diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2019-11-25 11:15:41 -0800 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2019-11-25 11:15:41 -0800 |
commit | 2d53943090c336c9d298638bad292be349e1b9c4 (patch) | |
tree | 18fc9bbc1ff13fe031a922cf2efc22a903257caf | |
parent | ff6814b078e33a4d26fee9ea80779c81a6744cd8 (diff) | |
parent | 00b89892c869f34528deca957b10d1468c4e8b38 (diff) | |
download | linux-2d53943090c336c9d298638bad292be349e1b9c4.tar.gz linux-2d53943090c336c9d298638bad292be349e1b9c4.tar.bz2 linux-2d53943090c336c9d298638bad292be349e1b9c4.zip |
Merge tag 'for-5.5/drivers-20191121' of git://git.kernel.dk/linux-block
Pull block driver updates from Jens Axboe:
"Here are the main block driver updates for 5.5. Nothing major in here,
mostly just fixes. This contains:
- a set of bcache changes via Coly
- MD changes from Song
- loop unmap write-zeroes fix (Darrick)
- spelling fixes (Geert)
- zoned additions cleanups to null_blk/dm (Ajay)
- allow null_blk online submit queue changes (Bart)
- NVMe changes via Keith, nothing major here either"
* tag 'for-5.5/drivers-20191121' of git://git.kernel.dk/linux-block: (56 commits)
Revert "bcache: fix fifo index swapping condition in journal_pin_cmp()"
drivers/md/raid5-ppl.c: use the new spelling of RWH_WRITE_LIFE_NOT_SET
drivers/md/raid5.c: use the new spelling of RWH_WRITE_LIFE_NOT_SET
bcache: don't export symbols
bcache: remove the extra cflags for request.o
bcache: at least try to shrink 1 node in bch_mca_scan()
bcache: add idle_max_writeback_rate sysfs interface
bcache: add code comments in bch_btree_leaf_dirty()
bcache: fix deadlock in bcache_allocator
bcache: add code comment bch_keylist_pop() and bch_keylist_pop_front()
bcache: deleted code comments for dead code in bch_data_insert_keys()
bcache: add more accurate error messages in read_super()
bcache: fix static checker warning in bcache_device_free()
bcache: fix a lost wake-up problem caused by mca_cannibalize_lock
bcache: fix fifo index swapping condition in journal_pin_cmp()
md/raid10: prevent access of uninitialized resync_pages offset
md: avoid invalid memory access for array sb->dev_roles
md/raid1: avoid soft lockup under high load
null_blk: add zone open, close, and finish support
dm: add zone open, close and finish support
...
48 files changed, 783 insertions, 400 deletions
diff --git a/drivers/block/loop.c b/drivers/block/loop.c index f6f77eaa7217..ef6e251857c8 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -417,18 +417,20 @@ out_free_page: return ret; } -static int lo_discard(struct loop_device *lo, struct request *rq, loff_t pos) +static int lo_fallocate(struct loop_device *lo, struct request *rq, loff_t pos, + int mode) { /* - * We use punch hole to reclaim the free space used by the - * image a.k.a. discard. However we do not support discard if - * encryption is enabled, because it may give an attacker - * useful information. + * We use fallocate to manipulate the space mappings used by the image + * a.k.a. discard/zerorange. However we do not support this if + * encryption is enabled, because it may give an attacker useful + * information. */ struct file *file = lo->lo_backing_file; - int mode = FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE; int ret; + mode |= FALLOC_FL_KEEP_SIZE; + if ((!file->f_op->fallocate) || lo->lo_encrypt_key_size) { ret = -EOPNOTSUPP; goto out; @@ -596,9 +598,17 @@ static int do_req_filebacked(struct loop_device *lo, struct request *rq) switch (req_op(rq)) { case REQ_OP_FLUSH: return lo_req_flush(lo, rq); - case REQ_OP_DISCARD: case REQ_OP_WRITE_ZEROES: - return lo_discard(lo, rq, pos); + /* + * If the caller doesn't want deallocation, call zeroout to + * write zeroes the range. Otherwise, punch them out. + */ + return lo_fallocate(lo, rq, pos, + (rq->cmd_flags & REQ_NOUNMAP) ? + FALLOC_FL_ZERO_RANGE : + FALLOC_FL_PUNCH_HOLE); + case REQ_OP_DISCARD: + return lo_fallocate(lo, rq, pos, FALLOC_FL_PUNCH_HOLE); case REQ_OP_WRITE: if (lo->transfer) return lo_write_transfer(lo, rq, pos); diff --git a/drivers/block/mtip32xx/mtip32xx.c b/drivers/block/mtip32xx/mtip32xx.c index 964f78cfffa0..f6bafa9a68b9 100644 --- a/drivers/block/mtip32xx/mtip32xx.c +++ b/drivers/block/mtip32xx/mtip32xx.c @@ -129,7 +129,7 @@ struct mtip_compat_ide_task_request_s { /* * This function check_for_surprise_removal is called * while card is removed from the system and it will - * read the vendor id from the configration space + * read the vendor id from the configuration space * * @pdev Pointer to the pci_dev structure. * diff --git a/drivers/block/null_blk.h b/drivers/block/null_blk.h index a235c45e22a7..93c2a3d403da 100644 --- a/drivers/block/null_blk.h +++ b/drivers/block/null_blk.h @@ -96,6 +96,8 @@ int null_zone_report(struct gendisk *disk, sector_t sector, blk_status_t null_handle_zoned(struct nullb_cmd *cmd, enum req_opf op, sector_t sector, sector_t nr_sectors); +size_t null_zone_valid_read_len(struct nullb *nullb, + sector_t sector, unsigned int len); #else static inline int null_zone_init(struct nullb_device *dev) { @@ -115,5 +117,11 @@ static inline blk_status_t null_handle_zoned(struct nullb_cmd *cmd, { return BLK_STS_NOTSUPP; } +static inline size_t null_zone_valid_read_len(struct nullb *nullb, + sector_t sector, + unsigned int len) +{ + return len; +} #endif /* CONFIG_BLK_DEV_ZONED */ #endif /* __NULL_BLK_H */ diff --git a/drivers/block/null_blk_main.c b/drivers/block/null_blk_main.c index 0e7da5015ccd..ea7a4d6b7848 100644 --- a/drivers/block/null_blk_main.c +++ b/drivers/block/null_blk_main.c @@ -227,7 +227,7 @@ static ssize_t nullb_device_uint_attr_store(unsigned int *val, int result; result = kstrtouint(page, 0, &tmp); - if (result) + if (result < 0) return result; *val = tmp; @@ -241,7 +241,7 @@ static ssize_t nullb_device_ulong_attr_store(unsigned long *val, unsigned long tmp; result = kstrtoul(page, 0, &tmp); - if (result) + if (result < 0) return result; *val = tmp; @@ -255,7 +255,7 @@ static ssize_t nullb_device_bool_attr_store(bool *val, const char *page, int result; result = kstrtobool(page, &tmp); - if (result) + if (result < 0) return result; *val = tmp; @@ -263,7 +263,7 @@ static ssize_t nullb_device_bool_attr_store(bool *val, const char *page, } /* The following macro should only be used with TYPE = {uint, ulong, bool}. */ -#define NULLB_DEVICE_ATTR(NAME, TYPE) \ +#define NULLB_DEVICE_ATTR(NAME, TYPE, APPLY) \ static ssize_t \ nullb_device_##NAME##_show(struct config_item *item, char *page) \ { \ @@ -274,31 +274,57 @@ static ssize_t \ nullb_device_##NAME##_store(struct config_item *item, const char *page, \ size_t count) \ { \ - if (test_bit(NULLB_DEV_FL_CONFIGURED, &to_nullb_device(item)->flags)) \ - return -EBUSY; \ - return nullb_device_##TYPE##_attr_store( \ - &to_nullb_device(item)->NAME, page, count); \ + int (*apply_fn)(struct nullb_device *dev, TYPE new_value) = APPLY; \ + struct nullb_device *dev = to_nullb_device(item); \ + TYPE new_value; \ + int ret; \ + \ + ret = nullb_device_##TYPE##_attr_store(&new_value, page, count); \ + if (ret < 0) \ + return ret; \ + if (apply_fn) \ + ret = apply_fn(dev, new_value); \ + else if (test_bit(NULLB_DEV_FL_CONFIGURED, &dev->flags)) \ + ret = -EBUSY; \ + if (ret < 0) \ + return ret; \ + dev->NAME = new_value; \ + return count; \ } \ CONFIGFS_ATTR(nullb_device_, NAME); -NULLB_DEVICE_ATTR(size, ulong); -NULLB_DEVICE_ATTR(completion_nsec, ulong); -NULLB_DEVICE_ATTR(submit_queues, uint); -NULLB_DEVICE_ATTR(home_node, uint); -NULLB_DEVICE_ATTR(queue_mode, uint); -NULLB_DEVICE_ATTR(blocksize, uint); -NULLB_DEVICE_ATTR(irqmode, uint); -NULLB_DEVICE_ATTR(hw_queue_depth, uint); -NULLB_DEVICE_ATTR(index, uint); -NULLB_DEVICE_ATTR(blocking, bool); -NULLB_DEVICE_ATTR(use_per_node_hctx, bool); -NULLB_DEVICE_ATTR(memory_backed, bool); -NULLB_DEVICE_ATTR(discard, bool); -NULLB_DEVICE_ATTR(mbps, uint); -NULLB_DEVICE_ATTR(cache_size, ulong); -NULLB_DEVICE_ATTR(zoned, bool); -NULLB_DEVICE_ATTR(zone_size, ulong); -NULLB_DEVICE_ATTR(zone_nr_conv, uint); +static int nullb_apply_submit_queues(struct nullb_device *dev, + unsigned int submit_queues) +{ + struct nullb *nullb = dev->nullb; + struct blk_mq_tag_set *set; + + if (!nullb) + return 0; + + set = nullb->tag_set; + blk_mq_update_nr_hw_queues(set, submit_queues); + return set->nr_hw_queues == submit_queues ? 0 : -ENOMEM; +} + +NULLB_DEVICE_ATTR(size, ulong, NULL); +NULLB_DEVICE_ATTR(completion_nsec, ulong, NULL); +NULLB_DEVICE_ATTR(submit_queues, uint, nullb_apply_submit_queues); +NULLB_DEVICE_ATTR(home_node, uint, NULL); +NULLB_DEVICE_ATTR(queue_mode, uint, NULL); +NULLB_DEVICE_ATTR(blocksize, uint, NULL); +NULLB_DEVICE_ATTR(irqmode, uint, NULL); +NULLB_DEVICE_ATTR(hw_queue_depth, uint, NULL); +NULLB_DEVICE_ATTR(index, uint, NULL); +NULLB_DEVICE_ATTR(blocking, bool, NULL); +NULLB_DEVICE_ATTR(use_per_node_hctx, bool, NULL); +NULLB_DEVICE_ATTR(memory_backed, bool, NULL); +NULLB_DEVICE_ATTR(discard, bool, NULL); +NULLB_DEVICE_ATTR(mbps, uint, NULL); +NULLB_DEVICE_ATTR(cache_size, ulong, NULL); +NULLB_DEVICE_ATTR(zoned, bool, NULL); +NULLB_DEVICE_ATTR(zone_size, ulong, NULL); +NULLB_DEVICE_ATTR(zone_nr_conv, uint, NULL); static ssize_t nullb_device_power_show(struct config_item *item, char *page) { @@ -996,6 +1022,16 @@ next: return 0; } +static void nullb_fill_pattern(struct nullb *nullb, struct page *page, + unsigned int len, unsigned int off) +{ + void *dst; + + dst = kmap_atomic(page); + memset(dst + off, 0xFF, len); + kunmap_atomic(dst); +} + static void null_handle_discard(struct nullb *nullb, sector_t sector, size_t n) { size_t temp; @@ -1036,10 +1072,24 @@ static int null_transfer(struct nullb *nullb, struct page *page, unsigned int len, unsigned int off, bool is_write, sector_t sector, bool is_fua) { + struct nullb_device *dev = nullb->dev; + unsigned int valid_len = len; int err = 0; if (!is_write) { - err = copy_from_nullb(nullb, page, off, sector, len); + if (dev->zoned) + valid_len = null_zone_valid_read_len(nullb, + sector, len); + + if (valid_len) { + err = copy_from_nullb(nullb, page, off, + sector, valid_len); + off += valid_len; + len -= valid_len; + } + + if (len) + nullb_fill_pattern(nullb, page, len, off); flush_dcache_page(page); } else { flush_dcache_page(page); diff --git a/drivers/block/null_blk_zoned.c b/drivers/block/null_blk_zoned.c index 3d7fdea872f8..02f41a3bc4cb 100644 --- a/drivers/block/null_blk_zoned.c +++ b/drivers/block/null_blk_zoned.c @@ -84,6 +84,24 @@ int null_zone_report(struct gendisk *disk, sector_t sector, return 0; } +size_t null_zone_valid_read_len(struct nullb *nullb, + sector_t sector, unsigned int len) +{ + struct nullb_device *dev = nullb->dev; + struct blk_zone *zone = &dev->zones[null_zone_no(dev, sector)]; + unsigned int nr_sectors = len >> SECTOR_SHIFT; + + /* Read must be below the write pointer position */ + if (zone->type == BLK_ZONE_TYPE_CONVENTIONAL || + sector + nr_sectors <= zone->wp) + return len; + + if (sector > zone->wp) + return 0; + + return (zone->wp - sector) << SECTOR_SHIFT; +} + static blk_status_t null_zone_write(struct nullb_cmd *cmd, sector_t sector, unsigned int nr_sectors) { @@ -118,14 +136,14 @@ static blk_status_t null_zone_write(struct nullb_cmd *cmd, sector_t sector, return BLK_STS_OK; } -static blk_status_t null_zone_reset(struct nullb_cmd *cmd, sector_t sector) +static blk_status_t null_zone_mgmt(struct nullb_cmd *cmd, enum req_opf op, + sector_t sector) { struct nullb_device *dev = cmd->nq->dev; - unsigned int zno = null_zone_no(dev, sector); - struct blk_zone *zone = &dev->zones[zno]; + struct blk_zone *zone = &dev->zones[null_zone_no(dev, sector)]; size_t i; - switch (req_op(cmd->rq)) { + switch (op) { case REQ_OP_ZONE_RESET_ALL: for (i = 0; i < dev->nr_zones; i++) { if (zone[i].type == BLK_ZONE_TYPE_CONVENTIONAL) @@ -141,6 +159,29 @@ static blk_status_t null_zone_reset(struct nullb_cmd *cmd, sector_t sector) zone->cond = BLK_ZONE_COND_EMPTY; zone->wp = zone->start; break; + case REQ_OP_ZONE_OPEN: + if (zone->type == BLK_ZONE_TYPE_CONVENTIONAL) + return BLK_STS_IOERR; + if (zone->cond == BLK_ZONE_COND_FULL) + return BLK_STS_IOERR; + + zone->cond = BLK_ZONE_COND_EXP_OPEN; + break; + case REQ_OP_ZONE_CLOSE: + if (zone->type == BLK_ZONE_TYPE_CONVENTIONAL) + return BLK_STS_IOERR; + if (zone->cond == BLK_ZONE_COND_FULL) + return BLK_STS_IOERR; + + zone->cond = BLK_ZONE_COND_CLOSED; + break; + case REQ_OP_ZONE_FINISH: + if (zone->type == BLK_ZONE_TYPE_CONVENTIONAL) + return BLK_STS_IOERR; + + zone->cond = BLK_ZONE_COND_FULL; + zone->wp = zone->start + zone->len; + break; default: return BLK_STS_NOTSUPP; } @@ -155,7 +196,10 @@ blk_status_t null_handle_zoned(struct nullb_cmd *cmd, enum req_opf op, return null_zone_write(cmd, sector, nr_sectors); case REQ_OP_ZONE_RESET: case REQ_OP_ZONE_RESET_ALL: - return null_zone_reset(cmd, sector); + case REQ_OP_ZONE_OPEN: + case REQ_OP_ZONE_CLOSE: + case REQ_OP_ZONE_FINISH: + return null_zone_mgmt(cmd, op, sector); default: return BLK_STS_OK; } diff --git a/drivers/md/bcache/Makefile b/drivers/md/bcache/Makefile index d26b35195825..fd714628da6a 100644 --- a/drivers/md/bcache/Makefile +++ b/drivers/md/bcache/Makefile @@ -5,5 +5,3 @@ obj-$(CONFIG_BCACHE) += bcache.o bcache-y := alloc.o bset.o btree.o closure.o debug.o extents.o\ io.o journal.o movinggc.o request.o stats.o super.o sysfs.o trace.o\ util.o writeback.o - -CFLAGS_request.o += -Iblock diff --git a/drivers/md/bcache/alloc.c b/drivers/md/bcache/alloc.c index 6f776823b9ba..a1df0d95151c 100644 --- a/drivers/md/bcache/alloc.c +++ b/drivers/md/bcache/alloc.c @@ -377,7 +377,10 @@ retry_invalidate: if (!fifo_full(&ca->free_inc)) goto retry_invalidate; - bch_prio_write(ca); + if (bch_prio_write(ca, false) < 0) { + ca->invalidate_needs_gc = 1; + wake_up_gc(ca->set); + } } } out: diff --git a/drivers/md/bcache/bcache.h b/drivers/md/bcache/bcache.h index 013e35a9e317..9198c1b480d9 100644 --- a/drivers/md/bcache/bcache.h +++ b/drivers/md/bcache/bcache.h @@ -582,6 +582,7 @@ struct cache_set { */ wait_queue_head_t btree_cache_wait; struct task_struct *btree_cache_alloc_lock; + spinlock_t btree_cannibalize_lock; /* * When we free a btree node, we increment the gen of the bucket the @@ -723,6 +724,7 @@ struct cache_set { unsigned int gc_always_rewrite:1; unsigned int shrinker_disabled:1; unsigned int copy_gc_enabled:1; + unsigned int idle_max_writeback_rate_enabled:1; #define BUCKET_HASH_BITS 12 struct hlist_head bucket_hash[1 << BUCKET_HASH_BITS]; @@ -977,7 +979,7 @@ bool bch_cached_dev_error(struct cached_dev *dc); __printf(2, 3) bool bch_cache_set_error(struct cache_set *c, const char *fmt, ...); -void bch_prio_write(struct cache *ca); +int bch_prio_write(struct cache *ca, bool wait); void bch_write_bdev_super(struct cached_dev *dc, struct closure *parent); extern struct workqueue_struct *bcache_wq; diff --git a/drivers/md/bcache/bset.c b/drivers/md/bcache/bset.c index 08768796b543..cffcdc9feefb 100644 --- a/drivers/md/bcache/bset.c +++ b/drivers/md/bcache/bset.c @@ -155,6 +155,7 @@ int __bch_keylist_realloc(struct keylist *l, unsigned int u64s) return 0; } +/* Pop the top key of keylist by pointing l->top to its previous key */ struct bkey *bch_keylist_pop(struct keylist *l) { struct bkey *k = l->keys; @@ -168,6 +169,7 @@ struct bkey *bch_keylist_pop(struct keylist *l) return l->top = k; } +/* Pop the bottom key of keylist and update l->top_p */ void bch_keylist_pop_front(struct keylist *l) { l->top_p -= bkey_u64s(l->keys); @@ -309,7 +311,6 @@ void bch_btree_keys_free(struct btree_keys *b) t->tree = NULL; t->data = NULL; } -EXPORT_SYMBOL(bch_btree_keys_free); int bch_btree_keys_alloc(struct btree_keys *b, unsigned int page_order, @@ -342,7 +343,6 @@ err: bch_btree_keys_free(b); return -ENOMEM; } -EXPORT_SYMBOL(bch_btree_keys_alloc); void bch_btree_keys_init(struct btree_keys *b, const struct btree_keys_ops *ops, bool *expensive_debug_checks) @@ -361,7 +361,6 @@ void bch_btree_keys_init(struct btree_keys *b, const struct btree_keys_ops *ops, * any more. */ } -EXPORT_SYMBOL(bch_btree_keys_init); /* Binary tree stuff for auxiliary search trees */ @@ -678,7 +677,6 @@ void bch_bset_init_next(struct btree_keys *b, struct bset *i, uint64_t magic) bch_bset_build_unwritten_tree(b); } -EXPORT_SYMBOL(bch_bset_init_next); /* * Build auxiliary binary tree 'struct bset_tree *t', this tree is used to @@ -732,7 +730,6 @@ void bch_bset_build_written_tree(struct btree_keys *b) j = inorder_next(j, t->size)) make_bfloat(t, j); } -EXPORT_SYMBOL(bch_bset_build_written_tree); /* Insert */ @@ -780,7 +777,6 @@ fix_right: do { j = j * 2 + 1; } while (j < t->size); } -EXPORT_SYMBOL(bch_bset_fix_invalidated_key); static void bch_bset_fix_lookup_table(struct btree_keys *b, struct bset_tree *t, @@ -855,7 +851,6 @@ bool bch_bkey_try_merge(struct btree_keys *b, struct bkey *l, struct bkey *r) return b->ops->key_merge(b, l, r); } -EXPORT_SYMBOL(bch_bkey_try_merge); void bch_bset_insert(struct btree_keys *b, struct bkey *where, struct bkey *insert) @@ -875,7 +870,6 @@ void bch_bset_insert(struct btree_keys *b, struct bkey *where, bkey_copy(where, insert); bch_bset_fix_lookup_table(b, t, where); } -EXPORT_SYMBOL(bch_bset_insert); unsigned int bch_btree_insert_key(struct btree_keys *b, struct bkey *k, struct bkey *replace_key) @@ -931,7 +925,6 @@ copy: bkey_copy(m, k); merged: return status; } -EXPORT_SYMBOL(bch_btree_insert_key); /* Lookup */ @@ -1077,7 +1070,6 @@ struct bkey *__bch_bset_search(struct btree_keys *b, struct bset_tree *t, return i.l; } -EXPORT_SYMBOL(__bch_bset_search); /* Btree iterator */ @@ -1132,7 +1124,6 @@ struct bkey *bch_btree_iter_init(struct btree_keys *b, { return __bch_btree_iter_init(b, iter, search, b->set); } -EXPORT_SYMBOL(bch_btree_iter_init); static inline struct bkey *__bch_btree_iter_next(struct btree_iter *iter, btree_iter_cmp_fn *cmp) @@ -1165,7 +1156,6 @@ struct bkey *bch_btree_iter_next(struct btree_iter *iter) return __bch_btree_iter_next(iter, btree_iter_cmp); } -EXPORT_SYMBOL(bch_btree_iter_next); struct bkey *bch_btree_iter_next_filter(struct btree_iter *iter, struct btree_keys *b, ptr_filter_fn fn) @@ -1196,7 +1186,6 @@ int bch_bset_sort_state_init(struct bset_sort_state *state, return mempool_init_page_pool(&state->pool, 1, page_order); } -EXPORT_SYMBOL(bch_bset_sort_state_init); static void btree_mergesort(struct btree_keys *b, struct bset *out, struct btree_iter *iter, @@ -1313,7 +1302,6 @@ void bch_btree_sort_partial(struct btree_keys *b, unsigned int start, EBUG_ON(oldsize >= 0 && bch_count_data(b) != oldsize); } -EXPORT_SYMBOL(bch_btree_sort_partial); void bch_btree_sort_and_fix_extents(struct btree_keys *b, struct btree_iter *iter, @@ -1366,7 +1354,6 @@ void bch_btree_sort_lazy(struct btree_keys *b, struct bset_sort_state *state) out: bch_bset_build_written_tree(b); } -EXPORT_SYMBOL(bch_btree_sort_lazy); void bch_btree_keys_stats(struct btree_keys *b, struct bset_stats *stats) { diff --git a/drivers/md/bcache/btree.c b/drivers/md/bcache/btree.c index ba434d9ac720..14d6c33b0957 100644 --- a/drivers/md/bcache/btree.c +++ b/drivers/md/bcache/btree.c @@ -543,6 +543,11 @@ static void bch_btree_leaf_dirty(struct btree *b, atomic_t *journal_ref) set_btree_node_dirty(b); + /* + * w->journal is always the oldest journal pin of all bkeys + * in the leaf node, to make sure the oldest jset seq won't + * be increased before this btree node is flushed. + */ if (journal_ref) { if (w->journal && journal_pin_cmp(b->c, w->journal, journal_ref)) { @@ -723,6 +728,8 @@ static unsigned long bch_mca_scan(struct shrinker *shrink, * IO can always make forward progress: */ nr /= c->btree_pages; + if (nr == 0) + nr = 1; nr = min_t(unsigned long, nr, mca_can_free(c)); i = 0; @@ -884,15 +891,17 @@ out: static int mca_cannibalize_lock(struct cache_set *c, struct btree_op *op) { - struct task_struct *old; - - old = cmpxchg(&c->btree_cache_alloc_lock, NULL, current); - if (old && old != current) { + spin_lock(&c->btree_cannibalize_lock); + if (likely(c->btree_cache_alloc_lock == NULL)) { + c->btree_cache_alloc_lock = current; + } else if (c->btree_cache_alloc_lock != current) { if (op) prepare_to_wait(&c->btree_cache_wait, &op->wait, TASK_UNINTERRUPTIBLE); + spin_unlock(&c->btree_cannibalize_lock); return -EINTR; } + spin_unlock(&c->btree_cannibalize_lock); return 0; } @@ -927,10 +936,12 @@ static struct btree *mca_cannibalize(struct cache_set *c, struct btree_op *op, */ static void bch_cannibalize_unlock(struct cache_set *c) { + spin_lock(&c->btree_cannibalize_lock); if (c->btree_cache_alloc_lock == current) { c->btree_cache_alloc_lock = NULL; wake_up(&c->btree_cache_wait); } + spin_unlock(&c->btree_cannibalize_lock); } static struct btree *mca_alloc(struct cache_set *c, struct btree_op *op, diff --git a/drivers/md/bcache/closure.c b/drivers/md/bcache/closure.c index c12cd809ab19..0164a1fe94a9 100644 --- a/drivers/md/bcache/closure.c +++ b/drivers/md/bcache/closure.c @@ -45,7 +45,6 @@ void closure_sub(struct closure *cl, int v) { closure_put_after_sub(cl, atomic_sub_return(v, &cl->remaining)); } -EXPORT_SYMBOL(closure_sub); /* * closure_put - decrement a closure's refcount @@ -54,7 +53,6 @@ void closure_put(struct closure *cl) { closure_put_after_sub(cl, atomic_dec_return(&cl->remaining)); } -EXPORT_SYMBOL(closure_put); /* * closure_wake_up - wake up all closures on a wait list, without memory barrier @@ -76,7 +74,6 @@ void __closure_wake_up(struct closure_waitlist *wait_list) closure_sub(cl, CLOSURE_WAITING + 1); } } -EXPORT_SYMBOL(__closure_wake_up); /** * closure_wait - add a closure to a waitlist @@ -96,7 +93,6 @@ bool closure_wait(struct closure_waitlist *waitlist, struct closure *cl) return true; } -EXPORT_SYMBOL(closure_wait); struct closure_syncer { struct task_struct *task; @@ -131,7 +127,6 @@ void __sched __closure_sync(struct closure *cl) __set_current_state(TASK_RUNNING); } -EXPORT_SYMBOL(__closure_sync); #ifdef CONFIG_BCACHE_CLOSURES_DEBUG @@ -149,7 +144,6 @@ void closure_debug_create(struct closure *cl) list_add(&cl->all, &closure_list); spin_unlock_irqrestore(&closure_list_lock, flags); } -EXPORT_SYMBOL(closure_debug_create); void closure_debug_destroy(struct closure *cl) { @@ -162,7 +156,6 @@ void closure_debug_destroy(struct closure *cl) list_del(&cl->all); spin_unlock_irqrestore(&closure_list_lock, flags); } -EXPORT_SYMBOL(closure_debug_destroy); static struct dentry *closure_debug; diff --git a/drivers/md/bcache/request.c b/drivers/md/bcache/request.c index 41adcd1546f1..73478a91a342 100644 --- a/drivers/md/bcache/request.c +++ b/drivers/md/bcache/request.c @@ -62,18 +62,6 @@ static void bch_data_insert_keys(struct closure *cl) struct bkey *replace_key = op->replace ? &op->replace_key : NULL; int ret; - /* - * If we're looping, might already be waiting on - * another journal write - can't wait on more than one journal write at - * a time - * - * XXX: this looks wrong - */ -#if 0 - while (atomic_read(&s->cl.remaining) & CLOSURE_WAITING) - closure_sync(&s->cl); -#endif - if (!op->replace) journal_ref = bch_journal(op->c, &op->insert_keys, op->flush_journal ? cl : NULL); diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c index 20ed838e9413..77e9869345e7 100644 --- a/drivers/md/bcache/super.c +++ b/drivers/md/bcache/super.c @@ -92,10 +92,11 @@ static const char *read_super(struct cache_sb *sb, struct block_device *bdev, pr_debug("read sb version %llu, flags %llu, seq %llu, journal size %u", sb->version, sb->flags, sb->seq, sb->keys); - err = "Not a bcache superblock"; + err = "Not a bcache superblock (bad offset)"; if (sb->offset != SB_SECTOR) goto err; + err = "Not a bcache superblock (bad magic)"; if (memcmp(sb->magic, bcache_magic, 16)) goto err; @@ -529,12 +530,29 @@ static void prio_io(struct cache *ca, uint64_t bucket, int op, closure_sync(cl); } -void bch_prio_write(struct cache *ca) +int bch_prio_write(struct cache *ca, bool wait) { int i; struct bucket *b; struct closure cl; + pr_debug("free_prio=%zu, free_none=%zu, free_inc=%zu", + fifo_used(&ca->free[RESERVE_PRIO]), + fifo_used(&ca->free[RESERVE_NONE]), + fifo_used(&ca->free_inc)); + + /* + * Pre-check if there are enough free buckets. In the non-blocking + * scenario it's better to fail early rather than starting to allocate + * buckets and do a cleanup later in case of failure. + */ + if (!wait) { + size_t avail = fifo_used(&ca->free[RESERVE_PRIO]) + + fifo_used(&ca->free[RESERVE_NONE]); + if (prio_buckets(ca) > avail) + return -ENOMEM; + } + closure_init_stack(&cl); lockdep_assert_held(&ca->set->bucket_lock); @@ -544,9 +562,6 @@ void bch_prio_write(struct cache *ca) atomic_long_add(ca->sb.bucket_size * prio_buckets(ca), &ca->meta_sectors_written); - //pr_debug("free %zu, free_inc %zu, unused %zu", fifo_used(&ca->free), - // fifo_used(&ca->free_inc), fifo_used(&ca->unused)); - for (i = prio_buckets(ca) - 1; i >= 0; --i) { long bucket; struct prio_set *p = ca->disk_buckets; @@ -564,7 +579,7 @@ void bch_prio_write(struct cache *ca) p->magic = pset_magic(&ca->sb); p->csum = bch_crc64(&p->magic, bucket_bytes(ca) - 8); - bucket = bch_bucket_alloc(ca, RESERVE_PRIO, true); + bucket = bch_bucket_alloc(ca, RESERVE_PRIO, wait); BUG_ON(bucket == -1); mutex_unlock(&ca->set->bucket_lock); @@ -593,6 +608,7 @@ void bch_prio_write(struct cache *ca) ca->prio_last_buckets[i] = ca->prio_buckets[i]; } + return 0; } static void prio_read(struct cache *ca, uint64_t bucket) @@ -761,20 +777,28 @@ static inline int idx_to_first_minor(int idx) static void bcache_device_free(struct bcache_device *d) { + struct gendisk *disk = d->disk; + lockdep_assert_held(&bch_register_lock); - pr_info("%s stopped", d->disk->disk_name); + if (disk) + pr_info("%s stopped", disk->disk_name); + else + pr_err("bcache device (NULL gendisk) stopped"); if (d->c) bcache_device_detach(d); - if (d->disk && d->disk->flags & GENHD_FL_UP) - del_gendisk(d->disk); - if (d->disk && d->disk->queue) - blk_cleanup_queue(d->disk->queue); - if (d->disk) { + + if (disk) { + if (disk->flags & GENHD_FL_UP) + del_gendisk(disk); + + if (disk->queue) + blk_cleanup_queue(disk->queue); + ida_simple_remove(&bcache_device_idx, - first_minor_to_idx(d->disk->first_minor)); - put_disk(d->disk); + first_minor_to_idx(disk->first_minor)); + put_disk(disk); } bioset_exit(&d->bio_split); @@ -1769,6 +1793,7 @@ struct cache_set *bch_cache_set_alloc(struct cache_sb *sb) sema_init(&c->sb_write_mutex, 1); mutex_init(&c->bucket_lock); init_waitqueue_head(&c->btree_cache_wait); + spin_lock_init(&c->btree_cannibalize_lock); init_waitqueue_head(&c->bucket_wait); init_waitqueue_head(&c->gc_wait); sema_init(&c->uuid_write_mutex, 1); @@ -1809,6 +1834,7 @@ struct cache_set *bch_cache_set_alloc(struct cache_sb *sb) c->congested_read_threshold_us = 2000; c->congested_write_threshold_us = 20000; c->error_limit = DEFAULT_IO_ERROR_LIMIT; + c->idle_max_writeback_rate_enabled = 1; WARN_ON(test_and_clear_bit(CACHE_SET_IO_DISABLE, &c->flags)); return c; @@ -1954,7 +1980,7 @@ static int run_cache_set(struct cache_set *c) mutex_lock(&c->bucket_lock); for_each_cache(ca, c, i) - bch_prio_write(ca); + bch_prio_write(ca, true); mutex_unlock(&c->bucket_lock); err = "cannot allocate new UUID bucket"; diff --git a/drivers/md/bcache/sysfs.c b/drivers/md/bcache/sysfs.c index 627dcea0f5b6..733e2ddf3c78 100644 --- a/drivers/md/bcache/sysfs.c +++ b/drivers/md/bcache/sysfs.c @@ -134,6 +134,7 @@ rw_attribute(expensive_debug_checks); rw_attribute(cache_replacement_policy); rw_attribute(btree_shrinker_disabled); rw_attribute(copy_gc_enabled); +rw_attribute(idle_max_writeback_rate); rw_attribute(gc_after_writeback); rw_attribute(size); @@ -747,6 +748,8 @@ SHOW(__bch_cache_set) sysfs_printf(gc_always_rewrite, "%i", c->gc_always_rewrite); sysfs_printf(btree_shrinker_disabled, "%i", c->shrinker_disabled); sysfs_printf(copy_gc_enabled, "%i", c->copy_gc_enabled); + sysfs_printf(idle_max_writeback_rate, "%i", + c->idle_max_writeback_rate_enabled); sysfs_printf(gc_after_writeback, "%i", c->gc_after_writeback); sysfs_printf(io_disable, "%i", test_bit(CACHE_SET_IO_DISABLE, &c->flags)); @@ -864,6 +867,9 @@ STORE(__bch_cache_set) sysfs_strtoul_bool(gc_always_rewrite, c->gc_always_rewrite); sysfs_strtoul_bool(btree_shrinker_disabled, c->shrinker_disabled); sysfs_strtoul_bool(copy_gc_enabled, c->copy_gc_enabled); + sysfs_strtoul_bool(idle_max_writeback_rate, + c->idle_max_writeback_rate_enabled); + /* * write gc_after_writeback here may overwrite an already set * BCH_DO_AUTO_GC, it doesn't matter because this flag will be @@ -954,6 +960,7 @@ static struct attribute *bch_cache_set_internal_files[] = { &sysfs_gc_always_rewrite, &sysfs_btree_shrinker_disabled, &sysfs_copy_gc_enabled, + &sysfs_idle_max_writeback_rate, &sysfs_gc_after_writeback, &sysfs_io_disable, &sysfs_cutoff_writeback, diff --git a/drivers/md/bcache/writeback.c b/drivers/md/bcache/writeback.c index d60268fe49e1..4a40f9eadeaf 100644 --- a/drivers/md/bcache/writeback.c +++ b/drivers/md/bcache/writeback.c @@ -122,6 +122,10 @@ static void __update_writeback_rate(struct cached_dev *dc) static bool set_at_max_writeback_rate(struct cache_set *c, struct cached_dev *dc) { + /* Don't sst max writeback rate if it is disabled */ + if (!c->idle_max_writeback_rate_enabled) + return false; + /* Don't set max writeback rate if gc is running */ if (!c->gc_mark_valid) return false; diff --git a/drivers/md/dm-flakey.c b/drivers/md/dm-flakey.c index 2900fbde89b3..76587e9af0ef 100644 --- a/drivers/md/dm-flakey.c +++ b/drivers/md/dm-flakey.c @@ -280,7 +280,7 @@ static void flakey_map_bio(struct dm_target *ti, struct bio *bio) struct flakey_c *fc = ti->private; bio_set_dev(bio, fc->dev->bdev); - if (bio_sectors(bio) || bio_op(bio) == REQ_OP_ZONE_RESET) + if (bio_sectors(bio) || op_is_zone_mgmt(bio_op(bio))) bio->bi_iter.bi_sector = flakey_map_sector(ti, bio->bi_iter.bi_sector); } @@ -322,8 +322,7 @@ static int flakey_map(struct dm_target *ti, struct bio *bio) struct per_bio_data *pb = dm_per_bio_data(bio, sizeof(struct per_bio_data)); pb->bio_submitted = false; - /* Do not fail reset zone */ - if (bio_op(bio) == REQ_OP_ZONE_RESET) + if (op_is_zone_mgmt(bio_op(bio))) goto map_bio; /* Are we alive ? */ @@ -384,7 +383,7 @@ static int flakey_end_io(struct dm_target *ti, struct bio *bio, struct flakey_c *fc = ti->private; struct per_bio_data *pb = dm_per_bio_data(bio, sizeof(struct per_bio_data)); - if (bio_op(bio) == REQ_OP_ZONE_RESET) + if (op_is_zone_mgmt(bio_op(bio))) return DM_ENDIO_DONE; if (!*error && pb->bio_submitted && (bio_data_dir(bio) == READ)) { diff --git a/drivers/md/dm-linear.c b/drivers/md/dm-linear.c index ecefe6703736..97acafd48c85 100644 --- a/drivers/md/dm-linear.c +++ b/drivers/md/dm-linear.c @@ -90,7 +90,7 @@ static void linear_map_bio(struct dm_target *ti, struct bio *bio) struct linear_c *lc = ti->private; bio_set_dev(bio, lc->dev->bdev); - if (bio_sectors(bio) || bio_op(bio) == REQ_OP_ZONE_RESET) + if (bio_sectors(bio) || op_is_zone_mgmt(bio_op(bio))) bio->bi_iter.bi_sector = linear_map_sector(ti, bio->bi_iter.bi_sector); } diff --git a/drivers/md/dm.c b/drivers/md/dm.c index 1a5e328c443a..bc143c1b2333 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -1174,7 +1174,8 @@ static size_t dm_dax_copy_to_iter(struct dax_device *dax_dev, pgoff_t pgoff, /* * A target may call dm_accept_partial_bio only from the map routine. It is - * allowed for all bio types except REQ_PREFLUSH and REQ_OP_ZONE_RESET. + * allowed for all bio types except REQ_PREFLUSH, REQ_OP_ZONE_RESET, + * REQ_OP_ZONE_OPEN, REQ_OP_ZONE_CLOSE and REQ_OP_ZONE_FINISH. * * dm_accept_partial_bio informs the dm that the target only wants to process * additional n_sectors sectors of the bio and the rest of the data should be @@ -1627,7 +1628,7 @@ static blk_qc_t __split_and_process_bio(struct mapped_device *md, ci.sector_count = 0; error = __send_empty_flush(&ci); /* dec_pending submits any data associated with flush */ - } else if (bio_op(bio) == REQ_OP_ZONE_RESET) { + } else if (op_is_zone_mgmt(bio_op(bio))) { ci.bio = bio; ci.sector_count = 0; error = __split_and_process_non_flush(&ci); diff --git a/drivers/md/md-bitmap.c b/drivers/md/md-bitmap.c index b092c7b5282f..3ad18246fcb3 100644 --- a/drivers/md/md-bitmap.c +++ b/drivers/md/md-bitmap.c @@ -2139,6 +2139,7 @@ int md_bitmap_resize(struct bitmap *bitmap, sector_t blocks, memcpy(page_address(store.sb_page), page_address(bitmap->storage.sb_page), sizeof(bitmap_super_t)); + spin_lock_irq(&bitmap->counts.lock); md_bitmap_file_unmap(&bitmap->storage); bitmap->storage = store; @@ -2154,7 +2155,6 @@ int md_bitmap_resize(struct bitmap *bitmap, sector_t blocks, blocks = min(old_counts.chunks << old_counts.chunkshift, chunks << chunkshift); - spin_lock_irq(&bitmap->counts.lock); /* For cluster raid, need to pre-allocate bitmap */ if (mddev_is_clustered(bitmap->mddev)) { unsigned long page; diff --git a/drivers/md/md-linear.c b/drivers/md/md-linear.c index c766c559d36d..26c75c0199fa 100644 --- a/drivers/md/md-linear.c +++ b/drivers/md/md-linear.c @@ -244,10 +244,9 @@ static bool linear_make_request(struct mddev *mddev, struct bio *bio) sector_t start_sector, end_sector, data_offset; sector_t bio_sector = bio->bi_iter.bi_sector; - if (unlikely(bio->bi_opf & REQ_PREFLUSH)) { - md_flush_request(mddev, bio); + if (unlikely(bio->bi_opf & REQ_PREFLUSH) + && md_flush_request(mddev, bio)) return true; - } tmp_dev = which_dev(mddev, bio_sector); start_sector = tmp_dev->end_sector - tmp_dev->rdev->sectors; diff --git a/drivers/md/md-multipath.c b/drivers/md/md-multipath.c index 6780938d2991..152f9e65a226 100644 --- a/drivers/md/md-multipath.c +++ b/drivers/md/md-multipath.c @@ -104,10 +104,9 @@ static bool multipath_make_request(struct mddev *mddev, struct bio * bio) struct multipath_bh * mp_bh; struct multipath_info *multipath; - if (unlikely(bio->bi_opf & REQ_PREFLUSH)) { - md_flush_request(mddev, bio); + if (unlikely(bio->bi_opf & REQ_PREFLUSH) + && md_flush_request(mddev, bio)) return true; - } mp_bh = mempool_alloc(&conf->pool, GFP_NOIO); diff --git a/drivers/md/md.c b/drivers/md/md.c index 1be7abeb24fd..805b33e27496 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -550,7 +550,13 @@ static void md_submit_flush_data(struct work_struct *ws) } } -void md_flush_request(struct mddev *mddev, struct bio *bio) +/* + * Manages consolidation of flushes and submitting any flushes needed for + * a bio with REQ_PREFLUSH. Returns true if the bio is finished or is + * being finished in another context. Returns false if the flushing is + * complete but still needs the I/O portion of the bio to be processed. + */ +bool md_flush_request(struct mddev *mddev, struct bio *bio) { ktime_t start = ktime_get_boottime(); spin_lock_irq(&mddev->lock); @@ -575,9 +581,10 @@ void md_flush_request(struct mddev *mddev, struct bio *bio) bio_endio(bio); else { bio->bi_opf &= ~REQ_PREFLUSH; - mddev->pers->make_request(mddev, bio); + return false; } } + return true; } EXPORT_SYMBOL(md_flush_request); @@ -1098,6 +1105,7 @@ static int super_90_load(struct md_rdev *rdev, struct md_rdev *refdev, int minor char b[BDEVNAME_SIZE], b2[BDEVNAME_SIZE]; mdp_super_t *sb; int ret; + bool spare_disk = true; /* * Calculate the position of the superblock (512byte sectors), @@ -1148,8 +1156,18 @@ static int super_90_load(struct md_rdev *rdev, struct md_rdev *refdev, int minor else rdev->desc_nr = sb->this_disk.number; + /* not spare disk, or LEVEL_MULTIPATH */ + if (sb->level == LEVEL_MULTIPATH || + (rdev->desc_nr >= 0 && + sb->disks[rdev->desc_nr].state & + ((1<<MD_DISK_SYNC) | (1 << MD_DISK_ACTIVE)))) + spare_disk = false; + if (!refdev) { - ret = 1; + if (!spare_disk) + ret = 1; + else + ret = 0; } else { __u64 ev1, ev2; mdp_super_t *refsb = page_address(refdev->sb_page); @@ -1165,7 +1183,8 @@ static int super_90_load(struct md_rdev *rdev, struct md_rdev *refdev, int minor } ev1 = md_event(sb); ev2 = md_event(refsb); - if (ev1 > ev2) + + if (!spare_disk && ev1 > ev2) ret = 1; else ret = 0; @@ -1525,6 +1544,7 @@ static int super_1_load(struct md_rdev *rdev, struct md_rdev *refdev, int minor_ sector_t sectors; char b[BDEVNAME_SIZE], b2[BDEVNAME_SIZE]; int bmask; + bool spare_disk = true; /* * Calculate the position of the superblock in 512byte sectors. @@ -1658,8 +1678,19 @@ static int super_1_load(struct md_rdev *rdev, struct md_rdev *refdev, int minor_ sb->level != 0) return -EINVAL; + /* not spare disk, or LEVEL_MULTIPATH */ + if (sb->level == cpu_to_le32(LEVEL_MULTIPATH) || + (rdev->desc_nr >= 0 && + rdev->desc_nr < le32_to_cpu(sb->max_dev) && + (le16_to_cpu(sb->dev_roles[rdev->desc_nr]) < MD_DISK_ROLE_MAX || + le16_to_cpu(sb->dev_roles[rdev->desc_nr]) == MD_DISK_ROLE_JOURNAL))) + spare_disk = false; + if (!refdev) { - ret = 1; + if (!spare_disk) + ret = 1; + else + ret = 0; } else { __u64 ev1, ev2; struct mdp_superblock_1 *refsb = page_address(refdev->sb_page); @@ -1676,7 +1707,7 @@ static int super_1_load(struct md_rdev *rdev, struct md_rdev *refdev, int minor_ ev1 = le64_to_cpu(sb->events); ev2 = le64_to_cpu(refsb->events); - if (ev1 > ev2) + if (!spare_disk && ev1 > ev2) ret = 1; else ret = 0; @@ -3597,7 +3628,7 @@ abort_free: * Check a full RAID array for plausibility */ -static void analyze_sbs(struct mddev *mddev) +static int analyze_sbs(struct mddev *mddev) { int i; struct md_rdev *rdev, *freshest, *tmp; @@ -3618,6 +3649,12 @@ static void analyze_sbs(struct mddev *mddev) md_kick_rdev_from_array(rdev); } + /* Cannot find a valid fresh disk */ + if (!freshest) { + pr_warn("md: cannot find a valid disk\n"); + return -EINVAL; + } + super_types[mddev->major_version]. validate_super(mddev, freshest); @@ -3652,6 +3689,8 @@ static void analyze_sbs(struct mddev *mddev) clear_bit(In_sync, &rdev->flags); } } + + return 0; } /* Read a fixed-point number. @@ -5570,7 +5609,9 @@ int md_run(struct mddev *mddev) if (!mddev->raid_disks) { if (!mddev->persistent) return -EINVAL; - analyze_sbs(mddev); + err = analyze_sbs(mddev); + if (err) + return -EINVAL; } if (mddev->level != LEVEL_NONE) diff --git a/drivers/md/md.h b/drivers/md/md.h index c5e3ff398b59..5f86f8adb0a4 100644 --- a/drivers/md/md.h +++ b/drivers/md/md.h @@ -550,7 +550,7 @@ struct md_personality int level; struct list_head list; struct module *owner; - bool (*make_request)(struct mddev *mddev, struct bio *bio); + bool __must_check (*make_request)(struct mddev *mddev, struct bio *bio); /* * start up works that do NOT require md_thread. tasks that * requires md_thread should go into start() @@ -703,7 +703,7 @@ extern void md_error(struct mddev *mddev, struct md_rdev *rdev); extern void md_finish_reshape(struct mddev *mddev); extern int mddev_congested(struct mddev *mddev, int bits); -extern void md_flush_request(struct mddev *mddev, struct bio *bio); +extern bool __must_check md_flush_request(struct mddev *mddev, struct bio *bio); extern void md_super_write(struct mddev *mddev, struct md_rdev *rdev, sector_t sector, int size, struct page *page); extern int md_super_wait(struct mddev *mddev); diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c index 1e772287b1c8..b7c20979bd19 100644 --- a/drivers/md/raid0.c +++ b/drivers/md/raid0.c @@ -575,10 +575,9 @@ static bool raid0_make_request(struct mddev *mddev, struct bio *bio) unsigned chunk_sects; unsigned sectors; - if (unlikely(bio->bi_opf & REQ_PREFLUSH)) { - md_flush_request(mddev, bio); + if (unlikely(bio->bi_opf & REQ_PREFLUSH) + && md_flush_request(mddev, bio)) return true; - } if (unlikely((bio_op(bio) == REQ_OP_DISCARD))) { raid0_handle_discard(mddev, bio); @@ -615,7 +614,7 @@ static bool raid0_make_request(struct mddev *mddev, struct bio *bio) tmp_dev = map_sector(mddev, zone, sector, §or); break; default: - WARN("md/raid0:%s: Invalid layout\n", mdname(mddev)); + WARN(1, "md/raid0:%s: Invalid layout\n", mdname(mddev)); bio_io_error(bio); return true; } diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c index 0466ee2453b4..a409ab6f30bc 100644 --- a/drivers/md/raid1.c +++ b/drivers/md/raid1.c @@ -819,6 +819,7 @@ static void flush_bio_list(struct r1conf *conf, struct bio *bio) else generic_make_request(bio); bio = next; + cond_resched(); } } @@ -1567,10 +1568,9 @@ static bool raid1_make_request(struct mddev *mddev, struct bio *bio) { sector_t sectors; - if (unlikely(bio->bi_opf & REQ_PREFLUSH)) { - md_flush_request(mddev, bio); + if (unlikely(bio->bi_opf & REQ_PREFLUSH) + && md_flush_request(mddev, bio)) return true; - } /* * There is a limit to the maximum size, but diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c index 299c7b1c9718..ec136e44aef7 100644 --- a/drivers/md/raid10.c +++ b/drivers/md/raid10.c @@ -191,7 +191,7 @@ static void * r10buf_pool_alloc(gfp_t gfp_flags, void *data) out_free_pages: while (--j >= 0) - resync_free_pages(&rps[j * 2]); + resync_free_pages(&rps[j]); j = 0; out_free_bio: @@ -1525,10 +1525,9 @@ static bool raid10_make_request(struct mddev *mddev, struct bio *bio) int chunk_sects = chunk_mask + 1; int sectors = bio_sectors(bio); - if (unlikely(bio->bi_opf & REQ_PREFLUSH)) { - md_flush_request(mddev, bio); + if (unlikely(bio->bi_opf & REQ_PREFLUSH) + && md_flush_request(mddev, bio)) return true; - } if (!md_write_start(mddev, bio)) return false; diff --git a/drivers/md/raid5-ppl.c b/drivers/md/raid5-ppl.c index 18a4064a61a8..cab5b1352892 100644 --- a/drivers/md/raid5-ppl.c +++ b/drivers/md/raid5-ppl.c @@ -1404,7 +1404,7 @@ int ppl_init_log(struct r5conf *conf) atomic64_set(&ppl_conf->seq, 0); INIT_LIST_HEAD(&ppl_conf->no_mem_stripes); spin_lock_init(&ppl_conf->no_mem_stripes_lock); - ppl_conf->write_hint = RWF_WRITE_LIFE_NOT_SET; + ppl_conf->write_hint = RWH_WRITE_LIFE_NOT_SET; if (!mddev->external) { ppl_conf->signature = ~crc32c_le(~0, mddev->uuid, sizeof(mddev->uuid)); diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index 223e97ab27e6..f0fc538bfe59 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -1134,7 +1134,7 @@ again: bi->bi_iter.bi_size = STRIPE_SIZE; bi->bi_write_hint = sh->dev[i].write_hint; if (!rrdev) - sh->dev[i].write_hint = RWF_WRITE_LIFE_NOT_SET; + sh->dev[i].write_hint = RWH_WRITE_LIFE_NOT_SET; /* * If this is discard request, set bi_vcnt 0. We don't * want to confuse SCSI because SCSI will replace payload @@ -1187,7 +1187,7 @@ again: rbi->bi_io_vec[0].bv_offset = 0; rbi->bi_iter.bi_size = STRIPE_SIZE; rbi->bi_write_hint = sh->dev[i].write_hint; - sh->dev[i].write_hint = RWF_WRITE_LIFE_NOT_SET; + sh->dev[i].write_hint = RWH_WRITE_LIFE_NOT_SET; /* * If this is discard request, set bi_vcnt 0. We don't * want to confuse SCSI because SCSI will replace payload @@ -5592,8 +5592,8 @@ static bool raid5_make_request(struct mddev *mddev, struct bio * bi) if (ret == 0) return true; if (ret == -ENODEV) { - md_flush_request(mddev, bi); - return true; + if (md_flush_request(mddev, bi)) + return true; } /* ret == -EAGAIN, fallback */ /* diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index fa7ba09dca77..c5e434c9af62 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -283,6 +283,8 @@ void nvme_complete_rq(struct request *req) trace_nvme_complete_rq(req); + nvme_cleanup_cmd(req); + if (nvme_req(req)->ctrl->kas) nvme_req(req)->ctrl->comp_seen = true; @@ -313,7 +315,7 @@ bool nvme_cancel_request(struct request *req, void *data, bool reserved) if (blk_mq_request_completed(req)) return true; - nvme_req(req)->status = NVME_SC_HOST_PATH_ERROR; + nvme_req(req)->status = NVME_SC_HOST_ABORTED_CMD; blk_mq_complete_request(req); return true; } @@ -626,7 +628,7 @@ static blk_status_t nvme_setup_discard(struct nvme_ns *ns, struct request *req, } __rq_for_each_bio(bio, req) { - u64 slba = nvme_block_nr(ns, bio->bi_iter.bi_sector); + u64 slba = nvme_sect_to_lba(ns, bio->bi_iter.bi_sector); u32 nlb = bio->bi_iter.bi_size >> ns->lba_shift; if (n < segments) { @@ -667,7 +669,7 @@ static inline blk_status_t nvme_setup_write_zeroes(struct nvme_ns *ns, cmnd->write_zeroes.opcode = nvme_cmd_write_zeroes; cmnd->write_zeroes.nsid = cpu_to_le32(ns->head->ns_id); cmnd->write_zeroes.slba = - cpu_to_le64(nvme_block_nr(ns, blk_rq_pos(req))); + cpu_to_le64(nvme_sect_to_lba(ns, blk_rq_pos(req))); cmnd->write_zeroes.length = cpu_to_le16((blk_rq_bytes(req) >> ns->lba_shift) - 1); cmnd->write_zeroes.control = 0; @@ -691,7 +693,7 @@ static inline blk_status_t nvme_setup_rw(struct nvme_ns *ns, cmnd->rw.opcode = (rq_data_dir(req) ? nvme_cmd_write : nvme_cmd_read); cmnd->rw.nsid = cpu_to_le32(ns->head->ns_id); - cmnd->rw.slba = cpu_to_le64(nvme_block_nr(ns, blk_rq_pos(req))); + cmnd->rw.slba = cpu_to_le64(nvme_sect_to_lba(ns, blk_rq_pos(req))); cmnd->rw.length = cpu_to_le16((blk_rq_bytes(req) >> ns->lba_shift) - 1); if (req_op(req) == REQ_OP_WRITE && ctrl->nr_streams) @@ -1647,7 +1649,7 @@ static void nvme_init_integrity(struct gendisk *disk, u16 ms, u8 pi_type) static void nvme_set_chunk_size(struct nvme_ns *ns) { - u32 chunk_size = (((u32)ns->noiob) << (ns->lba_shift - 9)); + u32 chunk_size = nvme_lba_to_sect(ns, ns->noiob); blk_queue_chunk_sectors(ns->queue, rounddown_pow_of_two(chunk_size)); } @@ -1684,8 +1686,7 @@ static void nvme_config_discard(struct gendisk *disk, struct nvme_ns *ns) static void nvme_config_write_zeroes(struct gendisk *disk, struct nvme_ns *ns) { - u32 max_sectors; - unsigned short bs = 1 << ns->lba_shift; + u64 max_blocks; if (!(ns->ctrl->oncs & NVME_CTRL_ONCS_WRITE_ZEROES) || (ns->ctrl->quirks & NVME_QUIRK_DISABLE_WRITE_ZEROES)) @@ -1701,11 +1702,12 @@ static void nvme_config_write_zeroes(struct gendisk *disk, struct nvme_ns *ns) * nvme_init_identify() if available. */ if (ns->ctrl->max_hw_sectors == UINT_MAX) - max_sectors = ((u32)(USHRT_MAX + 1) * bs) >> 9; + max_blocks = (u64)USHRT_MAX + 1; else - max_sectors = ((u32)(ns->ctrl->max_hw_sectors + 1) * bs) >> 9; + max_blocks = ns->ctrl->max_hw_sectors + 1; - blk_queue_max_write_zeroes_sectors(disk->queue, max_sectors); + blk_queue_max_write_zeroes_sectors(disk->queue, + nvme_lba_to_sect(ns, max_blocks)); } static int nvme_report_ns_ids(struct nvme_ctrl *ctrl, unsigned int nsid, @@ -1748,7 +1750,7 @@ static bool nvme_ns_ids_equal(struct nvme_ns_ids *a, struct nvme_ns_ids *b) static void nvme_update_disk_info(struct gendisk *disk, struct nvme_ns *ns, struct nvme_id_ns *id) { - sector_t capacity = le64_to_cpu(id->nsze) << (ns->lba_shift - 9); + sector_t capacity = nvme_lba_to_sect(ns, le64_to_cpu(id->nsze)); unsigned short bs = 1 << ns->lba_shift; u32 atomic_bs, phys_bs, io_opt; diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c index 265f89e11d8b..679a721ae229 100644 --- a/drivers/nvme/host/fc.c +++ b/drivers/nvme/host/fc.c @@ -1224,7 +1224,7 @@ nvme_fc_connect_admin_queue(struct nvme_fc_ctrl *ctrl, lsreq->rqstlen = sizeof(*assoc_rqst); lsreq->rspaddr = assoc_acc; lsreq->rsplen = sizeof(*assoc_acc); - lsreq->timeout = NVME_FC_CONNECT_TIMEOUT_SEC; + lsreq->timeout = NVME_FC_LS_TIMEOUT_SEC; ret = nvme_fc_send_ls_req(ctrl->rport, lsop); if (ret) @@ -1264,7 +1264,7 @@ nvme_fc_connect_admin_queue(struct nvme_fc_ctrl *ctrl, if (fcret) { ret = -EBADF; dev_err(ctrl->dev, - "q %d connect failed: %s\n", + "q %d Create Association LS failed: %s\n", queue->qnum, validation_errors[fcret]); } else { ctrl->association_id = @@ -1332,7 +1332,7 @@ nvme_fc_connect_queue(struct nvme_fc_ctrl *ctrl, struct nvme_fc_queue *queue, lsreq->rqstlen = sizeof(*conn_rqst); lsreq->rspaddr = conn_acc; lsreq->rsplen = sizeof(*conn_acc); - lsreq->timeout = NVME_FC_CONNECT_TIMEOUT_SEC; + lsreq->timeout = NVME_FC_LS_TIMEOUT_SEC; ret = nvme_fc_send_ls_req(ctrl->rport, lsop); if (ret) @@ -1363,7 +1363,7 @@ nvme_fc_connect_queue(struct nvme_fc_ctrl *ctrl, struct nvme_fc_queue *queue, if (fcret) { ret = -EBADF; dev_err(ctrl->dev, - "q %d connect failed: %s\n", + "q %d Create I/O Connection LS failed: %s\n", queue->qnum, validation_errors[fcret]); } else { queue->connection_id = @@ -1376,7 +1376,7 @@ out_free_buffer: out_no_memory: if (ret) dev_err(ctrl->dev, - "queue %d connect command failed (%d).\n", + "queue %d connect I/O queue failed (%d).\n", queue->qnum, ret); return ret; } @@ -1413,8 +1413,8 @@ nvme_fc_disconnect_assoc_done(struct nvmefc_ls_req *lsreq, int status) static void nvme_fc_xmt_disconnect_assoc(struct nvme_fc_ctrl *ctrl) { - struct fcnvme_ls_disconnect_rqst *discon_rqst; - struct fcnvme_ls_disconnect_acc *discon_acc; + struct fcnvme_ls_disconnect_assoc_rqst *discon_rqst; + struct fcnvme_ls_disconnect_assoc_acc *discon_acc; struct nvmefc_ls_req_op *lsop; struct nvmefc_ls_req *lsreq; int ret; @@ -1430,11 +1430,11 @@ nvme_fc_xmt_disconnect_assoc(struct nvme_fc_ctrl *ctrl) lsreq = &lsop->ls_req; lsreq->private = (void *)&lsop[1]; - discon_rqst = (struct fcnvme_ls_disconnect_rqst *) + discon_rqst = (struct fcnvme_ls_disconnect_assoc_rqst *) (lsreq->private + ctrl->lport->ops->lsrqst_priv_sz); - discon_acc = (struct fcnvme_ls_disconnect_acc *)&discon_rqst[1]; + discon_acc = (struct fcnvme_ls_disconnect_assoc_acc *)&discon_rqst[1]; - discon_rqst->w0.ls_cmd = FCNVME_LS_DISCONNECT; + discon_rqst->w0.ls_cmd = FCNVME_LS_DISCONNECT_ASSOC; discon_rqst->desc_list_len = cpu_to_be32( sizeof(struct fcnvme_lsdesc_assoc_id) + sizeof(struct fcnvme_lsdesc_disconn_cmd)); @@ -1451,22 +1451,17 @@ nvme_fc_xmt_disconnect_assoc(struct nvme_fc_ctrl *ctrl) discon_rqst->discon_cmd.desc_len = fcnvme_lsdesc_len( sizeof(struct fcnvme_lsdesc_disconn_cmd)); - discon_rqst->discon_cmd.scope = FCNVME_DISCONN_ASSOCIATION; - discon_rqst->discon_cmd.id = cpu_to_be64(ctrl->association_id); lsreq->rqstaddr = discon_rqst; lsreq->rqstlen = sizeof(*discon_rqst); lsreq->rspaddr = discon_acc; lsreq->rsplen = sizeof(*discon_acc); - lsreq->timeout = NVME_FC_CONNECT_TIMEOUT_SEC; + lsreq->timeout = NVME_FC_LS_TIMEOUT_SEC; ret = nvme_fc_send_ls_req_async(ctrl->rport, lsop, nvme_fc_disconnect_assoc_done); if (ret) kfree(lsop); - - /* only meaningful part to terminating the association */ - ctrl->association_id = 0; } @@ -1662,7 +1657,7 @@ nvme_fc_fcpio_done(struct nvmefc_fcp_req *req) (freq->rcv_rsplen / 4) || be32_to_cpu(op->rsp_iu.xfrd_len) != freq->transferred_length || - op->rsp_iu.status_code || + op->rsp_iu.ersp_result || sqe->common.command_id != cqe->command_id)) { status = cpu_to_le16(NVME_SC_HOST_PATH_ERROR << 1); dev_info(ctrl->ctrl.device, @@ -1672,7 +1667,7 @@ nvme_fc_fcpio_done(struct nvmefc_fcp_req *req) ctrl->cnum, be16_to_cpu(op->rsp_iu.iu_len), be32_to_cpu(op->rsp_iu.xfrd_len), freq->transferred_length, - op->rsp_iu.status_code, + op->rsp_iu.ersp_result, sqe->common.command_id, cqe->command_id); goto done; @@ -1731,9 +1726,14 @@ __nvme_fc_init_request(struct nvme_fc_ctrl *ctrl, op->rq = rq; op->rqno = rqno; - cmdiu->scsi_id = NVME_CMD_SCSI_ID; + cmdiu->format_id = NVME_CMD_FORMAT_ID; cmdiu->fc_id = NVME_CMD_FC_ID; cmdiu->iu_len = cpu_to_be16(sizeof(*cmdiu) / sizeof(u32)); + if (queue->qnum) + cmdiu->rsv_cat = fccmnd_set_cat_css(0, + (NVME_CC_CSS_NVM >> NVME_CC_CSS_SHIFT)); + else + cmdiu->rsv_cat = fccmnd_set_cat_admin(0); op->fcp_req.cmddma = fc_dma_map_single(ctrl->lport->dev, &op->cmd_iu, sizeof(op->cmd_iu), DMA_TO_DEVICE); @@ -2173,8 +2173,6 @@ nvme_fc_unmap_data(struct nvme_fc_ctrl *ctrl, struct request *rq, fc_dma_unmap_sg(ctrl->lport->dev, freq->sg_table.sgl, op->nents, rq_dma_dir(rq)); - nvme_cleanup_cmd(rq); - sg_free_table_chained(&freq->sg_table, SG_CHUNK_SIZE); freq->sg_cnt = 0; @@ -2305,6 +2303,7 @@ nvme_fc_start_fcp_op(struct nvme_fc_ctrl *ctrl, struct nvme_fc_queue *queue, if (!