X-Git-Url: https://git.whamcloud.com/?a=blobdiff_plain;f=lustre%2Flmv%2Flmv_obd.c;h=69479d123e89a68cda265257aed213aa559f62c5;hb=4c0dcdf290c8f3fc74a2585e976d7fc430bc79c4;hp=b58caade43d3e9fcd99795402708ea5141868b3f;hpb=930dca7253bc2531bffa15dc763db1081cdf32d8;p=fs%2Flustre-release.git diff --git a/lustre/lmv/lmv_obd.c b/lustre/lmv/lmv_obd.c index b58caad..69479d1 100644 --- a/lustre/lmv/lmv_obd.c +++ b/lustre/lmv/lmv_obd.c @@ -27,7 +27,7 @@ * Copyright (c) 2004, 2010, Oracle and/or its affiliates. All rights reserved. * Use is subject to license terms. * - * Copyright (c) 2011, 2014, Intel Corporation. + * Copyright (c) 2011, 2015, Intel Corporation. */ /* * This file is part of Lustre, http://www.lustre.org/ @@ -683,21 +683,26 @@ out_local: 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) @@ -710,23 +715,24 @@ 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", 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) @@ -755,7 +761,8 @@ 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; @@ -776,13 +783,15 @@ 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) @@ -796,6 +805,8 @@ 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]; @@ -805,14 +816,16 @@ 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) */ @@ -830,21 +843,19 @@ 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. @@ -892,21 +903,14 @@ 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); } @@ -915,7 +919,7 @@ 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; @@ -1092,8 +1096,8 @@ 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]; @@ -1101,6 +1105,8 @@ 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; @@ -1111,11 +1117,12 @@ 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); @@ -1183,51 +1190,6 @@ 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). */ @@ -1366,7 +1328,6 @@ static int lmv_setup(struct obd_device *obd, struct lustre_cfg *lcfg) lmv->desc.ld_active_tgt_count = 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->lmv_init_mutex); @@ -1500,18 +1461,19 @@ out_free_temp: return rc; } -static int lmv_getstatus(struct obd_export *exp, struct lu_fid *fid) +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 = lmv_check_connect(obd); + if (rc) + RETURN(rc); - rc = md_getstatus(lmv->tgts[0]->ltd_exp, fid); + rc = md_get_root(lmv->tgts[0]->ltd_exp, fileset, fid); RETURN(rc); } @@ -1622,50 +1584,6 @@ 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) { @@ -1752,26 +1670,27 @@ 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; } @@ -2748,25 +2667,13 @@ 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); } /** @@ -3058,8 +2965,9 @@ 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]; @@ -3175,47 +3083,42 @@ 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, - 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, suppgid, request); - RETURN(rc); -} - 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; + if (!fid_is_sane(&op_data->op_fid2)) + RETURN(-EINVAL); + 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)); + 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); } @@ -3370,9 +3273,8 @@ struct obd_ops lmv_obd_ops = { }; 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_enqueue = lmv_enqueue, @@ -3396,26 +3298,26 @@ struct md_ops lmv_md_ops = { .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_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, 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);