cregit-Linux how code gets into the kernel

Release 4.11 net/ceph/osdmap.c

Directory: net/ceph
#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>
#include <linux/ceph/decode.h>
#include <linux/crush/hash.h>
#include <linux/crush/mapper.h>


char *ceph_osdmap_state_str(char *str, int len, int state) { if (!len) return str; if ((state & CEPH_OSD_EXISTS) && (state & CEPH_OSD_UP)) snprintf(str, len, "exists, up"); else if (state & CEPH_OSD_EXISTS) snprintf(str, len, "exists"); else if (state & CEPH_OSD_UP) snprintf(str, len, "up"); else snprintf(str, len, "doesn't exist"); return str; }

Contributors

PersonTokensPropCommitsCommitProp
Sage Weil6975.00%150.00%
Cong Ding2325.00%150.00%
Total92100.00%2100.00%

/* maps */
static int calc_bits_of(unsigned int t) { int b = 0; while (t) { t = t >> 1; b++; } return b; }

Contributors

PersonTokensPropCommitsCommitProp
Sage Weil3296.97%150.00%
Eric Dumazet13.03%150.00%
Total33100.00%2100.00%

/* * the foo_mask is the smallest value 2^n-1 that is >= foo. */
static void calc_pg_masks(struct ceph_pg_pool_info *pi) { pi->pg_num_mask = (1 << calc_bits_of(pi->pg_num-1)) - 1; pi->pgp_num_mask = (1 << calc_bits_of(pi->pgp_num-1)) - 1; }

Contributors

PersonTokensPropCommitsCommitProp
Sage Weil49100.00%1100.00%
Total49100.00%1100.00%

/* * decode crush map */
static int crush_decode_uniform_bucket(void **p, void *end, struct crush_bucket_uniform *b) { dout("crush_decode_uniform_bucket %p to %p\n", *p, end); ceph_decode_need(p, end, (1+b->h.size) * sizeof(u32), bad); b->item_weight = ceph_decode_32(p); return 0; bad: return -EINVAL; }

Contributors

PersonTokensPropCommitsCommitProp
Sage Weil72100.00%2100.00%
Total72100.00%2100.00%


static int crush_decode_list_bucket(void **p, void *end, struct crush_bucket_list *b) { int j; dout("crush_decode_list_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; b->sum_weights = kcalloc(b->h.size, sizeof(u32), GFP_NOFS); if (b->sum_weights == NULL) return -ENOMEM; ceph_decode_need(p, end, 2 * b->h.size * sizeof(u32), bad); for (j = 0; j < b->h.size; j++) { b->item_weights[j] = ceph_decode_32(p); b->sum_weights[j] = ceph_decode_32(p); } return 0; bad: return -EINVAL; }

Contributors

PersonTokensPropCommitsCommitProp
Sage Weil171100.00%2100.00%
Total171100.00%2100.00%


static int crush_decode_tree_bucket(void **p, void *end, struct crush_bucket_tree *b) { int j; dout("crush_decode_tree_bucket %p to %p\n", *p, end); 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; ceph_decode_need(p, end, b->num_nodes * sizeof(u32), bad); for (j = 0; j < b->num_nodes; j++) b->node_weights[j] = ceph_decode_32(p); return 0; bad: return -EINVAL; }

Contributors

PersonTokensPropCommitsCommitProp
Sage Weil12999.23%266.67%
Ilya Dryomov10.77%133.33%
Total130100.00%3100.00%


static int crush_decode_straw_bucket(void **p, void *end, struct crush_bucket_straw *b) { int j; dout("crush_decode_straw_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; b->straws = kcalloc(b->h.size, sizeof(u32), GFP_NOFS); if (b->straws == NULL) return -ENOMEM; ceph_decode_need(p, end, 2 * b->h.size * sizeof(u32), bad); for (j = 0; j < b->h.size; j++) { b->item_weights[j] = ceph_decode_32(p); b->straws[j] = ceph_decode_32(p); } return 0; bad: return -EINVAL; }

Contributors

PersonTokensPropCommitsCommitProp
Sage Weil171100.00%2100.00%
Total171100.00%2100.00%


static int crush_decode_straw2_bucket(void **p, void *end, struct crush_bucket_straw2 *b) { 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; }

Contributors

PersonTokensPropCommitsCommitProp
Ilya Dryomov123100.00%1100.00%
Total123100.00%1100.00%


static int skip_name_map(void **p, void *end) { 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; bad: return -EINVAL; }

Contributors

PersonTokensPropCommitsCommitProp
Sage Weil72100.00%1100.00%
Total72100.00%1100.00%


