X-Git-Url: https://git.whamcloud.com/?p=fs%2Flustre-release.git;a=blobdiff_plain;f=lustre%2Flmv%2Flmv_obd.c;h=f9ae0250d9d3def42cdf0760af70f75dceed6eb2;hp=8e9d844c58baf364149783230d52900f0428d457;hb=5a6aa0e6d1583cc0d4c82ae8c95fb7b9856d6284;hpb=47c31bb3174a4f0ba81e088bed0d3dd5cb1223f4 diff --git a/lustre/lmv/lmv_obd.c b/lustre/lmv/lmv_obd.c index 8e9d844..f9ae025 100644 --- a/lustre/lmv/lmv_obd.c +++ b/lustre/lmv/lmv_obd.c @@ -15,11 +15,7 @@ * * You should have received a copy of the GNU General Public License * version 2 along with this program; If not, see - * http://www.sun.com/software/products/lustre/docs/GPLv2.pdf - * - * Please contact Sun Microsystems, Inc., 4150 Network Circle, Santa Clara, - * CA 95054 USA or visit www.sun.com if you need additional information or - * have any questions. + * http://www.gnu.org/licenses/gpl-2.0.html * * GPL HEADER END */ @@ -27,7 +23,7 @@ * Copyright (c) 2004, 2010, Oracle and/or its affiliates. All rights reserved. * Use is subject to license terms. * - * Copyright (c) 2011, 2013, Intel Corporation. + * Copyright (c) 2011, 2016, Intel Corporation. */ /* * This file is part of Lustre, http://www.lustre.org/ @@ -38,6 +34,10 @@ #include #include #include +#include +#ifdef HAVE_UIDGID_HEADER +# include +#endif #include #include #include @@ -53,70 +53,12 @@ #include #include #include -#include -#include #include #include +#include #include "lmv_internal.h" -/* This hash is only for testing purpose */ -static inline unsigned int -lmv_hash_all_chars(unsigned int count, const char *name, int namelen) -{ - unsigned int c = 0; - const unsigned char *p = (const unsigned char *)name; - - while (--namelen >= 0) - c += p[namelen]; - - c = c % count; - - return c; -} - -static inline unsigned int -lmv_hash_fnv1a(unsigned int count, const char *name, int namelen) -{ - __u64 hash; - - hash = lustre_hash_fnv_1a_64(name, namelen); - - hash = hash % count; - - return hash; -} - -int lmv_name_to_stripe_index(__u32 lmv_hash_type, unsigned int stripe_count, - const char *name, int namelen) -{ - int idx; - __u32 hash_type = lmv_hash_type & LMV_HASH_TYPE_MASK; - - LASSERT(namelen > 0); - if (stripe_count <= 1) - return 0; - - /* for migrating object, always start from 0 stripe */ - if (lmv_hash_type & LMV_HASH_FLAG_MIGRATION) - return 0; - - switch (hash_type) { - case LMV_HASH_TYPE_ALL_CHARS: - idx = lmv_hash_all_chars(stripe_count, name, namelen); - break; - case LMV_HASH_TYPE_FNV_1A_64: - idx = lmv_hash_fnv1a(stripe_count, name, namelen); - break; - default: - idx = -EBADFD; - break; - } - - CDEBUG(D_INFO, "name %.*s hash_type %d idx %d\n", namelen, name, - hash_type, idx); - - return idx; -} +static int lmv_check_connect(struct obd_device *obd); static void lmv_activate_target(struct lmv_obd *lmv, struct lmv_tgt_desc *tgt, @@ -127,6 +69,8 @@ static void lmv_activate_target(struct lmv_obd *lmv, tgt->ltd_active = activate; lmv->desc.ld_active_tgt_count += (activate ? 1 : -1); + + tgt->ltd_exp->exp_obd->obd_inactive = !activate; } /** @@ -155,7 +99,7 @@ static int lmv_set_mdc_active(struct lmv_obd *lmv, if (tgt == NULL || tgt->ltd_exp == NULL) continue; - CDEBUG(D_INFO, "Target idx %d is %s conn "LPX64"\n", i, + CDEBUG(D_INFO, "Target idx %d is %s conn %#llx\n", i, tgt->ltd_uuid.uuid, tgt->ltd_exp->exp_handle.h_cookie); if (obd_uuid_equals(uuid, &tgt->ltd_uuid)) @@ -237,14 +181,7 @@ static int lmv_notify(struct obd_device *obd, struct obd_device *watched, */ obd->obd_self_export->exp_connect_data = *conn_data; } -#if 0 - else if (ev == OBD_NOTIFY_DISCON) { - /* - * For disconnect event, flush fld cache for failout MDS case. - */ - fld_client_flush(&lmv->lmv_fld); - } -#endif + /* * Pass the notification up the chain. */ @@ -254,50 +191,33 @@ static int lmv_notify(struct obd_device *obd, struct obd_device *watched, RETURN(rc); } -/** - * This is fake connect function. Its purpose is to initialize lmv and say - * caller that everything is okay. Real connection will be performed later. - */ static int lmv_connect(const struct lu_env *env, - struct obd_export **exp, struct obd_device *obd, - struct obd_uuid *cluuid, struct obd_connect_data *data, - void *localdata) -{ - struct lmv_obd *lmv = &obd->u.lmv; - struct lustre_handle conn = { 0 }; - int rc = 0; - ENTRY; - - /* - * We don't want to actually do the underlying connections more than - * once, so keep track. - */ - lmv->refcount++; - if (lmv->refcount > 1) { - *exp = NULL; - RETURN(0); - } - - rc = class_connect(&conn, obd, cluuid); - if (rc) { - CERROR("class_connection() returned %d\n", rc); - RETURN(rc); - } + struct obd_export **pexp, struct obd_device *obd, + struct obd_uuid *cluuid, struct obd_connect_data *data, + void *localdata) +{ + struct lmv_obd *lmv = &obd->u.lmv; + struct lustre_handle conn = { 0 }; + struct obd_export *exp; + int rc; + ENTRY; - *exp = class_conn2export(&conn); - class_export_get(*exp); + rc = class_connect(&conn, obd, cluuid); + if (rc) { + CERROR("class_connection() returned %d\n", rc); + RETURN(rc); + } - lmv->exp = *exp; - lmv->connected = 0; - lmv->cluuid = *cluuid; + exp = class_conn2export(&conn); - if (data) - lmv->conn_data = *data; + lmv->connected = 0; + lmv->cluuid = *cluuid; + lmv->conn_data = *data; if (lmv->targets_proc_entry == NULL) { - lmv->targets_proc_entry = lprocfs_seq_register("target_obds", - obd->obd_proc_entry, - NULL, NULL); + lmv->targets_proc_entry = lprocfs_register("target_obds", + obd->obd_proc_entry, + NULL, NULL); if (IS_ERR(lmv->targets_proc_entry)) { CERROR("%s: cannot register " "/proc/fs/lustre/%s/%s/target_obds\n", @@ -307,45 +227,25 @@ static int lmv_connect(const struct lu_env *env, } } - /* - * All real clients should perform actual connection right away, because - * it is possible, that LMV will not have opportunity to connect targets - * and MDC stuff will be called directly, for instance while reading - * ../mdc/../kbytesfree procfs file, etc. - */ - if (data != NULL && (data->ocd_connect_flags & OBD_CONNECT_REAL)) - rc = lmv_check_connect(obd); - - if (rc && lmv->targets_proc_entry != NULL) - lprocfs_remove(&lmv->targets_proc_entry); - RETURN(rc); -} - -static void lmv_set_timeouts(struct obd_device *obd) -{ - struct lmv_obd *lmv; - __u32 i; + rc = lmv_check_connect(obd); + if (rc != 0) + GOTO(out_proc, rc); - lmv = &obd->u.lmv; - if (lmv->server_timeout == 0) - return; + *pexp = exp; - if (lmv->connected == 0) - return; + RETURN(rc); - for (i = 0; i < lmv->desc.ld_tgt_count; i++) { - struct lmv_tgt_desc *tgt = lmv->tgts[i]; +out_proc: + if (lmv->targets_proc_entry != NULL) + lprocfs_remove(&lmv->targets_proc_entry); - if (tgt == NULL || tgt->ltd_exp == NULL || !tgt->ltd_active) - continue; + class_disconnect(exp); - obd_set_info_async(NULL, tgt->ltd_exp, sizeof(KEY_INTERMDS), - KEY_INTERMDS, 0, NULL, NULL); - } + return rc; } -static int lmv_init_ea_size(struct obd_export *exp, int easize, - int def_easize, int cookiesize, int def_cookiesize) +static int lmv_init_ea_size(struct obd_export *exp, __u32 easize, + __u32 def_easize) { struct obd_device *obd = exp->exp_obd; struct lmv_obd *lmv = &obd->u.lmv; @@ -362,14 +262,7 @@ static int lmv_init_ea_size(struct obd_export *exp, int easize, lmv->max_def_easize = def_easize; change = 1; } - if (lmv->max_cookiesize < cookiesize) { - lmv->max_cookiesize = cookiesize; - change = 1; - } - if (lmv->max_def_cookiesize < def_cookiesize) { - lmv->max_def_cookiesize = def_cookiesize; - change = 1; - } + if (change == 0) RETURN(0); @@ -384,8 +277,7 @@ static int lmv_init_ea_size(struct obd_export *exp, int easize, continue; } - rc = md_init_ea_size(tgt->ltd_exp, easize, def_easize, - cookiesize, def_cookiesize); + rc = md_init_ea_size(tgt->ltd_exp, easize, def_easize); if (rc) { CERROR("%s: obd_init_ea_size() failed on MDT target %d:" " rc = %d\n", obd->obd_name, i, rc); @@ -470,8 +362,7 @@ int lmv_connect_mdc(struct obd_device *obd, struct lmv_tgt_desc *tgt) tgt->ltd_exp = mdc_exp; lmv->desc.ld_active_tgt_count++; - md_init_ea_size(tgt->ltd_exp, lmv->max_easize, lmv->max_def_easize, - lmv->max_cookiesize, lmv->max_def_cookiesize); + md_init_ea_size(tgt->ltd_exp, lmv->max_easize, lmv->max_def_easize); CDEBUG(D_CONFIG, "Connected to %s(%s) successfully (%d)\n", mdc_obd->obd_name, mdc_obd->obd_uuid.uuid, @@ -510,6 +401,7 @@ static void lmv_del_target(struct lmv_obd *lmv, int index) static int lmv_add_target(struct obd_device *obd, struct obd_uuid *uuidp, __u32 index, int gen) { + struct obd_device *mdc_obd; struct lmv_obd *lmv = &obd->u.lmv; struct lmv_tgt_desc *tgt; int orig_tgt_count = 0; @@ -517,28 +409,21 @@ static int lmv_add_target(struct obd_device *obd, struct obd_uuid *uuidp, ENTRY; CDEBUG(D_CONFIG, "Target uuid: %s. index %d\n", uuidp->uuid, index); - - lmv_init_lock(lmv); - - if (lmv->desc.ld_tgt_count == 0) { - struct obd_device *mdc_obd; - - mdc_obd = class_find_client_obd(uuidp, LUSTRE_MDC_NAME, - &obd->obd_uuid); - if (!mdc_obd) { - lmv_init_unlock(lmv); - CERROR("%s: Target %s not attached: rc = %d\n", - obd->obd_name, uuidp->uuid, -EINVAL); - RETURN(-EINVAL); - } + mdc_obd = class_find_client_obd(uuidp, LUSTRE_MDC_NAME, + &obd->obd_uuid); + if (!mdc_obd) { + CERROR("%s: Target %s not attached: rc = %d\n", + obd->obd_name, uuidp->uuid, -EINVAL); + RETURN(-EINVAL); } + mutex_lock(&lmv->lmv_init_mutex); if ((index < lmv->tgts_size) && (lmv->tgts[index] != NULL)) { tgt = lmv->tgts[index]; CERROR("%s: UUID %s already assigned at LOV target index %d:" " rc = %d\n", obd->obd_name, obd_uuid2str(&tgt->ltd_uuid), index, -EEXIST); - lmv_init_unlock(lmv); + mutex_unlock(&lmv->lmv_init_mutex); RETURN(-EEXIST); } @@ -552,7 +437,7 @@ static int lmv_add_target(struct obd_device *obd, struct obd_uuid *uuidp, newsize = newsize << 1; OBD_ALLOC(newtgts, sizeof(*newtgts) * newsize); if (newtgts == NULL) { - lmv_init_unlock(lmv); + mutex_unlock(&lmv->lmv_init_mutex); RETURN(-ENOMEM); } @@ -575,7 +460,7 @@ static int lmv_add_target(struct obd_device *obd, struct obd_uuid *uuidp, OBD_ALLOC_PTR(tgt); if (!tgt) { - lmv_init_unlock(lmv); + mutex_unlock(&lmv->lmv_init_mutex); RETURN(-ENOMEM); } @@ -589,26 +474,31 @@ static int lmv_add_target(struct obd_device *obd, struct obd_uuid *uuidp, lmv->desc.ld_tgt_count = index + 1; } - if (lmv->connected) { - rc = lmv_connect_mdc(obd, tgt); - if (rc != 0) { - spin_lock(&lmv->lmv_lock); - if (lmv->desc.ld_tgt_count == index + 1) - lmv->desc.ld_tgt_count = orig_tgt_count; - memset(tgt, 0, sizeof(*tgt)); - spin_unlock(&lmv->lmv_lock); - } else { - int easize = sizeof(struct lmv_stripe_md) + - lmv->desc.ld_tgt_count * sizeof(struct lu_fid); - lmv_init_ea_size(obd->obd_self_export, easize, 0, 0, 0); - } + if (lmv->connected == 0) { + /* lmv_check_connect() will connect this target. */ + mutex_unlock(&lmv->lmv_init_mutex); + RETURN(0); + } + + /* Otherwise let's connect it ourselves */ + mutex_unlock(&lmv->lmv_init_mutex); + rc = lmv_connect_mdc(obd, tgt); + if (rc != 0) { + spin_lock(&lmv->lmv_lock); + if (lmv->desc.ld_tgt_count == index + 1) + lmv->desc.ld_tgt_count = orig_tgt_count; + memset(tgt, 0, sizeof(*tgt)); + spin_unlock(&lmv->lmv_lock); + } else { + int easize = sizeof(struct lmv_stripe_md) + + lmv->desc.ld_tgt_count * sizeof(struct lu_fid); + lmv_init_ea_size(obd->obd_self_export, easize, 0); } - lmv_init_unlock(lmv); RETURN(rc); } -int lmv_check_connect(struct obd_device *obd) +static int lmv_check_connect(struct obd_device *obd) { struct lmv_obd *lmv = &obd->u.lmv; struct lmv_tgt_desc *tgt; @@ -620,14 +510,14 @@ int lmv_check_connect(struct obd_device *obd) if (lmv->connected) RETURN(0); - lmv_init_lock(lmv); + mutex_lock(&lmv->lmv_init_mutex); if (lmv->connected) { - lmv_init_unlock(lmv); + mutex_unlock(&lmv->lmv_init_mutex); RETURN(0); } if (lmv->desc.ld_tgt_count == 0) { - lmv_init_unlock(lmv); + mutex_unlock(&lmv->lmv_init_mutex); CERROR("%s: no targets configured.\n", obd->obd_name); RETURN(-EINVAL); } @@ -635,7 +525,7 @@ int lmv_check_connect(struct obd_device *obd) LASSERT(lmv->tgts != NULL); if (lmv->tgts[0] == NULL) { - lmv_init_unlock(lmv); + mutex_unlock(&lmv->lmv_init_mutex); CERROR("%s: no target configured for index 0.\n", obd->obd_name); RETURN(-EINVAL); @@ -653,12 +543,10 @@ int lmv_check_connect(struct obd_device *obd) GOTO(out_disc, rc); } - lmv_set_timeouts(obd); - class_export_put(lmv->exp); lmv->connected = 1; easize = lmv_mds_md_size(lmv->desc.ld_tgt_count, LMV_MAGIC); - lmv_init_ea_size(obd->obd_self_export, easize, 0, 0, 0); - lmv_init_unlock(lmv); + lmv_init_ea_size(obd->obd_self_export, easize, 0); + mutex_unlock(&lmv->lmv_init_mutex); RETURN(0); out_disc: @@ -678,9 +566,10 @@ int lmv_check_connect(struct obd_device *obd) } } } - class_disconnect(lmv->exp); - lmv_init_unlock(lmv); - RETURN(rc); + + mutex_unlock(&lmv->lmv_init_mutex); + + RETURN(rc); } static int lmv_disconnect_mdc(struct obd_device *obd, struct lmv_tgt_desc *tgt) @@ -699,11 +588,11 @@ static int lmv_disconnect_mdc(struct obd_device *obd, struct lmv_tgt_desc *tgt) mdc_obd->obd_force = obd->obd_force; mdc_obd->obd_fail = obd->obd_fail; mdc_obd->obd_no_recov = obd->obd_no_recov; - } - if (lmv->targets_proc_entry != NULL) - lprocfs_remove_proc_entry(mdc_obd->obd_name, - lmv->targets_proc_entry); + if (lmv->targets_proc_entry != NULL) + lprocfs_remove_proc_entry(mdc_obd->obd_name, + lmv->targets_proc_entry); + } rc = obd_fid_fini(tgt->ltd_exp->exp_obd); if (rc) @@ -738,13 +627,6 @@ static int lmv_disconnect(struct obd_export *exp) if (!lmv->tgts) goto out_local; - /* - * Only disconnect the underlying layers on the final disconnect. - */ - lmv->refcount--; - if (lmv->refcount != 0) - goto out_local; - for (i = 0; i < lmv->desc.ld_tgt_count; i++) { if (lmv->tgts[i] == NULL || lmv->tgts[i]->ltd_exp == NULL) continue; @@ -766,26 +648,31 @@ out_local: if (!lmv->connected) class_export_put(exp); rc = class_disconnect(exp); - if (lmv->refcount == 0) - lmv->connected = 0; - RETURN(rc); + lmv->connected = 0; + + RETURN(rc); } -static int lmv_fid2path(struct obd_export *exp, int len, void *karg, void *uarg) +static int lmv_fid2path(struct obd_export *exp, int len, void *karg, + void __user *uarg) { struct obd_device *obddev = class_exp2obd(exp); struct lmv_obd *lmv = &obddev->u.lmv; struct getinfo_fid2path *gf; struct lmv_tgt_desc *tgt; struct getinfo_fid2path *remote_gf = NULL; + struct lu_fid root_fid; int remote_gf_size = 0; int rc; - gf = (struct getinfo_fid2path *)karg; + gf = karg; tgt = lmv_find_target(lmv, &gf->gf_fid); if (IS_ERR(tgt)) RETURN(PTR_ERR(tgt)); + root_fid = *gf->gf_u.gf_root_fid; + LASSERT(fid_is_sane(&root_fid)); + repeat_fid2path: rc = obd_iocontrol(OBD_IOC_FID2PATH, tgt->ltd_exp, len, gf, uarg); if (rc != 0 && rc != -EREMOTE) @@ -798,23 +685,24 @@ repeat_fid2path: char *ptr; ori_gf = (struct getinfo_fid2path *)karg; - if (strlen(ori_gf->gf_path) + - strlen(gf->gf_path) > ori_gf->gf_pathlen) + if (strlen(ori_gf->gf_u.gf_path) + + strlen(gf->gf_u.gf_path) > ori_gf->gf_pathlen) GOTO(out_fid2path, rc = -EOVERFLOW); - ptr = ori_gf->gf_path; + ptr = ori_gf->gf_u.gf_path; - memmove(ptr + strlen(gf->gf_path) + 1, ptr, - strlen(ori_gf->gf_path)); + memmove(ptr + strlen(gf->gf_u.gf_path) + 1, ptr, + strlen(ori_gf->gf_u.gf_path)); - strncpy(ptr, gf->gf_path, strlen(gf->gf_path)); - ptr += strlen(gf->gf_path); + strncpy(ptr, gf->gf_u.gf_path, + strlen(gf->gf_u.gf_path)); + ptr += strlen(gf->gf_u.gf_path); *ptr = '/'; } - CDEBUG(D_INFO, "%s: get path %s "DFID" rec: "LPU64" ln: %u\n", + CDEBUG(D_INFO, "%s: get path %s "DFID" rec: %llu ln: %u\n", tgt->ltd_exp->exp_obd->obd_name, - gf->gf_path, PFID(&gf->gf_fid), gf->gf_recno, + gf->gf_u.gf_path, PFID(&gf->gf_fid), gf->gf_recno, gf->gf_linkno); if (rc == 0) @@ -843,7 +731,8 @@ repeat_fid2path: remote_gf->gf_fid = gf->gf_fid; remote_gf->gf_recno = -1; remote_gf->gf_linkno = -1; - memset(remote_gf->gf_path, 0, remote_gf->gf_pathlen); + memset(remote_gf->gf_u.gf_path, 0, remote_gf->gf_pathlen); + *remote_gf->gf_u.gf_root_fid = root_fid; gf = remote_gf; goto repeat_fid2path; @@ -864,13 +753,15 @@ static int lmv_hsm_req_count(struct lmv_obd *lmv, /* count how many requests must be sent to the given target */ for (i = 0; i < hur->hur_request.hr_itemcount; i++) { curr_tgt = lmv_find_target(lmv, &hur->hur_user_item[i].hui_fid); + if (IS_ERR(curr_tgt)) + RETURN(PTR_ERR(curr_tgt)); if (obd_uuid_equals(&curr_tgt->ltd_uuid, &tgt_mds->ltd_uuid)) nr++; } return nr; } -static void lmv_hsm_req_build(struct lmv_obd *lmv, +static int lmv_hsm_req_build(struct