diff options
129 files changed, 1581 insertions, 1752 deletions
diff --git a/Documentation/ABI/testing/sysfs-block b/Documentation/ABI/testing/sysfs-block index e34cdeeeb9d4..a0ed87386639 100644 --- a/Documentation/ABI/testing/sysfs-block +++ b/Documentation/ABI/testing/sysfs-block @@ -28,6 +28,18 @@ Description: For more details refer Documentation/admin-guide/iostats.rst +What: /sys/block/<disk>/diskseq +Date: February 2021 +Contact: Matteo Croce <mcroce@microsoft.com> +Description: + The /sys/block/<disk>/diskseq files reports the disk + sequence number, which is a monotonically increasing + number assigned to every drive. + Some devices, like the loop device, refresh such number + every time the backing file is changed. + The value type is 64 bit unsigned. + + What: /sys/block/<disk>/<part>/stat Date: February 2008 Contact: Jerome Marchand <jmarchan@redhat.com> diff --git a/arch/m68k/configs/stmark2_defconfig b/arch/m68k/configs/stmark2_defconfig index d92306472fce..8898ae321779 100644 --- a/arch/m68k/configs/stmark2_defconfig +++ b/arch/m68k/configs/stmark2_defconfig @@ -22,7 +22,6 @@ CONFIG_RAMSIZE=0x8000000 CONFIG_VECTORBASE=0x40000000 CONFIG_KERNELBASE=0x40001000 # CONFIG_BLK_DEV_BSG is not set -CONFIG_BLK_CMDLINE_PARSER=y CONFIG_BINFMT_FLAT=y CONFIG_BINFMT_ZFLAT=y CONFIG_BINFMT_MISC=y diff --git a/arch/mips/include/asm/mach-rc32434/rb.h b/arch/mips/include/asm/mach-rc32434/rb.h index d502673a4f6c..34d179ca020b 100644 --- a/arch/mips/include/asm/mach-rc32434/rb.h +++ b/arch/mips/include/asm/mach-rc32434/rb.h @@ -7,8 +7,6 @@ #ifndef __ASM_RC32434_RB_H #define __ASM_RC32434_RB_H -#include <linux/genhd.h> - #define REGBASE 0x18000000 #define IDT434_REG_BASE ((volatile void *) KSEG1ADDR(REGBASE)) #define UART0BASE 0x58000 diff --git a/arch/riscv/configs/defconfig b/arch/riscv/configs/defconfig index 1f2be234b11c..bc68231a8fb7 100644 --- a/arch/riscv/configs/defconfig +++ b/arch/riscv/configs/defconfig @@ -132,7 +132,6 @@ CONFIG_DEBUG_PLIST=y CONFIG_DEBUG_SG=y # CONFIG_RCU_TRACE is not set CONFIG_RCU_EQS_DEBUG=y -CONFIG_DEBUG_BLOCK_EXT_DEVT=y # CONFIG_FTRACE is not set # CONFIG_RUNTIME_TESTING_MENU is not set CONFIG_MEMTEST=y diff --git a/arch/riscv/configs/rv32_defconfig b/arch/riscv/configs/rv32_defconfig index 8dd02b842fef..434ef5b64599 100644 --- a/arch/riscv/configs/rv32_defconfig +++ b/arch/riscv/configs/rv32_defconfig @@ -127,7 +127,6 @@ CONFIG_DEBUG_PLIST=y CONFIG_DEBUG_SG=y # CONFIG_RCU_TRACE is not set CONFIG_RCU_EQS_DEBUG=y -CONFIG_DEBUG_BLOCK_EXT_DEVT=y # CONFIG_FTRACE is not set # CONFIG_RUNTIME_TESTING_MENU is not set CONFIG_MEMTEST=y diff --git a/arch/um/drivers/ubd_kern.c b/arch/um/drivers/ubd_kern.c index e497185dd393..cd9dc0556e91 100644 --- a/arch/um/drivers/ubd_kern.c +++ b/arch/um/drivers/ubd_kern.c @@ -1268,8 +1268,7 @@ static void ubd_map_req(struct ubd *dev, struct io_thread_req *io_req, rq_for_each_segment(bvec, req, iter) { BUG_ON(i >= io_req->desc_cnt); - io_req->io_desc[i].buffer = - page_address(bvec.bv_page) + bvec.bv_offset; + io_req->io_desc[i].buffer = bvec_virt(&bvec); io_req->io_desc[i].length = bvec.bv_len; i++; } diff --git a/block/Kconfig b/block/Kconfig index fd732aede922..bac87d773c54 100644 --- a/block/Kconfig +++ b/block/Kconfig @@ -114,16 +114,6 @@ config BLK_DEV_THROTTLING_LOW Note, this is an experimental interface and could be changed someday. -config BLK_CMDLINE_PARSER - bool "Block device command line partition parser" - help - Enabling this option allows you to specify the partition layout from - the kernel boot args. This is typically of use for embedded devices - which don't otherwise have any standardized method for listing the - partitions on a block device. - - See Documentation/block/cmdline-partition.rst for more information. - config BLK_WBT bool "Enable support for block device writeback throttling" help @@ -251,4 +241,8 @@ config BLK_MQ_RDMA config BLK_PM def_bool BLOCK && PM +# do not use in new code +config BLOCK_HOLDER_DEPRECATED + bool + source "block/Kconfig.iosched" diff --git a/block/Makefile b/block/Makefile index 1e1afa10f869..1d0d466f2182 100644 --- a/block/Makefile +++ b/block/Makefile @@ -26,7 +26,6 @@ obj-$(CONFIG_MQ_IOSCHED_KYBER) += kyber-iosched.o bfq-y := bfq-iosched.o bfq-wf2q.o bfq-cgroup.o obj-$(CONFIG_IOSCHED_BFQ) += bfq.o -obj-$(CONFIG_BLK_CMDLINE_PARSER) += cmdline-parser.o obj-$(CONFIG_BLK_DEV_INTEGRITY) += bio-integrity.o blk-integrity.o obj-$(CONFIG_BLK_DEV_INTEGRITY_T10) += t10-pi.o obj-$(CONFIG_BLK_MQ_PCI) += blk-mq-pci.o @@ -40,3 +39,4 @@ obj-$(CONFIG_BLK_SED_OPAL) += sed-opal.o obj-$(CONFIG_BLK_PM) += blk-pm.o obj-$(CONFIG_BLK_INLINE_ENCRYPTION) += keyslot-manager.o blk-crypto.o obj-$(CONFIG_BLK_INLINE_ENCRYPTION_FALLBACK) += blk-crypto-fallback.o +obj-$(CONFIG_BLOCK_HOLDER_DEPRECATED) += holder.o diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c index 727955918563..480e1a134859 100644 --- a/block/bfq-iosched.c +++ b/block/bfq-iosched.c @@ -2361,6 +2361,9 @@ static int bfq_request_merge(struct request_queue *q, struct request **req, __rq = bfq_find_rq_fmerge(bfqd, bio, q); if (__rq && elv_bio_merge_ok(__rq, bio)) { *req = __rq; + + if (blk_discard_mergable(__rq)) + return ELEVATOR_DISCARD_MERGE; return ELEVATOR_FRONT_MERGE; } @@ -2505,7 +2508,7 @@ void bfq_end_wr_async_queues(struct bfq_data *bfqd, int i, j; for (i = 0; i < 2; i++) - for (j = 0; j < IOPRIO_BE_NR; j++) + 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) @@ -5266,8 +5269,8 @@ bfq_set_next_ioprio_data(struct bfq_queue *bfqq, struct bfq_io_cq *bic) switch (ioprio_class) { default: pr_err("bdi %s: bfq: bad prio class %d\n", - bdi_dev_name(bfqq->bfqd->queue->backing_dev_info), - ioprio_class); + bdi_dev_name(bfqq->bfqd->queue->disk->bdi), + ioprio_class); fallthrough; case IOPRIO_CLASS_NONE: /* @@ -5290,10 +5293,10 @@ bfq_set_next_ioprio_data(struct bfq_queue *bfqq, struct bfq_io_cq *bic) break; } - if (bfqq->new_ioprio >= IOPRIO_BE_NR) { + if (bfqq->new_ioprio >= IOPRIO_NR_LEVELS) { pr_crit("bfq_set_next_ioprio_data: new_ioprio %d\n", bfqq->new_ioprio); - bfqq->new_ioprio = IOPRIO_BE_NR; + bfqq->new_ioprio = IOPRIO_NR_LEVELS - 1; } bfqq->entity.new_weight = bfq_ioprio_to_weight(bfqq->new_ioprio); @@ -5408,7 +5411,7 @@ static struct bfq_queue **bfq_async_queue_prio(struct bfq_data *bfqd, case IOPRIO_CLASS_RT: return &bfqg->async_bfqq[0][ioprio]; case IOPRIO_CLASS_NONE: - ioprio = IOPRIO_NORM; + ioprio = IOPRIO_BE_NORM; fallthrough; case IOPRIO_CLASS_BE: return &bfqg->async_bfqq[1][ioprio]; @@ -6822,7 +6825,7 @@ void bfq_put_async_queues(struct bfq_data *bfqd, struct bfq_group *bfqg) int i, j; for (i = 0; i < 2; i++) - for (j = 0; j < IOPRIO_BE_NR; j++) + for (j = 0; j < IOPRIO_NR_LEVELS; j++) __bfq_put_async_bfqq(bfqd, &bfqg->async_bfqq[i][j]); __bfq_put_async_bfqq(bfqd, &bfqg->async_idle_bfqq); diff --git a/block/bfq-iosched.h b/block/bfq-iosched.h index 99c2a3cb081e..a73488eec8a4 100644 --- a/block/bfq-iosched.h +++ b/block/bfq-iosched.h @@ -931,7 +931,7 @@ struct bfq_group { void *bfqd; - struct bfq_queue *async_bfqq[2][IOPRIO_BE_NR]; + struct bfq_queue *async_bfqq[2][IOPRIO_NR_LEVELS]; struct bfq_queue *async_idle_bfqq; struct bfq_entity *my_entity; @@ -948,15 +948,13 @@ struct bfq_group { struct bfq_entity entity; struct bfq_sched_data sched_data; - struct bfq_queue *async_bfqq[2][IOPRIO_BE_NR]; + struct bfq_queue *async_bfqq[2][IOPRIO_NR_LEVELS]; struct bfq_queue *async_idle_bfqq; struct rb_root rq_pos_tree; }; #endif -struct bfq_queue *bfq_entity_to_bfqq(struct bfq_entity *entity); - /* --------------- main algorithm interface ----------------- */ #define BFQ_SERVICE_TREE_INIT ((struct bfq_service_tree) \ diff --git a/block/bfq-wf2q.c b/block/bfq-wf2q.c index 7a462df71f68..b74cc0da118e 100644 --- a/block/bfq-wf2q.c +++ b/block/bfq-wf2q.c @@ -505,7 +505,7 @@ static void bfq_active_insert(struct bfq_service_tree *st, */ unsigned short bfq_ioprio_to_weight(int ioprio) { - return (IOPRIO_BE_NR - ioprio) * BFQ_WEIGHT_CONVERSION_COEFF; + return (IOPRIO_NR_LEVELS - ioprio) * BFQ_WEIGHT_CONVERSION_COEFF; } /** @@ -514,12 +514,12 @@ unsigned short bfq_ioprio_to_weight(int ioprio) * * To preserve as much as possible the old only-ioprio user interface, * 0 is used as an escape ioprio value for weights (numerically) equal or - * larger than IOPRIO_BE_NR * BFQ_WEIGHT_CONVERSION_COEFF. + * larger than IOPRIO_NR_LEVELS * BFQ_WEIGHT_CONVERSION_COEFF. */ static unsigned short bfq_weight_to_ioprio(int weight) { return max_t(int, 0, - IOPRIO_BE_NR * BFQ_WEIGHT_CONVERSION_COEFF - weight); + IOPRIO_NR_LEVELS * BFQ_WEIGHT_CONVERSION_COEFF - weight); } static void bfq_get_entity(struct bfq_entity *entity) diff --git a/block/bio-integrity.c b/block/bio-integrity.c index 4b4eb8964a6f..6b47cddbbca1 100644 --- a/block/bio-integrity.c +++ b/block/bio-integrity.c @@ -104,8 +104,7 @@ void bio_integrity_free(struct bio *bio) struct bio_set *bs = bio->bi_pool; if (bip->bip_flags & BIP_BLOCK_INTEGRITY) - kfree(page_address(bip->bip_vec->bv_page) + - bip->bip_vec->bv_offset); + kfree(bvec_virt(bip->bip_vec)); __bio_integrity_free(bs, bip); bio->bi_integrity = NULL; @@ -163,27 +162,23 @@ static blk_status_t bio_integrity_process(struct bio *bio, struct bio_vec bv; struct bio_integrity_payload *bip = bio_integrity(bio); blk_status_t ret = BLK_STS_OK; - void *prot_buf = page_address(bip->bip_vec->bv_page) + - bip->bip_vec->bv_offset; iter.disk_name = bio->bi_bdev->bd_disk->disk_name; iter.interval = 1 << bi->interval_exp; iter.seed = proc_iter->bi_sector; - iter.prot_buf = prot_buf; + iter.prot_buf = bvec_virt(bip->bip_vec); __bio_for_each_segment(bv, bio, bviter, *proc_iter) { - void *kaddr = kmap_atomic(bv.bv_page); + void *kaddr = bvec_kmap_local(&bv); - iter.data_buf = kaddr + bv.bv_offset; + iter.data_buf = kaddr; iter.data_size = bv.bv_len; - ret = proc_fn(&iter); - if (ret) { - kunmap_atomic(kaddr); - return ret; - } + kunmap_local(kaddr); + + if (ret) + break; - kunmap_atomic(kaddr); } return ret; } diff --git a/block/bio.c b/block/bio.c index 1fab762e079b..265bff6b549a 100644 --- a/block/bio.c +++ b/block/bio.c @@ -495,16 +495,11 @@ EXPORT_SYMBOL(bio_kmalloc); void zero_fill_bio(struct bio *bio) { - unsigned long flags; struct bio_vec bv; struct bvec_iter iter; - bio_for_each_segment(bv, bio, iter) { - char *data = bvec_kmap_irq(&bv, &flags); - memset(data, 0, bv.bv_len); - flush_dcache_page(bv.bv_page); - bvec_kunmap_irq(data, &flags); - } + bio_for_each_segment(bv, bio, iter) + memzero_bvec(&bv); } EXPORT_SYMBOL(zero_fill_bio); @@ -979,6 +974,14 @@ static int bio_iov_bvec_set_append(struct bio *bio, struct iov_iter *iter) return 0; } +static void bio_put_pages(struct page **pages, size_t size, size_t off) +{ + size_t i, nr = DIV_ROUND_UP(size + (off & ~PAGE_MASK), PAGE_SIZE); + + for (i = 0; i < nr; i++) + put_page(pages[i]); +} + #define PAGE_PTRS_PER_BVEC (sizeof(struct bio_vec) / sizeof(struct page *)) /** @@ -1023,8 +1026,10 @@ static int __bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter) if (same_page) put_page(page); } else { - if (WARN_ON_ONCE(bio_full(bio, len))) - return -EINVAL; + if (WARN_ON_ONCE(bio_full(bio, len))) { + bio_put_pages(pages + i, left, offset); + return -EINVAL; + } __bio_add_page(bio, page, len, offset); } offset = 0; @@ -1069,6 +1074,7 @@ static int __bio_iov_append_get_pages(struct bio *bio, struct iov_iter *iter) len = min_t(size_t, PAGE_SIZE - offset, left); if (bio_add_hw_page(q, bio, page, len, offset, max_append_sectors, &same_page) != len) { + bio_put_pages(pages + i, left, offset); ret = -EINVAL; break; } @@ -1191,27 +1197,15 @@ EXPORT_SYMBOL(bio_advance); void bio_copy_data_iter(struct bio *dst, struct bvec_iter *dst_iter, struct bio *src, struct bvec_iter *src_iter) { - struct bio_vec src_bv, dst_bv; - void *src_p, *dst_p; - unsigned bytes; - while (src_iter->bi_size && dst_iter->bi_size) { - src_bv = bio_iter_iovec(src, *src_iter); - dst_bv = bio_iter_iovec(dst, *dst_iter); - - bytes = min(src_bv.bv_len, dst_bv.bv_len); - - src_p = kmap_atomic(src_bv.bv_page); - dst_p = kmap_atomic(dst_bv.bv_page); - - memcpy(dst_p + dst_bv.bv_offset, - src_p + src_bv.bv_offset, - bytes); - - kunmap_atomic(dst_p); - kunmap_atomic(src_p); - - flush_dcache_page(dst_bv.bv_page); + struct bio_vec src_bv = bio_iter_iovec(src, *src_iter); + struct bio_vec dst_bv = bio_iter_iovec(dst, *dst_iter); + unsigned int bytes = min(src_bv.bv_len, dst_bv.bv_len); + void *src_buf; + + src_buf = bvec_kmap_local(&src_bv); + memcpy_to_bvec(&dst_bv, src_buf); + kunmap_local(src_buf); bio_advance_iter_single(src, src_iter, bytes); bio_advance_iter_single(dst, dst_iter, bytes); diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c index 31fe9be179d9..3c88a79a319b 100644 --- a/block/blk-cgroup.c +++ b/block/blk-cgroup.c @@ -489,10 +489,9 @@ static int blkcg_reset_stats(struct cgroup_subsys_state *css, const char *blkg_dev_name(struct blkcg_gq *blkg) { - /* some drivers (floppy) instantiate a queue w/o disk registered */ - if (blkg->q->backing_dev_info->dev) - return bdi_dev_name(blkg->q->backing_dev_info); - return NULL; + if (!blkg->q->disk || !blkg->q->disk->bdi->dev) + return NULL; + return bdi_dev_name(blkg->q->disk->bdi); } /** @@ -873,97 +872,79 @@ static void blkcg_fill_root_iostats(void) } } -static int blkcg_print_stat(struct seq_file *sf, void *v) +static void blkcg_print_one_stat(struct blkcg_gq *blkg, struct seq_file *s) { - struct blkcg *blkcg = css_to_blkcg(seq_css(sf)); - struct blkcg_gq *blkg; - - if (!seq_css(sf)->parent) - blkcg_fill_root_iostats(); - else - cgroup_rstat_flush(blkcg->css.cgroup); - - rcu_read_lock(); - - hlist_for_each_entry_rcu(blkg, &blkcg->blkg_list, blkcg_node) { - struct blkg_iostat_set *bis = &blkg->iostat; - const char *dname; - char *buf; - u64 rbytes, wbytes, rios, wios, dbytes, dios; - size_t size = seq_get_buf(sf, &buf), off = 0; - int i; - bool has_stats = false; - unsigned seq; + struct blkg_iostat_set *bis = &blkg->iostat; + u64 rbytes, wbytes, rios, wios, dbytes, dios; + bool has_stats = false; + const char *dname; + unsigned seq; + int i; - spin_lock_irq(&blkg->q->queue_lock); + if (!blkg->online) + return; - if (!blkg->online) - goto skip; + dname = blkg_dev_name(blkg); + if (!dname) + return; - dname = blkg_dev_name(blkg); - if (!dname) - goto skip; + seq_printf(s, "%s ", dname); - /* - * Hooray string manipulation, count is the size written NOT - * INCLUDING THE \0, so size is now count+1 less than what we - * had before, but we want to start writing the next bit from - * the \0 so we only add count to buf. - */ - off += scnprintf(buf+off, size-off, "%s ", dname); + do { + seq = u64_stats_fetch_begin(&bis->sync); + + rbytes = bis->cur.bytes[BLKG_IOSTAT_READ]; + wbytes = bis->cur.bytes[BLKG_IOSTAT_WRITE]; + dbytes = bis->cur.bytes[BLKG_IOSTAT_DISCARD]; + rios = bis->cur.ios[BLKG_IOSTAT_READ]; + wios = bis->cur.ios[BLKG_IOSTAT_WRITE]; + dios = bis->cur.ios[BLKG_IOSTAT_DISCARD]; + } while (u64_stats_fetch_retry(&bis->sync, seq)); + + if (rbytes || wbytes || rios || wios) { + has_stats = true; + seq_printf(s, "rbytes=%llu wbytes=%llu rios=%llu wios=%llu dbytes=%llu dios=%llu", + rbytes, wbytes, rios, wios, + dbytes, dios); + } - do { - seq = u64_stats_fetch_begin(&bis->sync); + if (blkcg_debug_stats && atomic_read(&blkg->use_delay)) { + has_stats = true; + seq_printf(s, " use_delay=%d delay_nsec=%llu", + atomic_read(&blkg->use_delay), + atomic64_read(&blkg->delay_nsec)); + } - rbytes = bis->cur.bytes[BLKG_IOSTAT_READ]; - wbytes = bis->cur.bytes[BLKG_IOSTAT_WRITE]; - dbytes = bis->cur.bytes[BLKG_IOSTAT_DISCARD]; - rios = bis->cur.ios[BLKG_IOSTAT_READ]; - wios = bis->cur.ios[BLKG_IOSTAT_WRITE]; - dios = bis->cur.ios[BLKG_IOSTAT_DISCARD]; - } while (u64_stats_fetch_retry(&bis->sync, seq)); + for (i = 0; i < BLKCG_MAX_POLS; i++) { + struct blkcg_policy *pol = blkcg_policy[i]; - if (rbytes || wbytes || rios || wios) { - has_stats = true; - off += scnprintf(buf+off, size-off, - "rbytes=%llu wbytes=%llu rios=%llu wios=%llu dbytes=%llu dios=%llu", - rbytes, wbytes, rios, wios, - dbytes, dios); - } + if (!blkg->pd[i] || !pol->pd_stat_fn) + continue; - if (blkcg_debug_stats && atomic_read(&blkg->use_delay)) { + if (pol->pd_stat_fn(blkg->pd[i], s)) has_stats = true; - off += scnprintf(buf+off, size-off, - " use_delay=%d delay_nsec=%llu", - atomic_read(&blkg->use_delay), - (unsigned long long)atomic64_read(&blkg->delay_nsec)); - } + } - for (i = 0; i < BLKCG_MAX_POLS; i++) { - struct blkcg_policy *pol = blkcg_policy[i]; - size_t written; + if (has_stats) + seq_printf(s, "\n"); +} - if (!blkg->pd[i] || !pol->pd_stat_fn) - continue; +static int blkcg_print_stat(struct seq_file *sf, void *v) +{ + struct blkcg *blkcg = css_to_blkcg(seq_css(sf)); + struct blkcg_gq *blkg; - written = pol->pd_stat_fn(blkg->pd[i], buf+off, size-off); - if (written) - has_stats = true; - off += written; - } + if (!seq_css(sf)->parent) + blkcg_fill_root_iostats(); + else + cgroup_rstat_flush(blkcg->css.cgroup); - if (has_stats) { - if (off < size - 1) { - off += scnprintf(buf+off, size-off, "\n"); - seq_commit(sf, off); - } else { - seq_commit(sf, -1); - } - } - skip: + rcu_read_lock(); + hlist_for_each_entry_rcu(blkg, &blkcg->blkg_list, blkcg_node) { + spin_lock_irq(&blkg->q->queue_lock); + blkcg_print_one_stat(blkg, sf); spin_unlock_irq(&blkg->q->queue_lock); } - rcu_read_unlock(); return 0; } diff --git a/block/blk-core.c b/block/blk-core.c index 4f8449b29b21..b5098739f72a 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -14,7 +14,6 @@ */ #include <linux/kernel.h> #include <linux/module.h> -#include <linux/backing-dev.h> #include <linux/bio.h> #include <linux/blkdev.h> #include <linux/blk-mq.h> @@ -393,10 +392,7 @@ void blk_cleanup_queue(struct request_queue *q) /* for synchronous bio-based driver finish in-flight integrity i/o */ blk_flush_integrity(); - /* @q won't process any more request, flush async actions */ - del_timer_sync(&q->backing_dev_info->laptop_mode_wb_timer); blk_sync_queue(q); - if (queue_is_mq(q)) blk_mq_exit_queue(q); @@ -533,20 +529,14 @@ struct request_queue *blk_alloc_queue(int node_id) if (ret) goto fail_id; - q->backing_dev_info = bdi_alloc(node_id); - if (!q->backing_dev_info) - goto fail_split; - q->stats = blk_alloc_queue_stats(); if (!q->stats) - goto fail_stats; + goto fail_split; q->node = node_id; atomic_set(&q->nr_active_requests_shared_sbitmap, 0); - timer_setup(&q->backing_dev_info->laptop_mode_wb_timer, - laptop_mode_timer_fn, 0); timer_setup(&q->timeout, blk_rq_timed_out_timer, 0); INIT_WORK(&q->timeout_work, blk_timeout_work); INIT_LIST_HEAD(&q->icq_list); @@ -571,7 +561,7 @@ struct request_queue *blk_alloc_queue(int node_id) if (percpu_ref_init(&q->q_usage_counter, blk_queue_usage_counter_release, PERCPU_REF_INIT_ATOMIC, GFP_KERNEL)) - goto fail_bdi; + goto fail_stats; if (blkcg_init_queue(q)) goto fail_ref; @@ -584,10 +574,8 @@ struct request_queue *blk_alloc_queue(int node_id) fail_ref: percpu_ref_exit(&q->q_usage_counter); -fail_bdi: - blk_free_queue_stats(q->stats); fail_stats: - bdi_put(q->backing_dev_info); + blk_free_queue_stats(q->stats); fail_split: bioset_exit(&q->bio_split); fail_id: diff --git a/block/blk-crypto.c b/block/blk-crypto.c index c5bdaafffa29..103c2e2d50d6 100644 --- a/block/blk-crypto.c +++ b/block/blk-crypto.c @@ -332,7 +332,7 @@ int blk_crypto_init_key(struct blk_crypto_key *blk_key, const u8 *raw_key, if (mode->keysize == 0) return -EINVAL; - if (dun_bytes == 0 || dun_bytes > BLK_CRYPTO_MAX_IV_SIZE) + if (dun_bytes == 0 || dun_bytes > mode->ivsize) return -EINVAL; if (!is_power_of_2(data_unit_size)) diff --git a/block/blk-integrity.c b/block/blk-integrity.c index 410da060d1f5..69a12177dfb6 100644 --- a/block/blk-integrity.c +++ b/block/blk-integrity.c @@ -431,13 +431,15 @@ void blk_integrity_unregister(struct gendisk *disk) } EXPORT_SYMBOL(blk_integrity_unregister); -void blk_integrity_add(struct gendisk *disk) +int blk_integrity_add(struct gendisk *disk) { - if (kobject_init_and_add(&disk->integrity_kobj, &integrity_ktype, - &disk_to_dev(disk)->kobj, "%s", "integrity")) - return; + int ret; - kobject_uevent(&disk->integrity_kobj, KOBJ_ADD); + ret = kobject_init_and_add(&disk->integrity_kobj, &integrity_ktype, + &disk_to_dev(disk)->kobj, "%s", "integrity"); + if (!ret) + kobject_uevent(&disk->integrity_kobj, KOBJ_ADD); + return ret; } void blk_integrity_del(struct gendisk *disk) diff --git a/block/blk-iocost.c b/block/blk-iocost.c index 0e56557cacf2..b3880e4ba22a 100644 --- a/block/blk-iocost.c +++ b/block/blk-iocost.c @@ -2988,34 +2988,29 @@ static void ioc_pd_free(struct blkg_policy_data *pd) kfree(iocg); } -static size_t ioc_pd_stat(struct blkg_policy_data *pd, char *buf, size_t size) +static bool ioc_pd_stat(struct blkg_policy_data *pd, struct seq_file *s) { struct ioc_gq *iocg = pd_to_iocg(pd); struct ioc *ioc = iocg->ioc; - size_t pos = 0; if (!ioc->enabled) - return 0; + return false; if (iocg->level == 0) { unsigned vp10k = DIV64_U64_ROUND_CLOSEST( ioc->vtime_base_rate * 10000, VTIME_PER_USEC); - pos += scnprintf(buf + pos, size - pos, " cost.vrate=%u.%02u", - vp10k / 100, vp10k % 100); + seq_printf(s, " cost.vrate=%u.%02u", vp10k / 100, vp10k % 100); } - pos += scnprintf(buf + pos, size - pos, " cost.usage=%llu", - iocg->last_stat.usage_us); + seq_printf(s, " cost.usage=%llu", iocg->last_stat.usage_us); if (blkcg_debug_stats) - pos += scnprintf(buf + pos, size - pos, - " cost.wait=%llu cost.indebt=%llu cost.indelay=%llu", - iocg->last_stat.wait_us, - iocg->last_stat.indebt_us, - iocg->last_stat.indelay_us); - - return pos; + seq_printf(s, " cost.wait=%llu cost.indebt=%llu cost.indelay=%llu", + iocg->last_stat.wait_us, + iocg->last_stat.indebt_us, + iocg->last_stat.indelay_us); + return true; } static u64 ioc_weight_prfill(struct seq_file *sf, struct blkg_policy_data *pd, diff --git a/block/blk-iolatency.c b/block/blk-iolatency.c index d8b0d8bd132b..c0545f9da549 100644 --- a/block/blk-iolatency.c +++ b/block/blk-iolatency.c @@ -890,8 +890,7 @@ static int iolatency_print_limit(struct seq_file *sf, void *v) return 0; } -static size_t iolatency_ssd_stat(struct iolatency_grp *iolat, char *buf, - size_t size) +static bool iolatency_ssd_stat(struct iolatency_grp *iolat, struct seq_file *s) { struct latency_stat stat; int cpu; @@ -906,39 +905,40 @@ static size_t iolatency_ssd_stat(struct iolatency_grp *iolat, char *buf, preempt_enable(); if (iolat->rq_depth.max_depth == UINT_MAX) - return scnprintf(buf, size, " missed=%llu total=%llu depth=max", - (unsigned long long)stat.ps.missed, - (unsigned long long)stat.ps.total); - return scnprintf(buf, size, " missed=%llu total=%llu depth=%u", - (unsigned long long)stat.ps.missed, - (unsigned long long)stat.ps.total, - iolat->rq_depth.max_depth); + seq_printf(s, " missed=%llu total=%llu depth=max", + (unsigned long long)stat.ps.missed, + (unsigned long long)stat.ps.total); + else + seq_printf(s, " missed=%llu total=%llu depth=%u", + (unsigned long long)stat.ps.missed, + (unsigned long long)stat.ps.total, + iolat->rq_depth.max_depth); + return true; } -static size_t iolatency_pd_stat(struct blkg_policy_data *pd, char *buf, - size_t size) +static bool iolatency_pd_stat(struct blkg_policy_data *pd, struct seq_file *s) { struct iolatency_grp *iolat = pd_to_lat(pd); unsigned long long avg_lat; unsigned long long cur_win; if (!blkcg_debug_stats) - return 0; + return false; if (iolat->ssd) - return iolatency_ssd_stat(iolat, buf, size); + return iolatency_ssd_stat(iolat, s); avg_lat = div64_u64(iolat->lat_avg, NSEC_PER_USEC); cur_win = div64_u64(iolat->cur_win_nsec, NSEC_PER_MSEC); if (iolat->rq_depth.max_depth == UINT_MAX) - return scnprintf(buf, size, " depth=max avg_lat=%llu win=%llu", - avg_lat, cur_win); - - return scnprintf(buf, size, " depth=%u avg_lat=%llu win=%llu", - iolat->rq_depth.max_depth, avg_lat, cur_win); + seq_printf(s, " depth=max avg_lat=%llu win=%llu", + avg_lat, cur_win); + else + seq_printf(s, " depth=%u avg_lat=%llu win=%llu", + iolat->rq_depth.max_depth, avg_lat, cur_win); + return true; } - static struct blkg_policy_data *iolatency_pd_alloc(gfp_t gfp, struct request_queue *q, struct blkcg *blkcg) diff --git a/block/blk-map.c b/block/blk-map.c index 3743158ddaeb..d1448aaad980 100644 --- a/block/blk-map.c +++ b/block/blk-map.c @@ -400,7 +400,7 @@ static void bio_copy_kern_endio_read(struct bio *bio) struct bvec_iter_all iter_all; bio_for_each_segment_all(bvec, bio, iter_all) { - memcpy(p, page_address(bvec->bv_page), bvec->bv_len); + memcpy_from_bvec(p, bvec); p += bvec->bv_len; } diff --git a/block/blk-merge.c b/block/blk-merge.c index a11b3b53717e..eeba8422ae82 100644 --- a/block/blk-merge.c +++ b/block/blk-merge.c @@ -348,6 +348,8 @@ void __blk_queue_split(struct bio **bio, unsigned int *nr_segs) trace_block_split(split, (*bio)->bi_iter.bi_sector); submit_bio_noacct(*bio); *bio = split; + + blk_throtl_charge_bio_split(*bio); } } @@ -705,22 +707,6 @@ static void blk_account_io_merge_request(struct request *req) } } -/* - * Two cases of handling DISCARD merge: - * If max_discard_segments > 1, the driver takes every bio - * as a range and send them to controller together. The ranges - * needn't to be contiguous. - * Otherwise, the bios/requests will be handled as same as - * others which should be contiguous. - */ -static inline bool blk_discard_mergable(struct request *req) -{ - if (req_op(req) == REQ_OP_DISCARD && - queue_max_discard_segments(req->q) > 1) - return true; - return false; -} - static enum elv_merge blk_try_req_merge(struct request *req, struct request *next) { diff --git a/block/blk-mq-sysfs.c b/block/blk-mq-sysfs.c index 7b52e7657b2d..253c857cba47 100644 --- a/block/blk-mq-sysfs.c +++ b/block/blk-mq-sysfs.c @@ -45,60 +45,12 @@ static void blk_mq_hw_sysfs_release(struct kobject *kobj) kfree(hctx); } -struct blk_mq_ctx_sysfs_entry { - struct attribute attr; - ssize_t (*show)(struct blk_mq_ctx *, char *); - ssize_t (*store)(struct blk_mq_ctx *, const char *, size_t); -}; - 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_sysfs_show(struct kobject *kobj, struct attribute *attr, - char *page) -{ - struct blk_mq_ctx_sysfs_entry *entry; - struct blk_mq_ctx *ctx; - struct request_queue *q; - ssize_t res; - - entry = container_of(attr, struct blk_mq_ctx_sysfs_entry, attr); - ctx = container_of(kobj, struct blk_mq_ctx, kobj); - q = ctx->queue; - - if (!entry->show) - return -EIO; - - mutex_lock(&q->sysfs_lock); - res = entry->show(ctx, page); - mutex_unlock(&q->sysfs_lock); - return res; -} - -static ssize_t blk_mq_sysfs_store(struct kobject *kobj, struct attribute *attr, - const char *page, size_t length) -{ - struct blk_mq_ctx_sysfs_entry *entry; - struct blk_mq_ctx *ctx; - struct request_queue *q; - ssize_t res; - - entry = container_of(attr, struct blk_mq_ctx_sysfs_entry, attr); - ctx = container_of(kobj, struct blk_mq_ctx, kobj); - q = ctx->queue; - - if (!entry->store) - return -EIO; - - mutex_lock(&q->sysfs_lock); - res = entry->store(ctx, page, length); - mutex_unlock(&q->sysfs_lock); - return res; -} - static ssize_t blk_mq_hw_sysfs_show(struct kobject *kobj, struct attribute *attr, char *page) { @@ -198,23 +150,16 @@ static struct attribute *default_hw_ctx_attrs[] = { }; ATTRIBUTE_GROUPS(default_hw_ctx); -static const struct sysfs_ops blk_mq_sysfs_ops = { - .show = blk_mq_sysfs_show, - .store = blk_mq_sysfs_store, -}; - 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 = { - .sysfs_ops = &blk_mq_sysfs_ops, .release = blk_mq_sysfs_release, }; static struct kobj_type blk_mq_ctx_ktype = { - .sysfs_ops = &blk_mq_sysfs_ops, .release = blk_mq_ctx_sysfs_release, }; diff --git a/block/blk-mq.c b/block/blk-mq.c index d0b881eed032..944049982e6e 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -525,7 +525,7 @@ void blk_mq_free_request(struct request *rq) __blk_mq_dec_active_requests(hctx); if (unlikely(laptop_mode && !blk_rq_is_passthrough(rq))) - laptop_io_completion(q->backing_dev_info); + laptop_io_completion(q->disk->bdi); rq_qos_done(q, rq); @@ -3115,7 +3115,8 @@ struct request_queue *blk_mq_init_queue(struct blk_mq_tag_set *set) } EXPORT_SYMBOL(blk_mq_init_queue); -struct gendisk *__blk_mq_alloc_disk(struct blk_mq_tag_set *set, void *queuedata) +struct gendisk *__blk_mq_alloc_disk(struct blk_mq_tag_set *set, void *queuedata, + struct lock_class_key *lkclass) { struct request_queue *q; struct gendisk *disk; @@ -3124,12 +3125,11 @@ struct gendisk *__blk_mq_alloc_disk(struct blk_mq_tag_set *set, void *queuedata) if (IS_ERR(q)) return ERR_CAST(q); - disk = __alloc_disk_node(0, set->numa_node); + disk = __alloc_disk_node(q, set->numa_node, lkclass); if (!disk) { blk_cleanup_queue(q); return ERR_PTR(-ENOMEM); } - disk->queue = q; return disk; } EXPORT_SYMBOL(__blk_mq_alloc_disk); diff --git a/block/blk-settings.c b/block/blk-settings.c index 902c40d67120..a7c857ad7d10 100644 --- a/block/blk-settings.c +++ b/block/blk-settings.c @@ -8,6 +8,7 @@ #include <linux/bio.h> #include <linux/blkdev.h> #include <linux/pagemap.h> +#include <linux/backing-dev-defs.h> #include <linux/gcd.h> #include <linux/lcm.h> #include <linux/jiffies.h> @@ -140,7 +141,9 @@ void blk_queue_max_hw_sectors(struct request_queue *q, unsigned int max_hw_secto limits->logical_block_size >> SECTOR_SHIFT); limits->max_sectors = max_sectors; - q->backing_dev_info->io_pages = max_sectors >> (PAGE_SHIFT - 9); + if (!q->disk) + return; + q->disk->bdi->io_pages = max_sectors >> (PAGE_SHIFT - 9); } EXPORT_SYMBOL(blk_queue_max_hw_sectors); @@ -380,18 +383,19 @@ void blk_queue_alignment_offset(struct request_queue *q, unsigned int offset) } EXPORT_SYMBOL(blk_queue_alignment_offset); -void blk_queue_update_readahead(struct request_queue *q) +void disk_update_readahead(struct gendisk *disk) { + struct request_queue *q = disk->queue; + /* * For read-ahead of large files to be effective, we need to read ahead * at least twice the optimal I/O size. */ - q->backing_dev_info->ra_pages = + disk->bdi->ra_pages = max(queue_io_opt(q) * 2 / PAGE_SIZE, VM_READAHEAD_PAGES); - q->backing_dev_info->io_pages = - queue_max_sectors(q) >> (PAGE_SHIFT - 9); + disk->bdi->io_pages = queue_max_sectors(q) >> (PAGE_SHIFT - 9); } -EXPORT_SYMBOL_GPL(blk_queue_update_readahead); +EXPORT_SYMBOL_GPL(disk_update_readahead); /** * blk_limits_io_min - set minimum request size for a device @@ -471,7 +475,9 @@ EXPORT_SYMBOL(blk_limits_io_opt); void blk_queue_io_opt(struct request_queue *q, unsigned int opt) { blk_limits_io_opt(&q->limits, opt); - q->backing_dev_info->ra_pages = + if (!q->disk) + return; + q->disk->bdi->ra_pages = max(queue_io_opt(q) * 2 / PAGE_SIZE, VM_READAHEAD_PAGES); } EXPORT_SYMBOL(blk_queue_io_opt); @@ -661,17 +667,11 @@ void disk_stack_limits(struct gendisk *disk, struct block_device *bdev, struct request_queue *t = disk->queue; if (blk_stack_limits(&t->limits, &bdev_get_queue(bdev)->limits, - get_start_sect(bdev) + (offset >> 9)) < 0) { - char top[BDEVNAME_SIZE], bottom[BDEVNAME_SIZE]; - - disk_name(disk, 0, top); - bdevname(bdev, bottom); - - printk(KERN_NOTICE "%s: Warning: Device %s is misaligned\n", - top, bottom); - } + get_start_sect(bdev) + (offset >> 9)) < 0) + pr_notice("%s: Warning: Device %pg is misaligned\n", + disk->disk_name, bdev); - blk_queue_update_readahead(disk->queue); + disk_update_readahead(disk); } EXPORT_SYMBOL(disk_stack_limits); diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c index 370d83c18057..614d9d47de36 100644 --- a/block/blk-sysfs.c +++ b/block/blk-sysfs.c @@ -88,9 +88,11 @@ queue_requests_store(struct request_queue *q, const char *page, size_t count) static ssize_t queue_ra_show(struct request_queue *q, char *page) { - unsigned long ra_kb = q->backing_dev_info->ra_pages << - (PAGE_SHIFT - 10); + unsigned long ra_kb; + if (!q->disk) + return -EINVAL; + ra_kb = q->disk->bdi->ra_pages << (PAGE_SHIFT - 10); return queue_var_show(ra_kb, page); } @@ -98,13 +100,14 @@ static ssize_t queue_ra_store(struct request_queue *q, const char *page, size_t count) { unsigned long ra_kb; - ssize_t ret = queue_var_store(&ra_kb, page, count); + ssize_t ret; + if (!q->disk) + return -EINVAL; + ret = queue_var_store(&ra_kb, page, count); if (ret < 0) return ret; - - q->backing_dev_info->ra_pages = ra_kb >> (PAGE_SHIFT - 10); - + q->disk->bdi->ra_pages = ra_kb >> (PAGE_SHIFT - 10); return ret; } @@ -251,7 +254,8 @@ queue_max_sectors_store(struct request_queue *q, const char *page, size_t count) spin_lock_irq(&q->queue_lock); q->limits.max_sectors = max_sectors_kb << 1; - q->backing_dev_info->io_pages = max_sectors_kb >> (PAGE_SHIFT - 10); + if (q->disk) + q->disk->bdi->io_pages = max_sectors_kb >> (PAGE_SHIFT - 10); spin_unlock_irq(&q->queue_lock); return ret; @@ -766,13 +770,6 @@ static void blk_exit_queue(struct request_queue *q) * e.g. blkcg_print_blkgs() to crash. */ blkcg_exit_queue(q); - - /* - * Since the cgroup code may dereference the @q->backing_dev_info - * pointer, only decrease its reference count after having removed the - * association with the block cgroup controller. - */ - bdi_put(q->backing_dev_info); } /** @@ -859,15 +856,6 @@ int blk_register_queue(struct gendisk *disk) struct device *dev = disk_to_dev(disk); struct request_queue *q = disk->queue; - if (WARN_ON(!q)) - return -ENXIO; - - WARN_ONCE(blk_queue_registered(q), - "%s is registering an already registered queue\n", - kobject_name(&dev->kobj)); - - blk_queue_update_readahead(q); - ret = blk_trace_init_sysfs(dev); if (ret) return ret; @@ -941,7 +929,6 @@ unlock: return ret; } -EXPORT_SYMBOL_GPL(blk_register_queue); /** * blk_unregister_queue - counterpart of blk_register_queue() diff --git a/block/blk-throttle.c b/block/blk-throttle.c index b1b22d863bdf..55c49015e533 100644 --- a/block/blk-throttle.c +++ b/block/blk-throttle.c @@ -178,6 +178,9 @@ struct throtl_grp { unsigned int bad_bio_cnt; /* bios exceeding latency threshold */ unsigned long bio_cnt_reset_time; + atomic_t io_split_cnt[2]; + atomic_t last_io_split_cnt[2]; + struct blkg_rwstat stat_bytes; struct blkg_rwstat stat_ios; }; @@ -777,6 +780,8 @@ static inline void throtl_start_new_slice_with_credit(struct throtl_grp *tg, tg->bytes_disp[rw] = 0; tg->io_disp[rw] = 0; + atomic_set(&tg->io_split_cnt[rw], 0); + /* * Previous slice has expired. We must have trimmed it after last * bio dispatch. That means since start of last slice, we never used @@ -799,6 +804,9 @@ static inline void throtl_start_new_slice(struct throtl_grp *tg, bool rw) tg->io_disp[rw] = 0; tg->slice_start[rw] = jiffies; tg->slice_end[rw] = jiffies + tg->td->throtl_slice; + + atomic_set(&tg->io_split_cnt[rw], 0); + throtl_log(&tg->service_queue, "[%c] new slice start=%lu end=%lu jiffies=%lu", rw == READ ? 'R' : 'W', tg->slice_start[rw], @@ -1031,6 +1039,9 @@ static bool tg_may_dispatch(struct throtl_grp *tg, struct bio *bio, jiffies + tg->td->throtl_slice); } + if (iops_limit != UINT_MAX) + tg->io_disp[rw] += atomic_xchg(&tg->io_split_cnt[rw], 0); + if (tg_with_in_bps_limit(tg, bio, bps_limit, &bps_wait) && tg_with_in_iops_limit(tg, bio, iops_limit, &iops_wait)) { if (wait) @@ -2052,12 +2063,14 @@ static void throtl_downgrade_check(struct throtl_grp *tg) } if (tg->iops[READ][LIMIT_LOW]) { + tg->last_io_disp[READ] += atomic_xchg(&tg->last_io_split_cnt[READ], 0); iops = tg->last_io_disp[READ] * HZ / elapsed_time; if (iops >= tg->iops[READ][LIMIT_LOW]) tg->last_low_overflow_time[READ] = now; } if (tg->iops[WRITE][LIMIT_LOW]) { + tg->last_io_disp[WRITE] += atomic_xchg(&tg->last_io_split_cnt[WRITE], 0); iops = tg->last_io_disp[WRITE] * HZ / elapsed_time; if (iops >= tg->iops[WRITE][LIMIT_LOW]) tg->last_low_overflow_time[WRITE] = now; @@ -2176,6 +2189,25 @@ static inline void throtl_update_latency_buckets(struct throtl_data *td) } #endif +void blk_throtl_charge_bio_split(struct bio *bio) +{ + struct blkcg_gq *blkg = bio->bi_blkg; + struct throtl_grp *parent = blkg_to_tg(blkg); + struct throtl_service_queue *parent_sq; + bool rw = bio_data_dir(bio); + + do { + if (!parent->has_rules[rw]) + break; + + atomic_inc(&parent->io_split_cnt[rw]); + atomic_inc(&parent->last_io_split_cnt[rw]); + + parent_sq = parent->service_queue.parent_sq; + parent = sq_to_tg(parent_sq); + } while (parent); +} + bool blk_throtl_bio(struct bio *bio) { struct request_queue *q = bio->bi_bdev->bd_disk->queue; diff --git a/block/blk-wbt.c b/block/blk-wbt.c index 3ed71b8da887..874c1c37bf0c 100644 --- a/block/blk-wbt.c +++ b/block/blk-wbt.c @@ -97,7 +97,7 @@ 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->backing_dev_info->wb; + struct bdi_writeback *wb = &rwb->rqos.q->disk->bdi->wb; return time_before(jiffies, wb->dirty_sleep + HZ); } @@ -234,7 +234,7 @@ enum { static int latency_exceeded(struct rq_wb *rwb, struct blk_rq_stat *stat) { - struct backing_dev_info *bdi = rwb->rqos.q->backing_dev_info; + struct backing_dev_info *bdi = rwb->rqos.q->disk->bdi; struct rq_depth *rqd = &rwb->rq_depth; u64 thislat; @@ -287,7 +287,7 @@ 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->backing_dev_info; + struct backing_dev_info *bdi = rwb->rqos.q->disk->bdi; struct rq_depth *rqd = &rwb->rq_depth; trace_wbt_step(bdi, msg, rqd->scale_step, rwb->cur_win_nsec, @@ -359,7 +359,7 @@ static void wb_timer_fn(struct blk_stat_callback *cb) status = latency_exceeded(rwb, cb->stat); - trace_wbt_timer(rwb->rqos.q->backing_dev_info, status, rqd->scale_step, + trace_wbt_timer(rwb->rqos.q->disk->bdi, status, rqd->scale_step, inflight); /* diff --git a/block/blk-zoned.c b/block/blk-zoned.c index 86fce751bb17..1d0c76c18fc5 100644 --- a/block/blk-zoned.c +++ b/block/blk-zoned.c @@ -360,9 +360,6 @@ int blkdev_report_zones_ioctl(struct block_device *bdev, fmode_t mode, if (!blk_queue_is_zoned(q)) return -ENOTTY; - if (!capable(CAP_SYS_ADMIN)) - return -EACCES; - if (copy_from_user(&rep, argp, sizeof(struct blk_zone_report))) return -EFAULT; @@ -421,9 +418,6 @@ int blkdev_zone_mgmt_ioctl(struct block_device *bdev, fmode_t mode, if (!blk_queue_is_zoned(q)) return -ENOTTY; - if (!capable(CAP_SYS_ADMIN)) - return -EACCES; - if (!(mode & FMODE_WRITE)) return -EBADF; diff --git a/block/blk.h b/block/blk.h index cb01429c162c..346d184c82b0 100644 --- a/block/blk.h +++ b/block/blk.h @@ -128,7 +128,7 @@ static inline bool integrity_req_gap_front_merge(struct request *req, bip_next->bip_vec[0].bv_offset); } -void blk_integrity_add(struct gendisk *); +int blk_integrity_add(struct gendisk *disk); void blk_integrity_del(struct gendisk *); #else /* CONFIG_BLK_DEV_INTEGRITY */ static inline bool blk_integrity_merge_rq(struct request_queue *rq, @@ -162,8 +162,9 @@ static inline bool bio_integrity_endio(struct bio *bio) static inline void bio_integrity_free(struct bio *bio) { } -static inline void blk_integrity_add(struct gendisk *disk) +static inline int blk_integrity_add(struct gendisk *disk) { + return 0; } static inline void blk_integrity_del(struct gendisk *disk) { @@ -289,11 +290,13 @@ int create_task_io_context(struct task_struct *task, gfp_t gfp_mask, int node); extern int blk_throtl_init(struct request_queue *q); extern void blk_throtl_exit(struct request_queue *q); extern void blk_throtl_register_queue(struct request_queue *q); +extern void blk_throtl_charge_bio_split(struct bio *bio); bool blk_throtl_bio(struct bio *bio); #else /* CONFIG_BLK_DEV_THROTTLING */ static inline int blk_throtl_init(struct request_queue *q) { return 0; } static inline void blk_throtl_exit(struct request_queue *q) { } static inline void blk_throtl_register_queue(struct request_queue *q) { } +static inline void blk_throtl_charge_bio_split(struct bio *bio) { } static inline bool blk_throtl_bio(struct bio *bio) { return false; } #endif /* CONFIG_BLK_DEV_THROTTLING */ #ifdef CONFIG_BLK_DEV_THROTTLING_LOW @@ -340,15 +343,14 @@ static inline void blk_queue_clear_zone_settings(struct request_queue *q) {} int blk_alloc_ext_minor(void); void blk_free_ext_minor(unsigned int minor); -char *disk_name(struct gendisk *hd, int partno, char *buf); #define ADDPART_FLAG_NONE 0 #define ADDPART_FLAG_RAID 1 #define ADDPART_FLAG_WHOLEDISK 2 -int bdev_add_partition(struct block_device *bdev, int partno, - sector_t start, sector_t length); -int bdev_del_partition(struct block_device *bdev, int partno); -int bdev_resize_partition(struct block_device *bdev, int partno, - sector_t start, sector_t length); +int bdev_add_partition(struct gendisk *disk, int partno, sector_t start, + sector_t length); +int bdev_del_partition(struct gendisk *disk, int partno); +int bdev_resize_partition(struct gendisk *disk, int partno, sector_t start, + sector_t length); int bio_add_hw_page(struct request_queue *q, struct bio *bio, struct page *page, unsigned int len, unsigned int offset, @@ -356,7 +358,7 @@ int bio_add_hw_page(struct request_queue *q, struct bio *bio, struct request_queue *blk_alloc_queue(int node_id); -void disk_alloc_events(struct gendisk *disk); +int disk_alloc_events(struct gendisk *disk); void disk_add_events(struct gendisk *disk); void disk_del_events(struct gendisk *disk); void disk_release_events(struct gendisk *disk); diff --git a/block/bounce.c b/block/bounce.c index 94081e013c58..05fc7148489d 100644 --- a/block/bounce.c +++ b/block/bounce.c @@ -68,25 +68,12 @@ static __init int init_emergency_pool(void) __initcall(init_emergency_pool); /* - * highmem version, map in to vec - */ -static void bounce_copy_vec(struct bio_vec *to, unsigned char *vfrom) -{ - unsigned char *vto; - - vto = kmap_atomic(to->bv_page); - memcpy(vto + to->bv_offset, vfrom, to->bv_len); - kunmap_atomic(vto); -} - -/* * Simple bounce buffer support for highmem pages. Depending on the * queue gfp mask set, *to may or may not be a highmem page. kmap it * always, it will do the Right Thing */ static void copy_to_high_bio_irq(struct bio *to, struct bio *from) { - unsigned char *vfrom; struct bio_vec tovec, fromvec; struct bvec_iter iter; /* @@ -104,11 +91,8 @@ static void copy_to_high_bio_irq(struct bio *to, struct bio *from) * been modified by the block layer, so use the original * copy, bounce_copy_vec already uses tovec->bv_len */ - vfrom = page_address(fromvec.bv_page) + - tovec.bv_offset; - - bounce_copy_vec(&tovec, vfrom); - flush_dcache_page(tovec.bv_page); + memcpy_to_bvec(&tovec, page_address(fromvec.bv_page) + + tovec.bv_offset); } bio_advance_iter(from, &from_iter, tovec.bv_len); } @@ -255,24 +239,19 @@ void __blk_queue_bounce(struct request_queue *q, struct bio **bio_orig) * because the 'bio' is single-page bvec. */ for (i = 0, to = bio->bi_io_vec; i < bio->bi_vcnt; to++, i++) { - struct page *page = to->bv_page; + struct page *bounce_page; - if (!PageHighMem(page)) + if (!PageHighMem(to->bv_page)) continue; - to->bv_page = mempool_alloc(&page_pool, GFP_NOIO); - inc_zone_page_state(to->bv_page, NR_BOUNCE); + bounce_page = mempool_alloc(&page_pool, GFP_NOIO); + inc_zone_page_state(bounce_page, NR_BOUNCE); if (rw == WRITE) { - char *vto, *vfrom; - - flush_dcache_page(page); - - vto = page_address(to->bv_page) + to->bv_offset; - vfrom = kmap_atomic(page) + to->bv_offset; - memcpy(vto, vfrom, to->bv_len); - kunmap_atomic(vfrom); + flush_dcache_page(to->bv_page); + memcpy_from_bvec(page_address(bounce_page), to); } + to->bv_page = bounce_page; } trace_block_bio_bounce(*bio_orig); diff --git a/block/cmdline-parser.c b/block/cmdline-parser.c deleted file mode 100644 index f2a14571882b..000000000000 --- a/block/cmdline-parser.c +++ /dev/null @@ -1,255 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * Parse command line, get partition information - * - * Written by Cai Zhiyong <caizhiyong@huawei.com> - * - */ -#include <linux/export.h> -#include <linux/cmdline-parser.h> - -static int parse_subpart(struct cmdline_subpart **subpart, char *partdef) -{ - int ret = 0; - struct cmdline_subpart *new_subpart; - - *subpart = NULL; - - new_subpart = kzalloc(sizeof(struct cmdline_subpart), GFP_KERNEL); - if (!new_subpart) - return -ENOMEM; - - if (*partdef == '-') { - new_subpart->size = (sector_t)(~0ULL); - partdef++; - } else { - new_subpart->size = (sector_t)memparse(partdef, &partdef); - if (new_subpart->size < (sector_t)PAGE_SIZE) { - pr_warn("cmdline partition size is invalid."); - ret = -EINVAL; - goto fail; - } - } - - if (*partdef == '@') { - partdef++; - new_subpart->from = (sector_t)memparse(partdef, &partdef); - } else { - new_subpart->from = (sector_t)(~0ULL); - } - - if (*partdef == '(') { - int length; - char *next = strchr(++partdef, ')'); - - if (!next) { - pr_warn("cmdline partition format is invalid."); - ret = -EINVAL; - goto fail; - } - - length = min_t(int, next - partdef, - sizeof(new_subpart->name) - 1); - strncpy(new_subpart->name, partdef, length); - new_subpart->name[length] = '\0'; - - partdef = ++next; - } else - new_subpart->name[0] = '\0'; - - new_subpart->flags = 0; - - if (!strncmp(partdef, "ro", 2)) { - new_subpart->flags |= PF_RDONLY; - partdef += 2; - } - - if (!strncmp(partdef, "lk", 2)) { - new_subpart->flags |= PF_POWERUP_LOCK; - partdef += 2; - } - - *subpart = new_subpart; - return 0; -fail: - kfree(new_subpart); - return ret; -} - -static void free_subpart(struct cmdline_parts *parts) -{ - struct cmdline_subpart *subpart; - - while (parts->subpart) { - subpart = parts->subpart; - parts->subpart = subpart->next_subpart; - kfree(subpart); - } -} - -static int parse_parts(struct cmdline_parts **parts, const char *bdevdef) -{ - int ret = -EINVAL; - char *next; - int length; - struct cmdline_subpart **next_subpart; - struct cmdline_parts *newparts; - char buf[BDEVNAME_SIZE + 32 + 4]; - - *parts = NULL; - - newparts = kzalloc(sizeof(struct cmdline_parts), GFP_KERNEL); - if (!newparts) - return -ENOMEM; - - next = strchr(bdevdef, ':'); - if (!next) { - pr_warn("cmdline partition has no block device."); - goto fail; - } - - length = min_t(int, next - bdevdef, sizeof(newparts->name) - 1); - strncpy(newparts->name, bdevdef, length); - newparts->name[length] = '\0'; - newparts->nr_subparts = 0; - - next_subpart = &newparts->subpart; - - while (next && *(++next)) { - bdevdef = next; - next = strchr(bdevdef, ','); - - length = (!next) ? (sizeof(buf) - 1) : - min_t(int, next - bdevdef, sizeof(buf) - 1); - - strncpy(buf, bdevdef, length); - buf[length] = '\0'; - - ret = parse_subpart(next_subpart, buf); - if (ret) - goto fail; - - newparts->nr_subparts++; - next_subpart = &(*next_subpart)->next_subpart; - } - - if (!newparts->subpart) { - pr_warn("cmdline partition has no valid partition."); - ret = -EINVAL; - goto fail; - } - - *parts = newparts; - - return 0; -fail: - free_subpart(newparts); - kfree(newparts); - return ret; -} - -void cmdline_parts_free(struct cmdline_parts **parts) -{ - struct cmdline_parts *next_parts; - - while (*parts) { - next_parts = (*parts)->next_parts; - free_subpart(*parts); - kfree(*parts); - *parts = next_parts; - } -} -EXPORT_SYMBOL(cmdline_parts_free); - -int cmdline_parts_parse(struct cmdline_parts **parts, const char *cmdline) -{ - int ret; - char *buf; - char *pbuf; - char *next; - struct cmdline_parts **next_parts; - - *parts = NULL; - - next = pbuf = buf = kstrdup(cmdline, GFP_KERNEL); - if (!buf) - return -ENOMEM; - - next_parts = parts; - - while (next && *pbuf) { - next = strchr(pbuf, ';'); - if (next) - *next = '\0'; - - ret = parse_parts(next_parts, pbuf); - if (ret) - goto fail; - - if (next) - pbuf = ++next; - - next_parts = &(*next_parts)->next_parts; - } - - if (!*parts) { - pr_warn("cmdline partition has no valid partition."); - ret = -EINVAL; - goto fail; - } - - ret = 0; -done: - kfree(buf); - return ret; - -fail: - cmdline_parts_free(parts); - goto done; -} -EXPORT_SYMBOL(cmdline_parts_parse); - -struct cmdline_parts *cmdline_parts_find(struct cmdline_parts *parts, - const char *bdev) -{ - while (parts && strncmp(bdev, parts->name, sizeof(parts->name))) - parts = parts->next_parts; - return parts; -} -EXPORT_SYMBOL(cmdline_parts_find); - -/* - * add_part() - * 0 success. - * 1 can not add so many partitions. - */ -int cmdline_parts_set(struct cmdline_parts *parts, sector_t disk_size, - int slot, - int (*add_part)(int, struct cmdline_subpart *, void *), - void *param) -{ - sector_t from = 0; - struct cmdline_subpart *subpart; - - for (subpart = parts->subpart; subpart; - subpart = subpart->next_subpart, slot++) { - if (subpart->from == (sector_t)(~0ULL)) - subpart->from = from; - else - from = subpart->from; - - if (from >= disk_size) - break; - - if (subpart->size > (disk_size - from)) - subpart->size = disk_size - from; - - from += subpart->size; - - if (add_part(slot, subpart, param)) - break; - } - - return slot; -} -EXPORT_SYMBOL(cmdline_parts_set); diff --git a/block/disk-events.c b/block/disk-events.c index a75931ff5da4..8d5496e7592a 100644 --- a/block/disk-events.c +++ b/block/disk-events.c @@ -163,15 +163,31 @@ void disk_flush_events(struct gendisk *disk, unsigned int mask) spin_unlock_irq(&ev->lock); } +/* + * Tell userland about new events. Only the events listed in @disk->events are + * reported, and only if DISK_EVENT_FLAG_UEVENT is set. Otherwise, events are + * processed internally but never get reported to userland. + */ +static void disk_event_uevent(struct gendisk *disk, unsigned int events) +{ + char *envp[ARRAY_SIZE(disk_uevents) + 1] = { }; + int nr_events = 0, i; + + for (i = 0; i < ARRAY_SIZE(disk_uevents); i++) + if (events & disk->events & (1 << i)) + envp[nr_events++] = disk_uevents[i]; + + if (nr_events) + kobject_uevent_env(&disk_to_dev(disk)->kobj, KOBJ_CHANGE, envp); +} + static void disk_check_events(struct disk_events *ev, unsigned int *clearing_ptr) { struct gendisk *disk = ev->disk; - char *envp[ARRAY_SIZE(disk_uevents) + 1] = { }; unsigned int clearing = *clearing_ptr; unsigned int events; unsigned long intv; - int nr_events = 0, i; /* check events */ events = disk->fops->check_events(disk, clearing); @@ -190,19 +206,11 @@ static void disk_check_events(struct disk_events *ev, spin_unlock_irq(&ev->lock); - /* - * Tell userland about new events. Only the events listed in - * @disk->events are reported, and only if DISK_EVENT_FLAG_UEVENT - * is set. Otherwise, events are processed internally but never - * get reported to userland. - */ - for (i = 0; i < ARRAY_SIZE(disk_uevents); i++) - if ((events & disk->events & (1 << i)) && - (disk->event_flags & DISK_EVENT_FLAG_UEVENT)) - envp[nr_events++] = disk_uevents[i]; + if (events & DISK_EVENT_MEDIA_CHANGE) + inc_diskseq(disk); - if (nr_events) - kobject_uevent_env(&disk_to_dev(disk)->kobj, KOBJ_CHANGE, envp); + if (disk->event_flags & DISK_EVENT_FLAG_UEVENT) + disk_event_uevent(disk, events); } /** @@ -281,6 +289,32 @@ bool bdev_check_media_change(struct block_device *bdev) } EXPORT_SYMBOL(bdev_check_media_change); +/** + * disk_force_media_change - force a media change event + * @disk: the disk which will raise the event + * @events: the events to raise + * + * Generate uevents for the disk. If DISK_EVENT_MEDIA_CHANGE is present, + * attempt to free all dentries and inodes and invalidates all block + * device page cache entries in that case. + * + * Returns %true if DISK_EVENT_MEDIA_CHANGE was raised, or %false if not. + */ +bool disk_force_media_change(struct gendisk *disk, unsigned int events) +{ + disk_event_uevent(disk, events); + + if (!