diff options
Diffstat (limited to 'drivers/md')
65 files changed, 317 insertions, 199 deletions
diff --git a/drivers/md/Makefile b/drivers/md/Makefile index 786ec9e86d65..e94b6f9be941 100644 --- a/drivers/md/Makefile +++ b/drivers/md/Makefile @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0 # # Makefile for the kernel software RAID and LVM drivers. # diff --git a/drivers/md/bcache/Makefile b/drivers/md/bcache/Makefile index c488b846f831..d26b35195825 100644 --- a/drivers/md/bcache/Makefile +++ b/drivers/md/bcache/Makefile @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0 obj-$(CONFIG_BCACHE) += bcache.o diff --git a/drivers/md/bcache/alloc.c b/drivers/md/bcache/alloc.c index cacbe2dbd5c3..08035634795c 100644 --- a/drivers/md/bcache/alloc.c +++ b/drivers/md/bcache/alloc.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Primary bucket allocation code * diff --git a/drivers/md/bcache/bcache.h b/drivers/md/bcache/bcache.h index 2ed9bd231d84..abd31e847f96 100644 --- a/drivers/md/bcache/bcache.h +++ b/drivers/md/bcache/bcache.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _BCACHE_H #define _BCACHE_H diff --git a/drivers/md/bcache/bset.c b/drivers/md/bcache/bset.c index 18526d44688d..e56d3ecdbfcb 100644 --- a/drivers/md/bcache/bset.c +++ b/drivers/md/bcache/bset.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Code for working with individual keys, and sorted sets of keys with in a * btree node diff --git a/drivers/md/bcache/bset.h b/drivers/md/bcache/bset.h index ae964624efb2..fa506c1aa524 100644 --- a/drivers/md/bcache/bset.h +++ b/drivers/md/bcache/bset.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _BCACHE_BSET_H #define _BCACHE_BSET_H diff --git a/drivers/md/bcache/btree.c b/drivers/md/bcache/btree.c index 866dcf78ff8e..658c54b3b07a 100644 --- a/drivers/md/bcache/btree.c +++ b/drivers/md/bcache/btree.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 2010 Kent Overstreet <kent.overstreet@gmail.com> * diff --git a/drivers/md/bcache/btree.h b/drivers/md/bcache/btree.h index 73da1f5626cb..42204d61bc95 100644 --- a/drivers/md/bcache/btree.h +++ b/drivers/md/bcache/btree.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _BCACHE_BTREE_H #define _BCACHE_BTREE_H diff --git a/drivers/md/bcache/closure.c b/drivers/md/bcache/closure.c index 7d5286b05036..1841d0359bac 100644 --- a/drivers/md/bcache/closure.c +++ b/drivers/md/bcache/closure.c @@ -64,7 +64,7 @@ EXPORT_SYMBOL(closure_put); void __closure_wake_up(struct closure_waitlist *wait_list) { struct llist_node *list; - struct closure *cl; + struct closure *cl, *t; struct llist_node *reverse = NULL; list = llist_del_all(&wait_list->list); @@ -73,7 +73,7 @@ void __closure_wake_up(struct closure_waitlist *wait_list) reverse = llist_reverse_order(list); /* Then do the wakeups */ - llist_for_each_entry(cl, reverse, list) { + llist_for_each_entry_safe(cl, t, reverse, list) { closure_set_waiting(cl, 0); closure_sub(cl, CLOSURE_WAITING + 1); } diff --git a/drivers/md/bcache/closure.h b/drivers/md/bcache/closure.h index 295b7e43f92c..965907ce1e20 100644 --- a/drivers/md/bcache/closure.h +++ b/drivers/md/bcache/closure.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_CLOSURE_H #define _LINUX_CLOSURE_H diff --git a/drivers/md/bcache/debug.c b/drivers/md/bcache/debug.c index 61076eda2e6d..c7a02c4900da 100644 --- a/drivers/md/bcache/debug.c +++ b/drivers/md/bcache/debug.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Assorted bcache debug code * diff --git a/drivers/md/bcache/debug.h b/drivers/md/bcache/debug.h index 1f63c195d247..acc48d3fa274 100644 --- a/drivers/md/bcache/debug.h +++ b/drivers/md/bcache/debug.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _BCACHE_DEBUG_H #define _BCACHE_DEBUG_H diff --git a/drivers/md/bcache/extents.c b/drivers/md/bcache/extents.c index 243de0bf15cd..41c238fc3733 100644 --- a/drivers/md/bcache/extents.c +++ b/drivers/md/bcache/extents.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 2010 Kent Overstreet <kent.overstreet@gmail.com> * diff --git a/drivers/md/bcache/extents.h b/drivers/md/bcache/extents.h index e2ed54054e7a..0cd3575afa1d 100644 --- a/drivers/md/bcache/extents.h +++ b/drivers/md/bcache/extents.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _BCACHE_EXTENTS_H #define _BCACHE_EXTENTS_H diff --git a/drivers/md/bcache/io.c b/drivers/md/bcache/io.c index 7e871bdc0097..fac97ec2d0e2 100644 --- a/drivers/md/bcache/io.c +++ b/drivers/md/bcache/io.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Some low level IO code, and hacks for various block layer limitations * diff --git a/drivers/md/bcache/journal.c b/drivers/md/bcache/journal.c index 7e1d1c3ba33a..02a98ddb592d 100644 --- a/drivers/md/bcache/journal.c +++ b/drivers/md/bcache/journal.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * bcache journalling code, for btree insertions * diff --git a/drivers/md/bcache/journal.h b/drivers/md/bcache/journal.h index e3c39457afbb..b5788199188f 100644 --- a/drivers/md/bcache/journal.h +++ b/drivers/md/bcache/journal.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _BCACHE_JOURNAL_H #define _BCACHE_JOURNAL_H diff --git a/drivers/md/bcache/movinggc.c b/drivers/md/bcache/movinggc.c index f633b30c962e..d50c1c97da68 100644 --- a/drivers/md/bcache/movinggc.c +++ b/drivers/md/bcache/movinggc.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Moving/copying garbage collector * diff --git a/drivers/md/bcache/request.c b/drivers/md/bcache/request.c index 681b4f12b05a..3475d6628e21 100644 --- a/drivers/md/bcache/request.c +++ b/drivers/md/bcache/request.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Main bcache entry point - handle a read or a write request and decide what to * do with it; the make_request functions are called by the block layer. diff --git a/drivers/md/bcache/request.h b/drivers/md/bcache/request.h index 7689176951ce..dea0886b81c1 100644 --- a/drivers/md/bcache/request.h +++ b/drivers/md/bcache/request.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _BCACHE_REQUEST_H_ #define _BCACHE_REQUEST_H_ diff --git a/drivers/md/bcache/stats.c b/drivers/md/bcache/stats.c index 0ca072c20d0d..d0831d5bcc87 100644 --- a/drivers/md/bcache/stats.c +++ b/drivers/md/bcache/stats.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * bcache stats code * diff --git a/drivers/md/bcache/stats.h b/drivers/md/bcache/stats.h index adbff141c887..0b70f9de0c03 100644 --- a/drivers/md/bcache/stats.h +++ b/drivers/md/bcache/stats.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _BCACHE_STATS_H_ #define _BCACHE_STATS_H_ diff --git a/drivers/md/bcache/sysfs.c b/drivers/md/bcache/sysfs.c index 104c57cd666c..234b2f5b286d 100644 --- a/drivers/md/bcache/sysfs.c +++ b/drivers/md/bcache/sysfs.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * bcache sysfs interfaces * diff --git a/drivers/md/bcache/sysfs.h b/drivers/md/bcache/sysfs.h index 0526fe92a683..b54fe9602529 100644 --- a/drivers/md/bcache/sysfs.h +++ b/drivers/md/bcache/sysfs.