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); } }

Contributors

PersonTokensPropCommitsCommitProp
Ilya Dryomov109100.00%1100.00%
Total109100.00%1100.00%


static struct crush_map *crush_decode(void *pbyval, void *end) { struct crush_map *c; int err = -EINVAL; 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)); c = kzalloc(sizeof(*c), GFP_NOFS); if (c == NULL) return ERR_PTR(-ENOMEM); /* set tunables to default values */ c->choose_local_tries = 2; c->choose_local_fallback_tries = 5; c->choose_total_tries = 19; c->chooseleaf_descend_once = 0; ceph_decode_need(p, end, 4*sizeof(u32), bad); magic = ceph_decode_32(p); if (magic != CRUSH_MAGIC) { pr_err("crush_decode magic %x != current %x\n", (unsigned int)magic, (unsigned int)CRUSH_MAGIC); goto bad; } c->max_buckets = ceph_decode_32(p); c->max_rules = ceph_decode_32(p); c->max_devices = ceph_decode_32(p); c->buckets = kcalloc(c->max_buckets, sizeof(*c->buckets), GFP_NOFS); if (c->buckets == NULL) goto badmem; c->rules = kcalloc(c->max_rules, sizeof(*c->rules), GFP_NOFS); if (c->rules == NULL) goto badmem; /* buckets */ for (i = 0; i < c->max_buckets; i++) { int size = 0; u32 alg; struct crush_bucket *b; ceph_decode_32_safe(p, end, alg, bad); if (alg == 0) { c->buckets[i] = NULL; continue; } dout("crush_decode bucket %d off %x %p to %p\n", i, (int)(*p-start), *p, end); switch (alg) { case CRUSH_BUCKET_UNIFORM: size = sizeof(struct crush_bucket_uniform); break; case CRUSH_BUCKET_LIST: size = sizeof(struct crush_bucket_list); break; case CRUSH_BUCKET_TREE: size = sizeof(struct crush_bucket_tree); break; 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); b = c->buckets[i] = kzalloc(size, GFP_NOFS); if (b == NULL) goto badmem; ceph_decode_need(p, end, 4*sizeof(u32), bad); b->id = ceph_decode_32(p); b->type = ceph_decode_16(p); b->alg = ceph_decode_8(p); b->hash = ceph_decode_8(p); b->weight = ceph_decode_32(p); b->size = ceph_decode_32(p); dout("crush_decode bucket size %d off %x %p to %p\n", b->size, (int)(*p-start), *p, end); b->items = kcalloc(b->size, sizeof(__s32), GFP_NOFS); if (b->items == NULL) goto badmem; ceph_decode_need(p, end, b->size*sizeof(u32), bad); for (j = 0; j < b->size; j++) b->items[j] = ceph_decode_32(p); switch (b->alg) { case CRUSH_BUCKET_UNIFORM: err = crush_decode_uniform_bucket(p, end, (struct crush_bucket_uniform *)b); if (err < 0) goto bad; break; case CRUSH_BUCKET_LIST: err = crush_decode_list_bucket(p, end, (struct crush_bucket_list *)b); if (err < 0) goto bad; break; case CRUSH_BUCKET_TREE: err = crush_decode_tree_bucket(p, end, (struct crush_bucket_tree *)b); if (err < 0) goto bad; break; case CRUSH_BUCKET_STRAW: err = crush_decode_straw_bucket(p, end, (struct crush_bucket_straw *)b); if (err < 0) goto bad; break; case CRUSH_BUCKET_STRAW2: err = crush_decode_straw2_bucket(p, end, (struct crush_bucket_straw2 *)b); if (err < 0) goto bad; break; } } /* rules */ dout("rule vec is %p\n", c->rules); for (i = 0; i < c->max_rules; i++) { u32 yes; struct crush_rule *r; ceph_decode_32_safe(p, end, yes, bad); if (!yes) { dout("crush_decode NO rule %d off %x %p to %p\n", i, (int)(*p-start), *p, end); c->rules[i] = NULL; continue; } dout("crush_decode rule %d off %x %p to %p\n", i, (int)(*p-start), *p, 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); if (r == NULL) goto badmem; dout(" rule %d is at %p\n", 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); for (j = 0; j < r->len; j++) { r->steps[j].op = ceph_decode_32(p); r->steps[j].arg1 = ceph_decode_32(p); r->steps[j].arg2 = ceph_decode_32(p); } } /* 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; } /* 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\n", c->choose_local_tries); dout("crush decode tunable choose_local_fallback_tries = %d\n", c->choose_local_fallback_tries); 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\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); done: crush_finalize(c); dout("crush_decode success\n"); return c; badmem: err = -ENOMEM; bad: dout("crush_decode fail %d\n", err); crush_destroy(c); return ERR_PTR(err); }

Contributors

PersonTokensPropCommitsCommitProp
Sage Weil115785.51%538.46%
Ilya Dryomov14911.01%538.46%
Jim Schutt372.73%17.69%
Xi Wang80.59%17.69%
Eric Dumazet20.15%17.69%
Total1353100.00%13100.00%


int ceph_pg_compare(const struct ceph_pg *lhs, const struct ceph_pg *rhs) { if (lhs->pool < rhs->pool) return -1; if (lhs->pool > rhs->pool) return 1; if (lhs->seed < rhs->seed) return -1; if (lhs->seed > rhs->seed) return 1; return 0; }