(op->flags & FCOP_FLAGS_AEN)) nvme_fc_unmap_data(ctrl, op->rq, op); + nvme_cleanup_cmd(op->rq); nvme_fc_ctrl_put(ctrl); if (ctrl->rport->remoteport.port_state == FC_OBJSTATE_ONLINE && @@ -2695,7 +2694,7 @@ nvme_fc_create_association(struct nvme_fc_ctrl *ctrl) /* warn if maxcmd is lower than queue_size */ dev_warn(ctrl->ctrl.device, "queue_size %zu > ctrl maxcmd %u, reducing " - "to queue_size\n", + "to maxcmd\n", opts->queue_size, ctrl->ctrl.maxcmd); opts->queue_size = ctrl->ctrl.maxcmd; } @@ -2703,7 +2702,8 @@ nvme_fc_create_association(struct nvme_fc_ctrl *ctrl) if (opts->queue_size > ctrl->ctrl.sqsize + 1) { /* warn if sqsize is lower than queue_size */ dev_warn(ctrl->ctrl.device, - "queue_size %zu > ctrl sqsize %u, clamping down\n", + "queue_size %zu > ctrl sqsize %u, reducing " + "to sqsize\n", opts->queue_size, ctrl->ctrl.sqsize + 1); opts->queue_size = ctrl->ctrl.sqsize + 1; } @@ -2739,6 +2739,7 @@ out_term_aen_ops: out_disconnect_admin_queue: /* send a Disconnect(association) LS to fc-nvme target */ nvme_fc_xmt_disconnect_assoc(ctrl); + ctrl->association_id = 0; out_delete_hw_queue: __nvme_fc_delete_hw_queue(ctrl, &ctrl->queues[0], 0); out_free_queue: @@ -2830,6 +2831,8 @@ nvme_fc_delete_association(struct nvme_fc_ctrl *ctrl) if (ctrl->association_id) nvme_fc_xmt_disconnect_assoc(ctrl); + ctrl->association_id = 0; + if (ctrl->ctrl.tagset) { nvme_fc_delete_hw_io_queues(ctrl); nvme_fc_free_io_queues(ctrl); diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c index e0f064dcbd02..797c18337d96 100644 --- a/drivers/nvme/host/multipath.c +++ b/drivers/nvme/host/multipath.c @@ -95,6 +95,7 @@ void nvme_failover_req(struct request *req) } break; case NVME_SC_HOST_PATH_ERROR: + case NVME_SC_HOST_ABORTED_CMD: /* * Temporary transport disruption in talking to the controller. * Try to send on a new path. @@ -446,8 +447,14 @@ static int nvme_parse_ana_log(struct nvme_ctrl *ctrl, void *data, for (i = 0; i < le16_to_cpu(ctrl->ana_log_buf->ngrps); i++) { struct nvme_ana_group_desc *desc = base + offset; - u32 nr_nsids = le32_to_cpu(desc->nnsids); - size_t nsid_buf_size = nr_nsids * sizeof(__le32); + u32 nr_nsids; + size_t nsid_buf_size; + + if (WARN_ON_ONCE(offset > ctrl->ana_log_size - sizeof(*desc))) + return -EINVAL; + + nr_nsids = le32_to_cpu(desc->nnsids); + nsid_buf_size = nr_nsids * sizeof(__le32); if (WARN_ON_ONCE(desc->grpid == 0)) return -EINVAL; @@ -467,8 +474,6 @@ static int nvme_parse_ana_log(struct nvme_ctrl *ctrl, void *data, return error; offset += nsid_buf_size; - if (WARN_ON_ONCE(offset > ctrl->ana_log_size - sizeof(*desc))) - return -EINVAL; } return 0; diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h index 22e8401352c2..fdda273cd2f6 100644 --- a/drivers/nvme/host/nvme.h +++ b/drivers/nvme/host/nvme.h @@ -419,9 +419,20 @@ static inline int nvme_reset_subsystem(struct nvme_ctrl *ctrl) return ctrl->ops->reg_write32(ctrl, NVME_REG_NSSR, 0x4E564D65); } -static inline u64 nvme_block_nr(struct nvme_ns *ns, sector_t sector) +/* + * Convert a 512B sector number to a device logical block number. + */ +static inline u64 nvme_sect_to_lba(struct nvme_ns *ns, sector_t sector) +{ + return sector >> (ns->lba_shift - SECTOR_SHIFT); +} + +/* + * Convert a device logical block number to a 512B sector number. + */ +static inline sector_t nvme_lba_to_sect(struct nvme_ns *ns, u64 lba) { - return (sector >> (ns->lba_shift - 9)); + return lba << (ns->lba_shift - SECTOR_SHIFT); } static inline void nvme_end_request(struct request *req, __le16 status, @@ -446,6 +457,11 @@ static inline void nvme_put_ctrl(struct nvme_ctrl *ctrl) put_device(ctrl->device); } +static inline bool nvme_is_aen_req(u16 qid, __u16 command_id) +{ + return !qid && command_id >= NVME_AQ_BLK_MQ_DEPTH; +} + void nvme_complete_rq(struct request *req); bool nvme_cancel_request(struct request *req, void *data, bool reserved); bool nvme_change_ctrl_state(struct nvme_ctrl *ctrl, diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index 869f462e6b6e..3aab92bd2263 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -925,7 +925,6 @@ static void nvme_pci_complete_rq(struct request *req) struct nvme_iod *iod = blk_mq_rq_to_pdu(req); struct nvme_dev *dev = iod->nvmeq->dev; - nvme_cleanup_cmd(req); if (blk_integrity_rq(req)) dma_unmap_page(dev->dev, iod->meta_dma, rq_integrity_vec(req)->bv_len, rq_data_dir(req)); @@ -968,8 +967,7 @@ static inline void nvme_handle_cqe(struct nvme_queue *nvmeq, u16 idx) * aborts. We don't even bother to allocate a struct request * for them but rather special case them here. */ - if (unlikely(nvmeq->qid == 0 && - cqe->command_id >= NVME_AQ_BLK_MQ_DEPTH)) { + if (unlikely(nvme_is_aen_req(nvmeq->qid, cqe->command_id))) { nvme_complete_async_event(&nvmeq->dev->ctrl, cqe->status, &cqe->result); return; @@ -2982,7 +2980,7 @@ static int nvme_suspend(struct device *dev) /* * Clearing npss forces a controller reset on resume. The - * correct value will be resdicovered then. + * correct value will be rediscovered then. */ ret = nvme_disable_prepare_reset(ndev, true); ctrl->npss = 0; diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c index cb4c3000a57e..dce59459ed41 100644 --- a/drivers/nvme/host/rdma.c +++ b/drivers/nvme/host/rdma.c @@ -1160,8 +1160,6 @@ static void nvme_rdma_unmap_data(struct nvme_rdma_queue *queue, } ib_dma_unmap_sg(ibdev, req->sg_table.sgl, req->nents, rq_dma_dir(rq)); - - nvme_cleanup_cmd(rq); sg_free_table_chained(&req->sg_table, SG_CHUNK_SIZE); } @@ -1501,8 +1499,8 @@ static void nvme_rdma_recv_done(struct ib_cq *cq, struct ib_wc *wc) * aborts. We don't even bother to allocate a struct request * for them but rather special case them here. */ - if (unlikely(nvme_rdma_queue_idx(queue) == 0 && - cqe->command_id >= NVME_AQ_BLK_MQ_DEPTH)) + if (unlikely(nvme_is_aen_req(nvme_rdma_queue_idx(queue), + cqe->command_id))) nvme_complete_async_event(&queue->ctrl->ctrl, cqe->status, &cqe->result); else @@ -1768,7 +1766,6 @@ static blk_status_t nvme_rdma_queue_rq(struct blk_mq_hw_ctx *hctx, if (unlikely(err < 0)) { dev_err(queue->ctrl->ctrl.device, "Failed to map data (%d)\n", err); - nvme_cleanup_cmd(rq); goto err; } @@ -1779,18 +1776,19 @@ static blk_status_t nvme_rdma_queue_rq(struct blk_mq_hw_ctx *hctx, err = nvme_rdma_post_send(queue, sqe, req->sge, req->num_sge, req->mr ? &req->reg_wr.wr : NULL); - if (unlikely(err)) { - nvme_rdma_unmap_data(queue, rq); - goto err; - } + if (unlikely(err)) + goto err_unmap; return BLK_STS_OK; +err_unmap: + nvme_rdma_unmap_data(queue, rq); err: if (err == -ENOMEM || err == -EAGAIN) ret = BLK_STS_RESOURCE; else ret = BLK_STS_IOERR; + nvme_cleanup_cmd(rq); unmap_qe: ib_dma_unmap_single(dev, req->sqe.dma, sizeof(struct nvme_command), DMA_TO_DEVICE); diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c index 7544be84ab35..6d43b23a0fc8 100644 --- a/drivers/nvme/host/tcp.c +++ b/drivers/nvme/host/tcp.c @@ -491,8 +491,8 @@ static int nvme_tcp_handle_comp(struct nvme_tcp_queue *queue, * aborts. We don't even bother to allocate a struct request * for them but rather special case them here. */ - if (unlikely(nvme_tcp_queue_id(queue) == 0 && - cqe->command_id >= NVME_AQ_BLK_MQ_DEPTH)) + if (unlikely(nvme_is_aen_req(nvme_tcp_queue_id(queue), + cqe->command_id))) nvme_complete_async_event(&queue->ctrl->ctrl, cqe->status, &cqe->result); else diff --git a/drivers/nvme/target/admin-cmd.c b/drivers/nvme/target/admin-cmd.c index 831a062d27cb..56c21b501185 100644 --- a/drivers/nvme/target/admin-cmd.c +++ b/drivers/nvme/target/admin-cmd.c @@ -31,7 +31,7 @@ u64 nvmet_get_log_page_offset(struct nvme_command *cmd) static void nvmet_execute_get_log_page_noop(struct nvmet_req *req) { - nvmet_req_complete(req, nvmet_zero_sgl(req, 0, req->data_len)); + nvmet_req_complete(req, nvmet_zero_sgl(req, 0, req->transfer_len)); } static void nvmet_execute_get_log_page_error(struct nvmet_req *req) @@ -134,7 +134,7 @@ static void nvmet_execute_get_log_page_smart(struct nvmet_req *req) u16 status = NVME_SC_INTERNAL; unsigned long flags; - if (req->data_len != sizeof(*log)) + if (req->transfer_len != sizeof(*log)) goto out; log = kzalloc(sizeof(*log), GFP_KERNEL); @@ -196,7 +196,7 @@ static void nvmet_execute_get_log_changed_ns(struct nvmet_req *req) u16 status = NVME_SC_INTERNAL; size_t len; - if (req->data_len != NVME_MAX_CHANGED_NAMESPACES * sizeof(__le32)) + if (req->transfer_len != NVME_MAX_CHANGED_NAMESPACES * sizeof(__le32)) goto out; mutex_lock(&ctrl->lock); @@ -206,7 +206,7 @@ static void nvmet_execute_get_log_changed_ns(struct nvmet_req *req) len = ctrl->nr_changed_ns * sizeof(__le32); status = nvmet_copy_to_sgl(req, 0, ctrl->changed_ns_list, len); if (!status) - status = nvmet_zero_sgl(req, len, req->data_len - len); + status = nvmet_zero_sgl(req, len, req->transfer_len - len); ctrl->nr_changed_ns = 0; nvmet_clear_aen_bit(req, NVME_AEN_BIT_NS_ATTR); mutex_unlock(&ctrl->lock); @@ -282,6 +282,36 @@ out: nvmet_req_complete(req, status); } +static void nvmet_execute_get_log_page(struct nvmet_req *req) +{ + if (!nvmet_check_data_len(req, nvmet_get_log_page_len(req->cmd))) + return; + + switch (req->cmd->get_log_page.lid) { + case NVME_LOG_ERROR: + return nvmet_execute_get_log_page_error(req); + case NVME_LOG_SMART: + return nvmet_execute_get_log_page_smart(req); + case NVME_LOG_FW_SLOT: + /* + * We only support a single firmware slot which always is + * active, so we can zero out the whole firmware slot log and + * still claim to fully implement this mandatory log page. + */ + return nvmet_execute_get_log_page_noop(req); + case NVME_LOG_CHANGED_NS: + return nvmet_execute_get_log_changed_ns(req); + case NVME_LOG_CMD_EFFECTS: + return nvmet_execute_get_log_cmd_effects_ns(req); + case NVME_LOG_ANA: + return nvmet_execute_get_log_page_ana(req); + } + pr_err("unhandled lid %d on qid %d\n", + req->cmd->get_log_page.lid, req->sq->qid); + req->error_loc = offsetof(struct nvme_get_log_page_command, lid); + nvmet_req_complete(req, NVME_SC_INVALID_FIELD | NVME_SC_DNR); +} + static void nvmet_execute_identify_ctrl(struct nvmet_req *req) { struct nvmet_ctrl *ctrl = req->sq->ctrl; @@ -565,6 +595,28 @@ out: nvmet_req_complete(req, status); } +static void nvmet_execute_identify(struct nvmet_req *req) +{ + if (!nvmet_check_data_len(req, NVME_IDENTIFY_DATA_SIZE)) + return; + + switch (req->cmd->identify.cns) { + case NVME_ID_CNS_NS: + return nvmet_execute_identify_ns(req); + case NVME_ID_CNS_CTRL: + return nvmet_execute_identify_ctrl(req); + case NVME_ID_CNS_NS_ACTIVE_LIST: + return nvmet_execute_identify_nslist(req); + case NVME_ID_CNS_NS_DESC_LIST: + return nvmet_execute_identify_desclist(req); + } + + pr_err("unhandled identify cns %d on qid %d\n", + req->cmd->identify.cns, req->sq->qid); + req->error_loc = offsetof(struct nvme_identify, cns); + nvmet_req_complete(req, NVME_SC_INVALID_FIELD | NVME_SC_DNR); +} + /* * A "minimum viable" abort implementation: the command is mandatory in the * spec, but we are not required to do any useful work. We couldn't really @@ -574,6 +626,8 @@ out: */ static void nvmet_execute_abort(struct nvmet_req *req) { + if (!nvmet_check_data_len(req, 0)) + return; nvmet_set_result(req, 1); nvmet_req_complete(req, 0); } @@ -658,6 +712,9 @@ static void nvmet_execute_set_features(struct nvmet_req *req) u32 cdw10 = le32_to_cpu(req->cmd->common.cdw10); u16 status = 0; + if (!nvmet_check_data_len(req, 0)) + return; + switch (cdw10 & 0xff) { case NVME_FEAT_NUM_QUEUES: nvmet_set_result(req, @@ -721,6 +778,9 @@ static void nvmet_execute_get_features(struct nvmet_req *req) u32 cdw10 = le32_to_cpu(req->cmd->common.cdw10); u16 status = 0; + if (!nvmet_check_data_len(req, 0)) + return; + switch (cdw10 & 0xff) { /* * These features are mandatory in