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _BCACHE_SYSFS_H_ #define _BCACHE_SYSFS_H_ diff --git a/drivers/md/bcache/trace.c b/drivers/md/bcache/trace.c index b7820b0d2621..a9a73f560c04 100644 --- a/drivers/md/bcache/trace.c +++ b/drivers/md/bcache/trace.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include "bcache.h" #include "btree.h" diff --git a/drivers/md/bcache/util.h b/drivers/md/bcache/util.h index cb8d2ccbb6c6..f54b58282f77 100644 --- a/drivers/md/bcache/util.h +++ b/drivers/md/bcache/util.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _BCACHE_UTIL_H #define _BCACHE_UTIL_H diff --git a/drivers/md/bcache/writeback.c b/drivers/md/bcache/writeback.c index e663ca082183..70454f2ad2fa 100644 --- a/drivers/md/bcache/writeback.c +++ b/drivers/md/bcache/writeback.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * background writeback - scan btree for dirty data and write it to the backing * device diff --git a/drivers/md/bcache/writeback.h b/drivers/md/bcache/writeback.h index e35421d20d2e..151544740148 100644 --- a/drivers/md/bcache/writeback.h +++ b/drivers/md/bcache/writeback.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _BCACHE_WRITEBACK_H #define _BCACHE_WRITEBACK_H diff --git a/drivers/md/bitmap.h b/drivers/md/bitmap.h index d15721ac07a6..5df35ca90f58 100644 --- a/drivers/md/bitmap.h +++ b/drivers/md/bitmap.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * bitmap.h: Copyright (C) Peter T. Breuer (ptb@ot.uc3m.es) 2003 * diff --git a/drivers/md/dm-bufio.c b/drivers/md/dm-bufio.c index 9601225e0ae9..d216a8f7bc22 100644 --- a/drivers/md/dm-bufio.c +++ b/drivers/md/dm-bufio.c @@ -64,6 +64,12 @@ #define DM_BUFIO_BLOCK_SIZE_GFP_LIMIT (PAGE_SIZE << (MAX_ORDER - 1)) /* + * Align buffer writes to this boundary. + * Tests show that SSDs have the highest IOPS when using 4k writes. + */ +#define DM_BUFIO_WRITE_ALIGN 4096 + +/* * dm_buffer->list_mode */ #define LIST_CLEAN 0 @@ -149,6 +155,10 @@ struct dm_buffer { blk_status_t write_error; unsigned long state; unsigned long last_accessed; + unsigned dirty_start; + unsigned dirty_end; + unsigned write_start; + unsigned write_end; struct dm_bufio_client *c; struct list_head write_list; struct bio bio; @@ -560,7 +570,7 @@ static void dmio_complete(unsigned long error, void *context) } static void use_dmio(struct dm_buffer *b, int rw, sector_t sector, - unsigned n_sectors, bio_end_io_t *end_io) + unsigned n_sectors, unsigned offset, bio_end_io_t *end_io) { int r; struct dm_io_request io_req = { @@ -578,10 +588,10 @@ static void use_dmio(struct dm_buffer *b, int rw, sector_t sector, if (b->data_mode != DATA_MODE_VMALLOC) { io_req.mem.type = DM_IO_KMEM; - io_req.mem.ptr.addr = b->data; + io_req.mem.ptr.addr = (char *)b->data + offset; } else { io_req.mem.type = DM_IO_VMA; - io_req.mem.ptr.vma = b->data; + io_req.mem.ptr.vma = (char *)b->data + offset; } b->bio.bi_end_io = end_io; @@ -609,10 +619,10 @@ static void inline_endio(struct bio *bio) } static void use_inline_bio(struct dm_buffer *b, int rw, sector_t sector, - unsigned n_sectors, bio_end_io_t *end_io) + unsigned n_sectors, unsigned offset, bio_end_io_t *end_io) { char *ptr; - int len; + unsigned len; bio_init(&b->bio, b->bio_vec, DM_BUFIO_INLINE_VECS); b->bio.bi_iter.bi_sector = sector; @@ -625,29 +635,20 @@ static void use_inline_bio(struct dm_buffer *b, int rw, sector_t sector, b->bio.bi_private = end_io; bio_set_op_attrs(&b->bio, rw, 0); - /* - * We assume that if len >= PAGE_SIZE ptr is page-aligned. - * If len < PAGE_SIZE the buffer doesn't cross page boundary. - */ - ptr = b->data; + ptr = (char *)b->data + offset; len = n_sectors << SECTOR_SHIFT; - if (len >= PAGE_SIZE) - BUG_ON((unsigned long)ptr & (PAGE_SIZE - 1)); - else - BUG_ON((unsigned long)ptr & (len - 1)); - do { - if (!bio_add_page(&b->bio, virt_to_page(ptr), - len < PAGE_SIZE ? len : PAGE_SIZE, + unsigned this_step = min((unsigned)(PAGE_SIZE - offset_in_page(ptr)), len); + if (!bio_add_page(&b->bio, virt_to_page(ptr), this_step, offset_in_page(ptr))) { BUG_ON(b->c->block_size <= PAGE_SIZE); - use_dmio(b, rw, sector, n_sectors, end_io); + use_dmio(b, rw, sector, n_sectors, offset, end_io); return; } - len -= PAGE_SIZE; - ptr += PAGE_SIZE; + len -= this_step; + ptr += this_step; } while (len > 0); submit_bio(&b->bio); @@ -657,18 +658,33 @@ static void submit_io(struct dm_buffer *b, int rw, bio_end_io_t *end_io) { unsigned n_sectors; sector_t sector; - - if (rw == WRITE && b->c->write_callback) - b->c->write_callback(b); + unsigned offset, end; sector = (b->block << b->c->sectors_per_block_bits) + b->c->start; - n_sectors = 1 << b->c->sectors_per_block_bits; + + if (rw != WRITE) { + n_sectors = 1 << b->c->sectors_per_block_bits; + offset = 0; + } else { + if (b->c->write_callback) + b->c->write_callback(b); + offset = b->write_start; + end = b->write_end; + offset &= -DM_BUFIO_WRITE_ALIGN; + end += DM_BUFIO_WRITE_ALIGN - 1; + end &= -DM_BUFIO_WRITE_ALIGN; + if (unlikely(end > b->c->block_size)) + end = b->c->block_size; + + sector += offset >> SECTOR_SHIFT; + n_sectors = (end - offset) >> SECTOR_SHIFT; + } if (n_sectors <= ((DM_BUFIO_INLINE_VECS * PAGE_SIZE) >> SECTOR_SHIFT) && b->data_mode != DATA_MODE_VMALLOC) - use_inline_bio(b, rw, sector, n_sectors, end_io); + use_inline_bio(b, rw, sector, n_sectors, offset, end_io); else - use_dmio(b, rw, sector, n_sectors, end_io); + use_dmio(b, rw, sector, n_sectors, offset, end_io); } /*---------------------------------------------------------------- @@ -720,6 +736,9 @@ static void __write_dirty_buffer(struct dm_buffer *b, clear_bit(B_DIRTY, &b->state); wait_on_bit_lock_io(&b->state, B_WRITING, TASK_UNINTERRUPTIBLE); + b->write_start = b->dirty_start; + b->write_end = b->dirty_end; + if (!write_list) submit_io(b, WRITE, write_endio); else @@ -1221,19 +1240,37 @@ void dm_bufio_release(struct dm_buffer *b) } EXPORT_SYMBOL_GPL(dm_bufio_release); -void dm_bufio_mark_buffer_dirty(struct dm_buffer *b) +void dm_bufio_mark_partial_buffer_dirty(struct dm_buffer *b, + unsigned start, unsigned end) { struct dm_bufio_client *c = b->c; + BUG_ON(start >= end); + BUG_ON(end > b->c->block_size); + dm_bufio_lock(c); BUG_ON(test_bit(B_READING, &b->state)); - if (!test_and_set_bit(B_DIRTY, &b->state)) + if (!test_and_set_bit(B_DIRTY, &b->state)) { + b->dirty_start = start; + b->dirty_end = end; __relink_lru(b, LIST_DIRTY); + } else { + if (start < b->dirty_start) + b->dirty_start = start; + if (end > b->dirty_end) + b->dirty_end = end; + } dm_bufio_unlock(c); } +EXPORT_SYMBOL_GPL(dm_bufio_mark_partial_buffer_dirty); + +void dm_bufio_mark_buffer_dirty(struct dm_buffer *b) +{ + dm_bufio_mark_partial_buffer_dirty(b, 0, b->c->block_size); +} EXPORT_SYMBOL_GPL(dm_bufio_mark_buffer_dirty); void dm_bufio_write_dirty_buffers_async(struct