Contributors

PersonTokensPropCommitsCommitProp
Sage Weil5168.92%375.00%
Ilya Dryomov2331.08%125.00%
Total74100.00%4100.00%

/* * 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_mapping(struct ceph_pg_mapping *new, struct rb_root *root) { struct rb_node **p = &root->rb_node; struct rb_node *parent = NULL; struct ceph_pg_mapping *pg = NULL; int c; 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 = ceph_pg_compare(&new->pgid, &pg->pgid); if (c < 0) p = &(*p)->rb_left; else if (c > 0) p = &(*p)->rb_right; else return -EEXIST; } rb_link_node(&new->node, parent, p); rb_insert_color(&new->node, root); return 0; }

Contributors

PersonTokensPropCommitsCommitProp
Sage Weil16098.16%266.67%
Ilya Dryomov31.84%133.33%
Total163100.00%3100.00%


static struct ceph_pg_mapping *__lookup_pg_mapping(struct rb_root *root, struct ceph_pg pgid) { 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 = ceph_pg_compare(&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; }

Contributors

PersonTokensPropCommitsCommitProp
Sage Weil11597.46%480.00%
Ilya Dryomov32.54%120.00%
Total118100.00%5100.00%


static int __remove_pg_mapping(struct rb_root *root, struct ceph_pg pgid) { struct ceph_pg_mapping *pg = __lookup_pg_mapping(root, pgid); 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; }

Contributors

PersonTokensPropCommitsCommitProp
Sage Weil83100.00%2100.00%
Total83100.00%2100.00%

/* * rbtree of pg pool info */
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; } rb_link_node(&new->node, parent, p); rb_insert_color(&new->node, root); return 0; }

Contributors

PersonTokensPropCommitsCommitProp
Sage Weil136100.00%4100.00%
Total136100.00%4100.00%


static struct ceph_pg_pool_info *__lookup_pg_pool(struct rb_root *root, 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; }

Contributors

PersonTokensPropCommitsCommitProp
Sage Weil84100.00%2100.00%
Total84100.00%2100.00%


struct ceph_pg_pool_info *ceph_pg_pool_by_id(struct ceph_osdmap *map, u64 id) { return __lookup_pg_pool(&map->pg_pools, id); }

Contributors

PersonTokensPropCommitsCommitProp
Ilya Dryomov26100.00%1100.00%
Total26100.00%1100.00%


const char *ceph_pg_pool_name_by_id(struct ceph_osdmap *map, u64 id) { struct ceph_pg_pool_info *pi; if (id == CEPH_NOPOOL) return NULL; if (WARN_ON_ONCE(id > (u64) INT_MAX)) return NULL; pi = __lookup_pg_pool(&map->pg_pools, (int) id); return pi ? pi->name : NULL; }

Contributors

PersonTokensPropCommitsCommitProp
Alex Elder68100.00%1100.00%
Total68100.00%1100.00%

EXPORT_SYMBOL(ceph_pg_pool_name_by_id);
int ceph_pg_poolid_by_name(struct ceph_osdmap *map, const char *name) { struct rb_node *rbp; for (rbp = rb_first(&map->pg_pools); rbp; rbp = rb_next(rbp)) { struct ceph_pg_pool_info *pi = rb_entry(rbp, struct ceph_pg_pool_info, node); if (pi->name && strcmp(pi->name, name) == 0) return pi->id; } return -ENOENT; }

Contributors

PersonTokensPropCommitsCommitProp
Yehuda Sadeh Weinraub84100.00%1100.00%
Total84100.00%1100.00%

EXPORT_SYMBOL(ceph_pg_poolid_by_name);
static void __remove_pg_pool(struct rb_root *root, struct ceph_pg_pool_info *pi) { rb_erase(&pi->node, root); kfree(pi->name); kfree(pi); }

Contributors

PersonTokensPropCommitsCommitProp
Sage Weil38100.00%1100.00%
Total38100.00%1100.00%


static int decode_pool(void **p, void *end, struct ceph_pg_pool_info *pi) { u8 ev, cv; unsigned len, num; void *pool_end; ceph_decode_need(p, end, 2 + 4, bad); ev = ceph_decode_8(p); /* encoding version */ cv = ceph_decode_8(p); /* compat version */ if (ev < 5) { pr_warn("got v %d < 5 cv %d of ceph_pg_pool\n", ev, cv); return -EINVAL; } 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); ceph_decode_need(p, end, len, bad); pool_end = *p + len; pi->type = ceph_decode_8(p); pi->size = ceph_decode_8(p); pi->crush_ruleset = ceph_decode_8(p); pi->object_hash = ceph_decode_8(p); pi->pg_num = ceph_decode_32(p); pi->pgp_num = ceph_decode_32(p); *p += 4 + 4; /* skip lpg* */ *p += 4; /* skip last_change */ *p += 8 + 4; /* skip snap_seq, snap_epoch */ /* skip snaps */ num = ceph_decode_32(p); while (num--) { *p += 8; /* snapid key */ *p += 1 + 1; /* versions */ len = ceph_decode_32(p); *p += len; } /* 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; } if (ev >= 15) pi->last_force_request_resend = ceph_decode_32(p); else pi->last_force_request_resend = 0; /* ignore the rest */ *p = pool_end; calc_pg_masks(pi); return 0; bad: return -EINVAL; }