lmv_obd *lmv, struct hsm_user_request *hur_in, const struct lmv_tgt_desc *tgt_mds, struct hsm_user_request *hur_out) @@ -884,6 +775,8 @@ static void lmv_hsm_req_build(struct lmv_obd *lmv, for (i = 0; i < hur_in->hur_request.hr_itemcount; i++) { curr_tgt = lmv_find_target(lmv, &hur_in->hur_user_item[i].hui_fid); + if (IS_ERR(curr_tgt)) + RETURN(PTR_ERR(curr_tgt)); if (obd_uuid_equals(&curr_tgt->ltd_uuid, &tgt_mds->ltd_uuid)) { hur_out->hur_user_item[nr_out] = hur_in->hur_user_item[i]; @@ -893,14 +786,16 @@ static void lmv_hsm_req_build(struct lmv_obd *lmv, hur_out->hur_request.hr_itemcount = nr_out; memcpy(hur_data(hur_out), hur_data(hur_in), hur_in->hur_request.hr_data_len); + + RETURN(0); } static int lmv_hsm_ct_unregister(struct lmv_obd *lmv, unsigned int cmd, int len, - struct lustre_kernelcomm *lk, void *uarg) + struct lustre_kernelcomm *lk, + void __user *uarg) { - __u32 i; - int rc; - struct kkuc_ct_data *kcd = NULL; + __u32 i; + int rc; ENTRY; /* unregister request (call from llapi_hsm_copytool_fini) */ @@ -918,21 +813,19 @@ static int lmv_hsm_ct_unregister(struct lmv_obd *lmv, unsigned int cmd, int len, * Unreached coordinators will get EPIPE on next requests * and will unregister automatically. */ - rc = libcfs_kkuc_group_rem(lk->lk_uid, lk->lk_group, (void **)&kcd); - if (kcd != NULL) - OBD_FREE_PTR(kcd); + rc = libcfs_kkuc_group_rem(lk->lk_uid, lk->lk_group); RETURN(rc); } static int lmv_hsm_ct_register(struct lmv_obd *lmv, unsigned int cmd, int len, - struct lustre_kernelcomm *lk, void *uarg) + struct lustre_kernelcomm *lk, __user void *uarg) { struct file *filp; __u32 i, j; int err, rc; bool any_set = false; - struct kkuc_ct_data *kcd; + struct kkuc_ct_data kcd = { 0 }; ENTRY; /* All or nothing: try to register to all MDS. @@ -949,7 +842,7 @@ static int lmv_hsm_ct_register(struct lmv_obd *lmv, unsigned int cmd, int len, /* permanent error */ CERROR("%s: iocontrol MDC %s on MDT" " idx %d cmd %x: err = %d\n", - class_exp2obd(lmv->exp)->obd_name, + lmv2obd_dev(lmv)->obd_name, tgt->ltd_uuid.uuid, i, cmd, err); rc = err; lk->lk_flags |= LK_FLG_STOP; @@ -980,21 +873,14 @@ static int lmv_hsm_ct_register(struct lmv_obd *lmv, unsigned int cmd, int len, if (filp == NULL) RETURN(-EBADF); - OBD_ALLOC_PTR(kcd); - if (kcd == NULL) { - fput(filp); - RETURN(-ENOMEM); - } - kcd->kcd_magic = KKUC_CT_DATA_MAGIC; - kcd->kcd_uuid = lmv->cluuid; - kcd->kcd_archive = lk->lk_data; + kcd.kcd_magic = KKUC_CT_DATA_MAGIC; + kcd.kcd_uuid = lmv->cluuid; + kcd.kcd_archive = lk->lk_data; - rc = libcfs_kkuc_group_add(filp, lk->lk_uid, lk->lk_group, kcd); - if (rc != 0) { - if (filp != NULL) - fput(filp); - OBD_FREE_PTR(kcd); - } + rc = libcfs_kkuc_group_add(filp, lk->lk_uid, lk->lk_group, + &kcd, sizeof(kcd)); + if (rc != 0) + fput(filp); RETURN(rc); } @@ -1003,7 +889,7 @@ static int lmv_hsm_ct_register(struct lmv_obd *lmv, unsigned int cmd, int len, static int lmv_iocontrol(unsigned int cmd, struct obd_export *exp, - int len, void *karg, void *uarg) + int len, void *karg, void __user *uarg) { struct obd_device *obddev = class_exp2obd(exp); struct lmv_obd *lmv = &obddev->u.lmv; @@ -1180,8 +1066,8 @@ static int lmv_iocontrol(unsigned int cmd, struct obd_export *exp, } else { /* split fid list to their respective MDS */ for (i = 0; i < count; i++) { - unsigned int nr, reqlen; - int rc1; + int nr, rc1; + size_t reqlen; struct hsm_user_request *req; tgt = lmv->tgts[i]; @@ -1189,6 +1075,8 @@ static int lmv_iocontrol(unsigned int cmd, struct obd_export *exp, continue; nr = lmv_hsm_req_count(lmv, hur, tgt); + if (nr < 0) + RETURN(nr); if (nr == 0) /* nothing for this MDS */ continue; @@ -1199,11 +1087,12 @@ static int lmv_iocontrol(unsigned int cmd, struct obd_export *exp, OBD_ALLOC_LARGE(req, reqlen); if (req == NULL) RETURN(-ENOMEM); - - lmv_hsm_req_build(lmv, hur, tgt, req); - + rc1 = lmv_hsm_req_build(lmv, hur, tgt, req); + if (rc1 < 0) + GOTO(hsm_req_err, rc1); rc1 = obd_iocontrol(cmd, tgt->ltd_exp, reqlen, req, uarg); +hsm_req_err: if (rc1 != 0 && rc == 0) rc = rc1; OBD_FREE_LARGE(req, reqlen); @@ -1254,9 +1143,7 @@ static int lmv_iocontrol(unsigned int cmd, struct obd_export *exp, mdc_obd = class_exp2obd(tgt->ltd_exp); mdc_obd->obd_force = obddev->obd_force; err = obd_iocontrol(cmd, tgt->ltd_exp, len, karg, uarg); - if (err == -ENODATA && cmd == OBD_IOC_POLL_QUOTACHECK) { - RETURN(err); - } else if (err) { + if (err) { if (tgt->ltd_active) { CERROR("error: iocontrol MDC %s on MDT" " idx %d cmd %x: err = %d\n", @@ -1273,59 +1160,15 @@ static int lmv_iocontrol(unsigned int cmd, struct obd_export *exp, RETURN(rc); } -#if 0 -static int lmv_all_chars_policy(int count, const char *name, - int len) -{ - unsigned int c = 0; - - while (len > 0) - c += name[--len]; - c = c % count; - return c; -} - -static int lmv_nid_policy(struct lmv_obd *lmv) -{ - struct obd_import *imp; - __u32 id; - - /* - * XXX: To get nid we assume that underlying obd device is mdc. - */ - imp = class_exp2cliimp(lmv->tgts[0].ltd_exp); - id = imp->imp_connection->c_self ^ (imp->imp_connection->c_self >> 32); - return id % lmv->desc.ld_tgt_count; -} - -static int lmv_choose_mds(struct lmv_obd *lmv, struct md_op_data *op_data, - placement_policy_t placement) -{ - switch (placement) { - case PLACEMENT_CHAR_POLICY: - return lmv_all_chars_policy(lmv->desc.ld_tgt_count, - op_data->op_name, - op_data->op_namelen); - case PLACEMENT_NID_POLICY: - return lmv_nid_policy(lmv); - - default: - break; - } - - CERROR("Unsupported placement policy %x\n", placement); - return -EINVAL; -} -#endif - /** * This is _inode_ placement policy function (not name). */ static int lmv_placement_policy(struct obd_device *obd, - struct md_op_data *op_data, - mdsno_t *mds) + struct md_op_data *op_data, u32 *mds) { - struct lmv_obd *lmv = &obd->u.lmv; + struct lmv_obd *lmv = &obd->u.lmv; + struct lmv_user_md *lum; + ENTRY; LASSERT(mds != NULL); @@ -1335,34 +1178,29 @@ static int lmv_placement_policy(struct obd_device *obd, RETURN(0); } - /** - * If stripe_offset is provided during setdirstripe - * (setdirstripe -i xx), xx MDS will be choosen. - */ - if (op_data->op_cli_flags & CLI_SET_MEA && op_data->op_data != NULL) { - struct lmv_user_md *lum; - - lum = op_data->op_data; - - if (le32_to_cpu(lum->lum_stripe_offset) != (__u32)-1) { - *mds = le32_to_cpu(lum->lum_stripe_offset); - } else { - /* -1 means default, which will be in the same MDT with - * the stripe */ - *mds = op_data->op_mds; - lum->lum_stripe_offset = cpu_to_le32(op_data->op_mds); - } + lum = op_data->op_data; + /* Choose MDS by + * 1. See if the stripe offset is specified by lum. + * 2. Then check if there is default stripe offset. + * 3. Finally choose MDS by name hash if the parent + * is striped directory. (see lmv_locate_mds()). */ + if (op_data->op_cli_flags & CLI_SET_MEA && lum != NULL && + le32_to_cpu(lum->lum_stripe_offset) != (__u32)-1) { + *mds = le32_to_cpu(lum->lum_stripe_offset); + } else if (op_data->op_default_stripe_offset != (__u32)-1) { + *mds = op_data->op_default_stripe_offset; + op_data->op_mds = *mds; + /* Correct the stripe offset in lum */ + if (lum != NULL) + lum->lum_stripe_offset = cpu_to_le32(*mds); } else { - /* Allocate new fid on target according to operation type and - * parent home mds. */ *mds = op_data->op_mds; } RETURN(0); } -int __lmv_fid_alloc(struct lmv_obd *lmv, struct lu_fid *fid, - mdsno_t mds) +int __lmv_fid_alloc(struct lmv_obd *lmv, struct lu_fid *fid, u32 mds) { struct lmv_tgt_desc *tgt; int rc; @@ -1401,7 +1239,7 @@ int lmv_fid_alloc(const struct lu_env *env, struct obd_export *exp, { struct obd_device *obd = class_exp2obd(exp); struct lmv_obd *lmv = &obd->u.lmv; - mdsno_t mds = 0; + u32 mds = 0; int rc; ENTRY; @@ -1443,25 +1281,23 @@ static int lmv_setup(struct obd_device *obd, struct lustre_cfg *lcfg) RETURN(-EINVAL); } - OBD_ALLOC(lmv->tgts, sizeof(*lmv->tgts) * 32); + lmv->tgts_size = 32U; + OBD_ALLOC(lmv->tgts, sizeof(*lmv->tgts) * lmv->tgts_size); if (lmv->tgts == NULL) RETURN(-ENOMEM); - lmv->tgts_size = 32; obd_str2uuid(&lmv->desc.ld_uuid, desc->ld_uuid.uuid); lmv->desc.ld_tgt_count = 0; lmv->desc.ld_active_tgt_count = 0; - lmv->max_cookiesize = 0; lmv->max_def_easize = 0; lmv->max_easize = 0; - lmv->lmv_placement = PLACEMENT_CHAR_POLICY; spin_lock_init(&lmv->lmv_lock); - mutex_init(&lmv->init_mutex); + mutex_init(&lmv->lmv_init_mutex); -#ifdef LPROCFS +#ifdef CONFIG_PROC_FS obd->obd_vars = lprocfs_lmv_obd_vars; - lprocfs_seq_obd_setup(obd); + lprocfs_obd_setup(obd); lprocfs_alloc_md_stats(obd, 0); rc = lprocfs_seq_create(obd->obd_proc_entry, "target_obd", 0444, &lmv_proc_target_fops, obd); @@ -1501,7 +1337,7 @@ static int lmv_cleanup(struct obd_device *obd) RETURN(0); } -static int lmv_process_config(struct obd_device *obd, obd_count len, void *buf) +static int lmv_process_config(struct obd_device *obd, size_t len, void *buf) { struct lustre_cfg *lcfg = buf; struct obd_uuid obd_uuid; @@ -1543,10 +1379,6 @@ static int lmv_statfs(const struct lu_env *env, struct obd_export *exp, __u32 i; ENTRY; - rc = lmv_check_connect(obd); - if (rc) - RETURN(rc); - OBD_ALLOC(temp, sizeof(*temp)); if (temp == NULL) RETURN(-ENOMEM); @@ -1588,27 +1420,22 @@ out_free_temp: return rc; } -static int lmv_getstatus(struct obd_export *exp, - struct lu_fid *fid, - struct obd_capa **pc) +static int lmv_get_root(struct obd_export *exp, const char *fileset, + struct lu_fid *fid) { struct obd_device *obd = exp->exp_obd; struct lmv_obd *lmv = &obd->u.lmv; int rc; ENTRY; - rc = lmv_check_connect(obd); - if (rc) - RETURN(rc); - - rc = md_getstatus(lmv->tgts[0]->ltd_exp, fid, pc); + rc = md_get_root(lmv->tgts[0]->ltd_exp, fileset, fid); RETURN(rc); } static int lmv_getxattr(struct obd_export *exp, const struct lu_fid *fid, - struct obd_capa *oc, obd_valid valid, const char *name, - const char *input, int input_size, int output_size, - int flags, struct ptlrpc_request **request) + u64 valid, const char *name, + const char *input, int input_size, int output_size, + int flags, struct ptlrpc_request **request) { struct obd_device *obd = exp->exp_obd; struct lmv_obd *lmv = &obd->u.lmv; @@ -1616,25 +1443,21 @@ static int lmv_getxattr(struct obd_export *exp, const struct lu_fid *fid, int rc; ENTRY; - rc = lmv_check_connect(obd); - if (rc) - RETURN(rc); - tgt = lmv_find_target(lmv, fid); if (IS_ERR(tgt)) RETURN(PTR_ERR(tgt)); - rc = md_getxattr(tgt->ltd_exp, fid, oc, valid, name, input, - input_size, output_size, flags, request); + rc = md_getxattr(tgt->ltd_exp, fid, valid, name, input, + input_size, output_size, flags, request); - RETURN(rc); + RETURN(rc); } static int lmv_setxattr(struct obd_export *exp, const struct lu_fid *fid, - struct obd_capa *oc, obd_valid valid, const char *name, - const char *input, int input_size, int output_size, - int flags, __u32 suppgid, - struct ptlrpc_request **request) + u64 valid, const char *name, + const char *input, int input_size, int output_size, + int flags, __u32 suppgid, + struct ptlrpc_request **request) { struct obd_device *obd = exp->exp_obd; struct lmv_obd *lmv = &obd->u.lmv; @@ -1642,19 +1465,15 @@ static int lmv_setxattr(struct obd_export *exp, const struct lu_fid *fid, int rc; ENTRY; - rc = lmv_check_connect(obd); - if (rc) - RETURN(rc); - tgt = lmv_find_target(lmv, fid); if (IS_ERR(tgt)) RETURN(PTR_ERR(tgt)); - rc = md_setxattr(tgt->ltd_exp, fid, oc, valid, name, input, - input_size, output_size, flags, suppgid, - request); + rc = md_setxattr(tgt->ltd_exp, fid, valid, name, input, + input_size, output_size, flags, suppgid, + request); - RETURN(rc); + RETURN(rc); } static int lmv_getattr(struct obd_export *exp, struct md_op_data *op_data, @@ -1666,10 +1485,6 @@ static int lmv_getattr(struct obd_export *exp, struct md_op_data *op_data, int rc; ENTRY; - rc = lmv_check_connect(obd); - if (rc) - RETURN(rc); - tgt = lmv_find_target(lmv, &op_data->op_fid1); if (IS_ERR(tgt)) RETURN(PTR_ERR(tgt)); @@ -1689,13 +1504,8 @@ static int lmv_null_inode(struct obd_export *exp, const struct lu_fid *fid) struct obd_device *obd = exp->exp_obd; struct lmv_obd *lmv = &obd->u.lmv; __u32 i; - int rc; ENTRY; - rc = lmv_check_connect(obd); - if (rc) - RETURN(rc); - CDEBUG(D_INODE, "CBDATA for "DFID"\n", PFID(fid)); /* @@ -1712,50 +1522,6 @@ static int lmv_null_inode(struct obd_export *exp, const struct lu_fid *fid) RETURN(0); } -static int lmv_find_cbdata(struct obd_export *exp, const struct lu_fid *fid, - ldlm_iterator_t it, void *data) -{ - struct obd_device *obd = exp->exp_obd; - struct lmv_obd *lmv = &obd->u.lmv; - int i; - int tgt; - int rc; - ENTRY; - - rc = lmv_check_connect(obd); - if (rc) - RETURN(rc); - - CDEBUG(D_INODE, "CBDATA for "DFID"\n", PFID(fid)); - - /* - * With DNE every object can have two locks in different namespaces: - * lookup lock in space of MDT storing direntry and update/open lock in - * space of MDT storing inode. Try the MDT that the FID maps to first, - * since this can be easily found, and only try others if that fails. - */ - for (i = 0, tgt = lmv_find_target_index(lmv, fid); - i < lmv->desc.ld_tgt_count; - i++, tgt = (tgt + 1) % lmv->desc.ld_tgt_count) { - if (tgt < 0) { - CDEBUG(D_HA, "%s: "DFID" is inaccessible: rc = %d\n", - obd->obd_name, PFID(fid), tgt); - tgt = 0; - } - - if (lmv->tgts[tgt] == NULL || - lmv->tgts[tgt]->ltd_exp == NULL) - continue; - - rc = md_find_cbdata(lmv->tgts[tgt]->ltd_exp, fid, it, data); - if (rc) - RETURN(rc); - } - - RETURN(rc); -} - - static int lmv_close(struct obd_export *exp, struct md_op_data *op_data, struct md_open_data *mod, struct ptlrpc_request **request) { @@ -1765,10 +1531,6 @@ static int lmv_close(struct obd_export *exp, struct md_op_data *op_data, int rc; ENTRY; - rc = lmv_check_connect(obd); - if (rc) - RETURN(rc); - tgt = lmv_find_target(lmv, &op_data->op_fid1); if (IS_ERR(tgt)) RETURN(PTR_ERR(tgt)); @@ -1787,19 +1549,30 @@ static int lmv_close(struct obd_export *exp, struct md_op_data *op_data, struct lmv_tgt_desc * lmv_locate_target_for_name(struct lmv_obd *lmv, struct lmv_stripe_md *lsm, const char *name, int namelen, struct lu_fid *fid, - mdsno_t *mds) + u32 *mds) { struct lmv_tgt_desc *tgt; const struct lmv_oinfo *oinfo; - oinfo = lsm_name_to_stripe_info(lsm, name, namelen); - if (IS_ERR(oinfo)) - RETURN(ERR_CAST(oinfo)); - *fid = oinfo->lmo_fid; - *mds = oinfo->lmo_mds; - tgt = lmv_get_target(lmv, *mds, NULL); + if (OBD_FAIL_CHECK(OBD_FAIL_LFSCK_BAD_NAME_HASH)) { + if (cfs_fail_val >= lsm->lsm_md_stripe_count) + RETURN(ERR_PTR(-EBADF)); + oinfo = &lsm->lsm_md_oinfo[cfs_fail_val]; + } else { + oinfo = lsm_name_to_stripe_info(lsm, name, namelen); + if (IS_ERR(oinfo)) + RETURN(ERR_CAST(oinfo)); + } + + if (fid != NULL) + *fid = oinfo->lmo_fid; + if (mds != NULL) + *mds = oinfo->lmo_mds; - CDEBUG(D_INFO, "locate on mds %u "DFID"\n", *mds, PFID(fid)); + tgt = lmv_get_target(lmv, oinfo->lmo_mds, NULL); + + CDEBUG(D_INFO, "locate on mds %u "DFID"\n", oinfo->lmo_mds, + PFID(&oinfo->lmo_fid)); return tgt; } @@ -1831,26 +1604,27 @@ lmv_locate_mds(struct lmv_obd *lmv, struct md_op_data *op_data, * index if the file under striped dir is being restored, see * ct_restore(). */ if (op_data->op_bias & MDS_CREATE_VOLATILE && - (int)op_data->op_mds != -1 && lsm != NULL) { + (int)op_data->op_mds != -1) { int i; tgt = lmv_get_target(lmv, op_data->op_mds, NULL); if (IS_ERR(tgt)) return tgt; - /* refill the right parent fid */ - for (i = 0; i < lsm->lsm_md_stripe_count; i++) { - struct lmv_oinfo *oinfo; + if (lsm != NULL) { + /* refill the right parent fid */ + for (i = 0; i < lsm->lsm_md_stripe_count; i++) { + struct lmv_oinfo *oinfo; - oinfo = &lsm->lsm_md_oinfo[i]; - if (oinfo->lmo_mds == op_data->op_mds) { - *fid = oinfo->lmo_fid; - break; + oinfo = &lsm->lsm_md_oinfo[i]; + if (oinfo->lmo_mds == op_data->op_mds) { + *fid = oinfo->lmo_fid; + break; + } } - } - /* Hmm, can not find the stripe by mdt_index(op_mds) */ - if (i == lsm->lsm_md_stripe_count) - tgt = ERR_PTR(-EINVAL); + if (i == lsm->lsm_md_stripe_count) + *fid = lsm->lsm_md_oinfo[0].lmo_fid; + } return tgt; } @@ -1870,9 +1644,9 @@ lmv_locate_mds(struct lmv_obd *lmv, struct md_op_data *op_data, } int lmv_create(struct obd_export *exp, struct md_op_data *op_data, - const void *data, int datalen, int mode, __u32 uid, - __u32 gid, cfs_cap_t cap_effective, __u64 rdev, - struct ptlrpc_request **request) + const void *data, size_t datalen, umode_t mode, uid_t uid, + gid_t gid, cfs_cap_t cap_effective, __u64 rdev, + struct ptlrpc_request **request) { struct obd_device *obd = exp->exp_obd; struct lmv_obd *lmv = &obd->u.lmv; @@ -1880,10 +1654,6 @@ int lmv_create(struct obd_export *exp, struct md_op_data *op_data, int rc; ENTRY; - rc = lmv_check_connect(obd); - if (rc) - RETURN(rc); - if (!lmv->desc.ld_active_tgt_count) RETURN(-EIO); @@ -1892,20 +1662,23 @@ int lmv_create(struct obd_export *exp, struct md_op_data *op_data, RETURN(PTR_ERR(tgt)); CDEBUG(D_INODE, "CREATE name '%.