dm_bufio_client *c) @@ -1398,6 +1435,8 @@ retry: wait_on_bit_io(&b->state, B_WRITING, TASK_UNINTERRUPTIBLE); set_bit(B_DIRTY, &b->state); + b->dirty_start = 0; + b->dirty_end = c->block_size; __unlink_buffer(b); __link_buffer(b, new_block, LIST_DIRTY); } else { diff --git a/drivers/md/dm-bufio.h b/drivers/md/dm-bufio.h index b6d8f53ec15b..be732d3f8611 100644 --- a/drivers/md/dm-bufio.h +++ b/drivers/md/dm-bufio.h @@ -94,6 +94,15 @@ void dm_bufio_release(struct dm_buffer *b); void dm_bufio_mark_buffer_dirty(struct dm_buffer *b); /* + * Mark a part of the buffer dirty. + * + * The specified part of the buffer is scheduled to be written. dm-bufio may + * write the specified part of the buffer or it may write a larger superset. + */ +void dm_bufio_mark_partial_buffer_dirty(struct dm_buffer *b, + unsigned start, unsigned end); + +/* * Initiate writing of dirty buffers, without waiting for completion. */ void dm_bufio_write_dirty_buffers_async(struct dm_bufio_client *c); diff --git a/drivers/md/dm-builtin.c b/drivers/md/dm-builtin.c index f092771878c2..8eb52e425141 100644 --- a/drivers/md/dm-builtin.c +++ b/drivers/md/dm-builtin.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include "dm-core.h" /* diff --git a/drivers/md/dm-cache-target.c b/drivers/md/dm-cache-target.c index dcac25c2be7a..8785134c9f1f 100644 --- a/drivers/md/dm-cache-target.c +++ b/drivers/md/dm-cache-target.c @@ -2306,7 +2306,7 @@ static void init_features(struct cache_features *cf) static int parse_features(struct cache_args *ca, struct dm_arg_set *as, char **error) { - static struct dm_arg _args[] = { + static const struct dm_arg _args[] = { {0, 2, "Invalid number of cache feature arguments"}, }; @@ -2348,7 +2348,7 @@ static int parse_features(struct cache_args *ca, struct dm_arg_set *as, static int parse_policy(struct cache_args *ca, struct dm_arg_set *as, char **error) { - static struct dm_arg _args[] = { + static const struct dm_arg _args[] = { {0, 1024, "Invalid number of policy arguments"}, }; diff --git a/drivers/md/dm-core.h b/drivers/md/dm-core.h index 24eddbdf2ab4..203144762f36 100644 --- a/drivers/md/dm-core.h +++ b/drivers/md/dm-core.h @@ -149,5 +149,6 @@ static inline bool dm_message_test_buffer_overflow(char *result, unsigned maxlen extern atomic_t dm_global_event_nr; extern wait_queue_head_t dm_global_eventq; +void dm_issue_global_event(void); #endif diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c index 54aef8ed97db..96ab46512e1f 100644 --- a/drivers/md/dm-crypt.c +++ b/drivers/md/dm-crypt.c @@ -2466,6 +2466,7 @@ static int crypt_ctr_cipher_old(struct dm_target *ti, char *cipher_in, char *key kfree(cipher_api); return ret; } + kfree(cipher_api); return 0; bad_mem: @@ -2529,7 +2530,7 @@ static int crypt_ctr_optional(struct dm_target *ti, unsigned int argc, char **ar { struct crypt_config *cc = ti->private; struct dm_arg_set as; - static struct dm_arg _args[] = { + static const struct dm_arg _args[] = { {0, 6, "Invalid number of feature args"}, }; unsigned int opt_params, val; @@ -2584,6 +2585,10 @@ static int crypt_ctr_optional(struct dm_target *ti, unsigned int argc, char **ar ti->error = "Invalid feature value for sector_size"; return -EINVAL; } + if (ti->len & ((cc->sector_size >> SECTOR_SHIFT) - 1)) { + ti->error = "Device size is not multiple of sector_size feature"; + return -EINVAL; + } cc->sector_shift = __ffs(cc->sector_size) - SECTOR_SHIFT; } else if (!strcasecmp(opt_string, "iv_large_sectors")) set_bit(CRYPT_IV_LARGE_SECTORS, &cc->cipher_flags); diff --git a/drivers/md/dm-flakey.c b/drivers/md/dm-flakey.c index 7146c2d9762d..b82cb1ab1eaa 100644 --- a/drivers/md/dm-flakey.c +++ b/drivers/md/dm-flakey.c @@ -51,7 +51,7 @@ static int parse_features(struct dm_arg_set *as, struct flakey_c *fc, unsigned argc; const char *arg_name; - static struct dm_arg _args[] = { + static const struct dm_arg _args[] = { {0, 6, "Invalid number of feature args"}, {1, UINT_MAX, "Invalid corrupt bio byte"}, {0, 255, "Invalid corrupt value to write into bio byte (0-255)"}, @@ -178,7 +178,7 @@ static int parse_features(struct dm_arg_set *as, struct flakey_c *fc, */ static int flakey_ctr(struct dm_target *ti, unsigned int argc, char **argv) { - static struct dm_arg _args[] = { + static const struct dm_arg _args[] = { {0, UINT_MAX, "Invalid up interval"}, {0, UINT_MAX, "Invalid down interval"}, }; diff --git a/drivers/md/dm-integrity.c b/drivers/md/dm-integrity.c index 27c0f223f8ea..096fe9b66c50 100644 --- a/drivers/md/dm-integrity.c +++ b/drivers/md/dm-integrity.c @@ -225,6 +225,8 @@ struct dm_integrity_c { struct alg_spec internal_hash_alg; struct alg_spec journal_crypt_alg; struct alg_spec journal_mac_alg; + + atomic64_t number_of_mismatches; }; struct dm_integrity_range { @@ -298,7 +300,7 @@ static void __DEBUG_bytes(__u8 *bytes, size_t len, const char *msg, ...) /* * DM Integrity profile, protection is performed layer above (dm-crypt) */ -static struct blk_integrity_profile dm_integrity_profile = { +static const struct blk_integrity_profile dm_integrity_profile = { .name = "DM-DIF-EXT-TAG", .generate_fn = NULL, .verify_fn = NULL, @@ -310,6 +312,8 @@ static void dm_integrity_dtr(struct dm_target *ti); static void dm_integrity_io_error(struct dm_integrity_c *ic, const char *msg, int err) { + if (err == -EILSEQ) + atomic64_inc(&ic->number_of_mismatches); if (!cmpxchg(&ic->failed, 0, err)) DMERR("Error on %s: %d", msg, err); } @@ -770,13 +774,13 @@ static void write_journal(struct dm_integrity_c *ic, unsigned commit_start, unsi unsigned i; io_comp.ic = ic; - io_comp.comp = COMPLETION_INITIALIZER_ONSTACK(io_comp.comp); + init_completion(&io_comp.comp); if (commit_start + commit_sections <= ic->journal_sections) { io_comp.in_flight = (atomic_t)ATOMIC_INIT(1); if (ic->journal_io) { crypt_comp_1.ic = ic; - crypt_comp_1.comp = COMPLETION_INITIALIZER_ONSTACK(crypt_comp_1.comp); + init_completion(&crypt_comp_1.comp); crypt_comp_1.in_flight = (atomic_t)ATOMIC_INIT(0); encrypt_journal(ic, true, commit_start, commit_sections, &crypt_comp_1); wait_for_completion_io(&crypt_comp_1.comp); @@ -792,18 +796,18 @@ static void write_journal(struct dm_integrity_c *ic, unsigned commit_start, unsi to_end = ic->journal_sections - commit_start; if (ic->journal_io) { crypt_comp_1.ic = ic; - crypt_comp_1.comp = COMPLETION_INITIALIZER_ONSTACK(crypt_comp_1.comp); + init_completion(&crypt_comp_1.comp); crypt_comp_1.in_flight = (atomic_t)ATOMIC_INIT(0); encrypt_journal(ic, true, commit_start, to_end, &crypt_comp_1); if (try_wait_for_completion(&crypt_comp_1.comp)) { rw_journal(ic, REQ_OP_WRITE, REQ_FUA, commit_start, to_end, &io_comp); - crypt_comp_1.comp = COMPLETION_INITIALIZER_ONSTACK(crypt_comp_1.comp); + reinit_completion(&crypt_comp_1.comp); crypt_comp_1.in_flight = (atomic_t)ATOMIC_INIT(0); encrypt_journal(ic, true, 0, commit_sections - to_end, &crypt_comp_1); wait_for_completion_io(&crypt_comp_1.comp); } else { crypt_comp_2.ic = ic; - crypt_comp_2.comp = COMPLETION_INITIALIZER_ONSTACK(crypt_comp_2.comp); + init_completion(&crypt_comp_2.comp); crypt_comp_2.in_flight = (atomic_t)ATOMIC_INIT(0); encrypt_journal(ic, true, 0, commit_sections - to_end, &crypt_comp_2); wait_for_completion_io(&crypt_comp_1.comp); @@ -1041,7 +1045,7 @@ static int dm_integrity_rw_tag(struct dm_integrity_c *ic, unsigned char *tag, se memcpy(tag, dp, to_copy); } else if (op == TAG_WRITE) { memcpy(dp, tag, to_copy); - dm_bufio_mark_buffer_dirty(b); + dm_bufio_mark_partial_buffer_dirty(b, *metadata_offset, *metadata_offset + to_copy); } else { /* e.g.: op == TAG_CMP */ if (unlikely(memcmp(dp, tag, to_copy))) { @@ -1275,6 +1279,7 @@ again: DMERR("Checksum failed at sector 0x%llx", (unsigned long long)(sector - ((r + ic->tag_size - 1) / ic->tag_size))); r = -EILSEQ; + atomic64_inc(&ic->number_of_mismatches); } if (likely(checksums != checksums_onstack)) kfree(checksums); @@ -1676,7 +1681,7 @@ sleep: dio->in_flight = (atomic_t)ATOMIC_INIT(2); if (need_sync_io) { - read_comp = COMPLETION_INITIALIZER_ONSTACK(read_comp); + init_completion(&read_comp); dio->completion = &read_comp; } else dio->completion = NULL; @@ -1700,7 +1705,11 @@ sleep: if (need_sync_io) { wait_for_completion_io(&read_comp); - integrity_metadata(&dio->work); + if (likely(!bio->bi_status)) + integrity_metadata(&dio->work); + else + dec_in_flight(dio); + } else { INIT_WORK(&dio->work, integrity_metadata); queue_work(ic->metadata_wq, &dio->work); @@ -1834,7 +1843,7 @@ static void do_journal_write(struct dm_integrity_c *ic, unsigned write_start, comp.ic = ic; comp.in_flight = (atomic_t)ATOMIC_INIT(1); - comp.comp = COMPLETION_INITIALIZER_ONSTACK(comp.comp); + init_completion(&comp.comp); i = write_start; for (n = 0; n < write_sections; n++, i++, wraparound_section(ic, &i)) { @@ -2061,7 +2070,7 @@ static void replay_journal(struct dm_integrity_c *ic) if (ic->journal_io) { struct journal_completion crypt_comp; crypt_comp.ic = ic; - crypt_comp.comp = COMPLETION_INITIALIZER_ONSTACK(crypt_comp.comp); + init_completion(&crypt_comp.comp); crypt_comp.in_flight = (atomic_t)ATOMIC_INIT(0); encrypt_journal(ic, false, 0, ic->journal_sections, &crypt_comp); wait_for_completion(&crypt_comp.comp); @@ -2233,7 +2242,7 @@ static void dm_integrity_status(struct dm_target *ti, status_type_t type, switch (type) { case STATUSTYPE_INFO: - result[0] = '\0'; + DMEMIT("%llu", (unsigned long long)atomic64_read(&ic->number_of_mismatches)); break; case STATUSTYPE_TABLE: { @@ -2634,7 +2643,7 @@ static int create_journal(struct dm_integrity_c *ic, char **error) memset(iv, 0x00, ivsize); skcipher_request_set_crypt(req, sg, sg, PAGE_SIZE * ic->journal_pages + sizeof ic->commit_ids, iv); - comp.comp = COMPLETION_INITIALIZER_ONSTACK(comp.comp); + init_completion(&comp.comp); comp.in_flight = (atomic_t)ATOMIC_INIT(1); if (do_crypt(true, req, &comp)) wait_for_completion(&comp.comp); @@ -2691,7 +2700,7 @@ static int create_journal(struct dm_integrity_c *ic, char **error) sg_init_one(&sg, crypt_data, crypt_len); skcipher_request_set_crypt(req, &sg, &sg, crypt_len, iv); - comp.comp = COMPLETION_INITIALIZER_ONSTACK(comp.comp); + init_completion(&comp.comp); comp.in_flight = (atomic_t)ATOMIC_INIT(1); if (do_crypt(true, req, &comp)) wait_for_completion(&comp.comp); @@ -2778,7 +2787,7 @@ static int dm_integrity_ctr(struct dm_target *ti, unsigned argc, char **argv) int r; unsigned extra_args; struct dm_arg_set as; - static struct dm_arg _args[] = { + static const struct dm_arg _args[] = { {0, 9, "Invalid number of feature args"}, }; unsigned journal_sectors, interleave_sectors, buffer_sectors, journal_watermark, sync_msec; @@ -2806,6 +2815,7 @@ static int dm_integrity_ctr(struct dm_target *ti, unsigned argc, char **argv) bio_list_init(&ic->flush_bio_list); init_waitqueue_head(&ic->copy_to_journal_wait); init_completion(&ic->crypto_backoff); + atomic64_set(&ic->number_of_mismatches, 0); r = dm_get_device(ti, argv[0], dm_table_get_mode(ti->table), &ic->dev); if (r) { @@ -3202,7 +3212,7 @@ static void dm_integrity_dtr(struct dm_target *ti) static struct target_type integrity_target = { .name = "integrity", - .version = {1, 0, 0}, + .version = {1, 1, 0}, .module = THIS_MODULE, .features = DM_TARGET_SINGLETON | DM_TARGET_INTEGRITY, .ctr = dm_integrity_ctr, diff --git a/drivers/md/dm-ioctl.c b/drivers/md/dm-ioctl.c index e06f0ef7d2ec..e52676fa9832 100644 --- a/drivers/md/dm-ioctl.c +++ b/drivers/md/dm-ioctl.c @@ -477,9 +477,13 @@ static int remove_all(struct file *filp, struct dm_ioctl *param, size_t param_si * Round up the ptr to an 8-byte boundary. */ #define ALIGN_MASK 7 +static inline size_t align_val(size_t val) +{ + return (val + ALIGN_MASK) & ~ALIGN_MASK; +} static inline void *align_ptr(void *ptr) { - return (void *) (((size_t) (ptr + ALIGN_MASK)) & ~ALIGN_MASK); + return (void *)align_val((size_t)ptr); } /* @@ -505,7 +509,7 @@ static int list_devices(struct file *filp, struct dm_ioctl *param, size_t param_ struct hash_cell *hc; size_t len, needed = 0; struct gendisk *disk; - struct dm_name_list *nl, *old_nl = NULL; + struct dm_name_list *orig_nl, *nl, *old_nl = NULL; uint32_t *event_nr; down_write(&_hash_lock); @@ -516,17 +520,15 @@ static int list_devices(struct file *filp, struct dm_ioctl *param, size_t param_ */ for (i = 0; i < NUM_BUCKETS; i++) { list_for_each_entry (hc, _name_buckets + i, name_list) { - needed += sizeof(struct dm_name_list); - needed += strlen(hc->name) + 1; - needed += ALIGN_MASK; - needed += (sizeof(uint32_t) + ALIGN_MASK) & ~ALIGN_MASK; + needed += align_val(offsetof(struct dm_name_list, name) + strlen(hc->name) + 1); + needed += align_val(sizeof(uint32_t)); } } /* * Grab our output buffer. */ - nl = get_result_buffer(param, param_size, &len); + nl = orig_nl = get_result_buffer(param, param_size, &len); if (len < needed) { param->flags |= DM_BUFFER_FULL_FLAG; goto out; @@ -549,11 +551,16 @@ static int list_devices(struct file *filp, struct dm_ioctl *param, size_t param_ strcpy(nl->name, hc->name); old_nl = nl; - event_nr = align_ptr(((void *) (nl + 1)) + strlen(hc->name) + 1); + event_nr = align_ptr(nl->name + strlen(hc->name) + 1); *event_nr = dm_get_event_nr(hc->md); nl = align_ptr(event_nr + 1); } } + /* + * If mismatch happens, security may be compromised due to buffer + * overflow, so it's better to crash. + */ + BUG_ON((char *)nl - (char *)orig_nl != needed); out: up_write(&_hash_lock); @@ -1621,7 +1628,8 @@ static int target_message(struct file *filp, struct dm_ioctl *param, size_t para * which has a variable size, is not used by the function processing * the ioctl. */ -#define IOCTL_FLAGS_NO_PARAMS 1 +#define IOCTL_FLAGS_NO_PARAMS 1 +#define IOCTL_FLAGS_ISSUE_GLOBAL_EVENT 2 /*----------------------------------------------------------------- * Implementation of open/close/ioctl on the special