Contributors

PersonTokensPropCommitsCommitProp
Ilya Dryomov31351.31%333.33%
Sage Weil29448.20%444.44%
Joe Perches20.33%111.11%
Yehuda Sadeh Weinraub10.16%111.11%
Total610100.00%9100.00%


static int decode_pool_names(void **p, void *end, struct ceph_osdmap *map) { struct ceph_pg_pool_info *pi; u32 num, len; u64 pool; ceph_decode_32_safe(p, end, num, bad); dout(" %d pool names\n", num); while (num--) { ceph_decode_64_safe(p, end, pool, bad); 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); if (pi) { char *name = kstrndup(*p, len, GFP_NOFS); if (!name) return -ENOMEM; kfree(pi->name); pi->name = name; dout(" name is %s\n", pi->name); } *p += len; } return 0; bad: return -EINVAL; }

Contributors

PersonTokensPropCommitsCommitProp
Sage Weil15084.75%466.67%
Xi Wang2614.69%116.67%
Ilya Dryomov10.56%116.67%
Total177100.00%6100.00%

/* * 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; mutex_init(&map->crush_workspace_mutex); return map; }

Contributors

PersonTokensPropCommitsCommitProp
Ilya Dryomov71100.00%2100.00%
Total71100.00%2100.00%


void ceph_osdmap_destroy(struct ceph_osdmap *map) { dout("osdmap_destroy %p\n", map); if (map->crush) crush_destroy(map->crush); 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); kfree(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); rb_erase(&pg->node, &map->primary_temp); kfree(pg); } while (!RB_EMPTY_ROOT(&map->pg_pools)) { struct ceph_pg_pool_info *pi = rb_entry(rb_first(&map->pg_pools), 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); kfree(map->osd_primary_affinity); kfree(map->crush_workspace); kfree(map); }

Contributors

PersonTokensPropCommitsCommitProp
Sage Weil15269.72%240.00%
Ilya Dryomov6630.28%360.00%
Total218100.00%5100.00%

/* * 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) { u8 *state; u32 *weight; struct ceph_entity_addr *addr; int i; state = krealloc(map->osd_state, max*sizeof(*state), GFP_NOFS); if (!state) return -ENOMEM; map->osd_state = state; weight = krealloc(map->osd_weight, max*sizeof(*weight), GFP_NOFS); if (!weight) return -ENOMEM; map->osd_weight = weight; addr = krealloc(map->osd_addr, max*sizeof(*addr), GFP_NOFS); if (!addr) return -ENOMEM; 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 = krealloc(map->osd_primary_affinity, max*sizeof(*affinity), GFP_NOFS); if (!affinity) return -ENOMEM; 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; }

Contributors

PersonTokensPropCommitsCommitProp
Ilya Dryomov11944.91%228.57%
Sage Weil8933.58%457.14%
Li RongQing5721.51%114.29%
Total265100.00%7100.00%


static int osdmap_set_crush(struct ceph_osdmap *map, struct crush_map *crush) { void *workspace; size_t work_size; if (IS_ERR(crush)) return PTR_ERR(crush); work_size = crush_work_size(crush, CEPH_PG_MAX_SIZE); dout("%s work_size %zu bytes\n", __func__, work_size); workspace = kmalloc(work_size, GFP_NOIO); if (!workspace) { crush_destroy(crush); return -ENOMEM; } crush_init_workspace(crush, workspace); if (map->crush) crush_destroy(map->crush); kfree(map->crush_workspace); map->crush = crush; map->crush_workspace = workspace; return 0; }

Contributors

PersonTokensPropCommitsCommitProp
Ilya Dryomov121100.00%3100.00%
Total121100.00%3100.00%

#define OSDMAP_WRAPPER_COMPAT_VER 7 #define OSDMAP_CLIENT_DATA_COMPAT_VER 1 /* * 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. */
static int get_osdmap_client_data_v(void **p, void *end, const char *prefix, u8 *v) { 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 enconding */ struct_v = 0; } *v = struct_v; return 0; e_inval: return -EINVAL; }

Contributors

PersonTokensPropCommitsCommitProp
Ilya Dryomov20398.54%150.00%
Joe Perches31.46%150.00%
Total206100.00%2100.00%


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; pi->id = pool; ret = __insert_pg_pool(&map->pg_pools, pi); if (ret) { kfree(pi); return ret; } } ret = decode_pool(p, end, pi); if (ret) return ret; } return 0; e_inval: return -EINVAL; }

Contributors

PersonTokensPropCommitsCommitProp
Ilya Dryomov169100.00%1100.00%
Total169100.00%1100.00%


static int decode_pools(void **p, void *end, struct ceph_osdmap *map) { return __decode_pools(p, end, map, false); }