(events & DISK_EVENT_MEDIA_CHANGE)) + return false; + + if (__invalidate_device(disk->part0, true)) + pr_warn("VFS: busy inodes on changed media %s\n", + disk->disk_name); + set_bit(GD_NEED_PART_SCAN, &disk->state); + return true; +} +EXPORT_SYMBOL_GPL(disk_force_media_change); + /* * Separate this part out so that a different pointer for clearing_ptr can be * passed in for disk_clear_events. @@ -410,17 +444,17 @@ module_param_cb(events_dfl_poll_msecs, &disk_events_dfl_poll_msecs_param_ops, /* * disk_{alloc|add|del|release}_events - initialize and destroy disk_events. */ -void disk_alloc_events(struct gendisk *disk) +int disk_alloc_events(struct gendisk *disk) { struct disk_events *ev; if (!disk->fops->check_events || !disk->events) - return; + return 0; ev = kzalloc(sizeof(*ev), GFP_KERNEL); if (!ev) { pr_warn("%s: failed to initialize events\n", disk->disk_name); - return; + return -ENOMEM; } INIT_LIST_HEAD(&ev->node); @@ -432,6 +466,7 @@ void disk_alloc_events(struct gendisk *disk) INIT_DELAYED_WORK(&ev->dwork, disk_events_workfn); disk->ev = ev; + return 0; } void disk_add_events(struct gendisk *disk) diff --git a/block/elevator.c b/block/elevator.c index 52ada14cfe45..ff45d8388f48 100644 --- a/block/elevator.c +++ b/block/elevator.c @@ -336,6 +336,9 @@ enum elv_merge elv_merge(struct request_queue *q, struct request **req, __rq = elv_rqhash_find(q, bio->bi_iter.bi_sector); if (__rq && elv_bio_merge_ok(__rq, bio)) { *req = __rq; + + if (blk_discard_mergable(__rq)) + return ELEVATOR_DISCARD_MERGE; return ELEVATOR_BACK_MERGE; } @@ -630,6 +633,9 @@ static inline bool elv_support_iosched(struct request_queue *q) */ static struct elevator_type *elevator_get_default(struct request_queue *q) { + if (q->tag_set && q->tag_set->flags & BLK_MQ_F_NO_SCHED_BY_DEFAULT) + return NULL; + if (q->nr_hw_queues != 1 && !blk_mq_is_sbitmap_shared(q->tag_set->flags)) return NULL; @@ -702,7 +708,6 @@ void elevator_init_mq(struct request_queue *q) elevator_put(e); } } -EXPORT_SYMBOL_GPL(elevator_init_mq); /* only for dm-rq */ /* * switch to new_e io scheduler. be careful not to introduce deadlocks - diff --git a/block/genhd.c b/block/genhd.c index 298ee78c1bda..567549a011d1 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -29,6 +29,23 @@ static struct kobject *block_depr; +/* + * Unique, monotonically increasing sequential number associated with block + * devices instances (i.e. incremented each time a device is attached). + * Associating uevents with block devices in userspace is difficult and racy: + * the uevent netlink socket is lossy, and on slow and overloaded systems has + * a very high latency. + * Block devices do not have exclusive owners in userspace, any process can set + * one up (e.g. loop devices). Moreover, device names can be reused (e.g. loop0 + * can be reused again and again). + * A userspace process setting up a block device and watching for its events + * cannot thus reliably tell whether an event relates to the device it just set + * up or another earlier instance with the same name. + * This sequential number allows userspace processes to solve this problem, and + * uniquely associate an uevent to the lifetime to a device. + */ +static atomic64_t diskseq; + /* for extended dynamic devt allocation, currently only one major is used */ #define NR_EXT_DEVT (1 << MINORBITS) static DEFINE_IDA(ext_devt_ida); @@ -60,7 +77,8 @@ bool set_capacity_and_notify(struct gendisk *disk, sector_t size) * initial capacity during probing. */ if (size == capacity || - (disk->flags & (GENHD_FL_UP | GENHD_FL_HIDDEN)) != GENHD_FL_UP) + !disk_live(disk) || + (disk->flags & GENHD_FL_HIDDEN)) return false; pr_info("%s: detected capacity change from %lld to %lld\n", @@ -78,11 +96,17 @@ bool set_capacity_and_notify(struct gendisk *disk, sector_t size) EXPORT_SYMBOL_GPL(set_capacity_and_notify); /* - * Format the device name of the indicated disk into the supplied buffer and - * return a pointer to that same buffer for convenience. + * Format the device name of the indicated block device into the supplied buffer + * and return a pointer to that same buffer for convenience. + * + * Note: do not use this in new code, use the %pg specifier to sprintf and + * printk insted. */ -char *disk_name(struct gendisk *hd, int partno, char *buf) +const char *bdevname(struct block_device *bdev, char *buf) { + struct gendisk *hd = bdev->bd_disk; + int partno = bdev->bd_partno; + if (!partno) snprintf(buf, BDEVNAME_SIZE, "%s", hd->disk_name); else if (isdigit(hd->disk_name[strlen(hd->disk_name)-1])) @@ -92,11 +116,6 @@ char *disk_name(struct gendisk *hd, int partno, char *buf) return buf; } - -const char *bdevname(struct block_device *bdev, char *buf) -{ - return disk_name(bdev->bd_disk, bdev->bd_partno, buf); -} EXPORT_SYMBOL(bdevname); static void part_stat_read_all(struct block_device *part, @@ -294,54 +313,19 @@ void unregister_blkdev(unsigned int major, const char *name) EXPORT_SYMBOL(unregister_blkdev); -/** - * blk_mangle_minor - scatter minor numbers apart - * @minor: minor number to mangle - * - * Scatter consecutively allocated @minor number apart if MANGLE_DEVT - * is enabled. Mangling twice gives the original value. - * - * RETURNS: - * Mangled value. - * - * CONTEXT: - * Don't care. - */ -static int blk_mangle_minor(int minor) -{ -#ifdef CONFIG_DEBUG_BLOCK_EXT_DEVT - int i; - - for (i = 0; i < MINORBITS / 2; i++) { - int low = minor & (1 << i); - int high = minor & (1 << (MINORBITS - 1 - i)); - int distance = MINORBITS - 1 - 2 * i; - - minor ^= low | high; /* clear both bits */ - low <<= distance; /* swap the positions */ - high >>= distance; - minor |= low | high; /* and set */ - } -#endif - return minor; -} - int blk_alloc_ext_minor(void) { int idx; idx = ida_alloc_range(&ext_devt_ida, 0, NR_EXT_DEVT, GFP_KERNEL); - if (idx < 0) { - if (idx == -ENOSPC) - return -EBUSY; - return idx; - } - return blk_mangle_minor(idx); + if (idx == -ENOSPC) + return -EBUSY; + return idx; } void blk_free_ext_minor(unsigned int minor) { - ida_free(&ext_devt_ida, blk_mangle_minor(minor)); + ida_free(&ext_devt_ida, minor); } static char *bdevt_str(dev_t devt, char *buf) @@ -390,78 +374,20 @@ static void disk_scan_partitions(struct gendisk *disk) blkdev_put(bdev, FMODE_READ); } -static void register_disk(struct device *parent, struct gendisk *disk, - const struct attribute_group **groups) -{ - struct device *ddev = disk_to_dev(disk); - int err; - - ddev->parent = parent; - - dev_set_name(ddev, "%s", disk->disk_name); - - /* delay uevents, until we scanned partition table */ - dev_set_uevent_suppress(ddev, 1); - - if (groups) { - WARN_ON(ddev->groups); - ddev->groups = groups; - } - if (device_add(ddev)) - return; - if (!sysfs_deprecated) { - err = sysfs_create_link(block_depr, &ddev->kobj, - kobject_name(&ddev->kobj)); - if (err) { - device_del(ddev); - return; - } - } - - /* - * avoid probable deadlock caused by allocating memory with - * GFP_KERNEL in runtime_resume callback of its all ancestor - * devices - */ - pm_runtime_set_memalloc_noio(ddev, true); - - disk->part0->bd_holder_dir = - kobject_create_and_add("holders", &ddev->kobj); - disk->slave_dir = kobject_create_and_add("slaves", &ddev->kobj); - - if (disk->flags & GENHD_FL_HIDDEN) - return; - - disk_scan_partitions(disk); - - /* announce the disk and partitions after all partitions are created */ - dev_set_uevent_suppress(ddev, 0); - disk_uevent(disk, KOBJ_ADD); - - if (disk->queue->backing_dev_info->dev) { - err = sysfs_create_link(&ddev->kobj, - &disk->queue->backing_dev_info->dev->kobj, - "bdi"); - WARN_ON(err); - } -} - /** - * __device_add_disk - add disk information to kernel list + * device_add_disk - add disk information to kernel list * @parent: parent device for the disk * @disk: per-device partitioning information * @groups: Additional per-device sysfs groups - * @register_queue: register the queue if set to true * * This function registers the partitioning information in @disk * with the kernel. - * - * FIXME: error handling */ -static void __device_add_disk(struct device *parent, struct gendisk *disk, - const struct attribute_group **groups, - bool register_queue) +int device_add_disk(struct device *parent, struct gendisk *disk, + const struct attribute_group **groups) + { + struct device *ddev = disk_to_dev(disk); int ret; /* @@ -470,8 +396,7 @@ static void __device_add_disk(struct device *parent, struct gendisk *disk, * elevator if one is needed, that is, for devices requesting queue * registration. */ - if (register_queue) - elevator_init_mq(disk->queue); + elevator_init_mq(disk->queue); /* * If the driver provides an explicit major number it also must provide @@ -481,7 +406,8 @@ static void __device_add_disk(struct device *parent, struct gendisk *disk, * and all partitions from the extended dev_t space. */ if (disk->major) { - WARN_ON(!disk->minors); + if (WARN_ON(!disk->minors)) + return -EINVAL; if (disk->minors > DISK_MAX_PARTS) { pr_err("block: can't allocate more than %d partitions\n", @@ -489,21 +415,65 @@ static void __device_add_disk(struct device *parent, struct gendisk *disk, disk->minors = DISK_MAX_PARTS; } } else { - WARN_ON(disk->minors); + if (WARN_ON(disk->minors)) + return -EINVAL; ret = blk_alloc_ext_minor(); - if (ret < 0) { - WARN_ON(1); - return; - } + if (ret < 0) + return ret; disk->major = BLOCK_EXT_MAJOR; - disk->first_minor = MINOR(ret); + disk->first_minor = ret; disk->flags |= GENHD_FL_EXT_DEVT; } - disk->flags |= GENHD_FL_UP; + ret = disk_alloc_events(disk); + if (ret) + goto out_free_ext_minor; - disk_alloc_events(disk); + /* delay uevents, until we scanned partition table */ + dev_set_uevent_suppress(ddev, 1); + + ddev->parent = parent; + ddev->groups = groups; + dev_set_name(ddev, "%s", disk->disk_name); + if (!(disk->flags & GENHD_FL_HIDDEN)) + ddev->devt = MKDEV(disk->major, disk->first_minor); + ret = device_add(ddev); + if (ret) + goto out_disk_release_events; + if (!sysfs_deprecated) { + ret = sysfs_create_link(block_depr, &ddev->kobj, + kobject_name(&ddev->kobj)); + if (ret) + goto out_device_del; + } + + /* + * avoid probable deadlock caused by allocating memory with + * GFP_KERNEL in runtime_resume callback of its all ancestor + * devices + */ + pm_runtime_set_memalloc_noio(ddev, true); + + ret = blk_integrity_add(disk); + if (ret) + goto out_del_block_link; + + disk->part0->bd_holder_dir = + kobject_create_and_add("holders", &ddev->kobj); + if (!disk->part0->bd_holder_dir) + goto out_del_integrity; + disk->slave_dir = kobject_create_and_add("slaves", &ddev->kobj); + if (!disk->slave_dir) + goto out_put_holder_dir; + + ret = bd_register_pending_holders(disk); + if (ret < 0) + goto out_put_slave_dir; + + ret = blk_register_queue(disk); + if (ret) + goto out_put_slave_dir; if (disk->flags & GENHD_FL_HIDDEN) { /* @@ -513,48 +483,56 @@ static void __device_add_disk(struct device *parent, struct gendisk *disk, disk->flags |= GENHD_FL_SUPPRESS_PARTITION_INFO; disk->flags |= GENHD_FL_NO_PART_SCAN; } else { - struct backing_dev_info *bdi = disk->queue->backing_dev_info; - struct device *dev = disk_to_dev(disk); - - /* Register BDI before referencing it from bdev */ - dev->devt = MKDEV(disk->major, disk->first_minor); - ret = bdi_register(bdi, "%u:%u", + ret = bdi_register(disk->bdi, "%u:%u", disk->major, disk->first_minor); - WARN_ON(ret); - bdi_set_owner(bdi, dev); - bdev_add(disk->part0, dev->devt); - } - register_disk(parent, disk, groups); - if (register_queue) - blk_register_queue(disk); + if (ret) + goto out_unregister_queue; + bdi_set_owner(disk->bdi, ddev); + ret = sysfs_create_link(&ddev->kobj, + &disk->bdi->dev->kobj, "bdi"); + if (ret) + goto out_unregister_bdi; - /* - * Take an extra ref on queue which will be put on disk_release() - * so that it sticks around as long as @disk is there. - */ - if (blk_get_queue(disk->queue)) - set_bit(GD_QUEUE_REF, &disk->state); - else - WARN_ON_ONCE(1); + bdev_add(disk->part0, ddev->devt); + disk_scan_partitions(disk); - disk_add_events(disk); - blk_integrity_add(disk); -} + /* + * Announce the disk and partitions after all partitions are + * created. (for hidden disks uevents remain suppressed forever) + */ + dev_set_uevent_suppress(ddev, 0); + disk_uevent(disk, KOBJ_ADD); + } -void device_add_disk(struct device *parent, struct gendisk *disk, - const struct attribute_group **groups) + disk_update_readahead(disk); + disk_add_events(disk); + return 0; -{ - __device_add_disk(parent, disk, groups, true); +out_unregister_bdi: + if (!(disk->flags & GENHD_FL_HIDDEN)) + bdi_unregister(disk->bdi); +out_unregister_queue: + blk_unregister_queue(disk); +out_put_slave_dir: + kobject_put(disk->slave_dir); +out_put_holder_dir: + kobject_put(disk->part0->bd_holder_dir); +out_del_integrity: + blk_integrity_del(disk); +out_del_block_link: + if (!sysfs_deprecated) + sysfs_remove_link(block_depr, dev_name(ddev)); +out_device_del: + device_del(ddev); +out_disk_release_events: + disk_release_events(disk); +out_free_ext_minor: + if (disk->major == BLOCK_EXT_MAJOR) + blk_free_ext_minor(disk->first_minor); + return WARN_ON_ONCE(ret); /* keep until all callers handle errors */ } EXPORT_SYMBOL(device_add_disk); -void device_add_disk_no_queue_reg(struct device *parent, struct gendisk *disk) -{ - __device_add_disk(parent, disk, NULL, false); -} -EXPORT_SYMBOL(device_add_disk_no_queue_reg); - /** * del_gendisk - remove the gendisk * @disk: the struct gendisk to remove @@ -578,26 +556,20 @@ void del_gendisk(struct gendisk *disk) { might_sleep(); - if (WARN_ON_ONCE(!disk->queue)) + if (WARN_ON_ONCE(!disk_live(disk) && !(disk->flags & GENHD_FL_HIDDEN))) return; blk_integrity_del(disk); disk_del_events(disk); mutex_lock(&disk->open_mutex); - disk->flags &= ~GENHD_FL_UP; + remove_inode_hash(disk->part0->bd_inode); blk_drop_partitions(disk); mutex_unlock(&disk->open_mutex); fsync_bdev(disk->part0); __invalidate_device(disk->part0, true); - /* - * Unhash the bdev inode for this device so that it can't be looked - * up any more even if openers still hold references to it. - */ - remove_inode_hash(disk->part0->bd_inode); - set_capacity(disk, 0); if (!(disk->flags & GENHD_FL_HIDDEN)) { @@ -607,7 +579,7 @@ void del_gendisk(struct gendisk *disk) * Unregister bdi before releasing device numbers (as they can * get reused and we'd get clashes in sysfs). */ - bdi_unregister(disk->queue->backing_dev_info); + bdi_unregister(disk->bdi); } blk_unregister_queue(disk); @@ -683,7 +655,6 @@ void __init printk_all_partitions(void) while ((dev = class_dev_iter_next(&iter))) { struct gendisk *disk = dev_to_disk(dev); struct block_device *part; - char name_buf[BDEVNAME_SIZE]; char devt_buf[BDEVT_SIZE]; unsigned long idx; @@ -703,11 +674,10 @@ void __init printk_all_partitions(void) xa_for_each(&disk->part_tbl, idx, part) { if (!bdev_nr_sectors(part)) continue; - printk("%s%s %10llu %s %s", + printk("%s%s %10llu %pg %s", bdev_is_partition(part) ? " " : "", bdevt_str(part->bd_dev, devt_buf), - bdev_nr_sectors(part) >> 1, - disk_name(disk, part->bd_partno, name_buf), + bdev_nr_sectors(part) >> 1, part, part->bd_meta_info ? part->bd_meta_info->uuid : ""); if (bdev_is_partition(part)) @@ -785,7 +755,6 @@ static int show_partition(struct seq_file *seqf, void *v) struct gendisk *sgp = v; struct block_device *part; unsigned long idx; - char buf[BDEVNAME_SIZE]; /* Don't show non-partitionable removeable devices or empty devices */ if (!get_capacity(sgp) || (!disk_max_parts(sgp) && @@ -798,10 +767,9 @@ static int show_partition(struct seq_file *seqf, void *v) xa_for_each(&sgp->part_tbl, idx, part) { if (!bdev_nr_sectors(part)) continue; - seq_printf(seqf, "%4d %7d %10llu %s\n", + seq_printf(seqf, "%4d %7d %10llu %pg\n", MAJOR(part->bd_dev), MINOR(part->bd_dev), - bdev_nr_sectors(part) >> 1, - disk_name(sgp, part->bd_partno, buf)); + bdev_nr_sectors(part) >> 1, part); } rcu_read_unlock(); return 0; @@ -968,6 +936,14 @@ static ssize_t disk_discard_alignment_show(struct device *dev, return sprintf(buf, "%d\n", queue_discard_alignment(disk->queue)); } +static ssize_t diskseq_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct gendisk *disk = dev_to_disk(dev); + + return sprintf(buf, "%llu\n", disk->diskseq); +} + static DEVICE_ATTR(range, 0444, disk_range_show, NULL); static DEVICE_ATTR(ext_range, 0444, disk_ext_range_show, NULL); static DEVICE_ATTR(removable, 0444, disk_removable_show, NULL); @@ -980,6 +956,7 @@ static DEVICE_ATTR(capability, 0444, disk_capability_show, NULL); static DEVICE_ATTR(stat, 0444, part_stat_show, NULL); static DEVICE_ATTR(inflight, 0444, part_inflight_show, NULL); static DEVICE_ATTR(badblocks, 0644, disk_badblocks_show, disk_badblocks_store); +static DEVICE_ATTR(diskseq, 0444, diskseq_show, NULL); #ifdef CONFIG_FAIL_MAKE_REQUEST ssize_t part_fail_show(struct device *dev, @@ -1025,6 +1002,7 @@ static struct attribute *disk_attrs[] = { &dev_attr_events.attr, &dev_attr_events_async.attr, &dev_attr_events_poll_msecs.attr, + &dev_attr_diskseq.attr, #ifdef CONFIG_FAIL_MAKE_REQUEST &dev_attr_fail.attr, #endif @@ -1074,17 +1052,24 @@ static void disk_release(struct device *dev) might_sleep(); - if (MAJOR(dev->devt) == BLOCK_EXT_MAJOR) - blk_free_ext_minor(MINOR(dev->devt)); disk_release_events(disk); kfree(disk->random); xa_destroy(&disk->part_tbl); - if (test_bit(GD_QUEUE_REF, &disk->state) && disk->queue) - blk_put_queue(disk->queue); - bdput(disk->part0); /* frees the disk */ + disk->queue->disk = NULL; + blk_put_queue(disk->queue); + iput(disk->part0->bd_inode); /* frees the disk */ +} + +static int block_uevent(struct device *dev, struct kobj_uevent_env *env) +{ + struct gendisk *disk = dev_to_disk(dev); + + return add_uevent_var(env, "DISKSEQ=%llu", disk->diskseq); } + struct class block_class = { .name = "block", + .dev_uevent = block_uevent, }; static char *block_devnode(struct device *dev, umode_t *mode, @@ -1116,7 +1101,6 @@ static int diskstats_show(struct seq_file *seqf, void *v) { struct gendisk *gp = v; struct block_device *hd; - char buf[BDEVNAME_SIZE]; unsigned int inflight; struct disk_stats stat; unsigned long idx; @@ -1139,15 +1123,14 @@ static int diskstats_show(struct seq_file *seqf, void *v) else inflight = part_in_flight(hd); - seq_printf(seqf, "%4d %7d %s " + seq_printf(seqf, "%4d %7d %pg " "%lu %lu %lu %u " "%lu %lu %lu %u " "%u %u %u " "%lu %lu %lu %u " "%lu %u" "\n", - MAJOR(hd->bd_dev), MINOR(hd->bd_dev), - disk_name(gp, hd->bd_partno, buf), + MAJOR(hd->bd_dev), MINOR(hd->bd_dev), hd, stat.ios[STAT_READ], stat.merges[STAT_READ], stat.sectors[STAT_READ], @@ -1239,17 +1222,25 @@ dev_t blk_lookup_devt(const char *name, int partno) return devt; } -struct gendisk *__alloc_disk_node(int minors, int node_id) +struct gendisk *__alloc_disk_node(struct request_queue *q, int node_id, + struct lock_class_key *lkclass) { struct gendisk *disk; + if (!blk_get_queue(q)) + return NULL; + disk = kzalloc_node(sizeof(struct gendisk), GFP_KERNEL, node_id); if (!disk) - return NULL; + goto out_put_queue; + + disk->bdi = bdi_alloc(node_id); + if (!disk->bdi) + goto out_free_disk; disk->part0 = bdev_alloc(disk, 0); if (!disk->part0) - goto out_free_disk; + goto out_free_bdi; disk->node_id = node_id; mutex_init(&disk->open_mutex); @@ -1257,23 +1248,33 @@ struct gendisk *__alloc_disk_node(int minors, int node_id) if (xa_insert(&disk->part_tbl, 0, disk->part0, GFP_KERNEL)) goto out_destroy_part_tbl; - disk->minors = minors; rand_initialize_disk(disk); disk_to_dev(disk)->class = &block_class; disk_to_dev(disk)->type = &disk_type; device_initialize(disk_to_dev(disk)); + inc_diskseq(disk); + disk->queue = q; + q->disk = disk; + lockdep_init_map(&disk->lockdep_map, "(bio completion)", lkclass, 0); +#ifdef CONFIG_BLOCK_HOLDER_DEPRECATED + INIT_LIST_HEAD(&disk->slave_bdevs); +#endif return disk; out_destroy_part_tbl: xa_destroy(&disk->part_tbl); - bdput(disk->part0); + iput(disk->part0->bd_inode); +out_free_bdi: + bdi_put(disk->bdi); out_free_disk: kfree(disk); +out_put_queue: + blk_put_queue(q); return NULL; } EXPORT_SYMBOL(__alloc_disk_node); -struct gendisk *__blk_alloc_disk(int node) +struct gendisk *__blk_alloc_disk(int node, struct lock_class_key *lkclass) { struct request_queue *q; struct gendisk *disk; @@ -1282,12 +1283,11 @@ struct gendisk *__blk_alloc_disk(int node) if (!q) return NULL; - disk = __alloc_disk_node(0, node); + disk = __alloc_disk_node(q, node, lkclass); if (!disk) { blk_cleanup_queue(q); return NULL; } - disk->queue = q; return disk; } EXPORT_SYMBOL(__blk_alloc_disk); @@ -1362,3 +1362,8 @@ int bdev_read_only(struct block_device *bdev) return bdev->bd_read_only || get_disk_ro(bdev->bd_disk); } EXPORT_SYMBOL(bdev_read_only); + +void inc_diskseq(struct gendisk *disk) +{ + disk->diskseq = atomic64_inc_return(&diskseq); +} diff --git a/block/holder.c b/block/holder.c new file mode 100644 index 000000000000..9dc084182337 --- /dev/null +++ b/block/holder.c @@ -0,0 +1,174 @@ +// SPDX-License-Identifier: GPL-2.0-only +#include <linux/genhd.h> + +struct bd_holder_disk { + struct list_head list; + struct block_device *bdev; + int refcnt; +}; + +static struct bd_holder_disk *bd_find_holder_disk(struct block_device *bdev, + struct gendisk *disk) +{ + struct bd_holder_disk *holder; + + list_for_each_entry(holder, &disk->slave_bdevs, list) + if (holder->bdev == bdev) + return holder; + return NULL; +} + +static int add_symlink(struct kobject *from, struct kobject *to) +{ + return sysfs_create_link(from, to, kobject_name(to)); +} + +static void del_symlink(struct kobject *from, struct kobject *to) +{ + sysfs_remove_link(from, kobject_name(to)); +} + +static int __link_disk_holder(struct block_device *bdev, struct gendisk *disk) +{ + int ret; + + ret = add_symlink(disk->slave_dir, bdev_kobj(bdev)); + if (ret) + return ret; + ret = add_symlink(bdev->bd_holder_dir, &disk_to_dev(disk)->kobj); + if (ret) + del_symlink(disk->slave_dir, bdev_kobj(bdev)); + return ret; +} + +/** + * bd_link_disk_holder - create symlinks between holding disk and slave bdev + * @bdev: the claimed slave bdev + * @disk: the holding disk + * + * DON'T USE THIS UNLESS YOU'RE ALREADY USING IT. + * + * This functions creates the following sysfs symlinks. + * + * - from "slaves" directory of the holder @disk to the claimed @bdev + * - from "holders" directory of the @bdev to the holder @disk + * + * For example, if /dev/dm-0 maps to /dev/sda and disk for dm-0 is + * passed to bd_link_disk_holder(), then: + * + * /sys/block/dm-0/slaves/sda --> /sys/block/sda + * /sys/block/sda/holders/dm-0 --> /sys/block/dm-0 + * + * The caller must have claimed @bdev before calling this function and + * ensure that both @bdev and @disk are valid during the creation and + * lifetime of these symlinks. + * + * CONTEXT: + * Might sleep. + * + * RETURNS: + * 0 on success, -errno on failure. + */ +int bd_link_disk_holder(struct block_device *bdev, struct gendisk *disk) +{ + struct bd_holder_disk *holder; + int ret = 0; + + mutex_lock(&disk->open_mutex); + + WARN_ON_ONCE(!bdev->bd_holder); + + /* FIXME: remove the following once add_disk() handles errors */ + if (WARN_ON(!bdev->bd_holder_dir)) + goto out_unlock; + + holder = bd_find_holder_disk(bdev, disk); + if (holder) { + holder->refcnt++; + goto out_unlock; + } + + holder = kzalloc(sizeof(*holder), GFP_KERNEL); + if (!holder) { + ret = -ENOMEM; + goto out_unlock; + } + + INIT_LIST_HEAD(&holder->list); + holder->bdev = bdev; + holder->refcnt = 1; + if (disk->slave_dir) { + ret = __link_disk_holder(bdev, disk); + if (ret) { + kfree(holder); + goto out_unlock; + } + } + + list_add(&holder->list, &disk->slave_bdevs); + /* + * del_gendisk drops the initial reference to bd_holder_dir, so we need + * to keep our own here to allow for cleanup past that point. + */ + kobject_get(bdev->bd_holder_dir); + +out_unlock: + mutex_unlock(&disk->open_mutex); + return ret; +} +EXPORT_SYMBOL_GPL(bd_link_disk_holder); + +static void __unlink_disk_holder(struct block_device *bdev, + struct gendisk *disk) +{ + del_symlink(disk->slave_dir, bdev_kobj(bdev)); + del_symlink(bdev->bd_holder_dir, &disk_to_dev(disk)->kobj); +} + +/** + * bd_unlink_disk_holder - destroy symlinks created by bd_link_disk_holder() + * @bdev: the calimed slave bdev + * @disk: the holding disk + * + * DON'T USE THIS UNLESS YOU'RE ALREADY USING IT. + * + * CONTEXT: + * Might sleep. + */ +void bd_unlink_disk_holder(struct block_device *bdev, struct gendisk *disk) +{ + struct bd_holder_disk *holder; + + mutex_lock(&disk->open_mutex); + holder = bd_find_holder_disk(bdev, disk); + if (!WARN_ON_ONCE(holder == NULL) && !