char @@ -1629,18 +1637,18 @@ static int target_message(struct file *filp, struct dm_ioctl *param, size_t para *---------------------------------------------------------------*/ static ioctl_fn lookup_ioctl(unsigned int cmd, int *ioctl_flags) { - static struct { + static const struct { int cmd; int flags; ioctl_fn fn; } _ioctls[] = { {DM_VERSION_CMD, 0, NULL}, /* version is dealt with elsewhere */ - {DM_REMOVE_ALL_CMD, IOCTL_FLAGS_NO_PARAMS, remove_all}, + {DM_REMOVE_ALL_CMD, IOCTL_FLAGS_NO_PARAMS | IOCTL_FLAGS_ISSUE_GLOBAL_EVENT, remove_all}, {DM_LIST_DEVICES_CMD, 0, list_devices}, - {DM_DEV_CREATE_CMD, IOCTL_FLAGS_NO_PARAMS, dev_create}, - {DM_DEV_REMOVE_CMD, IOCTL_FLAGS_NO_PARAMS, dev_remove}, - {DM_DEV_RENAME_CMD, 0, dev_rename}, + {DM_DEV_CREATE_CMD, IOCTL_FLAGS_NO_PARAMS | IOCTL_FLAGS_ISSUE_GLOBAL_EVENT, dev_create}, + {DM_DEV_REMOVE_CMD, IOCTL_FLAGS_NO_PARAMS | IOCTL_FLAGS_ISSUE_GLOBAL_EVENT, dev_remove}, + {DM_DEV_RENAME_CMD, IOCTL_FLAGS_ISSUE_GLOBAL_EVENT, dev_rename}, {DM_DEV_SUSPEND_CMD, IOCTL_FLAGS_NO_PARAMS, dev_suspend}, {DM_DEV_STATUS_CMD, IOCTL_FLAGS_NO_PARAMS, dev_status}, {DM_DEV_WAIT_CMD, 0, dev_wait}, @@ -1869,6 +1877,9 @@ static int ctl_ioctl(struct file *file, uint command, struct dm_ioctl __user *us unlikely(ioctl_flags & IOCTL_FLAGS_NO_PARAMS)) DMERR("ioctl %d tried to output some data but has IOCTL_FLAGS_NO_PARAMS set", cmd); + if (!r && ioctl_flags & IOCTL_FLAGS_ISSUE_GLOBAL_EVENT) + dm_issue_global_event(); + /* * Copy the results back to userland. */ diff --git a/drivers/md/dm-linear.c b/drivers/md/dm-linear.c index 405eca206d67..d5f8eff7c11d 100644 --- a/drivers/md/dm-linear.c +++ b/drivers/md/dm-linear.c @@ -184,20 +184,6 @@ static size_t linear_dax_copy_from_iter(struct dm_target *ti, pgoff_t pgoff, return dax_copy_from_iter(dax_dev, pgoff, addr, bytes, i); } -static void linear_dax_flush(struct dm_target *ti, pgoff_t pgoff, void *addr, - size_t size) -{ - struct linear_c *lc = ti->private; - struct block_device *bdev = lc->dev->bdev; - struct dax_device *dax_dev = lc->dev->dax_dev; - sector_t dev_sector, sector = pgoff * PAGE_SECTORS; - - dev_sector = linear_map_sector(ti, sector); - if (bdev_dax_pgoff(bdev, dev_sector, ALIGN(size, PAGE_SIZE), &pgoff)) - return; - dax_flush(dax_dev, pgoff, addr, size); -} - static struct target_type linear_target = { .name = "linear", .version = {1, 4, 0}, @@ -212,7 +198,6 @@ static struct target_type linear_target = { .iterate_devices = linear_iterate_devices, .direct_access = linear_dax_direct_access, .dax_copy_from_iter = linear_dax_copy_from_iter, - .dax_flush = linear_dax_flush, }; int __init dm_linear_init(void) diff --git a/drivers/md/dm-log-writes.c b/drivers/md/dm-log-writes.c index 534a254eb977..8b80a9ce9ea9 100644 --- a/drivers/md/dm-log-writes.c +++ b/drivers/md/dm-log-writes.c @@ -100,6 +100,7 @@ struct log_writes_c { struct dm_dev *logdev; u64 logged_entries; u32 sectorsize; + u32 sectorshift; atomic_t io_blocks; atomic_t pending_blocks; sector_t next_sector; @@ -128,6 +129,18 @@ struct per_bio_data { struct pending_block *block; }; +static inline sector_t bio_to_dev_sectors(struct log_writes_c *lc, + sector_t sectors) +{ + return sectors >> (lc->sectorshift - SECTOR_SHIFT); +} + +static inline sector_t dev_to_bio_sectors(struct log_writes_c *lc, + sector_t sectors) +{ + return sectors << (lc->sectorshift - SECTOR_SHIFT); +} + static void put_pending_block(struct log_writes_c *lc) { if (atomic_dec_and_test(&lc->pending_blocks)) { @@ -253,7 +266,7 @@ static int log_one_block(struct log_writes_c *lc, if (!block->vec_cnt) goto out; - sector++; + sector += dev_to_bio_sectors(lc, 1); atomic_inc(&lc->io_blocks); bio = bio_alloc(GFP_KERNEL, min(block->vec_cnt, BIO_MAX_PAGES)); @@ -354,10 +367,9 @@ static int log_writes_kthread(void *arg) goto next; sector = lc->next_sector; - if (block->flags & LOG_DISCARD_FLAG) - lc->next_sector++; - else - lc->next_sector += block->nr_sectors + 1; + if (!(block->flags & LOG_DISCARD_FLAG)) + lc->next_sector += dev_to_bio_sectors(lc, block->nr_sectors); + lc->next_sector += dev_to_bio_sectors(lc, 1); /* * Apparently the size of the device may not be known @@ -399,7 +411,7 @@ next: if (!try_to_freeze()) { set_current_state(TASK_INTERRUPTIBLE); if (!kthread_should_stop() && - !atomic_read(&lc->pending_blocks)) + list_empty(&lc->logging_blocks)) schedule(); __set_current_state(TASK_RUNNING); } @@ -435,7 +447,6 @@ 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); - lc->sectorsize = 1 << SECTOR_SHIFT; atomic_set(&lc->io_blocks, 0); atomic_set(&lc->pending_blocks, 0); @@ -455,6 +466,8 @@ static int log_writes_ctr(struct dm_target *ti, unsigned int argc, char **argv) goto bad; } + lc->sectorsize = bdev_logical_block_size(lc->dev->bdev); + lc->sectorshift = ilog2(lc->sectorsize); lc->log_kthread = kthread_run(log_writes_kthread, lc, "log-write"); if (IS_ERR(lc->log_kthread)) { ret = PTR_ERR(lc->log_kthread); @@ -464,8 +477,12 @@ static int log_writes_ctr(struct dm_target *ti, unsigned int argc, char **argv) goto bad; } - /* We put the super at sector 0, start logging at sector 1 */ - lc->next_sector = 1; + /* + * next_sector is in 512b sectors to correspond to what bi_sector expects. + * The super starts at sector 0, and the next_sector is the next logical + * one based on the sectorsize of the device. + */ + lc->next_sector = lc->sectorsize >> SECTOR_SHIFT; lc->logging_enabled = true; lc->end_sector = logdev_last_sector(lc); lc->device_supports_discard = true; @@ -599,8 +616,8 @@ static int log_writes_map(struct dm_target *ti, struct bio *bio) if (discard_bio) block->flags |= LOG_DISCARD_FLAG; - block->sector = bio->bi_iter.bi_sector; - block->nr_sectors = bio_sectors(bio); + block->sector = bio_to_dev_sectors(lc, bio->bi_iter.bi_sector); + block->nr_sectors = bio_to_dev_sectors(lc, bio_sectors(bio)); /* We don't need the data, just submit */ if (discard_bio) { @@ -767,9 +784,12 @@ static void log_writes_io_hints(struct dm_target *ti, struct queue_limits *limit if (!q || !blk_queue_discard(q)) { lc->device_supports_discard = false; - limits->discard_granularity = 1 << SECTOR_SHIFT; + limits->discard_granularity = lc->sectorsize; limits->max_discard_sectors = (UINT_MAX >> SECTOR_SHIFT); } + limits->logical_block_size = bdev_logical_block_size(lc->dev->bdev); + limits->physical_block_size = bdev_physical_block_size(lc->dev->bdev); + limits->io_min = limits->physical_block_size; } static struct target_type log_writes_target = { diff --git a/drivers/md/dm-mpath.c b/drivers/md/dm-mpath.c index 96aedaac2c64..11f273d2f018 100644 --- a/drivers/md/dm-mpath.c +++ b/drivers/md/dm-mpath.c @@ -632,6 +632,10 @@ static void process_queued_bios(struct work_struct *work) case DM_MAPIO_REMAPPED: generic_make_request(bio); break; + case 0: + break; + default: + WARN_ONCE(true, "__multipath_map_bio() returned %d\n", r); } } blk_finish_plug(&plug); @@ -698,7 +702,7 @@ static int parse_path_selector(struct dm_arg_set *as, struct priority_group *pg, struct path_selector_type *pst; unsigned ps_argc; - static struct dm_arg _args[] = { + static const struct dm_arg _args[] = { {0, 1024, "invalid number of path selector args"}, }; @@ -822,7 +826,7 @@ retain: static struct priority_group *parse_priority_group(struct dm_arg_set *as, struct multipath *m) { - static struct dm_arg _args[] = { + static const struct dm_arg _args[] = { {1, 1024, "invalid number of paths"}, {0, 1024, "invalid number of selector args"} }; @@ -898,7 +902,7 @@ static int parse_hw_handler(struct dm_arg_set *as, struct multipath *m) int ret; struct dm_target *ti = m->ti; - static struct dm_arg _args[] = { + static const struct dm_arg _args[] = { {0, 1024, "invalid number of hardware handler args"}, }; @@ -950,7 +954,7 @@ static int parse_features(struct dm_arg_set *as, struct multipath *m) struct dm_target *ti = m->ti; const char *arg_name; - static struct dm_arg _args[] = { + static const struct dm_arg _args[] = { {0, 8, "invalid number of feature args"}, {1, 50, "pg_init_retries must be between 1 and 50"}, {0, 60000, "pg_init_delay_msecs must be between 0 and 60000"}, @@ -1019,7 +1023,7 @@ static int parse_features(struct dm_arg_set *as, struct multipath *m) static int multipath_ctr(struct dm_target *ti, unsigned argc, char **argv) { /* target arguments */ - static struct dm_arg _args[] = { + static const struct dm_arg _args[] = { {0, 1024, "invalid number of priority groups"}, {0, 1024, "invalid initial priority group number"}, }; @@ -1379,6 +1383,7 @@ static void pg_init_done(void *data, int errors) case SCSI_DH_RETRY: /* Wait before retrying. */ delay_retry = 1; + /* fall through */ case SCSI_DH_IMM_RETRY: case SCSI_DH_RES_TEMP_UNAVAIL: if (pg_init_limit_reached(m, pgpath)) diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c index 5bfe285ea9d1..2245d06d2045 100644 --- a/drivers/md/dm-raid.c +++ b/drivers/md/dm-raid.c @@ -3238,7 +3238,7 @@ static int raid_map(struct dm_target *ti, struct bio *bio) if (unlikely(bio_end_sector(bio) > mddev->array_sectors)) return DM_MAPIO_REQUEUE; - mddev->pers->make_request(mddev, bio); + md_handle_request(mddev, bio); return DM_MAPIO_SUBMITTED; } @@ -3297,11 +3297,10 @@ static const char *__raid_dev_status(struct raid_set *rs, struct md_rdev *rdev, static sector_t rs_get_progress(struct raid_set *rs, sector_t resync_max_sectors, bool *array_in_sync) { - sector_t r, recovery_cp, curr_resync_completed; + sector_t r, curr_resync_completed; struct mddev *mddev = &rs->md; curr_resync_completed = mddev->curr_resync_completed ?: mddev->recovery_cp; - recovery_cp = mddev->recovery_cp; *array_in_sync = false; if (rs_is_raid0(rs)) { @@ -3330,9 +3329,11 @@ static sector_t rs_get_progress(struct raid_set *rs, } else if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery)) r = curr_resync_completed; else - r = recovery_cp; + r = mddev->recovery_cp; - if (r == MaxSector) { + if ((r == MaxSector) || + (test_bit(MD_RECOVERY_DONE, &mddev->recovery) && + (mddev->curr_resync_completed == resync_max_sectors))) { /* * Sync complete. */ @@ -3892,7 +3893,7 @@ static void raid_resume(struct dm_target *ti) static struct target_type raid_target = { .name = "raid", - .version = {1, 12, 1}, + .version = {1, 13, 0}, .module = THIS_MODULE, .ctr = raid_ctr, .dtr = raid_dtr, diff --git a/drivers/md/dm-rq.c b/drivers/md/dm-rq.c index c6ebc5b1e00e..eadfcfd106ff 100644 --- a/drivers/md/dm-rq.c +++ b/drivers/md/dm-rq.c @@ -117,9 +117,9 @@ static void end_clone_bio(struct bio *clone) struct dm_rq_clone_bio_info *info = container_of(clone, struct dm_rq_clone_bio_info, clone); struct dm_rq_target_io *tio = info->tio; - struct bio *bio = info->orig; unsigned int nr_bytes = info->orig->bi_iter.bi_size; blk_status_t error = clone->bi_status; + bool is_last = !clone->bi_next; bio_put(clone); @@ -137,28 +137,23 @@ static void end_clone_bio(struct bio *clone) * when the request is completed. */ tio->error = error; - return; + goto exit; } /* * I/O for the bio successfully completed. * Notice the data completion to the upper layer. */ - - /* - * bios are processed from the head of the list. - * So the completing bio should always be rq->bio. - * If it's not, something wrong is happening. - */ - if (tio->orig->bio != bio) - DMERR("bio completion is going in the middle of the request"); + tio->completed += nr_bytes; /* * Update the original request. * Do not use blk_end_request() here, because it may complete * the original request before the clone, and break the ordering. */ - blk_update_request(tio->orig, BLK_STS_OK, nr_bytes); + if (is_last) + exit: + blk_update_request(tio->orig, BLK_STS_OK, tio->completed); } static struct dm_rq_target_io *tio_from_request(struct request *rq) @@ -237,14 +232,14 @@ static void dm_end_request(struct request *clone, blk_status_t error) /* * Requeue the original request of a clone. */ -static void dm_old_requeue_request(struct request *rq) +static void dm_old_requeue_request(struct request *rq, unsigned long delay_ms) { struct request_queue *q = rq->q; unsigned long flags; spin_lock_irqsave(q->queue_lock, flags); blk_requeue_request(q, rq); - blk_run_queue_async(q); + blk_delay_queue(q, delay_ms); spin_unlock_irqrestore(q->queue_lock, flags); } @@ -270,6 +265,7 @@ static void dm_requeue_original_request(struct dm_rq_target_io *tio, bool delay_ struct mapped_device *md = tio->md; struct request *rq = tio->orig; int rw = rq_data_dir(rq); + unsigned long delay_ms = delay_requeue ? 100 : 0; rq_end_stats(md, rq); if (tio->clone) { @@ -278,9 +274,9 @@ static void dm_requeue_original_request(struct dm_rq_target_io *tio, bool delay_ } if (!rq->q->mq_ops) - dm_old_requeue_request(rq); + dm_old_requeue_request(rq, delay_ms); else - dm_mq_delay_requeue_request(rq, delay_requeue ? 100/*ms*/ : 0); + dm_mq_delay_requeue_request(rq, delay_ms); rq_completed(md, rw, false); } @@ -455,6 +451,7 @@ static void init_tio(struct dm_rq_target_io *tio, struct request *rq, tio->clone = NULL; tio->orig = rq; tio->error = 0; + tio->completed = 0; /* * Avoid initializing info for blk-mq; it passes * target-specific data through info.ptr diff --git a/drivers/md/dm-rq.h b/drivers/md/dm-rq.h index 9813922e4fe5..f43c45460aac 100644 --- a/drivers/md/dm-rq.h +++ b/drivers/md/dm-rq.h @@ -29,6 +29,7 @@ struct dm_rq_target_io { struct dm_stats_aux stats_aux; unsigned long duration_jiffies; unsigned n_sectors; + unsigned completed; }; /* diff --git a/drivers/md/dm-stats.c b/drivers/md/dm-stats.c index 6028d8247f58..a7868503d135 100644 --- a/drivers/md/dm-stats.c +++ b/drivers/md/dm-stats.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include <linux/errno.h> #include <linux/numa.h> #include <linux/slab.h> diff --git a/drivers/md/dm-stats.h b/drivers/md/dm-stats.h index f1c0956e3843..2ddfae678f32 100644 --- a/drivers/md/dm-stats.h +++ b/drivers/md/dm-stats.