Contributors

PersonTokensPropCommitsCommitProp
Ilya Dryomov32100.00%1100.00%
Total32100.00%1100.00%


static int decode_new_pools(void **p, void *end, struct ceph_osdmap *map) { return __decode_pools(p, end, map, true); }

Contributors

PersonTokensPropCommitsCommitProp
Ilya Dryomov32100.00%1100.00%
Total32100.00%1100.00%


static int __decode_pg_temp(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 pgid; u32 len, i; int ret; ret = ceph_decode_pgid(p, end, &pgid); if (ret) return ret; ceph_decode_32_safe(p, end, len, e_inval); ret = __remove_pg_mapping(&map->pg_temp, pgid); BUG_ON(!incremental && ret != -ENOENT); if (!incremental || len > 0) { struct ceph_pg_mapping *pg; ceph_decode_need(p, end, len*sizeof(u32), e_inval); if (len > (UINT_MAX - sizeof(*pg)) / sizeof(u32)) return -EINVAL; pg = kzalloc(sizeof(*pg) + len*sizeof(u32), GFP_NOFS); if (!pg) return -ENOMEM; pg->pgid = pgid; pg->pg_temp.len = len; for (i = 0; i < len; i++) pg->pg_temp.osds[i] = ceph_decode_32(p); ret = __insert_pg_mapping(pg, &map->pg_temp); if (ret) { kfree(pg); return ret; } } } return 0; e_inval: return -EINVAL; }

Contributors

PersonTokensPropCommitsCommitProp
Ilya Dryomov269100.00%2100.00%
Total269100.00%2100.00%


static int decode_pg_temp(void **p, void *end, struct ceph_osdmap *map) { return __decode_pg_temp(p, end, map, false); }

Contributors

PersonTokensPropCommitsCommitProp
Ilya Dryomov32100.00%1100.00%
Total32100.00%1100.00%


static int decode_new_pg_temp(void **p, void *end, struct ceph_osdmap *map) { return __decode_pg_temp(p, end, map, true); }

Contributors

PersonTokensPropCommitsCommitProp
Ilya Dryomov32100.00%1100.00%
Total32100.00%1100.00%


static int __decode_primary_temp(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 pgid; u32 osd; int ret; ret = ceph_decode_pgid(p, end, &pgid); if (ret) return ret; ceph_decode_32_safe(p, end, osd, e_inval); ret = __remove_pg_mapping(&map->primary_temp, pgid); BUG_ON(!incremental && ret != -ENOENT); if (!incremental || osd != (u32)-1) { struct ceph_pg_mapping *pg; pg = kzalloc(sizeof(*pg), GFP_NOFS); if (!pg) return -ENOMEM; pg->pgid = pgid; pg->primary_temp.osd = osd; ret = __insert_pg_mapping(pg, &map->primary_temp); if (ret) { kfree(pg); return ret; } } } return 0; e_inval: return -EINVAL; }

Contributors

PersonTokensPropCommitsCommitProp
Ilya Dryomov198100.00%1100.00%
Total198100.00%1100.00%


static int decode_primary_temp(void **p, void *end, struct ceph_osdmap *map) { return __decode_primary_temp(p, end, map, false); }

Contributors

PersonTokensPropCommitsCommitProp
Ilya Dryomov32100.00%1100.00%
Total32100.00%1100.00%


static int decode_new_primary_temp(void **p, void *end, struct ceph_osdmap *map) { return __decode_primary_temp(p, end, map, true); }

Contributors

PersonTokensPropCommitsCommitProp
Ilya Dryomov32100.00%1100.00%
Total32100.00%1100.00%


u32 ceph_get_primary_affinity(struct ceph_osdmap *map, int osd) { BUG_ON(osd >= map->max_osd); if (!map->osd_primary_affinity) return CEPH_OSD_DEFAULT_PRIMARY_AFFINITY; return map->osd_primary_affinity[osd]; }

Contributors

PersonTokensPropCommitsCommitProp
Ilya Dryomov40100.00%1100.00%
Total40100.00%1100.00%


static int set_primary_affinity(struct ceph_osdmap *map, int osd, u32 aff) { BUG_ON(osd >= map->max_osd); if (!map->osd_primary_affinity) { int i; map->osd_primary_affinity = kmalloc(map->max_osd*sizeof(u32), 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; } map->osd_primary_affinity[osd] = aff; return 0; }

Contributors

PersonTokensPropCommitsCommitProp
Ilya Dryomov103100.00%1100.00%
Total103100.00%1100.00%


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) { kfree(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; }

Contributors

PersonTokensPropCommitsCommitProp
Ilya Dryomov139100.00%1100.00%
Total139100.00%1100.00%


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); ret = set_primary_affinity(map, osd, aff); if (ret) return ret; pr_info("osd%d primary-affinity 0x%x\n", osd, aff); } return 0; e_inval: return -EINVAL; }

Contributors

PersonTokensPropCommitsCommitProp
Ilya Dryomov107100.00%2100.00%
Total107100.00%2100.00%