the spec, but we don't @@ -785,6 +845,9 @@ void nvmet_execute_async_event(struct nvmet_req *req) { struct nvmet_ctrl *ctrl = req->sq->ctrl; + if (!nvmet_check_data_len(req, 0)) + return; + mutex_lock(&ctrl->lock); if (ctrl->nr_async_event_cmds >= NVMET_ASYNC_EVENTS) { mutex_unlock(&ctrl->lock); @@ -801,6 +864,9 @@ void nvmet_execute_keep_alive(struct nvmet_req *req) { struct nvmet_ctrl *ctrl = req->sq->ctrl; + if (!nvmet_check_data_len(req, 0)) + return; + pr_debug("ctrl %d update keep-alive timer for %d secs\n", ctrl->cntlid, ctrl->kato); @@ -813,77 +879,36 @@ u16 nvmet_parse_admin_cmd(struct nvmet_req *req) struct nvme_command *cmd = req->cmd; u16 ret; + if (nvme_is_fabrics(cmd)) + return nvmet_parse_fabrics_cmd(req); + if (req->sq->ctrl->subsys->type == NVME_NQN_DISC) + return nvmet_parse_discovery_cmd(req); + ret = nvmet_check_ctrl_status(req, cmd); if (unlikely(ret)) return ret; switch (cmd->common.opcode) { case nvme_admin_get_log_page: - req->data_len = nvmet_get_log_page_len(cmd); - - switch (cmd->get_log_page.lid) { - case NVME_LOG_ERROR: - req->execute = nvmet_execute_get_log_page_error; - return 0; - case NVME_LOG_SMART: - req->execute = nvmet_execute_get_log_page_smart; - return 0; - case NVME_LOG_FW_SLOT: - /* - * We only support a single firmware slot which always - * is active, so we can zero out the whole firmware slot - * log and still claim to fully implement this mandatory - * log page. - */ - req->execute = nvmet_execute_get_log_page_noop; - return 0; - case NVME_LOG_CHANGED_NS: - req->execute = nvmet_execute_get_log_changed_ns; - return 0; - case NVME_LOG_CMD_EFFECTS: - req->execute = nvmet_execute_get_log_cmd_effects_ns; - return 0; - case NVME_LOG_ANA: - req->execute = nvmet_execute_get_log_page_ana; - return 0; - } - break; + req->execute = nvmet_execute_get_log_page; + return 0; case nvme_admin_identify: - req->data_len = NVME_IDENTIFY_DATA_SIZE; - switch (cmd->identify.cns) { - case NVME_ID_CNS_NS: - req->execute = nvmet_execute_identify_ns; - return 0; - case NVME_ID_CNS_CTRL: - req->execute = nvmet_execute_identify_ctrl; - return 0; - case NVME_ID_CNS_NS_ACTIVE_LIST: - req->execute = nvmet_execute_identify_nslist; - return 0; - case NVME_ID_CNS_NS_DESC_LIST: - req->execute = nvmet_execute_identify_desclist; - return 0; - } - break; + req->execute = nvmet_execute_identify; + return 0; case nvme_admin_abort_cmd: req->execute = nvmet_execute_abort; - req->data_len = 0; return 0; case nvme_admin_set_features: req->execute = nvmet_execute_set_features; - req->data_len = 0; return 0; case nvme_admin_get_features: req->execute = nvmet_execute_get_features; - req->data_len = 0; return 0; case nvme_admin_async_event: req->execute = nvmet_execute_async_event; - req->data_len = 0; return 0; case nvme_admin_keep_alive: req->execute = nvmet_execute_keep_alive; - req->data_len = 0; return 0; } diff --git a/drivers/nvme/target/core.c b/drivers/nvme/target/core.c index 3a67e244e568..28438b833c1b 100644 --- a/drivers/nvme/target/core.c +++ b/drivers/nvme/target/core.c @@ -892,14 +892,10 @@ bool nvmet_req_init(struct nvmet_req *req, struct nvmet_cq *cq, } if (unlikely(!req->sq->ctrl)) - /* will return an error for any Non-connect command: */ + /* will return an error for any non-connect command: */ status = nvmet_parse_connect_cmd(req); else if (likely(req->sq->qid != 0)) status = nvmet_parse_io_cmd(req); - else if (nvme_is_fabrics(req->cmd)) - status = nvmet_parse_fabrics_cmd(req); - else if (req->sq->ctrl->subsys->type == NVME_NQN_DISC) - status = nvmet_parse_discovery_cmd(req); else status = nvmet_parse_admin_cmd(req); @@ -930,15 +926,17 @@ void nvmet_req_uninit(struct nvmet_req *req) } EXPORT_SYMBOL_GPL(nvmet_req_uninit); -void nvmet_req_execute(struct nvmet_req *req) +bool nvmet_check_data_len(struct nvmet_req *req, size_t data_len) { - if (unlikely(req->data_len != req->transfer_len)) { + if (unlikely(data_len != req->transfer_len)) { req->error_loc = offsetof(struct nvme_common_command, dptr); nvmet_req_complete(req, NVME_SC_SGL_INVALID_DATA | NVME_SC_DNR); - } else - req->execute(req); + return false; + } + + return true; } -EXPORT_SYMBOL_GPL(nvmet_req_execute); +EXPORT_SYMBOL_GPL(nvmet_check_data_len); int nvmet_req_alloc_sgl(struct nvmet_req *req) { @@ -966,7 +964,7 @@ int nvmet_req_alloc_sgl(struct nvmet_req *req) } req->sg = sgl_alloc(req->transfer_len, GFP_KERNEL, &req->sg_cnt); - if (!req->sg) + if (unlikely(!req->sg)) return -ENOMEM; return 0; diff --git a/drivers/nvme/target/discovery.c b/drivers/nvme/target/discovery.c index 3764a8900850..0c2274b21e15 100644 --- a/drivers/nvme/target/discovery.c +++ b/drivers/nvme/target/discovery.c @@ -157,7 +157,7 @@ static size_t discovery_log_entries(struct nvmet_req *req) return entries; } -static void nvmet_execute_get_disc_log_page(struct nvmet_req *req) +static void nvmet_execute_disc_get_log_page(struct nvmet_req *req) { const int entry_size = sizeof(struct nvmf_disc_rsp_page_entry); struct nvmet_ctrl *ctrl = req->sq->ctrl; @@ -171,6 +171,16 @@ static void nvmet_execute_get_disc_log_page(struct nvmet_req *req) u16 status = 0; void *buffer; + if (!nvmet_check_data_len(req, data_len)) + return; + + if (req->cmd->get_log_page.lid != NVME_LOG_DISC) { + req->error_loc = + offsetof(struct nvme_get_log_page_command, lid); + status = NVME_SC_INVALID_OPCODE | NVME_SC_DNR; + goto out; + } + /* Spec requires dword aligned offsets */ if (offset & 0x3) { status = NVME_SC_INVALID_FIELD | NVME_SC_DNR; @@ -227,20 +237,35 @@ out: nvmet_req_complete(req, status); } -static void nvmet_execute_identify_disc_ctrl(struct nvmet_req *req) +static void nvmet_execute_disc_identify(struct nvmet_req *req) { struct nvmet_ctrl *ctrl = req->sq->ctrl; struct nvme_id_ctrl *id; + const char model[] = "Linux"; u16 status = 0; + if (!nvmet_check_data_len(req, NVME_IDENTIFY_DATA_SIZE)) + return; + + if (req->cmd->identify.cns != NVME_ID_CNS_CTRL) { + req->error_loc = offsetof(struct nvme_identify, cns); + status = NVME_SC_INVALID_OPCODE | NVME_SC_DNR; + goto out; + } + id = kzalloc(sizeof(*id), GFP_KERNEL); if (!id) { status = NVME_SC_INTERNAL; goto out; } + memset(id->sn, ' ', sizeof(id->sn)); + bin2hex(id->sn, &ctrl->subsys->serial, + min(sizeof(ctrl->subsys->serial), sizeof(id->sn) / 2)); memset(id->fr, ' ', sizeof(id->fr)); - strncpy((char *)id->fr, UTS_RELEASE, sizeof(id->fr)); + memcpy_and_pad(id->mn, sizeof(id->mn), model, sizeof(model) - 1, ' '); + memcpy_and_pad(id->fr, sizeof(id->fr), + UTS_RELEASE, strlen(UTS_RELEASE), ' '); /* no limit on data transfer sizes for now */ id->mdts = 0; @@ -273,6 +298,9 @@ static void nvmet_execute_disc_set_features(struct nvmet_req *req) u32 cdw10 = le32_to_cpu(req->cmd->common.cdw10); u16 stat; + if (!nvmet_check_data_len(req, 0)) + return; + switch (cdw10 & 0xff) { case NVME_FEAT_KATO: stat = nvmet_set_feat_kato(req); @@ -296,6 +324,9 @@ static void nvmet_execute_disc_get_features(struct nvmet_req *req) u32 cdw10 = le32_to_cpu(req->cmd->common.cdw10); u16 stat = 0; + if (!nvmet_check_data_len(req, 0)) + return; + switch (cdw10 & 0xff) { case NVME_FEAT_KATO: nvmet_get_feat_kato(req); @@ -328,47 +359,22 @@ u16 nvmet_parse_discovery_cmd(struct nvmet_req *req) switch (cmd->common.opcode) { case nvme_admin_set_features: req->execute = nvmet_execute_disc_set_features; - req->data_len = 0; return 0; case nvme_admin_get_features: req->execute = nvmet_execute_disc_get_features; - req->data_len = 0; return 0; case nvme_admin_async_event: req->execute = nvmet_execute_async_event; - req->data_len = 0; return 0; case nvme_admin_keep_alive: req->execute = nvmet_execute_keep_alive; - req->data_len = 0; return 0; case nvme_admin_get_log_page: - req->data_len = nvmet_get_log_page_len(cmd); - - switch (cmd->get_log_page.lid) { - case NVME_LOG_DISC: - req->execute = nvmet_execute_get_disc_log_page; - return 0; - default: - pr_err("unsupported get_log_page lid %d\n", - cmd->get_log_page.lid); - req->error_loc = - offsetof(struct nvme_get_log_page_command, lid); - return NVME_SC_INVALID_OPCODE | NVME_SC_DNR; - } + req->execute = nvmet_execute_disc_get_log_page; + return 0; case nvme_admin_identify: - req->data_len = NVME_IDENTIFY_DATA_SIZE; - switch (cmd->identify.cns) { - case NVME_ID_CNS_CTRL: - req->execute = - nvmet_execute_identify_disc_ctrl; - return 0; - default: - pr_err("unsupported identify cns %d\n", - cmd->identify.cns); - req->error_loc = offsetof(struct nvme_identify, cns); - return NVME_SC_INVALID_OPCODE | NVME_SC_DNR; - } + req->execute = nvmet_execute_disc_identify; + return 0; default: pr_err("unhandled cmd %d\n", cmd->common.opcode); req->error_loc = offsetof(struct nvme_common_command, opcode); diff --git a/drivers/nvme/target/fabrics-cmd.c b/drivers/nvme/target/fabrics-cmd.c index d16b55ffe79f..f7297473d9eb 100644 --- a/drivers/nvme/target/fabrics-cmd.c +++ b/drivers/nvme/target/fabrics-cmd.c @@ -12,6 +12,9 @@ static void nvmet_execute_prop_set(struct nvmet_req *req) u64 val = le64_to_cpu(req->cmd->prop_set.value); u16 status = 0; + if (!nvmet_check_data_len(req, 0)) + return; + if (req->cmd->prop_set.attrib & 1) { req->error_loc = offsetof(struct nvmf_property_set_command, attrib); @@ -38,6 +41,9 @@ static void nvmet_execute_prop_get(struct nvmet_req *req) u16 status = 0; u64 val = 0; + if (!nvmet_check_data_len(req, 0)) + return; + if (req->cmd->prop_get.attrib & 1) { switch (le32_to_cpu(req->cmd->prop_get.offset)) { case NVME_REG_CAP: @@ -82,11 +88,9 @@ u16 nvmet_parse_fabrics_cmd(struct nvmet_req *req) switch (cmd->fabrics.fctype) { case nvme_fabrics_type_property_set: - req->data_len = 0; req->execute = nvmet_execute_prop_set; break; case nvme_fabrics_type_property_get: - req->data_len = 0; req->execute = nvmet_execute_prop_get; break; default: @@ -147,6 +151,9 @@ static void nvmet_execute_admin_connect(struct nvmet_req *req) struct nvmet_ctrl *ctrl = NULL; u16 status = 0; + if (!nvmet_check_data_len(req, sizeof(struct nvmf_connect_data))) + return; + d = kmalloc(sizeof(*d), GFP_KERNEL); if (!d) { status = NVME_SC_INTERNAL; @@ -211,6 +218,9 @@ static void nvmet_execute_io_connect(struct nvmet_req *req) u16 qid = le16_to_cpu(c->qid); u16 status = 0; + if (!nvmet_check_data_len(req, sizeof(struct nvmf_connect_data))) + return; + d = kmalloc(sizeof(*d), GFP_KERNEL); if (!d) { status = NVME_SC_INTERNAL; @@ -281,7 +291,6 @@ u16 nvmet_parse_connect_cmd(struct nvmet_req *req) return NVME_SC_INVALID_OPCODE | NVME_SC_DNR; } - req->data_len = sizeof(struct nvmf_connect_data); if (cmd->connect.qid == 0) req->execute = nvmet_execute_admin_connect; else diff --git a/drivers/nvme/target/fc.c b/drivers/nvme/target/fc.c index ce8d819f86cc..a0db6371b43e 100644 --- a/drivers/nvme/target/fc.c +++ b/drivers/nvme/target/fc.c @@ -1495,20 +1495,20 @@ static void nvmet_fc_ls_disconnect(struct nvmet_fc_tgtport *tgtport, struct nvmet_fc_ls_iod *iod) { - struct fcnvme_ls_disconnect_rqst *rqst = - (struct fcnvme_ls_disconnect_rqst *)iod->rqstbuf; - struct fcnvme_ls_disconnect_acc *acc = - (struct fcnvme_ls_disconnect_acc *)iod->rspbuf; + struct fcnvme_ls_disconnect_assoc_rqst *rqst = + (struct fcnvme_ls_disconnect_assoc_rqst *)iod->rqstbuf; + struct fcnvme_ls_disconnect_assoc_acc *acc = + (struct fcnvme_ls_disconnect_assoc_acc *)iod->rspbuf; struct nvmet_fc_tgt_assoc *assoc; int ret = 0; memset(acc, 0, sizeof(*acc)); - if (iod->rqstdatalen < sizeof(struct fcnvme_ls_disconnect_rqst)) + if (iod->rqstdatalen < sizeof(struct fcnvme_ls_disconnect_assoc_rqst)) ret = VERR_DISCONN_LEN; else if (rqst->desc_list_len != fcnvme_lsdesc_len( - sizeof(struct fcnvme_ls_disconnect_rqst))) + sizeof(struct fcnvme_ls_disconnect_assoc_rqst))) ret = VERR_DISCONN_RQST_LEN; else if (rqst->associd.desc_tag != cpu_to_be32(FCNVME_LSDESC_ASSOC_ID)) ret = VERR_ASSOC_ID; @@ -1523,8 +1523,11 @@ nvmet_fc_ls_disconnect(struct nvmet_fc_tgtport *tgtport, fcnvme_lsdesc_len( sizeof(struct fcnvme_lsdesc_disconn_cmd))) ret = VERR_DISCONN_CMD_LEN; - else if ((rqst->discon_cmd.scope != FCNVME_DISCONN_ASSOCIATION) && - (rqst->discon_cmd.scope != FCNVME_DISCONN_CONNECTION)) + /* + * As the standard changed on the LS, check if old format and scope + * something other than Association (e.g. 0). + */ + else if (rqst->discon_cmd.rsvd8[0]) ret = VERR_DISCONN_SCOPE; else { /* match an active association */ @@ -1556,8 +1559,8 @@ nvmet_fc_ls_disconnect(struct nvmet_fc_tgtport *tgtport, nvmet_fc_format_rsp_hdr(acc, FCNVME_LS_ACC, fcnvme_lsdesc_len( - sizeof(struct fcnvme_ls_disconnect_acc)), - FCNVME_LS_DISCONNECT); + sizeof(struct fcnvme_ls_disconnect_assoc_acc)), + FCNVME_LS_DISCONNECT_ASSOC); /* release get taken in