Loading...
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 | // SPDX-License-Identifier: GPL-2.0-only /****************************************************************************** ******************************************************************************* ** ** Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved. ** Copyright (C) 2004-2005 Red Hat, Inc. All rights reserved. ** ** ******************************************************************************* ******************************************************************************/ #include "dlm_internal.h" #include "lockspace.h" #include "member.h" #include "lowcomms.h" #include "rcom.h" #include "config.h" #include "memory.h" #include "recover.h" #include "util.h" #include "lock.h" #include "dir.h" /* * We use the upper 16 bits of the hash value to select the directory node. * Low bits are used for distribution of rsb's among hash buckets on each node. * * To give the exact range wanted (0 to num_nodes-1), we apply a modulus of * num_nodes to the hash value. This value in the desired range is used as an * offset into the sorted list of nodeid's to give the particular nodeid. */ int dlm_hash2nodeid(struct dlm_ls *ls, uint32_t hash) { uint32_t node; if (ls->ls_num_nodes == 1) return dlm_our_nodeid(); else { node = (hash >> 16) % ls->ls_total_weight; return ls->ls_node_array[node]; } } int dlm_dir_nodeid(struct dlm_rsb *r) { return r->res_dir_nodeid; } void dlm_recover_dir_nodeid(struct dlm_ls *ls) { struct dlm_rsb *r; down_read(&ls->ls_root_sem); list_for_each_entry(r, &ls->ls_root_list, res_root_list) { r->res_dir_nodeid = dlm_hash2nodeid(ls, r->res_hash); } up_read(&ls->ls_root_sem); } int dlm_recover_directory(struct dlm_ls *ls) { struct dlm_member *memb; char *b, *last_name = NULL; int error = -ENOMEM, last_len, nodeid, result; uint16_t namelen; unsigned int count = 0, count_match = 0, count_bad = 0, count_add = 0; log_rinfo(ls, "dlm_recover_directory"); if (dlm_no_directory(ls)) goto out_status; last_name = kmalloc(DLM_RESNAME_MAXLEN, GFP_NOFS); if (!last_name) goto out; list_for_each_entry(memb, &ls->ls_nodes, list) { if (memb->nodeid == dlm_our_nodeid()) continue; memset(last_name, 0, DLM_RESNAME_MAXLEN); last_len = 0; for (;;) { int left; error = dlm_recovery_stopped(ls); if (error) { error = -EINTR; goto out_free; } error = dlm_rcom_names(ls, memb->nodeid, last_name, last_len); if (error) goto out_free; cond_resched(); /* * pick namelen/name pairs out of received buffer */ b = ls->ls_recover_buf->rc_buf; left = ls->ls_recover_buf->rc_header.h_length; left -= sizeof(struct dlm_rcom); for (;;) { __be16 v; error = -EINVAL; if (left < sizeof(__be16)) goto out_free; memcpy(&v, b, sizeof(__be16)); namelen = be16_to_cpu(v); b += sizeof(__be16); left -= sizeof(__be16); /* namelen of 0xFFFFF marks end of names for this node; namelen of 0 marks end of the buffer */ if (namelen == 0xFFFF) goto done; if (!namelen) break; if (namelen > left) goto out_free; if (namelen > DLM_RESNAME_MAXLEN) goto out_free; error = dlm_master_lookup(ls, memb->nodeid, b, namelen, DLM_LU_RECOVER_DIR, &nodeid, &result); if (error) { log_error(ls, "recover_dir lookup %d", error); goto out_free; } /* The name was found in rsbtbl, but the * master nodeid is different from * memb->nodeid which says it is the master. * This should not happen. */ if (result == DLM_LU_MATCH && nodeid != memb->nodeid) { count_bad++; log_error(ls, "recover_dir