diff options
Diffstat (limited to 'net/ceph/osdmap.c')
| -rw-r--r-- | net/ceph/osdmap.c | 2990 |
1 files changed, 2441 insertions, 549 deletions
diff --git a/net/ceph/osdmap.c b/net/ceph/osdmap.c index 603ddd92db19..d245fa508e1c 100644 --- a/net/ceph/osdmap.c +++ b/net/ceph/osdmap.c @@ -1,9 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0 #include <linux/ceph/ceph_debug.h> #include <linux/module.h> #include <linux/slab.h> -#include <asm/div64.h> #include <linux/ceph/libceph.h> #include <linux/ceph/osdmap.h> @@ -11,7 +11,23 @@ #include <linux/crush/hash.h> #include <linux/crush/mapper.h> -char *ceph_osdmap_state_str(char *str, int len, int state) +static __printf(2, 3) +void osdmap_info(const struct ceph_osdmap *map, const char *fmt, ...) +{ + struct va_format vaf; + va_list args; + + va_start(args, fmt); + vaf.fmt = fmt; + vaf.va = &args; + + printk(KERN_INFO "%s (%pU e%u): %pV", KBUILD_MODNAME, &map->fsid, + map->epoch, &vaf); + + va_end(args); +} + +char *ceph_osdmap_state_str(char *str, int len, u32 state) { if (!len) return str; @@ -89,7 +105,7 @@ static int crush_decode_tree_bucket(void **p, void *end, { int j; dout("crush_decode_tree_bucket %p to %p\n", *p, end); - ceph_decode_32_safe(p, end, b->num_nodes, bad); + ceph_decode_8_safe(p, end, b->num_nodes, bad); b->node_weights = kcalloc(b->num_nodes, sizeof(u32), GFP_NOFS); if (b->node_weights == NULL) return -ENOMEM; @@ -122,30 +138,304 @@ bad: return -EINVAL; } -static int skip_name_map(void **p, void *end) +static int crush_decode_straw2_bucket(void **p, void *end, + struct crush_bucket_straw2 *b) { - int len; - ceph_decode_32_safe(p, end, len ,bad); - while (len--) { - int strlen; - *p += sizeof(u32); - ceph_decode_32_safe(p, end, strlen, bad); - *p += strlen; -} - return 0; + int j; + dout("crush_decode_straw2_bucket %p to %p\n", *p, end); + b->item_weights = kcalloc(b->h.size, sizeof(u32), GFP_NOFS); + if (b->item_weights == NULL) + return -ENOMEM; + ceph_decode_need(p, end, b->h.size * sizeof(u32), bad); + for (j = 0; j < b->h.size; j++) + b->item_weights[j] = ceph_decode_32(p); + return 0; bad: - return -EINVAL; + return -EINVAL; +} + +struct crush_name_node { + struct rb_node cn_node; + int cn_id; + char cn_name[]; +}; + +static struct crush_name_node *alloc_crush_name(size_t name_len) +{ + struct crush_name_node *cn; + + cn = kmalloc(sizeof(*cn) + name_len + 1, GFP_NOIO); + if (!cn) + return NULL; + + RB_CLEAR_NODE(&cn->cn_node); + return cn; +} + +static void free_crush_name(struct crush_name_node *cn) +{ + WARN_ON(!RB_EMPTY_NODE(&cn->cn_node)); + + kfree(cn); +} + +DEFINE_RB_FUNCS(crush_name, struct crush_name_node, cn_id, cn_node) + +static int decode_crush_names(void **p, void *end, struct rb_root *root) +{ + u32 n; + + ceph_decode_32_safe(p, end, n, e_inval); + while (n--) { + struct crush_name_node *cn; + int id; + u32 name_len; + + ceph_decode_32_safe(p, end, id, e_inval); + ceph_decode_32_safe(p, end, name_len, e_inval); + ceph_decode_need(p, end, name_len, e_inval); + + cn = alloc_crush_name(name_len); + if (!cn) + return -ENOMEM; + + cn->cn_id = id; + memcpy(cn->cn_name, *p, name_len); + cn->cn_name[name_len] = '\0'; + *p += name_len; + + if (!__insert_crush_name(root, cn)) { + free_crush_name(cn); + return -EEXIST; + } + } + + return 0; + +e_inval: + return -EINVAL; +} + +void clear_crush_names(struct rb_root *root) +{ + while (!RB_EMPTY_ROOT(root)) { + struct crush_name_node *cn = + rb_entry(rb_first(root), struct crush_name_node, cn_node); + + erase_crush_name(root, cn); + free_crush_name(cn); + } +} + +static struct crush_choose_arg_map *alloc_choose_arg_map(void) +{ + struct crush_choose_arg_map *arg_map; + + arg_map = kzalloc(sizeof(*arg_map), GFP_NOIO); + if (!arg_map) + return NULL; + + RB_CLEAR_NODE(&arg_map->node); + return arg_map; +} + +static void free_choose_arg_map(struct crush_choose_arg_map *arg_map) +{ + if (arg_map) { + int i, j; + + WARN_ON(!RB_EMPTY_NODE(&arg_map->node)); + + for (i = 0; i < arg_map->size; i++) { + struct crush_choose_arg *arg = &arg_map->args[i]; + + for (j = 0; j < arg->weight_set_size; j++) + kfree(arg->weight_set[j].weights); + kfree(arg->weight_set); + kfree(arg->ids); + } + kfree(arg_map->args); + kfree(arg_map); + } +} + +DEFINE_RB_FUNCS(choose_arg_map, struct crush_choose_arg_map, choose_args_index, + node); + +void clear_choose_args(struct crush_map *c) +{ + while (!RB_EMPTY_ROOT(&c->choose_args)) { + struct crush_choose_arg_map *arg_map = + rb_entry(rb_first(&c->choose_args), + struct crush_choose_arg_map, node); + + erase_choose_arg_map(&c->choose_args, arg_map); + free_choose_arg_map(arg_map); + } +} + +static u32 *decode_array_32_alloc(void **p, void *end, u32 *plen) +{ + u32 *a = NULL; + u32 len; + int ret; + + ceph_decode_32_safe(p, end, len, e_inval); + if (len) { + u32 i; + + a = kmalloc_array(len, sizeof(u32), GFP_NOIO); + if (!a) { + ret = -ENOMEM; + goto fail; + } + + ceph_decode_need(p, end, len * sizeof(u32), e_inval); + for (i = 0; i < len; i++) + a[i] = ceph_decode_32(p); + } + + *plen = len; + return a; + +e_inval: + ret = -EINVAL; +fail: + kfree(a); + return ERR_PTR(ret); +} + +/* + * Assumes @arg is zero-initialized. + */ +static int decode_choose_arg(void **p, void *end, struct crush_choose_arg *arg) +{ + int ret; + + ceph_decode_32_safe(p, end, arg->weight_set_size, e_inval); + if (arg->weight_set_size) { + u32 i; + + arg->weight_set = kmalloc_array(arg->weight_set_size, + sizeof(*arg->weight_set), + GFP_NOIO); + if (!arg->weight_set) + return -ENOMEM; + + for (i = 0; i < arg->weight_set_size; i++) { + struct crush_weight_set *w = &arg->weight_set[i]; + + w->weights = decode_array_32_alloc(p, end, &w->size); + if (IS_ERR(w->weights)) { + ret = PTR_ERR(w->weights); + w->weights = NULL; + return ret; + } + } + } + + arg->ids = decode_array_32_alloc(p, end, &arg->ids_size); + if (IS_ERR(arg->ids)) { + ret = PTR_ERR(arg->ids); + arg->ids = NULL; + return ret; + } + + return 0; + +e_inval: + return -EINVAL; +} + +static int decode_choose_args(void **p, void *end, struct crush_map *c) +{ + struct crush_choose_arg_map *arg_map = NULL; + u32 num_choose_arg_maps, num_buckets; + int ret; + + ceph_decode_32_safe(p, end, num_choose_arg_maps, e_inval); + while (num_choose_arg_maps--) { + arg_map = alloc_choose_arg_map(); + if (!arg_map) { + ret = -ENOMEM; + goto fail; + } + + ceph_decode_64_safe(p, end, arg_map->choose_args_index, + e_inval); + arg_map->size = c->max_buckets; + arg_map->args = kcalloc(arg_map->size, sizeof(*arg_map->args), + GFP_NOIO); + if (!arg_map->args) { + ret = -ENOMEM; + goto fail; + } + + ceph_decode_32_safe(p, end, num_buckets, e_inval); + while (num_buckets--) { + struct crush_choose_arg *arg; + u32 bucket_index; + + ceph_decode_32_safe(p, end, bucket_index, e_inval); + if (bucket_index >= arg_map->size) + goto e_inval; + + arg = &arg_map->args[bucket_index]; + ret = decode_choose_arg(p, end, arg); + if (ret) + goto fail; + + if (arg->ids_size && + arg->ids_size != c->buckets[bucket_index]->size) + goto e_inval; + } + + insert_choose_arg_map(&c->choose_args, arg_map); + } + + return 0; + +e_inval: + ret = -EINVAL; +fail: + free_choose_arg_map(arg_map); + return ret; +} + +static void crush_finalize(struct crush_map *c) +{ + __s32 b; + + /* Space for the array of pointers to per-bucket workspace */ + c->working_size = sizeof(struct crush_work) + + c->max_buckets * sizeof(struct crush_work_bucket *); + + for (b = 0; b < c->max_buckets; b++) { + if (!c->buckets[b]) + continue; + + switch (c->buckets[b]->alg) { + default: + /* + * The base case, permutation variables and + * the pointer to the permutation array. + */ + c->working_size += sizeof(struct crush_work_bucket); + break; + } + /* Every bucket has a permutation array. */ + c->working_size += c->buckets[b]->size * sizeof(__u32); + } } static struct crush_map *crush_decode(void *pbyval, void *end) { struct crush_map *c; - int err = -EINVAL; + int err; int i, j; void **p = &pbyval; void *start = pbyval; u32 magic; - u32 num_name_maps; dout("crush_decode %p to %p len %d\n", *p, end, (int)(end - *p)); @@ -153,6 +443,10 @@ static struct crush_map *crush_decode(void *pbyval, void *end) if (c == NULL) return ERR_PTR(-ENOMEM); + c->type_names = RB_ROOT; + c->names = RB_ROOT; + c->choose_args = RB_ROOT; + /* set tunables to default values */ c->choose_local_tries = 2; c->choose_local_fallback_tries = 5; @@ -204,8 +498,10 @@ static struct crush_map *crush_decode(void *pbyval, void *end) case CRUSH_BUCKET_STRAW: size = sizeof(struct crush_bucket_straw); break; + case CRUSH_BUCKET_STRAW2: + size = sizeof(struct crush_bucket_straw2); + break; default: - err = -EINVAL; goto bad; } BUG_ON(size == 0); @@ -227,10 +523,6 @@ static struct crush_map *crush_decode(void *pbyval, void *end) b->items = kcalloc(b->size, sizeof(__s32), GFP_NOFS); if (b->items == NULL) goto badmem; - b->perm = kcalloc(b->size, sizeof(u32), GFP_NOFS); - if (b->perm == NULL) - goto badmem; - b->perm_n = 0; ceph_decode_need(p, end, b->size*sizeof(u32), bad); for (j = 0; j < b->size; j++) @@ -241,25 +533,31 @@ static struct crush_map *crush_decode(void *pbyval, void *end) err = crush_decode_uniform_bucket(p, end, (struct crush_bucket_uniform *)b); if (err < 0) - goto bad; + goto fail; break; case CRUSH_BUCKET_LIST: err = crush_decode_list_bucket(p, end, (struct crush_bucket_list *)b); if (err < 0) - goto bad; + goto fail; break; case CRUSH_BUCKET_TREE: err = crush_decode_tree_bucket(p, end, (struct crush_bucket_tree *)b); if (err < 0) - goto bad; + goto fail; break; case CRUSH_BUCKET_STRAW: err = crush_decode_straw_bucket(p, end, (struct crush_bucket_straw *)b); if (err < 0) - goto bad; + goto fail; + break; + case CRUSH_BUCKET_STRAW2: + err = crush_decode_straw2_bucket(p, end, + (struct crush_bucket_straw2 *)b); + if (err < 0) + goto fail; break; } } @@ -284,17 +582,15 @@ static struct crush_map *crush_decode(void *pbyval, void *end) /* len */ ceph_decode_32_safe(p, end, yes, bad); #if BITS_PER_LONG == 32 - err = -EINVAL; if (yes > (ULONG_MAX - sizeof(*r)) / sizeof(struct crush_rule_step)) goto bad; #endif - r = c->rules[i] = kmalloc(sizeof(*r) + - yes*sizeof(struct crush_rule_step), - GFP_NOFS); + r = kmalloc(struct_size(r, steps, yes), GFP_NOFS); if (r == NULL) goto badmem; dout(" rule %d is at %p\n", i, r); + c->rules[i] = r; r->len = yes; ceph_decode_copy_safe(p, end, &r->mask, 4, bad); /* 4 u8's */ ceph_decode_need(p, end, r->len*3*sizeof(u32), bad); @@ -305,163 +601,143 @@ static struct crush_map *crush_decode(void *pbyval, void *end) } } - /* ignore trailing name maps. */ - for (num_name_maps = 0; num_name_maps < 3; num_name_maps++) { - err = skip_name_map(p, end); - if (err < 0) - goto done; - } + err = decode_crush_names(p, end, &c->type_names); + if (err) + goto fail; + + err = decode_crush_names(p, end, &c->names); + if (err) + goto fail; + + ceph_decode_skip_map(p, end, 32, string, bad); /* rule_name_map */ /* tunables */ ceph_decode_need(p, end, 3*sizeof(u32), done); c->choose_local_tries = ceph_decode_32(p); c->choose_local_fallback_tries = ceph_decode_32(p); c->choose_total_tries = ceph_decode_32(p); - dout("crush decode tunable choose_local_tries = %d", + dout("crush decode tunable choose_local_tries = %d\n", c->choose_local_tries); - dout("crush decode tunable choose_local_fallback_tries = %d", + dout("crush decode tunable choose_local_fallback_tries = %d\n", c->choose_local_fallback_tries); - dout("crush decode tunable choose_total_tries = %d", + dout("crush decode tunable choose_total_tries = %d\n", c->choose_total_tries); ceph_decode_need(p, end, sizeof(u32), done); c->chooseleaf_descend_once = ceph_decode_32(p); - dout("crush decode tunable chooseleaf_descend_once = %d", + dout("crush decode tunable chooseleaf_descend_once = %d\n", c->chooseleaf_descend_once); + ceph_decode_need(p, end, sizeof(u8), done); + c->chooseleaf_vary_r = ceph_decode_8(p); + dout("crush decode tunable chooseleaf_vary_r = %d\n", + c->chooseleaf_vary_r); + + /* skip straw_calc_version, allowed_bucket_algs */ + ceph_decode_need(p, end, sizeof(u8) + sizeof(u32), done); + *p += sizeof(u8) + sizeof(u32); + + ceph_decode_need(p, end, sizeof(u8), done); + c->chooseleaf_stable = ceph_decode_8(p); + dout("crush decode tunable chooseleaf_stable = %d\n", + c->chooseleaf_stable); + + if (*p != end) { + /* class_map */ + ceph_decode_skip_map(p, end, 32, 32, bad); + /* class_name */ + ceph_decode_skip_map(p, end, 32, string, bad); + /* class_bucket */ + ceph_decode_skip_map_of_map(p, end, 32, 32, 32, bad); + } + + if (*p != end) { + err = decode_choose_args(p, end, c); + if (err) + goto fail; + } + done: + crush_finalize(c); dout("crush_decode success\n"); return c; badmem: err = -ENOMEM; -bad: +fail: dout("crush_decode fail %d\n", err); crush_destroy(c); return ERR_PTR(err); + +bad: + err = -EINVAL; + goto fail; } -/* - * rbtree of pg_mapping for handling pg_temp (explicit mapping of pgid - * to a set of osds) - */ -static int pgid_cmp(struct ceph_pg l, struct ceph_pg r) +int ceph_pg_compare(const struct ceph_pg *lhs, const struct ceph_pg *rhs) { - if (l.pool < r.pool) + if (lhs->pool < rhs->pool) return -1; - if (l.pool > r.pool) + if (lhs->pool > rhs->pool) return 1; - if (l.seed < r.seed) + if (lhs->seed < rhs->seed) return -1; - if (l.seed > r.seed) + if (lhs->seed > rhs->seed) return 1; + return 0; } -static int __insert_pg_mapping(struct ceph_pg_mapping *new, - struct rb_root *root) +int ceph_spg_compare(const struct ceph_spg *lhs, const struct ceph_spg *rhs) { - struct rb_node **p = &root->rb_node; - struct rb_node *parent = NULL; - struct ceph_pg_mapping *pg = NULL; - int c; + int ret; - dout("__insert_pg_mapping %llx %p\n", *(u64 *)&new->pgid, new); - while (*p) { - parent = *p; - pg = rb_entry(parent, struct ceph_pg_mapping, node); - c = pgid_cmp(new->pgid, pg->pgid); - if (c < 0) - p = &(*p)->rb_left; - else if (c > 0) - p = &(*p)->rb_right; - else - return -EEXIST; - } + ret = ceph_pg_compare(&lhs->pgid, &rhs->pgid); + if (ret) + return ret; + + if (lhs->shard < rhs->shard) + return -1; + if (lhs->shard > rhs->shard) + return 1; - rb_link_node(&new->node, parent, p); - rb_insert_color(&new->node, root); return 0; } -static struct ceph_pg_mapping *__lookup_pg_mapping(struct rb_root *root, - struct ceph_pg pgid) +static struct ceph_pg_mapping *alloc_pg_mapping(size_t payload_len) { - struct rb_node *n = root->rb_node; struct ceph_pg_mapping *pg; - int c; - - while (n) { - pg = rb_entry(n, struct ceph_pg_mapping, node); - c = pgid_cmp(pgid, pg->pgid); - if (c < 0) { - n = n->rb_left; - } else if (c > 0) { - n = n->rb_right; - } else { - dout("__lookup_pg_mapping %lld.%x got %p\n", - pgid.pool, pgid.seed, pg); - return pg; - } - } - return NULL; + + pg = kmalloc(sizeof(*pg) + payload_len, GFP_NOIO); + if (!pg) + return NULL; + + RB_CLEAR_NODE(&pg->node); + return pg; } -static int __remove_pg_mapping(struct rb_root *root, struct ceph_pg pgid) +static void free_pg_mapping(struct ceph_pg_mapping *pg) { - struct ceph_pg_mapping *pg = __lookup_pg_mapping(root, pgid); + WARN_ON(!RB_EMPTY_NODE(&pg->node)); - if (pg) { - dout("__remove_pg_mapping %lld.%x %p\n", pgid.pool, pgid.seed, - pg); - rb_erase(&pg->node, root); - kfree(pg); - return 0; - } - dout("__remove_pg_mapping %lld.%x dne\n", pgid.pool, pgid.seed); - return -ENOENT; + kfree(pg); } /* - * rbtree of pg pool info + * rbtree of pg_mapping for handling pg_temp (explicit mapping of pgid + * to a set of osds) and primary_temp (explicit primary setting) */ -static int __insert_pg_pool(struct rb_root *root, struct ceph_pg_pool_info *new) -{ - struct rb_node **p = &root->rb_node; - struct rb_node *parent = NULL; - struct ceph_pg_pool_info *pi = NULL; - - while (*p) { - parent = *p; - pi = rb_entry(parent, struct ceph_pg_pool_info, node); - if (new->id < pi->id) - p = &(*p)->rb_left; - else if (new->id > pi->id) - p = &(*p)->rb_right; - else - return -EEXIST; - } +DEFINE_RB_FUNCS2(pg_mapping, struct ceph_pg_mapping, pgid, ceph_pg_compare, + RB_BYPTR, const struct ceph_pg *, node) - rb_link_node(&new->node, parent, p); - rb_insert_color(&new->node, root); - return 0; -} +/* + * rbtree of pg pool info + */ +DEFINE_RB_FUNCS(pg_pool, struct ceph_pg_pool_info, id, node) -static struct ceph_pg_pool_info *__lookup_pg_pool(struct rb_root *root, u64 id) +struct ceph_pg_pool_info *ceph_pg_pool_by_id(struct ceph_osdmap *map, u64 id) { - struct ceph_pg_pool_info *pi; - struct rb_node *n = root->rb_node; - - while (n) { - pi = rb_entry(n, struct ceph_pg_pool_info, node); - if (id < pi->id) - n = n->rb_left; - else if (id > pi->id) - n = n->rb_right; - else - return pi; - } - return NULL; + return lookup_pg_pool(&map->pg_pools, id); } const char *ceph_pg_pool_name_by_id(struct ceph_osdmap *map, u64 id) @@ -474,8 +750,7 @@ const char *ceph_pg_pool_name_by_id(struct ceph_osdmap *map, u64 id) if (WARN_ON_ONCE(id > (u64) INT_MAX)) return NULL; - pi = __lookup_pg_pool(&map->pg_pools, (int) id); - + pi = lookup_pg_pool(&map->pg_pools, id); return pi ? pi->name : NULL; } EXPORT_SYMBOL(ceph_pg_pool_name_by_id); @@ -494,14 +769,23 @@ int ceph_pg_poolid_by_name(struct ceph_osdmap *map, const char *name) } EXPORT_SYMBOL(ceph_pg_poolid_by_name); +u64 ceph_pg_pool_flags(struct ceph_osdmap *map, u64 id) +{ + struct ceph_pg_pool_info *pi; + + pi = lookup_pg_pool(&map->pg_pools, id); + return pi ? pi->flags : 0; +} +EXPORT_SYMBOL(ceph_pg_pool_flags); + static void __remove_pg_pool(struct rb_root *root, struct ceph_pg_pool_info *pi) { - rb_erase(&pi->node, root); + erase_pg_pool(root, pi); kfree(pi->name); kfree(pi); } -static int __decode_pool(void **p, void *end, struct ceph_pg_pool_info *pi) +static int decode_pool(void **p, void *end, struct ceph_pg_pool_info *pi) { u8 ev, cv; unsigned len, num; @@ -511,11 +795,11 @@ static int __decode_pool(void **p, void *end, struct ceph_pg_pool_info *pi) ev = ceph_decode_8(p); /* encoding version */ cv = ceph_decode_8(p); /* compat version */ if (ev < 5) { - pr_warning("got v %d < 5 cv %d of ceph_pg_pool\n", ev, cv); + pr_warn("got v %d < 5 cv %d of ceph_pg_pool\n", ev, cv); return -EINVAL; } - if (cv > 7) { - pr_warning("got v %d cv %d > 7 of ceph_pg_pool\n", ev, cv); + if (cv > 9) { + pr_warn("got v %d cv %d > 9 of ceph_pg_pool\n", ev, cv); return -EINVAL; } len = ceph_decode_32(p); @@ -543,12 +827,117 @@ static int __decode_pool(void **p, void *end, struct ceph_pg_pool_info *pi) *p += len; } - /* skip removed snaps */ + /* skip removed_snaps */ num = ceph_decode_32(p); *p += num * (8 + 8); *p += 8; /* skip auid */ pi->flags = ceph_decode_64(p); + *p += 4; /* skip crash_replay_interval */ + + if (ev >= 7) + pi->min_size = ceph_decode_8(p); + else + pi->min_size = pi->size - pi->size / 2; + + if (ev >= 8) + *p += 8 + 8; /* skip quota_max_* */ + + if (ev >= 9) { + /* skip tiers */ + num = ceph_decode_32(p); + *p += num * 8; + + *p += 8; /* skip tier_of */ + *p += 1; /* skip cache_mode */ + + pi->read_tier = ceph_decode_64(p); + pi->write_tier = ceph_decode_64(p); + } else { + pi->read_tier = -1; + pi->write_tier = -1; + } + + if (ev >= 10) { + /* skip properties */ + num = ceph_decode_32(p); + while (num--) { + len = ceph_decode_32(p); + *p += len; /* key */ + len = ceph_decode_32(p); + *p += len; /* val */ + } + } + + if (ev >= 11) { + /* skip hit_set_params */ + *p += 1 + 1; /* versions */ + len = ceph_decode_32(p); + *p += len; + + *p += 4; /* skip hit_set_period */ + *p += 4; /* skip hit_set_count */ + } + + if (ev >= 12) + *p += 4; /* skip stripe_width */ + + if (ev >= 13) { + *p += 8; /* skip target_max_bytes */ + *p += 8; /* skip target_max_objects */ + *p += 4; /* skip cache_target_dirty_ratio_micro */ + *p += 4; /* skip cache_target_full_ratio_micro */ + *p += 4; /* skip cache_min_flush_age */ + *p += 4; /* skip cache_min_evict_age */ + } + + if (ev >= 14) { + /* skip erasure_code_profile */ + len = ceph_decode_32(p); + *p += len; + } + + /* + * last_force_op_resend_preluminous, will be overridden if the + * map was encoded with RESEND_ON_SPLIT + */ + if (ev >= 15) + pi->last_force_request_resend = ceph_decode_32(p); + else + pi->last_force_request_resend = 0; + + if (ev >= 16) + *p += 4; /* skip min_read_recency_for_promote */ + + if (ev >= 17) + *p += 8; /* skip expected_num_objects */ + + if (ev >= 19) + *p += 4; /* skip cache_target_dirty_high_ratio_micro */ + + if (ev >= 20) + *p += 4; /* skip min_write_recency_for_promote */ + + if (ev >= 21) + *p += 1; /* skip use_gmt_hitset */ + + if (ev >= 22) + *p += 1; /* skip fast_read */ + + if (ev >= 23) { + *p += 4; /* skip hit_set_grade_decay_rate */ + *p += 4; /* skip hit_set_search_last_n */ + } + + if (ev >= 24) { + /* skip opts */ + *p += 1 + 1; /* versions */ + len = ceph_decode_32(p); + *p += len; + } + + if (ev >= 25) + pi->last_force_request_resend = ceph_decode_32(p); /* ignore the rest */ @@ -560,7 +949,7 @@ bad: return -EINVAL; } -static int __decode_pool_names(void **p, void *end, struct ceph_osdmap *map) +static int decode_pool_names(void **p, void *end, struct