/* * decode a full map. */
static int osdmap_decode(void **p, void *end, 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)); 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)); /* pools */ err = decode_pools(p, end, map); if (err) goto bad; /* pool_name */ err = decode_pool_names(p, end, map); if (err) goto bad; ceph_decode_32_safe(p, end, map->pool_max, e_inval); ceph_decode_32_safe(p, end, map->flags, e_inval); /* max_osd */ ceph_decode_32_safe(p, end, max, e_inval); /* (re)alloc osd arrays */ err = osdmap_set_max_osd(map, max); if (err) goto bad; /* 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)), e_inval); if (ceph_decode_32(p) != map->max_osd) goto e_inval; ceph_decode_copy(p, map->osd_state, map->max_osd); if (ceph_decode_32(p) != map->max_osd) goto e_inval; for (i = 0; i < map->max_osd; i++) map->osd_weight[i] = ceph_decode_32(p); if (ceph_decode_32(p) != map->max_osd) goto e_inval; 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]); /* 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; } /* primary_affinity */ if (struct_v >= 2) { err = decode_primary_affinity(p, end, map); if (err) goto bad; } else { /* XXX can this happen? */ kfree(map->osd_primary_affinity); map->osd_primary_affinity = NULL; } /* crush */ 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; /* ignore the rest */ *p = end; dout("full osdmap epoch %d max_osd %d\n", map->epoch, map->max_osd); return 0; e_inval: err = -EINVAL; bad: 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; }

Contributors

PersonTokensPropCommitsCommitProp
Sage Weil39559.58%1041.67%
Ilya Dryomov26840.42%1458.33%
Total663100.00%24100.00%

/* * Allocate and decode a full map. */
struct ceph_osdmap *ceph_osdmap_decode(void **p, void *end) { struct ceph_osdmap *map; int ret; map = ceph_osdmap_alloc(); if (!map) return ERR_PTR(-ENOMEM); ret = osdmap_decode(p, end, map); if (ret) { ceph_osdmap_destroy(map); return ERR_PTR(ret); } return map; }

Contributors

PersonTokensPropCommitsCommitProp
Ilya Dryomov6184.72%266.67%
Sage Weil1115.28%133.33%
Total72100.00%3100.00%

/* * 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, struct ceph_osdmap *map) { void *new_up_client; void *new_state; void *new_weight_end; u32 len; new_up_client = *p; ceph_decode_32_safe(p, end, len, e_inval); len *= sizeof(u32) + sizeof(struct ceph_entity_addr); ceph_decode_need(p, end, len, e_inval); *p += len; new_state = *p; ceph_decode_32_safe(p, end, len, e_inval); len *= 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); BUG_ON(osd >= map->max_osd); pr_info("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; u8 xorstate; int ret; osd = ceph_decode_32(p); xorstate = ceph_decode_8(p); if (xorstate == 0) xorstate = CEPH_OSD_UP; BUG_ON(osd >= map->max_osd); if ((map->osd_state[osd] & CEPH_OSD_UP) && (xorstate & CEPH_OSD_UP)) pr_info("osd%d down\n", osd); if ((map->osd_state[osd] & CEPH_OSD_EXISTS) && (xorstate & CEPH_OSD_EXISTS)) { pr_info("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); ceph_decode_copy(p, &addr, sizeof(addr)); ceph_decode_addr(&addr); BUG_ON(osd >= map->max_osd); pr_info("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; }

Contributors

PersonTokensPropCommitsCommitProp
Ilya Dryomov38872.66%450.00%
Sage Weil14627.34%450.00%
Total534100.00%8100.00%

/* * decode and apply an incremental map update. */
struct ceph_osdmap *osdmap_apply_incremental(void **p, void *end, struct ceph_osdmap *map) { struct ceph_fsid fsid; u32 epoch = 0; struct ceph_timespec modified; s32 len; u64 pool; __s64 new_pool_max; __s32 new_flags, max; void *start = *p; int err; u8 struct_v; dout("%s %p to %p len %d\n", __func__, *p, end, (int)(end - *p)); err = get_osdmap_client_data_v(p, end, "inc", &struct_v); if (err) goto 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); ceph_decode_copy(p, &modified, sizeof(modified)); new_pool_max = ceph_decode_64(p); new_flags = ceph_decode_32(p); /* full map? */ 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 ceph_osdmap_decode(p, min(*p+len, end)); } /* new crush? */ ceph_decode_32_safe(p, end, len, e_inval); if (len > 0) { err = osdmap_set_crush(map, crush_decode(*p, min(*p + len, end))); if (err) goto bad; *p += len; } /* new flags? */ if (new_flags >= 0) map->flags = new_flags; if (new_pool_max >= 0) map->pool_max = new_pool_max; /* new max? */ ceph_decode_32_safe(p, end, max, e_inval); if (max >= 0) { err = osdmap_set_max_osd(map, max); if (err) goto bad; } map->epoch++; map->modified = modified; /* new_pools */ err = decode_new_pools(p, end, map); if (err) 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, e_inval); while (len--) { struct ceph_pg_pool_info *pi; 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_client, new_state, new_weight */ err = decode_new_up_state_weight(p, end, 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_primary_affinity */ if (struct_v >= 2) { err = decode_new_primary_affinity(p, end, map); if (err) goto bad; } /* 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 (%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_PTR(err); }

