diff options
Diffstat (limited to 'drivers/md')
| -rw-r--r-- | drivers/md/bcache/bset.c | 16 | ||||
| -rw-r--r-- | drivers/md/bcache/bset.h | 34 | ||||
| -rw-r--r-- | drivers/md/bcache/sysfs.c | 7 | ||||
| -rw-r--r-- | drivers/md/dm-init.c | 10 | ||||
| -rw-r--r-- | drivers/md/dm-log-writes.c | 23 | ||||
| -rw-r--r-- | drivers/md/dm-table.c | 2 | ||||
| -rw-r--r-- | drivers/md/dm-verity-target.c | 7 | ||||
| -rw-r--r-- | drivers/md/dm-verity.h | 3 | ||||
| -rw-r--r-- | drivers/md/md.c | 36 | ||||
| -rw-r--r-- | drivers/md/raid5-cache.c | 11 | ||||
| -rw-r--r-- | drivers/md/raid5-ppl.c | 10 |
11 files changed, 94 insertions, 65 deletions
diff --git a/drivers/md/bcache/bset.c b/drivers/md/bcache/bset.c index 8f07fa6e1739..268f1b685084 100644 --- a/drivers/md/bcache/bset.c +++ b/drivers/md/bcache/bset.c @@ -887,12 +887,22 @@ unsigned int bch_btree_insert_key(struct btree_keys *b, struct bkey *k, struct bset *i = bset_tree_last(b)->data; struct bkey *m, *prev = NULL; struct btree_iter iter; + struct bkey preceding_key_on_stack = ZERO_KEY; + struct bkey *preceding_key_p = &preceding_key_on_stack; BUG_ON(b->ops->is_extents && !KEY_SIZE(k)); - m = bch_btree_iter_init(b, &iter, b->ops->is_extents - ? PRECEDING_KEY(&START_KEY(k)) - : PRECEDING_KEY(k)); + /* + * If k has preceding key, preceding_key_p will be set to address + * of k's preceding key; otherwise preceding_key_p will be set + * to NULL inside preceding_key(). + */ + if (b->ops->is_extents) + preceding_key(&START_KEY(k), &preceding_key_p); + else + preceding_key(k, &preceding_key_p); + + m = bch_btree_iter_init(b, &iter, preceding_key_p); if (b->ops->insert_fixup(b, k, &iter, replace_key)) return status; diff --git a/drivers/md/bcache/bset.h b/drivers/md/bcache/bset.h index bac76aabca6d..c71365e7c1fa 100644 --- a/drivers/md/bcache/bset.h +++ b/drivers/md/bcache/bset.h @@ -434,20 +434,26 @@ static inline bool bch_cut_back(const struct bkey *where, struct bkey *k) return __bch_cut_back(where, k); } -#define PRECEDING_KEY(_k) \ -({ \ - struct bkey *_ret = NULL; \ - \ - if (KEY_INODE(_k) || KEY_OFFSET(_k)) { \ - _ret = &KEY(KEY_INODE(_k), KEY_OFFSET(_k), 0); \ - \ - if (!_ret->low) \ - _ret->high--; \ - _ret->low--; \ - } \ - \ - _ret; \ -}) +/* + * Pointer '*preceding_key_p' points to a memory object to store preceding + * key of k. If the preceding key does not exist, set '*preceding_key_p' to + * NULL. So the caller of preceding_key() needs to take care of memory + * which '*preceding_key_p' pointed to before calling preceding_key(). + * Currently the only caller of preceding_key() is bch_btree_insert_key(), + * and it points to an on-stack variable, so the memory release is handled + * by stackframe itself. + */ +static inline void preceding_key(struct bkey *k, struct bkey **preceding_key_p) +{ + if (KEY_INODE(k) || KEY_OFFSET(k)) { + (**preceding_key_p) = KEY(KEY_INODE(k), KEY_OFFSET(k), 0); + if (!(*preceding_key_p)->low) + (*preceding_key_p)->high--; + (*preceding_key_p)->low--; + } else { + (*preceding_key_p) = NULL; + } +} static inline bool bch_ptr_invalid(struct btree_keys *b, const struct bkey *k) { diff --git a/drivers/md/bcache/sysfs.c b/drivers/md/bcache/sysfs.c index 6cd44d3cf906..bfb437ffb13c 100644 --- a/drivers/md/bcache/sysfs.c +++ b/drivers/md/bcache/sysfs.c @@ -431,8 +431,13 @@ STORE(bch_cached_dev) bch_writeback_queue(dc); } + /* + * Only set BCACHE_DEV_WB_RUNNING when cached device attached to + * a cache set, otherwise it doesn't make sense. + */ if (attr == &sysfs_writeback_percent) - if (!test_and_set_bit(BCACHE_DEV_WB_RUNNING, &dc->disk.flags)) + if ((dc->disk.c != NULL) && + (!test_and_set_bit(BCACHE_DEV_WB_RUNNING, &dc->disk.flags))) schedule_delayed_work(&dc->writeback_rate_update, dc->writeback_rate_update_seconds * HZ); diff --git a/drivers/md/dm-init.c b/drivers/md/dm-init.c index 352e803f566e..728733a514c7 100644 --- a/drivers/md/dm-init.c +++ b/drivers/md/dm-init.c @@ -140,8 +140,8 @@ static char __init *dm_parse_table_entry(struct