ceph_osdmap *map) { struct ceph_pg_pool_info *pi; u32 num, len; @@ -573,7 +962,7 @@ static int __decode_pool_names(void **p, void *end, struct ceph_osdmap *map) ceph_decode_32_safe(p, end, len, bad); dout(" pool %llu len %d\n", pool, len); ceph_decode_need(p, end, len, bad); - pi = __lookup_pg_pool(&map->pg_pools, pool); + pi = lookup_pg_pool(&map->pg_pools, pool); if (pi) { char *name = kstrndup(*p, len, GFP_NOFS); @@ -592,18 +981,199 @@ bad: } /* + * CRUSH workspaces + * + * workspace_manager framework borrowed from fs/btrfs/compression.c. + * Two simplifications: there is only one type of workspace and there + * is always at least one workspace. + */ +static struct crush_work *alloc_workspace(const struct crush_map *c) +{ + struct crush_work *work; + size_t work_size; + + WARN_ON(!c->working_size); + work_size = crush_work_size(c, CEPH_PG_MAX_SIZE); + dout("%s work_size %zu bytes\n", __func__, work_size); + + work = kvmalloc(work_size, GFP_NOIO); + if (!work) + return NULL; + + INIT_LIST_HEAD(&work->item); + crush_init_workspace(c, work); + return work; +} + +static void free_workspace(struct crush_work *work) +{ + WARN_ON(!list_empty(&work->item)); + kvfree(work); +} + +static void init_workspace_manager(struct workspace_manager *wsm) +{ + INIT_LIST_HEAD(&wsm->idle_ws); + spin_lock_init(&wsm->ws_lock); + atomic_set(&wsm->total_ws, 0); + wsm->free_ws = 0; + init_waitqueue_head(&wsm->ws_wait); +} + +static void add_initial_workspace(struct workspace_manager *wsm, + struct crush_work *work) +{ + WARN_ON(!list_empty(&wsm->idle_ws)); + + list_add(&work->item, &wsm->idle_ws); + atomic_set(&wsm->total_ws, 1); + wsm->free_ws = 1; +} + +static void cleanup_workspace_manager(struct workspace_manager *wsm) +{ + struct crush_work *work; + + while (!list_empty(&wsm->idle_ws)) { + work = list_first_entry(&wsm->idle_ws, struct crush_work, + item); + list_del_init(&work->item); + free_workspace(work); + } + atomic_set(&wsm->total_ws, 0); + wsm->free_ws = 0; +} + +/* + * Finds an available workspace or allocates a new one. If it's not + * possible to allocate a new one, waits until there is one. + */ +static struct crush_work *get_workspace(struct workspace_manager *wsm, + const struct crush_map *c) +{ + struct crush_work *work; + int cpus = num_online_cpus(); + +again: + spin_lock(&wsm->ws_lock); + if (!list_empty(&wsm->idle_ws)) { + work = list_first_entry(&wsm->idle_ws, struct crush_work, + item); + list_del_init(&work->item); + wsm->free_ws--; + spin_unlock(&wsm->ws_lock); + return work; + + } + if (atomic_read(&wsm->total_ws) > cpus) { + DEFINE_WAIT(wait); + + spin_unlock(&wsm->ws_lock); + prepare_to_wait(&wsm->ws_wait, &wait, TASK_UNINTERRUPTIBLE); + if (atomic_read(&wsm->total_ws) > cpus && !wsm->free_ws) + schedule(); + finish_wait(&wsm->ws_wait, &wait); + goto again; + } + atomic_inc(&wsm->total_ws); + spin_unlock(&wsm->ws_lock); + + work = alloc_workspace(c); + if (!work) { + atomic_dec(&wsm->total_ws); + wake_up(&wsm->ws_wait); + + /* + * Do not return the error but go back to waiting. We + * have the initial workspace and the CRUSH computation + * time is bounded so we will get it eventually. + */ + WARN_ON(atomic_read(&wsm->total_ws) < 1); + goto again; + } + return work; +} + +/* + * Puts a workspace back on the list or frees it if we have enough + * idle ones sitting around. + */ +static void put_workspace(struct workspace_manager *wsm, + struct crush_work *work) +{ + spin_lock(&wsm->ws_lock); + if (wsm->free_ws <= num_online_cpus()) { + list_add(&work->item, &wsm->idle_ws); + wsm->free_ws++; + spin_unlock(&wsm->ws_lock); + goto wake; + } + spin_unlock(&wsm->ws_lock); + + free_workspace(work); + atomic_dec(&wsm->total_ws); +wake: + if (wq_has_sleeper(&wsm->ws_wait)) + wake_up(&wsm->ws_wait); +} + +/* * osd map */ +struct ceph_osdmap *ceph_osdmap_alloc(void) +{ + struct ceph_osdmap *map; + + map = kzalloc(sizeof(*map), GFP_NOIO); + if (!map) + return NULL; + + map->pg_pools = RB_ROOT; + map->pool_max = -1; + map->pg_temp = RB_ROOT; + map->primary_temp = RB_ROOT; + map->pg_upmap = RB_ROOT; + map->pg_upmap_items = RB_ROOT; + + init_workspace_manager(&map->crush_wsm); + + return map; +} + void ceph_osdmap_destroy(struct ceph_osdmap *map) { dout("osdmap_destroy %p\n", map); + if (map->crush) crush_destroy(map->crush); + cleanup_workspace_manager(&map->crush_wsm); + while (!RB_EMPTY_ROOT(&map->pg_temp)) { struct ceph_pg_mapping *pg = rb_entry(rb_first(&map->pg_temp), struct ceph_pg_mapping, node); - rb_erase(&pg->node, &map->pg_temp); + erase_pg_mapping(&map->pg_temp, pg); + free_pg_mapping(pg); + } + while (!RB_EMPTY_ROOT(&map->primary_temp)) { + struct ceph_pg_mapping *pg = + rb_entry(rb_first(&map->primary_temp), + struct ceph_pg_mapping, node); + erase_pg_mapping(&map->primary_temp, pg); + free_pg_mapping(pg); + } + while (!RB_EMPTY_ROOT(&map->pg_upmap)) { + struct ceph_pg_mapping *pg = + rb_entry(rb_first(&map->pg_upmap), + struct ceph_pg_mapping, node); + rb_erase(&pg->node, &map->pg_upmap); + kfree(pg); + } + while (!RB_EMPTY_ROOT(&map->pg_upmap_items)) { + struct ceph_pg_mapping *pg = + rb_entry(rb_first(&map->pg_upmap_items), + struct ceph_pg_mapping, node); + rb_erase(&pg->node, &map->pg_upmap_items); kfree(pg); } while (!RB_EMPTY_ROOT(&map->pg_pools)) { @@ -612,199 +1182,793 @@ void ceph_osdmap_destroy(struct ceph_osdmap *map) struct ceph_pg_pool_info, node); __remove_pg_pool(&map->pg_pools, pi); } - kfree(map->osd_state); - kfree(map->osd_weight); - kfree(map->osd_addr); + kvfree(map->osd_state); + kvfree(map->osd_weight); + kvfree(map->osd_addr); + kvfree(map->osd_primary_affinity); kfree(map); } /* - * adjust max osd value. reallocate arrays. + * Adjust max_osd value, (re)allocate arrays. + * + * The new elements are properly initialized. */ -static int osdmap_set_max_osd(struct ceph_osdmap *map, int max) +static int osdmap_set_max_osd(struct ceph_osdmap *map, u32 max) { - u8 *state; - struct ceph_entity_addr *addr; + u32 *state; u32 *weight; + struct ceph_entity_addr *addr; + u32 to_copy; + int i; + + dout("%s old %u new %u\n", __func__, map->max_osd, max); + if (max == map->max_osd) + return 0; - state = kcalloc(max, sizeof(*state), GFP_NOFS); - addr = kcalloc(max, sizeof(*addr), GFP_NOFS); - weight = kcalloc(max, sizeof(*weight), GFP_NOFS); - if (state == NULL || addr == NULL || weight == NULL) { - kfree(state); - kfree(addr); - kfree(weight); + state = kvmalloc(array_size(max, sizeof(*state)), GFP_NOFS); + weight = kvmalloc(array_size(max, sizeof(*weight)), GFP_NOFS); + addr = kvmalloc(array_size(max, sizeof(*addr)), GFP_NOFS); + if (!state || !weight || !addr) { + kvfree(state); + kvfree(weight); + kvfree(addr); return -ENOMEM; } - /* copy old? */ + to_copy = min(map->max_osd, max); if (map->osd_state) { - memcpy(state, map->osd_state, map->max_osd*sizeof(*state)); - memcpy(addr, map->osd_addr, map->max_osd*sizeof(*addr)); - memcpy(weight, map->osd_weight, map->max_osd*sizeof(*weight)); - kfree(map->osd_state); - kfree(map->osd_addr); - kfree(map->osd_weight); + memcpy(state, map->osd_state, to_copy * sizeof(*state)); + memcpy(weight, map->osd_weight, to_copy * sizeof(*weight)); + memcpy(addr, map->osd_addr, to_copy * sizeof(*addr)); + kvfree(map->osd_state); + kvfree(map->osd_weight); + kvfree(map->osd_addr); } map->osd_state = state; map->osd_weight = weight; map->osd_addr = addr; + for (i = map->max_osd; i < max; i++) { + map->osd_state[i] = 0; + map->osd_weight[i] = CEPH_OSD_OUT; + memset(map->osd_addr + i, 0, sizeof(*map->osd_addr)); + } + + if (map->osd_primary_affinity) { + u32 *affinity; + + affinity = kvmalloc(array_size(max, sizeof(*affinity)), + GFP_NOFS); + if (!affinity) + return -ENOMEM; + + memcpy(affinity, map->osd_primary_affinity, + to_copy * sizeof(*affinity)); + kvfree(map->osd_primary_affinity); + + map->osd_primary_affinity = affinity; + for (i = map->max_osd; i < max; i++) + map->osd_primary_affinity[i] = + CEPH_OSD_DEFAULT_PRIMARY_AFFINITY; + } + map->max_osd = max; + + return 0; +} + +static int osdmap_set_crush(struct ceph_osdmap *map, struct crush_map *crush) +{ + struct crush_work *work; + + if (IS_ERR(crush)) + return PTR_ERR(crush); + + work = alloc_workspace(crush); + if (!work) { + crush_destroy(crush); + return -ENOMEM; + } + + if (map->crush) + crush_destroy(map->crush); + cleanup_workspace_manager(&map->crush_wsm); + map->crush = crush; + add_initial_workspace(&map->crush_wsm, work); return 0; } +#define OSDMAP_WRAPPER_COMPAT_VER 7 +#define OSDMAP_CLIENT_DATA_COMPAT_VER 1 + /* - * decode a full map. + * Return 0 or error. On success, *v is set to 0 for old (v6) osdmaps, + * to struct_v of the client_data section for new (v7 and above) + * osdmaps. */ -struct ceph_osdmap *osdmap_decode(void **p, void *end) +static int get_osdmap_client_data_v(void **p, void *end, + const char *prefix, u8 *v) { - struct ceph_osdmap *map; - u16 version; - u32 len, max, i; - int err = -EINVAL; - void *start = *p; - struct ceph_pg_pool_info *pi; + u8 struct_v; + + ceph_decode_8_safe(p, end, struct_v, e_inval); + if (struct_v >= 7) { + u8 struct_compat; + + ceph_decode_8_safe(p, end, struct_compat, e_inval); + if (struct_compat > OSDMAP_WRAPPER_COMPAT_VER) { + pr_warn("got v %d cv %d > %d of %s ceph_osdmap\n", + struct_v, struct_compat, + OSDMAP_WRAPPER_COMPAT_VER, prefix); + return -EINVAL; + } + *p += 4; /* ignore wrapper struct_len */ + + ceph_decode_8_safe(p, end, struct_v, e_inval); + ceph_decode_8_safe(p, end, struct_compat, e_inval); + if (struct_compat > OSDMAP_CLIENT_DATA_COMPAT_VER) { + pr_warn("got v %d cv %d > %d of %s ceph_osdmap client data\n", + struct_v, struct_compat, + OSDMAP_CLIENT_DATA_COMPAT_VER, prefix); + return -EINVAL; + } + *p += 4; /* ignore client data struct_len */ + } else { + u16 version; + + *p -= 1; + ceph_decode_16_safe(p, end, version, e_inval); + if (version < 6) { + pr_warn("got v %d < 6 of %s ceph_osdmap\n", + version, prefix); + return -EINVAL; + } + + /* old osdmap encoding */ + struct_v = 0; + } + + *v = struct_v; + return 0; + +e_inval: + return -EINVAL; +} + +static int __decode_pools(void **p, void *end, struct ceph_osdmap *map, + bool incremental) +{ + u32 n; + + ceph_decode_32_safe(p, end, n, e_inval); + while (n--) { + struct ceph_pg_pool_info *pi; + u64 pool; + int ret; + + ceph_decode_64_safe(p, end, pool, e_inval); + + pi = lookup_pg_pool(&map->pg_pools, pool); + if (!incremental || !pi) { + pi = kzalloc(sizeof(*pi), GFP_NOFS); + if (!pi) + return -ENOMEM; + + RB_CLEAR_NODE(&pi->node); + pi->id = pool; + + if (!