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef DM_STATS_H #define DM_STATS_H diff --git a/drivers/md/dm-stripe.c b/drivers/md/dm-stripe.c index ab50d7c4377f..b5e892149c54 100644 --- a/drivers/md/dm-stripe.c +++ b/drivers/md/dm-stripe.c @@ -351,25 +351,6 @@ static size_t stripe_dax_copy_from_iter(struct dm_target *ti, pgoff_t pgoff, return dax_copy_from_iter(dax_dev, pgoff, addr, bytes, i); } -static void stripe_dax_flush(struct dm_target *ti, pgoff_t pgoff, void *addr, - size_t size) -{ - sector_t dev_sector, sector = pgoff * PAGE_SECTORS; - struct stripe_c *sc = ti->private; - struct dax_device *dax_dev; - struct block_device *bdev; - uint32_t stripe; - - stripe_map_sector(sc, sector, &stripe, &dev_sector); - dev_sector += sc->stripe[stripe].physical_start; - dax_dev = sc->stripe[stripe].dev->dax_dev; - bdev = sc->stripe[stripe].dev->bdev; - - if (bdev_dax_pgoff(bdev, dev_sector, ALIGN(size, PAGE_SIZE), &pgoff)) - return; - dax_flush(dax_dev, pgoff, addr, size); -} - /* * Stripe status: * @@ -489,7 +470,6 @@ static struct target_type stripe_target = { .io_hints = stripe_io_hints, .direct_access = stripe_dax_direct_access, .dax_copy_from_iter = stripe_dax_copy_from_iter, - .dax_flush = stripe_dax_flush, }; int __init dm_stripe_init(void) diff --git a/drivers/md/dm-switch.c b/drivers/md/dm-switch.c index 2dcea4c56f37..4c8de1ff78ca 100644 --- a/drivers/md/dm-switch.c +++ b/drivers/md/dm-switch.c @@ -251,7 +251,7 @@ static void switch_dtr(struct dm_target *ti) */ static int switch_ctr(struct dm_target *ti, unsigned argc, char **argv) { - static struct dm_arg _args[] = { + static const struct dm_arg _args[] = { {1, (KMALLOC_MAX_SIZE - sizeof(struct switch_ctx)) / sizeof(struct switch_path), "Invalid number of paths"}, {1, UINT_MAX, "Invalid region size"}, {0, 0, "Invalid number of optional args"}, diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c index 28a4071cdf85..ef7b8f201f73 100644 --- a/drivers/md/dm-table.c +++ b/drivers/md/dm-table.c @@ -806,7 +806,8 @@ int dm_table_add_target(struct dm_table *t, const char *type, /* * Target argument parsing helpers. */ -static int validate_next_arg(struct dm_arg *arg, struct dm_arg_set *arg_set, +static int validate_next_arg(const struct dm_arg *arg, + struct dm_arg_set *arg_set, unsigned *value, char **error, unsigned grouped) { const char *arg_str = dm_shift_arg(arg_set); @@ -824,14 +825,14 @@ static int validate_next_arg(struct dm_arg *arg, struct dm_arg_set *arg_set, return 0; } -int dm_read_arg(struct dm_arg *arg, struct dm_arg_set *arg_set, +int dm_read_arg(const struct dm_arg *arg, struct dm_arg_set *arg_set, unsigned *value, char **error) { return validate_next_arg(arg, arg_set, value, error, 0); } EXPORT_SYMBOL(dm_read_arg); -int dm_read_arg_group(struct dm_arg *arg, struct dm_arg_set *arg_set, +int dm_read_arg_group(const struct dm_arg *arg, struct dm_arg_set *arg_set, unsigned *value, char **error) { return validate_next_arg(arg, arg_set, value, error, 1); diff --git a/drivers/md/dm-thin.c b/drivers/md/dm-thin.c index 69d88aee3055..1e25705209c2 100644 --- a/drivers/md/dm-thin.c +++ b/drivers/md/dm-thin.c @@ -3041,7 +3041,7 @@ static int parse_pool_features(struct dm_arg_set *as, struct pool_features *pf, unsigned argc; const char *arg_name; - static struct dm_arg _args[] = { + static const struct dm_arg _args[] = { {0, 4, "Invalid number of pool feature arguments"}, }; diff --git a/drivers/md/dm-verity-target.c b/drivers/md/dm-verity-target.c index 1c5b6185c79d..bda3caca23ca 100644 --- a/drivers/md/dm-verity-target.c +++ b/drivers/md/dm-verity-target.c @@ -839,7 +839,7 @@ static int verity_parse_opt_args(struct dm_arg_set *as, struct dm_verity *v) struct dm_target *ti = v->ti; const char *arg_name; - static struct dm_arg _args[] = { + static const struct dm_arg _args[] = { {0, DM_VERITY_OPTS_MAX, "Invalid number of feature args"}, }; diff --git a/drivers/md/dm.c b/drivers/md/dm.c index 04ae795e8a5f..4be85324f44d 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -52,6 +52,12 @@ static struct workqueue_struct *deferred_remove_workqueue; atomic_t dm_global_event_nr = ATOMIC_INIT(0); DECLARE_WAIT_QUEUE_HEAD(dm_global_eventq); +void dm_issue_global_event(void) +{ + atomic_inc(&dm_global_event_nr); + wake_up(&dm_global_eventq); +} + /* * One of these is allocated per bio. */ @@ -987,24 +993,6 @@ static size_t dm_dax_copy_from_iter(struct dax_device *dax_dev, pgoff_t pgoff, return ret; } -static void dm_dax_flush(struct dax_device *dax_dev, pgoff_t pgoff, void *addr, - size_t size) -{ - struct mapped_device *md = dax_get_private(dax_dev); - sector_t sector = pgoff * PAGE_SECTORS; - struct dm_target *ti; - int srcu_idx; - - ti = dm_dax_get_live_target(md, sector, &srcu_idx); - - if (!ti) - goto out; - if (ti->type->dax_flush) - ti->type->dax_flush(ti, pgoff, addr, size); - out: - dm_put_live_table(md, srcu_idx); -} - /* * A target may call dm_accept_partial_bio only from the map routine. It is * allowed for all bio types except REQ_PREFLUSH. @@ -1883,9 +1871,8 @@ static void event_callback(void *context) dm_send_uevents(&uevents, &disk_to_dev(md->disk)->kobj); atomic_inc(&md->event_nr); - atomic_inc(&dm_global_event_nr); wake_up(&md->eventq); - wake_up(&dm_global_eventq); + dm_issue_global_event(); } /* @@ -2301,6 +2288,7 @@ struct dm_table *dm_swap_table(struct mapped_device *md, struct dm_table *table) } map = __bind(md, table, &limits); + dm_issue_global_event(); out: mutex_unlock(&md->suspend_lock); @@ -2992,7 +2980,6 @@ static const struct block_device_operations dm_blk_dops = { static const struct dax_operations dm_dax_ops = { .direct_access = dm_dax_direct_access, .copy_from_iter = dm_dax_copy_from_iter, - .flush = dm_dax_flush, }; /* diff --git a/drivers/md/linear.h b/drivers/md/linear.h index 8d392e6098b3..8381d651d4ed 100644 --- a/drivers/md/linear.h +++ b/drivers/md/linear.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINEAR_H #define _LINEAR_H diff --git a/drivers/md/md-cluster.h b/drivers/md/md-cluster.h index 274016177983..c0240708f443 100644 --- a/drivers/md/md-cluster.h +++ b/drivers/md/md-cluster.