*s' on "DFID" -> mds #%x\n", - op_data->op_namelen, op_data->op_name, PFID(&op_data->op_fid1), - op_data->op_mds); + (int)op_data->op_namelen, op_data->op_name, + PFID(&op_data->op_fid1), op_data->op_mds); rc = lmv_fid_alloc(NULL, exp, &op_data->op_fid2, op_data); if (rc) RETURN(rc); + if (exp_connect_flags(exp) & OBD_CONNECT_DIR_STRIPE) { + /* Send the create request to the MDT where the object + * will be located */ + tgt = lmv_find_target(lmv, &op_data->op_fid2); + if (IS_ERR(tgt)) + RETURN(PTR_ERR(tgt)); - /* Send the create request to the MDT where the object - * will be located */ - tgt = lmv_find_target(lmv, &op_data->op_fid2); - if (IS_ERR(tgt)) - RETURN(PTR_ERR(tgt)); - - op_data->op_mds = tgt->ltd_idx; + op_data->op_mds = tgt->ltd_idx; + } else { + CDEBUG(D_CONFIG, "Server doesn't support striped dirs\n"); + } CDEBUG(D_INODE, "CREATE obj "DFID" -> mds #%x\n", PFID(&op_data->op_fid2), op_data->op_mds); @@ -1921,32 +1694,9 @@ int lmv_create(struct obd_export *exp, struct md_op_data *op_data, RETURN(rc); } -static int lmv_done_writing(struct obd_export *exp, - struct md_op_data *op_data, - struct md_open_data *mod) -{ - struct obd_device *obd = exp->exp_obd; - struct lmv_obd *lmv = &obd->u.lmv; - struct lmv_tgt_desc *tgt; - int rc; - ENTRY; - - rc = lmv_check_connect(obd); - if (rc) - RETURN(rc); - - tgt = lmv_find_target(lmv, &op_data->op_fid1); - if (IS_ERR(tgt)) - RETURN(PTR_ERR(tgt)); - - rc = md_done_writing(tgt->ltd_exp, op_data, mod); - RETURN(rc); -} - static int lmv_enqueue(struct obd_export *exp, struct ldlm_enqueue_info *einfo, - const union ldlm_policy_data *policy, - struct lookup_intent *it, struct md_op_data *op_data, + const union ldlm_policy_data *policy, struct md_op_data *op_data, struct lustre_handle *lockh, __u64 extra_lock_flags) { struct obd_device *obd = exp->exp_obd; @@ -1955,21 +1705,16 @@ lmv_enqueue(struct obd_export *exp, struct ldlm_enqueue_info *einfo, int rc; ENTRY; - rc = lmv_check_connect(obd); - if (rc) - RETURN(rc); - - CDEBUG(D_INODE, "ENQUEUE '%s' on "DFID"\n", - LL_IT2STR(it), PFID(&op_data->op_fid1)); + CDEBUG(D_INODE, "ENQUEUE on "DFID"\n", PFID(&op_data->op_fid1)); tgt = lmv_locate_mds(lmv, op_data, &op_data->op_fid1); if (IS_ERR(tgt)) RETURN(PTR_ERR(tgt)); - CDEBUG(D_INODE, "ENQUEUE '%s' on "DFID" -> mds #%d\n", - LL_IT2STR(it), PFID(&op_data->op_fid1), tgt->ltd_idx); + CDEBUG(D_INODE, "ENQUEUE on "DFID" -> mds #%u\n", + PFID(&op_data->op_fid1), tgt->ltd_idx); - rc = md_enqueue(tgt->ltd_exp, einfo, policy, it, op_data, lockh, + rc = md_enqueue(tgt->ltd_exp, einfo, policy, op_data, lockh, extra_lock_flags); RETURN(rc); @@ -1987,17 +1732,13 @@ lmv_getattr_name(struct obd_export *exp,struct md_op_data *op_data, int rc; ENTRY; - rc = lmv_check_connect(obd); - if (rc) - RETURN(rc); - tgt = lmv_locate_mds(lmv, op_data, &op_data->op_fid1); if (IS_ERR(tgt)) RETURN(PTR_ERR(tgt)); CDEBUG(D_INODE, "GETATTR_NAME for %*s on "DFID" -> mds #%d\n", - op_data->op_namelen, op_data->op_name, PFID(&op_data->op_fid1), - tgt->ltd_idx); + (int)op_data->op_namelen, op_data->op_name, + PFID(&op_data->op_fid1), tgt->ltd_idx); rc = md_getattr_name(tgt->ltd_exp, op_data, preq); if (rc != 0) @@ -2038,14 +1779,13 @@ lmv_getattr_name(struct obd_export *exp,struct md_op_data *op_data, NULL) static int lmv_early_cancel(struct obd_export *exp, struct lmv_tgt_desc *tgt, - struct md_op_data *op_data, - int op_tgt, ldlm_mode_t mode, int bits, int flag) -{ - struct lu_fid *fid = md_op_data_fid(op_data, flag); - struct obd_device *obd = exp->exp_obd; - struct lmv_obd *lmv = &obd->u.lmv; - ldlm_policy_data_t policy = {{ 0 }}; - int rc = 0; + struct md_op_data *op_data, __u32 op_tgt, + enum ldlm_mode mode, int bits, int flag) +{ + struct lu_fid *fid = md_op_data_fid(op_data, flag); + struct lmv_obd *lmv = &exp->exp_obd->u.lmv; + union ldlm_policy_data policy = { { 0 } }; + int rc = 0; ENTRY; if (!fid_is_sane(fid)) @@ -2086,14 +1826,10 @@ static int lmv_link(struct obd_export *exp, struct md_op_data *op_data, int rc; ENTRY; - rc = lmv_check_connect(obd); - if (rc) - RETURN(rc); - LASSERT(op_data->op_namelen != 0); CDEBUG(D_INODE, "LINK "DFID":%*s to "DFID"\n", - PFID(&op_data->op_fid2), op_data->op_namelen, + PFID(&op_data->op_fid2), (int)op_data->op_namelen, op_data->op_name, PFID(&op_data->op_fid1)); op_data->op_fsuid = from_kuid(&init_user_ns, current_fsuid()); @@ -2130,37 +1866,56 @@ static int lmv_link(struct obd_export *exp, struct md_op_data *op_data, } static int lmv_rename(struct obd_export *exp, struct md_op_data *op_data, - const char *old, int oldlen, const char *new, int newlen, - struct ptlrpc_request **request) + const char *old, size_t oldlen, + const char *new, size_t newlen, + struct ptlrpc_request **request) { struct obd_device *obd = exp->exp_obd; struct lmv_obd *lmv = &obd->u.lmv; struct lmv_tgt_desc *src_tgt; + struct lmv_tgt_desc *tgt_tgt; + struct obd_export *target_exp; + struct mdt_body *body; int rc; ENTRY; LASSERT(oldlen != 0); CDEBUG(D_INODE, "RENAME %.*s in "DFID":%d to %.*s in "DFID":%d\n", - oldlen, old, PFID(&op_data->op_fid1), + (int)oldlen, old, PFID(&op_data->op_fid1), op_data->op_mea1 ? op_data->op_mea1->lsm_md_stripe_count : 0, - newlen, new, PFID(&op_data->op_fid2), + (int)newlen, new, PFID(&op_data->op_fid2), op_data->op_mea2 ? op_data->op_mea2->lsm_md_stripe_count : 0); - rc = lmv_check_connect(obd); - if (rc) - RETURN(rc); - op_data->op_fsuid = from_kuid(&init_user_ns, current_fsuid()); op_data->op_fsgid = from_kgid(&init_user_ns, current_fsgid()); op_data->op_cap = cfs_curproc_cap_pack(); if (op_data->op_cli_flags & CLI_MIGRATE) { LASSERTF(fid_is_sane(&op_data->op_fid3), "invalid FID "DFID"\n", PFID(&op_data->op_fid3)); + + if (op_data->op_mea1 != NULL) { + struct lmv_stripe_md *lsm = op_data->op_mea1; + struct lmv_tgt_desc *tmp; + + /* Fix the parent fid for striped dir */ + tmp = lmv_locate_target_for_name(lmv, lsm, old, + oldlen, + &op_data->op_fid1, + NULL); + if (IS_ERR(tmp)) + RETURN(PTR_ERR(tmp)); + } + rc = lmv_fid_alloc(NULL, exp, &op_data->op_fid2, op_data); - if (rc) + if (rc != 0) RETURN(rc); - src_tgt = lmv_locate_mds(lmv, op_data, &op_data->op_fid3); + + src_tgt = lmv_find_target(lmv, &op_data->op_fid3); + if (IS_ERR(src_tgt)) + RETURN(PTR_ERR(src_tgt)); + + target_exp = src_tgt->ltd_exp; } else { if (op_data->op_mea1 != NULL) { struct lmv_stripe_md *lsm = op_data->op_mea1; @@ -2169,29 +1924,29 @@ static int lmv_rename(struct obd_export *exp, struct md_op_data *op_data, oldlen, &op_data->op_fid1, &op_data->op_mds); - if (IS_ERR(src_tgt)) - RETURN(PTR_ERR(src_tgt)); } else { src_tgt = lmv_find_target(lmv, &op_data->op_fid1); - if (IS_ERR(src_tgt)) - RETURN(PTR_ERR(src_tgt)); - - op_data->op_mds = src_tgt->ltd_idx; } + if (IS_ERR(src_tgt)) + RETURN(PTR_ERR(src_tgt)); + - if (op_data->op_mea2) { + if (op_data->op_mea2 != NULL) { struct lmv_stripe_md *lsm = op_data->op_mea2; - const struct lmv_oinfo *oinfo; - oinfo = lsm_name_to_stripe_info(lsm, new, newlen); - if (IS_ERR(oinfo)) - RETURN(PTR_ERR(oinfo)); + tgt_tgt = lmv_locate_target_for_name(lmv, lsm, new, + newlen, + &op_data->op_fid2, + &op_data->op_mds); + } else { + tgt_tgt = lmv_find_target(lmv, &op_data->op_fid2); - op_data->op_fid2 = oinfo->lmo_fid; } + if (IS_ERR(tgt_tgt)) + RETURN(PTR_ERR(tgt_tgt)); + + target_exp = tgt_tgt->ltd_exp; } - if (IS_ERR(src_tgt)) - RETURN(PTR_ERR(src_tgt)); /* * LOOKUP lock on src child (fid3) should also be cancelled for @@ -2233,27 +1988,56 @@ static int lmv_rename(struct obd_export *exp, struct md_op_data *op_data, RETURN(rc); } +retry_rename: /* * Cancel all the locks on tgt child (fid4). */ - if (fid_is_sane(&op_data->op_fid4)) + if (fid_is_sane(&op_data->op_fid4)) { + struct lmv_tgt_desc *tgt; + rc = lmv_early_cancel(exp, NULL, op_data, src_tgt->ltd_idx, LCK_EX, MDS_INODELOCK_FULL, MF_MDC_CANCEL_FID4); + if (rc != 0) + RETURN(rc); - CDEBUG(D_INODE, DFID":m%d to "DFID"\n", PFID(&op_data->op_fid1), - op_data->op_mds, PFID(&op_data->op_fid2)); + tgt = lmv_find_target(lmv, &op_data->op_fid4); + if (IS_ERR(tgt)) + RETURN(PTR_ERR(tgt)); - rc = md_rename(src_tgt->ltd_exp, op_data, old, oldlen, new, newlen, + /* Since the target child might be destroyed, and it might + * become orphan, and we can only check orphan on the local + * MDT right now, so we send rename request to the MDT where + * target child is located. If target child does not exist, + * then it will send the request to the target parent */ + target_exp = tgt->ltd_exp; + } + + rc = md_rename(target_exp, op_data, old, oldlen, new, newlen, request); - RETURN(rc); + if (rc != 0 && rc != -EXDEV) + RETURN(rc); + + body = req_capsule_server_get(&(*request)->rq_pill, &RMF_MDT_BODY); + if (body == NULL) + RETURN(-EPROTO); + + /* Not cross-ref case, just get out of here. */ + if (likely(!