--holder->refcnt) { + if (disk->slave_dir) + __unlink_disk_holder(bdev, disk); + kobject_put(bdev->bd_holder_dir); + list_del_init(&holder->list); + kfree(holder); + } + mutex_unlock(&disk->open_mutex); +} +EXPORT_SYMBOL_GPL(bd_unlink_disk_holder); + +int bd_register_pending_holders(struct gendisk *disk) +{ + struct bd_holder_disk *holder; + int ret; + + mutex_lock(&disk->open_mutex); + list_for_each_entry(holder, &disk->slave_bdevs, list) { + ret = __link_disk_holder(holder->bdev, disk); + if (ret) + goto out_undo; + } + mutex_unlock(&disk->open_mutex); + return 0; + +out_undo: + list_for_each_entry_continue_reverse(holder, &disk->slave_bdevs, list) + __unlink_disk_holder(holder->bdev, disk); + mutex_unlock(&disk->open_mutex); + return ret; +} diff --git a/block/ioctl.c b/block/ioctl.c index 24beec9ca9c9..eb0491e90b9a 100644 --- a/block/ioctl.c +++ b/block/ioctl.c @@ -16,6 +16,7 @@ static int blkpg_do_ioctl(struct block_device *bdev, struct blkpg_partition __user *upart, int op) { + struct gendisk *disk = bdev->bd_disk; struct blkpg_partition p; long long start, length; @@ -30,7 +31,7 @@ static int blkpg_do_ioctl(struct block_device *bdev, return -EINVAL; if (op == BLKPG_DEL_PARTITION) - return bdev_del_partition(bdev, p.pno); + return bdev_del_partition(disk, p.pno); start = p.start >> SECTOR_SHIFT; length = p.length >> SECTOR_SHIFT; @@ -40,9 +41,9 @@ static int blkpg_do_ioctl(struct block_device *bdev, /* check if partition is aligned to blocksize */ if (p.start & (bdev_logical_block_size(bdev) - 1)) return -EINVAL; - return bdev_add_partition(bdev, p.pno, start, length); + return bdev_add_partition(disk, p.pno, start, length); case BLKPG_RESIZE_PARTITION: - return bdev_resize_partition(bdev, p.pno, start, length); + return bdev_resize_partition(disk, p.pno, start, length); default: return -EINVAL; } @@ -469,6 +470,8 @@ static int blkdev_common_ioctl(struct block_device *bdev, fmode_t mode, BLKDEV_DISCARD_SECURE); case BLKZEROOUT: return blk_ioctl_zeroout(bdev, mode, arg); + case BLKGETDISKSEQ: + return put_u64(argp, bdev->bd_disk->diskseq); case BLKREPORTZONE: return blkdev_report_zones_ioctl(bdev, mode, cmd, arg); case BLKRESETZONE: @@ -504,7 +507,7 @@ static int blkdev_common_ioctl(struct block_device *bdev, fmode_t mode, case BLKFRASET: if(!capable(CAP_SYS_ADMIN)) return -EACCES; - bdev->bd_bdi->ra_pages = (arg * 512) / PAGE_SIZE; + bdev->bd_disk->bdi->ra_pages = (arg * 512) / PAGE_SIZE; return 0; case BLKRRPART: return blkdev_reread_part(bdev, mode); @@ -554,7 +557,8 @@ int blkdev_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd, case BLKFRAGET: if (!argp) return -EINVAL; - return put_long(argp, (bdev->bd_bdi->ra_pages*PAGE_SIZE) / 512); + return put_long(argp, + (bdev->bd_disk->bdi->ra_pages * PAGE_SIZE) / 512); case BLKGETSIZE: size = i_size_read(bdev->bd_inode); if ((size >> 9) > ~0UL) @@ -626,7 +630,7 @@ long compat_blkdev_ioctl(struct file *file, unsigned cmd, unsigned long arg) if (!argp) return -EINVAL; return compat_put_long(argp, - (bdev->bd_bdi->ra_pages * PAGE_SIZE) / 512); + (bdev->bd_disk->bdi->ra_pages * PAGE_SIZE) / 512); case BLKGETSIZE: size = i_size_read(bdev->bd_inode); if ((size >> 9) > ~0UL) diff --git a/block/ioprio.c b/block/ioprio.c index bee628f9f1b2..0e4ff245f2bf 100644 --- a/block/ioprio.c +++ b/block/ioprio.c @@ -74,9 +74,8 @@ int ioprio_check_cap(int ioprio) fallthrough; /* rt has prio field too */ case IOPRIO_CLASS_BE: - if (data >= IOPRIO_BE_NR || data < 0) + if (data >= IOPRIO_NR_LEVELS || data < 0) return -EINVAL; - break; case IOPRIO_CLASS_IDLE: break; @@ -171,7 +170,7 @@ static int get_task_ioprio(struct task_struct *p) ret = security_task_getioprio(p); if (ret) goto out; - ret = IOPRIO_PRIO_VALUE(IOPRIO_CLASS_NONE, IOPRIO_NORM); + ret = IOPRIO_DEFAULT; task_lock(p); if (p->io_context) ret = p->io_context->ioprio; @@ -183,9 +182,9 @@ out: int ioprio_best(unsigned short aprio, unsigned short bprio) { if (!ioprio_valid(aprio)) - aprio = IOPRIO_PRIO_VALUE(IOPRIO_CLASS_BE, IOPRIO_NORM); + aprio = IOPRIO_DEFAULT; if (!ioprio_valid(bprio)) - bprio = IOPRIO_PRIO_VALUE(IOPRIO_CLASS_BE, IOPRIO_NORM); + bprio = IOPRIO_DEFAULT; return min(aprio, bprio); } diff --git a/block/mq-deadline.c b/block/mq-deadline.c index 36920670dccc..3c3693c34f06 100644 --- a/block/mq-deadline.c +++ b/block/mq-deadline.c @@ -629,6 +629,8 @@ static int dd_request_merge(struct request_queue *q, struct request **rq, if (elv_bio_merge_ok(__rq, bio)) { *rq = __rq; + if (blk_discard_mergable(__rq)) + return ELEVATOR_DISCARD_MERGE; return ELEVATOR_FRONT_MERGE; } } diff --git a/block/partitions/Kconfig b/block/partitions/Kconfig index 6e2a649669e5..278593b8e4e9 100644 --- a/block/partitions/Kconfig +++ b/block/partitions/Kconfig @@ -264,7 +264,6 @@ config SYSV68_PARTITION config CMDLINE_PARTITION bool "Command line partition support" if PARTITION_ADVANCED - select BLK_CMDLINE_PARSER help Say Y here if you want to read the partition table from bootargs. The format for the command line is just like mtdparts. diff --git a/block/partitions/acorn.c b/block/partitions/acorn.c index c64c57b958bf..2c381c694c57 100644 --- a/block/partitions/acorn.c +++ b/block/partitions/acorn.c @@ -275,7 +275,7 @@ int adfspart_check_ADFS(struct parsed_partitions *state) /* * Work out start of non-adfs partition. */ - nr_sects = (state->bdev->bd_inode->i_size >> 9) - start_sect; + nr_sects = get_capacity(state->disk) - start_sect; if (start_sect) { switch (id) { @@ -540,7 +540,7 @@ int adfspart_check_EESOX(struct parsed_partitions *state) if (i != 0) { sector_t size; - size = get_capacity(state->bdev->bd_disk); + size = get_capacity(state->disk); put_partition(state, slot++, start, size - start); strlcat(state->pp_buf, "\n", PAGE_SIZE); } diff --git a/block/partitions/aix.c b/block/partitions/aix.c index c7b4fd1a4a97..85f4b967565e 100644 --- a/block/partitions/aix.c +++ b/block/partitions/aix.c @@ -67,29 +67,13 @@ struct pvd { #define LVM_MAXLVS 256 /** - * last_lba(): return number of last logical block of device - * @bdev: block device - * - * Description: Returns last LBA value on success, 0 on error. - * This is stored (by sd and ide-geometry) in - * the part[0] entry for this disk, and is the number of - * physical sectors available on the disk. - */ -static u64 last_lba(struct block_device *bdev) -{ - if (!bdev || !bdev->bd_inode) - return 0; - return (bdev->bd_inode->i_size >> 9) - 1ULL; -} - -/** * read_lba(): Read bytes from disk, starting at given LBA * @state * @lba * @buffer * @count * - * Description: Reads @count bytes from @state->bdev into @buffer. + * Description: Reads @count bytes from @state->disk into @buffer. * Returns number of bytes read on success, 0 on error. */ static size_t read_lba(struct parsed_partitions *state, u64 lba, u8 *buffer, @@ -97,7 +81,7 @@ static size_t read_lba(struct parsed_partitions *state, u64 lba, u8 *buffer, { size_t totalreadcount = 0; - if (!buffer || lba + count / 512 > last_lba(state->bdev)) + if (!buffer || lba + count / 512 > get_capacity(state->disk) - 1ULL) return 0; while (count) { diff --git a/block/partitions/amiga.c b/block/partitions/amiga.c index 9526491d9aed..5c8624e26a54 100644 --- a/block/partitions/amiga.c +++ b/block/partitions/amiga.c @@ -34,7 +34,6 @@ int amiga_partition(struct parsed_partitions *state) int start_sect, nr_sects, blk, part, res = 0; int blksize = 1; /* Multiplier for disk block size */ int slot = 1; - char b[BDEVNAME_SIZE]; for (blk = 0; ; blk++, put_dev_sector(sect)) { if (blk == RDB_ALLOCATION_LIMIT) @@ -42,7 +41,7 @@ int amiga_partition(struct parsed_partitions *state) data = read_part_sector(state, blk, §); if (!data) { pr_err("Dev %s: unable to read RDB block %d\n", - bdevname(state->bdev, b), blk); + state->disk->disk_name, blk); res = -1; goto rdb_done; } @@ -64,7 +63,7 @@ int amiga_partition(struct parsed_partitions *state) } pr_err("Dev %s: RDB in block %d has bad checksum\n", - bdevname(state->bdev, b), blk); + state->disk->disk_name, blk); } /* blksize is blocks per 512 byte standard block */ @@ -84,7 +83,7 @@ int amiga_partition(struct parsed_partitions *state) data = read_part_sector(state, blk, §); if (!data) { pr_err("Dev %s: unable to read partition block %d\n", - bdevname(state->bdev, b), blk); + state->disk->disk_name, blk); res = -1; goto rdb_done; } diff --git a/block/partitions/atari.c b/block/partitions/atari.c index 2305840c8522..da5994175416 100644 --- a/block/partitions/atari.c +++ b/block/partitions/atari.c @@ -47,7 +47,7 @@ int atari_partition(struct parsed_partitions *state) * ATARI partition scheme supports 512 lba only. If this is not * the case, bail early to avoid miscalculating hd_size. */ - if (bdev_logical_block_size(state->bdev) != 512) + if (queue_logical_block_size(state->disk->queue) != 512) return 0; rs = read_part_sector(state, 0, §); @@ -55,7 +55,7 @@ int atari_partition(struct parsed_partitions *state) return -1; /* Verify this is an Atari rootsector: */ - hd_size = state->bdev->bd_inode->i_size >> 9; + hd_size = get_capacity(state->disk); if (!VALID_PARTITION(&rs->part[0], hd_size) && !VALID_PARTITION(&rs->part[1], hd_size) && !VALID_PARTITION(&rs->part[2], hd_size) && diff --git a/block/partitions/check.h b/block/partitions/check.h index c577e9ee67f0..d5b28e309d64 100644 --- a/block/partitions/check.h +++ b/block/partitions/check.h @@ -9,7 +9,7 @@ * description. */ struct parsed_partitions { - struct block_device *bdev; + struct gendisk *disk; char name[BDEVNAME_SIZE]; struct { sector_t from; diff --git a/block/partitions/cmdline.c b/block/partitions/cmdline.c index 8f545c36cde4..1af610f0ba8c 100644 --- a/block/partitions/cmdline.c +++ b/block/partitions/cmdline.c @@ -14,20 +14,248 @@ * For further information, see "Documentation/block/cmdline-partition.rst" * */ +#include <linux/blkdev.h> +#include <linux/fs.h> +#include <linux/slab.h> +#include "check.h" -#include <linux/cmdline-parser.h> -#include "check.h" +/* partition flags */ +#define PF_RDONLY 0x01 /* Device is read only */ +#define PF_POWERUP_LOCK 0x02 /* Always locked after reset */ + +struct cmdline_subpart { + char name[BDEVNAME_SIZE]; /* partition name, such as 'rootfs' */ + sector_t from; + sector_t size; + int flags; + struct cmdline_subpart *next_subpart; +}; + +struct cmdline_parts { + char name[BDEVNAME_SIZE]; /* block device, such as 'mmcblk0' */ + unsigned int nr_subparts; + struct cmdline_subpart *subpart; + struct cmdline_parts *next_parts; +}; + +static int parse_subpart(struct cmdline_subpart **subpart, char *partdef) +{ + int ret = 0; + struct cmdline_subpart *new_subpart; + + *subpart = NULL; + + new_subpart = kzalloc(sizeof(struct cmdline_subpart), GFP_KERNEL); + if (!new_subpart) + return -ENOMEM; + + if (*partdef == '-') { + new_subpart->size = (sector_t)(~0ULL); + partdef++; + } else { + new_subpart->size = (sector_t)memparse(partdef, &partdef); + if (new_subpart->size < (sector_t)PAGE_SIZE) { + pr_warn("cmdline partition size is invalid."); + ret = -EINVAL; + goto fail; + } + } + + if (*partdef == '@') { + partdef++; + new_subpart->from = (sector_t)memparse(partdef, &partdef); + } else { + new_subpart->from = (sector_t)(~0ULL); + } + + if (*partdef == '(') { + int length; + char *next = strchr(++partdef, ')'); + + if (!next) { + pr_warn("cmdline partition format is invalid."); + ret = -EINVAL; + goto fail; + } + + length = min_t(int, next - partdef, + sizeof(new_subpart->name) - 1); + strncpy(new_subpart->name, partdef, length); + new_subpart->name[length] = '\0'; + + partdef = ++next; + } else + new_subpart->name[0] = '\0'; + + new_subpart->flags = 0; + + if (!strncmp(partdef, "ro", 2)) { + new_subpart->flags |= PF_RDONLY; + partdef += 2; + } + + if (!strncmp(partdef, "lk", 2)) { + new_subpart->flags |= PF_POWERUP_LOCK; + partdef += 2; + } + + *subpart = new_subpart; + return 0; +fail: + kfree(new_subpart); + return ret; +} + +static void free_subpart(struct cmdline_parts *parts) +{ + struct cmdline_subpart *subpart; + + while (parts->subpart) { + subpart = parts->subpart; + parts->subpart = subpart->next_subpart; + kfree(subpart); + } +} + +static int parse_parts(struct cmdline_parts **parts, const char *bdevdef) +{ + int ret = -EINVAL; + char *next; + int length; + struct cmdline_subpart **next_subpart; + struct cmdline_parts *newparts; + char buf[BDEVNAME_SIZE + 32 + 4]; + + *parts = NULL; + + newparts = kzalloc(sizeof(struct cmdline_parts), GFP_KERNEL); + if (!newparts) + return -ENOMEM; + + next = strchr(bdevdef, ':'); + if (!next) { + pr_warn("cmdline partition has no block device."); + goto fail; + } + + length = min_t(int, next - bdevdef, sizeof(newparts->name) - 1); + strncpy(newparts->name, bdevdef, length); + newparts->name[length] = '\0'; + newparts->nr_subparts = 0; + + next_subpart = &newparts->subpart; + + while (next && *(++next)) { + bdevdef = next; + next = strchr(bdevdef, ','); + + length = (!next) ? (sizeof(buf) - 1) : + min_t(int, next - bdevdef, sizeof(buf) - 1); + + strncpy(buf, bdevdef, length); + buf[length] = '\0'; + + ret = parse_subpart(next_subpart, buf); + if (ret) + goto fail; + + newparts->nr_subparts++; + next_subpart = &(*next_subpart)->next_subpart; + } + + if (!newparts->subpart) { + pr_warn("cmdline partition has no valid partition."); + ret = -EINVAL; + goto fail; + } + + *parts = newparts; + + return 0; +fail: + free_subpart(newparts); + kfree(newparts); + return ret; +} + +static void cmdline_parts_free(struct cmdline_parts **parts) +{ + struct cmdline_parts *next_parts; + + while (*parts) { + next_parts = (*parts)->next_parts; + free_subpart(*parts); + kfree(*parts); + *parts = next_parts; + } +} + +static int cmdline_parts_parse(struct cmdline_parts **parts, + const char *cmdline) +{ + int ret; + char *buf; + char *pbuf; + char *next; + struct cmdline_parts **next_parts; + + *parts = NULL; + + next = pbuf = buf = kstrdup(cmdline, GFP_KERNEL); + if (!buf) + return -ENOMEM; + + next_parts = parts; + + while (next && *pbuf) { + next = strchr(pbuf, ';'); + if (next) + *next = '\0'; + + ret = parse_parts(next_parts, pbuf); + if (ret) + goto fail; + + if (next) + pbuf = ++next; + + next_parts = &(*next_parts)->next_parts; + } + + if (!*parts) { + pr_warn("cmdline partition has no valid partition."); + ret = -EINVAL; + goto fail; + } + + ret = 0; +done: + kfree(buf); + return ret; + +fail: + cmdline_parts_free(parts); + goto done; +} + +static struct cmdline_parts *cmdline_parts_find(struct cmdline_parts *parts, + const char *bdev) +{ + while (parts && strncmp(bdev, parts->name, sizeof(parts->name))) + parts = parts->next_parts; + return parts; +} static char *cmdline; static struct cmdline_parts *bdev_parts; -static int add_part(int slot, struct cmdline_subpart *subpart, void *param) +static int add_part(int slot, struct cmdline_subpart *subpart, + struct parsed_partitions *state) { int label_min; struct partition_meta_info *info; char tmp[sizeof(info->volname) + 4]; - struct parsed_partitions *state = (struct parsed_partitions *)param; if (slot >= state->limit) return 1; @@ -50,6 +278,35 @@ static int add_part(int slot, struct cmdline_subpart *subpart, void *param) return 0; } +static int cmdline_parts_set(struct cmdline_parts *parts, sector_t disk_size, + struct parsed_partitions *state) +{ + sector_t from = 0; + struct cmdline_subpart *subpart; + int slot = 1; + + for (subpart = parts->subpart; subpart; + subpart = subpart->next_subpart, slot++) { + if (subpart->from == (sector_t)(~0ULL)) + subpart->from = from; + else + from = subpart->from; + + if (from >= disk_size) + break; + + if (subpart->size > (disk_size - from)) + subpart->size = disk_size - from; + + from += subpart->size; + + if (add_part(slot, subpart, state)) + break; + } + + return slot; +} + static int __init cmdline_parts_setup(char *s) { cmdline = s; @@ -123,7 +380,6 @@ static void cmdline_parts_verifier(int slot, struct parsed_partitions *state) int cmdline_partition(struct parsed_partitions *state) { sector_t disk_size; - char bdev[BDEVNAME_SIZE]; struct cmdline_parts *parts; if (cmdline) { @@ -140,14 +396,13 @@ int cmdline_partition(struct parsed_partitions *state) if (!bdev_parts) return 0; - bdevname(state->bdev, bdev); - parts = cmdline_parts_find(bdev_parts, bdev); + parts = cmdline_parts_find(bdev_parts, state->disk->disk_name); if (!parts) return 0; - disk_size = get_capacity(state->bdev->bd_disk) << 9; + disk_size = get_capacity(state->disk) << 9; - cmdline_parts_set(parts, disk_size, 1, add_part, (void *)state); + cmdline_parts_set(parts, disk_size, state); cmdline_parts_verifier(1, state); strlcat(state->pp_buf, "\n", PAGE_SIZE); diff --git a/block/partitions/core.c b/block/partitions/core.c index 4230d4f71879..58c4c362c94f 100644 --- a/block/partitions/core.c +++ b/block/partitions/core.c @@ -135,8 +135,8 @@ static struct parsed_partitions *check_partition(struct gendisk *hd) } state->pp_buf[0] = '\0'; - state->bdev = hd->part0; - disk_name(hd, 0, state->name); + state->disk = hd; + snprintf(state->name, BDEVNAME_SIZE, "%s", hd->disk_name); snprintf(state->pp_buf, PAGE_SIZE, " %s:", state->name); if (isdigit(state->name[strlen(state->name)-1])) sprintf(state->name, "p"); @@ -259,9 +259,8 @@ static const struct attribute_group *part_attr_groups[] = { static void part_release(struct device *dev) { - if (MAJOR(dev->devt) == BLOCK_EXT_MAJOR) - blk_free_ext_minor(MINOR(dev->devt)); - bdput(dev_to_bdev(dev)); + put_disk(dev_to_bdev(dev)->bd_disk); + iput(dev_to_bdev(dev)->bd_inode); } static int part_uevent(struct device *dev, struct kobj_uevent_env *env) @@ -281,12 +280,10 @@ struct device_type part_type = { .uevent = part_uevent, }; -/* - * Must be called either with open_mutex held, before a disk can be opened or - * after all disk users are gone. - */ static void delete_partition(struct block_device *part) { + lockdep_assert_held(&part->bd_disk->open_mutex); + fsync_bdev(part); __invalidate_device(part, true); @@ -351,20 +348,17 @@ static struct block_device *add_partition(struct gendisk *disk, int partno, if (xa_load(&disk->part_tbl, partno)) return ERR_PTR(-EBUSY); + /* ensure we always have a reference to the whole disk */ + get_device(disk_to_dev(disk)); + + err = -ENOMEM; bdev = bdev_alloc(disk, partno); if (!bdev) - return ERR_PTR(-ENOMEM); + goto out_put_disk; bdev->bd_start_sect = start; bdev_set_nr_sectors(bdev, len); - if (info) { - err = -ENOMEM; - bdev->bd_meta_info = kmemdup(info, sizeof(*info), GFP_KERNEL); - if (!bdev->bd_meta_info) - goto out_bdput; - } - pdev = &bdev->bd_device; dname = dev_name(ddev); if (isdigit(dname[strlen(dname) - 1])) @@ -388,6 +382,13 @@ static struct block_device *add_partition(struct gendisk *disk, int partno, } pdev->devt = devt; + if (info) { + err = -ENOMEM; + bdev->bd_meta_info = kmemdup(info, sizeof(*info), GFP_KERNEL); + if (!bdev->bd_meta_info) + goto out_put; + } + /* delay uevent until 'holders' subdir is created */ dev_set_uevent_suppress(pdev, 1); err = device_add(pdev); @@ -417,14 +418,13 @@ static struct block_device *add_partition(struct gendisk *disk, int partno, kobject_uevent(&pdev->kobj, KOBJ_ADD); return bdev; -out_bdput: - bdput(bdev); - return ERR_PTR(err); out_del: kobject_put(bdev->bd_holder_dir); device_del(pdev); out_put: put_device(pdev); +out_put_disk: + put_disk(disk); return ERR_PTR(err); } @@ -449,15 +449,14 @@ static bool partition_overlaps(struct gendisk *disk, sector_t start, return overlap; } -int bdev_add_partition(struct block_device *bdev, int partno, - sector_t start, sector_t length) +int bdev_add_partition(struct gendisk *disk, int partno, sector_t start, + sector_t length) { struct block_device *part; - struct gendisk *disk = bdev->bd_disk; int ret; mutex_lock(&disk->open_mutex); - if (!(disk->flags & GENHD_FL_UP)) { + if (!disk_live(disk)) { ret = -ENXIO; goto out; } @@ -475,13 +474,13 @@ out: return ret; } -int bdev_del_partition(struct block_device *bdev, int partno) +int bdev_del_partition(struct gendisk *disk, int partno) { struct block_device *part = NULL; int ret = -ENXIO; - mutex_lock(&bdev->bd_disk->open_mutex); - part = xa_load(&bdev->bd_disk->part_tbl, partno); + mutex_lock(&disk->open_mutex); + part = xa_load(&disk->part_tbl, partno); if (!part) goto out_unlock; @@ -492,18 +491,18 @@ int bdev_del_partition(struct block_device *bdev, int partno) delete_partition(part); ret = 0; out_unlock: - mutex_unlock(&bdev->bd_disk->open_mutex); + mutex_unlock(&disk->open_mutex); return ret; } -int bdev_resize_partition(struct block_device *bdev, int partno, - sector_t start, sector_t length) +int bdev_resize_partition(struct gendisk *disk, int partno, sector_t start, + sector_t length) { struct block_device *part = NULL; int ret = -ENXIO; - mutex_lock(&bdev->bd_disk->open_mutex); - part = xa_load(&bdev->bd_disk->part_tbl, partno); + mutex_lock(&disk->open_mutex); + part = xa_load(&disk->part_tbl, partno); if (!part) goto out_unlock; @@ -512,14 +511,14 @@ int bdev_resize_partition(struct block_device *bdev, int partno, goto out_unlock; ret = -EBUSY; - if (partition_overlaps(bdev->bd_disk, start, length, partno)) + if (partition_overlaps(disk, start, length, partno)) goto out_unlock; bdev_set_nr_sectors(part, length); ret = 0; out_unlock: - mutex_unlock(&bdev->bd_disk->open_mutex); + mutex_unlock(&disk->open_mutex); return ret; } @@ -667,7 +666,7 @@ int bdev_disk_changed(struct gendisk *disk, bool invalidate) lockdep_assert_held(&disk->open_mutex); - if (!(disk->flags & GENHD_FL_UP)) + if (!disk_live(disk)) return -ENXIO; rescan: @@ -715,10 +714,10 @@ EXPORT_SYMBOL_GPL(bdev_disk_changed); void *read_part_sector(struct parsed_partitions *state, sector_t n, Sector *p) { - struct address_space *mapping = state->bdev->bd_inode->i_mapping; + struct address_space *mapping = state->disk->part0->bd_inode->i_mapping; struct page *page; - if (n >= get_capacity(state->bdev->bd_disk)) { + if (n >= get_capacity(state->disk)) { state->access_beyond_eod = true; return NULL; } diff --git a/block/partitions/efi.c b/block/partitions/efi.c index e2716792ecc1..7ca5c4c374d4 100644 --- a/block/partitions/efi.c +++ b/block/partitions/efi.c @@ -124,19 +124,17 @@ efi_crc32(const void *buf, unsigned long len) /** * last_lba(): return number of last logical block of device - * @bdev: block device + * @disk: block device * * Description: Returns last LBA value on success, 0 on error. * This is stored (by sd and ide-geometry) in * the part[0] entry for this disk, and is the number of * physical sectors available on the disk. */ -static u64 last_lba(struct block_device *bdev) +static u64 last_lba(struct gendisk *disk) { - if (!bdev || !bdev->bd_inode) - return 0; - return div_u64(bdev->bd_inode->i_size, - bdev_logical_block_size(bdev)) - 1ULL; + return div_u64(disk->part0->bd_inode->i_size, + queue_logical_block_size(disk->queue)) - 1ULL; } static inline int pmbr_part_valid(gpt_mbr_record *part) @@ -231,17 +229,17 @@ done: * @buffer: destination buffer * @count: bytes to read * - * Description: Reads @count bytes from @state->bdev into @buffer. + * Description: Reads @count bytes from @state->disk into @buffer. * Returns number of bytes read on success, 0 on error. */ static size_t read_lba(struct parsed_partitions *state, u64 lba, u8 *buffer, size_t count) { size_t totalreadcount = 0; - struct block_device *bdev = state->bdev; - sector_t n = lba * (bdev_logical_block_size(bdev) / 512); + sector_t n = lba * + (queue_logical_block_size(state->disk->queue) / 512); - if (!buffer || lba > last_lba(bdev)) + if (!buffer || lba > last_lba(state->disk)) return 0; while (count) { @@ -302,14 +300,14 @@ static gpt_entry *alloc_read_gpt_entries(struct parsed_partitions *state, * @lba: the Logical Block Address of the partition table * * Description: returns GPT header on success, NULL on error. Allocates - * and fills a GPT header starting at @ from @state->bdev. + * and fills a GPT header starting at @ from @state->disk. * Note: remember to free gpt when finished with it. */ static gpt_header *alloc_read_gpt_header(struct parsed_partitions *state, u64 lba) { gpt_header *gpt; - unsigned ssz = bdev_logical_block_size(state->bdev); + unsigned ssz = queue_logical_block_size(state->disk->queue); gpt = kmalloc(ssz, GFP_KERNEL); if (!gpt) @@ -356,10 +354,10 @@ static int is_gpt_valid(struct parsed_partitions *state, u64 lba, /* Check the GUID Partition Table header size is too big */ if (le32_to_cpu((*gpt)->header_size) > - bdev_logical_block_size(state->bdev)) { + queue_logical_block_size(state->disk->queue)) { pr_debug("GUID Partition Table Header size is too large: %u > %u\n", le32_to_cpu((*gpt)->header_size), - bdev_logical_block_size(state->bdev)); + queue_logical_block_size(state->disk->queue)); goto fail; } @@ -395,7 +393,7 @@ static int is_gpt_valid(struct parsed_partitions *state, u64 lba, /* Check the first_usable_lba and last_usable_lba are * within the disk. */ - lastlba = last_lba(state->bdev); + lastlba = last_lba(state->disk); if (le64_to_cpu((*gpt)->first_usable_lba) > lastlba) { pr_debug("GPT: first_usable_lba incorrect: %lld > %lld\n", (unsigned long long)le64_to_cpu((*gpt)->first_usable_lba), @@ -587,13 +585,15 @@ static int find_valid_gpt(struct parsed_partitions *state, gpt_header **gpt, gpt_header *pgpt = NULL, *agpt = NULL; gpt_entry *pptes = NULL, *aptes = NULL; legacy_mbr *legacymbr; - sector_t total_sectors = i_size_read(state->bdev->bd_inode) >> 9; + struct gendisk *disk = state->disk; + const struct block_device_operations *fops = disk->fops; + sector_t total_sectors = get_capacity(state->disk); u64 lastlba; if (!ptes) return 0; - lastlba = last_lba(state->bdev); + lastlba = last_lba(state->disk); if (!force_gpt) { /* This will be added to the EFI Spec. per Intel after v1.02. */ legacymbr = kzalloc(sizeof(*legacymbr), GFP_KERNEL); @@ -621,6 +621,16 @@ static int find_valid_gpt(struct parsed_partitions *state, gpt_header **gpt, if (!good_agpt && force_gpt) good_agpt = is_gpt_valid(state, lastlba, &agpt, &aptes); + if (!good_agpt && force_gpt && fops->alternative_gpt_sector) { + sector_t agpt_sector; + int err; + + err = fops->alternative_gpt_sector(disk, &agpt_sector); + if (!err) + good_agpt = is_gpt_valid(state, agpt_sector, + &agpt, &aptes); + } + /* The obviously unsuccessful case */ if (!good_pgpt && !good_agpt) goto fail; @@ -705,7 +715,7 @@ int efi_partition(struct parsed_partitions *state) gpt_header *gpt = NULL; gpt_entry *ptes = NULL; u32 i; - unsigned ssz = bdev_logical_block_size(state->bdev) / 512; + unsigned ssz = queue_logical_block_size(state->disk->queue) / 512; if (!find_valid_gpt(state, &gpt, &ptes) || !gpt || !ptes) { kfree(gpt); @@ -722,7 +732,7 @@ int efi_partition(struct parsed_partitions *state) u64 size = le64_to_cpu(ptes[i].ending_lba) - le64_to_cpu(ptes[i].starting_lba) + 1ULL; - if (!is_pte_valid(&ptes[i], last_lba(state->bdev))) + if (!is_pte_valid(&ptes[i], last_lba(state->disk))) continue; put_partition(state, i+1, start * ssz, size * ssz); diff --git a/block/partitions/ibm.c b/block/partitions/ibm.c index 4b044e620d35..9bca396aef4a 100644 --- a/block/partitions/ibm.c +++ b/block/partitions/ibm.c @@ -290,8 +290,8 @@ static int find_cms1_partitions(struct parsed_partitions *state, int ibm_partition(struct parsed_partitions *state) { int (*fn)(struct gendisk *disk, dasd_information2_t *info); - struct block_device *bdev = state->bdev; - struct gendisk *disk = bdev->bd_disk; + struct gendisk *disk = state->disk; + struct block_device *bdev = disk->part0; int blocksize, res; loff_t i_size, offset, size; dasd_information2_t *info; diff --git a/block/partitions/ldm.c b/block/partitions/ldm.c index b8b518d7fb77..27f6c7d9c776 100644 --- a/block/partitions/ldm.c +++ b/block/partitions/ldm.c @@ -304,7 +304,7 @@ static bool ldm_validate_privheads(struct parsed_partitions *state, } } - num_sects = state->bdev->bd_inode->i_size >> 9; + num_sects = get_capacity(state->disk); if ((ph[0]->config_start > num_sects) || ((ph[0]->config_start + ph[0]->config_size) > num_sects)) { @@ -339,11 +339,11 @@ out: /** * ldm_validate_tocblocks - Validate the table of contents and its backups * @state: Partition check state including device holding the LDM Database - * @base: Offset, into @state->bdev, of the database + * @base: Offset, into @state->disk, of the database * @ldb: Cache of the database structures * * Find and compare the four tables of contents of the LDM Database stored on - * @state->bdev and return the parsed information into @toc1. + * @state->disk and return the parsed information into @toc1. * * The offsets and sizes of the configs are range-checked against a privhead. * @@ -486,8 +486,8 @@ out: * only likely to happen if the underlying device is strange. If that IS * the case we should return zero to let someone else try. * - * Return: 'true' @state->bdev is a dynamic disk - * 'false' @state->bdev is not a dynamic disk, or an error occurred + * Return: 'true' @state->disk is a dynamic disk + * 'false' @state->disk is not a dynamic disk, or an error occurred */ static bool ldm_validate_partition_table(struct parsed_partitions *state) { @@ -1340,7 +1340,7 @@ static bool ldm_frag_commit (struct list_head *frags, struct ldmdb *ldb) /** * ldm_get_vblks - Read the on-disk database of VBLKs into memory * @state: Partition check state including device holding the LDM Database - * @base: Offset, into @state->bdev, of the database + * @base: Offset, into @state->disk, of the database * @ldb: Cache of the database structures * * To use the information from the VBLKs, they need to be read from the disk, @@ -1432,10 +1432,10 @@ static void ldm_free_vblks (struct list_head *lh) * example, if the device is hda, we would have: hda1: LDM database, hda2, hda3, * and so on: the actual data containing partitions. * - * Return: 1 Success, @state->bdev is a dynamic disk and we handled it - * 0 Success, @state->bdev is not a dynamic disk + * Return: 1 Success, @state->disk is a dynamic disk and we handled it + * 0 Success, @state->disk is not a dynamic disk * -1 An error occurred before enough information had been read - * Or @state->bdev is a dynamic disk, but it may be corrupted + * Or @state->disk is a dynamic disk, but it may be corrupted */ int ldm_partition(struct parsed_partitions *state) { diff --git a/block/partitions/mac.c b/block/partitions/mac.c index b6095335636c..7b521df00a39 100644 --- a/block/partitions/mac.c +++ b/block/partitions/mac.c @@ -133,7 +133,7 @@ int mac_partition(struct parsed_partitions *state) } #ifdef CONFIG_PPC_PMAC if (found_root_goodness) - note_bootable_part(state->bdev->bd_dev, found_root, + note_bootable_part(state->disk->part0->bd_dev, found_root, found_root_goodness); #endif diff --git a/block/partitions/msdos.c b/block/partitions/msdos.c index f5102596a984..b5d5c229cc3b 100644 --- a/block/partitions/msdos.c +++ b/block/partitions/msdos.c @@ -135,11 +135,12 @@ static void parse_extended(struct parsed_partitions *state, Sector sect; unsigned char *data; sector_t this_sector, this_size; - sector_t sector_size = bdev_logical_block_size(state->bdev) / 512; + sector_t sector_size; int loopct = 0; /* number of links followed without finding a data partition */ int i; + sector_size = queue_logical_block_size(state->disk->queue) / 512; this_sector = first_sector; this_size = first_size; @@ -579,7 +580,7 @@ static struct { int msdos_partition(struct parsed_partitions *state) { - sector_t sector_size = bdev_logical_block_size(state->bdev) / 512; + sector_t sector_size; Sector sect; unsigned char *data; struct msdos_partition *p; @@ -587,6 +588,7 @@ int msdos_partition(struct parsed_partitions *state) int slot; u32 disksig; + sector_size = queue_logical_block_size(state->disk->queue) / 512; data = read_part_sector(state, 0, §); if (!data) return -1; diff --git a/block/partitions/sgi.c b/block/partitions/sgi.c index 4273f1bb0515..9cc6b8c1eea4 100644 --- a/block/partitions/sgi.c +++ b/block/partitions/sgi.c @@ -43,7 +43,6 @@ int sgi_partition(struct parsed_partitions *state) Sector sect; struct sgi_disklabel *label; struct sgi_partition *p; - char b[BDEVNAME_SIZE]; label = read_part_sector(state, 0, §); if (!label) @@ -52,7 +51,7 @@ int sgi_partition(struct parsed_partitions *state) magic = label->magic_mushroom; if(be32_to_cpu(magic) != SGI_LABEL_MAGIC) { /*printk("Dev %s SGI disklabel: bad magic %08x\n", - bdevname(bdev, b), be32_to_cpu(magic));*/ + state->disk->disk_name, be32_to_cpu(magic));*/ put_dev_sector(sect); return 0; } @@ -63,7 +62,7 @@ int sgi_partition(struct parsed_partitions *state) } if(csum) { printk(KERN_WARNING "Dev %s SGI disklabel: csum bad, label corrupted\n", - bdevname(state->bdev, b)); + state->disk->disk_name); put_dev_sector(sect); return 0; } diff --git a/block/partitions/sun.c b/block/partitions/sun.c index 47dc53eccf77..ddf9e6def4b2 100644 --- a/block/partitions/sun.c +++ b/block/partitions/sun.c @@ -65,7 +65,6 @@ int sun_partition(struct parsed_partitions *state) } * label; struct sun_partition *p; unsigned long spc; - char b[BDEVNAME_SIZE]; int use_vtoc; int nparts; @@ -76,7 +75,7 @@ int sun_partition(struct parsed_partitions *state) p = label->partitions; if (be16_to_cpu(label->magic) != SUN_LABEL_MAGIC) { /* printk(KERN_INFO "Dev %s Sun disklabel: bad magic %04x\n", - bdevname(bdev, b), be16_to_cpu(label->magic)); */ + state->disk->disk_name, be16_to_cpu(label->magic)); */ put_dev_sector(sect); return 0; } @@ -86,7 +85,7 @@ int sun_partition(struct parsed_partitions *state) csum ^= *ush--; if (csum) { printk("Dev %s Sun disklabel: Csum bad, label corrupted\n", - bdevname(state->bdev, b)); + state->disk->disk_name); put_dev_sector(sect); return 0; } diff --git a/block/t10-pi.c b/block/t10-pi.c index d910534b3a41..00c203b2a921 100644 --- a/block/t10-pi.c +++ b/block/t10-pi.c @@ -147,11 +147,10 @@ static void t10_pi_type1_prepare(struct request *rq) break; bip_for_each_vec(iv, bip, iter) { - void *p, *pmap; unsigned int j; + void *p; - pmap = kmap_atomic(iv.bv_page); - p = pmap + iv.bv_offset; + p = bvec_kmap_local(&iv); for (j = 0; j < iv.bv_len; j += tuple_sz) { struct t10_pi_tuple *pi = p; @@ -161,8 +160,7 @@ static void t10_pi_type1_prepare(struct request *rq) ref_tag++; p += tuple_sz; } - - kunmap_atomic(pmap); + kunmap_local(p); } bip->bip_flags |= BIP_MAPPED_INTEGRITY; @@ -195,11 +193,10 @@ static void t10_pi_type1_complete(struct request *rq, unsigned int nr_bytes) struct bvec_iter iter; bip_for_each_vec(iv, bip, iter) { - void *p, *pmap; unsigned int j; + void *p; - pmap = kmap_atomic(iv.bv_page); - p = pmap + iv.bv_offset; + p = bvec_kmap_local(&iv); for (j = 0; j < iv.bv_len && intervals; j += tuple_sz) { struct t10_pi_tuple *pi = p; @@ -210,8 +207,7 @@ static void t10_pi_type1_complete(struct request *rq, unsigned int nr_bytes) intervals--; p += tuple_sz; } - - kunmap_atomic(pmap); + kunmap_local(p); } } } diff --git a/drivers/block/brd.c b/drivers/block/brd.c index 95694113e38e..58ec167aa018 100644 --- a/drivers/block/brd.c +++ b/drivers/block/brd.c @@ -27,9 +27,6 @@ #include <linux/uaccess.h> -#define PAGE_SECTORS_SHIFT (PAGE_SHIFT - SECTOR_SHIFT) -#define PAGE_SECTORS (1 << PAGE_SECTORS_SHIFT) - /* * Each block ramdisk device has a radix_tree brd_pages of pages that stores * the pages containing the block device's contents. A brd page's ->index is diff --git a/drivers/block/drbd/drbd_nl.c b/drivers/block/drbd/drbd_nl.c index e7d0e637e632..44ccf8b4f4b2 100644 --- a/drivers/block/drbd/drbd_nl.c +++ b/drivers/block/drbd/drbd_nl.c @@ -1364,7 +1364,7 @@ static void drbd_setup_queue_param(struct drbd_device *device, struct drbd_backi if (b) { blk_stack_limits(&q->limits, &b->limits, 0); - blk_queue_update_readahead(q); + disk_update_readahead(device->vdisk); } fixup_discard_if_not_supported(q); fixup_write_zeroes(device, q); diff --git a/drivers/block/drbd/drbd_req.c b/drivers/block/drbd/drbd_req.c index 13beb98a7c5a..5ca233644d70 100644 --- a/drivers/block/drbd/drbd_req.c +++ b/drivers/block/drbd/drbd_req.c @@ -905,13 +905,12 @@ static bool drbd_may_do_local_read(struct drbd_device *device, sector_t sector, static bool remote_due_to_read_balancing(struct drbd_device *device, sector_t sector, enum drbd_read_balancing rbm) { - struct backing_dev_info *bdi; int stripe_shift; switch (rbm) { case RB_CONGESTED_REMOTE: - bdi = device->ldev->backing_bdev->bd_disk->queue->backing_dev_info; - return bdi_read_congested(bdi); + return bdi_read_congested( + device->ldev->backing_bdev->bd_disk->bdi); case RB_LEAST_PENDING: return atomic_read(&device->local_cnt) > atomic_read(&device->ap_pending_cnt) + atomic_read(&device->rs_pending_cnt); diff --git a/drivers/block/loop.c b/drivers/block/loop.c index f0cdff0c5fbf..fa1c298a8cfb 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -774,6 +774,7 @@ static int loop_change_fd(struct loop_device *lo, struct block_device *bdev, goto out_err; /* and ... switch */ + disk_force_media_change(lo->lo_disk, DISK_EVENT_MEDIA_CHANGE); blk_mq_freeze_queue(lo->lo_queue); mapping_set_gfp_mask(old_file->f_mapping, lo->old_gfp_mask); lo->lo_backing_file = file; @@ -1257,6 +1258,7 @@ static int loop_configure(struct loop_device *lo, fmode_t mode, goto out_unlock; } + disk_force_media_change(lo->lo_disk, DISK_EVENT_MEDIA_CHANGE); set_disk_ro(lo->lo_disk, (lo->lo_flags & LO_FLAGS_READ_ONLY) != 0); INIT_WORK(&lo->rootcg_work, loop_rootcg_workfn); @@ -1304,10 +1306,6 @@ static int loop_configure(struct loop_device *lo, fmode_t mode, if (partscan) lo->lo_disk->flags &= ~GENHD_FL_NO_PART_SCAN; - /* Grab the block_device to prevent its destruction after we - * put /dev/loopXX inode. Later in __loop_clr_fd() we bdput(bdev). - */ - bdgrab(bdev); loop_global_unlock(lo, is_loop); if (partscan) loop_reread_partitions(lo); @@ -1398,7 +1396,6 @@ static int __loop_clr_fd(struct loop_device *lo, bool release) blk_queue_physical_block_size(lo->lo_queue, 512); blk_queue_io_min(lo->lo_queue, 512); if (bdev) { - bdput(bdev); invalidate_bdev(bdev); bdev->bd_inode->i_mapping->wb_err = 0; } @@ -1415,6 +1412,7 @@ static int __loop_clr_fd(struct loop_device *lo, bool release) partscan = lo->lo_flags & LO_FLAGS_PARTSCAN && bdev; lo_number = lo->lo_number; + disk_force_media_change(lo->lo_disk, DISK_EVENT_MEDIA_CHANGE); out_unlock: mutex_unlock(&lo->lo_mutex); if (partscan) { @@ -2335,7 +2333,8 @@ static int loop_add(int i) lo->tag_set.queue_depth = 128; lo->tag_set.numa_node = NUMA_NO_NODE; lo->tag_set.cmd_size = sizeof(struct loop_cmd); - lo->tag_set.flags = BLK_MQ_F_SHOULD_MERGE | BLK_MQ_F_STACKING; + lo->tag_set.flags = BLK_MQ_F_SHOULD_MERGE | BLK_MQ_F_STACKING | + BLK_MQ_F_NO_SCHED_BY_DEFAULT; lo->tag_set.driver_data = lo; err = blk_mq_alloc_tag_set(&lo->tag_set); @@ -2391,6 +2390,8 @@ static int loop_add(int i) disk->fops = &lo_fops; disk->private_data = lo; disk->queue = lo->lo_queue; + disk->events = DISK_EVENT_MEDIA_CHANGE; + disk->event_flags = DISK_EVENT_FLAG_UEVENT; sprintf(disk->disk_name, "loop%d", i); add_disk(disk); mutex_unlock(&loop_ctl_mutex); diff --git a/drivers/block/null_blk/main.c b/drivers/block/null_blk/main.c index d734e9ee1546..187d779c8ca0 100644 --- a/drivers/block/null_blk/main.c +++ b/drivers/block/null_blk/main.c @@ -11,10 +11,6 @@ #include <linux/init.h> #include "null_blk.h" -#define PAGE_SECTORS_SHIFT (PAGE_SHIFT - SECTOR_SHIFT) -#define PAGE_SECTORS (1 << PAGE_SECTORS_SHIFT) -#define SECTOR_MASK (PAGE_SECTORS - 1) - #define FREE_BATCH 16 #define TICKS_PER_SEC 50ULL @@ -1721,8 +1717,7 @@ static int null_gendisk_register(struct nullb *nullb) return ret; } - add_disk(disk); - return 0; + return add_disk(disk); } static int null_init_tag_set(struct nullb *nullb, struct blk_mq_tag_set *set) diff --git a/drivers/block/pktcdvd.c b/drivers/block/pktcdvd.c index 538446b652de..0f26b2510a75 100644 --- a/drivers/block/pktcdvd.c +++ b/drivers/block/pktcdvd.c @@ -1183,10 +1183,8 @@ try_next_bio: wakeup = (pd->write_congestion_on > 0 && pd->bio_queue_size <= pd->write_congestion_off); spin_unlock(&pd->lock); - if (wakeup) { - clear_bdi_congested(pd->disk->queue->backing_dev_info, - BLK_RW_ASYNC); - } + if (wakeup) + clear_bdi_congested(pd->disk->bdi, BLK_RW_ASYNC); pkt->sleep_time = max(PACKET_WAIT_TIME, 1); pkt_set_state(pkt, PACKET_WAITING_STATE); @@ -2366,7 +2364,7 @@ static void pkt_make_request_write(struct request_queue *q, struct bio *bio) spin_lock(&pd->lock); if (pd->write_congestion_on > 0 && pd->bio_queue_size >= pd->write_congestion_on) { - set_bdi_congested(q->backing_dev_info, BLK_RW_ASYNC); + set_bdi_congested(bio->bi_bdev->bd_disk->bdi, BLK_RW_ASYNC); do { spin_unlock(&pd->lock); congestion_wait(BLK_RW_ASYNC, HZ); diff --git a/drivers/block/ps3disk.c b/drivers/block/ps3disk.c index f374ea2c67ce..8d51efbe045d 100644 --- a/drivers/block/ps3disk.c +++ b/drivers/block/ps3disk.c @@ -83,26 +83,12 @@ static void ps3disk_scatter_gather(struct ps3_storage_device *dev, unsigned int offset = 0; struct req_iterator iter; struct bio_vec bvec; - unsigned int i = 0; - size_t size; - void *buf; rq_for_each_segment(bvec, req, iter) { - unsigned long flags; - dev_dbg(&dev->sbd.core, "%s:%u: bio %u: %u sectors from %llu\n", - __func__, __LINE__, i, bio_sectors(iter.bio), - iter.bio->bi_iter.bi_sector); - - size = bvec.bv_len; - buf = bvec_kmap_irq(&bvec, &flags); if (gather) - memcpy(dev->bounce_buf+offset, buf, size); + memcpy_from_bvec(dev->bounce_buf + offset, &bvec); else - memcpy(buf, dev->bounce_buf+offset, size); - offset += size; - flush_kernel_dcache_page(bvec.bv_page); - bvec_kunmap_irq(buf, &flags); - i++; + memcpy_to_bvec(&bvec, dev->bounce_buf + offset); } } diff --git a/drivers/block/ps3vram.c b/drivers/block/ps3vram.c index 7fbf469651c4..c7b19e128b03 100644 --- a/drivers/block/ps3vram.c +++ b/drivers/block/ps3vram.c @@ -541,7 +541,7 @@ static struct bio *ps3vram_do_bio(struct ps3_system_bus_device *dev, bio_for_each_segment(bvec, bio, iter) { /* PS3 is ppc64, so we don't handle highmem */ - char *ptr = page_address(bvec.bv_page) + bvec.bv_offset; + char *ptr = bvec_virt(&bvec); size_t len = bvec.bv_len, retlen; dev_dbg(&dev->core, " %s %zu bytes at offset %llu\n", op, diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c index 90b947c96402..e65c9d706f6f 100644 --- a/drivers/block/rbd.c +++ b/drivers/block/rbd.c @@ -1219,24 +1219,13 @@ static void rbd_dev_mapping_clear(struct rbd_device *rbd_dev) rbd_dev->mapping.size = 0; } -static void zero_bvec(struct bio_vec *bv) -{ - void *buf; - unsigned long flags; - - buf = bvec_kmap_irq(bv, &flags); - memset(buf, 0, bv->bv_len); - flush_dcache_page(bv->bv_page); - bvec_kunmap_irq(buf, &flags); -} - static void zero_bios(struct ceph_bio_iter *bio_pos, u32 off, u32 bytes) { struct ceph_bio_iter it = *bio_pos; ceph_bio_iter_advance(&it, off); ceph_bio_iter_advance_step(&it, bytes, ({ - zero_bvec(&bv); + memzero_bvec(&bv); })); } @@ -1246,7 +1235,7 @@ static void zero_bvecs(struct ceph_bvec_iter *bvec_pos, u32 off, u32 bytes) ceph_bvec_iter_advance(&it, off); ceph_bvec_iter_advance_step(&it, bytes, ({ - zero_bvec(&bv); + memzero_bvec(&bv); })); } @@ -2997,8 +2986,7 @@ static bool is_zero_bvecs(struct bio_vec *bvecs, u32 bytes) }; ceph_bvec_iter_advance_step(&it, bytes, ({ - if (memchr_inv(page_address(bv.bv_page) + bv.bv_offset, 0, - bv.bv_len)) + if (memchr_inv(bvec_virt(&bv), 0, bv.bv_len)) return false; })); return true; diff --git a/drivers/block/sx8.c b/drivers/block/sx8.c index 7b54353ee92b..420cd952ddc4 100644 --- a/drivers/block/sx8.c +++ b/drivers/block/sx8.c @@ -1373,7 +1373,7 @@ static void carm_free_disk(struct carm_host *host, unsigned int port_no) if (!disk) return; - if (disk->flags & GENHD_FL_UP) + if (host->state > HST_DEV_ACTIVATE) del_gendisk(disk); blk_cleanup_disk(disk); } diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c index afb37aac09e8..57c6ae7debd9 100644 --- a/drivers/block/virtio_blk.c +++ b/drivers/block/virtio_blk.c @@ -166,11 +166,8 @@ static inline void virtblk_request_done(struct request *req) { struct virtblk_req *vbr = blk_mq_rq_to_pdu(req); - if (req->rq_flags & RQF_SPECIAL_PAYLOAD) { - kfree(page_address(req->special_vec.bv_page) + - req->special_vec.bv_offset); - } - + if (req->rq_flags & RQF_SPECIAL_PAYLOAD) + kfree(bvec_virt(&req->special_vec)); blk_mq_end_request(req, virtblk_result(vbr)); } @@ -844,7 +841,7 @@ static int virtblk_probe(struct virtio_device *vdev) "block size is changed unexpectedly, now is %u\n", blk_size); err = -EINVAL; - goto err_cleanup_disk; + goto out_cleanup_disk; } /* Use topology information if available */ @@ -902,10 +899,13 @@ static int virtblk_probe(struct virtio_device *vdev) virtblk_update_capacity(vblk, false); virtio_device_ready(vdev); - device_add_disk(&vdev->dev, vblk->disk, virtblk_attr_groups); + err = device_add_disk(&vdev->dev, vblk->disk, virtblk_attr_groups); + if (err) + goto out_cleanup_disk; + return 0; -err_cleanup_disk: +out_cleanup_disk: blk_cleanup_disk(vblk->disk); out_free_tags: blk_mq_free_tag_set(&vblk->tag_set); diff --git a/drivers/md/Kconfig b/drivers/md/Kconfig index 0602e82a9516..f45fb372e51b 100644 --- a/drivers/md/Kconfig +++ b/drivers/md/Kconfig @@ -15,6 +15,7 @@ if MD config BLK_DEV_MD tristate "RAID support" + select BLOCK_HOLDER_DEPRECATED if SYSFS help This driver lets you combine several hard disk partitions into one logical block device. This can be used to simply append one @@ -201,6 +202,7 @@ config BLK_DEV_DM_BUILTIN config BLK_DEV_DM tristate "Device mapper support" + select BLOCK_HOLDER_DEPRECATED if SYSFS select BLK_DEV_DM_BUILTIN depends on DAX || DAX=n help @@ -340,7 +342,7 @@ config DM_WRITECACHE config DM_EBS tristate "Emulated block size target (EXPERIMENTAL)" - depends on BLK_DEV_DM + depends on BLK_DEV_DM && !HIGHMEM select DM_BUFIO help dm-ebs emulates smaller logical block size on backing devices diff --git a/drivers/md/bcache/Kconfig b/drivers/md/bcache/Kconfig index d1ca4d059c20..cf3e8096942a 100644 --- a/drivers/md/bcache/Kconfig +++ b/drivers/md/bcache/Kconfig @@ -2,6 +2,7 @@ config BCACHE tristate "Block device as cache" + select BLOCK_HOLDER_DEPRECATED if SYSFS select CRC64 help Allows a block device to be used as cache for other devices; uses diff --git a/drivers/md/bcache/btree.c b/drivers/md/bcache/btree.c index 183a58c89377..0595559de174 100644 --- a/drivers/md/bcache/btree.c +++ b/drivers/md/bcache/btree.c @@ -378,7 +378,7 @@ static void do_btree_node_write(struct btree *b) struct bvec_iter_all iter_all; bio_for_each_segment_all(bv, b->bio, iter_all) { - memcpy(page_address(bv->bv_page), addr, PAGE_SIZE); + memcpy(bvec_virt(bv), addr, PAGE_SIZE); addr += PAGE_SIZE; } diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c index 185246a0d855..f2874c77ff79 100644 --- a/drivers/md/bcache/super.c +++ b/drivers/md/bcache/super.c @@ -885,11 +885,6 @@ static void bcache_device_free(struct bcache_device *d) bcache_device_detach(d); if (disk) { - bool disk_added = (disk->flags & GENHD_FL_UP) != 0; - - if (disk_added) - del_gendisk(disk); - blk_cleanup_disk(disk); ida_simple_remove(&bcache_device_idx, first_minor_to_idx(disk->first_minor)); @@ -931,20 +926,20 @@ static int bcache_device_init(struct bcache_device *d, unsigned int block_size, n = BITS_TO_LONGS(d->nr_stripes) * sizeof(unsigned long); d->full_dirty_stripes = kvzalloc(n, GFP_KERNEL); if (!d->full_dirty_stripes) - return -ENOMEM; + goto out_free_stripe_sectors_dirty; idx = ida_simple_get(&bcache_device_idx, 0, BCACHE_DEVICE_IDX_MAX, GFP_KERNEL); if (idx < 0) - return idx; + goto out_free_full_dirty_stripes; if (bioset_init(&d->bio_split, 4, offsetof(struct bbio, bio), BIOSET_NEED_BVECS|BIOSET_NEED_RESCUER)) - goto err; + goto out_ida_remove; d->disk = blk_alloc_disk(NUMA_NO_NODE); if (!d->disk) - goto err; + goto out_bioset_exit; set_capacity(d->disk, sectors); snprintf(d->disk->disk_name, DISK_NAME_LEN, "bcache%i", idx); @@ -987,8 +982,14 @@ static int bcache_device_init(struct bcache_device *d, unsigned int block_size, return 0; -err: +out_bioset_exit: + bioset_exit(&d->bio_split); +out_ida_remove: ida_simple_remove(&bcache_device_idx, idx); +out_free_full_dirty_stripes: + kvfree(d->full_dirty_stripes); +out_free_stripe_sectors_dirty: + kvfree(d->stripe_sectors_dirty); return -ENOMEM; } @@ -1365,8 +1366,10 @@ static void cached_dev_free(struct closure *cl) mutex_lock(&bch_register_lock); - if (atomic_read(&dc->running)) + if (atomic_read(&dc->running)) { bd_unlink_disk_holder(dc->bdev, dc->disk.disk); + del_gendisk(dc->disk.disk); + } bcache_device_free(&dc->disk); list_del(&dc->list); @@ -1512,6 +1515,7 @@ static void flash_dev_free(struct closure *cl) mutex_lock(&bch_register_lock); atomic_long_sub(bcache_dev_sectors_dirty(d), &d->c->flash_dev_dirty_sectors); + del_gendisk(d->disk); bcache_device_free(d); mutex_unlock(&bch_register_lock); kobject_put(&d->kobj); diff --git a/drivers/md/bcache/util.h b/drivers/md/bcache/util.h index bca4a7c97da7..b64460a76267 100644 --- a/drivers/md/bcache/util.h +++ b/drivers/md/bcache/util.h @@ -15,8 +15,6 @@ #include "closure.h" -#define PAGE_SECTORS (PAGE_SIZE / 512) - struct closure; #ifdef CONFIG_BCACHE_DEBUG diff --git a/drivers/md/dm-ebs-target.c b/drivers/md/dm-ebs-target.c index 71475a2410be..0c509dae0ff8 100644 --- a/drivers/md/dm-ebs-target.c +++ b/drivers/md/dm-ebs-target.c @@ -74,7 +74,7 @@ static int __ebs_rw_bvec(struct ebs_c *ec, int rw, struct bio_vec *bv, struct bv if (unlikely(!bv->bv_page || !bv_len)) return -EIO; - pa = page_address(bv->bv_page) + bv->bv_offset; + pa = bvec_virt(bv); /* Handle overlapping page <-> blocks */ while (bv_len) { diff --git a/drivers/md/dm-integrity.c b/drivers/md/dm-integrity.c index 20f2510db1f6..a9ea361769a7 100644 --- a/drivers/md/dm-integrity.c +++ b/drivers/md/dm-integrity.c @@ -1819,7 +1819,7 @@ again: unsigned this_len; BUG_ON(PageHighMem(biv.bv_page)); - tag = lowmem_page_address(biv.bv_page) + biv.bv_offset; + tag = bvec_virt(&biv); this_len = min(biv.bv_len, data_to_process); r = dm_integrity_rw_tag(ic, tag, &dio->metadata_block, &dio->metadata_offset, this_len, dio->op == REQ_OP_READ ? TAG_READ : TAG_WRITE); @@ -2006,7 +2006,7 @@ retry_kmap: unsigned tag_now = min(biv.bv_len, tag_todo); char *tag_addr; BUG_ON(PageHighMem(biv.bv_page)); - tag_addr = lowmem_page_address(biv.bv_page) + biv.bv_offset; + tag_addr = bvec_virt(&biv); if (likely(dio->op == REQ_OP_WRITE)) memcpy(tag_ptr, tag_addr, tag_now); else diff --git a/drivers/md/dm-ioctl.c b/drivers/md/dm-ioctl.c index 2209cbcd84db..2575074a2204 100644 --- a/drivers/md/dm-ioctl.c +++ b/drivers/md/dm-ioctl.c @@ -1436,9 +1436,6 @@ static int table_load(struct file *filp, struct dm_ioctl *param, size_t param_si } if (dm_get_md_type(md) == DM_TYPE_NONE) { - /* Initial table load: acquire type of table. */ - dm_set_md_type(md, dm_table_get_type(t)); - /* setup md->queue to reflect md's type (may block) */ r = dm_setup_md_queue(md, t); if (r) { @@ -2187,7 +2184,6 @@ int __init dm_early_create(struct dm_ioctl *dmi, if (r) goto err_destroy_table; - md->type = dm_table_get_type(t); /* setup md->queue to reflect md's type (may block) */ r = dm_setup_md_queue(md, t); if (r) { diff --git a/drivers/md/dm-rq.c b/drivers/md/dm-rq.c index 0dbd48cbdff9..5b95eea517d1 100644 --- a/drivers/md/dm-rq.c +++ b/drivers/md/dm-rq.c @@ -559,7 +559,6 @@ int dm_mq_init_request_queue(struct mapped_device *md, struct dm_table *t) err = blk_mq_init_allocated_queue(md->tag_set, md->queue); if (err) goto out_tag_set; - elevator_init_mq(md->queue); return 0; out_tag_set: diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c index 0543cdf89e92..b03eabc1ed7c 100644 --- a/drivers/md/dm-table.c +++ b/drivers/md/dm-table.c @@ -2076,7 +2076,7 @@ int dm_table_set_restrictions(struct dm_table *t, struct request_queue *q, } dm_update_keyslot_manager(q, t); - blk_queue_update_readahead(q); + disk_update_readahead(t->md->disk); return 0; } diff --git a/drivers/md/dm-writecache.c b/drivers/md/dm-writecache.c index e21e29e81bbf..3d2cf811ec3e 100644 --- a/drivers/md/dm-writecache.c +++ b/drivers/md/dm-writecache.c @@ -1214,14 +1214,13 @@ static void memcpy_flushcache_optimized(void *dest, void *source, size_t size) static void bio_copy_block(struct dm_writecache *wc, struct bio *bio, void *data) { void *buf; - unsigned long flags; unsigned size; int rw = bio_data_dir(bio); unsigned remaining_size = wc->block_size; do { struct bio_vec bv = bio_iter_iovec(bio, bio->bi_iter); - buf = bvec_kmap_irq(&bv, &flags); + buf = bvec_kmap_local(&bv); size = bv.bv_len; if (unlikely(size > remaining_size)) size = remaining_size; @@ -1239,7 +1238,7 @@ static void bio_copy_block(struct dm_writecache *wc, struct bio *bio, void *data memcpy_flushcache_optimized(data, buf, size); } - bvec_kunmap_irq(buf, &flags); + kunmap_local(buf); data = (char *)data + size; remaining_size -= size; diff --git a/drivers/md/dm.c b/drivers/md/dm.c index 2c5f9e585211..7981b7287628 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -1693,14 +1693,13 @@ static void cleanup_mapped_device(struct mapped_device *md) spin_lock(&_minor_lock); md->disk->private_data = NULL; spin_unlock(&_minor_lock); - del_gendisk(md->disk); - } - - if (md->queue) + if (dm_get_md_type(md) != DM_TYPE_NONE) { + dm_sysfs_exit(md); + del_gendisk(md->disk); + } dm_queue_destroy_keyslot_manager(md->queue); - - if (md->disk) blk_cleanup_disk(md->disk); + } cleanup_srcu_struct(&md->io_barrier); @@ -1792,7 +1791,6 @@ static struct mapped_device *alloc_dev(int minor) goto bad; } - add_disk_no_queue_reg(md->disk); format_dev_t(md->name, MKDEV(_major, minor)); md->wq = alloc_workqueue("kdmflush", WQ_MEM_RECLAIM, 0); @@ -1993,19 +1991,12 @@ static struct dm_table *__unbind(struct mapped_device *md) */ int dm_create(int minor, struct mapped_device **result) { - int r; struct mapped_device *md; md = alloc_dev(minor); if (!md) return -ENXIO; - r = dm_sysfs_init(md); - if (r) { - free_dev(md); - return r; - } - *result = md; return 0; } @@ -2056,9 +2047,9 @@ EXPORT_SYMBOL_GPL(dm_get_queue_limits); */ int dm_setup_md_queue(struct mapped_device *md, struct dm_table *t) { - int r; + enum dm_queue_mode type = dm_table_get_type(t); struct queue_limits limits; - enum dm_queue_mode type = dm_get_md_type(md); + int r; switch (type) { case DM_TYPE_REQUEST_BASED: @@ -2086,8 +2077,14 @@ int dm_setup_md_queue(struct mapped_device *md, struct dm_table *t) if (r) return r; - blk_register_queue(md->disk); + add_disk(md->disk); + r = dm_sysfs_init(md); + if (r) { + del_gendisk(md->disk); + return r; + } + md->type = type; return 0; } @@ -2193,7 +2190,6 @@ static void __dm_destroy(struct mapped_device *md, bool wait) DMWARN("%s: Forcibly removing mapped_device still in use! (%d users)", dm_device_name(md), atomic_read(&md->holders)); - dm_sysfs_exit(md); dm_table_destroy(__unbind(md)); free_dev(md); } diff --git a/drivers/md/md.h b/drivers/md/md.h index 832547cf038f..4c96c36bd01a 100644 --- a/drivers/md/md.h +++ b/drivers/md/md.h @@ -764,9 +764,7 @@ struct md_rdev *md_find_rdev_rcu(struct mddev *mddev, dev_t dev); static inline bool is_mddev_broken(struct md_rdev *rdev, const char *md_type) { - int flags = rdev->bdev->bd_disk->flags; - - if (!