->ki_flags |= IOCB_EVENTFD; - req->ki_hint = ki_hint_validate(file_write_hint(req->ki_filp)); if (iocb->aio_flags & IOCB_FLAG_IOPRIO) { /* * If the IOCB_FLAG_IOPRIO flag of aio_flags is set, then diff --git a/fs/cachefiles/io.c b/fs/cachefiles/io.c index 753986ea1583..bc7c7a7d9260 100644 --- a/fs/cachefiles/io.c +++ b/fs/cachefiles/io.c @@ -138,7 +138,6 @@ static int cachefiles_read(struct netfs_cache_resources *cres, ki->iocb.ki_filp = file; ki->iocb.ki_pos = start_pos + skipped; ki->iocb.ki_flags = IOCB_DIRECT; - ki->iocb.ki_hint = ki_hint_validate(file_write_hint(file)); ki->iocb.ki_ioprio = get_current_ioprio(); ki->skipped = skipped; ki->object = object; @@ -313,7 +312,6 @@ static int cachefiles_write(struct netfs_cache_resources *cres, ki->iocb.ki_filp = file; ki->iocb.ki_pos = start_pos; ki->iocb.ki_flags = IOCB_DIRECT | IOCB_WRITE; - ki->iocb.ki_hint = ki_hint_validate(file_write_hint(file)); ki->iocb.ki_ioprio = get_current_ioprio(); ki->object = object; ki->inval_counter = cres->inval_counter; diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c index 3c98ef6af97d..45076c01a2ba 100644 --- a/fs/f2fs/file.c +++ b/fs/f2fs/file.c @@ -4479,10 +4479,8 @@ static ssize_t f2fs_dio_write_iter(struct kiocb *iocb, struct iov_iter *from, struct f2fs_inode_info *fi = F2FS_I(inode); struct f2fs_sb_info *sbi = F2FS_I_SB(inode); const bool do_opu = f2fs_lfs_mode(sbi); - const int whint_mode = F2FS_OPTION(sbi).whint_mode; const loff_t pos = iocb->ki_pos; const ssize_t count = iov_iter_count(from); - const enum rw_hint hint = iocb->ki_hint; unsigned int dio_flags; struct iomap_dio *dio; ssize_t ret; @@ -4515,8 +4513,6 @@ static ssize_t f2fs_dio_write_iter(struct kiocb *iocb, struct iov_iter *from, if (do_opu) down_read(&fi->i_gc_rwsem[READ]); } - if (whint_mode == WHINT_MODE_OFF) - iocb->ki_hint = WRITE_LIFE_NOT_SET; /* * We have to use __iomap_dio_rw() and iomap_dio_complete() instead of @@ -4539,8 +4535,6 @@ static ssize_t f2fs_dio_write_iter(struct kiocb *iocb, struct iov_iter *from, ret = iomap_dio_complete(dio); } - if (whint_mode == WHINT_MODE_OFF) - iocb->ki_hint = hint; if (do_opu) up_read(&fi->i_gc_rwsem[READ]); up_read(&fi->i_gc_rwsem[WRITE]); diff --git a/fs/io_uring.c b/fs/io_uring.c index 4715980e9015..36e09169ff93 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -3747,7 +3747,6 @@ static int io_write_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { if (unlikely(!(req->file->f_mode & FMODE_WRITE))) return -EBADF; - req->rw.kiocb.ki_hint = ki_hint_validate(file_write_hint(req->file)); return io_prep_rw(req, sqe); } diff --git a/include/linux/fs.h b/include/linux/fs.h index e2d892b201b0..d5658ac5d8c6 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -327,7 +327,6 @@ struct kiocb { void (*ki_complete)(struct kiocb *iocb, long ret); void *private; int ki_flags; - u16 ki_hint; u16 ki_ioprio; /* See linux/ioprio.h */ struct wait_page_queue *ki_waitq; /* for async buffered IO */ randomized_struct_fields_end @@ -2225,21 +2224,11 @@ static inline enum rw_hint file_write_hint(struct file *file) static inline int iocb_flags(struct file *file); -static inline u16 ki_hint_validate(enum rw_hint hint) -{ - typeof(((struct kiocb *)0)->ki_hint) max_hint = -1; - - if (hint <= max_hint) - return hint; - return 0; -} - static inline void init_sync_kiocb(struct kiocb *kiocb, struct file *filp) { *kiocb = (struct kiocb) { .ki_filp = filp, .ki_flags = iocb_flags(filp), - .ki_hint = ki_hint_validate(file_write_hint(filp)), .ki_ioprio = get_current_ioprio(), }; } @@ -2250,7 +2239,6 @@ static inline void kiocb_clone(struct kiocb *kiocb, struct kiocb *kiocb_src, *kiocb = (struct kiocb) { .ki_filp = filp, .ki_flags = kiocb_src->ki_flags, - .ki_hint = kiocb_src->ki_hint, .ki_ioprio = kiocb_src->ki_ioprio, .ki_pos = kiocb_src->ki_pos, }; diff --git a/include/trace/events/f2fs.h b/include/trace/events/f2fs.h index f701bb23f83c..1779e133cea0 100644 --- a/include/trace/events/f2fs.h +++ b/include/trace/events/f2fs.h @@ -956,12 +956,11 @@ TRACE_EVENT(f2fs_direct_IO_enter, __entry->rw = rw; ), - TP_printk("dev = (%d,%d), ino = %lu pos = %lld len = %lu ki_flags = %x ki_hint = %x ki_ioprio = %x rw = %d", + TP_printk("dev = (%d,%d), ino = %lu pos = %lld len = %lu ki_flags = %x ki_ioprio = %x rw = %d", show_dev_ino(__entry), __entry->iocb->ki_pos, __entry->len, __entry->iocb->ki_flags, - __entry->iocb->ki_hint, __entry->iocb->ki_ioprio, __entry->rw) ); -- cgit From 7b12e49669c99f63bc12351c57e581f1f14d4adf Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 8 Mar 2022 07:05:29 +0100 Subject: fs: remove fs.f_write_hint The value is now completely unused except for reporting it back through the F_GET_FILE_RW_HINT ioctl, so remove the value and the two ioctls for it. Trying to use the F_SET_FILE_RW_HINT and F_GET_FILE_RW_HINT fcntls will now return EINVAL, just like it would on a kernel that never supported this functionality in the first place. Signed-off-by: Christoph Hellwig Reviewed-by: Dave Chinner Reviewed-by: Chaitanya Kulkarni Link: https://lore.kernel.org/r/20220308060529.736277-3-hch@lst.de Signed-off-by: Jens Axboe --- fs/fcntl.c | 18 ------------------ fs/open.c | 1 - include/linux/fs.h | 9 --------- 3 files changed, 28 deletions(-) diff --git a/fs/fcntl.c b/fs/fcntl.c index 9c6c6a3e2de5..f15d885b9796 100644 --- a/fs/fcntl.c +++ b/fs/fcntl.c @@ -291,22 +291,6 @@ static long fcntl_rw_hint(struct file *file, unsigned int cmd, u64 h; switch (cmd) { - case F_GET_FILE_RW_HINT: - h = file_write_hint(file); - if (copy_to_user(argp, &h, sizeof(*argp))) - return -EFAULT; - return 0; - case F_SET_FILE_RW_HINT: - if (copy_from_user(&h, argp, sizeof(h))) - return -EFAULT; - hint = (enum rw_hint) h; - if (!rw_hint_valid(hint)) - return -EINVAL; - - spin_lock(&file->f_lock); - file->f_write_hint = hint; - spin_unlock(&file->f_lock); - return 0; case F_GET_RW_HINT: h = inode->i_write_hint; if (copy_to_user(argp, &h, sizeof(*argp))) @@ -431,8 +415,6 @@ static long do_fcntl(int fd, unsigned int cmd, unsigned long arg, break; case F_GET_RW_HINT: case F_SET_RW_HINT: - case F_GET_FILE_RW_HINT: - case F_SET_FILE_RW_HINT: err = fcntl_rw_hint(filp, cmd, arg); break; default: diff --git a/fs/open.c b/fs/open.c index 9ff2f621b760..1315253e0247 100644 --- a/fs/open.c +++ b/fs/open.c @@ -835,7 +835,6 @@ static int do_dentry_open(struct file *f, likely(f->f_op->write || f->f_op->write_iter)) f->f_mode |= FMODE_CAN_WRITE; - f->f_write_hint = WRITE_LIFE_NOT_SET; f->f_flags &= ~(O_CREAT | O_EXCL | O_NOCTTY | O_TRUNC); file_ra_state_init(&f->f_ra, f->f_mapping->host->i_mapping); diff --git a/include/linux/fs.h b/include/linux/fs.h index d5658ac5d8c6..a1fc3b41cd82 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -966,7 +966,6 @@ struct file { * Must not be taken from IRQ context. */ spinlock_t f_lock; - enum rw_hint f_write_hint; atomic_long_t f_count; unsigned int f_flags; fmode_t f_mode; @@ -2214,14 +2213,6 @@ static inline bool HAS_UNMAPPED_ID(struct user_namespace *mnt_userns, !gid_valid(i_gid_into_mnt(mnt_userns, inode)); } -static inline enum rw_hint file_write_hint(struct file *file) -{ - if (file->f_write_hint != WRITE_LIFE_NOT_SET) - return file->f_write_hint; - - return file_inode(file)->i_write_hint; -} - static inline int iocb_flags(struct file *file); static inline void init_sync_kiocb(struct kiocb *kiocb, struct file *filp) -- cgit