__insert_pg_pool(&map->pg_pools, pi)) { + kfree(pi); + return -EEXIST; + } + } + + ret = decode_pool(p, end, pi); + if (ret) + return ret; + } + + return 0; + +e_inval: + return -EINVAL; +} + +static int decode_pools(void **p, void *end, struct ceph_osdmap *map) +{ + return __decode_pools(p, end, map, false); +} + +static int decode_new_pools(void **p, void *end, struct ceph_osdmap *map) +{ + return __decode_pools(p, end, map, true); +} + +typedef struct ceph_pg_mapping *(*decode_mapping_fn_t)(void **, void *, bool); + +static int decode_pg_mapping(void **p, void *end, struct rb_root *mapping_root, + decode_mapping_fn_t fn, bool incremental) +{ + u32 n; + + WARN_ON(!incremental && !fn); - dout("osdmap_decode %p to %p len %d\n", *p, end, (int)(end - *p)); + ceph_decode_32_safe(p, end, n, e_inval); + while (n--) { + struct ceph_pg_mapping *pg; + struct ceph_pg pgid; + int ret; - map = kzalloc(sizeof(*map), GFP_NOFS); - if (map == NULL) + ret = ceph_decode_pgid(p, end, &pgid); + if (ret) + return ret; + + pg = lookup_pg_mapping(mapping_root, &pgid); + if (pg) { + WARN_ON(!incremental); + erase_pg_mapping(mapping_root, pg); + free_pg_mapping(pg); + } + + if (fn) { + pg = fn(p, end, incremental); + if (IS_ERR(pg)) + return PTR_ERR(pg); + + if (pg) { + pg->pgid = pgid; /* struct */ + insert_pg_mapping(mapping_root, pg); + } + } + } + + return 0; + +e_inval: + return -EINVAL; +} + +static struct ceph_pg_mapping *__decode_pg_temp(void **p, void *end, + bool incremental) +{ + struct ceph_pg_mapping *pg; + u32 len, i; + + ceph_decode_32_safe(p, end, len, e_inval); + if (len == 0 && incremental) + return NULL; /* new_pg_temp: [] to remove */ + if (len > (SIZE_MAX - sizeof(*pg)) / sizeof(u32)) + return ERR_PTR(-EINVAL); + + ceph_decode_need(p, end, len * sizeof(u32), e_inval); + pg = alloc_pg_mapping(len * sizeof(u32)); + if (!pg) return ERR_PTR(-ENOMEM); - map->pg_temp = RB_ROOT; - ceph_decode_16_safe(p, end, version, bad); - if (version > 6) { - pr_warning("got unknown v %d > 6 of osdmap\n", version); - goto bad; + pg->pg_temp.len = len; + for (i = 0; i < len; i++) + pg->pg_temp.osds[i] = ceph_decode_32(p); + + return pg; + +e_inval: + return ERR_PTR(-EINVAL); +} + +static int decode_pg_temp(void **p, void *end, struct ceph_osdmap *map) +{ + return decode_pg_mapping(p, end, &map->pg_temp, __decode_pg_temp, + false); +} + +static int decode_new_pg_temp(void **p, void *end, struct ceph_osdmap *map) +{ + return decode_pg_mapping(p, end, &map->pg_temp, __decode_pg_temp, + true); +} + +static struct ceph_pg_mapping *__decode_primary_temp(void **p, void *end, + bool incremental) +{ + struct ceph_pg_mapping *pg; + u32 osd; + + ceph_decode_32_safe(p, end, osd, e_inval); + if (osd == (u32)-1 && incremental) + return NULL; /* new_primary_temp: -1 to remove */ + + pg = alloc_pg_mapping(0); + if (!pg) + return ERR_PTR(-ENOMEM); + + pg->primary_temp.osd = osd; + return pg; + +e_inval: + return ERR_PTR(-EINVAL); +} + +static int decode_primary_temp(void **p, void *end, struct ceph_osdmap *map) +{ + return decode_pg_mapping(p, end, &map->primary_temp, + __decode_primary_temp, false); +} + +static int decode_new_primary_temp(void **p, void *end, + struct ceph_osdmap *map) +{ + return decode_pg_mapping(p, end, &map->primary_temp, + __decode_primary_temp, true); +} + +u32 ceph_get_primary_affinity(struct ceph_osdmap *map, int osd) +{ + if (!map->osd_primary_affinity) + return CEPH_OSD_DEFAULT_PRIMARY_AFFINITY; + + return map->osd_primary_affinity[osd]; +} + +static int set_primary_affinity(struct ceph_osdmap *map, int osd, u32 aff) +{ + if (!map->osd_primary_affinity) { + int i; + + map->osd_primary_affinity = kvmalloc( + array_size(map->max_osd, sizeof(*map->osd_primary_affinity)), + GFP_NOFS); + if (!map->osd_primary_affinity) + return -ENOMEM; + + for (i = 0; i < map->max_osd; i++) + map->osd_primary_affinity[i] = + CEPH_OSD_DEFAULT_PRIMARY_AFFINITY; } - if (version < 6) { - pr_warning("got old v %d < 6 of osdmap\n", version); - goto bad; + + map->osd_primary_affinity[osd] = aff; + + return 0; +} + +static int decode_primary_affinity(void **p, void *end, + struct ceph_osdmap *map) +{ + u32 len, i; + + ceph_decode_32_safe(p, end, len, e_inval); + if (len == 0) { + kvfree(map->osd_primary_affinity); + map->osd_primary_affinity = NULL; + return 0; } + if (len != map->max_osd) + goto e_inval; + + ceph_decode_need(p, end, map->max_osd*sizeof(u32), e_inval); + + for (i = 0; i < map->max_osd; i++) { + int ret; + + ret = set_primary_affinity(map, i, ceph_decode_32(p)); + if (ret) + return ret; + } + + return 0; + +e_inval: + return -EINVAL; +} - ceph_decode_need(p, end, 2*sizeof(u64)+6*sizeof(u32), bad); +static int decode_new_primary_affinity(void **p, void *end, + struct ceph_osdmap *map) +{ + u32 n; + + ceph_decode_32_safe(p, end, n, e_inval); + while (n--) { + u32 osd, aff; + int ret; + + ceph_decode_32_safe(p, end, osd, e_inval); + ceph_decode_32_safe(p, end, aff, e_inval); + if (osd >= map->max_osd) + goto e_inval; + + ret = set_primary_affinity(map, osd, aff); + if (ret) + return ret; + + osdmap_info(map, "osd%d primary-affinity 0x%x\n", osd, aff); + } + + return 0; + +e_inval: + return -EINVAL; +} + +static struct ceph_pg_mapping *__decode_pg_upmap(void **p, void *end, + bool __unused) +{ + return __decode_pg_temp(p, end, false); +} + +static int decode_pg_upmap(void **p, void *end, struct ceph_osdmap *map) +{ + return decode_pg_mapping(p, end, &map->pg_upmap, __decode_pg_upmap, + false); +} + +static int decode_new_pg_upmap(void **p, void *end, struct ceph_osdmap *map) +{ + return decode_pg_mapping(p, end, &map->pg_upmap, __decode_pg_upmap, + true); +} + +static int decode_old_pg_upmap(void **p, void *end, struct ceph_osdmap *map) +{ + return decode_pg_mapping(p, end, &map->pg_upmap, NULL, true); +} + +static struct ceph_pg_mapping *__decode_pg_upmap_items(void **p, void *end, + bool __unused) +{ + struct ceph_pg_mapping *pg; + u32 len, i; + + ceph_decode_32_safe(p, end, len, e_inval); + if (len > (SIZE_MAX - sizeof(*pg)) / (2 * sizeof(u32))) + return ERR_PTR(-EINVAL); + + ceph_decode_need(p, end, 2 * len * sizeof(u32), e_inval); + pg = alloc_pg_mapping(2 * len * sizeof(u32)); + if (!pg) + return ERR_PTR(-ENOMEM); + + pg->pg_upmap_items.len = len; + for (i = 0; i < len; i++) { + pg->pg_upmap_items.from_to[i][0] = ceph_decode_32(p); + pg->pg_upmap_items.from_to[i][1] = ceph_decode_32(p); + } + + return pg; + +e_inval: + return ERR_PTR(-EINVAL); +} + +static int decode_pg_upmap_items(void **p, void *end, struct ceph_osdmap *map) +{ + return decode_pg_mapping(p, end, &map->pg_upmap_items, + __decode_pg_upmap_items, false); +} + +static int decode_new_pg_upmap_items(void **p, void *end, + struct ceph_osdmap *map) +{ + return decode_pg_mapping(p, end, &map->pg_upmap_items, + __decode_pg_upmap_items, true); +} + +static int decode_old_pg_upmap_items(void **p, void *end, + struct ceph_osdmap *map) +{ + return decode_pg_mapping(p, end, &map->pg_upmap_items, NULL, true); +} + +/* + * decode a full map. + */ +static int osdmap_decode(void **p, void *end, bool msgr2, + struct ceph_osdmap *map) +{ + u8 struct_v; + u32 epoch = 0; + void *start = *p; + u32 max; + u32 len, i; + int err; + + dout("%s %p to %p len %d\n", __func__, *p, end, (int)(end - *p)); + + err = get_osdmap_client_data_v(p, end, "full", &struct_v); + if (err) + goto bad; + + /* fsid, epoch, created, modified */ + ceph_decode_need(p, end, sizeof(map->fsid) + sizeof(u32) + + sizeof(map->created) + sizeof(map->modified), e_inval); ceph_decode_copy(p, &map->fsid, sizeof(map->fsid)); - map->epoch = ceph_decode_32(p); + epoch = map->epoch = ceph_decode_32(p); ceph_decode_copy(p, &map->created, sizeof(map->created)); ceph_decode_copy(p, &map->modified, sizeof(map->modified)); - ceph_decode_32_safe(p, end, max, bad); - while (max--) { - ceph_decode_need(p, end, 8 + 2, bad); - err = -ENOMEM; - pi = kzalloc(sizeof(*pi), GFP_NOFS); - if (!pi) - goto bad; - pi->id = ceph_decode_64(p); - err = __decode_pool(p, end, pi); - if (err < 0) { - kfree(pi); - goto bad; - } - __insert_pg_pool(&map->pg_pools, pi); - } + /* pools */ + err = decode_pools(p, end, map); + if (err) + goto bad; - err = __decode_pool_names(p, end, map); - if (err < 0) { - dout("fail to decode pool names"); + /* pool_name */ + err = decode_pool_names(p, end, map); + if (err) goto bad; - } - ceph_decode_32_safe(p, end, map->pool_max, bad); + ceph_decode_32_safe(p, end, map->pool_max, e_inval); - ceph_decode_32_safe(p, end, map->flags, bad); + ceph_decode_32_safe(p, end, map->flags, e_inval); - max = ceph_decode_32(p); + /* max_osd */ + ceph_decode_32_safe(p, end, max, e_inval); /* (re)alloc osd arrays */ err = osdmap_set_max_osd(map, max); - if (err < 0) + if (err) goto bad; - dout("osdmap_decode max_osd = %d\n", map->max_osd); - /* osds */ - err = -EINVAL; + /* osd_state, osd_weight, osd_addrs->client_addr */ ceph_decode_need(p, end, 3*sizeof(u32) + - map->max_osd*(1 + sizeof(*map->osd_weight) + - sizeof(*map->osd_addr)), bad); - *p += 4; /* skip length field (should match max) */ - ceph_decode_copy(p, map->osd_state, map->max_osd); + map->max_osd*(struct_v >= 5 ? sizeof(u32) : + sizeof(u8)) + + sizeof(*map->osd_weight), e_inval); + if (ceph_decode_32(p) != map->max_osd) + goto e_inval; + + if (struct_v >= 5) { + for (i = 0; i < map->max_osd; i++) + map->osd_state[i] = ceph_decode_32(p); + } else { + for (i = 0; i < map->max_osd; i++) + map->osd_state[i] = ceph_decode_8(p); + } + + if (ceph_decode_32(p) != map->max_osd) + goto e_inval; - *p += 4; /* skip length field (should match max) */ for (i = 0; i < map->max_osd; i++) map->osd_weight[i] = ceph_decode_32(p); - *p += 4; /* skip length field (should match max) */ - ceph_decode_copy(p, map->osd_addr, map->max_osd*sizeof(*map->osd_addr)); - for (i = 0; i < map->max_osd; i++) - ceph_decode_addr(&map->osd_addr[i]); + if (ceph_decode_32(p) != map->max_osd) + goto e_inval; - /* pg_temp */ - ceph_decode_32_safe(p, end, len, bad); - for (i = 0; i < len; i++) { - int n, j; - struct ceph_pg pgid; - struct ceph_pg_mapping *pg; + for (i = 0; i < map->max_osd; i++) { + struct ceph_entity_addr *addr = &map->osd_addr[i]; - err = ceph_decode_pgid(p, end, &pgid); + if (struct_v >= 8) + err = ceph_decode_entity_addrvec(p, end, msgr2, addr); + else + err = ceph_decode_entity_addr(p, end, addr); if (err) goto bad; - ceph_decode_need(p, end, sizeof(u32), bad); - n = ceph_decode_32(p); - err = -EINVAL; - if (n > (UINT_MAX - sizeof(*pg)) / sizeof(u32)) - goto bad; - ceph_decode_need(p, end, n * sizeof(u32), bad); - err = -ENOMEM; - pg = kmalloc(sizeof(*pg) + n*sizeof(u32), GFP_NOFS); - if (!pg) + + dout("%s osd%d addr %s\n", __func__, i, ceph_pr_addr(addr)); + } + + /* pg_temp */ + err = decode_pg_temp(p, end, map); + if (err) + goto bad; + + /* primary_temp */ + if (struct_v >= 1) { + err = decode_primary_temp(p, end, map); + if (err) goto bad; - pg->pgid = pgid; - pg->len = n; - for (j = 0; j < n; j++) - pg->osds[j] = ceph_decode_32(p); + } - err = __insert_pg_mapping(pg, &map->pg_temp); + /* primary_affinity */ + if (struct_v >= 2) { + err = decode_primary_affinity(p, end, map); if (err) goto bad; - dout(" added pg_temp %lld.