(flags & GENHD_FL_UP)) { + if (!disk_live(rdev->bdev->bd_disk)) { if (!test_and_set_bit(MD_BROKEN, &rdev->mddev->flags)) pr_warn("md: %s: %s array has a missing/failed member\n", mdname(rdev->mddev), md_type); diff --git a/drivers/mmc/core/block.c b/drivers/mmc/core/block.c index ce8aed562929..6a15fdf6e5f2 100644 --- a/drivers/mmc/core/block.c +++ b/drivers/mmc/core/block.c @@ -128,8 +128,6 @@ struct mmc_blk_data { * track of the current selected device partition. */ unsigned int part_curr; - struct device_attribute force_ro; - struct device_attribute power_ro_lock; int area_type; /* debugfs files (only in main mmc_blk_data) */ @@ -281,6 +279,9 @@ out_put: return count; } +static DEVICE_ATTR(ro_lock_until_next_power_on, 0, + power_ro_lock_show, power_ro_lock_store); + static ssize_t force_ro_show(struct device *dev, struct device_attribute *attr, char *buf) { @@ -313,6 +314,44 @@ out: return ret; } +static DEVICE_ATTR(force_ro, 0644, force_ro_show, force_ro_store); + +static struct attribute *mmc_disk_attrs[] = { + &dev_attr_force_ro.attr, + &dev_attr_ro_lock_until_next_power_on.attr, + NULL, +}; + +static umode_t mmc_disk_attrs_is_visible(struct kobject *kobj, + struct attribute *a, int n) +{ + struct device *dev = container_of(kobj, struct device, kobj); + struct mmc_blk_data *md = mmc_blk_get(dev_to_disk(dev)); + umode_t mode = a->mode; + + if (a == &dev_attr_ro_lock_until_next_power_on.attr && + (md->area_type & MMC_BLK_DATA_AREA_BOOT) && + md->queue.card->ext_csd.boot_ro_lockable) { + mode = S_IRUGO; + if (!(md->queue.card->ext_csd.boot_ro_lock & + EXT_CSD_BOOT_WP_B_PWR_WP_DIS)) + mode |= S_IWUSR; + } + + mmc_blk_put(md); + return mode; +} + +static const struct attribute_group mmc_disk_attr_group = { + .is_visible = mmc_disk_attrs_is_visible, + .attrs = mmc_disk_attrs, +}; + +static const struct attribute_group *mmc_disk_attr_groups[] = { + &mmc_disk_attr_group, + NULL, +}; + static int mmc_blk_open(struct block_device *bdev, fmode_t mode) { struct mmc_blk_data *md = mmc_blk_get(bdev->bd_disk); @@ -792,6 +831,26 @@ static int mmc_blk_compat_ioctl(struct block_device *bdev, fmode_t mode, } #endif +static int mmc_blk_alternative_gpt_sector(struct gendisk *disk, + sector_t *sector) +{ + struct mmc_blk_data *md; + int ret; + + md = mmc_blk_get(disk); + if (!md) + return -EINVAL; + + if (md->queue.card) + ret = mmc_card_alternative_gpt_sector(md->queue.card, sector); + else + ret = -ENODEV; + + mmc_blk_put(md); + + return ret; +} + static const struct block_device_operations mmc_bdops = { .open = mmc_blk_open, .release = mmc_blk_release, @@ -801,6 +860,7 @@ static const struct block_device_operations mmc_bdops = { #ifdef CONFIG_COMPAT .compat_ioctl = mmc_blk_compat_ioctl, #endif + .alternative_gpt_sector = mmc_blk_alternative_gpt_sector, }; static int mmc_blk_part_switch_pre(struct mmc_card *card, @@ -2289,7 +2349,8 @@ static struct mmc_blk_data *mmc_blk_alloc_req(struct mmc_card *card, sector_t size, bool default_ro, const char *subname, - int area_type) + int area_type, + unsigned int part_type) { struct mmc_blk_data *md; int devidx, ret; @@ -2336,6 +2397,7 @@ static struct mmc_blk_data *mmc_blk_alloc_req(struct mmc_card *card, kref_init(&md->kref); md->queue.blkdata = md; + md->part_type = part_type; md->disk->major = MMC_BLOCK_MAJOR; md->disk->minors = perdev_minors; @@ -2388,6 +2450,10 @@ static struct mmc_blk_data *mmc_blk_alloc_req(struct mmc_card *card, md->disk->disk_name, mmc_card_id(card), mmc_card_name(card), cap_str, md->read_only ? "(ro)" : ""); + /* used in ->open, must be set before add_disk: */ + if (area_type == MMC_BLK_DATA_AREA_MAIN) + dev_set_drvdata(&card->dev, md); + device_add_disk(md->parent, md->disk, mmc_disk_attr_groups); return md; err_kfree: @@ -2417,7 +2483,7 @@ static struct mmc_blk_data *mmc_blk_alloc(struct mmc_card *card) } return mmc_blk_alloc_req(card, &card->dev, size, false, NULL, - MMC_BLK_DATA_AREA_MAIN); + MMC_BLK_DATA_AREA_MAIN, 0); } static int mmc_blk_alloc_part(struct mmc_card *card, @@ -2431,10 +2497,9 @@ static int mmc_blk_alloc_part(struct mmc_card *card, struct mmc_blk_data *part_md; part_md = mmc_blk_alloc_req(card, disk_to_dev(md->disk), size, default_ro, - subname, area_type); + subname, area_type, part_type); if (IS_ERR(part_md)) return PTR_ERR(part_md); - part_md->part_type = part_type; list_add(&part_md->part, &md->part); return 0; @@ -2635,27 +2700,13 @@ static int mmc_blk_alloc_parts(struct mmc_card *card, struct mmc_blk_data *md) static void mmc_blk_remove_req(struct mmc_blk_data *md) { - struct mmc_card *card; - - if (md) { - /* - * Flush remaining requests and free queues. It - * is freeing the queue that stops new requests - * from being accepted. - */ - card = md->queue.card; - if (md->disk->flags & GENHD_FL_UP) { - device_remove_file(disk_to_dev(md->disk), &md->force_ro); - if ((md->area_type & MMC_BLK_DATA_AREA_BOOT) && - card->ext_csd.boot_ro_lockable) - device_remove_file(disk_to_dev(md->disk), - &md->power_ro_lock); - - del_gendisk(md->disk); - } - mmc_cleanup_queue(&md->queue); - mmc_blk_put(md); - } + /* + * Flush remaining requests and free queues. It is freeing the queue + * that stops new requests from being accepted. + */ + del_gendisk(md->disk); + mmc_cleanup_queue(&md->queue); + mmc_blk_put(md); } static void mmc_blk_remove_parts(struct mmc_card *card, @@ -2679,51 +2730,6 @@ static void mmc_blk_remove_parts(struct mmc_card *card, } } -static int mmc_add_disk(struct mmc_blk_data *md) -{ - int ret; - struct mmc_card *card = md->queue.card; - - device_add_disk(md->parent, md->disk, NULL); - md->force_ro.show = force_ro_show; - md->force_ro.store = force_ro_store; - sysfs_attr_init(&md->force_ro.attr); - md->force_ro.attr.name = "force_ro"; - md->force_ro.attr.mode = S_IRUGO | S_IWUSR; - ret = device_create_file(disk_to_dev(md->disk), &md->force_ro); - if (ret) - goto force_ro_fail; - - if ((md->area_type & MMC_BLK_DATA_AREA_BOOT) && - card->ext_csd.boot_ro_lockable) { - umode_t mode; - - if (card->ext_csd.boot_ro_lock & EXT_CSD_BOOT_WP_B_PWR_WP_DIS) - mode = S_IRUGO; - else - mode = S_IRUGO | S_IWUSR; - - md->power_ro_lock.show = power_ro_lock_show; - md->power_ro_lock.store = power_ro_lock_store; - sysfs_attr_init(&md->power_ro_lock.attr); - md->power_ro_lock.attr.mode = mode; - md->power_ro_lock.attr.name = - "ro_lock_until_next_power_on"; - ret = device_create_file(disk_to_dev(md->disk), - &md->power_ro_lock); - if (ret) - goto power_ro_lock_fail; - } - return ret; - -power_ro_lock_fail: - device_remove_file(disk_to_dev(md->disk), &md->force_ro); -force_ro_fail: - del_gendisk(md->disk); - - return ret; -} - #ifdef CONFIG_DEBUG_FS static int mmc_dbg_card_status_get(void *data, u64 *val) @@ -2889,7 +2895,7 @@ static void mmc_blk_remove_debugfs(struct mmc_card *card, static int mmc_blk_probe(struct mmc_card *card) { - struct mmc_blk_data *md, *part_md; + struct mmc_blk_data *md; int ret = 0; /* @@ -2917,18 +2923,6 @@ static int mmc_blk_probe(struct mmc_card *card) if (ret) goto out; - dev_set_drvdata(&card->dev, md); - - ret = mmc_add_disk(md); - if (ret) - goto out; - - list_for_each_entry(part_md, &md->part, part) { - ret = mmc_add_disk(part_md); - if (ret) - goto out; - } - /* Add two debugfs entries */ mmc_blk_add_debugfs(card, md); diff --git a/drivers/mmc/core/core.c b/drivers/mmc/core/core.c index 95fedcf56e4a..605f5e8648c1 100644 --- a/drivers/mmc/core/core.c +++ b/drivers/mmc/core/core.c @@ -2149,6 +2149,41 @@ int mmc_detect_card_removed(struct mmc_host *host) } EXPORT_SYMBOL(mmc_detect_card_removed); +int mmc_card_alternative_gpt_sector(struct mmc_card *card, sector_t *gpt_sector) +{ + unsigned int boot_sectors_num; + + if ((!(card->host->caps2 & MMC_CAP2_ALT_GPT_TEGRA))) + return -EOPNOTSUPP; + + /* filter out unrelated cards */ + if (card->ext_csd.rev < 3 || + !mmc_card_mmc(card) || + !mmc_card_is_blockaddr(card) || + mmc_card_is_removable(card->host)) + return -ENOENT; + + /* + * eMMC storage has two special boot partitions in addition to the + * main one. NVIDIA's bootloader linearizes eMMC boot0->boot1->main + * accesses, this means that the partition table addresses are shifted + * by the size of boot partitions. In accordance with the eMMC + * specification, the boot partition size is calculated as follows: + * + * boot partition size = 128K byte x BOOT_SIZE_MULT + * + * Calculate number of sectors occupied by the both boot partitions. + */ + boot_sectors_num = card->ext_csd.raw_boot_mult * SZ_128K / + SZ_512 * MMC_NUM_BOOT_PARTITION; + + /* Defined by NVIDIA and used by Android devices. */ + *gpt_sector = card->ext_csd.sectors - boot_sectors_num - 1; + + return 0; +} +EXPORT_SYMBOL(mmc_card_alternative_gpt_sector); + void mmc_rescan(struct work_struct *work) { struct mmc_host *host = diff --git a/drivers/mmc/core/core.h b/drivers/mmc/core/core.h index 0c4de2030b3f..7931a4f0137d 100644 --- a/drivers/mmc/core/core.h +++ b/drivers/mmc/core/core.h @@ -119,6 +119,8 @@ void mmc_release_host(struct mmc_host *host); void mmc_get_card(struct mmc_card *card, struct mmc_ctx *ctx); void mmc_put_card(struct mmc_card *card, struct mmc_ctx *ctx); +int mmc_card_alternative_gpt_sector(struct mmc_card *card, sector_t *sector); + /** * mmc_claim_host - exclusively claim a host * @host: mmc host to claim diff --git a/drivers/mmc/core/mmc.c b/drivers/mmc/core/mmc.c index 838726b68ff3..29e58ffae379 100644 --- a/drivers/mmc/core/mmc.c +++ b/drivers/mmc/core/mmc.c @@ -418,6 +418,8 @@ static int mmc_decode_ext_csd(struct mmc_card *card, u8 *ext_csd) ext_csd[EXT_CSD_ERASE_TIMEOUT_MULT]; card->ext_csd.raw_hc_erase_grp_size = ext_csd[EXT_CSD_HC_ERASE_GRP_SIZE]; + card->ext_csd.raw_boot_mult = + ext_csd[EXT_CSD_BOOT_MULT]; if (card->ext_csd.rev >= 3) { u8 sa_shift = ext_csd[EXT_CSD_S_A_TIMEOUT]; card->ext_csd.part_config = ext_csd[EXT_CSD_PART_CONFIG]; diff --git a/drivers/mmc/host/sdhci-tegra.c b/drivers/mmc/host/sdhci-tegra.c index 387ce9cdbd7c..a5001875876b 100644 --- a/drivers/mmc/host/sdhci-tegra.c +++ b/drivers/mmc/host/sdhci-tegra.c @@ -116,6 +116,8 @@ */ #define NVQUIRK_HAS_TMCLK BIT(10) +#define NVQUIRK_HAS_ANDROID_GPT_SECTOR BIT(11) + /* SDMMC CQE Base Address for Tegra Host Ver 4.1 and Higher */ #define SDHCI_TEGRA_CQE_BASE_ADDR 0xF000 @@ -1361,6 +1363,7 @@ static const struct sdhci_tegra_soc_data soc_data_tegra20 = { .pdata = &sdhci_tegra20_pdata, .dma_mask = DMA_BIT_MASK(32), .nvquirks = NVQUIRK_FORCE_SDHCI_SPEC_200 | + NVQUIRK_HAS_ANDROID_GPT_SECTOR | NVQUIRK_ENABLE_BLOCK_GAP_DET, }; @@ -1390,6 +1393,7 @@ static const struct sdhci_tegra_soc_data soc_data_tegra30 = { .nvquirks = NVQUIRK_ENABLE_SDHCI_SPEC_300 | NVQUIRK_ENABLE_SDR50 | NVQUIRK_ENABLE_SDR104 | + NVQUIRK_HAS_ANDROID_GPT_SECTOR | NVQUIRK_HAS_PADCALIB, }; @@ -1422,6 +1426,7 @@ static const struct sdhci_pltfm_data sdhci_tegra114_pdata = { static const struct sdhci_tegra_soc_data soc_data_tegra114 = { .pdata = &sdhci_tegra114_pdata, .dma_mask = DMA_BIT_MASK(32), + .nvquirks = NVQUIRK_HAS_ANDROID_GPT_SECTOR, }; static const struct sdhci_pltfm_data sdhci_tegra124_pdata = { @@ -1438,6 +1443,7 @@ static const struct sdhci_pltfm_data sdhci_tegra124_pdata = { static const struct sdhci_tegra_soc_data soc_data_tegra124 = { .pdata = &sdhci_tegra124_pdata, .dma_mask = DMA_BIT_MASK(34), + .nvquirks = NVQUIRK_HAS_ANDROID_GPT_SECTOR, }; static const struct sdhci_ops tegra210_sdhci_ops = { @@ -1616,6 +1622,9 @@ static int sdhci_tegra_probe(struct platform_device *pdev) tegra_host->pad_control_available = false; tegra_host->soc_data = soc_data; + if (soc_data->nvquirks & NVQUIRK_HAS_ANDROID_GPT_SECTOR) + host->mmc->caps2 |= MMC_CAP2_ALT_GPT_TEGRA; + if (soc_data->nvquirks & NVQUIRK_NEEDS_PAD_CONTROL) { rc = tegra_sdhci_init_pinctrl_info(&pdev->dev, tegra_host); if (rc == 0) diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index dfd9dec0c1f6..68acd33c3856 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -968,12 +968,11 @@ void nvme_cleanup_cmd(struct request *req) { if (req->rq_flags & RQF_SPECIAL_PAYLOAD) { struct nvme_ctrl *ctrl = nvme_req(req)->ctrl; - struct page *page = req->special_vec.bv_page; - if (page == ctrl->discard_page) + if (req->special_vec.bv_page == ctrl->discard_page) clear_bit_unlock(0, &ctrl->discard_page_busy); else - kfree(page_address(page) + req->special_vec.bv_offset); + kfree(bvec_virt(&req->special_vec)); } } EXPORT_SYMBOL_GPL(nvme_cleanup_cmd); @@ -1822,7 +1821,7 @@ static void nvme_update_disk_info(struct gendisk *disk, static inline bool nvme_first_scan(struct gendisk *disk) { /* nvme_alloc_ns() scans the disk prior to adding it */ - return !(disk->flags & GENHD_FL_UP); + return !disk_live(disk); } static void nvme_set_chunk_sectors(struct nvme_ns *ns, struct nvme_id_ns *id) @@ -1890,7 +1889,7 @@ static int nvme_update_ns_info(struct nvme_ns *ns, struct nvme_id_ns *id) nvme_update_disk_info(ns->head->disk, ns, id); blk_stack_limits(&ns->head->disk->queue->limits, &ns->queue->limits, 0); - blk_queue_update_readahead(ns->head->disk->queue); + disk_update_readahead(ns->head->disk); blk_mq_unfreeze_queue(ns->head->disk->queue); } return 0; @@ -3729,9 +3728,14 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid, if (!ns) goto out_free_id; - ns->queue = blk_mq_init_queue(ctrl->tagset); - if (IS_ERR(ns->queue)) + disk = blk_mq_alloc_disk(ctrl->tagset, ns); + if (IS_ERR(disk)) goto out_free_ns; + disk->fops = &nvme_bdev_ops; + disk->private_data = ns; + + ns->disk = disk; + ns->queue = disk->queue; if (ctrl->opts && ctrl->opts->data_digest) blk_queue_flag_set(QUEUE_FLAG_STABLE_WRITES, ns->queue); @@ -3740,20 +3744,12 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid, if (ctrl->ops->flags & NVME_F_PCI_P2PDMA) blk_queue_flag_set(QUEUE_FLAG_PCI_P2PDMA, ns->queue); - ns->queue->queuedata = ns; ns->ctrl = ctrl; kref_init(&ns->kref); if (nvme_init_ns_head(ns, nsid, ids, id->nmic & NVME_NS_NMIC_SHARED)) - goto out_free_queue; + goto out_cleanup_disk; - disk = alloc_disk_node(0, node); - if (!disk) - goto out_unlink_ns; - - disk->fops = &nvme_bdev_ops; - disk->private_data = ns; - disk->queue = ns->queue; /* * Without the multipath code enabled, multiple controller per * subsystems are visible as devices and thus we cannot use the @@ -3762,15 +3758,14 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid, if (!nvme_mpath_set_disk_name(ns, disk->disk_name, &disk->flags)) sprintf(disk->disk_name, "nvme%dn%d", ctrl->instance, ns->head->instance); - ns->disk = disk; if (nvme_update_ns_info(ns, id)) - goto out_put_disk; + goto out_unlink_ns; if ((ctrl->quirks & NVME_QUIRK_LIGHTNVM) && id->vs[0] == 0x1) { if (nvme_nvm_register(ns, disk->disk_name, node)) { dev_warn(ctrl->device, "LightNVM init failure\n"); - goto out_put_disk; + goto out_unlink_ns; } } @@ -3789,10 +3784,7 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid, kfree(id); return; - out_put_disk: - /* prevent double queue cleanup */ - ns->disk->queue = NULL; - put_disk(ns->disk); + out_unlink_ns: mutex_lock(&ctrl->subsys->lock); list_del_rcu(&ns->siblings); @@ -3800,8 +3792,8 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid, list_del_init(&ns->head->entry); mutex_unlock(&ctrl->subsys->lock); nvme_put_ns_head(ns->head); - out_free_queue: - blk_cleanup_queue(ns->queue); + out_cleanup_disk: + blk_cleanup_disk(disk); out_free_ns: kfree(ns); out_free_id: @@ -3826,14 +3818,12 @@ static void nvme_ns_remove(struct nvme_ns *ns) nvme_mpath_clear_current_path(ns); synchronize_srcu(&ns->head->srcu); /* wait for concurrent submissions */ - if (ns->disk->flags & GENHD_FL_UP) { - if (!nvme_ns_head_multipath(ns->head)) - nvme_cdev_del(&ns->cdev, &ns->cdev_device); - del_gendisk(ns->disk); - blk_cleanup_queue(ns->queue); - if (blk_get_integrity(ns->disk)) - blk_integrity_unregister(ns->disk); - } + if (!nvme_ns_head_multipath(ns->head)) + nvme_cdev_del(&ns->cdev, &ns->cdev_device); + del_gendisk(ns->disk); + blk_cleanup_queue(ns->queue); + if (blk_get_integrity(ns->disk)) + blk_integrity_unregister(ns->disk); down_write(&ns->ctrl->namespaces_rwsem); list_del_init(&ns->list); diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c index 3f32c5e86bfc..37ce3e8b1db2 100644 --- a/drivers/nvme/host/multipath.c +++ b/drivers/nvme/host/multipath.c @@ -765,7 +765,7 @@ void nvme_mpath_shutdown_disk(struct nvme_ns_head *head) if (!head->disk) return; kblockd_schedule_work(&head->requeue_work); - if (head->disk->flags & GENHD_FL_UP) { + if (test_bit(NVME_NSHEAD_DISK_LIVE, &head->flags)) { nvme_cdev_del(&head->cdev, &head->cdev_device); del_gendisk(head->disk); } diff --git a/drivers/s390/block/dasd_diag.c b/drivers/s390/block/dasd_diag.c index 6bb775236c16..db5987281010 100644 --- a/drivers/s390/block/dasd_diag.c +++ b/drivers/s390/block/dasd_diag.c @@ -552,7 +552,7 @@ static struct dasd_ccw_req *dasd_diag_build_cp(struct dasd_device *memdev, dbio = dreq->bio; recid = first_rec; rq_for_each_segment(bv, req, iter) { - dst = page_address(bv.bv_page) + bv.bv_offset; + dst = bvec_virt(&bv); for (off = 0; off < bv.bv_len; off += blksize) { memset(dbio, 0, sizeof (struct dasd_diag_bio)); dbio->type = rw_cmd; diff --git a/drivers/s390/block/dasd_eckd.c b/drivers/s390/block/dasd_eckd.c index fb5d8152652d..460e0f1cca53 100644 --- a/drivers/s390/block/dasd_eckd.c +++ b/drivers/s390/block/dasd_eckd.c @@ -3276,7 +3276,7 @@ static int dasd_eckd_ese_read(struct dasd_ccw_req *cqr, struct irb *irb) end_blk = (curr_trk + 1) * recs_per_trk; rq_for_each_segment(bv, req, iter) { - dst = page_address(bv.bv_page) + bv.bv_offset; + dst = bvec_virt(&bv); for (off = 0; off < bv.bv_len; off += blksize) { if (first_blk + blk_count >= end_blk) { cqr->proc_bytes = blk_count * blksize; @@ -4008,7 +4008,7 @@ static struct dasd_ccw_req *dasd_eckd_build_cp_cmd_single( last_rec - recid + 1, cmd, basedev, blksize); } rq_for_each_segment(bv, req, iter) { - dst = page_address(bv.bv_page) + bv.bv_offset; + dst = bvec_virt(&bv); if (dasd_page_cache) { char *copy = kmem_cache_alloc(dasd_page_cache, GFP_DMA | __GFP_NOWARN); @@ -4175,7 +4175,7 @@ static struct dasd_ccw_req *dasd_eckd_build_cp_cmd_track( idaw_dst = NULL; idaw_len = 0; rq_for_each_segment(bv, req, iter) { - dst = page_address(bv.bv_page) + bv.bv_offset; + dst = bvec_virt(&bv); seg_len = bv.bv_len; while (seg_len) { if (new_track) { @@ -4518,7 +4518,7 @@ static struct dasd_ccw_req *dasd_eckd_build_cp_tpm_track( new_track = 1; recid = first_rec; rq_for_each_segment(bv, req, iter) { - dst = page_address(bv.bv_page) + bv.bv_offset; + dst = bvec_virt(&bv); seg_len = bv.bv_len; while (seg_len) { if (new_track) { @@ -4551,7 +4551,7 @@ static struct dasd_ccw_req *dasd_eckd_build_cp_tpm_track( } } else { rq_for_each_segment(bv, req, iter) { - dst = page_address(bv.bv_page) + bv.bv_offset; + dst = bvec_virt(&bv); last_tidaw = itcw_add_tidaw(itcw, 0x00, dst, bv.bv_len); if (IS_ERR(last_tidaw)) { @@ -4787,7 +4787,7 @@ static struct dasd_ccw_req *dasd_eckd_build_cp_raw(struct dasd_device *startdev, idaws = idal_create_words(idaws, rawpadpage, PAGE_SIZE); } rq_for_each_segment(bv, req, iter) { - dst = page_address(bv.bv_page) + bv.bv_offset; + dst = bvec_virt(&bv); seg_len = bv.bv_len; if (cmd == DASD_ECKD_CCW_READ_TRACK) memset(dst, 0, seg_len); @@ -4848,7 +4848,7 @@ dasd_eckd_free_cp(struct dasd_ccw_req *cqr, struct request *req) if (private->uses_cdl == 0 || recid > 2*blk_per_trk) ccw++; rq_for_each_segment(bv, req, iter) { - dst = page_address(bv.bv_page) + bv.bv_offset; + dst = bvec_virt(&bv); for (off = 0; off < bv.bv_len; off += blksize) { /* Skip locate record. */ if (private->uses_cdl && recid <= 2*blk_per_trk) diff --git a/drivers/s390/block/dasd_fba.c b/drivers/s390/block/dasd_fba.c index 3ad319aee51e..e084f4dedddd 100644 --- a/drivers/s390/block/dasd_fba.c +++ b/drivers/s390/block/dasd_fba.c @@ -501,7 +501,7 @@ static struct dasd_ccw_req *dasd_fba_build_cp_regular( } recid = first_rec; rq_for_each_segment(bv, req, iter) { - dst = page_address(bv.bv_page) + bv.bv_offset; + dst = bvec_virt(&bv); if (dasd_page_cache) { char *copy = kmem_cache_alloc(dasd_page_cache, GFP_DMA | __GFP_NOWARN); @@ -583,7 +583,7 @@ dasd_fba_free_cp(struct dasd_ccw_req *cqr, struct request *req) if (private->rdc_data.mode.bits.data_chain != 0) ccw++; rq_for_each_segment(bv, req, iter) { - dst = page_address(bv.bv_page) + bv.bv_offset; + dst = bvec_virt(&bv); for (off = 0; off < bv.bv_len; off += blksize) { /* Skip locate record. */ if (private->rdc_data.mode.bits.data_chain == 0) diff --git a/drivers/s390/block/dasd_genhd.c b/drivers/s390/block/dasd_genhd.c index 493e8469893c..fa966e0db6ca 100644 --- a/drivers/s390/block/dasd_genhd.c +++ b/drivers/s390/block/dasd_genhd.c @@ -24,6 +24,8 @@ #include "dasd_int.h" +static struct lock_class_key dasd_bio_compl_lkclass; + /* * Allocate and register gendisk structure for device. */ @@ -38,13 +40,15 @@ int dasd_gendisk_alloc(struct dasd_block *block) if (base->devindex >= DASD_PER_MAJOR) return -EBUSY; - gdp = alloc_disk(1 << DASD_PARTN_BITS); + gdp = __alloc_disk_node(block->request_queue, NUMA_NO_NODE, + &dasd_bio_compl_lkclass); if (!gdp) return -ENOMEM; /* Initialize gendisk structure. */ gdp->major = DASD_MAJOR; gdp->first_minor = base->devindex << DASD_PARTN_BITS; + gdp->minors = 1 << DASD_PARTN_BITS; gdp->fops = &dasd_device_operations; /* @@ -73,7 +77,6 @@ int dasd_gendisk_alloc(struct dasd_block *block) test_bit(DASD_FLAG_DEVICE_RO, &base->flags)) set_disk_ro(gdp, 1); dasd_add_link_to_gendisk(gdp, base); - gdp->queue = block->request_queue; block->gdp = gdp; set_capacity(block->gdp, 0); device_add_disk(&base->cdev->dev, block->gdp, NULL); diff --git a/drivers/s390/block/dcssblk.c b/drivers/s390/block/dcssblk.c index 29180bdf0977..5be3d1c39a78 100644 --- a/drivers/s390/block/dcssblk.c +++ b/drivers/s390/block/dcssblk.c @@ -892,8 +892,7 @@ dcssblk_submit_bio(struct bio *bio) index = (bio->bi_iter.bi_sector >> 3); bio_for_each_segment(bvec, bio, iter) { - page_addr = (unsigned long) - page_address(bvec.bv_page) + bvec.bv_offset; + page_addr = (unsigned long)bvec_virt(&bvec); source_addr = dev_info->start + (index<<12) + bytes_done; if (unlikely((page_addr & 4095) != 0) || (bvec.bv_len & 4095) != 0) // More paranoia. diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c index b8d55af763f9..610ebba0d66e 100644 --- a/drivers/scsi/sd.c +++ b/drivers/scsi/sd.c @@ -129,6 +129,7 @@ static DEFINE_MUTEX(sd_ref_mutex); static struct kmem_cache *sd_cdb_cache; static mempool_t *sd_cdb_pool; static mempool_t *sd_page_pool; +static struct lock_class_key sd_bio_compl_lkclass; static const char *sd_cache_types[] = { "write through", "none", "write back", @@ -886,7 +887,7 @@ static blk_status_t sd_setup_unmap_cmnd(struct scsi_cmnd *cmd) cmd->cmnd[0] = UNMAP; cmd->cmnd[8] = 24; - buf = page_address(rq->special_vec.bv_page); + 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]); @@ -3408,7 +3409,8 @@ static int sd_probe(struct device *dev) if (!sdkp) goto out; - gd = alloc_disk(SD_MINORS); + gd = __alloc_disk_node(sdp->request_queue, NUMA_NO_NODE, + &sd_bio_compl_lkclass); if (!gd) goto out_free; @@ -3454,10 +3456,10 @@ static int sd_probe(struct device *dev) gd->major = sd_major((index & 0xf0) >> 4); gd->first_minor = ((index & 0xf) << 4) | (index & 0xfff00); + gd->minors = SD_MINORS; gd->fops = &sd_fops; gd->private_data = &sdkp->driver; - gd->queue = sdkp->device->request_queue; /* defaults, until the device tells us otherwise */ sdp->sector_size = 512; diff --git a/drivers/scsi/sg.c b/drivers/scsi/sg.c index 91e2221bbb0d..d5889b4f0fd4 100644 --- a/drivers/scsi/sg.c +++ b/drivers/scsi/sg.c @@ -166,7 +166,7 @@ typedef struct sg_device { /* holds the state of each scsi generic device */ bool exclude; /* 1->open(O_EXCL) succeeded and is active */ int open_cnt; /* count of opens (perhaps < num(sfds) ) */ char sgdebug; /* 0->off, 1->sense, 9->dump dev, 10-> all devs */ - struct gendisk *disk; + char name[DISK_NAME_LEN]; struct cdev * cdev; /* char_dev [sysfs: /sys/cdev/major/sg<n>] */ struct kref d_ref; } Sg_device; @@ -202,8 +202,7 @@ static void sg_device_destroy(struct kref *kref); #define SZ_SG_REQ_INFO sizeof(sg_req_info_t) #define sg_printk(prefix, sdp, fmt, a...) \ - sdev_prefix_printk(prefix, (sdp)->device, \ - (sdp)->disk->disk_name, fmt, ##a) + sdev_prefix_printk(prefix, (sdp)->device, (sdp)->name, fmt, ##a) /* * The SCSI interfaces that use read() and write() as an asynchronous variant of @@ -832,7 +831,7 @@ sg_common_write(Sg_fd * sfp, Sg_request * srp, srp->rq->timeout = timeout; kref_get(&sfp->f_ref); /* sg_rq_end_io() does kref_put(). */ - blk_execute_rq_nowait(sdp->disk, srp->rq, at_head, sg_rq_end_io); + blk_execute_rq_nowait(NULL, srp->rq, at_head, sg_rq_end_io); return 0; } @@ -1119,8 +1118,7 @@ sg_ioctl_common(struct file *filp, Sg_device *sdp, Sg_fd *sfp, return