nvmet_fc_find_target_assoc */ nvmet_fc_tgt_a_put(iod->assoc); @@ -1632,7 +1635,7 @@ nvmet_fc_handle_ls_rqst(struct nvmet_fc_tgtport *tgtport, /* Creates an IO Queue/Connection */ nvmet_fc_ls_create_connection(tgtport, iod); break; - case FCNVME_LS_DISCONNECT: + case FCNVME_LS_DISCONNECT_ASSOC: /* Terminate a Queue/Connection or the Association */ nvmet_fc_ls_disconnect(tgtport, iod); break; @@ -2015,7 +2018,7 @@ nvmet_fc_fod_op_done(struct nvmet_fc_fcp_iod *fod) } /* data transfer complete, resume with nvmet layer */ - nvmet_req_execute(&fod->req); + fod->req.execute(&fod->req); break; case NVMET_FCOP_READDATA: @@ -2231,7 +2234,7 @@ nvmet_fc_handle_fcp_rqst(struct nvmet_fc_tgtport *tgtport, * can invoke the nvmet_layer now. If read data, cmd completion will * push the data */ - nvmet_req_execute(&fod->req); + fod->req.execute(&fod->req); return; transport_error: @@ -2299,7 +2302,7 @@ nvmet_fc_rcv_fcp_req(struct nvmet_fc_target_port *target_port, /* validate iu, so the connection id can be used to find the queue */ if ((cmdiubuf_len != sizeof(*cmdiu)) || - (cmdiu->scsi_id != NVME_CMD_SCSI_ID) || + (cmdiu->format_id != NVME_CMD_FORMAT_ID) || (cmdiu->fc_id != NVME_CMD_FC_ID) || (be16_to_cpu(cmdiu->iu_len) != (sizeof(*cmdiu)/4))) return -EIO; diff --git a/drivers/nvme/target/io-cmd-bdev.c b/drivers/nvme/target/io-cmd-bdev.c index 32008d85172b..b6fca0e421ef 100644 --- a/drivers/nvme/target/io-cmd-bdev.c +++ b/drivers/nvme/target/io-cmd-bdev.c @@ -147,8 +147,12 @@ static void nvmet_bdev_execute_rw(struct nvmet_req *req) int sg_cnt = req->sg_cnt; struct bio *bio; struct scatterlist *sg; + struct blk_plug plug; sector_t sector; - int op, op_flags = 0, i; + int op, i; + + if (!nvmet_check_data_len(req, nvmet_rw_len(req))) + return; if (!req->sg_cnt) { nvmet_req_complete(req, 0); @@ -156,21 +160,20 @@ static void nvmet_bdev_execute_rw(struct nvmet_req *req) } if (req->cmd->rw.opcode == nvme_cmd_write) { - op = REQ_OP_WRITE; - op_flags = REQ_SYNC | REQ_IDLE; + op = REQ_OP_WRITE | REQ_SYNC | REQ_IDLE; if (req->cmd->rw.control & cpu_to_le16(NVME_RW_FUA)) - op_flags |= REQ_FUA; + op |= REQ_FUA; } else { op = REQ_OP_READ; } if (is_pci_p2pdma_page(sg_page(req->sg))) - op_flags |= REQ_NOMERGE; + op |= REQ_NOMERGE; sector = le64_to_cpu(req->cmd->rw.slba); sector <<= (req->ns->blksize_shift - 9); - if (req->data_len <= NVMET_MAX_INLINE_DATA_LEN) { + if (req->transfer_len <= NVMET_MAX_INLINE_DATA_LEN) { bio = &req->b.inline_bio; bio_init(bio, req->inline_bvec, ARRAY_SIZE(req->inline_bvec)); } else { @@ -180,8 +183,9 @@ static void nvmet_bdev_execute_rw(struct nvmet_req *req) bio->bi_iter.bi_sector = sector; bio->bi_private = req; bio->bi_end_io = nvmet_bio_done; - bio_set_op_attrs(bio, op, op_flags); + bio->bi_opf = op; + blk_start_plug(&plug); for_each_sg(req->sg, sg, req->sg_cnt, i) { while (bio_add_page(bio, sg_page(sg), sg->length, sg->offset) != sg->length) { @@ -190,7 +194,7 @@ static void nvmet_bdev_execute_rw(struct nvmet_req *req) bio = bio_alloc(GFP_KERNEL, min(sg_cnt, BIO_MAX_PAGES)); bio_set_dev(bio, req->ns->bdev); bio->bi_iter.bi_sector = sector; - bio_set_op_attrs(bio, op, op_flags); + bio->bi_opf = op; bio_chain(bio, prev); submit_bio(prev); @@ -201,12 +205,16 @@ static void nvmet_bdev_execute_rw(struct nvmet_req *req) } submit_bio(bio); + blk_finish_plug(&plug); } static void nvmet_bdev_execute_flush(struct nvmet_req *req) { struct bio *bio = &req->b.inline_bio; + if (!nvmet_check_data_len(req, 0)) + return; + bio_init(bio, req->inline_bvec, ARRAY_SIZE(req->inline_bvec)); bio_set_dev(bio, req->ns->bdev); bio->bi_private = req; @@ -261,12 +269,10 @@ static void nvmet_bdev_execute_discard(struct nvmet_req *req) if (bio) { bio->bi_private = req; bio->bi_end_io = nvmet_bio_done; - if (status) { - bio->bi_status = BLK_STS_IOERR; - bio_endio(bio); - } else { + if (status) + bio_io_error(bio); + else submit_bio(bio); - } } else { nvmet_req_complete(req, status); } @@ -274,6 +280,9 @@ static void nvmet_bdev_execute_discard(struct nvmet_req *req) static void nvmet_bdev_execute_dsm(struct nvmet_req *req) { + if (!nvmet_check_data_len(req, nvmet_dsm_len(req))) + return; + switch (le32_to_cpu(req->cmd->dsm.attributes)) { case NVME_DSMGMT_AD: nvmet_bdev_execute_discard(req); @@ -295,6 +304,9 @@ static void nvmet_bdev_execute_write_zeroes(struct nvmet_req *req) sector_t nr_sector; int ret; + if (!nvmet_check_data_len(req, 0)) + return; + sector = le64_to_cpu(write_zeroes->slba) << (req->ns->blksize_shift - 9); nr_sector = (((sector_t)le16_to_cpu(write_zeroes->length) + 1) << @@ -319,20 +331,15 @@ u16 nvmet_bdev_parse_io_cmd(struct nvmet_req *req) case nvme_cmd_read: case nvme_cmd_write: req->execute = nvmet_bdev_execute_rw; - req->data_len = nvmet_rw_len(req); return 0; case nvme_cmd_flush: req->execute = nvmet_bdev_execute_flush; - req->data_len = 0; return 0; case nvme_cmd_dsm: req->execute = nvmet_bdev_execute_dsm; - req->data_len = (le32_to_cpu(cmd->dsm.nr) + 1) * - sizeof(struct nvme_dsm_range); return 0; case nvme_cmd_write_zeroes: req->execute = nvmet_bdev_execute_write_zeroes; - req->data_len = 0; return 0; default: pr_err("unhandled cmd %d on qid %d\n", cmd->common.opcode, diff --git a/drivers/nvme/target/io-cmd-file.c b/drivers/nvme/target/io-cmd-file.c index 05453f5d1448..caebfce06605 100644 --- a/drivers/nvme/target/io-cmd-file.c +++ b/drivers/nvme/target/io-cmd-file.c @@ -126,7 +126,7 @@ static void nvmet_file_io_done(struct kiocb *iocb, long ret, long ret2) mempool_free(req->f.bvec, req->ns->bvec_pool); } - if (unlikely(ret != req->data_len)) + if (unlikely(ret != req->transfer_len)) status = errno_to_nvme_status(req, ret); nvmet_req_complete(req, status); } @@ -146,7 +146,7 @@ static bool nvmet_file_execute_io(struct nvmet_req *req, int ki_flags) is_sync = true; pos = le64_to_cpu(req->cmd->rw.slba) << req->ns->blksize_shift; - if (unlikely(pos + req->data_len > req->ns->size)) { + if (unlikely(pos + req->transfer_len > req->ns->size)) { nvmet_req_complete(req, errno_to_nvme_status(req, -ENOSPC)); return true; } @@ -173,7 +173,7 @@ static bool nvmet_file_execute_io(struct nvmet_req *req, int ki_flags) nr_bvec--; } - if (WARN_ON_ONCE(total_len != req->data_len)) { + if (WARN_ON_ONCE(total_len != req->transfer_len)) { ret = -EIO; goto complete; } @@ -232,6 +232,9 @@ static void nvmet_file_execute_rw(struct nvmet_req *req) { ssize_t nr_bvec = req->sg_cnt; + if (!nvmet_check_data_len(req, nvmet_rw_len(req))) + return; + if (!req->sg_cnt || !nr_bvec) { nvmet_req_complete(req, 0); return; @@ -273,6 +276,8 @@ static void nvmet_file_flush_work(struct work_struct *w) static void nvmet_file_execute_flush(struct nvmet_req *req) { + if (!nvmet_check_data_len(req, 0)) + return; INIT_WORK(&req->f.work, nvmet_file_flush_work); schedule_work(&req->f.work); } @@ -331,6 +336,8 @@ static void nvmet_file_dsm_work(struct work_struct *w) static void nvmet_file_execute_dsm(struct nvmet_req *req) { + if (!nvmet_check_data_len(req, nvmet_dsm_len(req))) + return; INIT_WORK(&req->f.work, nvmet_file_dsm_work); schedule_work(&req->f.work); } @@ -359,6 +366,8 @@ static void nvmet_file_write_zeroes_work(struct work_struct *w) static void nvmet_file_execute_write_zeroes(struct nvmet_req *req) { + if (!nvmet_check_data_len(req, 0)) + return; INIT_WORK(&req->f.work, nvmet_file_write_zeroes_work); schedule_work(&req->f.work); } @@ -371,20 +380,15 @@ u16 nvmet_file_parse_io_cmd(struct nvmet_req *req) case nvme_cmd_read: case nvme_cmd_write: req->execute = nvmet_file_execute_rw; - req->data_len = nvmet_rw_len(req); return 0; case nvme_cmd_flush: req->execute = nvmet_file_execute_flush; - req->data_len = 0; return 0; case nvme_cmd_dsm: req->execute = nvmet_file_execute_dsm; - req->data_len = (le32_to_cpu(cmd->dsm.nr) + 1) * - sizeof(struct nvme_dsm_range); return 0; case nvme_cmd_write_zeroes: req->execute = nvmet_file_execute_write_zeroes; - req->data_len = 0; return 0; default: pr_err("unhandled cmd for file ns %d on qid %d\n", diff --git a/drivers/nvme/target/loop.c b/drivers/nvme/target/loop.c index 11f5aea97d1b..a758bb3d5dd4 100644 --- a/drivers/nvme/target/loop.c +++ b/drivers/nvme/target/loop.c @@ -76,7 +76,6 @@ static void nvme_loop_complete_rq(struct request *req) { struct nvme_loop_iod *iod = blk_mq_rq_to_pdu(req); - nvme_cleanup_cmd(req); sg_free_table_chained(&iod->sg_table, SG_CHUNK_SIZE); nvme_complete_rq(req); } @@ -102,8 +101,8 @@ static void nvme_loop_queue_response(struct nvmet_req *req) * aborts. We don't even bother to allocate a struct request * for them but rather special case them here. */ - if (unlikely(nvme_loop_queue_idx(queue) == 0 && - cqe->command_id >= NVME_AQ_BLK_MQ_DEPTH)) { + if (unlikely(nvme_is_aen_req(nvme_loop_queue_idx(queue), + cqe->command_id))) { nvme_complete_async_event(&queue->ctrl->ctrl, cqe->status, &cqe->result); } else { @@ -126,7 +125,7 @@ static void nvme_loop_execute_work(struct work_struct *work) struct nvme_loop_iod *iod = container_of(work, struct nvme_loop_iod, work); - nvmet_req_execute(&iod->req); + iod->req.execute(&iod->req); } static blk_status_t nvme_loop_queue_rq(struct blk_mq_hw_ctx *hctx, diff --git a/drivers/nvme/target/nvmet.h b/drivers/nvme/target/nvmet.h index c51f8dd01dc4..46df45e837c9 100644 --- a/drivers/nvme/target/nvmet.h +++ b/drivers/nvme/target/nvmet.h @@ -304,8 +304,6 @@ struct nvmet_req { } f; }; int sg_cnt; - /* data length as parsed from the command: */ - size_t data_len; /* data length as parsed from the SGL descriptor: */ size_t transfer_len; @@ -375,7 +373,7 @@ u16 nvmet_parse_fabrics_cmd(struct nvmet_req *req); bool nvmet_req_init(struct nvmet_req *req, struct nvmet_cq *cq, struct nvmet_sq *sq, const struct nvmet_fabrics_ops *ops); void nvmet_req_uninit(struct nvmet_req *req); -void nvmet_req_execute(struct nvmet_req *req); +bool nvmet_check_data_len(struct nvmet_req *req, size_t data_len); void nvmet_req_complete(struct nvmet_req *req, u16 status); int nvmet_req_alloc_sgl(struct nvmet_req *req); void nvmet_req_free_sgl(struct nvmet_req *req); @@ -495,6 +493,12 @@ static inline u32 nvmet_rw_len(struct nvmet_req *req) req->ns->blksize_shift; } +static inline u32 nvmet_dsm_len(struct nvmet_req *req) +{ + return (le32_to_cpu(req->cmd->dsm.nr) + 1) * + sizeof(struct nvme_dsm_range); +} + u16 errno_to_nvme_status(struct nvmet_req *req, int errno); /* Convert a 32-bit number to a 16-bit 0's based number */ diff --git a/drivers/nvme/target/rdma.c b/drivers/nvme/target/rdma.c index 36d906a7f70d..37d262a65877 100644 --- a/drivers/nvme/target/rdma.c +++ b/drivers/nvme/target/rdma.c @@ -603,7 +603,7 @@ static void nvmet_rdma_read_data_done(struct ib_cq *cq, struct ib_wc *wc) return; } - nvmet_req_execute(&rsp->req); + rsp->req.execute(&rsp->req); } static void nvmet_rdma_use_inline_sg(struct nvmet_rdma_rsp *rsp, u32 len, @@ -672,13 +672,13 @@ static u16 nvmet_rdma_map_sgl_keyed(struct nvmet_rdma_rsp *rsp, return 0; ret = nvmet_req_alloc_sgl(&rsp->req); - if (ret < 0) + if (unlikely(ret < 0)) goto error_out; ret = rdma_rw_ctx_init(&rsp->rw, cm_id->qp, cm_id->port_num, rsp->req.sg, rsp->req.sg_cnt, 0, addr, key, nvmet_data_dir(&rsp->req)); - if (ret < 0) + if (unlikely(ret < 0)) goto error_out; rsp->n_rdma += ret; @@ -746,7 +746,7 @@ static bool nvmet_rdma_execute_command(struct nvmet_rdma_rsp *rsp) queue->cm_id->port_num, &rsp->read_cqe, NULL)) nvmet_req_complete(&rsp->req, NVME_SC_DATA_XFER_ERROR); } else { - nvmet_req_execute(&rsp->req); + rsp->req.execute(&rsp->req); } return true; diff --git a/drivers/nvme/target/tcp.c b/drivers/nvme/target/tcp.c index d535080b781f..af674fc0bb1e 100644 --- a/drivers/nvme/target/tcp.c +++ b/drivers/nvme/target/tcp.c @@ -320,7 +320,7 @@ static int nvmet_tcp_map_data(struct nvmet_tcp_cmd *cmd) struct nvme_sgl_desc *sgl = &cmd->req.cmd->common.dptr.sgl; u32 len = le32_to_cpu(sgl->length); - if (!cmd->req.data_len) + if (!len) return 0; if (sgl->type == ((NVME_SGL_FMT_DATA_DESC << 4) | @@ -813,13 +813,11 @@ free_crypto: static void nvmet_tcp_handle_req_failure(struct nvmet_tcp_queue *queue, struct nvmet_tcp_cmd *cmd, struct nvmet_req *req) { + size_t data_len = le32_to_cpu(req->cmd->common.dptr.sgl.length); int ret; - /* recover the expected data transfer length */ - req->data_len = le32_to_cpu(req->cmd->common.dptr.sgl.length); - if (!nvme_is_write(cmd->req.cmd) || - req->data_len > cmd->req.port->inline_data_size) { + data_len > cmd->req.port->inline_data_size) { nvmet_prepare_receive_pdu(queue); return; } @@ -932,7 +930,7 @@ static int nvmet_tcp_done_recv_pdu(struct nvmet_tcp_queue *queue) goto out; } - nvmet_req_execute(&queue->cmd->req); + queue->cmd->req.execute(&queue->cmd->req); out: nvmet_prepare_receive_pdu(queue); return ret; @@ -1052,7 +1050,7 @@ static int nvmet_tcp_try_recv_data(struct nvmet_tcp_queue *queue) nvmet_tcp_prep_recv_ddgst(cmd); return 0; } - nvmet_req_execute(&cmd->req); + cmd->req.execute(&cmd->req); } nvmet_prepare_receive_pdu(queue); @@ -1092,7 +1090,7 @@ static int nvmet_tcp_try_recv_ddgst(struct nvmet_tcp_queue *queue) if (!