%x len %d\n", pgid.pool, pgid.seed, - len); + } else { + WARN_ON(map->osd_primary_affinity); } /* crush */ - ceph_decode_32_safe(p, end, len, bad); - dout("osdmap_decode crush len %d from off 0x%x\n", len, - (int)(*p - start)); - ceph_decode_need(p, end, len, bad); - map->crush = crush_decode(*p, end); - *p += len; - if (IS_ERR(map->crush)) { - err = PTR_ERR(map->crush); - map->crush = NULL; + ceph_decode_32_safe(p, end, len, e_inval); + err = osdmap_set_crush(map, crush_decode(*p, min(*p + len, end))); + if (err) goto bad; + + *p += len; + if (struct_v >= 3) { + /* erasure_code_profiles */ + ceph_decode_skip_map_of_map(p, end, string, string, string, + e_inval); + } + + if (struct_v >= 4) { + err = decode_pg_upmap(p, end, map); + if (err) + goto bad; + + err = decode_pg_upmap_items(p, end, map); + if (err) + goto bad; + } else { + WARN_ON(!RB_EMPTY_ROOT(&map->pg_upmap)); + WARN_ON(!RB_EMPTY_ROOT(&map->pg_upmap_items)); } - /* ignore the rest of the map */ + /* ignore the rest */ *p = end; - dout("osdmap_decode done %p %p\n", *p, end); - return map; + dout("full osdmap epoch %d max_osd %d\n", map->epoch, map->max_osd); + return 0; +e_inval: + err = -EINVAL; bad: - dout("osdmap_decode fail err %d\n", err); - ceph_osdmap_destroy(map); - return ERR_PTR(err); + pr_err("corrupt full osdmap (%d) epoch %d off %d (%p of %p-%p)\n", + err, epoch, (int)(*p - start), *p, start, end); + print_hex_dump(KERN_DEBUG, "osdmap: ", + DUMP_PREFIX_OFFSET, 16, 1, + start, end - start, true); + return err; +} + +/* + * Allocate and decode a full map. + */ +struct ceph_osdmap *ceph_osdmap_decode(void **p, void *end, bool msgr2) +{ + struct ceph_osdmap *map; + int ret; + + map = ceph_osdmap_alloc(); + if (!map) + return ERR_PTR(-ENOMEM); + + ret = osdmap_decode(p, end, msgr2, map); + if (ret) { + ceph_osdmap_destroy(map); + return ERR_PTR(ret); + } + + return map; +} + +/* + * Encoding order is (new_up_client, new_state, new_weight). Need to + * apply in the (new_weight, new_state, new_up_client) order, because + * an incremental map may look like e.g. + * + * new_up_client: { osd=6, addr=... } # set osd_state and addr + * new_state: { osd=6, xorstate=EXISTS } # clear osd_state + */ +static int decode_new_up_state_weight(void **p, void *end, u8 struct_v, + bool msgr2, struct ceph_osdmap *map) +{ + void *new_up_client; + void *new_state; + void *new_weight_end; + u32 len; + int ret; + int i; + + new_up_client = *p; + ceph_decode_32_safe(p, end, len, e_inval); + for (i = 0; i < len; ++i) { + struct ceph_entity_addr addr; + + ceph_decode_skip_32(p, end, e_inval); + if (struct_v >= 7) + ret = ceph_decode_entity_addrvec(p, end, msgr2, &addr); + else + ret = ceph_decode_entity_addr(p, end, &addr); + if (ret) + return ret; + } + + new_state = *p; + ceph_decode_32_safe(p, end, len, e_inval); + len *= sizeof(u32) + (struct_v >= 5 ? sizeof(u32) : sizeof(u8)); + ceph_decode_need(p, end, len, e_inval); + *p += len; + + /* new_weight */ + ceph_decode_32_safe(p, end, len, e_inval); + while (len--) { + s32 osd; + u32 w; + + ceph_decode_need(p, end, 2*sizeof(u32), e_inval); + osd = ceph_decode_32(p); + w = ceph_decode_32(p); + if (osd >= map->max_osd) + goto e_inval; + + osdmap_info(map, "osd%d weight 0x%x %s\n", osd, w, + w == CEPH_OSD_IN ? "(in)" : + (w == CEPH_OSD_OUT ? "(out)" : "")); + map->osd_weight[osd] = w; + + /* + * If we are marking in, set the EXISTS, and clear the + * AUTOOUT and NEW bits. + */ + if (w) { + map->osd_state[osd] |= CEPH_OSD_EXISTS; + map->osd_state[osd] &= ~(CEPH_OSD_AUTOOUT | + CEPH_OSD_NEW); + } + } + new_weight_end = *p; + + /* new_state (up/down) */ + *p = new_state; + len = ceph_decode_32(p); + while (len--) { + s32 osd; + u32 xorstate; + + osd = ceph_decode_32(p); + if (osd >= map->max_osd) + goto e_inval; + + if (struct_v >= 5) + xorstate = ceph_decode_32(p); + else + xorstate = ceph_decode_8(p); + if (xorstate == 0) + xorstate = CEPH_OSD_UP; + if ((map->osd_state[osd] & CEPH_OSD_UP) && + (xorstate & CEPH_OSD_UP)) + osdmap_info(map, "osd%d down\n", osd); + if ((map->osd_state[osd] & CEPH_OSD_EXISTS) && + (xorstate & CEPH_OSD_EXISTS)) { + osdmap_info(map, "osd%d does not exist\n", osd); + ret = set_primary_affinity(map, osd, + CEPH_OSD_DEFAULT_PRIMARY_AFFINITY); + if (ret) + return ret; + memset(map->osd_addr + osd, 0, sizeof(*map->osd_addr)); + map->osd_state[osd] = 0; + } else { + map->osd_state[osd] ^= xorstate; + } + } + + /* new_up_client */ + *p = new_up_client; + len = ceph_decode_32(p); + while (len--) { + s32 osd; + struct ceph_entity_addr addr; + + osd = ceph_decode_32(p); + if (osd >= map->max_osd) + goto e_inval; + + if (struct_v >= 7) + ret = ceph_decode_entity_addrvec(p, end, msgr2, &addr); + else + ret = ceph_decode_entity_addr(p, end, &addr); + if (ret) + return ret; + + dout("%s osd%d addr %s\n", __func__, osd, ceph_pr_addr(&addr)); + + osdmap_info(map, "osd%d up\n", osd); + map->osd_state[osd] |= CEPH_OSD_EXISTS | CEPH_OSD_UP; + map->osd_addr[osd] = addr; + } + + *p = new_weight_end; + return 0; + +e_inval: + return -EINVAL; } /* * decode and apply an incremental map update. */ -struct ceph_osdmap *osdmap_apply_incremental(void **p, void *end, - struct ceph_osdmap *map, - struct ceph_messenger *msgr) +struct ceph_osdmap *osdmap_apply_incremental(void **p, void *end, bool msgr2, + struct ceph_osdmap *map) { - struct crush_map *newcrush = NULL; struct ceph_fsid fsid; u32 epoch = 0; struct ceph_timespec modified; @@ -813,17 +1977,18 @@ struct ceph_osdmap *osdmap_apply_incremental(void **p, void *end, __s64 new_pool_max; __s32 new_flags, max; void *start = *p; - int err = -EINVAL; - u16 version; + int err; + u8 struct_v; + + dout("%s %p to %p len %d\n", __func__, *p, end, (int)(end - *p)); - ceph_decode_16_safe(p, end, version, bad); - if (version != 6) { - pr_warning("got unknown v %d != 6 of inc osdmap\n", version); + err = get_osdmap_client_data_v(p, end, "inc", &struct_v); + if (err) goto bad; - } - ceph_decode_need(p, end, sizeof(fsid)+sizeof(modified)+2*sizeof(u32), - bad); + /* fsid, epoch, modified, new_pool_max, new_flags */ + ceph_decode_need(p, end, sizeof(fsid) + sizeof(u32) + sizeof(modified) + + sizeof(u64) + sizeof(u32), e_inval); ceph_decode_copy(p, &fsid, sizeof(fsid)); epoch = ceph_decode_32(p); BUG_ON(epoch != map->epoch+1); @@ -832,21 +1997,20 @@ struct ceph_osdmap *osdmap_apply_incremental(void **p, void *end, new_flags = ceph_decode_32(p); /* full map? */ - ceph_decode_32_safe(p, end, len, bad); + ceph_decode_32_safe(p, end, len, e_inval); if (len > 0) { dout("apply_incremental full map len %d, %p to %p\n", len, *p, end); - return osdmap_decode(p, min(*p+len, end)); + return ceph_osdmap_decode(p, min(*p+len, end), msgr2); } /* new crush? */ - ceph_decode_32_safe(p, end, len, bad); + ceph_decode_32_safe(p, end, len, e_inval); if (len > 0) { - dout("apply_incremental new crush map len %d, %p to %p\n", - len, *p, end); - newcrush = crush_decode(*p, min(*p+len, end)); - if (IS_ERR(newcrush)) - return ERR_CAST(newcrush); + err = osdmap_set_crush(map, + crush_decode(*p, min(*p + len, end))); + if (err) + goto bad; *p += len; } @@ -856,363 +2020,1091 @@ struct ceph_osdmap *osdmap_apply_incremental(void **p, void *end, if (new_pool_max >= 0) map->pool_max = new_pool_max; - ceph_decode_need(p, end, 5*sizeof(u32), bad); - /* new max? */ - max = ceph_decode_32(p); + ceph_decode_32_safe(p, end, max, e_inval); if (max >= 0) { err = osdmap_set_max_osd(map, max); - if (err < 0) + if (err) goto bad; } map->epoch++; map->modified = modified; - if (newcrush) { - if (map->crush) - crush_destroy(map->crush); - map->crush = newcrush; - newcrush = NULL; - } - /* new_pool */ - ceph_decode_32_safe(p, end, len, bad); - while (len--) { - struct ceph_pg_pool_info *pi; + /* new_pools */ + err = decode_new_pools(p, end, map); + if (err) + goto bad; - ceph_decode_64_safe(p, end, pool, bad); - pi = __lookup_pg_pool(&map->pg_pools, pool); - if (!pi) { - pi = kzalloc(sizeof(*pi), GFP_NOFS); - if (!pi) { - err = -ENOMEM; - goto bad; - } - pi->id = pool; - __insert_pg_pool(&map->pg_pools, pi); - } - err = __decode_pool(p, end, pi); - if (err < 0) - goto bad; - } - if (version >= 5) { - err = __decode_pool_names(p, end, map); - if (err < 0) - goto bad; - } + /* new_pool_names */ + err = decode_pool_names(p, end, map); + if (err) + goto bad; /* old_pool */ - ceph_decode_32_safe(p, end, len, bad); + ceph_decode_32_safe(p, end, len, e_inval); while (len--) { struct ceph_pg_pool_info *pi; - ceph_decode_64_safe(p, end, pool, bad); - pi = __lookup_pg_pool(&map->pg_pools, pool); + ceph_decode_64_safe(p, end, pool, e_inval); + pi = lookup_pg_pool(&map->pg_pools, pool); if (pi) __remove_pg_pool(&map->pg_pools, pi); } - /* new_up */ - err = -EINVAL; - ceph_decode_32_safe(p, end, len, bad); - while (len--) { - u32 osd; - struct ceph_entity_addr addr; - ceph_decode_32_safe(p, end, osd, bad); - ceph_decode_copy_safe(p, end, &addr, sizeof(addr), bad); - ceph_decode_addr(&addr); - pr_info("osd%d up\n", osd); - BUG_ON(osd >= map->max_osd); - map->osd_state[osd] |= CEPH_OSD_UP; - map->osd_addr[osd] = addr; + /* new_up_client, new_state, new_weight */ + err = decode_new_up_state_weight(p, end, struct_v, msgr2, map); + if (err) + goto bad; + + /* new_pg_temp */ + err = decode_new_pg_temp(p, end, map); + if (err) + goto bad; + + /* new_primary_temp */ + if (struct_v >= 1) { + err = decode_new_primary_temp(p, end, map); + if (err) + goto bad; } - /* new_state */ - ceph_decode_32_safe(p, end, len, bad); - while (len--) { - u32 osd; - u8 xorstate; - ceph_decode_32_safe(p, end, osd, bad); - xorstate = **(u8 **)p; - (*p)++; /* clean flag */ - if (xorstate == 0) - xorstate = CEPH_OSD_UP; - if (xorstate & CEPH_OSD_UP) - pr_info("osd%d down\n", osd); - if (osd < map->max_osd) - map->osd_state[osd] ^= xorstate; + /* new_primary_affinity */ + if (struct_v >= 2) { + err = decode_new_primary_affinity(p, end, map); + if (err) + goto bad; } - /* new_weight */ - ceph_decode_32_safe(p, end, len, bad); - while (len--) { - u32 osd, off; - ceph_decode_need(p, end, sizeof(u32)*2, bad); - osd = ceph_decode_32(p); - off = ceph_decode_32(p); - pr_info("osd%d weight 0x%x %s\n", osd, off, - off == CEPH_OSD_IN ? "(in)" : - (off == CEPH_OSD_OUT ? "(out)" : "")); - if (osd < map->max_osd) - map->osd_weight[osd] = off; + if (struct_v >= 3) { + /* new_erasure_code_profiles */ + ceph_decode_skip_map_of_map(p, end, string, string, string, + e_inval); + /* old_erasure_code_profiles */ + ceph_decode_skip_set(p, end, string, e_inval); } - /* new_pg_temp */ - ceph_decode_32_safe(p, end, len, bad); - while (len--) { - struct ceph_pg_mapping *pg; - int j; - struct ceph_pg pgid; - u32 pglen; + if (struct_v >= 4) { + err = decode_new_pg_upmap(p, end, map); + if (err) + goto bad; - err = ceph_decode_pgid(p, end, &pgid); + err = decode_old_pg_upmap(p, end, map); + if (err) + goto bad; + + err = decode_new_pg_upmap_items(p, end, map); + if (err) + goto bad; + + err = decode_old_pg_upmap_items(p, end, map); if (err) goto bad; - ceph_decode_need(p, end, sizeof(u32), bad); - pglen = ceph_decode_32(p); - if (pglen) { - ceph_decode_need(p, end, pglen*sizeof(u32), bad); - - /* removing existing (if any) */ - (void) __remove_pg_mapping(&map->pg_temp, pgid); - - /* insert */ - err = -EINVAL; - if (pglen > (UINT_MAX - sizeof(*pg)) / sizeof(u32)) - goto bad; - err = -ENOMEM; - pg = kmalloc(sizeof(*pg) + sizeof(u32)*pglen, GFP_NOFS); - if (!pg) - goto bad; - pg->pgid = pgid; - pg->len = pglen; - for (j = 0; j < pglen; j++) - pg->osds[j] = ceph_decode_32(p); - err = __insert_pg_mapping(pg, &map->pg_temp); - if (err) { - kfree(pg); - goto bad; - } - dout(" added pg_temp %lld.%x len %d\n", pgid.pool, - pgid.seed, pglen); - } else { - /* remove */ - __remove_pg_mapping(&map->pg_temp, pgid); - } } /* ignore the rest */ *p = end; + + dout("inc osdmap epoch %d max_osd %d\n", map->epoch, map->max_osd); return map; +e_inval: + err = -EINVAL; bad: - pr_err("corrupt inc osdmap epoch %d off %d (%p of %p-%p)\n", - epoch, (int)(*p - start), *p, start, end); + pr_err("corrupt inc osdmap (%d) epoch %d off %d (%p of %p-%p)\n", + err, epoch, (int)(*p - start), *p, start, end); print_hex_dump(KERN_DEBUG, "osdmap: ", DUMP_PREFIX_OFFSET, 16, 1, start, end - start, true); - if (newcrush) - crush_destroy(newcrush); return ERR_PTR(err); } +void ceph_oloc_copy(struct ceph_object_locator *dest, + const struct ceph_object_locator *src) +{ + ceph_oloc_destroy(dest); + + dest->pool = src->pool; + if (src->pool_ns) + dest->pool_ns = ceph_get_string(src->pool_ns); + else + dest->pool_ns = NULL; +} +EXPORT_SYMBOL(ceph_oloc_copy); + +void ceph_oloc_destroy(struct ceph_object_locator *oloc) +{ + ceph_put_string(oloc->pool_ns); +} +EXPORT_SYMBOL(ceph_oloc_destroy); + +void ceph_oid_copy(struct ceph_object_id *dest, + const struct ceph_object_id *src) +{ + ceph_oid_destroy(dest); + + if (src->name != src->inline_name) { + /* very rare, see ceph_object_id definition */ + dest->name = kmalloc(src->name_len + 1, + GFP_NOIO | __GFP_NOFAIL); + } else { + dest->name = dest->inline_name; + } + memcpy(dest->name, src->name, src->name_len + 1); + dest->name_len = src->name_len; +} +EXPORT_SYMBOL(ceph_oid_copy); + +static __printf(2, 0) +int oid_printf_vargs(struct ceph_object_id *oid, const char *fmt, va_list ap) +{ + int len; + + WARN_ON(!ceph_oid_empty(oid)); + len = vsnprintf(oid->inline_name, sizeof(oid->inline_name), fmt, ap); + if (len >= sizeof(oid->inline_name)) + return len; + oid->name_len = len; + return 0; +} /* - * calculate file layout from given offset, length. - * fill in correct oid, logical length, and object extent - * offset, length. - * - * for now, we write only a single su, until we can - * pass a stride back to the caller. + * If oid doesn't fit into inline buffer, BUG. */ -int ceph_calc_file_object_mapping(struct ceph_file_layout *layout, - u64 off, u64 len, - u64 *ono, - u64 *oxoff, u64 *oxlen) -{ - u32 osize = le32_to_cpu(layout->fl_object_size); - u32 su = le32_to_cpu(layout->fl_stripe_unit); - u32 sc = le32_to_cpu(layout->fl_stripe_count); - u32 bl, stripeno, stripepos, objsetno; - u32 su_per_object; - u64 t, su_offset; - - dout("mapping %llu~%llu osize %u fl_su %u\n", off, len, - osize, su); - if (su == 0 || sc == 0) - goto invalid; - su_per_object = osize / su; - if (su_per_object == 0) - goto invalid; - dout("osize %u / su %u = su_per_object %u\n", osize, su, - su_per_object); - - if ((su & ~PAGE_MASK) != 0) - goto invalid; - - /* bl = *off / su; */ - t = off; - do_div(t, su); - bl = t; - dout("off %llu / su %u = bl %u\n", off, su, bl); - - stripeno = bl / sc; - stripepos = bl % sc; - objsetno = stripeno / su_per_object; - - *ono = objsetno * sc + stripepos; - dout("objset %u * sc %u = ono %u\n", objsetno, sc, (unsigned int)*ono); - - /* *oxoff = *off % layout->fl_stripe_unit; # offset in su */ - t = off; - su_offset = do_div(t, su); - *oxoff = su_offset + (stripeno % su_per_object) * su; +void ceph_oid_printf(struct ceph_object_id *oid, const char *fmt, ...) +{ + va_list ap; - /* - * Calculate the length of the extent being written to the selected - * object. This is the minimum of the full length requested (len) or - * the remainder of the current stripe being written to. - */ - *oxlen = min_t(u64, len, su - su_offset); + va_start(ap, fmt); + BUG_ON(oid_printf_vargs(oid, fmt, ap)); + va_end(ap); +} +EXPORT_SYMBOL(ceph_oid_printf); - dout(" obj extent %llu~%llu\n", *oxoff, *oxlen); - return 0; +static __printf(3, 0) +int oid_aprintf_vargs(struct ceph_object_id *oid, gfp_t gfp, + const char *fmt, va_list ap) +{ + va_list aq; + int len; -invalid: - dout(" invalid layout\n"); - *ono = 0; - *oxoff = 0; - *oxlen = 0; - return -EINVAL; + va_copy(aq, ap); + len = oid_printf_vargs(oid, fmt, aq); + va_end(aq); + + if (len) { + char *external_name; + + external_name = kmalloc(len + 1, gfp); + if (!external_name) + return -ENOMEM; + + oid->name = external_name; + WARN_ON(vsnprintf(oid->name, len + 1, fmt, ap) != len); + oid->name_len = len; + } + + return 0; } -EXPORT_SYMBOL(ceph_calc_file_object_mapping); /* - * calculate an object layout (i.e. pgid) from an oid, - * file_layout, and osdmap + * If oid doesn't fit into inline buffer, allocate. */ -int ceph_calc_ceph_pg(struct ceph_pg *pg, const char *oid, - struct ceph_osdmap *osdmap, uint64_t pool) +int ceph_oid_aprintf(struct ceph_object_id *oid, gfp_t gfp, + const char *fmt, ...) { - struct ceph_pg_pool_info *pool_info; + va_list ap; + int ret; - BUG_ON(!osdmap); - pool_info = __lookup_pg_pool(&osdmap->pg_pools, pool); - if (!pool_info) - return -EIO; - pg->pool = pool; - pg->seed = ceph_str_hash(pool_info->object_hash, oid, strlen(oid)); + va_start(ap, fmt); + ret = oid_aprintf_vargs(oid, gfp, fmt, ap); + va_end(ap); - dout("%s '%s' pgid %lld.%x\n", __func__, oid, pg->pool, pg->seed); - return 0; + return ret; +} +EXPORT_SYMBOL(ceph_oid_aprintf); + +void ceph_oid_destroy(struct ceph_object_id *oid) +{ + if (oid->name != oid->inline_name) + kfree(oid->name); } -EXPORT_SYMBOL(ceph_calc_ceph_pg); +EXPORT_SYMBOL(ceph_oid_destroy); /* - * Calculate raw osd vector for the given pgid. Return pointer to osd - * array, or NULL on failure. + * osds only */ -static int *calc_pg_raw(struct ceph_osdmap *osdmap, struct ceph_pg pgid, - int *osds, int *num) +static bool __osds_equal(const struct ceph_osds *lhs, + const struct ceph_osds *rhs) { - struct ceph_pg_mapping *pg; - struct ceph_pg_pool_info *pool; - int ruleno; - int r; - u32 pps; + if (lhs->size == rhs->size && + !memcmp(lhs->osds, rhs->osds, rhs->size * sizeof(rhs->osds[0]))) + return true; - pool = __lookup_pg_pool(&osdmap->pg_pools, pgid.pool); - if (!pool) - return NULL; + return false; +} - /* pg_temp? */ - pgid.seed = ceph_stable_mod(pgid.seed, pool->pg_num, - pool->pgp_num_mask); - pg = __lookup_pg_mapping(&osdmap->pg_temp, pgid); - if (pg) { - *num = pg->len; - return pg->osds; +/* + * osds + primary + */ +static bool osds_equal(const struct ceph_osds *lhs, + const struct ceph_osds *rhs) +{ + if (__osds_equal(lhs, rhs) && + lhs->primary == rhs->primary) + return true; + + return false; +} + +static bool osds_valid(const struct ceph_osds *set) +{ + /* non-empty set */ + if (set->size > 0 && set->primary >= 0) + return true; + + /* empty can_shift_osds set */ + if (!set->size && set->primary == -1) + return true; + + /* empty !can_shift_osds set - all NONE */ + if (set->size > 0 && set->primary == -1) { + int i; + + for (i = 0; i < set->size; i++) { + if (set->osds[i] != CRUSH_ITEM_NONE) + break; + } + if (i == set->size) + return true; } - /* crush */ - ruleno = crush_find_rule(osdmap->crush, pool->crush_ruleset, - pool->type, pool->size); - if (ruleno < 0) { - pr_err("no crush rule pool %lld ruleset %d type %d size %d\n", - pgid.pool, pool->crush_ruleset, pool->type, - pool->size); - return NULL; + return false; +} + +void ceph_osds_copy(struct ceph_osds *dest, const struct ceph_osds *src) +{ + memcpy(dest->osds, src->osds, src->size * sizeof(src->osds[0])); + dest->size = src->size; + dest->primary = src->primary; +} + +bool ceph_pg_is_split(const struct ceph_pg *pgid, u32 old_pg_num, + u32 new_pg_num) +{ + int old_bits = calc_bits_of(old_pg_num); + int old_mask = (1 << old_bits) - 1; + int n; + + WARN_ON(pgid->seed >= old_pg_num); + if (new_pg_num <= old_pg_num) + return false; + + for (n = 1; ; n++) { + int next_bit = n << (old_bits - 1); + u32 s = next_bit | pgid->seed; + + if (s < old_pg_num || s == pgid->seed) + continue; + if (s >= new_pg_num) + break; + + s = ceph_stable_mod(s, old_pg_num, old_mask); + if (s == pgid->seed) + return true; } - if (pool->flags & CEPH_POOL_FLAG_HASHPSPOOL) { - /* hash pool id and seed sothat pool PGs do not overlap */ - pps = crush_hash32_2(CRUSH_HASH_RJENKINS1, - ceph_stable_mod(pgid.seed, pool->pgp_num, - pool->pgp_num_mask), - pgid.pool); + return false; +} + +bool ceph_is_new_interval(const struct ceph_osds *old_acting, + const struct ceph_osds *new_acting, + const struct ceph_osds *old_up, + const struct ceph_osds *new_up, + int old_size, + int new_size, + int old_min_size, + int new_min_size, + u32 old_pg_num, + u32 new_pg_num, + bool old_sort_bitwise, + bool new_sort_bitwise, + bool old_recovery_deletes, + bool new_recovery_deletes, + const struct ceph_pg *pgid) +{ + return !osds_equal(old_acting, new_acting) || + !osds_equal(old_up, new_up) || + old_size != new_size || + old_min_size != new_min_size || + ceph_pg_is_split(pgid, old_pg_num, new_pg_num) || + old_sort_bitwise != new_sort_bitwise || + old_recovery_deletes != new_recovery_deletes; +} + +static int calc_pg_rank(int osd, const struct ceph_osds *acting) +{ + int i; + + for (i = 0; i < acting->size; i++) { + if (acting->osds[i] == osd) + return i; + } + + return -1; +} + +static bool primary_changed(const struct ceph_osds *old_acting, + const struct ceph_osds *new_acting) +{ + if (!old_acting->size && !new_acting->size) + return false; /* both still empty */ + + if (!old_acting->size ^ !new_acting->size) + return true; /* was empty, now not, or vice versa */ + + if (old_acting->primary != new_acting->primary) + return true; /* primary changed */ + + if (calc_pg_rank(old_acting->primary, old_acting) != + calc_pg_rank(new_acting->primary, new_acting)) + return true; + + return false; /* same primary (tho replicas may have changed) */ +} + +bool ceph_osds_changed(const struct ceph_osds *old_acting, + const struct ceph_osds *new_acting, + bool any_change) +{ + if (primary_changed(old_acting, new_acting)) + return true; + + if (any_change && !