(body->mbo_valid & OBD_MD_MDS))) + RETURN(rc); + + CDEBUG(D_INODE, "%s: try rename to another MDT for "DFID"\n", + exp->exp_obd->obd_name, PFID(&body->mbo_fid1)); + + op_data->op_fid4 = body->mbo_fid1; + ptlrpc_req_finished(*request); + *request = NULL; + goto retry_rename; } static int lmv_setattr(struct obd_export *exp, struct md_op_data *op_data, - void *ea, int ealen, void *ea2, int ea2len, - struct ptlrpc_request **request, - struct md_open_data **mod) + void *ea, size_t ealen, struct ptlrpc_request **request) { struct obd_device *obd = exp->exp_obd; struct lmv_obd *lmv = &obd->u.lmv; @@ -2261,10 +2045,6 @@ static int lmv_setattr(struct obd_export *exp, struct md_op_data *op_data, int rc = 0; ENTRY; - rc = lmv_check_connect(obd); - if (rc) - RETURN(rc); - CDEBUG(D_INODE, "SETATTR for "DFID", valid 0x%x\n", PFID(&op_data->op_fid1), op_data->op_attr.ia_valid); @@ -2273,14 +2053,13 @@ static int lmv_setattr(struct obd_export *exp, struct md_op_data *op_data, if (IS_ERR(tgt)) RETURN(PTR_ERR(tgt)); - rc = md_setattr(tgt->ltd_exp, op_data, ea, ealen, ea2, - ea2len, request, mod); + rc = md_setattr(tgt->ltd_exp, op_data, ea, ealen, request); RETURN(rc); } static int lmv_fsync(struct obd_export *exp, const struct lu_fid *fid, - struct obd_capa *oc, struct ptlrpc_request **request) + struct ptlrpc_request **request) { struct obd_device *obd = exp->exp_obd; struct lmv_obd *lmv = &obd->u.lmv; @@ -2288,15 +2067,11 @@ static int lmv_fsync(struct obd_export *exp, const struct lu_fid *fid, int rc; ENTRY; - rc = lmv_check_connect(obd); - if (rc != 0) - RETURN(rc); - tgt = lmv_find_target(lmv, fid); if (IS_ERR(tgt)) RETURN(PTR_ERR(tgt)); - rc = md_fsync(tgt->ltd_exp, fid, oc, request); + rc = md_fsync(tgt->ltd_exp, fid, request); RETURN(rc); } @@ -2360,7 +2135,6 @@ static int lmv_get_min_striped_entry(struct obd_export *exp, /* op_data will be shared by each stripe, so we need * reset these value for each stripe */ - op_data->op_stripe_offset = i; op_data->op_fid1 = lsm->lsm_md_oinfo[i].lmo_fid; op_data->op_fid2 = lsm->lsm_md_oinfo[i].lmo_fid; op_data->op_data = lsm->lsm_md_oinfo[i].lmo_root; @@ -2398,7 +2172,7 @@ next: stripe_hash = le64_to_cpu(dp->ldp_hash_end); kunmap(page); - page_cache_release(page); + put_page(page); page = NULL; /* reach the end of current stripe, go to next stripe */ @@ -2413,12 +2187,12 @@ next: le64_to_cpu(ent->lde_hash)) { min_ent = ent; kunmap(min_page); - page_cache_release(min_page); + put_page(min_page); min_idx = i; min_page = page; } else { kunmap(page); - page_cache_release(page); + put_page(page); page = NULL; } } else { @@ -2431,7 +2205,7 @@ next: out: if (*ppage != NULL) { kunmap(*ppage); - page_cache_release(*ppage); + put_page(*ppage); } *stripe_offset = min_idx; *entp = min_ent; @@ -2468,7 +2242,6 @@ static int lmv_read_striped_page(struct obd_export *exp, struct md_callback *cb_op, __u64 offset, struct page **ppage) { - struct obd_device *obd = exp->exp_obd; struct lu_fid master_fid = op_data->op_fid1; struct inode *master_inode = op_data->op_data; __u64 hash_offset = offset; @@ -2480,14 +2253,10 @@ static int lmv_read_striped_page(struct obd_export *exp, int ent_idx = 0; struct lu_dirent *min_ent = NULL; struct lu_dirent *last_ent; - int left_bytes; + size_t left_bytes; int rc; ENTRY; - rc = lmv_check_connect(obd); - if (rc) - RETURN(rc); - /* Allocate a page and read entries from all of stripes and fill * the page by hash order */ ent_page = alloc_page(GFP_KERNEL); @@ -2501,7 +2270,7 @@ static int lmv_read_striped_page(struct obd_export *exp, dp->ldp_flags |= LDF_COLLIDE; area = dp + 1; - left_bytes = PAGE_CACHE_SIZE - sizeof(*dp); + left_bytes = PAGE_SIZE - sizeof(*dp); ent = area; last_ent = ent; do { @@ -2562,7 +2331,7 @@ static int lmv_read_striped_page(struct obd_export *exp, out: if (min_ent_page != NULL) { kunmap(min_ent_page); - page_cache_release(min_ent_page); + put_page(min_ent_page); } if (unlikely(rc != 0)) { @@ -2599,10 +2368,6 @@ int lmv_read_page(struct obd_export *exp, struct md_op_data *op_data, int rc; ENTRY; - rc = lmv_check_connect(obd); - if (rc != 0) - RETURN(rc); - if (unlikely(lsm != NULL)) { rc = lmv_read_striped_page(exp, op_data, cb_op, offset, ppage); RETURN(rc); @@ -2654,9 +2419,6 @@ static int lmv_unlink(struct obd_export *exp, struct md_op_data *op_data, struct lmv_stripe_md *lsm = op_data->op_mea1; ENTRY; - rc = lmv_check_connect(obd); - if (rc) - RETURN(rc); retry_unlink: /* For striped dir, we need to locate the parent as well */ if (lsm != NULL) { @@ -2681,7 +2443,7 @@ retry_unlink: * name from stripe 0, but migrating dir is already handled * inside lmv_locate_target_for_name(), so we only check * unknown hash type directory here */ - if (!lmv_is_known_hash_type(lsm)) { + if (!lmv_is_known_hash_type(lsm->lsm_md_hash_type)) { struct lmv_oinfo *oinfo; oinfo = &lsm->lsm_md_oinfo[stripe_index]; @@ -2734,7 +2496,7 @@ try_next_stripe: if (rc != 0) RETURN(rc); - CDEBUG(D_INODE, "unlink with fid="DFID"/"DFID" -> mds #%d\n", + CDEBUG(D_INODE, "unlink with fid="DFID"/"DFID" -> mds #%u\n", PFID(&op_data->op_fid1), PFID(&op_data->op_fid2), tgt->ltd_idx); rc = md_unlink(tgt->ltd_exp, op_data, request); @@ -2797,30 +2559,33 @@ try_next_stripe: goto retry_unlink; } -static int lmv_precleanup(struct obd_device *obd, enum obd_cleanup_stage stage) +static int lmv_precleanup(struct obd_device *obd) { - struct lmv_obd *lmv = &obd->u.lmv; - int rc = 0; - - switch (stage) { - case OBD_CLEANUP_EARLY: - /* XXX: here should be calling obd_precleanup() down to - * stack. */ - break; - case OBD_CLEANUP_EXPORTS: - fld_client_proc_fini(&lmv->lmv_fld); - lprocfs_obd_cleanup(obd); - lprocfs_free_md_stats(obd); - break; - default: - break; - } - RETURN(rc); + ENTRY; + fld_client_proc_fini(&obd->u.lmv.lmv_fld); + lprocfs_obd_cleanup(obd); + lprocfs_free_md_stats(obd); + RETURN(0); } +/** + * Get by key a value associated with a LMV device. + * + * Dispatch request to lower-layer devices as needed. + * + * \param[in] env execution environment for this thread + * \param[in] exp export for the LMV device + * \param[in] keylen length of key identifier + * \param[in] key identifier of key to get value for + * \param[in] vallen size of \a val + * \param[out] val pointer to storage location for value + * \param[in] lsm optional striping metadata of object + * + * \retval 0 on success + * \retval negative negated errno on failure + */ static int lmv_get_info(const struct lu_env *env, struct obd_export *exp, - __u32 keylen, void *key, __u32 *vallen, void *val, - struct lov_stripe_md *lsm) + __u32 keylen, void *key, __u32 *vallen, void *val) { struct obd_device *obd; struct lmv_obd *lmv; @@ -2829,7 +2594,7 @@ static int lmv_get_info(const struct lu_env *env, struct obd_export *exp, obd = class_exp2obd(exp); if (obd == NULL) { - CDEBUG(D_IOCTL, "Invalid client cookie "LPX64"\n", + CDEBUG(D_IOCTL, "Invalid client cookie %#llx\n", exp->exp_handle.h_cookie); RETURN(-EINVAL); } @@ -2838,10 +2603,6 @@ static int lmv_get_info(const struct lu_env *env, struct obd_export *exp, if (keylen >= strlen("remote_flag") && !strcmp(key, "remote_flag")) { int i; - rc = lmv_check_connect(obd); - if (rc) - RETURN(rc); - LASSERT(*vallen == sizeof(__u32)); for (i = 0; i < lmv->desc.ld_tgt_count; i++) { struct lmv_tgt_desc *tgt = lmv->tgts[i]; @@ -2852,25 +2613,19 @@ static int lmv_get_info(const struct lu_env *env, struct obd_export *exp, continue; if (!obd_get_info(env, tgt->ltd_exp, keylen, key, - vallen, val, NULL)) + vallen, val)) RETURN(0); } RETURN(-EINVAL); } else if (KEY_IS(KEY_MAX_EASIZE) || KEY_IS(KEY_DEFAULT_EASIZE) || - KEY_IS(KEY_MAX_COOKIESIZE) || - KEY_IS(KEY_DEFAULT_COOKIESIZE) || KEY_IS(KEY_CONN_DATA)) { - rc = lmv_check_connect(obd); - if (rc) - RETURN(rc); - /* * Forwarding this request to first MDS, it should know LOV * desc. */ rc = obd_get_info(env, lmv->tgts[0]->ltd_exp, keylen, key, - vallen, val, NULL); + vallen, val); if (!rc && KEY_IS(KEY_CONN_DATA)) exp->exp_connect_data = *(struct obd_connect_data *)val; RETURN(rc); @@ -2883,26 +2638,43 @@ static int lmv_get_info(const struct lu_env *env, struct obd_export *exp, RETURN(-EINVAL); } +/** + * Asynchronously set by key a value associated with a LMV device. + * + * Dispatch request to lower-layer devices as needed. + * + * \param[in] env execution environment for this thread + * \param[in] exp export for the LMV device + * \param[in] keylen length of key identifier + * \param[in] key identifier of key to store value for + * \param[in] vallen size of value to store + * \param[in] val pointer to data to be stored + * \param[in] set optional list of related ptlrpc requests + * + * \retval 0 on success + * \retval negative negated errno on failure + */ int lmv_set_info_async(const struct lu_env *env, struct obd_export *exp, - obd_count keylen, void *key, obd_count vallen, - void *val, struct ptlrpc_request_set *set) + __u32 keylen, void *key, __u32 vallen, void *val, + struct ptlrpc_request_set *set) { - struct lmv_tgt_desc *tgt = NULL; - struct obd_device *obd; - struct lmv_obd *lmv; - int rc = 0; - ENTRY; + struct lmv_tgt_desc *tgt = NULL; + struct obd_device *obd; + struct lmv_obd *lmv; + int rc = 0; + ENTRY; - obd = class_exp2obd(exp); - if (obd == NULL) { - CDEBUG(D_IOCTL, "Invalid client cookie "LPX64"\n", - exp->exp_handle.h_cookie); - RETURN(-EINVAL); - } - lmv = &obd->u.lmv; + obd = class_exp2obd(exp); + if (obd == NULL) { + CDEBUG(D_IOCTL, "Invalid client cookie %#llx\n", + exp->exp_handle.h_cookie); + RETURN(-EINVAL); + } + lmv = &obd->u.lmv; - if (KEY_IS(KEY_READ_ONLY) || KEY_IS(KEY_FLUSH_CTX)) { - int i, err = 0; + if (KEY_IS(KEY_READ_ONLY) || KEY_IS(KEY_FLUSH_CTX) || + KEY_IS(KEY_DEFAULT_EASIZE)) { + int i, err = 0; for (i = 0; i < lmv->desc.ld_tgt_count; i++) { tgt = lmv->tgts[i]; @@ -2910,101 +2682,17 @@ int lmv_set_info_async(const struct lu_env *env, struct obd_export *exp, if (tgt == NULL || tgt->ltd_exp == NULL) continue; - err = obd_set_info_async(env, tgt->ltd_exp, - keylen, key, vallen, val, set); - if (err && rc == 0) - rc = err; - } - - RETURN(rc); - } - - RETURN(-EINVAL); -} - -static int lmv_pack_md_v1(const struct lmv_stripe_md *lsm, - struct lmv_mds_md_v1 *lmm1) -{ - int cplen; - int i; - - lmm1->lmv_magic = cpu_to_le32(lsm->lsm_md_magic); - lmm1->lmv_stripe_count = cpu_to_le32(lsm->lsm_md_stripe_count); - lmm1->lmv_master_mdt_index = cpu_to_le32(lsm->lsm_md_master_mdt_index); - lmm1->lmv_hash_type = cpu_to_le32(lsm->lsm_md_hash_type); - cplen = strlcpy(lmm1->lmv_pool_name, lsm->lsm_md_pool_name, - sizeof(lmm1->lmv_pool_name)); - if (cplen >= sizeof(lmm1->lmv_pool_name)) - return -E2BIG; - - for (i = 0; i < lsm->lsm_md_stripe_count; i++) - fid_cpu_to_le(&lmm1->lmv_stripe_fids[i], - &lsm->lsm_md_oinfo[i].lmo_fid); - return 0; -} - -int lmv_pack_md(union lmv_mds_md **lmmp, const struct lmv_stripe_md *lsm, - int stripe_count) -{ - int lmm_size = 0; - bool allocated = false; - int rc = 0; - ENTRY; - - LASSERT(lmmp != NULL); - /* Free lmm */ - if (*lmmp != NULL && lsm == NULL) { - int stripe_count; - - stripe_count = lmv_mds_md_stripe_count_get(*lmmp); - lmm_size = lmv_mds_md_size(stripe_count, - le32_to_cpu((*lmmp)->lmv_magic)); - if (lmm_size == 0) - RETURN(-EINVAL); - OBD_FREE(*lmmp, lmm_size); - *lmmp = NULL; - RETURN(0); - } - - /* Alloc lmm */ - if (*lmmp == NULL && lsm == NULL) { - lmm_size = lmv_mds_md_size(stripe_count, LMV_MAGIC); - LASSERT(lmm_size > 0); - OBD_ALLOC(*lmmp, lmm_size); - if (*lmmp == NULL) - RETURN(-ENOMEM); - lmv_mds_md_stripe_count_set(*lmmp, stripe_count); - (*lmmp)->lmv_magic = cpu_to_le32(LMV_MAGIC); - RETURN(lmm_size); - } - - /* pack lmm */ - LASSERT(lsm != NULL); - lmm_size = lmv_mds_md_size(lsm->lsm_md_stripe_count, lsm->lsm_md_magic); - if (*lmmp == NULL) { - OBD_ALLOC(*lmmp, lmm_size); - if (*lmmp == NULL) - RETURN(-ENOMEM); - allocated = true; - } - - switch (lsm->lsm_md_magic) { - case LMV_MAGIC_V1: - rc = lmv_pack_md_v1(lsm, &(*lmmp)->lmv_md_v1); - break; - default: - rc = -EINVAL; - break; - } + err = obd_set_info_async(env, tgt->ltd_exp, + keylen, key, vallen, val, set); + if (err && rc == 0) + rc = err; + } - if (rc != 0 && allocated) { - OBD_FREE(*lmmp, lmm_size); - *lmmp = NULL; + RETURN(rc); } - RETURN(lmm_size); + RETURN(-EINVAL); } -EXPORT_SYMBOL(lmv_pack_md); static int lmv_unpack_md_v1(struct obd_export *exp, struct lmv_stripe_md *lsm, const struct lmv_mds_md_v1 *lmm1) @@ -3036,7 +2724,7 @@ static int lmv_unpack_md_v1(struct obd_export *exp, struct lmv_stripe_md *lsm, lsm->lsm_md_layout_version); stripe_count = le32_to_cpu(lmm1->lmv_stripe_count); - for (i = 0; i < le32_to_cpu(stripe_count); i++) { + for (i = 0; i < stripe_count; i++) { fid_le_to_cpu(&lsm->lsm_md_oinfo[i].lmo_fid, &lmm1->lmv_stripe_fids[i]); rc = lmv_fld_lookup(lmv, &lsm->lsm_md_oinfo[i].lmo_fid, @@ -3050,8 +2738,8 @@ static int lmv_unpack_md_v1(struct obd_export *exp, struct lmv_stripe_md *lsm, RETURN(rc); } -int lmv_unpack_md(struct obd_export *exp, struct lmv_stripe_md **lsmp, - const union lmv_mds_md *lmm, int stripe_count) +static int lmv_unpackmd(struct obd_export *exp, struct lmv_stripe_md **lsmp, + const union lmv_mds_md *lmm, size_t lmm_size) { struct lmv_stripe_md *lsm; int lsm_size; @@ -3079,17 +2767,6 @@ int lmv_unpack_md(struct obd_export *exp, struct lmv_stripe_md **lsmp, RETURN(0); } - /* Alloc memmd */ - if (lsm == NULL && lmm == NULL) { - lsm_size = lmv_stripe_md_size(stripe_count); - OBD_ALLOC(lsm, lsm_size); - if (lsm == NULL) - RETURN(-ENOMEM); - lsm->lsm_md_stripe_count = stripe_count; - *lsmp = lsm; - RETURN(0); - } - if (le32_to_cpu(lmm->lmv_magic) == LMV_MAGIC_STRIPE) RETURN(-EPERM); @@ -3139,60 +2816,27 @@ int lmv_unpack_md(struct obd_export *exp, struct lmv_stripe_md **lsmp, RETURN(lsm_size); } -int lmv_alloc_memmd(struct lmv_stripe_md **lsmp, int stripes) -{ - return lmv_unpack_md(NULL, lsmp, NULL, stripes); -} -EXPORT_SYMBOL(lmv_alloc_memmd); - void lmv_free_memmd(struct lmv_stripe_md *lsm) { - lmv_unpack_md(NULL, &lsm, NULL, 0); + lmv_unpackmd(NULL, &lsm, NULL, 0); } EXPORT_SYMBOL(lmv_free_memmd); -int lmv_unpackmd(struct obd_export *exp, struct lov_stripe_md **lsmp, - struct lov_mds_md *lmm, int disk_len) -{ - return lmv_unpack_md(exp, (struct lmv_stripe_md **)lsmp, - (union lmv_mds_md *)lmm, disk_len); -} - -int lmv_packmd(struct obd_export *exp, struct lov_mds_md **lmmp, - struct lov_stripe_md *lsm) -{ - struct obd_device *obd = exp->exp_obd; - struct lmv_obd *lmv_obd = &obd->u.lmv; - const struct lmv_stripe_md *lmv = (struct lmv_stripe_md *)lsm; - int stripe_count; - - if (lmmp == NULL) { - if (lsm != NULL) - stripe_count = lmv->lsm_md_stripe_count; - else - stripe_count = lmv_obd->desc.ld_tgt_count; - - return lmv_mds_md_size(stripe_count, LMV_MAGIC_V1); - } - - return lmv_pack_md((union lmv_mds_md **)lmmp, lmv, 0); -} - static int lmv_cancel_unused(struct obd_export *exp, const struct lu_fid *fid, - ldlm_policy_data_t *policy, ldlm_mode_t mode, - ldlm_cancel_flags_t flags, void *opaque) + union ldlm_policy_data *policy, + enum ldlm_mode mode, enum ldlm_cancel_flags flags, + void *opaque) { - struct obd_device *obd = exp->exp_obd; - struct lmv_obd *lmv = &obd->u.lmv; - int rc = 0; - int err; - __u32 i; - ENTRY; + struct lmv_obd *lmv = &exp->exp_obd->u.lmv; + int rc = 0; + __u32 i; + ENTRY; - LASSERT(fid != NULL); + LASSERT(fid != NULL); for (i = 0; i < lmv->desc.ld_tgt_count; i++) { struct lmv_tgt_desc *tgt = lmv->tgts[i]; + int err; if (tgt == NULL || tgt->ltd_exp == NULL || !tgt->ltd_active) continue; @@ -3205,8 +2849,9 @@ static int lmv_cancel_unused(struct obd_export *exp, const struct lu_fid *fid, RETURN(rc); } -int lmv_set_lock_data(struct obd_export *exp, __u64 *lockh, void *data, - __u64 *bits) +static int lmv_set_lock_data(struct obd_export *exp, + const struct lustre_handle *lockh, + void *data, __u64 *bits) { struct lmv_obd *lmv = &exp->exp_obd->u.lmv; struct lmv_tgt_desc *tgt = lmv->tgts[0]; @@ -3219,14 +2864,14 @@ int lmv_set_lock_data(struct obd_export *exp, __u64 *lockh, void *data, RETURN(rc); } -ldlm_mode_t lmv_lock_match(struct obd_export *exp, __u64 flags, - const struct lu_fid *fid, ldlm_type_t type, - ldlm_policy_data_t *policy, ldlm_mode_t mode, - struct lustre_handle *lockh) +enum ldlm_mode lmv_lock_match(struct obd_export *exp, __u64 flags, + const struct lu_fid *fid, enum ldlm_type type, + union ldlm_policy_data *policy, + enum ldlm_mode mode, struct lustre_handle *lockh) { struct obd_device *obd = exp->exp_obd; struct lmv_obd *lmv = &obd->u.lmv; - ldlm_mode_t rc; + enum ldlm_mode rc; int tgt; int i; ENTRY; @@ -3322,81 +2967,38 @@ int lmv_clear_open_replay_data(struct obd_export *exp, RETURN(md_clear_open_replay_data(tgt->ltd_exp, och)); } -static int lmv_get_remote_perm(struct obd_export *exp, - const struct lu_fid *fid, - struct obd_capa *oc, __u32 suppgid, - struct ptlrpc_request **request) -{ - struct obd_device *obd = exp->exp_obd; - struct lmv_obd *lmv = &obd->u.lmv; - struct lmv_tgt_desc *tgt; - int rc; - ENTRY; - - rc = lmv_check_connect(obd); - if (rc) - RETURN(rc); - - tgt = lmv_find_target(lmv, fid); - if (IS_ERR(tgt)) - RETURN(PTR_ERR(tgt)); - - rc = md_get_remote_perm(tgt->ltd_exp, fid, oc, suppgid, request); - RETURN(rc); -} - -static int lmv_renew_capa(struct obd_export *exp, struct obd_capa *oc, - renew_capa_cb_t cb) -{ - struct obd_device *obd = exp->exp_obd; - struct lmv_obd *lmv = &obd->u.lmv; - struct lmv_tgt_desc *tgt; - int rc; - ENTRY; - - rc = lmv_check_connect(obd); - if (rc) - RETURN(rc); - - tgt = lmv_find_target(lmv, &oc->c_capa.lc_fid); - if (IS_ERR(tgt)) - RETURN(PTR_ERR(tgt)); - - rc = md_renew_capa(tgt->ltd_exp, oc, cb); - RETURN(rc); -} - -int lmv_unpack_capa(struct obd_export *exp, struct ptlrpc_request *req, - const struct req_msg_field *field, struct obd_capa **oc) -{ - struct lmv_obd *lmv = &exp->exp_obd->u.lmv; - struct lmv_tgt_desc *tgt = lmv->tgts[0]; - - if (tgt == NULL || tgt->ltd_exp == NULL) - RETURN(-EINVAL); - return md_unpack_capa(tgt->ltd_exp, req, field, oc); -} - int lmv_intent_getattr_async(struct obd_export *exp, - struct md_enqueue_info *minfo, - struct ldlm_enqueue_info *einfo) + struct md_enqueue_info *minfo) { struct md_op_data *op_data = &minfo->mi_data; struct obd_device *obd = exp->exp_obd; struct lmv_obd *lmv = &obd->u.lmv; - struct lmv_tgt_desc *tgt = NULL; + struct lmv_tgt_desc *ptgt = NULL; + struct lmv_tgt_desc *ctgt = NULL; int rc; ENTRY; - rc = lmv_check_connect(obd); - if (rc) - RETURN(rc); + if (!fid_is_sane(&op_data->op_fid2)) + RETURN(-EINVAL); - tgt = lmv_locate_mds(lmv, op_data, &op_data->op_fid1); - if (IS_ERR(tgt)) - RETURN(PTR_ERR(tgt)); + ptgt = lmv_locate_mds(lmv, op_data, &op_data->op_fid1); + if (IS_ERR(ptgt)) + RETURN(PTR_ERR(ptgt)); + + ctgt = lmv_locate_mds(lmv, op_data, &op_data->op_fid2); + if (IS_ERR(ctgt)) + RETURN(PTR_ERR(ctgt)); + + /* + * if child is on remote MDT, we need 2 async RPCs to fetch both LOOKUP + * lock on parent, and UPDATE lock on child MDT, which makes all + * complicated. Considering remote dir is rare case, and not supporting + * it in statahead won't cause any issue, drop its support for now. + */ + if (ptgt != ctgt) + RETURN(-ENOTSUPP); - rc = md_intent_getattr_async(tgt->ltd_exp, minfo, einfo); + rc = md_intent_getattr_async(ptgt->ltd_exp, minfo); RETURN(rc); } @@ -3409,10 +3011,6 @@ int lmv_revalidate_lock(struct obd_export *exp, struct lookup_intent *it, int rc; ENTRY; - rc = lmv_check_connect(obd); - if (rc) - RETURN(rc); - tgt = lmv_find_target(lmv, fid); if (IS_ERR(tgt)) RETURN(PTR_ERR(tgt)); @@ -3490,51 +3088,27 @@ int lmv_quotactl(struct obd_device *unused, struct obd_export *exp, RETURN(rc); } -int lmv_quotacheck(struct obd_device *unused, struct obd_export *exp, - struct obd_quotactl *oqctl) -{ - struct obd_device *obd = class_exp2obd(exp); - struct lmv_obd *lmv = &obd->u.lmv; - struct lmv_tgt_desc *tgt; - __u32 i; - int rc = 0; - ENTRY; - - for (i = 0; i < lmv->desc.ld_tgt_count; i++) { - int err; - tgt = lmv->tgts[i]; - if (tgt == NULL || tgt->ltd_exp == NULL || !tgt->ltd_active) { - CERROR("lmv idx %d inactive\n", i); - RETURN(-EIO); - } - - err = obd_quotacheck(tgt->ltd_exp, oqctl); - if (err && !rc) - rc = err; - } - - RETURN(rc); -} - -int lmv_update_lsm_md(struct obd_export *exp, struct lmv_stripe_md *lsm, - struct mdt_body *body, ldlm_blocking_callback cb_blocking) -{ - return lmv_revalidate_slaves(exp, body, lsm, cb_blocking, 0); -} - -int lmv_merge_attr(struct obd_export *exp, const struct lmv_stripe_md *lsm, - struct cl_attr *attr) +static int lmv_merge_attr(struct obd_export *exp, + const struct lmv_stripe_md *lsm, + struct cl_attr *attr, + ldlm_blocking_callback cb_blocking) { + int rc; int i; + rc = lmv_revalidate_slaves(exp, lsm, cb_blocking, 0); + if (rc < 0) + return rc; + for (i = 0; i < lsm->lsm_md_stripe_count; i++) { struct inode *inode = lsm->lsm_md_oinfo[i].lmo_root; - CDEBUG(D_INFO, ""DFID" size %llu, nlink %u, atime %lu ctime" - "%lu, mtime %lu.\n", PFID(&lsm->lsm_md_oinfo[i].lmo_fid), - i_size_read(inode), inode->i_nlink, - LTIME_S(inode->i_atime), LTIME_S(inode->i_ctime), - LTIME_S(inode->i_mtime)); + CDEBUG(D_INFO, ""DFID" size %llu, blocks %llu nlink %u," + " atime %lu ctime %lu, mtime %lu.\n", + PFID(&lsm->lsm_md_oinfo[i].lmo_fid), + i_size_read(inode), (unsigned long long)inode->i_blocks, + inode->i_nlink, LTIME_S(inode->i_atime), + LTIME_S(inode->i_ctime), LTIME_S(inode->i_mtime)); /* for slave stripe, it needs to subtract nlink for . and .. */ if (i != 0) @@ -3543,6 +3117,7 @@ int lmv_merge_attr(struct obd_export *exp, const struct lmv_stripe_md *lsm, attr->cat_nlink = inode->i_nlink; attr->cat_size += i_size_read(inode); + attr->cat_blocks += inode->i_blocks; if (attr->cat_atime < LTIME_S(inode->i_atime)) attr->cat_atime = LTIME_S(inode->i_atime); @@ -3567,22 +3142,17 @@ struct obd_ops lmv_obd_ops = { .o_statfs = lmv_statfs, .o_get_info = lmv_get_info, .o_set_info_async = lmv_set_info_async, - .o_packmd = lmv_packmd, - .o_unpackmd = lmv_unpackmd, .o_notify = lmv_notify, .o_get_uuid = lmv_get_uuid, .o_iocontrol = lmv_iocontrol, - .o_quotacheck = lmv_quotacheck, .o_quotactl = lmv_quotactl }; struct md_ops lmv_md_ops = { - .m_getstatus = lmv_getstatus, + .m_get_root = lmv_get_root, .m_null_inode = lmv_null_inode, - .m_find_cbdata = lmv_find_cbdata, .m_close = lmv_close, .m_create = lmv_create, - .m_done_writing = lmv_done_writing, .m_enqueue = lmv_enqueue, .m_getattr = lmv_getattr, .m_getxattr = lmv_getxattr, @@ -3601,34 +3171,29 @@ struct md_ops lmv_md_ops = { .m_lock_match = lmv_lock_match, .m_get_lustre_md = lmv_get_lustre_md, .m_free_lustre_md = lmv_free_lustre_md, - .m_update_lsm_md = lmv_update_lsm_md, .m_merge_attr = lmv_merge_attr, .m_set_open_replay_data = lmv_set_open_replay_data, .m_clear_open_replay_data = lmv_clear_open_replay_data, - .m_renew_capa = lmv_renew_capa, - .m_unpack_capa = lmv_unpack_capa, - .m_get_remote_perm = lmv_get_remote_perm, .m_intent_getattr_async = lmv_intent_getattr_async, .m_revalidate_lock = lmv_revalidate_lock, .m_get_fid_from_lsm = lmv_get_fid_from_lsm, + .m_unpackmd = lmv_unpackmd, }; -int __init lmv_init(void) +static int __init lmv_init(void) { return class_register_type(&lmv_obd_ops, &lmv_md_ops, true, NULL, -#ifndef HAVE_ONLY_PROCFS_SEQ - NULL, -#endif LUSTRE_LMV_NAME, NULL); } -static void lmv_exit(void) +static void __exit lmv_exit(void) { - class_unregister_type(LUSTRE_LMV_NAME); + class_unregister_type(LUSTRE_LMV_NAME); } -MODULE_AUTHOR("Sun Microsystems, Inc. "); -MODULE_DESCRIPTION("Lustre Logical Metadata Volume OBD driver"); +MODULE_AUTHOR("OpenSFS, Inc. "); +MODULE_DESCRIPTION("Lustre Logical Metadata Volume"); +MODULE_VERSION(LUSTRE_VERSION_STRING); MODULE_LICENSE("GPL"); module_init(lmv_init);