dm_device *dev, char *str) return ERR_PTR(-EINVAL); } /* target_args */ - dev->target_args_array[n] = kstrndup(field[3], GFP_KERNEL, - DM_MAX_STR_SIZE); + dev->target_args_array[n] = kstrndup(field[3], DM_MAX_STR_SIZE, + GFP_KERNEL); if (!dev->target_args_array[n]) return ERR_PTR(-ENOMEM); @@ -272,10 +272,10 @@ static int __init dm_init_init(void) return 0; if (strlen(create) >= DM_MAX_STR_SIZE) { - DMERR("Argument is too big. Limit is %d\n", DM_MAX_STR_SIZE); + DMERR("Argument is too big. Limit is %d", DM_MAX_STR_SIZE); return -EINVAL; } - str = kstrndup(create, GFP_KERNEL, DM_MAX_STR_SIZE); + str = kstrndup(create, DM_MAX_STR_SIZE, GFP_KERNEL); if (!str) return -ENOMEM; @@ -283,7 +283,7 @@ static int __init dm_init_init(void) if (r) goto out; - DMINFO("waiting for all devices to be available before creating mapped devices\n"); + DMINFO("waiting for all devices to be available before creating mapped devices"); wait_for_device_probe(); list_for_each_entry(dev, &devices, list) { diff --git a/drivers/md/dm-log-writes.c b/drivers/md/dm-log-writes.c index 9ea2b0291f20..e549392e0ea5 100644 --- a/drivers/md/dm-log-writes.c +++ b/drivers/md/dm-log-writes.c @@ -60,6 +60,7 @@ #define WRITE_LOG_VERSION 1ULL #define WRITE_LOG_MAGIC 0x6a736677736872ULL +#define WRITE_LOG_SUPER_SECTOR 0 /* * The disk format for this is braindead simple. @@ -115,6 +116,7 @@ struct log_writes_c { struct list_head logging_blocks; wait_queue_head_t wait; struct task_struct *log_kthread; + struct completion super_done; }; struct pending_block { @@ -180,6 +182,14 @@ static void log_end_io(struct bio *bio) bio_put(bio); } +static void log_end_super(struct bio *bio) +{ + struct log_writes_c *lc = bio->bi_private; + + complete(&lc->super_done); + log_end_io(bio); +} + /* * Meant to be called if there is an error, it will free all the pages * associated with the block. @@ -215,7 +225,8 @@ static int write_metadata(struct log_writes_c *lc, void *entry, bio->bi_iter.bi_size = 0; bio->bi_iter.bi_sector = sector; bio_set_dev(bio, lc->logdev->bdev); - bio->bi_end_io = log_end_io; + bio->bi_end_io = (sector == WRITE_LOG_SUPER_SECTOR) ? + log_end_super : log_end_io; bio->bi_private = lc; bio_set_op_attrs(bio, REQ_OP_WRITE, 0); @@ -418,11 +429,18 @@ static int log_super(struct log_writes_c *lc) super.nr_entries = cpu_to_le64(lc->logged_entries); super.sectorsize = cpu_to_le32(lc->sectorsize); - if (write_metadata(lc, &super, sizeof(super), NULL, 0, 0)) { + if (write_metadata(lc, &super, sizeof(super), NULL, 0, + WRITE_LOG_SUPER_SECTOR)) { DMERR("Couldn't write super"); return -1; } + /* + * Super sector should be writen in-order, otherwise the + * nr_entries could be rewritten incorrectly by an old bio. + */ + wait_for_completion_io(&lc->super_done); + return 0; } @@ -531,6 +549,7 @@ static int log_writes_ctr(struct dm_target *ti, unsigned int argc, char **argv) INIT_LIST_HEAD(&lc->unflushed_blocks); INIT_LIST_HEAD(&lc->logging_blocks); init_waitqueue_head(&lc->wait); + init_completion(&lc->super_done); atomic_set(&lc->io_blocks, 0); atomic_set(&lc->pending_blocks, 0); diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c index 350cf0451456..ec8b27e20de3 100644 --- a/drivers/md/dm-table.c +++ b/drivers/md/dm-table.c @@ -561,7 +561,7 @@ static char **realloc_argv(unsigned *size, char **old_argv) gfp = GFP_NOIO; } argv = kmalloc_array(new_size, sizeof(*argv), gfp); - if (argv) { + if (argv && old_argv) { memcpy(argv, old_argv, *size * sizeof(*argv)); *size = new_size; } diff --git a/drivers/md/dm-verity-target.c b/drivers/md/dm-verity-target.c index f4c31ffaa88e..ea24ff0612e3 100644 --- a/drivers/md/dm-verity-target.c +++ b/drivers/md/dm-verity-target.