__osds_equal(old_acting, new_acting)) + return true; + + return false; +} + +/* + * Map an object into a PG. + * + * Should only be called with target_oid and target_oloc (as opposed to + * base_oid and base_oloc), since tiering isn't taken into account. + */ +void __ceph_object_locator_to_pg(struct ceph_pg_pool_info *pi, + const struct ceph_object_id *oid, + const struct ceph_object_locator *oloc, + struct ceph_pg *raw_pgid) +{ + WARN_ON(pi->id != oloc->pool); + + if (!oloc->pool_ns) { + raw_pgid->pool = oloc->pool; + raw_pgid->seed = ceph_str_hash(pi->object_hash, oid->name, + oid->name_len); + dout("%s %s -> raw_pgid %llu.%x\n", __func__, oid->name, + raw_pgid->pool, raw_pgid->seed); + } else { + char stack_buf[256]; + char *buf = stack_buf; + int nsl = oloc->pool_ns->len; + size_t total = nsl + 1 + oid->name_len; + + if (total > sizeof(stack_buf)) + buf = kmalloc(total, GFP_NOIO | __GFP_NOFAIL); + memcpy(buf, oloc->pool_ns->str, nsl); + buf[nsl] = '\037'; + memcpy(buf + nsl + 1, oid->name, oid->name_len); + raw_pgid->pool = oloc->pool; + raw_pgid->seed = ceph_str_hash(pi->object_hash, buf, total); + if (buf != stack_buf) + kfree(buf); + dout("%s %s ns %.*s -> raw_pgid %llu.%x\n", __func__, + oid->name, nsl, oloc->pool_ns->str, + raw_pgid->pool, raw_pgid->seed); + } +} + +int ceph_object_locator_to_pg(struct ceph_osdmap *osdmap, + const struct ceph_object_id *oid, + const struct ceph_object_locator *oloc, + struct ceph_pg *raw_pgid) +{ + struct ceph_pg_pool_info *pi; + + pi = ceph_pg_pool_by_id(osdmap, oloc->pool); + if (!pi) + return -ENOENT; + + __ceph_object_locator_to_pg(pi, oid, oloc, raw_pgid); + return 0; +} +EXPORT_SYMBOL(ceph_object_locator_to_pg); + +/* + * Map a raw PG (full precision ps) into an actual PG. + */ +static void raw_pg_to_pg(struct ceph_pg_pool_info *pi, + const struct ceph_pg *raw_pgid, + struct ceph_pg *pgid) +{ + pgid->pool = raw_pgid->pool; + pgid->seed = ceph_stable_mod(raw_pgid->seed, pi->pg_num, + pi->pg_num_mask); +} + +/* + * Map a raw PG (full precision ps) into a placement ps (placement + * seed). Include pool id in that value so that different pools don't + * use the same seeds. + */ +static u32 raw_pg_to_pps(struct ceph_pg_pool_info *pi, + const struct ceph_pg *raw_pgid) +{ + if (pi->flags & CEPH_POOL_FLAG_HASHPSPOOL) { + /* hash pool id and seed so that pool PGs do not overlap */ + return crush_hash32_2(CRUSH_HASH_RJENKINS1, + ceph_stable_mod(raw_pgid->seed, + pi->pgp_num, + pi->pgp_num_mask), + raw_pgid->pool); } else { /* - * legacy ehavior: add ps and pool together. this is + * legacy behavior: add ps and pool together. this is * not a great approach because the PGs from each pool * will overlap on top of each other: 0.5 == 1.4 == * 2.3 == ... */ - pps = ceph_stable_mod(pgid.seed, pool->pgp_num, - pool->pgp_num_mask) + - (unsigned)pgid.pool; - } - r = crush_do_rule(osdmap->crush, ruleno, pps, osds, - min_t(int, pool->size, *num), - osdmap->osd_weight); - if (r < 0) { - pr_err("error %d from crush rule: pool %lld ruleset %d type %d" - " size %d\n", r, pgid.pool, pool->crush_ruleset, - pool->type, pool->size); - return NULL; + return ceph_stable_mod(raw_pgid->seed, pi->pgp_num, + pi->pgp_num_mask) + + (unsigned)raw_pgid->pool; + } +} + +/* + * Magic value used for a "default" fallback choose_args, used if the + * crush_choose_arg_map passed to do_crush() does not exist. If this + * also doesn't exist, fall back to canonical weights. + */ +#define CEPH_DEFAULT_CHOOSE_ARGS -1 + +static int do_crush(struct ceph_osdmap *map, int ruleno, int x, + int *result, int result_max, + const __u32 *weight, int weight_max, + s64 choose_args_index) +{ + struct crush_choose_arg_map *arg_map; + struct crush_work *work; + int r; + + BUG_ON(result_max > CEPH_PG_MAX_SIZE); + + arg_map = lookup_choose_arg_map(&map->crush->choose_args, + choose_args_index); + if (!arg_map) + arg_map = lookup_choose_arg_map(&map->crush->choose_args, + CEPH_DEFAULT_CHOOSE_ARGS); + + work = get_workspace(&map->crush_wsm, map->crush); + r = crush_do_rule(map->crush, ruleno, x, result, result_max, + weight, weight_max, work, + arg_map ? arg_map->args : NULL); + put_workspace(&map->crush_wsm, work); + return r; +} + +static void remove_nonexistent_osds(struct ceph_osdmap *osdmap, + struct ceph_pg_pool_info *pi, + struct ceph_osds *set) +{ + int i; + + if (ceph_can_shift_osds(pi)) { + int removed = 0; + + /* shift left */ + for (i = 0; i < set->size; i++) { + if (!ceph_osd_exists(osdmap, set->osds[i])) { + removed++; + continue; + } + if (removed) + set->osds[i - removed] = set->osds[i]; + } + set->size -= removed; + } else { + /* set dne devices to NONE */ + for (i = 0; i < set->size; i++) { + if (!ceph_osd_exists(osdmap, set->osds[i])) + set->osds[i] = CRUSH_ITEM_NONE; + } + } +} + +/* + * Calculate raw set (CRUSH output) for given PG and filter out + * nonexistent OSDs. ->primary is undefined for a raw set. + * + * Placement seed (CRUSH input) is returned through @ppps. + */ +static void pg_to_raw_osds(struct ceph_osdmap *osdmap, + struct ceph_pg_pool_info *pi, + const struct ceph_pg *raw_pgid, + struct ceph_osds *raw, + u32 *ppps) +{ + u32 pps = raw_pg_to_pps(pi, raw_pgid); + int ruleno; + int len; + + ceph_osds_init(raw); + if (ppps) + *ppps = pps; + + ruleno = crush_find_rule(osdmap->crush, pi->crush_ruleset, pi->type, + pi->size); + if (ruleno < 0) { + pr_err("no crush rule: pool %lld ruleset %d type %d size %d\n", + pi->id, pi->crush_ruleset, pi->type, pi->size); + return; + } + + if (pi->size > ARRAY_SIZE(raw->osds)) { + pr_err_ratelimited("pool %lld ruleset %d type %d too wide: size %d > %zu\n", + pi->id, pi->crush_ruleset, pi->type, pi->size, + ARRAY_SIZE(raw->osds)); + return; + } + + len = do_crush(osdmap, ruleno, pps, raw->osds, pi->size, + osdmap->osd_weight, osdmap->max_osd, pi->id); + if (len < 0) { + pr_err("error %d from crush rule %d: pool %lld ruleset %d type %d size %d\n", + len, ruleno, pi->id, pi->crush_ruleset, pi->type, + pi->size); + return; + } + + raw->size = len; + remove_nonexistent_osds(osdmap, pi, raw); +} + +/* apply pg_upmap[_items] mappings */ +static void apply_upmap(struct ceph_osdmap *osdmap, + const struct ceph_pg *pgid, + struct ceph_osds *raw) +{ + struct ceph_pg_mapping *pg; + int i, j; + + pg = lookup_pg_mapping(&osdmap->pg_upmap, pgid); + if (pg) { + /* make sure targets aren't marked out */ + for (i = 0; i < pg->pg_upmap.len; i++) { + int osd = pg->pg_upmap.osds[i]; + + if (osd != CRUSH_ITEM_NONE && + osd < osdmap->max_osd && + osdmap->osd_weight[osd] == 0) { + /* reject/ignore explicit mapping */ + return; + } + } + for (i = 0; i < pg->pg_upmap.len; i++) + raw->osds[i] = pg->pg_upmap.osds[i]; + raw->size = pg->pg_upmap.len; + /* check and apply pg_upmap_items, if any */ + } + + pg = lookup_pg_mapping(&osdmap->pg_upmap_items, pgid); + if (pg) { + /* + * Note: this approach does not allow a bidirectional swap, + * e.g., [[1,2],[2,1]] applied to [0,1,2] -> [0,2,1]. + */ + for (i = 0; i < pg->pg_upmap_items.len; i++) { + int from = pg->pg_upmap_items.from_to[i][0]; + int to = pg->pg_upmap_items.from_to[i][1]; + int pos = -1; + bool exists = false; + + /* make sure replacement doesn't already appear */ + for (j = 0; j < raw->size; j++) { + int osd = raw->osds[j]; + + if (osd == to) { + exists = true; + break; + } + /* ignore mapping if target is marked out */ + if (osd == from && pos < 0 && + !(to != CRUSH_ITEM_NONE && + to < osdmap->max_osd && + osdmap->osd_weight[to] == 0)) { + pos = j; + } + } + if (!exists && pos >= 0) + raw->osds[pos] = to; + } } - *num = r; - return osds; } /* - * Return acting set for given pgid. + * Given raw set, calculate up set and up primary. By definition of an + * up set, the result won't contain nonexistent or down OSDs. + * + * This is done in-place - on return @set is the up set. If it's + * empty, ->primary will remain undefined. */ -int ceph_calc_pg_acting(struct ceph_osdmap *osdmap, struct ceph_pg pgid, - int *acting) +static void raw_to_up_osds(struct ceph_osdmap *osdmap, + struct ceph_pg_pool_info *pi, + struct ceph_osds *set) +{ + int i; + + /* ->primary is undefined for a raw set */ + BUG_ON(set->primary != -1); + + if (ceph_can_shift_osds(pi)) { + int removed = 0; + + /* shift left */ + for (i = 0; i < set->size; i++) { + if (ceph_osd_is_down(osdmap, set->osds[i])) { + removed++; + continue; + } + if (removed) + set->osds[i - removed] = set->osds[i]; + } + set->size -= removed; + if (set->size > 0) + set->primary = set->osds[0]; + } else { + /* set down/dne devices to NONE */ + for (i = set->size - 1; i >= 0; i--) { + if (ceph_osd_is_down(osdmap, set->osds[i])) + set->osds[i] = CRUSH_ITEM_NONE; + else + set->primary = set->osds[i]; + } + } +} + +static void apply_primary_affinity(struct ceph_osdmap *osdmap, + struct ceph_pg_pool_info *pi, + u32 pps, + struct ceph_osds *up) { - int rawosds[CEPH_PG_MAX_SIZE], *osds; - int i, o, num = CEPH_PG_MAX_SIZE; + int i; + int pos = -1; + + /* + * Do we have any non-default primary_affinity values for these + * osds? + */ + if (!osdmap->osd_primary_affinity) + return; - osds = calc_pg_raw(osdmap, pgid, rawosds, &num); - if (!osds) + for (i = 0; i < up->size; i++) { + int osd = up->osds[i]; + + if (osd != CRUSH_ITEM_NONE && + osdmap->osd_primary_affinity[osd] != + CEPH_OSD_DEFAULT_PRIMARY_AFFINITY) { + break; + } + } + if (i == up->size) + return; + + /* + * Pick the primary. Feed both the seed (for the pg) and the + * osd into the hash/rng so that a proportional fraction of an + * osd's pgs get rejected as primary. + */ + for (i = 0; i < up->size; i++) { + int osd = up->osds[i]; + u32 aff; + + if (osd == CRUSH_ITEM_NONE) + continue; + + aff = osdmap->osd_primary_affinity[osd]; + if (aff < CEPH_OSD_MAX_PRIMARY_AFFINITY && + (crush_hash32_2(CRUSH_HASH_RJENKINS1, + pps, osd) >> 16) >= aff) { + /* + * We chose not to use this primary. Note it + * anyway as a fallback in case we don't pick + * anyone else, but keep looking. + */ + if (pos < 0) + pos = i; + } else { + pos = i; + break; + } + } + if (pos < 0) + return; + + up->primary = up->osds[pos]; + + if (ceph_can_shift_osds(pi) && pos > 0) { + /* move the new primary to the front */ + for (i = pos; i > 0; i--) + up->osds[i] = up->osds[i - 1]; + up->osds[0] = up->primary; + } +} + +/* + * Get pg_temp and primary_temp mappings for given PG. + * + * Note that a PG may have none, only pg_temp, only primary_temp or + * both pg_temp and primary_temp mappings. This means @temp isn't + * always a valid OSD set on return: in the "only primary_temp" case, + * @temp will have its ->primary >= 0 but ->size == 0. + */ +static void get_temp_osds(struct ceph_osdmap *osdmap, + struct ceph_pg_pool_info *pi, + const struct ceph_pg *pgid, + struct ceph_osds *temp) +{ + struct ceph_pg_mapping *pg; + int i; + + ceph_osds_init(temp); + + /* pg_temp? */ + pg = lookup_pg_mapping(&osdmap->pg_temp, pgid); + if (pg) { + for (i = 0; i < pg->pg_temp.len; i++) { + if (ceph_osd_is_down(osdmap, pg->pg_temp.osds[i])) { + if (ceph_can_shift_osds(pi)) + continue; + + temp->osds[temp->size++] = CRUSH_ITEM_NONE; + } else { + temp->osds[temp->size++] = pg->pg_temp.osds[i]; + } + } + + /* apply pg_temp's primary */ + for (i = 0; i < temp->size; i++) { + if (temp->osds[i] != CRUSH_ITEM_NONE) { + temp->primary = temp->osds[i]; + break; + } + } + } + + /* primary_temp? */ + pg = lookup_pg_mapping(&osdmap->primary_temp, pgid); + if (pg) + temp->primary = pg->primary_temp.osd; +} + +/* + * Map a PG to its acting set as well as its up set. + * + * Acting set is used for data mapping purposes, while up set can be + * recorded for detecting interval changes and deciding whether to + * resend a request. + */ +void ceph_pg_to_up_acting_osds(struct ceph_osdmap *osdmap, + struct ceph_pg_pool_info *pi, + const struct ceph_pg *raw_pgid, + struct ceph_osds *up, + struct ceph_osds *acting) +{ + struct ceph_pg pgid; + u32 pps; + + WARN_ON(pi->id != raw_pgid->pool); + raw_pg_to_pg(pi, raw_pgid, &pgid); + + pg_to_raw_osds(osdmap, pi, raw_pgid, up, &pps); + apply_upmap(osdmap, &pgid, up); + raw_to_up_osds(osdmap, pi, up); + apply_primary_affinity(osdmap, pi, pps, up); + get_temp_osds(osdmap, pi, &pgid, acting); + if (!acting->size) { + memcpy(acting->osds, up->osds, up->size * sizeof(up->osds[0])); + acting->size = up->size; + if (acting->primary == -1) + acting->primary = up->primary; + } + WARN_ON(!osds_valid(up) || !osds_valid(acting)); +} + +bool ceph_pg_to_primary_shard(struct ceph_osdmap *osdmap, + struct ceph_pg_pool_info *pi, + const struct ceph_pg *raw_pgid, + struct ceph_spg *spgid) +{ + struct ceph_pg pgid; + struct ceph_osds up, acting; + int i; + + WARN_ON(pi->id != raw_pgid->pool); + raw_pg_to_pg(pi, raw_pgid, &pgid); + + if (ceph_can_shift_osds(pi)) { + spgid->pgid = pgid; /* struct */ + spgid->shard = CEPH_SPG_NOSHARD; + return true; + } + + ceph_pg_to_up_acting_osds(osdmap, pi, &pgid, &up, &acting); + for (i = 0; i < acting.size; i++) { + if (acting.osds[i] == acting.primary) { + spgid->pgid = pgid; /* struct */ + spgid->shard = i; + return true; + } + } + + return false; +} + +/* + * Return acting primary for given PG, or -1 if none. + */ +int ceph_pg_to_acting_primary(struct ceph_osdmap *osdmap, + const struct ceph_pg *raw_pgid) +{ + struct ceph_pg_pool_info *pi; + struct ceph_osds up, acting; + + pi = ceph_pg_pool_by_id(osdmap, raw_pgid->pool); + if (!pi) return -1; - /* primary is first up osd */ - o = 0; - for (i = 0; i < num; i++) - if (ceph_osd_is_up(osdmap, osds[i])) - acting[o++] = osds[i]; - return o; + ceph_pg_to_up_acting_osds(osdmap, pi, raw_pgid, &up, &acting); + return acting.primary; } +EXPORT_SYMBOL(ceph_pg_to_acting_primary); + +static struct crush_loc_node *alloc_crush_loc(size_t type_name_len, + size_t name_len) +{ + struct crush_loc_node *loc; + + loc = kmalloc(sizeof(*loc) + type_name_len + name_len + 2, GFP_NOIO); + if (!loc) + return NULL; + + RB_CLEAR_NODE(&loc->cl_node); + return loc; +} + +static void free_crush_loc(struct crush_loc_node *loc) +{ + WARN_ON(!RB_EMPTY_NODE(&loc->cl_node)); + + kfree(loc); +} + +static int crush_loc_compare(const struct crush_loc *loc1, + const struct crush_loc *loc2) +{ + return strcmp(loc1->cl_type_name, loc2->cl_type_name) ?: + strcmp(loc1->cl_name, loc2->cl_name); +} + +DEFINE_RB_FUNCS2(crush_loc, struct crush_loc_node, cl_loc, crush_loc_compare, + RB_BYPTR, const struct crush_loc *, cl_node) /* - * Return primary osd for given pgid, or -1 if none. + * Parses a set of <bucket type name>':'<bucket name> pairs separated + * by '|', e.g. "rack:foo1|rack:foo2|datacenter:bar". + * + * Note that @crush_location is modified by strsep(). */ -int ceph_calc_pg_primary(struct ceph_osdmap *osdmap, struct ceph_pg pgid) +int ceph_parse_crush_location(char *crush_location, struct rb_root *locs) +{ + struct crush_loc_node *loc; + const char *type_name, *name, *colon; + size_t type_name_len, name_len; + + dout("%s '%s'\n", __func__, crush_location); + while ((type_name = strsep(&crush_location, "|"))) { + colon = strchr(type_name, ':'); + if (!colon) + return -EINVAL; + + type_name_len = colon - type_name; + if (type_name_len == 0) + return -EINVAL; + + name = colon + 1; + name_len = strlen(name); + if (name_len == 0) + return -EINVAL; + + loc = alloc_crush_loc(type_name_len, name_len); + if (!loc) + return -ENOMEM; + + loc->cl_loc.cl_type_name = loc->cl_data; + memcpy(loc->cl_loc.cl_type_name, type_name, type_name_len); + loc->cl_loc.cl_type_name[type_name_len] = '\0'; + + loc->cl_loc.cl_name = loc->cl_data + type_name_len + 1; + memcpy(loc->cl_loc.cl_name, name, name_len); + loc->cl_loc.cl_name[name_len] = '\0'; + + if (!__insert_crush_loc(locs, loc)) { + free_crush_loc(loc); + return -EEXIST; + } + + dout("%s type_name '%s' name '%s'\n", __func__, + loc->cl_loc.cl_type_name, loc->cl_loc.cl_name); + } + + return 0; +} + +int ceph_compare_crush_locs(struct rb_root *locs1, struct rb_root *locs2) { - int rawosds[CEPH_PG_MAX_SIZE], *osds; - int i, num = CEPH_PG_MAX_SIZE; + struct rb_node *n1 = rb_first(locs1); + struct rb_node *n2 = rb_first(locs2); + int ret; + + for ( ; n1 && n2; n1 = rb_next(n1), n2 = rb_next(n2)) { + struct crush_loc_node *loc1 = + rb_entry(n1, struct crush_loc_node, cl_node); + struct crush_loc_node *loc2 = + rb_entry(n2, struct crush_loc_node, cl_node); + + ret = crush_loc_compare(&loc1->cl_loc, &loc2->cl_loc); + if (ret) + return ret; + } - osds = calc_pg_raw(osdmap, pgid, rawosds, &num); - if (!osds) + if (!n1 && n2) return -1; + if (n1 && !n2) + return 1; + return 0; +} - /* primary is first up osd */ - for (i = 0; i < num; i++) - if (ceph_osd_is_up(osdmap, osds[i])) - return osds[i]; - return -1; +void ceph_clear_crush_locs(struct rb_root *locs) +{ + while (!RB_EMPTY_ROOT(locs)) { + struct crush_loc_node *loc = + rb_entry(rb_first(locs), struct crush_loc_node, cl_node); + + erase_crush_loc(locs, loc); + free_crush_loc(loc); + } +} + +/* + * [a-zA-Z0-9-_.]+ + */ +static bool is_valid_crush_name(const char *name) +{ + do { + if (!('a' <= *name && *name <= 'z') && + !('A' <= *name && *name <= 'Z') && + !('0' <= *name && *name <= '9') && + *name != '-' && *name != '_' && *name != '.') + return false; + } while (*++name != '\0'); + + return true; +} + +/* + * Gets the parent of an item. Returns its id (<0 because the + * parent is always a bucket), type id (>0 for the same reason, + * via @parent_type_id) and location (via @parent_loc). If no + * parent, returns 0. + * + * Does a linear search, as there are no parent pointers of any + * kind. Note that the result is ambiguous for items that occur + * multiple times in the map. + */ +static int get_immediate_parent(struct crush_map *c, int id, + u16 *parent_type_id, + struct crush_loc *parent_loc) +{ + struct crush_bucket *b; + struct crush_name_node *type_cn, *cn; + int i, j; + + for (i = 0; i < c->max_buckets; i++) { + b = c->buckets[i]; + if (!b) + continue; + + /* ignore per-class shadow hierarchy */ + cn = lookup_crush_name(&c->names, b->id); + if (!cn || !is_valid_crush_name(cn->cn_name)) + continue; + + for (j = 0; j < b->size; j++) { + if (b->items[j] != id) + continue; + + *parent_type_id = b->type; + type_cn = lookup_crush_name(&c->type_names, b->type); + parent_loc->cl_type_name = type_cn->cn_name; + parent_loc->cl_name = cn->cn_name; + return b->id; + } + } + + return 0; /* no parent */ +} + +/* + * Calculates the locality/distance from an item to a client + * location expressed in terms of CRUSH hierarchy as a set of + * (bucket type name, bucket name) pairs. Specifically, looks + * for the lowest-valued bucket type for which the location of + * @id matches one of the locations in @locs, so for standard + * bucket types (host = 1, rack = 3, datacenter = 8, zone = 9) + * a matching host is closer than a matching rack and a matching + * data center is closer than a matching zone. + * + * Specifying multiple locations (a "multipath" location) such + * as "rack=foo1 rack=foo2 datacenter=bar" is allowed -- @locs + * is a multimap. The locality will be: + * + * - 3 for OSDs in racks foo1 and foo2 + * - 8 for OSDs in data center bar + * - -1 for all other OSDs + * + * The lowest possible bucket type is 1, so the best locality + * for an OSD is 1 (i.e. a matching host). Locality 0 would be + * the OSD itself. + */ +int ceph_get_crush_locality(struct ceph_osdmap *osdmap, int id, + struct rb_root *locs) +{ + struct crush_loc loc; + u16 type_id; + + /* + * Instead of repeated get_immediate_parent() calls, + * the location of @id could be obtained with a single + * depth-first traversal. + */ + for (;;) { + id = get_immediate_parent(osdmap->crush, id, &type_id, &loc); + if (id >= 0) + return -1; /* not local */ + + if (lookup_crush_loc(locs, &loc)) + return type_id; + } } -EXPORT_SYMBOL(ceph_calc_pg_primary); |