X-Git-Url: https://git.whamcloud.com/?a=blobdiff_plain;f=lustre%2Fllite%2Fllite_lib.c;h=5ba34dbc114f2a528033d876e918cfbf6e6f6eac;hb=72a84970e6d2a2d4b3a35f2ee058511be2fda82e;hp=8c82dd8d740d208b43cfc4fc13b22e6a1223aefc;hpb=3a6bbda28826ec1eda59ecb9f442a31f87bb409c;p=fs%2Flustre-release.git diff --git a/lustre/llite/llite_lib.c b/lustre/llite/llite_lib.c index 8c82dd8..5ba34db 100644 --- a/lustre/llite/llite_lib.c +++ b/lustre/llite/llite_lib.c @@ -37,9 +37,11 @@ #define DEBUG_SUBSYSTEM S_LLITE #include +#include #include #include #include +#include #include #include #include @@ -49,6 +51,10 @@ #include #include +#ifdef HAVE_UAPI_LINUX_MOUNT_H +#include +#endif + #include #include #include @@ -71,44 +77,56 @@ static struct ll_sb_info *ll_init_sbi(void) unsigned long pages; unsigned long lru_page_max; struct sysinfo si; - class_uuid_t uuid; + int rc; int i; + ENTRY; OBD_ALLOC_PTR(sbi); if (sbi == NULL) - RETURN(NULL); + RETURN(ERR_PTR(-ENOMEM)); + + rc = pcc_super_init(&sbi->ll_pcc_super); + if (rc < 0) + GOTO(out_sbi, rc); spin_lock_init(&sbi->ll_lock); mutex_init(&sbi->ll_lco.lco_lock); spin_lock_init(&sbi->ll_pp_extent_lock); spin_lock_init(&sbi->ll_process_lock); sbi->ll_rw_stats_on = 0; + sbi->ll_statfs_max_age = OBD_STATFS_CACHE_SECONDS; si_meminfo(&si); pages = si.totalram - si.totalhigh; lru_page_max = pages / 2; + sbi->ll_ra_info.ra_async_max_active = 0; + sbi->ll_ra_info.ll_readahead_wq = + alloc_workqueue("ll-readahead-wq", WQ_UNBOUND, + sbi->ll_ra_info.ra_async_max_active); + if (!sbi->ll_ra_info.ll_readahead_wq) + GOTO(out_pcc, rc = -ENOMEM); + /* initialize ll_cache data */ sbi->ll_cache = cl_cache_init(lru_page_max); - if (sbi->ll_cache == NULL) { - OBD_FREE(sbi, sizeof(*sbi)); - RETURN(NULL); - } + if (sbi->ll_cache == NULL) + GOTO(out_destroy_ra, rc = -ENOMEM); sbi->ll_ra_info.ra_max_pages_per_file = min(pages / 32, SBI_DEFAULT_READAHEAD_MAX); + sbi->ll_ra_info.ra_async_pages_per_file_threshold = + sbi->ll_ra_info.ra_max_pages_per_file; sbi->ll_ra_info.ra_max_pages = sbi->ll_ra_info.ra_max_pages_per_file; sbi->ll_ra_info.ra_max_read_ahead_whole_pages = -1; - ll_generate_random_uuid(uuid); - class_uuid_unparse(uuid, &sbi->ll_sb_uuid); - CDEBUG(D_CONFIG, "generated uuid: %s\n", sbi->ll_sb_uuid.uuid); - sbi->ll_flags |= LL_SBI_VERBOSE; #ifdef ENABLE_CHECKSUM sbi->ll_flags |= LL_SBI_CHECKSUM; #endif +#ifdef ENABLE_FLOCK + sbi->ll_flags |= LL_SBI_FLOCK; +#endif #ifdef HAVE_LRU_RESIZE_SUPPORT sbi->ll_flags |= LL_SBI_LRU_RESIZE; @@ -137,9 +155,19 @@ static struct ll_sb_info *ll_init_sbi(void) sbi->ll_squash.rsi_uid = 0; sbi->ll_squash.rsi_gid = 0; INIT_LIST_HEAD(&sbi->ll_squash.rsi_nosquash_nids); - init_rwsem(&sbi->ll_squash.rsi_sem); + spin_lock_init(&sbi->ll_squash.rsi_lock); + /* Per-filesystem file heat */ + sbi->ll_heat_decay_weight = SBI_DEFAULT_HEAT_DECAY_WEIGHT; + sbi->ll_heat_period_second = SBI_DEFAULT_HEAT_PERIOD_SECOND; RETURN(sbi); +out_destroy_ra: + destroy_workqueue(sbi->ll_ra_info.ll_readahead_wq); +out_pcc: + pcc_super_fini(&sbi->ll_pcc_super); +out_sbi: + OBD_FREE_PTR(sbi); + RETURN(ERR_PTR(rc)); } static void ll_free_sbi(struct super_block *sb) @@ -150,39 +178,35 @@ static void ll_free_sbi(struct super_block *sb) if (sbi != NULL) { if (!list_empty(&sbi->ll_squash.rsi_nosquash_nids)) cfs_free_nidlist(&sbi->ll_squash.rsi_nosquash_nids); + if (sbi->ll_ra_info.ll_readahead_wq) + destroy_workqueue(sbi->ll_ra_info.ll_readahead_wq); if (sbi->ll_cache != NULL) { cl_cache_decref(sbi->ll_cache); sbi->ll_cache = NULL; } + pcc_super_fini(&sbi->ll_pcc_super); OBD_FREE(sbi, sizeof(*sbi)); } EXIT; } -static inline int obd_connect_has_secctx(struct obd_connect_data *data) -{ - return data->ocd_connect_flags & OBD_CONNECT_FLAGS2 && - data->ocd_connect_flags2 & OBD_CONNECT2_FILE_SECCTX; -} - static int client_common_fill_super(struct super_block *sb, char *md, char *dt, struct vfsmount *mnt) { struct inode *root = NULL; - struct ll_sb_info *sbi = ll_s2sbi(sb); - struct obd_device *obd; - struct obd_statfs *osfs = NULL; - struct ptlrpc_request *request = NULL; - struct obd_connect_data *data = NULL; - struct obd_uuid *uuid; - struct md_op_data *op_data; - struct lustre_md lmd; + struct ll_sb_info *sbi = ll_s2sbi(sb); + struct obd_statfs *osfs = NULL; + struct ptlrpc_request *request = NULL; + struct obd_connect_data *data = NULL; + struct obd_uuid *uuid; + struct md_op_data *op_data; + struct lustre_md lmd; u64 valid; - int size, err, checksum; - ENTRY; + int size, err, checksum; - obd = class_name2obd(md); - if (!obd) { + ENTRY; + sbi->ll_md_obd = class_name2obd(md); + if (!sbi->ll_md_obd) { CERROR("MD %s: not setup or attached\n", md); RETURN(-EINVAL); } @@ -225,10 +249,15 @@ static int client_common_fill_super(struct super_block *sb, char *md, char *dt, OBD_CONNECT_GRANT_PARAM | OBD_CONNECT_SHORTIO | OBD_CONNECT_FLAGS2; - data->ocd_connect_flags2 = OBD_CONNECT2_FLR | + data->ocd_connect_flags2 = OBD_CONNECT2_DIR_MIGRATE | + OBD_CONNECT2_SUM_STATFS | + OBD_CONNECT2_OVERSTRIPING | + OBD_CONNECT2_FLR | OBD_CONNECT2_LOCK_CONVERT | - OBD_CONNECT2_DIR_MIGRATE | - OBD_CONNECT2_SUM_STATFS; + OBD_CONNECT2_ARCHIVE_ID_ARRAY | + OBD_CONNECT2_LSOM | + OBD_CONNECT2_ASYNC_DISCARD | + OBD_CONNECT2_PCC; #ifdef HAVE_LRU_RESIZE_SUPPORT if (sbi->ll_flags & LL_SBI_LRU_RESIZE) @@ -244,51 +273,54 @@ static int client_common_fill_super(struct super_block *sb, char *md, char *dt, if (OBD_FAIL_CHECK(OBD_FAIL_MDC_LIGHTWEIGHT)) /* flag mdc connection as lightweight, only used for test * purpose, use with care */ - data->ocd_connect_flags |= OBD_CONNECT_LIGHTWEIGHT; + data->ocd_connect_flags |= OBD_CONNECT_LIGHTWEIGHT; - data->ocd_ibits_known = MDS_INODELOCK_FULL; - data->ocd_version = LUSTRE_VERSION_CODE; + data->ocd_ibits_known = MDS_INODELOCK_FULL; + data->ocd_version = LUSTRE_VERSION_CODE; - if (sb->s_flags & MS_RDONLY) - data->ocd_connect_flags |= OBD_CONNECT_RDONLY; - if (sbi->ll_flags & LL_SBI_USER_XATTR) - data->ocd_connect_flags |= OBD_CONNECT_XATTR; + if (sb->s_flags & SB_RDONLY) + data->ocd_connect_flags |= OBD_CONNECT_RDONLY; + if (sbi->ll_flags & LL_SBI_USER_XATTR) + data->ocd_connect_flags |= OBD_CONNECT_XATTR; -#ifdef MS_NOSEC +#ifdef SB_NOSEC /* Setting this indicates we correctly support S_NOSEC (See kernel * commit 9e1f1de02c2275d7172e18dc4e7c2065777611bf) */ - sb->s_flags |= MS_NOSEC; + sb->s_flags |= SB_NOSEC; #endif - if (sbi->ll_flags & LL_SBI_FLOCK) - sbi->ll_fop = &ll_file_operations_flock; - else if (sbi->ll_flags & LL_SBI_LOCALFLOCK) - sbi->ll_fop = &ll_file_operations; - else - sbi->ll_fop = &ll_file_operations_noflock; + if (sbi->ll_flags & LL_SBI_FLOCK) + sbi->ll_fop = &ll_file_operations_flock; + else if (sbi->ll_flags & LL_SBI_LOCALFLOCK) + sbi->ll_fop = &ll_file_operations; + else + sbi->ll_fop = &ll_file_operations_noflock; /* always ping even if server suppress_pings */ if (sbi->ll_flags & LL_SBI_ALWAYS_PING) data->ocd_connect_flags &= ~OBD_CONNECT_PINGLESS; -#if defined(HAVE_SECURITY_DENTRY_INIT_SECURITY) && defined(CONFIG_SECURITY) - data->ocd_connect_flags2 |= OBD_CONNECT2_FILE_SECCTX; -#endif /* HAVE_SECURITY_DENTRY_INIT_SECURITY */ + obd_connect_set_secctx(data); + +#if defined(CONFIG_SECURITY) + data->ocd_connect_flags2 |= OBD_CONNECT2_SELINUX_POLICY; +#endif data->ocd_brw_size = MD_MAX_BRW_SIZE; - err = obd_connect(NULL, &sbi->ll_md_exp, obd, &sbi->ll_sb_uuid, data, NULL); - if (err == -EBUSY) { - LCONSOLE_ERROR_MSG(0x14f, "An MDT (md %s) is performing " - "recovery, of which this client is not a " - "part. Please wait for recovery to complete," - " abort, or time out.\n", md); - GOTO(out, err); - } else if (err) { - CERROR("cannot connect to %s: rc = %d\n", md, err); - GOTO(out, err); - } + err = obd_connect(NULL, &sbi->ll_md_exp, sbi->ll_md_obd, + &sbi->ll_sb_uuid, data, sbi->ll_cache); + if (err == -EBUSY) { + LCONSOLE_ERROR_MSG(0x14f, "An MDT (md %s) is performing " + "recovery, of which this client is not a " + "part. Please wait for recovery to complete," + " abort, or time out.\n", md); + GOTO(out, err); + } else if (err) { + CERROR("cannot connect to %s: rc = %d\n", md, err); + GOTO(out, err); + } sbi->ll_md_exp->exp_connect_data = *data; @@ -304,7 +336,7 @@ static int client_common_fill_super(struct super_block *sb, char *md, char *dt, * can make sure the client can be mounted as long as MDT0 is * avaible */ err = obd_statfs(NULL, sbi->ll_md_exp, osfs, - ktime_get_seconds() -OBD_STATFS_CACHE_SECONDS, + ktime_get_seconds() - sbi->ll_statfs_max_age, OBD_STATFS_FOR_MDT0); if (err) GOTO(out_md_fid, err); @@ -350,28 +382,28 @@ static int client_common_fill_super(struct super_block *sb, char *md, char *dt, sbi->ll_namelen = osfs->os_namelen; sbi->ll_mnt.mnt = current->fs->root.mnt; - if ((sbi->ll_flags & LL_SBI_USER_XATTR) && - !(data->ocd_connect_flags & OBD_CONNECT_XATTR)) { - LCONSOLE_INFO("Disabling user_xattr feature because " - "it is not supported on the server\n"); - sbi->ll_flags &= ~LL_SBI_USER_XATTR; - } + if ((sbi->ll_flags & LL_SBI_USER_XATTR) && + !(data->ocd_connect_flags & OBD_CONNECT_XATTR)) { + LCONSOLE_INFO("Disabling user_xattr feature because " + "it is not supported on the server\n"); + sbi->ll_flags &= ~LL_SBI_USER_XATTR; + } - if (data->ocd_connect_flags & OBD_CONNECT_ACL) { -#ifdef MS_POSIXACL - sb->s_flags |= MS_POSIXACL; + if (data->ocd_connect_flags & OBD_CONNECT_ACL) { +#ifdef SB_POSIXACL + sb->s_flags |= SB_POSIXACL; #endif - sbi->ll_flags |= LL_SBI_ACL; - } else { - LCONSOLE_INFO("client wants to enable acl, but mdt not!