Contributors

PersonTokensPropCommitsCommitProp
Ilya Dryomov41664.30%738.89%
Sage Weil23135.70%1161.11%
Total647100.00%18100.00%


void ceph_oloc_copy(struct ceph_object_locator *dest, const struct ceph_object_locator *src) { WARN_ON(!ceph_oloc_empty(dest)); WARN_ON(dest->pool_ns); /* empty() only covers ->pool */ dest->pool = src->pool; if (src->pool_ns) dest->pool_ns = ceph_get_string(src->pool_ns); }

Contributors

PersonTokensPropCommitsCommitProp
Yan, Zheng58100.00%1100.00%
Total58100.00%1100.00%

EXPORT_SYMBOL(ceph_oloc_copy);
void ceph_oloc_destroy(struct ceph_object_locator *oloc) { ceph_put_string(oloc->pool_ns); }

Contributors

PersonTokensPropCommitsCommitProp
Yan, Zheng17100.00%1100.00%
Total17100.00%1100.00%

EXPORT_SYMBOL(ceph_oloc_destroy);
void ceph_oid_copy(struct ceph_object_id *dest, const struct ceph_object_id *src) { WARN_ON(!ceph_oid_empty(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); } memcpy(dest->name, src->name, src->name_len + 1); dest->name_len = src->name_len; }

Contributors

PersonTokensPropCommitsCommitProp
Ilya Dryomov80100.00%1100.00%
Total80100.00%1100.00%

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; } /* * If oid doesn't fit into inline buffer, BUG. */ void ceph_oid_printf(struct ceph_object_id *oid, const char *fmt, ...) { va_list ap; va_start(ap, fmt); BUG_ON(oid_printf_vargs(oid, fmt, ap)); va_end(ap); } EXPORT_SYMBOL(ceph_oid_printf); 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; 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; } /* * If oid doesn't fit into inline buffer, allocate. */ int ceph_oid_aprintf(struct ceph_object_id *oid, gfp_t gfp, const char *fmt, ...) { va_list ap; int ret; va_start(ap, fmt); ret = oid_aprintf_vargs(oid, gfp, fmt, ap); va_end(ap); 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); }

Contributors

PersonTokensPropCommitsCommitProp
Ilya Dryomov27100.00%1100.00%
Total27100.00%1100.00%

EXPORT_SYMBOL(ceph_oid_destroy); /* * osds only */
static bool __osds_equal(const struct ceph_osds *lhs, const struct ceph_osds *rhs) { if (lhs->size == rhs->size && !memcmp(lhs->osds, rhs->osds, rhs->size * sizeof(rhs->osds[0]))) return true; return false; }

Contributors

PersonTokensPropCommitsCommitProp
Ilya Dryomov60100.00%1100.00%
Total60100.00%1100.00%

/* * 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; }

Contributors

PersonTokensPropCommitsCommitProp
Ilya Dryomov41100.00%1100.00%
Total41100.00%1100.00%


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; } return false; }

Contributors

PersonTokensPropCommitsCommitProp
Ilya Dryomov112100.00%1100.00%
Total112100.00%1100.00%


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; }

Contributors

PersonTokensPropCommitsCommitProp
Ilya Dryomov57100.00%1100.00%
Total57100.00%1100.00%


static bool 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; } return false; }

Contributors

PersonTokensPropCommitsCommitProp
Ilya Dryomov135100.00%1100.00%
Total135100.00%1100.00%


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, 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 || is_split(pgid, old_pg_num, new_pg_num) || old_sort_bitwise != new_sort_bitwise; }

Contributors

PersonTokensPropCommitsCommitProp
Ilya Dryomov97100.00%1100.00%
Total97100.00%1100.00%


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; }

Contributors

PersonTokensPropCommitsCommitProp
Ilya Dryomov53100.00%1100.00%
Total53100.00%1100.00%


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) */ }

Contributors

PersonTokensPropCommitsCommitProp
Ilya Dryomov91100.00%1100.00%
Total91100.00%1100.00%


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; }

Contributors

PersonTokensPropCommitsCommitProp
Ilya Dryomov50100.00%1100.00%
Total50100.00%1100.00%

/* * 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. */
int ceph_calc_file_object_mapping(struct ceph_file_layout *layout, u64 off, u64 len, u64 *ono, u64 *oxoff, u64 *oxlen) { u32 osize = layout->object_size; u32 su = layout->stripe_unit; u32 sc = layout->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; /* * 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); dout(" obj extent %llu~%llu\n", *oxoff, *oxlen); return 0; invalid: dout(" invalid layout\n"); *ono = 0; *oxoff = 0; *oxlen = 0; return -EINVAL; }