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2012 Red Hat, Inc. * @@ -5,8 +6,6 @@ * * Based on Chromium dm-verity driver (C) 2011 The Chromium OS Authors * - * This file is released under the GPLv2. - * * In the file "/sys/module/dm_verity/parameters/prefetch_cluster" you can set * default prefetch value. Data are read in "prefetch_cluster" chunks from the * hash device. Setting this greatly improves performance when data and hash @@ -236,8 +235,8 @@ static int verity_handle_err(struct dm_verity *v, enum verity_block_type type, BUG(); } - DMERR("%s: %s block %llu is corrupted", v->data_dev->name, type_str, - block); + DMERR_LIMIT("%s: %s block %llu is corrupted", v->data_dev->name, + type_str, block); if (v->corrupted_errs == DM_VERITY_MAX_CORRUPTED_ERRS) DMERR("%s: reached maximum errors", v->data_dev->name); diff --git a/drivers/md/dm-verity.h b/drivers/md/dm-verity.h index 3441c10b840c..eeaf940aef6d 100644 --- a/drivers/md/dm-verity.h +++ b/drivers/md/dm-verity.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright (C) 2012 Red Hat, Inc. * Copyright (C) 2015 Google, Inc. @@ -5,8 +6,6 @@ * Author: Mikulas Patocka <mpatocka@redhat.com> * * Based on Chromium dm-verity driver (C) 2011 The Chromium OS Authors - * - * This file is released under the GPLv2. */ #ifndef DM_VERITY_H diff --git a/drivers/md/md.c b/drivers/md/md.c index 04f4f131f9d6..9801d540fea1 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -7607,9 +7607,9 @@ static void status_unused(struct seq_file *seq) static int status_resync(struct seq_file *seq, struct mddev *mddev) { sector_t max_sectors, resync, res; - unsigned long dt, db; - sector_t rt; - int scale; + unsigned long dt, db = 0; + sector_t rt, curr_mark_cnt, resync_mark_cnt; + int scale, recovery_active; unsigned int per_milli; if (test_bit(MD_RECOVERY_SYNC, &mddev->recovery) || @@ -7698,22 +7698,30 @@ static int status_resync(struct seq_file *seq, struct mddev *mddev) * db: blocks written from mark until now * rt: remaining time * - * rt is a sector_t, so could be 32bit or 64bit. - * So we divide before multiply in case it is 32bit and close - * to the limit. - * We scale the divisor (db) by 32 to avoid losing precision - * near the end of resync when the number of remaining sectors - * is close to 'db'. - * We then divide rt by 32 after multiplying by db to compensate. - * The '+1' avoids division by zero if db is very small. + * rt is a sector_t, which is always 64bit now. We are keeping + * the original algorithm, but it is not really necessary. + * + * Original algorithm: + * So we divide before multiply in case it is 32bit and close + * to the limit. + * We scale the divisor (db) by 32 to avoid losing precision + * near the end of resync when the number of remaining sectors + * is close to 'db'. + * We then divide rt by 32 after multiplying by db to compensate. + * The '+1' avoids division by zero if db is very small. */ dt = ((jiffies - mddev->resync_mark) / HZ); if (!dt) dt++; - db = (mddev->curr_mark_cnt - atomic_read(&mddev->recovery_active)) - - mddev->resync_mark_cnt; + + curr_mark_cnt = mddev->curr_mark_cnt; + recovery_active = atomic_read(&mddev->recovery_active); + resync_mark_cnt = mddev->resync_mark_cnt; + + if (curr_mark_cnt >= (recovery_active + resync_mark_cnt)) + db = curr_mark_cnt - (recovery_active + resync_mark_cnt); rt = max_sectors - resync; /* number of remaining sectors */ - sector_div(rt, db/32+1); + rt = div64_u64(rt, db/32+1); rt *= dt; rt >>= 5; diff --git a/drivers/md/raid5-cache.c b/drivers/md/raid5-cache.c index cbbe6b6535be..9b6da759dca2 100644 --- a/drivers/md/raid5-cache.c +++ b/drivers/md/raid5-cache.c @@ -1,16 +1,7 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2015 Shaohua Li <shli@fb.com> * Copyright (C) 2016 Song Liu <songliubraving@fb.com> - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * */ #include <linux/kernel.h> #include <linux/wait.h> diff --git a/drivers/md/raid5-ppl.c b/drivers/md/raid5-ppl.c index 17e9e7d51097..18a4064a61a8 100644 --- a/drivers/md/raid5-ppl.c +++ b/drivers/md/raid5-ppl.c @@ -1,15 +1,7 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Partial Parity Log for closing the RAID5 write hole * Copyright (c) 2017, Intel Corporation. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. */ #include <linux/kernel.h> |