\n"); -#ifdef MS_POSIXACL - sb->s_flags &= ~MS_POSIXACL; + sbi->ll_flags |= LL_SBI_ACL; + } else { + LCONSOLE_INFO("client wants to enable acl, but mdt not!\n"); +#ifdef SB_POSIXACL + sb->s_flags &= ~SB_POSIXACL; #endif - sbi->ll_flags &= ~LL_SBI_ACL; - } + sbi->ll_flags &= ~LL_SBI_ACL; + } - if (data->ocd_connect_flags & OBD_CONNECT_64BITHASH) - sbi->ll_flags |= LL_SBI_64BIT_HASH; + if (data->ocd_connect_flags & OBD_CONNECT_64BITHASH) + sbi->ll_flags |= LL_SBI_64BIT_HASH; if (data->ocd_connect_flags & OBD_CONNECT_LAYOUTLOCK) sbi->ll_flags |= LL_SBI_LAYOUT_LOCK; @@ -391,8 +423,8 @@ static int client_common_fill_super(struct super_block *sb, char *md, char *dt, } } - obd = class_name2obd(dt); - if (!obd) { + sbi->ll_dt_obd = class_name2obd(dt); + if (!sbi->ll_dt_obd) { CERROR("DT %s: not setup or attached\n", dt); GOTO(out_md_fid, err = -ENODEV); } @@ -439,8 +471,9 @@ static int client_common_fill_super(struct super_block *sb, char *md, char *dt, /* OBD_CONNECT_CKSUM should always be set, even if checksums are * disabled by default, because it can still be enabled on the - * fly via /proc. As a consequence, we still need to come to an - * agreement on the supported algorithms at connect time */ + * fly via /sys. As a consequence, we still need to come to an + * agreement on the supported algorithms at connect time + */ data->ocd_connect_flags |= OBD_CONNECT_CKSUM; if (OBD_FAIL_CHECK(OBD_FAIL_OSC_CKSUM_ADLER_ONLY)) @@ -459,13 +492,13 @@ static int client_common_fill_super(struct super_block *sb, char *md, char *dt, "ocd_grant: %d\n", data->ocd_connect_flags, data->ocd_version, data->ocd_grant); - obd->obd_upcall.onu_owner = &sbi->ll_lco; - obd->obd_upcall.onu_upcall = cl_ocd_update; + sbi->ll_dt_obd->obd_upcall.onu_owner = &sbi->ll_lco; + sbi->ll_dt_obd->obd_upcall.onu_upcall = cl_ocd_update; data->ocd_brw_size = DT_MAX_BRW_SIZE; - err = obd_connect(NULL, &sbi->ll_dt_exp, obd, &sbi->ll_sb_uuid, data, - NULL); + err = obd_connect(NULL, &sbi->ll_dt_exp, sbi->ll_dt_obd, + &sbi->ll_sb_uuid, data, sbi->ll_cache); if (err == -EBUSY) { LCONSOLE_ERROR_MSG(0x150, "An OST (dt %s) is performing " "recovery, of which this client is not a " @@ -481,10 +514,15 @@ static int client_common_fill_super(struct super_block *sb, char *md, char *dt, sbi->ll_dt_exp->exp_connect_data = *data; /* Don't change value if it was specified in the config log */ - if (sbi->ll_ra_info.ra_max_read_ahead_whole_pages == -1) + if (sbi->ll_ra_info.ra_max_read_ahead_whole_pages == -1) { sbi->ll_ra_info.ra_max_read_ahead_whole_pages = max_t(unsigned long, SBI_DEFAULT_READAHEAD_WHOLE_MAX, (data->ocd_brw_size >> PAGE_SHIFT)); + if (sbi->ll_ra_info.ra_max_read_ahead_whole_pages > + sbi->ll_ra_info.ra_max_pages_per_file) + sbi->ll_ra_info.ra_max_read_ahead_whole_pages = + sbi->ll_ra_info.ra_max_pages_per_file; + } err = obd_fid_init(sbi->ll_dt_exp->exp_obd, sbi->ll_dt_exp, LUSTRE_SEQ_METADATA); @@ -587,20 +625,12 @@ static int client_common_fill_super(struct super_block *sb, char *md, char *dt, } cl_sb_init(sb); - err = obd_set_info_async(NULL, sbi->ll_dt_exp, sizeof(KEY_CACHE_SET), - KEY_CACHE_SET, sizeof(*sbi->ll_cache), - sbi->ll_cache, NULL); - if (err) { - CERROR("%s: Set cache_set failed: rc = %d\n", - sbi->ll_dt_exp->exp_obd->obd_name, err); - GOTO(out_root, err); - } - sb->s_root = d_make_root(root); if (sb->s_root == NULL) { - CERROR("%s: can't make root dentry\n", - ll_get_fsname(sb, NULL, 0)); - GOTO(out_root, err = -ENOMEM); + err = -ENOMEM; + CERROR("%s: can't make root dentry: rc = %d\n", + sbi->ll_fsname, err); + GOTO(out_root, err); } #ifdef HAVE_DCACHE_LOCK sb->s_root->d_op = &ll_d_ops; @@ -622,17 +652,24 @@ static int client_common_fill_super(struct super_block *sb, char *md, char *dt, if (osfs != NULL) OBD_FREE_PTR(osfs); - if (sbi->ll_proc_root != NULL) { - err = lprocfs_ll_register_obd(sb, dt); + if (sbi->ll_dt_obd) { + err = sysfs_create_link(&sbi->ll_kset.kobj, + &sbi->ll_dt_obd->obd_kset.kobj, + sbi->ll_dt_obd->obd_type->typ_name); if (err < 0) { CERROR("%s: could not register %s in llite: rc = %d\n", - dt, ll_get_fsname(sb, NULL, 0), err); + dt, sbi->ll_fsname, err); err = 0; } - err = lprocfs_ll_register_obd(sb, md); + } + + if (sbi->ll_md_obd) { + err = sysfs_create_link(&sbi->ll_kset.kobj, + &sbi->ll_md_obd->obd_kset.kobj, + sbi->ll_md_obd->obd_type->typ_name); if (err < 0) { CERROR("%s: could not register %s in llite: rc = %d\n", - md, ll_get_fsname(sb, NULL, 0), err); + md, sbi->ll_fsname, err); err = 0; } } @@ -646,11 +683,13 @@ out_lock_cn_cb: out_dt: obd_disconnect(sbi->ll_dt_exp); sbi->ll_dt_exp = NULL; + sbi->ll_dt_obd = NULL; out_md_fid: obd_fid_fini(sbi->ll_md_exp->exp_obd); out_md: obd_disconnect(sbi->ll_md_exp); sbi->ll_md_exp = NULL; + sbi->ll_md_obd = NULL; out: if (data != NULL) OBD_FREE_PTR(data); @@ -672,12 +711,16 @@ int ll_get_max_mdsize(struct ll_sb_info *sbi, int *lmmsize) RETURN(rc); } + CDEBUG(D_INFO, "max LOV ea size: %d\n", *lmmsize); + size = sizeof(int); rc = obd_get_info(NULL, sbi->ll_md_exp, sizeof(KEY_MAX_EASIZE), KEY_MAX_EASIZE, &size, lmmsize); if (rc) CERROR("Get max mdsize error rc %d\n", rc); + CDEBUG(D_INFO, "max LMV ea size: %d\n", *lmmsize); + RETURN(rc); } @@ -756,8 +799,8 @@ void ll_kill_super(struct super_block *sb) struct ll_sb_info *sbi; ENTRY; - /* not init sb ?*/ - if (!(sb->s_flags & MS_ACTIVE)) + /* not init sb ?*/ + if (!(sb->s_flags & SB_ACTIVE)) return; sbi = ll_s2sbi(sb); @@ -771,7 +814,7 @@ void ll_kill_super(struct super_block *sb) /* wait running statahead threads to quit */ while (atomic_read(&sbi->ll_sa_running) > 0) { set_current_state(TASK_UNINTERRUPTIBLE); - schedule_timeout(msecs_to_jiffies(MSEC_PER_SEC >> 3)); + schedule_timeout(cfs_time_seconds(1 >> 3)); } } @@ -951,7 +994,7 @@ void ll_lli_init(struct ll_inode_info *lli) spin_lock_init(&lli->lli_sa_lock); lli->lli_opendir_pid = 0; lli->lli_sa_enabled = 0; - lli->lli_def_stripe_offset = -1; + init_rwsem(&lli->lli_lsm_sem); } else { mutex_init(&lli->lli_size_mutex); lli->lli_symlink_name = NULL; @@ -962,6 +1005,12 @@ void ll_lli_init(struct ll_inode_info *lli) INIT_LIST_HEAD(&lli->lli_agl_list); lli->lli_agl_index = 0; lli->lli_async_rc = 0; + spin_lock_init(&lli->lli_heat_lock); + obd_heat_clear(lli->lli_heat_instances, OBD_HEAT_COUNT); + lli->lli_heat_flags = 0; + mutex_init(&lli->lli_pcc_lock); + lli->lli_pcc_state = PCC_STATE_FL_NONE; + lli->lli_pcc_inode = NULL; } mutex_init(&lli->lli_layout_mutex); memset(lli->lli_jobid, 0, sizeof(lli->lli_jobid)); @@ -1012,49 +1061,72 @@ int ll_fill_super(struct super_block *sb, struct vfsmount *mnt) char *profilenm = get_profile_name(sb); struct config_llog_instance *cfg; /* %p for void* in printf needs 16+2 characters: 0xffffffffffffffff */ - const int instlen = sizeof(cfg->cfg_instance) * 2 + 2; + const int instlen = 16 + 2; + unsigned long cfg_instance = ll_get_cfg_instance(sb); char name[MAX_STRING_SIZE]; int md_len = 0; int dt_len = 0; + uuid_t uuid; char *ptr; int len; int err; ENTRY; - CDEBUG(D_VFSTRACE, "VFS Op: sb %p\n", sb); + /* for ASLR, to map between cfg_instance and hashed ptr */ + CDEBUG(D_VFSTRACE, "VFS Op: cfg_instance %s-%016lx (sb %p)\n", + profilenm, cfg_instance, sb); try_module_get(THIS_MODULE); OBD_ALLOC_PTR(cfg); if (cfg == NULL) - GOTO(out_free, err = -ENOMEM); + GOTO(out_free_cfg, err = -ENOMEM); /* client additional sb info */ lsi->lsi_llsbi = sbi = ll_init_sbi(); - if (!sbi) - GOTO(out_free, err = -ENOMEM); + if (IS_ERR(sbi)) + GOTO(out_free_cfg, err = PTR_ERR(sbi)); err = ll_options(lsi->lsi_lmd->lmd_opts, sbi); if (err) - GOTO(out_free, err); - - err = super_setup_bdi_name(sb, "lustre-%p", sb); - if (err) - GOTO(out_free, err); + GOTO(out_free_cfg, err); #ifndef HAVE_DCACHE_LOCK /* kernel >= 2.6.38 store dentry operations in sb->s_d_op. */ sb->s_d_op = &ll_d_ops; #endif + /* UUID handling */ + generate_random_uuid(uuid.b); + snprintf(sbi->ll_sb_uuid.uuid, UUID_SIZE, "%pU", uuid.b); + + CDEBUG(D_CONFIG, "llite sb uuid: %s\n", sbi->ll_sb_uuid.uuid); + /* Get fsname */ - len = strlen(lsi->lsi_lmd->lmd_profile); - ptr = strrchr(lsi->lsi_lmd->lmd_profile, '-'); + len = strlen(profilenm); + ptr = strrchr(profilenm, '-'); if (ptr && (strcmp(ptr, "-client") == 0)) len -= 7; + if (len > LUSTRE_MAXFSNAME) { + if (unlikely(len >= MAX_STRING_SIZE)) + len = MAX_STRING_SIZE - 1; + strncpy(name, profilenm, len); + name[len] = '\0'; + err = -ENAMETOOLONG; + CERROR("%s: fsname longer than %u characters: rc = %d\n", + name, LUSTRE_MAXFSNAME, err); + GOTO(out_free_cfg, err); + } + strncpy(sbi->ll_fsname, profilenm, len); + sbi->ll_fsname[len] = '\0'; + /* Mount info */ - snprintf(name, MAX_STRING_SIZE, "%.*s-%p", len, - lsi->lsi_lmd->lmd_profile, sb); + snprintf(name, sizeof(name), "%.*s-%016lx", len, + profilenm, cfg_instance); + + err = super_setup_bdi_name(sb, "%s", name); + if (err) + GOTO(out_free_cfg, err); /* Call ll_debugfs_register_super() before lustre_process_log() * so that "llite.*.*" params can be processed correctly. @@ -1062,21 +1134,21 @@ int ll_fill_super(struct super_block *sb, struct vfsmount *mnt) err = ll_debugfs_register_super(sb, name); if (err < 0) { CERROR("%s: could not register mountpoint in llite: rc = %d\n", - ll_get_fsname(sb, NULL, 0), err); + sbi->ll_fsname, err); err = 0; } - /* Generate a string unique to this super, in case some joker tries - to mount the same fs at two mount points. - Use the address of the super itself.