Contributors

PersonTokensPropCommitsCommitProp
Sage Weil26894.37%337.50%
Noah Watkins82.82%225.00%
Alex Elder41.41%112.50%
Yan, Zheng31.06%112.50%
Eric Dumazet10.35%112.50%
Total284100.00%8100.00%

EXPORT_SYMBOL(ceph_calc_file_object_mapping); /* * 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. */
int ceph_object_locator_to_pg(struct ceph_osdmap *osdmap, struct ceph_object_id *oid, 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; 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); if (!buf) return -ENOMEM; } 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); } return 0; }

Contributors

PersonTokensPropCommitsCommitProp
Yan, Zheng17163.33%18.33%
Sage Weil5721.11%758.33%
Ilya Dryomov3412.59%325.00%
Alex Elder82.96%18.33%
Total270100.00%12100.00%

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); }

Contributors

PersonTokensPropCommitsCommitProp
Ilya Dryomov49100.00%3100.00%
Total49100.00%3100.00%

/* * 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 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 == ... */ return ceph_stable_mod(raw_pgid->seed, pi->pgp_num, pi->pgp_num_mask) + (unsigned)raw_pgid->pool; } }

Contributors

PersonTokensPropCommitsCommitProp
Ilya Dryomov80100.00%2100.00%
Total80100.00%2100.00%


static int do_crush(struct ceph_osdmap *map, int ruleno, int x, int *result, int result_max, const __u32 *weight, int weight_max) { int r; BUG_ON(result_max > CEPH_PG_MAX_SIZE); mutex_lock(&map->crush_workspace_mutex); r = crush_do_rule(map->crush, ruleno, x, result, result_max, weight, weight_max, map->crush_workspace); mutex_unlock(&map->crush_workspace_mutex); return r; }

Contributors

PersonTokensPropCommitsCommitProp
Ilya Dryomov86100.00%3100.00%
Total86100.00%3100.00%

/* * Calculate raw set (CRUSH output) for given PG. The result may * contain 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); 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; }

Contributors

PersonTokensPropCommitsCommitProp
Ilya Dryomov223100.00%3100.00%
Total223100.00%3100.00%

/* * 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. */
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]; } } }

Contributors

PersonTokensPropCommitsCommitProp
Ilya Dryomov190100.00%2100.00%
Total190100.00%2100.00%


static void apply_primary_affinity(struct ceph_osdmap *osdmap, struct ceph_pg_pool_info *pi, u32 pps, struct ceph_osds *up) { int i; int pos = -1; /* * Do we have any non-default primary_affinity values for these * osds? */ if (!osdmap->osd_primary_affinity) return; 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; } }

Contributors

PersonTokensPropCommitsCommitProp
Ilya Dryomov257100.00%3100.00%
Total257100.00%3100.00%

/* * 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 *raw_pgid, struct ceph_osds *temp) { struct ceph_pg pgid; struct ceph_pg_mapping *pg; int i; raw_pg_to_pg(pi, raw_pgid, &pgid); 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; }

Contributors

PersonTokensPropCommitsCommitProp
Ilya Dryomov222100.00%3100.00%
Total222100.00%3100.00%

/* * 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, const struct ceph_pg *raw_pgid, struct ceph_osds *up, struct ceph_osds *acting) { struct ceph_pg_pool_info *pi; u32 pps; pi = ceph_pg_pool_by_id(osdmap, raw_pgid->pool); if (!pi) { ceph_osds_init(up); ceph_osds_init(acting); goto out; } pg_to_raw_osds(osdmap, pi, raw_pgid, up, &pps); raw_to_up_osds(osdmap, pi, up); apply_primary_affinity(osdmap, pi, pps, up); get_temp_osds(osdmap, pi, raw_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; } out: WARN_ON(!osds_valid(up) || !osds_valid(acting)); }

Contributors

PersonTokensPropCommitsCommitProp
Ilya Dryomov15583.33%450.00%
Sage Weil3116.67%450.00%
Total186100.00%8100.00%

/* * 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_osds up, acting; ceph_pg_to_up_acting_osds(osdmap, raw_pgid, &up, &acting); return acting.primary; }

Contributors

PersonTokensPropCommitsCommitProp
Sage Weil2357.50%350.00%
Ilya Dryomov1742.50%350.00%
Total40100.00%6100.00%

EXPORT_SYMBOL(ceph_pg_to_acting_primary);

Overall Contributors

PersonTokensPropCommitsCommitProp
Ilya Dryomov611754.61%5152.58%
Sage Weil445639.78%2828.87%
Yan, Zheng2592.31%22.06%
Yehuda Sadeh Weinraub1121.00%33.09%
Alex Elder850.76%33.09%
Li RongQing570.51%11.03%
Jim Schutt370.33%11.03%
Xi Wang340.30%22.06%
Cong Ding230.21%11.03%
Noah Watkins80.07%22.06%
Tejun Heo50.04%11.03%
Joe Perches50.04%11.03%
Eric Dumazet40.04%11.03%
Total11202100.00%97100.00%
Directory: net/ceph
Information contained on this website is for historical information purposes only and does not indicate or represent copyright ownership.
Created with cregit.