put_user(max_sectors_bytes(sdp->device->request_queue), ip); case BLKTRACESETUP: - return blk_trace_setup(sdp->device->request_queue, - sdp->disk->disk_name, + return blk_trace_setup(sdp->device->request_queue, sdp->name, MKDEV(SCSI_GENERIC_MAJOR, sdp->index), NULL, p); case BLKTRACESTART: @@ -1456,7 +1454,7 @@ static struct class *sg_sysfs_class; static int sg_sysfs_valid = 0; static Sg_device * -sg_alloc(struct gendisk *disk, struct scsi_device *scsidp) +sg_alloc(struct scsi_device *scsidp) { struct request_queue *q = scsidp->request_queue; Sg_device *sdp; @@ -1492,9 +1490,7 @@ sg_alloc(struct gendisk *disk, struct scsi_device *scsidp) SCSI_LOG_TIMEOUT(3, sdev_printk(KERN_INFO, scsidp, "sg_alloc: dev=%d \n", k)); - sprintf(disk->disk_name, "sg%d", k); - disk->first_minor = k; - sdp->disk = disk; + sprintf(sdp->name, "sg%d", k); sdp->device = scsidp; mutex_init(&sdp->open_rel_lock); INIT_LIST_HEAD(&sdp->sfds); @@ -1521,19 +1517,11 @@ static int sg_add_device(struct device *cl_dev, struct class_interface *cl_intf) { struct scsi_device *scsidp = to_scsi_device(cl_dev->parent); - struct gendisk *disk; Sg_device *sdp = NULL; struct cdev * cdev = NULL; int error; unsigned long iflags; - disk = alloc_disk(1); - if (!disk) { - pr_warn("%s: alloc_disk failed\n", __func__); - return -ENOMEM; - } - disk->major = SCSI_GENERIC_MAJOR; - error = -ENOMEM; cdev = cdev_alloc(); if (!cdev) { @@ -1543,7 +1531,7 @@ sg_add_device(struct device *cl_dev, struct class_interface *cl_intf) cdev->owner = THIS_MODULE; cdev->ops = &sg_fops; - sdp = sg_alloc(disk, scsidp); + sdp = sg_alloc(scsidp); if (IS_ERR(sdp)) { pr_warn("%s: sg_alloc failed\n", __func__); error = PTR_ERR(sdp); @@ -1561,7 +1549,7 @@ sg_add_device(struct device *cl_dev, struct class_interface *cl_intf) sg_class_member = device_create(sg_sysfs_class, cl_dev->parent, MKDEV(SCSI_GENERIC_MAJOR, sdp->index), - sdp, "%s", disk->disk_name); + sdp, "%s", sdp->name); if (IS_ERR(sg_class_member)) { pr_err("%s: device_create failed\n", __func__); error = PTR_ERR(sg_class_member); @@ -1589,7 +1577,6 @@ cdev_add_err: kfree(sdp); out: - put_disk(disk); if (cdev) cdev_del(cdev); return error; @@ -1613,7 +1600,6 @@ sg_device_destroy(struct kref *kref) SCSI_LOG_TIMEOUT(3, sg_printk(KERN_INFO, sdp, "sg_device_destroy\n")); - put_disk(sdp->disk); kfree(sdp); } @@ -2606,7 +2592,7 @@ static int sg_proc_seq_show_debug(struct seq_file *s, void *v) goto skip; read_lock(&sdp->sfd_lock); if (!list_empty(&sdp->sfds)) { - seq_printf(s, " >>> device=%s ", sdp->disk->disk_name); + seq_printf(s, " >>> device=%s ", sdp->name); if (atomic_read(&sdp->detaching)) seq_puts(s, "detaching pending close "); else if (sdp->device) { diff --git a/drivers/scsi/sr.c b/drivers/scsi/sr.c index a6d3ac0a6cbc..2942a4ec9bdd 100644 --- a/drivers/scsi/sr.c +++ b/drivers/scsi/sr.c @@ -106,6 +106,8 @@ static struct scsi_driver sr_template = { static unsigned long sr_index_bits[SR_DISKS / BITS_PER_LONG]; static DEFINE_SPINLOCK(sr_index_lock); +static struct lock_class_key sr_bio_compl_lkclass; + /* This semaphore is used to mediate the 0->1 reference get in the * face of object destruction (i.e. we can't allow a get on an * object after last put) */ @@ -712,7 +714,8 @@ static int sr_probe(struct device *dev) kref_init(&cd->kref); - disk = alloc_disk(1); + disk = __alloc_disk_node(sdev->request_queue, NUMA_NO_NODE, + &sr_bio_compl_lkclass); if (!disk) goto fail_free; mutex_init(&cd->lock); @@ -729,6 +732,7 @@ static int sr_probe(struct device *dev) disk->major = SCSI_CDROM_MAJOR; disk->first_minor = minor; + disk->minors = 1; sprintf(disk->disk_name, "sr%d", minor); disk->fops = &sr_bdops; disk->flags = GENHD_FL_CD | GENHD_FL_BLOCK_EVENTS_ON_EXCL_WRITE; @@ -762,7 +766,6 @@ static int sr_probe(struct device *dev) set_capacity(disk, cd->capacity); disk->private_data = &cd->driver; - disk->queue = sdev->request_queue; if (register_cdrom(disk, &cd->cdi)) goto fail_minor; diff --git a/drivers/scsi/st.c b/drivers/scsi/st.c index c6f14540ae03..d1abc020f3c0 100644 --- a/drivers/scsi/st.c +++ b/drivers/scsi/st.c @@ -309,13 +309,8 @@ static char * st_incompatible(struct scsi_device* SDp) } -static inline char *tape_name(struct scsi_tape *tape) -{ - return tape->disk->disk_name; -} - #define st_printk(prefix, t, fmt, a...) \ - sdev_prefix_printk(prefix, (t)->device, tape_name(t), fmt, ##a) + sdev_prefix_printk(prefix, (t)->device, (t)->name, fmt, ##a) #ifdef DEBUG #define DEBC_printk(t, fmt, a...) \ if (debugging) { st_printk(ST_DEB_MSG, t, fmt, ##a ); } @@ -363,7 +358,7 @@ static int st_chk_result(struct scsi_tape *STp, struct st_request * SRpnt) int result = SRpnt->result; u8 scode; DEB(const char *stp;) - char *name = tape_name(STp); + char *name = STp->name; struct st_cmdstatus *cmdstatp; if (!result) @@ -3841,8 +3836,9 @@ static long st_ioctl_common(struct file *file, unsigned int cmd_in, void __user !capable(CAP_SYS_RAWIO)) i = -EPERM; else - i = scsi_cmd_ioctl(STp->disk->queue, STp->disk, - file->f_mode, cmd_in, p); + i = scsi_cmd_ioctl(STp->device->request_queue, + NULL, file->f_mode, cmd_in, + p); if (i != -ENOTTY) return i; break; @@ -4216,7 +4212,7 @@ static int create_one_cdev(struct scsi_tape *tape, int mode, int rew) i = mode << (4 - ST_NBR_MODE_BITS); snprintf(name, 10, "%s%s%s", rew ? "n" : "", - tape->disk->disk_name, st_formats[i]); + tape->name, st_formats[i]); dev = device_create(&st_sysfs_class, &tape->device->sdev_gendev, cdev_devno, &tape->modes[mode], "%s", name); @@ -4271,7 +4267,6 @@ static void remove_cdevs(struct scsi_tape *tape) static int st_probe(struct device *dev) { struct scsi_device *SDp = to_scsi_device(dev); - struct gendisk *disk = NULL; struct scsi_tape *tpnt = NULL; struct st_modedef *STm; struct st_partstat *STps; @@ -4301,27 +4296,13 @@ static int st_probe(struct device *dev) goto out; } - disk = alloc_disk(1); - if (!disk) { - sdev_printk(KERN_ERR, SDp, - "st: out of memory. Device not attached.\n"); - goto out_buffer_free; - } - tpnt = kzalloc(sizeof(struct scsi_tape), GFP_KERNEL); if (tpnt == NULL) { sdev_printk(KERN_ERR, SDp, "st: Can't allocate device descriptor.\n"); - goto out_put_disk; + goto out_buffer_free; } kref_init(&tpnt->kref); - tpnt->disk = disk; - disk->private_data = &tpnt->driver; - /* SCSI tape doesn't register this gendisk via add_disk(). Manually - * take queue reference that release_disk() expects. */ - if (!blk_get_queue(SDp->request_queue)) - goto out_put_disk; - disk->queue = SDp->request_queue; tpnt->driver = &st_template; tpnt->device = SDp; @@ -4394,10 +4375,10 @@ static int st_probe(struct device *dev) idr_preload_end(); if (error < 0) { pr_warn("st: idr allocation failed: %d\n", error); - goto out_put_queue; + goto out_free_tape; } tpnt->index = error; - sprintf(disk->disk_name, "st%d", tpnt->index); + sprintf(tpnt->name, "st%d", tpnt->index); tpnt->stats = kzalloc(sizeof(struct scsi_tape_stats), GFP_KERNEL); if (tpnt->stats == NULL) { sdev_printk(KERN_ERR, SDp, @@ -4414,9 +4395,9 @@ static int st_probe(struct device *dev) scsi_autopm_put_device(SDp); sdev_printk(KERN_NOTICE, SDp, - "Attached scsi tape %s\n", tape_name(tpnt)); + "Attached scsi tape %s\n", tpnt->name); sdev_printk(KERN_INFO, SDp, "%s: try direct i/o: %s (alignment %d B)\n", - tape_name(tpnt), tpnt->try_dio ? "yes" : "no", + tpnt->name, tpnt->try_dio ? "yes" : "no", queue_dma_alignment(SDp->request_queue) + 1); return 0; @@ -4428,10 +4409,7 @@ out_idr_remove: spin_lock(&st_index_lock); idr_remove(&st_index_idr, tpnt->index); spin_unlock(&st_index_lock); -out_put_queue: - blk_put_queue(disk->queue); -out_put_disk: - put_disk(disk); +out_free_tape: kfree(tpnt); out_buffer_free: kfree(buffer); @@ -4470,7 +4448,6 @@ static int st_remove(struct device *dev) static void scsi_tape_release(struct kref *kref) { struct scsi_tape *tpnt = to_scsi_tape(kref); - struct gendisk *disk = tpnt->disk; tpnt->device = NULL; @@ -4480,8 +4457,6 @@ static void scsi_tape_release(struct kref *kref) kfree(tpnt->buffer); } - disk->private_data = NULL; - put_disk(disk); kfree(tpnt->stats); kfree(tpnt); return; diff --git a/drivers/scsi/st.h b/drivers/scsi/st.h index 9d3c38bb0794..c0ef0d9aaf8a 100644 --- a/drivers/scsi/st.h +++ b/drivers/scsi/st.h @@ -187,7 +187,7 @@ struct scsi_tape { unsigned char last_cmnd[6]; unsigned char last_sense[16]; #endif - struct gendisk *disk; + char name[DISK_NAME_LEN]; struct kref kref; struct scsi_tape_stats *stats; }; diff --git a/fs/block_dev.c b/fs/block_dev.c index 9ef4f1fc2cb0..1f21ac984253 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -35,6 +35,7 @@ #include <linux/uaccess.h> #include <linux/suspend.h> #include "internal.h" +#include "../block/blk.h" struct bdev_inode { struct block_device bdev; @@ -686,7 +687,8 @@ static loff_t block_llseek(struct file *file, loff_t offset, int whence) return retval; } -int blkdev_fsync(struct file *filp, loff_t start, loff_t end, int datasync) +static int blkdev_fsync(struct file *filp, loff_t start, loff_t end, + int datasync) { struct inode *bd_inode = bdev_file_inode(filp); struct block_device *bdev = I_BDEV(bd_inode); @@ -707,7 +709,6 @@ int blkdev_fsync(struct file *filp, loff_t start, loff_t end, int datasync) return error; } -EXPORT_SYMBOL(blkdev_fsync); /** * bdev_read_page() - Start reading a page from a block device @@ -801,7 +802,6 @@ static struct inode *bdev_alloc_inode(struct super_block *sb) if (!ei) return NULL; memset(&ei->bdev, 0, sizeof(ei->bdev)); - ei->bdev.bd_bdi = &noop_backing_dev_info; return &ei->vfs_inode; } @@ -812,8 +812,15 @@ static void bdev_free_inode(struct inode *inode) free_percpu(bdev->bd_stats); kfree(bdev->bd_meta_info); - if (!bdev_is_partition(bdev)) + if (!bdev_is_partition(bdev)) { + if (bdev->bd_disk && bdev->bd_disk->bdi) + bdi_put(bdev->bd_disk->bdi); kfree(bdev->bd_disk); + } + + if (MAJOR(bdev->bd_dev) == BLOCK_EXT_MAJOR) + blk_free_ext_minor(MINOR(bdev->bd_dev)); + kmem_cache_free(bdev_cachep, BDEV_I(inode)); } @@ -826,16 +833,9 @@ static void init_once(void *data) static void bdev_evict_inode(struct inode *inode) { - struct block_device *bdev = &BDEV_I(inode)->bdev; truncate_inode_pages_final(&inode->i_data); invalidate_inode_buffers(inode); /* is it needed here? */ clear_inode(inode); - /* Detach inode from wb early as bdi_put() may free bdi->wb */ - inode_detach_wb(inode); - if (bdev->bd_bdi != &noop_backing_dev_info) { - bdi_put(bdev->bd_bdi); - bdev->bd_bdi = &noop_backing_dev_info; - } } static const struct super_operations bdev_sops = { @@ -902,9 +902,6 @@ struct block_device *bdev_alloc(struct gendisk *disk, u8 partno) bdev->bd_disk = disk; bdev->bd_partno = partno; bdev->bd_inode = inode; -#ifdef CONFIG_SYSFS - INIT_LIST_HEAD(&bdev->bd_holder_disks); -#endif bdev->bd_stats = alloc_percpu(struct disk_stats); if (!bdev->bd_stats) { iput(inode); @@ -921,31 +918,6 @@ void bdev_add(struct block_device *bdev, dev_t dev) insert_inode_hash(bdev->bd_inode); } -static struct block_device *bdget(dev_t dev) -{ - struct inode *inode; - - inode = ilookup(blockdev_superblock, dev); - if (!inode) - return NULL; - return &BDEV_I(inode)->bdev; -} - -/** - * bdgrab -- Grab a reference to an already referenced block device - * @bdev: Block device to grab a reference to. - * - * Returns the block_device with an additional reference when successful, - * or NULL if the inode is already beeing freed. - */ -struct block_device *bdgrab(struct block_device *bdev) -{ - if (!igrab(bdev->bd_inode)) - return NULL; - return bdev; -} -EXPORT_SYMBOL(bdgrab); - long nr_blockdev_pages(void) { struct inode *inode; @@ -959,12 +931,6 @@ long nr_blockdev_pages(void) return ret; } -void bdput(struct block_device *bdev) -{ - iput(bdev->bd_inode); -} -EXPORT_SYMBOL(bdput); - /** * bd_may_claim - test whether a block device can be claimed * @bdev: block device of interest @@ -1094,148 +1060,6 @@ void bd_abort_claiming(struct block_device *bdev, void *holder) } EXPORT_SYMBOL(bd_abort_claiming); -#ifdef CONFIG_SYSFS -struct bd_holder_disk { - struct list_head list; - struct gendisk *disk; - int refcnt; -}; - -static struct bd_holder_disk *bd_find_holder_disk(struct block_device *bdev, - struct gendisk *disk) -{ - struct bd_holder_disk *holder; - - list_for_each_entry(holder, &bdev->bd_holder_disks, list) - if (holder->disk == disk) - return holder; - return NULL; -} - -static int add_symlink(struct kobject *from, struct kobject *to) -{ - return sysfs_create_link(from, to, kobject_name(to)); -} - -static void del_symlink(struct kobject *from, struct kobject *to) -{ - sysfs_remove_link(from, kobject_name(to)); -} - -/** - * bd_link_disk_holder - create symlinks between holding disk and slave bdev - * @bdev: the claimed slave bdev - * @disk: the holding disk - * - * DON'T USE THIS UNLESS YOU'RE ALREADY USING IT. - * - * This functions creates the following sysfs symlinks. - * - * - from "slaves" directory of the holder @disk to the claimed @bdev - * - from "holders" directory of the @bdev to the holder @disk - * - * For example, if /dev/dm-0 maps to /dev/sda and disk for dm-0 is - * passed to bd_link_disk_holder(), then: - * - * /sys/block/dm-0/slaves/sda --> /sys/block/sda - * /sys/block/sda/holders/dm-0 --> /sys/block/dm-0 - * - * The caller must have claimed @bdev before calling this function and - * ensure that both @bdev and @disk are valid during the creation and - * lifetime of these symlinks. - * - * CONTEXT: - * Might sleep. - * - * RETURNS: - * 0 on success, -errno on failure. - */ -int bd_link_disk_holder(struct block_device *bdev, struct gendisk *disk) -{ - struct bd_holder_disk *holder; - int ret = 0; - - mutex_lock(&bdev->bd_disk->open_mutex); - - WARN_ON_ONCE(!bdev->bd_holder); - - /* FIXME: remove the following once add_disk() handles errors */ - if (WARN_ON(!disk->slave_dir || !bdev->bd_holder_dir)) - goto out_unlock; - - holder = bd_find_holder_disk(bdev, disk); - if (holder) { - holder->refcnt++; - goto out_unlock; - } - - holder = kzalloc(sizeof(*holder), GFP_KERNEL); - if (!holder) { - ret = -ENOMEM; - goto out_unlock; - } - - INIT_LIST_HEAD(&holder->list); - holder->disk = disk; - holder->refcnt = 1; - - ret = add_symlink(disk->slave_dir, bdev_kobj(bdev)); - if (ret) - goto out_free; - - ret = add_symlink(bdev->bd_holder_dir, &disk_to_dev(disk)->kobj); - if (ret) - goto out_del; - /* - * bdev could be deleted beneath us which would implicitly destroy - * the holder directory. Hold on to it. - */ - kobject_get(bdev->bd_holder_dir); - - list_add(&holder->list, &bdev->bd_holder_disks); - goto out_unlock; - -out_del: - del_symlink(disk->slave_dir, bdev_kobj(bdev)); -out_free: - kfree(holder); -out_unlock: - mutex_unlock(&bdev->bd_disk->open_mutex); - return ret; -} -EXPORT_SYMBOL_GPL(bd_link_disk_holder); - -/** - * bd_unlink_disk_holder - destroy symlinks created by bd_link_disk_holder() - * @bdev: the calimed slave bdev - * @disk: the holding disk - * - * DON'T USE THIS UNLESS YOU'RE ALREADY USING IT. - * - * CONTEXT: - * Might sleep. - */ -void bd_unlink_disk_holder(struct block_device *bdev, struct gendisk *disk) -{ - struct bd_holder_disk *holder; - - mutex_lock(&bdev->bd_disk->open_mutex); - - holder = bd_find_holder_disk(bdev, disk); - - if (!WARN_ON_ONCE(holder == NULL) && !--holder->refcnt) { - del_symlink(disk->slave_dir, bdev_kobj(bdev)); - del_symlink(bdev->bd_holder_dir, &disk_to_dev(disk)->kobj); - kobject_put(bdev->bd_holder_dir); - list_del_init(&holder->list); - kfree(holder); - } - - mutex_unlock(&bdev->bd_disk->open_mutex); -} -EXPORT_SYMBOL_GPL(bd_unlink_disk_holder); -#endif - static void blkdev_flush_mapping(struct block_device *bdev) { WARN_ON_ONCE(bdev->bd_holders); @@ -1260,11 +1084,8 @@ static int blkdev_get_whole(struct block_device *bdev, fmode_t mode) } } - if (!bdev->bd_openers) { + if (!bdev->bd_openers) set_init_blocksize(bdev); - if (bdev->bd_bdi == &noop_backing_dev_info) - bdev->bd_bdi = bdi_get(disk->queue->backing_dev_info); - } if (test_bit(GD_NEED_PART_SCAN, &disk->state)) bdev_disk_changed(disk, false); bdev->bd_openers++; @@ -1282,16 +1103,14 @@ static void blkdev_put_whole(struct block_device *bdev, fmode_t mode) static int blkdev_get_part(struct block_device *part, fmode_t mode) { struct gendisk *disk = part->bd_disk; - struct block_device *whole; int ret; if (part->bd_openers) goto done; - whole = bdgrab(disk->part0); - ret = blkdev_get_whole(whole, mode); + ret = blkdev_get_whole(bdev_whole(part), mode); if (ret) - goto out_put_whole; + return ret; ret = -ENXIO; if (!bdev_nr_sectors(part)) @@ -1299,16 +1118,12 @@ static int blkdev_get_part(struct block_device *part, fmode_t mode) disk->open_partitions++; set_init_blocksize(part); - if (part->bd_bdi == &noop_backing_dev_info) - part->bd_bdi = bdi_get(disk->queue->backing_dev_info); done: part->bd_openers++; return 0; out_blkdev_put: - blkdev_put_whole(whole, mode); -out_put_whole: - bdput(whole); + blkdev_put_whole(bdev_whole(part), mode); return ret; } @@ -1321,42 +1136,42 @@ static void blkdev_put_part(struct block_device *part, fmode_t mode) blkdev_flush_mapping(part); whole->bd_disk->open_partitions--; blkdev_put_whole(whole, mode); - bdput(whole); } struct block_device *blkdev_get_no_open(dev_t dev) { struct block_device *bdev; - struct gendisk *disk; + struct inode *inode; - bdev = bdget(dev); - if (!bdev) { + inode = ilookup(blockdev_superblock, dev); + if (!inode) { blk_request_module(dev); - bdev = bdget(dev); - if (!bdev) + inode = ilookup(blockdev_superblock, dev); + if (!inode) return NULL; } - disk = bdev->bd_disk; - if (!kobject_get_unless_zero(&disk_to_dev(disk)->kobj)) - goto bdput; - if ((disk->flags & (GENHD_FL_UP | GENHD_FL_HIDDEN)) != GENHD_FL_UP) - goto put_disk; - if (!try_module_get(bdev->bd_disk->fops->owner)) - goto put_disk; + /* switch from the inode reference to a device mode one: */ + bdev = &BDEV_I(inode)->bdev; + if (!kobject_get_unless_zero(&bdev->bd_device.kobj)) + bdev = NULL; + iput(inode); + + if (!bdev) + return NULL; + if ((bdev->bd_disk->flags & GENHD_FL_HIDDEN) || + !try_module_get(bdev->bd_disk->fops->owner)) { + put_device(&bdev->bd_device); + return NULL; + } + return bdev; -put_disk: - put_disk(disk); -bdput: - bdput(bdev); - return NULL; } void blkdev_put_no_open(struct block_device *bdev) { module_put(bdev->bd_disk->fops->owner); - put_disk(bdev->bd_disk); - bdput(bdev); + put_device(&bdev->bd_device); } /** @@ -1409,7 +1224,7 @@ struct block_device *blkdev_get_by_dev(dev_t dev, fmode_t mode, void *holder) mutex_lock(&disk->open_mutex); ret = -ENXIO; - if (!(disk->flags & GENHD_FL_UP)) + if (!disk_live(disk)) goto abort_claiming; if (bdev_is_partition(bdev)) ret = blkdev_get_part(bdev, mode); diff --git a/fs/f2fs/sysfs.c b/fs/f2fs/sysfs.c index 6642246206bd..daad532a4e2b 100644 --- a/fs/f2fs/sysfs.c +++ b/fs/f2fs/sysfs.c @@ -378,7 +378,7 @@ out: ret = kstrtol(name, 10, &data); if (ret) return ret; - if (data >= IOPRIO_BE_NR || data < 0) + if (data >= IOPRIO_NR_LEVELS || data < 0) return -EINVAL; cprc->ckpt_thread_ioprio = IOPRIO_PRIO_VALUE(class, data); diff --git a/fs/fat/fatent.c b/fs/fat/fatent.c index 860e884e56e8..978ac6751aeb 100644 --- a/fs/fat/fatent.c +++ b/fs/fat/fatent.c @@ -5,6 +5,7 @@ #include <linux/blkdev.h> #include <linux/sched/signal.h> +#include <linux/backing-dev-defs.h> #include "fat.h" struct fatent_operations { diff --git a/fs/nilfs2/super.c b/fs/nilfs2/super.c index 4abd928b0bc8..f6b2d280aab5 100644 --- a/fs/nilfs2/super.c +++ b/fs/nilfs2/super.c @@ -1053,7 +1053,7 @@ nilfs_fill_super(struct super_block *sb, void *data, int silent) sb->s_time_gran = 1; sb->s_max_links = NILFS_LINK_MAX; - sb->s_bdi = bdi_get(sb->s_bdev->bd_bdi); + sb->s_bdi = bdi_get(sb->s_bdev->bd_disk->bdi); err = load_nilfs(nilfs, sb); if (err) diff --git a/fs/squashfs/block.c b/fs/squashfs/block.c index 855f0e87066d..2db8bcf7ff85 100644 --- a/fs/squashfs/block.c +++ b/fs/squashfs/block.c @@ -49,8 +49,7 @@ static int copy_bio_to_actor(struct bio *bio, bytes_to_copy = min_t(int, bytes_to_copy, req_length - copied_bytes); - memcpy(actor_addr + actor_offset, - page_address(bvec->bv_page) + bvec->bv_offset + offset, + memcpy(actor_addr + actor_offset, bvec_virt(bvec) + offset, bytes_to_copy); actor_offset += bytes_to_copy; @@ -177,7 +176,7 @@ int squashfs_read_data(struct super_block *sb, u64 index, int length, goto out_free_bio; } /* Extract the length of the metadata block */ - data = page_address(bvec->bv_page) + bvec->bv_offset; + data = bvec_virt(bvec); length = data[offset]; if (offset < bvec->bv_len - 1) { length |= data[offset + 1] << 8; @@ -186,7 +185,7 @@ int squashfs_read_data(struct super_block *sb, u64 index, int length, res = -EIO; goto out_free_bio; } - data = page_address(bvec->bv_page) + bvec->bv_offset; + data = bvec_virt(bvec); length |= data[0] << 8; } bio_free_pages(bio); diff --git a/fs/squashfs/lz4_wrapper.c b/fs/squashfs/lz4_wrapper.c index 233d5582fbee..b685b6238316 100644 --- a/fs/squashfs/lz4_wrapper.c +++ b/fs/squashfs/lz4_wrapper.c @@ -101,7 +101,7 @@ static int lz4_uncompress(struct squashfs_sb_info *msblk, void *strm, while (bio_next_segment(bio, &iter_all)) { int avail = min(bytes, ((int)bvec->bv_len) - offset); - data = page_address(bvec->bv_page) + bvec->bv_offset; + data = bvec_virt(bvec); memcpy(buff, data + offset, avail); buff += avail; bytes -= avail; diff --git a/fs/squashfs/lzo_wrapper.c b/fs/squashfs/lzo_wrapper.c index 97bb7d92ddcd..cb510a631968 100644 --- a/fs/squashfs/lzo_wrapper.c +++ b/fs/squashfs/lzo_wrapper.c @@ -76,7 +76,7 @@ static int lzo_uncompress(struct squashfs_sb_info *msblk, void *strm, while (bio_next_segment(bio, &iter_all)) { int avail = min(bytes, ((int)bvec->bv_len) - offset); - data = page_address(bvec->bv_page) + bvec->bv_offset; + data = bvec_virt(bvec); memcpy(buff, data + offset, avail); buff += avail; bytes -= avail; diff --git a/fs/squashfs/xz_wrapper.c b/fs/squashfs/xz_wrapper.c index e80419aed862..68f6d09bb3a2 100644 --- a/fs/squashfs/xz_wrapper.c +++ b/fs/squashfs/xz_wrapper.c @@ -146,7 +146,7 @@ static int squashfs_xz_uncompress(struct squashfs_sb_info *msblk, void *strm, } avail = min(length, ((int)bvec->bv_len) - offset); - data = page_address(bvec->bv_page) + bvec->bv_offset; + data = bvec_virt(bvec); length -= avail; stream->buf.in = data + offset; stream->buf.in_size = avail; diff --git a/fs/squashfs/zlib_wrapper.c b/fs/squashfs/zlib_wrapper.c index bcb881ec47f2..a20e9042146b 100644 --- a/fs/squashfs/zlib_wrapper.c +++ b/fs/squashfs/zlib_wrapper.c @@ -76,7 +76,7 @@ static int zlib_uncompress(struct squashfs_sb_info *msblk, void *strm, } avail = min(length, ((int)bvec->bv_len) - offset); - data = page_address(bvec->bv_page) + bvec->bv_offset; + data = bvec_virt(bvec); length -= avail; stream->next_in = data + offset; stream->avail_in = avail; diff --git a/fs/squashfs/zstd_wrapper.c b/fs/squashfs/zstd_wrapper.c index b7cb1faa652d..0015cf8b5582 100644 --- a/fs/squashfs/zstd_wrapper.c +++ b/fs/squashfs/zstd_wrapper.c @@ -94,7 +94,7 @@ static int zstd_uncompress(struct squashfs_sb_info *msblk, void *strm, } avail = min(length, ((int)bvec->bv_len) - offset); - data = page_address(bvec->bv_page) + bvec->bv_offset; + data = bvec_virt(bvec); length -= avail; in_buf.src = data + offset; in_buf.size = avail; diff --git a/fs/super.c b/fs/super.c index 91b7f156735b..bcef3a6f4c4b 100644 --- a/fs/super.c +++ b/fs/super.c @@ -1203,7 +1203,7 @@ static int set_bdev_super(struct super_block *s, void *data) { s->s_bdev = data; s->s_dev = s->s_bdev->bd_dev; - s->s_bdi = bdi_get(s->s_bdev->bd_bdi); + s->s_bdi = bdi_get(s->s_bdev->bd_disk->bdi); if (blk_queue_stable_writes(s->s_bdev->bd_disk->queue)) s->s_iflags |= SB_I_STABLE_WRITES; diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c index 8ff42b3585e0..3ab73567a0f5 100644 --- a/fs/xfs/xfs_buf.c +++ b/fs/xfs/xfs_buf.c @@ -844,7 +844,7 @@ xfs_buf_readahead_map( { struct xfs_buf *bp; - if (bdi_read_congested(target->bt_bdev->bd_bdi)) + if (bdi_read_congested(target->bt_bdev->bd_disk->bdi)) return; xfs_buf_read_map(target, map, nmaps, diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index 44df4fcef65c..29530859d9ff 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -143,7 +143,7 @@ static inline struct backing_dev_info *inode_to_bdi(struct inode *inode) sb = inode->i_sb; #ifdef CONFIG_BLOCK if (sb_is_blkdev_sb(sb)) - return I_BDEV(inode)->bd_bdi; + return I_BDEV(inode)->bd_disk->bdi; #endif return sb->s_bdi; } diff --git a/include/linux/bio.h b/include/linux/bio.h index 2203b686e1f0..7b5f65a81f2b 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -5,7 +5,6 @@ #ifndef __LINUX_BIO_H #define __LINUX_BIO_H -#include <linux/highmem.h> #include <linux/mempool.h> #include <linux/ioprio.h> /* struct bio, bio_vec and BIO_* flags are defined in blk_types.h */ @@ -519,47 +518,6 @@ static inline void bio_clone_blkg_association(struct bio *dst, struct bio *src) { } #endif /* CONFIG_BLK_CGROUP */ -#ifdef CONFIG_HIGHMEM -/* - * remember never ever reenable interrupts between a bvec_kmap_irq and - * bvec_kunmap_irq! - */ -static inline char *bvec_kmap_irq(struct bio_vec *bvec, unsigned long *flags) -{ - unsigned long addr; - - /* - * might not be a highmem page, but the preempt/irq count - * balancing is a lot nicer this way - */ - local_irq_save(*flags); - addr = (unsigned long) kmap_atomic(bvec->bv_page); - - BUG_ON(addr & ~PAGE_MASK); - - return (char *) addr + bvec->bv_offset; -} - -static inline void bvec_kunmap_irq(char *buffer, unsigned long *flags) -{ - unsigned long ptr = (unsigned long) buffer & PAGE_MASK; - - kunmap_atomic((void *) ptr); - local_irq_restore(*flags); -} - -#else -static inline char *bvec_kmap_irq(struct bio_vec *bvec, unsigned long *flags) -{ - return page_address(bvec->bv_page) + bvec->bv_offset; -} - -static inline void bvec_kunmap_irq(char *buffer, unsigned long *flags) -{ - *flags = 0; -} -#endif - /* * BIO list management for use by remapping drivers (e.g. DM or MD) and loop. * diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h