lookup %d " "nodeid %d memb %d bad %u", result, nodeid, memb->nodeid, count_bad); print_hex_dump_bytes("dlm_recover_dir ", DUMP_PREFIX_NONE, b, namelen); } /* The name was found in rsbtbl, and the * master nodeid matches memb->nodeid. */ if (result == DLM_LU_MATCH && nodeid == memb->nodeid) { count_match++; } /* The name was not found in rsbtbl and was * added with memb->nodeid as the master. */ if (result == DLM_LU_ADD) { count_add++; } last_len = namelen; memcpy(last_name, b, namelen); b += namelen; left -= namelen; count++; } } done: ; } out_status: error = 0; dlm_set_recover_status(ls, DLM_RS_DIR); log_rinfo(ls, "dlm_recover_directory %u in %u new", count, count_add); out_free: kfree(last_name); out: return error; } static struct dlm_rsb *find_rsb_root(struct dlm_ls *ls, char *name, int len) { struct dlm_rsb *r; uint32_t hash, bucket; int rv; hash = jhash(name, len, 0); bucket = hash & (ls->ls_rsbtbl_size - 1); spin_lock(&ls->ls_rsbtbl[bucket].lock); rv = dlm_search_rsb_tree(&ls->ls_rsbtbl[bucket].keep, name, len, &r); if (rv) rv = dlm_search_rsb_tree(&ls->ls_rsbtbl[bucket].toss, name, len, &r); spin_unlock(&ls->ls_rsbtbl[bucket].lock); if (!rv) return r; down_read(&ls->ls_root_sem); list_for_each_entry(r, &ls->ls_root_list, res_root_list) { if (len == r->res_length && !memcmp(name, r->res_name, len)) { up_read(&ls->ls_root_sem); log_debug(ls, "find_rsb_root revert to root_list %s", r->res_name); return r; } } up_read(&ls->ls_root_sem); return NULL; } /* Find the rsb where we left off (or start again), then send rsb names for rsb's we're master of and whose directory node matches the requesting node. inbuf is the rsb name last sent, inlen is the name's length */ void dlm_copy_master_names(struct dlm_ls *ls, char *inbuf, int inlen, char *outbuf, int outlen, int nodeid) { struct list_head *list; struct dlm_rsb *r; int offset = 0, dir_nodeid; __be16 be_namelen; down_read(&ls->ls_root_sem); if (inlen > 1) { r = find_rsb_root(ls, inbuf, inlen); if (!r) { inbuf[inlen - 1] = '\0'; log_error(ls, "copy_master_names from %d start %d %s", nodeid, inlen, inbuf); goto out; } list = r->res_root_list.next; } else { list = ls->ls_root_list.next; } for (offset = 0; list != &ls->ls_root_list; list = list->next) { r = list_entry(list, struct dlm_rsb, res_root_list); if (r->res_nodeid) continue; dir_nodeid = dlm_dir_nodeid(r); if (dir_nodeid != nodeid) continue; /* * The block ends when we can't fit the following in the * remaining buffer space: * namelen (uint16_t) + * name (r->res_length) + * end-of-block record 0x0000 (uint16_t) */ if (offset + sizeof(uint16_t)*2 + r->res_length > outlen) { /* Write end-of-block record */ be_namelen = cpu_to_be16(0); memcpy(outbuf + offset, &be_namelen, sizeof(__be16)); offset += sizeof(__be16); ls->ls_recover_dir_sent_msg++; goto out; } be_namelen = cpu_to_be16(r->res_length); memcpy(outbuf + offset, &be_namelen, sizeof(__be16)); offset += sizeof(__be16); memcpy(outbuf + offset, r->res_name, r->res_length); offset += r->res_length; ls->ls_recover_dir_sent_res++; } /* * If we've reached the end of the list (and there's room) write a * terminating record. */ if ((list == &ls->ls_root_list) && (offset + sizeof(uint16_t) <= outlen)) { be_namelen = cpu_to_be16(0xFFFF); memcpy(outbuf + offset, &be_namelen, sizeof(__be16)); offset += sizeof(__be16); ls->ls_recover_dir_sent_msg++; } out: up_read(&ls->ls_root_sem); } |