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _MD_CLUSTER_H diff --git a/drivers/md/md.c b/drivers/md/md.c index 08fcaebc61bd..0ff1bbf6c90e 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -266,6 +266,37 @@ static DEFINE_SPINLOCK(all_mddevs_lock); * call has finished, the bio has been linked into some internal structure * and so is visible to ->quiesce(), so we don't need the refcount any more. */ +void md_handle_request(struct mddev *mddev, struct bio *bio) +{ +check_suspended: + rcu_read_lock(); + if (mddev->suspended) { + DEFINE_WAIT(__wait); + for (;;) { + prepare_to_wait(&mddev->sb_wait, &__wait, + TASK_UNINTERRUPTIBLE); + if (!mddev->suspended) + break; + rcu_read_unlock(); + schedule(); + rcu_read_lock(); + } + finish_wait(&mddev->sb_wait, &__wait); + } + atomic_inc(&mddev->active_io); + rcu_read_unlock(); + + if (!mddev->pers->make_request(mddev, bio)) { + atomic_dec(&mddev->active_io); + wake_up(&mddev->sb_wait); + goto check_suspended; + } + + if (atomic_dec_and_test(&mddev->active_io) && mddev->suspended) + wake_up(&mddev->sb_wait); +} +EXPORT_SYMBOL(md_handle_request); + static blk_qc_t md_make_request(struct request_queue *q, struct bio *bio) { const int rw = bio_data_dir(bio); @@ -285,23 +316,6 @@ static blk_qc_t md_make_request(struct request_queue *q, struct bio *bio) bio_endio(bio); return BLK_QC_T_NONE; } -check_suspended: - rcu_read_lock(); - if (mddev->suspended) { - DEFINE_WAIT(__wait); - for (;;) { - prepare_to_wait(&mddev->sb_wait, &__wait, - TASK_UNINTERRUPTIBLE); - if (!mddev->suspended) - break; - rcu_read_unlock(); - schedule(); - rcu_read_lock(); - } - finish_wait(&mddev->sb_wait, &__wait); - } - atomic_inc(&mddev->active_io); - rcu_read_unlock(); /* * save the sectors now since our bio can @@ -310,20 +324,14 @@ check_suspended: sectors = bio_sectors(bio); /* bio could be mergeable after passing to underlayer */ bio->bi_opf &= ~REQ_NOMERGE; - if (!mddev->pers->make_request(mddev, bio)) { - atomic_dec(&mddev->active_io); - wake_up(&mddev->sb_wait); - goto check_suspended; - } + + md_handle_request(mddev, bio); cpu = part_stat_lock(); part_stat_inc(cpu, &mddev->gendisk->part0, ios[rw]); part_stat_add(cpu, &mddev->gendisk->part0, sectors[rw], sectors); part_stat_unlock(); - if (atomic_dec_and_test(&mddev->active_io) && mddev->suspended) - wake_up(&mddev->sb_wait); - return BLK_QC_T_NONE; } @@ -439,16 +447,22 @@ static void md_submit_flush_data(struct work_struct *ws) struct mddev *mddev = container_of(ws, struct mddev, flush_work); struct bio *bio = mddev->flush_bio; + /* + * must reset flush_bio before calling into md_handle_request to avoid a + * deadlock, because other bios passed md_handle_request suspend check + * could wait for this and below md_handle_request could wait for those + * bios because of suspend check + */ + mddev->flush_bio = NULL; + wake_up(&mddev->sb_wait); + if (bio->bi_iter.bi_size == 0) /* an empty barrier - all done */ bio_endio(bio); else { bio->bi_opf &= ~REQ_PREFLUSH; - mddev->pers->make_request(mddev, bio); + md_handle_request(mddev, bio); } - - mddev->flush_bio = NULL; - wake_up(&mddev->sb_wait); } void md_flush_request(struct mddev *mddev, struct bio *bio) diff --git a/drivers/md/md.h b/drivers/md/md.h index 561d22b9a9a8..d8287d3cd1bf 100644 --- a/drivers/md/md.h +++ b/drivers/md/md.h @@ -692,6 +692,7 @@ extern void md_stop_writes(struct mddev *mddev); extern int md_rdev_init(struct md_rdev *rdev); extern void md_rdev_clear(struct md_rdev *rdev); +extern void md_handle_request(struct mddev *mddev, struct bio *bio); extern void mddev_suspend(struct mddev *mddev); extern void mddev_resume(struct mddev *mddev); extern struct bio *bio_alloc_mddev(gfp_t gfp_mask, int nr_iovecs, diff --git a/drivers/md/multipath.h b/drivers/md/multipath.h index 717c60f62898..0adb941f485a 100644 --- a/drivers/md/multipath.h +++ b/drivers/md/multipath.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _MULTIPATH_H #define _MULTIPATH_H diff --git a/drivers/md/persistent-data/Makefile b/drivers/md/persistent-data/Makefile index ff528792c358..66be7c66479a 100644 --- a/drivers/md/persistent-data/Makefile +++ b/drivers/md/persistent-data/Makefile @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0 obj-$(CONFIG_DM_PERSISTENT_DATA) += dm-persistent-data.o dm-persistent-data-objs := \ dm-array.o \ diff --git a/drivers/md/raid0.h b/drivers/md/raid0.h index 7127a623f5da..540e65d92642 100644 --- a/drivers/md/raid0.h +++ b/drivers/md/raid0.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _RAID0_H #define _RAID0_H diff --git a/drivers/md/raid1-10.c b/drivers/md/raid1-10.c index 9f2670b45f31..400001b815db 100644 --- a/drivers/md/raid1-10.c +++ b/drivers/md/raid1-10.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* Maximum size of each resync request */ #define RESYNC_BLOCK_SIZE (64*1024) #define RESYNC_PAGES ((RESYNC_BLOCK_SIZE + PAGE_SIZE-1) / PAGE_SIZE) diff --git a/drivers/md/raid1.h b/drivers/md/raid1.h index c8894ef1e9d2..c7294e7557e0 100644 --- a/drivers/md/raid1.h +++ b/drivers/md/raid1.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _RAID1_H #define _RAID1_H diff --git a/drivers/md/raid10.h b/drivers/md/raid10.h index 735ce1a3d260..abceccab6671 100644 --- a/drivers/md/raid10.h +++ b/drivers/md/raid10.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _RAID10_H #define _RAID10_H diff --git a/drivers/md/raid5-log.h b/drivers/md/raid5-log.h index 328d67aedda4..7f9ad5f7cda0 100644 --- a/drivers/md/raid5-log.h +++ b/drivers/md/raid5-log.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _RAID5_LOG_H #define _RAID5_LOG_H diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index 4188a4881148..928e24a07133 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -811,6 +811,14 @@ static void stripe_add_to_batch_list(struct r5conf *conf, struct stripe_head *sh spin_unlock(&head->batch_head->batch_lock); goto unlock_out; } + /* + * We must assign batch_head of this stripe within the + * batch_lock, otherwise clear_batch_ready of batch head + * stripe could clear BATCH_READY bit of this stripe and + * this stripe->batch_head doesn't get assigned, which + * could confuse clear_batch_ready for this stripe + */ + sh->batch_head = head->batch_head; /* * at this point, head's BATCH_READY could be cleared, but we @@ -818,8 +826,6 @@ static void stripe_add_to_batch_list(struct r5conf *conf, struct stripe_head *sh */ list_add(&sh->batch_list, &head->batch_list); spin_unlock(&head->batch_head->batch_lock); - - sh->batch_head = head->batch_head; } else { head->batch_head = head; sh->batch_head = head->batch_head; @@ -4599,7 +4605,8 @@ static void break_stripe_batch_list(struct stripe_head *head_sh, set_mask_bits(&sh->state, ~(STRIPE_EXPAND_SYNC_FLAGS | (1 << STRIPE_PREREAD_ACTIVE) | - (1 << STRIPE_DEGRADED)), + (1 << STRIPE_DEGRADED) | + (1 << STRIPE_ON_UNPLUG_LIST)), head_sh->state & (1 << STRIPE_INSYNC)); sh->check_state = head_sh->check_state; @@ -6568,14 +6575,17 @@ static ssize_t raid5_store_group_thread_cnt(struct mddev *mddev, const char *page, size_t len) { struct r5conf *conf; - unsigned long new; + unsigned int new; int err; struct r5worker_group *new_groups, *old_groups; int group_cnt, worker_cnt_per_group; if (len >= PAGE_SIZE) return -EINVAL; - if (kstrtoul(page, 10, &new)) + if (kstrtouint(page, 10, &new)) + return -EINVAL; + /* 8192 should be big enough */ + if (new > 8192) return -EINVAL; err = mddev_lock(mddev); diff --git a/drivers/md/raid5.h b/drivers/md/raid5.h index f6536399677a..2e6123825095 100644 --- a/drivers/md/raid5.h +++ b/drivers/md/raid5.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _RAID5_H #define _RAID5_H |