(cmd->flags & NVMET_TCP_F_INIT_FAILED) && cmd->rbytes_done == cmd->req.transfer_len) - nvmet_req_execute(&cmd->req); + cmd->req.execute(&cmd->req); ret = 0; out: nvmet_prepare_receive_pdu(queue); diff --git a/include/linux/nvme-fc.h b/include/linux/nvme-fc.h index 067c9fea64fe..e8c30b39bb27 100644 --- a/include/linux/nvme-fc.h +++ b/include/linux/nvme-fc.h @@ -4,33 +4,60 @@ */ /* - * This file contains definitions relative to FC-NVME r1.14 (16-020vB). - * The fcnvme_lsdesc_cr_assoc_cmd struct reflects expected r1.16 content. + * This file contains definitions relative to FC-NVME-2 r1.06 + * (T11-2019-00210-v001). */ #ifndef _NVME_FC_H #define _NVME_FC_H 1 +#include <uapi/scsi/fc/fc_fs.h> -#define NVME_CMD_SCSI_ID 0xFD +#define NVME_CMD_FORMAT_ID 0xFD #define NVME_CMD_FC_ID FC_TYPE_NVME /* FC-NVME Cmd IU Flags */ -#define FCNVME_CMD_FLAGS_DIRMASK 0x03 -#define FCNVME_CMD_FLAGS_WRITE 0x01 -#define FCNVME_CMD_FLAGS_READ 0x02 +enum { + FCNVME_CMD_FLAGS_DIRMASK = 0x03, + FCNVME_CMD_FLAGS_WRITE = (1 << 0), + FCNVME_CMD_FLAGS_READ = (1 << 1), + + FCNVME_CMD_FLAGS_PICWP = (1 << 2), +}; + +enum { + FCNVME_CMD_CAT_MASK = 0x0F, + FCNVME_CMD_CAT_ADMINQ = 0x01, + FCNVME_CMD_CAT_CSSMASK = 0x07, + FCNVME_CMD_CAT_CSSFLAG = 0x08, +}; + +static inline __u8 fccmnd_set_cat_admin(__u8 rsv_cat) +{ + return (rsv_cat & ~FCNVME_CMD_CAT_MASK) | FCNVME_CMD_CAT_ADMINQ; +} + +static inline __u8 fccmnd_set_cat_css(__u8 rsv_cat, __u8 css) +{ + return (rsv_cat & ~FCNVME_CMD_CAT_MASK) | FCNVME_CMD_CAT_CSSFLAG | + (css & FCNVME_CMD_CAT_CSSMASK); +} struct nvme_fc_cmd_iu { - __u8 scsi_id; + __u8 format_id; __u8 fc_id; __be16 iu_len; - __u8 rsvd4[3]; + __u8 rsvd4[2]; + __u8 rsv_cat; __u8 flags; __be64 connection_id; __be32 csn; __be32 data_len; struct nvme_command sqe; - __be32 rsvd88[2]; + __u8 dps; + __u8 lbads; + __be16 ms; + __be32 rsvd92; }; #define NVME_FC_SIZEOF_ZEROS_RSP 12 @@ -38,11 +65,12 @@ struct nvme_fc_cmd_iu { enum { FCNVME_SC_SUCCESS = 0, FCNVME_SC_INVALID_FIELD = 1, - FCNVME_SC_INVALID_CONNID = 2, + /* reserved 2 */ + FCNVME_SC_ILL_CONN_PARAMS = 3, }; struct nvme_fc_ersp_iu { - __u8 status_code; + __u8 ersp_result; __u8 rsvd1; __be16 iu_len; __be32 rsn; @@ -53,14 +81,44 @@ struct nvme_fc_ersp_iu { }; -/* FC-NVME Link Services */ +#define FCNVME_NVME_SR_OPCODE 0x01 + +struct nvme_fc_nvme_sr_iu { + __u8 fc_id; + __u8 opcode; + __u8 rsvd2; + __u8 retry_rctl; + __be32 rsvd4; +}; + + +enum { + FCNVME_SRSTAT_ACC = 0x0, + FCNVME_SRSTAT_INV_FCID = 0x1, + /* reserved 0x2 */ + FCNVME_SRSTAT_LOGICAL_ERR = 0x3, + FCNVME_SRSTAT_INV_QUALIF = 0x4, + FCNVME_SRSTAT_UNABL2PERFORM = 0x9, +}; + +struct nvme_fc_nvme_sr_rsp_iu { + __u8 fc_id; + __u8 opcode; + __u8 rsvd2; + __u8 status; + __be32 rsvd4; +}; + + +/* FC-NVME Link Services - LS cmd values (w0 bits 31:24) */ enum { FCNVME_LS_RSVD = 0, FCNVME_LS_RJT = 1, FCNVME_LS_ACC = 2, - FCNVME_LS_CREATE_ASSOCIATION = 3, - FCNVME_LS_CREATE_CONNECTION = 4, - FCNVME_LS_DISCONNECT = 5, + FCNVME_LS_CREATE_ASSOCIATION = 3, /* Create Association */ + FCNVME_LS_CREATE_CONNECTION = 4, /* Create I/O Connection */ + FCNVME_LS_DISCONNECT_ASSOC = 5, /* Disconnect Association */ + FCNVME_LS_DISCONNECT_CONN = 6, /* Disconnect Connection */ }; /* FC-NVME Link Service Descriptors */ @@ -117,14 +175,17 @@ enum fcnvme_ls_rjt_reason { FCNVME_RJT_RC_UNSUP = 0x0b, /* command not supported */ - FCNVME_RJT_RC_INPROG = 0x0e, - /* command already in progress */ - FCNVME_RJT_RC_INV_ASSOC = 0x40, - /* Invalid Association ID*/ + /* Invalid Association ID */ FCNVME_RJT_RC_INV_CONN = 0x41, - /* Invalid Connection ID*/ + /* Invalid Connection ID */ + + FCNVME_RJT_RC_INV_PARAM = 0x42, + /* Invalid Parameters */ + + FCNVME_RJT_RC_INSUF_RES = 0x43, + /* Insufficient Resources */ FCNVME_RJT_RC_VENDOR = 0xff, /* vendor specific error */ @@ -138,14 +199,32 @@ enum fcnvme_ls_rjt_explan { FCNVME_RJT_EXP_OXID_RXID = 0x17, /* invalid OX_ID-RX_ID combination */ - FCNVME_RJT_EXP_INSUF_RES = 0x29, - /* insufficient resources */ - FCNVME_RJT_EXP_UNAB_DATA = 0x2a, /* unable to supply requested data */ FCNVME_RJT_EXP_INV_LEN = 0x2d, /* Invalid payload length */ + + FCNVME_RJT_EXP_INV_ERSP_RAT = 0x40, + /* Invalid NVMe_ERSP Ratio */ + + FCNVME_RJT_EXP_INV_CTLR_ID = 0x41, + /* Invalid Controller ID */ + + FCNVME_RJT_EXP_INV_QUEUE_ID = 0x42, + /* Invalid Queue ID */ + + FCNVME_RJT_EXP_INV_SQSIZE = 0x43, + /* Invalid Submission Queue Size */ + + FCNVME_RJT_EXP_INV_HOSTID = 0x44, + /* Invalid HOST ID */ + + FCNVME_RJT_EXP_INV_HOSTNQN = 0x45, + /* Invalid HOSTNQN */ + + FCNVME_RJT_EXP_INV_SUBNQN = 0x46, + /* Invalid SUBNQN */ }; /* FCNVME_LSDESC_RJT */ @@ -209,21 +288,11 @@ struct fcnvme_lsdesc_cr_conn_cmd { __be32 rsvd52; }; -/* Disconnect Scope Values */ -enum { - FCNVME_DISCONN_ASSOCIATION = 0, - FCNVME_DISCONN_CONNECTION = 1, -}; - /* FCNVME_LSDESC_DISCONN_CMD */ struct fcnvme_lsdesc_disconn_cmd { __be32 desc_tag; /* FCNVME_LSDESC_xxx */ __be32 desc_len; - u8 rsvd8[3]; - /* note: scope is really a 1 bit field */ - u8 scope; /* FCNVME_DISCONN_xxx */ - __be32 rsvd12; - __be64 id; + __be32 rsvd8[4]; }; /* FCNVME_LSDESC_CONN_ID */ @@ -242,9 +311,14 @@ struct fcnvme_lsdesc_assoc_id { /* r_ctl values */ enum { - FCNVME_RS_RCTL_DATA = 1, - FCNVME_RS_RCTL_XFER_RDY = 5, - FCNVME_RS_RCTL_RSP = 8, + FCNVME_RS_RCTL_CMND = 0x6, + FCNVME_RS_RCTL_DATA = 0x1, + FCNVME_RS_RCTL_CONF = 0x3, + FCNVME_RS_RCTL_SR = 0x9, + FCNVME_RS_RCTL_XFER_RDY = 0x5, + FCNVME_RS_RCTL_RSP = 0x7, + FCNVME_RS_RCTL_ERSP = 0x8, + FCNVME_RS_RCTL_SR_RSP = 0xA, }; @@ -264,7 +338,10 @@ struct fcnvme_ls_acc_hdr { struct fcnvme_ls_rqst_w0 w0; __be32 desc_list_len; struct fcnvme_lsdesc_rqst rqst; - /* Followed by cmd-specific ACC descriptors, see next definitions */ + /* + * Followed by cmd-specific ACCEPT descriptors, see xxx_acc + * definitions below + */ }; /* FCNVME_LS_CREATE_ASSOCIATION */ @@ -302,25 +379,39 @@ struct fcnvme_ls_cr_conn_acc { struct fcnvme_lsdesc_conn_id connectid; }; -/* FCNVME_LS_DISCONNECT */ -struct fcnvme_ls_disconnect_rqst { +/* FCNVME_LS_DISCONNECT_ASSOC */ +struct fcnvme_ls_disconnect_assoc_rqst { struct fcnvme_ls_rqst_w0 w0; __be32 desc_list_len; struct fcnvme_lsdesc_assoc_id associd; struct fcnvme_lsdesc_disconn_cmd discon_cmd; }; -struct fcnvme_ls_disconnect_acc { +struct fcnvme_ls_disconnect_assoc_acc { + struct fcnvme_ls_acc_hdr hdr; +}; + + +/* FCNVME_LS_DISCONNECT_CONN */ +struct fcnvme_ls_disconnect_conn_rqst { + struct fcnvme_ls_rqst_w0 w0; + __be32 desc_list_len; + struct fcnvme_lsdesc_assoc_id associd; + struct fcnvme_lsdesc_disconn_cmd connectid; +}; + +struct fcnvme_ls_disconnect_conn_acc { struct fcnvme_ls_acc_hdr hdr; }; /* - * Yet to be defined in FC-NVME: + * Default R_A_TOV is pulled in from fc_fs.h but needs conversion + * from ms to seconds for our use. */ -#define NVME_FC_CONNECT_TIMEOUT_SEC 2 /* 2 seconds */ -#define NVME_FC_LS_TIMEOUT_SEC 2 /* 2 seconds */ -#define NVME_FC_TGTOP_TIMEOUT_SEC 2 /* 2 seconds */ +#define FC_TWO_TIMES_R_A_TOV (2 * (FC_DEF_R_A_TOV / 1000)) +#define NVME_FC_LS_TIMEOUT_SEC FC_TWO_TIMES_R_A_TOV +#define NVME_FC_TGTOP_TIMEOUT_SEC FC_TWO_TIMES_R_A_TOV /* * TRADDR string must be of form "nn-<16hexdigits>:pn-<16hexdigits>" @@ -328,6 +419,7 @@ struct fcnvme_ls_disconnect_acc { * infront of the <16hexdigits>. Without is considered the "min" string * and with is considered the "max" string. The hexdigits may be upper * or lower case. + * Note: FC-NVME-2 standard requires a "0x" prefix. */ #define NVME_FC_TRADDR_NNLEN 3 /* "?n-" */ #define NVME_FC_TRADDR_OXNNLEN 5 /* "?n-0x" */ diff --git a/include/linux/nvme.h b/include/linux/nvme.h index f61d6906e59d..3eca4f7d8510 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -107,8 +107,22 @@ enum { NVME_REG_AQA = 0x0024, /* Admin Queue Attributes */ NVME_REG_ASQ = 0x0028, /* Admin SQ Base Address */ NVME_REG_ACQ = 0x0030, /* Admin CQ Base Address */ - NVME_REG_CMBLOC = 0x0038, /* Controller Memory Buffer Location */ + NVME_REG_CMBLOC = 0x0038, /* Controller Memory Buffer Location */ NVME_REG_CMBSZ = 0x003c, /* Controller Memory Buffer Size */ + NVME_REG_BPINFO = 0x0040, /* Boot Partition Information */ + NVME_REG_BPRSEL = 0x0044, /* Boot Partition Read Select */ + NVME_REG_BPMBL = 0x0048, /* Boot Partition Memory Buffer + * Location + */ + NVME_REG_PMRCAP = 0x0e00, /* Persistent Memory Capabilities */ + NVME_REG_PMRCTL = 0x0e04, /* Persistent Memory Region Control */ + NVME_REG_PMRSTS = 0x0e08, /* Persistent Memory Region Status */ + NVME_REG_PMREBS = 0x0e0c, /* Persistent Memory Region Elasticity + * Buffer Size + */ + NVME_REG_PMRSWTP = 0x0e10, /* Persistent Memory Region Sustained + * Write Throughput + */ NVME_REG_DBS = 0x1000, /* SQ 0 Tail Doorbell */ }; @@ -295,6 +309,14 @@ enum { NVME_CTRL_OACS_DIRECTIVES = 1 << 5, NVME_CTRL_OACS_DBBUF_SUPP = 1 << 8, NVME_CTRL_LPA_CMD_EFFECTS_LOG = 1 << 1, + NVME_CTRL_CTRATT_128_ID = 1 << 0, + NVME_CTRL_CTRATT_NON_OP_PSP = 1 << 1, + NVME_CTRL_CTRATT_NVM_SETS = 1 << 2, + NVME_CTRL_CTRATT_READ_RECV_LVLS = 1 << 3, + NVME_CTRL_CTRATT_ENDURANCE_GROUPS = 1 << 4, + NVME_CTRL_CTRATT_PREDICTABLE_LAT = 1 << 5, + NVME_CTRL_CTRATT_NAMESPACE_GRANULARITY = 1 << 7, + NVME_CTRL_CTRATT_UUID_LIST = 1 << 9, }; struct nvme_lbaf { @@ -352,6 +374,9 @@ enum { NVME_ID_CNS_NS_PRESENT = 0x11, NVME_ID_CNS_CTRL_NS_LIST = 0x12, NVME_ID_CNS_CTRL_LIST = 0x13, + NVME_ID_CNS_SCNDRY_CTRL_LIST = 0x15, + NVME_ID_CNS_NS_GRANULARITY = 0x16, + NVME_ID_CNS_UUID_LIST = 0x17, }; enum { @@ -409,7 +434,8 @@ struct nvme_smart_log { __u8 avail_spare; __u8 spare_thresh; __u8 percent_used; - __u8 rsvd6[26]; + __u8 endu_grp_crit_warn_sumry; + __u8 rsvd7[25]; __u8 data_units_read[16]; __u8 data_units_written[16]; __u8 host_reads[16]; @@ -423,7 +449,11 @@ struct nvme_smart_log { __le32 warning_temp_time; __le32 critical_comp_time; __le16 temp_sensor[8]; - __u8 rsvd216[296]; + __le32 thm_temp1_trans_count; + __le32 thm_temp2_trans_count; + __le32 thm_temp1_total_time; + __le32 thm_temp2_total_time; + __u8 rsvd232[280]; }; struct nvme_fw_slot_info_log { @@ -440,6 +470,7 @@ enum { NVME_CMD_EFFECTS_NIC = 1 << 3, NVME_CMD_EFFECTS_CCC = 1 << 4, NVME_CMD_EFFECTS_CSE_MASK = 3 << 16, + NVME_CMD_EFFECTS_UUID_SEL = 1 << 19, }; struct nvme_effects_log { @@ -563,6 +594,7 @@ enum nvme_opcode { nvme_cmd_compare = 0x05, nvme_cmd_write_zeroes = 0x08, nvme_cmd_dsm = 0x09, + nvme_cmd_verify = 0x0c, nvme_cmd_resv_register = 0x0d, nvme_cmd_resv_report = 0x0e, nvme_cmd_resv_acquire = 0x11, @@ -806,10 +838,14 @@ enum nvme_admin_opcode { nvme_admin_ns_mgmt = 0x0d, nvme_admin_activate_fw = 0x10, nvme_admin_download_fw = 0x11, + nvme_admin_dev_self_test = 0x14, nvme_admin_ns_attach = 0x15, nvme_admin_keep_alive = 0x18, nvme_admin_directive_send = 0x19, nvme_admin_directive_recv = 0x1a, + nvme_admin_virtual_mgmt = 0x1c, + nvme_admin_nvme_mi_send = 0x1d, + nvme_admin_nvme_mi_recv = 0x1e, nvme_admin_dbbuf = 0x7C, nvme_admin_format_nvm = 0x80, nvme_admin_security_send = 0x81, @@ -873,6 +909,7 @@ enum { NVME_FEAT_PLM_CONFIG = 0x13, NVME_FEAT_PLM_WINDOW = 0x14, NVME_FEAT_HOST_BEHAVIOR = 0x16, + NVME_FEAT_SANITIZE = 0x17, NVME_FEAT_SW_PROGRESS = 0x80, NVME_FEAT_HOST_ID = 0x81, NVME_FEAT_RESV_MASK = 0x82, @@ -883,6 +920,10 @@ enum { NVME_LOG_FW_SLOT = 0x03, NVME_LOG_CHANGED_NS = 0x04, NVME_LOG_CMD_EFFECTS = 0x05, + NVME_LOG_DEVICE_SELF_TEST = 0x06, + NVME_LOG_TELEMETRY_HOST = 0x07, + NVME_LOG_TELEMETRY_CTRL = 0x08, + NVME_LOG_ENDURANCE_GROUP = 0x09, NVME_LOG_ANA = 0x0c, NVME_LOG_DISC = 0x70, NVME_LOG_RESERVATION = 0x80, @@ -1290,7 +1331,11 @@ enum { NVME_SC_SGL_INVALID_OFFSET = 0x16, NVME_SC_SGL_INVALID_SUBTYPE = 0x17, + NVME_SC_SANITIZE_FAILED = 0x1C, + NVME_SC_SANITIZE_IN_PROGRESS = 0x1D, + NVME_SC_NS_WRITE_PROTECTED = 0x20, + NVME_SC_CMD_INTERRUPTED = 0x21, NVME_SC_LBA_RANGE = 0x80, NVME_SC_CAP_EXCEEDED = 0x81, @@ -1328,6 +1373,8 @@ enum { NVME_SC_NS_NOT_ATTACHED = 0x11a, NVME_SC_THIN_PROV_NOT_SUPP = 0x11b, NVME_SC_CTRL_LIST_INVALID = 0x11c, + NVME_SC_BP_WRITE_PROHIBITED = 0x11e, + NVME_SC_PMR_SAN_PROHIBITED = 0x123, /* * I/O Command Set Specific - NVM commands: @@ -1368,6 +1415,7 @@ enum { NVME_SC_ANA_INACCESSIBLE = 0x302, NVME_SC_ANA_TRANSITION = 0x303, NVME_SC_HOST_PATH_ERROR = 0x370, + NVME_SC_HOST_ABORTED_CMD = 0x371, NVME_SC_CRD = 0x1800, NVME_SC_DNR = 0x4000, |