index 37048438872c..b4de2010fba5 100644 --- a/include/linux/blk-cgroup.h +++ b/include/linux/blk-cgroup.h @@ -152,8 +152,8 @@ typedef void (blkcg_pol_online_pd_fn)(struct blkg_policy_data *pd); typedef void (blkcg_pol_offline_pd_fn)(struct blkg_policy_data *pd); typedef void (blkcg_pol_free_pd_fn)(struct blkg_policy_data *pd); typedef void (blkcg_pol_reset_pd_stats_fn)(struct blkg_policy_data *pd); -typedef size_t (blkcg_pol_stat_pd_fn)(struct blkg_policy_data *pd, char *buf, - size_t size); +typedef bool (blkcg_pol_stat_pd_fn)(struct blkg_policy_data *pd, + struct seq_file *s); struct blkcg_policy { int plid; diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index 1d18447ebebc..13ba1861e688 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -404,7 +404,13 @@ enum { BLK_MQ_F_STACKING = 1 << 2, BLK_MQ_F_TAG_HCTX_SHARED = 1 << 3, BLK_MQ_F_BLOCKING = 1 << 5, + /* Do not allow an I/O scheduler to be configured. */ BLK_MQ_F_NO_SCHED = 1 << 6, + /* + * Select 'none' during queue registration in case of a single hwq + * or shared hwqs instead of 'mq-deadline'. + */ + BLK_MQ_F_NO_SCHED_BY_DEFAULT = 1 << 7, BLK_MQ_F_ALLOC_POLICY_START_BIT = 8, BLK_MQ_F_ALLOC_POLICY_BITS = 1, @@ -426,18 +432,14 @@ enum { ((policy & ((1 << BLK_MQ_F_ALLOC_POLICY_BITS) - 1)) \ << BLK_MQ_F_ALLOC_POLICY_START_BIT) +struct gendisk *__blk_mq_alloc_disk(struct blk_mq_tag_set *set, void *queuedata, + struct lock_class_key *lkclass); #define blk_mq_alloc_disk(set, queuedata) \ ({ \ static struct lock_class_key __key; \ - struct gendisk *__disk = __blk_mq_alloc_disk(set, queuedata); \ \ - if (!IS_ERR(__disk)) \ - lockdep_init_map(&__disk->lockdep_map, \ - "(bio completion)", &__key, 0); \ - __disk; \ + __blk_mq_alloc_disk(set, queuedata, &__key); \ }) -struct gendisk *__blk_mq_alloc_disk(struct blk_mq_tag_set *set, - void *queuedata); struct request_queue *blk_mq_init_queue(struct blk_mq_tag_set *); int blk_mq_init_allocated_queue(struct blk_mq_tag_set *set, struct request_queue *q); diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index 290f9061b29a..1335efa8a1db 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -34,14 +34,10 @@ struct block_device { void * bd_holder; int bd_holders; bool bd_write_holder; -#ifdef CONFIG_SYSFS - struct list_head bd_holder_disks; -#endif struct kobject *bd_holder_dir; u8 bd_partno; spinlock_t bd_size_lock; /* for bd_inode->i_size updates */ struct gendisk * bd_disk; - struct backing_dev_info *bd_bdi; /* The counter of freeze processes */ int bd_fsfreeze_count; diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index d3afea47ade6..c9cb12483e12 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -11,7 +11,6 @@ #include <linux/minmax.h> #include <linux/timer.h> #include <linux/workqueue.h> -#include <linux/backing-dev-defs.h> #include <linux/wait.h> #include <linux/mempool.h> #include <linux/pfn.h> @@ -398,8 +397,6 @@ struct request_queue { struct blk_mq_hw_ctx **queue_hw_ctx; unsigned int nr_hw_queues; - struct backing_dev_info *backing_dev_info; - /* * The queue owner gets to use this for whatever they like. * ll_rw_blk doesn't touch it. @@ -424,6 +421,8 @@ struct request_queue { spinlock_t queue_lock; + struct gendisk *disk; + /* * queue kobject */ @@ -664,8 +663,6 @@ extern void blk_clear_pm_only(struct request_queue *q); dma_map_page_attrs(dev, (bv)->bv_page, (bv)->bv_offset, (bv)->bv_len, \ (dir), (attrs)) -#define queue_to_disk(q) (dev_to_disk(kobj_to_dev((q)->kobj.parent))) - static inline bool queue_is_mq(struct request_queue *q) { return q->mq_ops; @@ -941,6 +938,10 @@ static inline struct request_queue *bdev_get_queue(struct block_device *bdev) #define SECTOR_SIZE (1 << SECTOR_SHIFT) #endif +#define PAGE_SECTORS_SHIFT (PAGE_SHIFT - SECTOR_SHIFT) +#define PAGE_SECTORS (1 << PAGE_SECTORS_SHIFT) +#define SECTOR_MASK (PAGE_SECTORS - 1) + /* * blk_rq_pos() : the current sector * blk_rq_bytes() : bytes left in the entire request @@ -1139,7 +1140,7 @@ void blk_queue_zone_write_granularity(struct request_queue *q, unsigned int size); extern void blk_queue_alignment_offset(struct request_queue *q, unsigned int alignment); -void blk_queue_update_readahead(struct request_queue *q); +void disk_update_readahead(struct gendisk *disk); extern void blk_limits_io_min(struct queue_limits *limits, unsigned int min); extern void blk_queue_io_min(struct request_queue *q, unsigned int min); extern void blk_limits_io_opt(struct queue_limits *limits, unsigned int opt); @@ -1521,6 +1522,22 @@ static inline int queue_limit_discard_alignment(struct queue_limits *lim, sector return offset << SECTOR_SHIFT; } +/* + * Two cases of handling DISCARD merge: + * If max_discard_segments > 1, the driver takes every bio + * as a range and send them to controller together. The ranges + * needn't to be contiguous. + * Otherwise, the bios/requests will be handled as same as + * others which should be contiguous. + */ +static inline bool blk_discard_mergable(struct request *req) +{ + if (req_op(req) == REQ_OP_DISCARD && + queue_max_discard_segments(req->q) > 1) + return true; + return false; +} + static inline int bdev_discard_alignment(struct block_device *bdev) { struct request_queue *q = bdev_get_queue(bdev); @@ -1855,6 +1872,13 @@ struct block_device_operations { char *(*devnode)(struct gendisk *disk, umode_t *mode); struct module *owner; const struct pr_ops *pr_ops; + + /* + * Special callback for probing GPT entry at a given sector. + * Needed by Android devices, used by GPT scanner and MMC blk + * driver. + */ + int (*alternative_gpt_sector)(struct gendisk *disk, sector_t *sector); }; #ifdef CONFIG_COMPAT @@ -1984,8 +2008,6 @@ void blkdev_put_no_open(struct block_device *bdev); struct block_device *bdev_alloc(struct gendisk *disk, u8 partno); void bdev_add(struct block_device *bdev, dev_t dev); struct block_device *I_BDEV(struct inode *inode); -struct block_device *bdgrab(struct block_device *bdev); -void bdput(struct block_device *); int truncate_bdev_range(struct block_device *bdev, fmode_t mode, loff_t lstart, loff_t lend); diff --git a/include/linux/bvec.h b/include/linux/bvec.h index ff832e698efb..0e9bdd42dafb 100644 --- a/include/linux/bvec.h +++ b/include/linux/bvec.h @@ -4,9 +4,10 @@ * * Copyright (C) 2001 Ming Lei <ming.lei@canonical.com> */ -#ifndef __LINUX_BVEC_ITER_H -#define __LINUX_BVEC_ITER_H +#ifndef __LINUX_BVEC_H +#define __LINUX_BVEC_H +#include <linux/highmem.h> #include <linux/bug.h> #include <linux/errno.h> #include <linux/limits.h> @@ -183,4 +184,61 @@ static inline void bvec_advance(const struct bio_vec *bvec, } } -#endif /* __LINUX_BVEC_ITER_H */ +/** + * bvec_kmap_local - map a bvec into the kernel virtual address space + * @bvec: bvec to map + * + * Must be called on single-page bvecs only. Call kunmap_local on the returned + * address to unmap. + */ +static inline void *bvec_kmap_local(struct bio_vec *bvec) +{ + return kmap_local_page(bvec->bv_page) + bvec->bv_offset; +} + +/** + * memcpy_from_bvec - copy data from a bvec + * @bvec: bvec to copy from + * + * Must be called on single-page bvecs only. + */ +static inline void memcpy_from_bvec(char *to, struct bio_vec *bvec) +{ + memcpy_from_page(to, bvec->bv_page, bvec->bv_offset, bvec->bv_len); +} + +/** + * memcpy_to_bvec - copy data to a bvec + * @bvec: bvec to copy to + * + * Must be called on single-page bvecs only. + */ +static inline void memcpy_to_bvec(struct bio_vec *bvec, const char *from) +{ + memcpy_to_page(bvec->bv_page, bvec->bv_offset, from, bvec->bv_len); +} + +/** + * memzero_bvec - zero all data in a bvec + * @bvec: bvec to zero + * + * Must be called on single-page bvecs only. + */ +static inline void memzero_bvec(struct bio_vec *bvec) +{ + memzero_page(bvec->bv_page, bvec->bv_offset, bvec->bv_len); +} + +/** + * bvec_virt - return the virtual address for a bvec + * @bvec: bvec to return the virtual address for + * + * Note: the caller must ensure that @bvec->bv_page is not a highmem page. + */ +static inline void *bvec_virt(struct bio_vec *bvec) +{ + WARN_ON_ONCE(PageHighMem(bvec->bv_page)); + return page_address(bvec->bv_page) + bvec->bv_offset; +} + +#endif /* __LINUX_BVEC_H */ diff --git a/include/linux/cmdline-parser.h b/include/linux/cmdline-parser.h deleted file mode 100644 index 68a541807bdf..000000000000 --- a/include/linux/cmdline-parser.h +++ /dev/null @@ -1,46 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * Parsing command line, get the partitions information. - * - * Written by Cai Zhiyong <caizhiyong@huawei.com> - * - */ -#ifndef CMDLINEPARSEH -#define CMDLINEPARSEH - -#include <linux/blkdev.h> -#include <linux/fs.h> -#include <linux/slab.h> - -/* partition flags */ -#define PF_RDONLY 0x01 /* Device is read only */ -#define PF_POWERUP_LOCK 0x02 /* Always locked after reset */ - -struct cmdline_subpart { - char name[BDEVNAME_SIZE]; /* partition name, such as 'rootfs' */ - sector_t from; - sector_t size; - int flags; - struct cmdline_subpart *next_subpart; -}; - -struct cmdline_parts { - char name[BDEVNAME_SIZE]; /* block device, such as 'mmcblk0' */ - unsigned int nr_subparts; - struct cmdline_subpart *subpart; - struct cmdline_parts *next_parts; -}; - -void cmdline_parts_free(struct cmdline_parts **parts); - -int cmdline_parts_parse(struct cmdline_parts **parts, const char *cmdline); - -struct cmdline_parts *cmdline_parts_find(struct cmdline_parts *parts, - const char *bdev); - -int cmdline_parts_set(struct cmdline_parts *parts, sector_t disk_size, - int slot, - int (*add_part)(int, struct cmdline_subpart *, void *), - void *param); - -#endif /* CMDLINEPARSEH */ diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h index 7457d49acf9a..94f2cd6a8e83 100644 --- a/include/linux/device-mapper.h +++ b/include/linux/device-mapper.h @@ -151,7 +151,6 @@ typedef size_t (*dm_dax_copy_iter_fn)(struct dm_target *ti, pgoff_t pgoff, void *addr, size_t bytes, struct iov_iter *i); typedef int (*dm_dax_zero_page_range_fn)(struct dm_target *ti, pgoff_t pgoff, size_t nr_pages); -#define PAGE_SECTORS (PAGE_SIZE / 512) void dm_error(const char *message); diff --git a/include/linux/fs.h b/include/linux/fs.h index 719345723911..7eae53fff7c5 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -3204,10 +3204,6 @@ ssize_t vfs_iocb_iter_read(struct file *file, struct kiocb *iocb, ssize_t vfs_iocb_iter_write(struct file *file, struct kiocb *iocb, struct iov_iter *iter); -/* fs/block_dev.c */ -extern int blkdev_fsync(struct file *filp, loff_t start, loff_t end, - int datasync); - /* fs/splice.c */ extern ssize_t generic_file_splice_read(struct file *, loff_t *, struct pipe_inode_info *, size_t, unsigned int); diff --git a/include/linux/genhd.h b/include/linux/genhd.h index 13b34177cc85..c68d83c87f83 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -60,9 +60,6 @@ struct partition_meta_info { * device. * Affects responses to the ``CDROM_GET_CAPABILITY`` ioctl. * - * ``GENHD_FL_UP`` (0x0010): indicates that the block device is "up", - * with a similar meaning to network interfaces. - * * ``GENHD_FL_SUPPRESS_PARTITION_INFO`` (0x0020): don't include * partition information in ``/proc/partitions`` or in the output of * printk_all_partitions(). @@ -97,7 +94,6 @@ struct partition_meta_info { /* 2 is unused (used to be GENHD_FL_DRIVERFS) */ /* 4 is unused (used to be GENHD_FL_MEDIA_CHANGE_NOTIFY) */ #define GENHD_FL_CD 0x0008 -#define GENHD_FL_UP 0x0010 #define GENHD_FL_SUPPRESS_PARTITION_INFO 0x0020 #define GENHD_FL_EXT_DEVT 0x0040 #define GENHD_FL_NATIVE_CAPACITY 0x0080 @@ -153,13 +149,15 @@ struct gendisk { unsigned long state; #define GD_NEED_PART_SCAN 0 #define GD_READ_ONLY 1 -#define GD_QUEUE_REF 2 struct mutex open_mutex; /* open/close mutex */ unsigned open_partitions; /* number of open partitions */ + struct backing_dev_info *bdi; struct kobject *slave_dir; - +#ifdef CONFIG_BLOCK_HOLDER_DEPRECATED + struct list_head slave_bdevs; +#endif struct timer_rand_state *random; atomic_t sync_io; /* RAID */ struct disk_events *ev; @@ -172,8 +170,14 @@ struct gendisk { int node_id; struct badblocks *bb; struct lockdep_map lockdep_map; + u64 diskseq; }; +static inline bool disk_live(struct gendisk *disk) +{ + return !inode_unhashed(disk->part0->bd_inode); +} + /* * The gendisk is refcounted by the part0 block_device, and the bd_device * therein is also used for device model presentation in sysfs. @@ -210,18 +214,12 @@ static inline dev_t disk_devt(struct gendisk *disk) void disk_uevent(struct gendisk *disk, enum kobject_action action); /* block/genhd.c */ -extern void device_add_disk(struct device *parent, struct gendisk *disk, - const struct attribute_group **groups); -static inline void add_disk(struct gendisk *disk) +int device_add_disk(struct device *parent, struct gendisk *disk, + const struct attribute_group **groups); +static inline int add_disk(struct gendisk *disk) { - device_add_disk(NULL, disk, NULL); + return device_add_disk(NULL, disk, NULL); } -extern void device_add_disk_no_queue_reg(struct device *parent, struct gendisk *disk); -static inline void add_disk_no_queue_reg(struct gendisk *disk) -{ - device_add_disk_no_queue_reg(NULL, disk); -} - extern void del_gendisk(struct gendisk *gp); void set_disk_ro(struct gendisk *disk, bool read_only); @@ -236,6 +234,7 @@ extern void disk_block_events(struct gendisk *disk); extern void disk_unblock_events(struct gendisk *disk); extern void disk_flush_events(struct gendisk *disk, unsigned int mask); bool set_capacity_and_notify(struct gendisk *disk, sector_t size); +bool disk_force_media_change(struct gendisk *disk, unsigned int events); /* drivers/char/random.c */ extern void add_disk_randomness(struct gendisk *disk) __latent_entropy; @@ -259,26 +258,10 @@ static inline sector_t get_capacity(struct gendisk *disk) int bdev_disk_changed(struct gendisk *disk, bool invalidate); void blk_drop_partitions(struct gendisk *disk); -extern struct gendisk *__alloc_disk_node(int minors, int node_id); +struct gendisk *__alloc_disk_node(struct request_queue *q, int node_id, + struct lock_class_key *lkclass); extern void put_disk(struct gendisk *disk); - -#define alloc_disk_node(minors, node_id) \ -({ \ - static struct lock_class_key __key; \ - const char *__name; \ - struct gendisk *__disk; \ - \ - __name = "(gendisk_completion)"#minors"("#node_id")"; \ - \ - __disk = __alloc_disk_node(minors, node_id); \ - \ - if (__disk) \ - lockdep_init_map(&__disk->lockdep_map, __name, &__key, 0); \ - \ - __disk; \ -}) - -#define alloc_disk(minors) alloc_disk_node(minors, NUMA_NO_NODE) +struct gendisk *__blk_alloc_disk(int node, struct lock_class_key *lkclass); /** * blk_alloc_disk - allocate a gendisk structure @@ -291,15 +274,10 @@ extern void put_disk(struct gendisk *disk); */ #define blk_alloc_disk(node_id) \ ({ \ - struct gendisk *__disk = __blk_alloc_disk(node_id); \ static struct lock_class_key __key; \ \ - if (__disk) \ - lockdep_init_map(&__disk->lockdep_map, \ - "(bio completion)", &__key, 0); \ - __disk; \ + __blk_alloc_disk(node_id, &__key); \ }) -struct gendisk *__blk_alloc_disk(int node); void blk_cleanup_disk(struct gendisk *disk); int __register_blkdev(unsigned int major, const char *name, @@ -316,9 +294,10 @@ void set_capacity(struct gendisk *disk, sector_t size); int blkdev_ioctl(struct block_device *, fmode_t, unsigned, unsigned long); long compat_blkdev_ioctl(struct file *, unsigned, unsigned long); -#ifdef CONFIG_SYSFS +#ifdef CONFIG_BLOCK_HOLDER_DEPRECATED int bd_link_disk_holder(struct block_device *bdev, struct gendisk *disk); void bd_unlink_disk_holder(struct block_device *bdev, struct gendisk *disk); +int bd_register_pending_holders(struct gendisk *disk); #else static inline int bd_link_disk_holder(struct block_device *bdev, struct gendisk *disk) @@ -329,9 +308,14 @@ static inline void bd_unlink_disk_holder(struct block_device *bdev, struct gendisk *disk) { } -#endif /* CONFIG_SYSFS */ +static inline int bd_register_pending_holders(struct gendisk *disk) +{ + return 0; +} +#endif /* CONFIG_BLOCK_HOLDER_DEPRECATED */ dev_t part_devt(struct gendisk *disk, u8 partno); +void inc_diskseq(struct gendisk *disk); dev_t blk_lookup_devt(const char *name, int partno); void blk_request_module(dev_t devt); #ifdef CONFIG_BLOCK diff --git a/include/linux/ioprio.h b/include/linux/ioprio.h index e9bfe6972aed..3f53bc27a19b 100644 --- a/include/linux/ioprio.h +++ b/include/linux/ioprio.h @@ -6,46 +6,22 @@ #include <linux/sched/rt.h> #include <linux/iocontext.h> -/* - * Gives us 8 prio classes with 13-bits of data for each class - */ -#define IOPRIO_CLASS_SHIFT (13) -#define IOPRIO_PRIO_MASK ((1UL << IOPRIO_CLASS_SHIFT) - 1) - -#define IOPRIO_PRIO_CLASS(mask) ((mask) >> IOPRIO_CLASS_SHIFT) -#define IOPRIO_PRIO_DATA(mask) ((mask) & IOPRIO_PRIO_MASK) -#define IOPRIO_PRIO_VALUE(class, data) (((class) << IOPRIO_CLASS_SHIFT) | data) - -#define ioprio_valid(mask) (IOPRIO_PRIO_CLASS((mask)) != IOPRIO_CLASS_NONE) +#include <uapi/linux/ioprio.h> /* - * These are the io priority groups as implemented by CFQ. RT is the realtime - * class, it always gets premium service. BE is the best-effort scheduling - * class, the default for any process. IDLE is the idle scheduling class, it - * is only served when no one else is using the disk. + * Default IO priority. */ -enum { - IOPRIO_CLASS_NONE, - IOPRIO_CLASS_RT, - IOPRIO_CLASS_BE, - IOPRIO_CLASS_IDLE, -}; +#define IOPRIO_DEFAULT IOPRIO_PRIO_VALUE(IOPRIO_CLASS_BE, IOPRIO_BE_NORM) /* - * 8 best effort priority levels are supported + * Check that a priority value has a valid class. */ -#define IOPRIO_BE_NR (8) - -enum { - IOPRIO_WHO_PROCESS = 1, - IOPRIO_WHO_PGRP, - IOPRIO_WHO_USER, -}; +static inline bool ioprio_valid(unsigned short ioprio) +{ + unsigned short class = IOPRIO_PRIO_CLASS(ioprio); -/* - * Fallback BE priority - */ -#define IOPRIO_NORM (4) + return class > IOPRIO_CLASS_NONE && class <= IOPRIO_CLASS_IDLE; +} /* * if process has set io priority explicitly, use that. if not, convert @@ -80,7 +56,7 @@ static inline int get_current_ioprio(void) if (ioc) return ioc->ioprio; - return IOPRIO_PRIO_VALUE(IOPRIO_CLASS_NONE, 0); + return IOPRIO_DEFAULT; } /* diff --git a/include/linux/mmc/card.h b/include/linux/mmc/card.h index 74e6c0624d27..37f975875102 100644 --- a/include/linux/mmc/card.h +++ b/include/linux/mmc/card.h @@ -109,6 +109,7 @@ struct mmc_ext_csd { u8 raw_hc_erase_gap_size; /* 221 */ u8 raw_erase_timeout_mult; /* 223 */ u8 raw_hc_erase_grp_size; /* 224 */ + u8 raw_boot_mult; /* 226 */ u8 raw_sec_trim_mult; /* 229 */ u8 raw_sec_erase_mult; /* 230 */ u8 raw_sec_feature_support;/* 231 */ diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h index 0abd47e9ef9b..78dadf86b38f 100644 --- a/include/linux/mmc/host.h +++ b/include/linux/mmc/host.h @@ -398,6 +398,7 @@ struct mmc_host { #else #define MMC_CAP2_CRYPTO 0 #endif +#define MMC_CAP2_ALT_GPT_TEGRA (1 << 28) /* Host with eMMC that has GPT entry at a non-standard location */ int fixed_drv_type; /* fixed driver type for non-removable media */ diff --git a/include/linux/writeback.h b/include/linux/writeback.h index 667e86cfbdcf..270677dc4f36 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -336,14 +336,9 @@ static inline void cgroup_writeback_umount(void) /* * mm/page-writeback.c */ -#ifdef CONFIG_BLOCK void laptop_io_completion(struct backing_dev_info *info); void laptop_sync_completion(void); -void laptop_mode_sync(struct work_struct *work); void laptop_mode_timer_fn(struct timer_list *t); -#else -static inline void laptop_sync_completion(void) { } -#endif bool node_dirty_ok(struct pglist_data *pgdat); int wb_domain_init(struct wb_domain *dom, gfp_t gfp); #ifdef CONFIG_CGROUP_WRITEBACK diff --git a/include/trace/events/kyber.h b/include/trace/events/kyber.h index f9802562edf6..491098a0d8ed 100644 --- a/include/trace/events/kyber.h +++ b/include/trace/events/kyber.h @@ -30,7 +30,7 @@ TRACE_EVENT(kyber_latency, ), TP_fast_assign( - __entry->dev = disk_devt(queue_to_disk(q)); + __entry->dev = disk_devt(q->disk); strlcpy(__entry->domain, domain, sizeof(__entry->domain)); strlcpy(__entry->type, type, sizeof(__entry->type)); __entry->percentile = percentile; @@ -59,7 +59,7 @@ TRACE_EVENT(kyber_adjust, ), TP_fast_assign( - __entry->dev = disk_devt(queue_to_disk(q)); + __entry->dev = disk_devt(q->disk); strlcpy(__entry->domain, domain, sizeof(__entry->domain)); __entry->depth = depth; ), @@ -81,7 +81,7 @@ TRACE_EVENT(kyber_throttled, ), TP_fast_assign( - __entry->dev = disk_devt(queue_to_disk(q)); + __entry->dev = disk_devt(q->disk); strlcpy(__entry->domain, domain, sizeof(__entry->domain)); ), diff --git a/include/uapi/linux/fs.h b/include/uapi/linux/fs.h index 4c32e97dcdf0..bdf7b404b3e7 100644 --- a/include/uapi/linux/fs.h +++ b/include/uapi/linux/fs.h @@ -184,6 +184,7 @@ struct fsxattr { #define BLKSECDISCARD _IO(0x12,125) #define BLKROTATIONAL _IO(0x12,126) #define BLKZEROOUT _IO(0x12,127) +#define BLKGETDISKSEQ _IOR(0x12,128,__u64) /* * A jump here: 130-136 are reserved for zoned block devices * (see uapi/linux/blkzoned.h) diff --git a/include/uapi/linux/ioprio.h b/include/uapi/linux/ioprio.h new file mode 100644 index 000000000000..f70f2596a6bf --- /dev/null +++ b/include/uapi/linux/ioprio.h @@ -0,0 +1,52 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +#ifndef _UAPI_LINUX_IOPRIO_H +#define _UAPI_LINUX_IOPRIO_H + +/* + * Gives us 8 prio classes with 13-bits of data for each class + */ +#define IOPRIO_CLASS_SHIFT 13 +#define IOPRIO_CLASS_MASK 0x07 +#define IOPRIO_PRIO_MASK ((1UL << IOPRIO_CLASS_SHIFT) - 1) + +#define IOPRIO_PRIO_CLASS(ioprio) \ + (((ioprio) >> IOPRIO_CLASS_SHIFT) & IOPRIO_CLASS_MASK) +#define IOPRIO_PRIO_DATA(ioprio) ((ioprio) & IOPRIO_PRIO_MASK) +#define IOPRIO_PRIO_VALUE(class, data) \ + ((((class) & IOPRIO_CLASS_MASK) << IOPRIO_CLASS_SHIFT) | \ + ((data) & IOPRIO_PRIO_MASK)) + +/* + * These are the io priority groups as implemented by the BFQ and mq-deadline + * schedulers. RT is the realtime class, it always gets premium service. For + * ATA disks supporting NCQ IO priority, RT class IOs will be processed using + * high priority NCQ commands. BE is the best-effort scheduling class, the + * default for any process. IDLE is the idle scheduling class, it is only + * served when no one else is using the disk. + */ +enum { + IOPRIO_CLASS_NONE, + IOPRIO_CLASS_RT, + IOPRIO_CLASS_BE, + IOPRIO_CLASS_IDLE, +}; + +/* + * The RT and BE priority classes both support up to 8 priority levels. + */ +#define IOPRIO_NR_LEVELS 8 +#define IOPRIO_BE_NR IOPRIO_NR_LEVELS + +enum { + IOPRIO_WHO_PROCESS = 1, + IOPRIO_WHO_PGRP, + IOPRIO_WHO_USER, +}; + +/* + * Fallback BE priority level. + */ +#define IOPRIO_NORM 4 +#define IOPRIO_BE_NORM IOPRIO_NORM + +#endif /* _UAPI_LINUX_IOPRIO_H */ diff --git a/init/do_mounts.c b/init/do_mounts.c index 74aede860de7..b691d6891e51 100644 --- a/init/do_mounts.c +++ b/init/do_mounts.c @@ -432,10 +432,6 @@ retry: printk("Please append a correct \"root=\" boot option; here are the available partitions:\n"); printk_all_partitions(); -#ifdef CONFIG_DEBUG_BLOCK_EXT_DEVT - printk("DEBUG_BLOCK_EXT_DEVT is enabled, you need to specify " - "explicit textual name for \"root=\" boot option.\n"); -#endif panic("VFS: Unable to mount root fs on %s", b); } if (!(flags & SB_RDONLY)) { diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index e5cdf98f50c2..73604bff3d2c 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -1680,33 +1680,6 @@ config DEBUG_WQ_FORCE_RR_CPU feature by default. When enabled, memory and cache locality will be impacted. -config DEBUG_BLOCK_EXT_DEVT - bool "Force extended block device numbers and spread them" - depends on DEBUG_KERNEL - depends on BLOCK - default n - help - BIG FAT WARNING: ENABLING THIS OPTION MIGHT BREAK BOOTING ON - SOME DISTRIBUTIONS. DO NOT ENABLE THIS UNLESS YOU KNOW WHAT - YOU ARE DOING. Distros, please enable this and fix whatever - is broken. - - Conventionally, block device numbers are allocated from - predetermined contiguous area. However, extended block area - may introduce non-contiguous block device numbers. This - option forces most block device numbers to be allocated from - the extended space and spreads them to discover kernel or - userland code paths which assume predetermined contiguous - device number allocation. - - Note that turning on this debug option shuffles all the - device numbers for all IDE and SCSI devices including libata - ones, so root partition specified using device number - directly (via rdev or root=MAJ:MIN) won't work anymore. - Textual device names (root=/dev/sdXn) will continue to work. - - Say N if you are unsure. - config CPU_HOTPLUG_STATE_CONTROL bool "Enable CPU hotplug state control" depends on DEBUG_KERNEL diff --git a/mm/backing-dev.c b/mm/backing-dev.c index f5561ea7d90a..cd06dca232c3 100644 --- a/mm/backing-dev.c +++ b/mm/backing-dev.c @@ -807,6 +807,7 @@ struct backing_dev_info *bdi_alloc(int node_id) bdi->capabilities = BDI_CAP_WRITEBACK | BDI_CAP_WRITEBACK_ACCT; bdi->ra_pages = VM_READAHEAD_PAGES; bdi->io_pages = VM_READAHEAD_PAGES; + timer_setup(&bdi->laptop_mode_wb_timer, laptop_mode_timer_fn, 0); return bdi; } EXPORT_SYMBOL(bdi_alloc); @@ -928,6 +929,8 @@ static void bdi_remove_from_list(struct backing_dev_info *bdi) void bdi_unregister(struct backing_dev_info *bdi) { + del_timer_sync(&bdi->laptop_mode_wb_timer); + /* make sure nobody finds us on the bdi_list anymore */ bdi_remove_from_list(bdi); wb_shutdown(&bdi->wb); diff --git a/mm/page-writeback.c b/mm/page-writeback.c index 9f63548f247c..c12f67cbfa19 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -2010,7 +2010,6 @@ int dirty_writeback_centisecs_handler(struct ctl_table *table, int write, return ret; } -#ifdef CONFIG_BLOCK void laptop_mode_timer_fn(struct timer_list *t) { struct backing_dev_info *backing_dev_info = @@ -2045,7 +2044,6 @@ void laptop_sync_completion(void) rcu_read_unlock(); } -#endif /* * If ratelimit_pages is too high then we can get into dirty-data overload |