*/ - cfg->cfg_instance = sb; + /* The cfg_instance is a value unique to this super, in case some + * joker tries to mount the same fs at two mount points. + */ + cfg->cfg_instance = cfg_instance; cfg->cfg_uuid = lsi->lsi_llsbi->ll_sb_uuid; cfg->cfg_callback = class_config_llog_handler; cfg->cfg_sub_clds = CONFIG_SUB_CLIENT; /* set up client obds */ err = lustre_process_log(sb, profilenm, cfg); if (err < 0) - GOTO(out_proc, err); + GOTO(out_debugfs, err); /* Profile set with LCFG_MOUNTOPT so we can find our mdc and osc obds */ lprof = class_get_profile(profilenm); @@ -1084,7 +1156,7 @@ int ll_fill_super(struct super_block *sb, struct vfsmount *mnt) LCONSOLE_ERROR_MSG(0x156, "The client profile '%s' could not be" " read from the MGS. Does that filesystem " "exist?\n", profilenm); - GOTO(out_proc, err = -EINVAL); + GOTO(out_debugfs, err = -EINVAL); } CDEBUG(D_CONFIG, "Found profile %s: mdc=%s osc=%s\n", profilenm, lprof->lp_md, lprof->lp_dt); @@ -1092,34 +1164,38 @@ int ll_fill_super(struct super_block *sb, struct vfsmount *mnt) dt_len = strlen(lprof->lp_dt) + instlen + 2; OBD_ALLOC(dt, dt_len); if (!dt) - GOTO(out_proc, err = -ENOMEM); - snprintf(dt, dt_len - 1, "%s-%p", lprof->lp_dt, cfg->cfg_instance); + GOTO(out_profile, err = -ENOMEM); + snprintf(dt, dt_len - 1, "%s-%016lx", lprof->lp_dt, cfg_instance); md_len = strlen(lprof->lp_md) + instlen + 2; OBD_ALLOC(md, md_len); if (!md) - GOTO(out_proc, err = -ENOMEM); - snprintf(md, md_len - 1, "%s-%p", lprof->lp_md, cfg->cfg_instance); + GOTO(out_free_dt, err = -ENOMEM); + snprintf(md, md_len - 1, "%s-%016lx", lprof->lp_md, cfg_instance); /* connections, registrations, sb setup */ err = client_common_fill_super(sb, md, dt, mnt); if (err < 0) - GOTO(out_proc, err); + GOTO(out_free_md, err); sbi->ll_client_common_fill_super_succeeded = 1; -out_proc: - if (err < 0) - ll_debugfs_unregister_super(sb); -out_free: +out_free_md: if (md) OBD_FREE(md, md_len); +out_free_dt: if (dt) OBD_FREE(dt, dt_len); - if (lprof != NULL) +out_profile: + if (lprof) class_put_profile(lprof); +out_debugfs: + if (err < 0) + ll_debugfs_unregister_super(sb); +out_free_cfg: if (cfg) OBD_FREE_PTR(cfg); + if (err) ll_put_super(sb); else if (sbi->ll_flags & LL_SBI_VERBOSE) @@ -1130,23 +1206,26 @@ out_free: void ll_put_super(struct super_block *sb) { struct config_llog_instance cfg, params_cfg; - struct obd_device *obd; - struct lustre_sb_info *lsi = s2lsi(sb); - struct ll_sb_info *sbi = ll_s2sbi(sb); - char *profilenm = get_profile_name(sb); + struct obd_device *obd; + struct lustre_sb_info *lsi = s2lsi(sb); + struct ll_sb_info *sbi = ll_s2sbi(sb); + char *profilenm = get_profile_name(sb); + unsigned long cfg_instance = ll_get_cfg_instance(sb); long ccc_count; int next, force = 1, rc = 0; - ENTRY; + ENTRY; - if (!sbi) + if (IS_ERR(sbi)) GOTO(out_no_sbi, 0); - CDEBUG(D_VFSTRACE, "VFS Op: sb %p - %s\n", sb, profilenm); + /* Should replace instance_id with something better for ASLR */ + CDEBUG(D_VFSTRACE, "VFS Op: cfg_instance %s-%016lx (sb %p)\n", + profilenm, cfg_instance, sb); - cfg.cfg_instance = sb; - lustre_end_log(sb, profilenm, &cfg); + cfg.cfg_instance = cfg_instance; + lustre_end_log(sb, profilenm, &cfg); - params_cfg.cfg_instance = sb; + params_cfg.cfg_instance = cfg_instance; lustre_end_log(sb, PARAMS_FILENAME, ¶ms_cfg); if (sbi->ll_md_exp) { @@ -1167,7 +1246,6 @@ void ll_put_super(struct super_block *sb) if (force == 0 && rc != -EINTR) LASSERTF(ccc_count == 0, "count: %li\n", ccc_count); - /* We need to set force before the lov_disconnect in lustre_common_put_super, since l_d cleans up osc's as well. */ if (force) { @@ -1244,10 +1322,15 @@ void ll_dir_clear_lsm_md(struct inode *inode) LASSERT(S_ISDIR(inode->i_mode)); - if (lli->lli_lsm_md != NULL) { + if (lli->lli_lsm_md) { lmv_free_memmd(lli->lli_lsm_md); lli->lli_lsm_md = NULL; } + + if (lli->lli_default_lsm_md) { + lmv_free_memmd(lli->lli_default_lsm_md); + lli->lli_default_lsm_md = NULL; + } } static struct inode *ll_iget_anon_dir(struct super_block *sb, @@ -1264,7 +1347,7 @@ static struct inode *ll_iget_anon_dir(struct super_block *sb, inode = iget_locked(sb, ino); if (inode == NULL) { CERROR("%s: failed get simple inode "DFID": rc = -ENOENT\n", - ll_get_fsname(sb, NULL, 0), PFID(fid)); + sbi->ll_fsname, PFID(fid)); RETURN(ERR_PTR(-ENOENT)); } @@ -1277,9 +1360,9 @@ static struct inode *ll_iget_anon_dir(struct super_block *sb, LASSERTF(S_ISDIR(inode->i_mode), "Not slave inode "DFID"\n", PFID(fid)); - LTIME_S(inode->i_mtime) = 0; - LTIME_S(inode->i_atime) = 0; - LTIME_S(inode->i_ctime) = 0; + inode->i_mtime.tv_sec = 0; + inode->i_atime.tv_sec = 0; + inode->i_ctime.tv_sec = 0; inode->i_rdev = 0; #ifdef HAVE_BACKING_DEV_INFO @@ -1307,15 +1390,28 @@ static int ll_init_lsm_md(struct inode *inode, struct lustre_md *md) { struct lu_fid *fid; struct lmv_stripe_md *lsm = md->lmv; + struct ll_inode_info *lli = ll_i2info(inode); int i; LASSERT(lsm != NULL); + + CDEBUG(D_INODE, "%s: "DFID" set dir layout:\n", + ll_i2sbi(inode)->ll_fsname, PFID(&lli->lli_fid)); + lsm_md_dump(D_INODE, lsm); + + if (!lmv_dir_striped(lsm)) + goto out; + /* XXX sigh, this lsm_root initialization should be in * LMV layer, but it needs ll_iget right now, so we * put this here right now. */ for (i = 0; i < lsm->lsm_md_stripe_count; i++) { fid = &lsm->lsm_md_oinfo[i].lmo_fid; LASSERT(lsm->lsm_md_oinfo[i].lmo_root == NULL); + + if (!fid_is_sane(fid)) + continue; + /* Unfortunately ll_iget will call ll_update_inode, * where the initialization of slave inode is slightly * different, so it reset lsm_md to NULL to avoid @@ -1326,24 +1422,75 @@ static int ll_init_lsm_md(struct inode *inode, struct lustre_md *md) int rc = PTR_ERR(lsm->lsm_md_oinfo[i].lmo_root); lsm->lsm_md_oinfo[i].lmo_root = NULL; + while (i-- > 0) { + iput(lsm->lsm_md_oinfo[i].lmo_root); + lsm->lsm_md_oinfo[i].lmo_root = NULL; + } return rc; } } +out: + lli->lli_lsm_md = lsm; return 0; } +static void ll_update_default_lsm_md(struct inode *inode, struct lustre_md *md) +{ + struct ll_inode_info *lli = ll_i2info(inode); + + if (!md->default_lmv) { + /* clear default lsm */ + if (lli->lli_default_lsm_md) { + down_write(&lli->lli_lsm_sem); + if (lli->lli_default_lsm_md) { + lmv_free_memmd(lli->lli_default_lsm_md); + lli->lli_default_lsm_md = NULL; + } + up_write(&lli->lli_lsm_sem); + } + } else if (lli->lli_default_lsm_md) { + /* update default lsm if it changes */ + down_read(&lli->lli_lsm_sem); + if (lli->lli_default_lsm_md && + !lsm_md_eq(lli->lli_default_lsm_md, md->default_lmv)) { + up_read(&lli->lli_lsm_sem); + down_write(&lli->lli_lsm_sem); + if (lli->lli_default_lsm_md) + lmv_free_memmd(lli->lli_default_lsm_md); + lli->lli_default_lsm_md = md->default_lmv; + lsm_md_dump(D_INODE, md->default_lmv); + md->default_lmv = NULL; + up_write(&lli->lli_lsm_sem); + } else { + up_read(&lli->lli_lsm_sem); + } + } else { + /* init default lsm */ + down_write(&lli->lli_lsm_sem); + lli->lli_default_lsm_md = md->default_lmv; + lsm_md_dump(D_INODE, md->default_lmv); + md->default_lmv = NULL; + up_write(&lli->lli_lsm_sem); + } +} + static int ll_update_lsm_md(struct inode *inode, struct lustre_md *md) { struct ll_inode_info *lli = ll_i2info(inode); struct lmv_stripe_md *lsm = md->lmv; - int rc; + int rc = 0; + ENTRY; LASSERT(S_ISDIR(inode->i_mode)); CDEBUG(D_INODE, "update lsm %p of "DFID"\n", lli->lli_lsm_md, PFID(ll_inode2fid(inode))); + /* update default LMV */ + if (md->default_lmv) + ll_update_default_lsm_md(inode, md); + /* * no striped information from request, lustre_md from req does not * include stripeEA, see ll_md_setattr() @@ -1351,75 +1498,71 @@ static int ll_update_lsm_md(struct inode *inode, struct lustre_md *md) if (!lsm) RETURN(0); - /* Compare the old and new stripe information */ + /* + * normally dir layout doesn't change, only take read lock to check + * that to avoid blocking other MD operations. + */ + if (lli->lli_lsm_md) + down_read(&lli->lli_lsm_sem); + else + down_write(&lli->lli_lsm_sem); + + /* + * if dir layout mismatch, check whether version is increased, which + * means layout is changed, this happens in dir migration and lfsck. + * + * foreign LMV should not change. + */ if (lli->lli_lsm_md && !lsm_md_eq(lli->lli_lsm_md, lsm)) { - struct lmv_stripe_md *old_lsm = lli->lli_lsm_md; - int idx; - bool layout_changed = lsm->lsm_md_layout_version > - old_lsm->lsm_md_layout_version; - - int mask = layout_changed ? D_INODE : D_ERROR; - - CDEBUG(mask, - "%s: inode@%p "DFID" lmv layout %s magic %#x/%#x " - "stripe count %d/%d master_mdt %d/%d " - "hash_type %#x/%#x version %d/%d migrate offset %d/%d " - "migrate hash %#x/%#x pool %s/%s\n", - ll_get_fsname(inode->i_sb, NULL, 0), inode, - PFID(&lli->lli_fid), - layout_changed ? "changed" : "mismatch", - lsm->lsm_md_magic, old_lsm->lsm_md_magic, - lsm->lsm_md_stripe_count, - old_lsm->lsm_md_stripe_count, - lsm->lsm_md_master_mdt_index, - old_lsm->lsm_md_master_mdt_index, - lsm->lsm_md_hash_type, old_lsm->lsm_md_hash_type, - lsm->lsm_md_layout_version, - old_lsm->lsm_md_layout_version, - lsm->lsm_md_migrate_offset, - old_lsm->lsm_md_migrate_offset, - lsm->lsm_md_migrate_hash, - old_lsm->lsm_md_migrate_hash, - lsm->lsm_md_pool_name, - old_lsm->lsm_md_pool_name); - - for (idx = 0; idx < old_lsm->lsm_md_stripe_count; idx++) - CDEBUG(mask, "old stripe[%d] "DFID"\n", - idx, PFID(&old_lsm->lsm_md_oinfo[idx].lmo_fid)); - - for (idx = 0; idx < lsm->lsm_md_stripe_count; idx++) - CDEBUG(mask, "new stripe[%d] "DFID"\n", - idx, PFID(&lsm->lsm_md_oinfo[idx].lmo_fid)); - - if (!layout_changed) - RETURN(-EINVAL); + if (lmv_dir_striped(lli->lli_lsm_md) && + lsm->lsm_md_layout_version <= + lli->lli_lsm_md->lsm_md_layout_version) { + CERROR("%s: "DFID" dir layout mismatch:\n", + ll_i2sbi(inode)->ll_fsname, + PFID(&lli->lli_fid)); + lsm_md_dump(D_ERROR, lli->lli_lsm_md); + lsm_md_dump(D_ERROR, lsm); + GOTO(unlock, rc = -EINVAL); + } + /* layout changed, switch to write lock */ + up_read(&lli->lli_lsm_sem); + down_write(&lli->lli_lsm_sem); ll_dir_clear_lsm_md(inode); } - /* set the directory layout */ + /* set directory layout */ if (!lli->lli_lsm_md) { struct cl_attr *attr; rc = ll_init_lsm_md(inode, md); + up_write(&lli->lli_lsm_sem); if (rc != 0) RETURN(rc); /* set md->lmv to NULL, so the following free lustre_md * will not free this lsm */ md->lmv = NULL; - lli->lli_lsm_md = lsm; + + /* + * md_merge_attr() may take long, since lsm is already set, + * switch to read lock. + */ + down_read(&lli->lli_lsm_sem); + + if (!lmv_dir_striped(lli->lli_lsm_md)) + GOTO(unlock, rc); OBD_ALLOC_PTR(attr); if (attr == NULL) - RETURN(-ENOMEM); + GOTO(unlock, rc = -ENOMEM); /* validate the lsm */ rc = md_merge_attr(ll_i2mdexp(inode), lsm, attr, ll_md_blocking_ast); if (rc != 0) { OBD_FREE_PTR(attr); - RETURN(rc); + GOTO(unlock, rc); } if (md->body->mbo_valid & OBD_MD_FLNLINK) @@ -1434,66 +1577,31 @@ static int ll_update_lsm_md(struct inode *inode, struct lustre_md *md) md->body->mbo_mtime = attr->cat_mtime; OBD_FREE_PTR(attr); - - CDEBUG(D_INODE, "Set lsm %p magic %x to "DFID"\n", lsm, - lsm->lsm_md_magic, PFID(ll_inode2fid(inode))); - RETURN(0); - } - - /* Compare the old and new stripe information */ - if (!lsm_md_eq(lli->lli_lsm_md, lsm)) { - struct lmv_stripe_md *old_lsm = lli->lli_lsm_md; - int idx; - - CERROR("%s: inode "DFID"(%p)'s lmv layout mismatch (%p)/(%p)" - "magic:0x%x/0x%x stripe count: %d/%d master_mdt: %d/%d" - "hash_type:0x%x/0x%x layout: 0x%x/0x%x pool:%s/%s\n", - ll_get_fsname(inode->i_sb, NULL, 0), PFID(&lli->lli_fid), - inode, lsm, old_lsm, - lsm->lsm_md_magic, old_lsm->lsm_md_magic, - lsm->lsm_md_stripe_count, - old_lsm->lsm_md_stripe_count, - lsm->lsm_md_master_mdt_index, - old_lsm->lsm_md_master_mdt_index, - lsm->lsm_md_hash_type, old_lsm->lsm_md_hash_type, - lsm->lsm_md_layout_version, - old_lsm->lsm_md_layout_version, - lsm->lsm_md_pool_name, - old_lsm->lsm_md_pool_name); - - for (idx = 0; idx < old_lsm->lsm_md_stripe_count; idx++) { - CERROR("%s: sub FIDs in old lsm idx %d, old: "DFID"\n", - ll_get_fsname(inode->i_sb, NULL, 0), idx, - PFID(&old_lsm->lsm_md_oinfo[idx].lmo_fid)); - } - - for (idx = 0; idx < lsm->lsm_md_stripe_count; idx++) { - CERROR("%s: sub FIDs in new lsm idx %d, new: "DFID"\n", - ll_get_fsname(inode->i_sb, NULL, 0), idx, - PFID(&lsm->lsm_md_oinfo[idx].lmo_fid)); - } - - RETURN(-EIO); } +unlock: + up_read(&lli->lli_lsm_sem); - RETURN(0); + RETURN(rc); } void ll_clear_inode(struct inode *inode) { struct ll_inode_info *lli = ll_i2info(inode); struct ll_sb_info *sbi = ll_i2sbi(inode); + ENTRY; CDEBUG(D_VFSTRACE, "VFS Op:inode="DFID"(%p)\n", PFID(ll_inode2fid(inode)), inode); - if (S_ISDIR(inode->i_mode)) { - /* these should have been cleared in ll_file_release */ - LASSERT(lli->lli_opendir_key == NULL); - LASSERT(lli->lli_sai == NULL); - LASSERT(lli->lli_opendir_pid == 0); - } + if (S_ISDIR(inode->i_mode)) { + /* these should have been cleared in ll_file_release */ + LASSERT(lli->lli_opendir_key == NULL); + LASSERT(lli->lli_sai == NULL); + LASSERT(lli->lli_opendir_pid == 0); + } else { + pcc_inode_free(inode); + } md_null_inode(sbi->ll_md_exp, ll_inode2fid(inode)); @@ -1519,7 +1627,6 @@ void ll_clear_inode(struct inode *inode) #ifdef CONFIG_FS_POSIX_ACL forget_all_cached_acls(inode); if (lli->lli_posix_acl) { - LASSERT(atomic_read(&lli->lli_posix_acl->a_refcount) == 1); posix_acl_release(lli->lli_posix_acl); lli->lli_posix_acl = NULL; } @@ -1620,11 +1727,12 @@ int ll_setattr_raw(struct dentry *dentry, struct iattr *attr, struct ll_inode_info *lli = ll_i2info(inode); struct md_op_data *op_data = NULL; int rc = 0; + ENTRY; CDEBUG(D_VFSTRACE, "%s: setattr inode "DFID"(%p) from %llu to %llu, " "valid %x, hsm_import %d\n", - ll_get_fsname(inode->i_sb, NULL, 0), PFID(&lli->lli_fid), + ll_i2sbi(inode)->ll_fsname, PFID(&lli->lli_fid), inode, i_size_read(inode), attr->ia_size, attr->ia_valid, hsm_import); @@ -1672,9 +1780,9 @@ int ll_setattr_raw(struct dentry *dentry, struct iattr *attr, } if (attr->ia_valid & (ATTR_MTIME | ATTR_CTIME)) - CDEBUG(D_INODE, "setting mtime %lu, ctime %lu, now = %llu\n", - LTIME_S(attr->ia_mtime), LTIME_S(attr->ia_ctime), - (s64)ktime_get_real_seconds()); + CDEBUG(D_INODE, "setting mtime %lld, ctime %lld, now = %lld\n", + (s64)attr->ia_mtime.tv_sec, (s64)attr->ia_ctime.tv_sec, + ktime_get_real_seconds()); if (S_ISREG(inode->i_mode)) { if (attr->ia_valid & ATTR_SIZE) @@ -1718,14 +1826,28 @@ int ll_setattr_raw(struct dentry *dentry, struct iattr *attr, if (attr->ia_valid & (ATTR_SIZE | ATTR_ATIME | ATTR_ATIME_SET | ATTR_MTIME | ATTR_MTIME_SET | ATTR_CTIME) || xvalid & OP_XVALID_CTIME_SET) { - /* For truncate and utimes sending attributes to OSTs, setting - * mtime/atime to the past will be performed under PW [0:EOF] - * extent lock (new_size:EOF for truncate). It may seem - * excessive to send mtime/atime updates to OSTs when not - * setting times to past, but it is necessary due to possible - * time de-synchronization between MDT inode and OST objects - */ - rc = cl_setattr_ost(lli->lli_clob, attr, xvalid, 0); + bool cached = false; + + rc = pcc_inode_setattr(inode, attr, &cached); + if (cached) { + if (rc) { + CERROR("%s: PCC inode "DFID" setattr failed: " + "rc = %d\n", + ll_i2sbi(inode)->ll_fsname, + PFID(&lli->lli_fid), rc); + GOTO(out, rc); + } + } else { + /* For truncate and utimes sending attributes to OSTs, + * setting mtime/atime to the past will be performed + * under PW [0:EOF] extent lock (new_size:EOF for + * truncate). It may seem excessive to send mtime/atime + * updates to OSTs when not setting times to past, but + * it is necessary due to possible time + * de-synchronization between MDT inode and OST objects + */ + rc = cl_setattr_ost(lli->lli_clob, attr, xvalid, 0); + } } /* If the file was restored, it needs to set dirty flag. @@ -1816,57 +1938,54 @@ int ll_setattr(struct dentry *de, struct iattr *attr) int ll_statfs_internal(struct ll_sb_info *sbi, struct obd_statfs *osfs, u32 flags) { - struct obd_statfs obd_osfs; + struct obd_statfs obd_osfs = { 0 }; time64_t max_age; int rc; ENTRY; - max_age = ktime_get_seconds() - OBD_STATFS_CACHE_SECONDS; + max_age = ktime_get_seconds() - sbi->ll_statfs_max_age; - rc = obd_statfs(NULL, sbi->ll_md_exp, osfs, max_age, flags); - if (rc) { - CERROR("md_statfs fails: rc = %d\n", rc); - RETURN(rc); - } + rc = obd_statfs(NULL, sbi->ll_md_exp, osfs, max_age, flags); + if (rc) + RETURN(rc); osfs->os_type = LL_SUPER_MAGIC; CDEBUG(D_SUPER, "MDC blocks %llu/%llu objects %llu/%llu\n", - osfs->os_bavail, osfs->os_blocks, osfs->os_ffree,osfs->os_files); + osfs->os_bavail, osfs->os_blocks, osfs->os_ffree, osfs->os_files); if (osfs->os_state & OS_STATE_SUM) GOTO(out, rc); - if (sbi->ll_flags & LL_SBI_LAZYSTATFS) - flags |= OBD_STATFS_NODELAY; + if (sbi->ll_flags & LL_SBI_LAZYSTATFS) + flags |= OBD_STATFS_NODELAY; rc = obd_statfs(NULL, sbi->ll_dt_exp, &obd_osfs, max_age, flags); - if (rc) { - CERROR("obd_statfs fails: rc = %d\n", rc); - RETURN(rc); - } + if (rc) /* Possibly a filesystem with no OSTs. Report MDT totals. */ + GOTO(out, rc = 0); CDEBUG(D_SUPER, "OSC blocks %llu/%llu objects %llu/%llu\n", - obd_osfs.os_bavail, obd_osfs.os_blocks, obd_osfs.os_ffree, - obd_osfs.os_files); - - osfs->os_bsize = obd_osfs.os_bsize; - osfs->os_blocks = obd_osfs.os_blocks; - osfs->os_bfree = obd_osfs.os_bfree; - osfs->os_bavail = obd_osfs.os_bavail; - - /* If we don't have as many objects free on the OST as inodes - * on the MDS, we reduce the total number of inodes to - * compensate, so that the "inodes in use" number is correct. - */ - if (obd_osfs.os_ffree < osfs->os_ffree) { - osfs->os_files = (osfs->os_files - osfs->os_ffree) + - obd_osfs.os_ffree; - osfs->os_ffree = obd_osfs.os_ffree; - } + obd_osfs.os_bavail, obd_osfs.os_blocks, obd_osfs.os_ffree, + obd_osfs.os_files); + + osfs->os_bsize = obd_osfs.os_bsize; + osfs->os_blocks = obd_osfs.os_blocks; + osfs->os_bfree = obd_osfs.os_bfree; + osfs->os_bavail = obd_osfs.os_bavail; + + /* If we have _some_ OSTs, but don't have as many free objects on the + * OSTs as inodes on the MDTs, reduce the reported number of inodes + * to compensate, so that the "inodes in use" number is correct. + * This should be kept in sync with lod_statfs() behaviour. + */ + if (obd_osfs.os_files && obd_osfs.os_ffree < osfs->os_ffree) { + osfs->os_files = (osfs->os_files - osfs->os_ffree) + + obd_osfs.os_ffree; + osfs->os_ffree = obd_osfs.os_ffree; + } out: - RETURN(rc); + RETURN(rc); } int ll_statfs(struct dentry *de, struct kstatfs *sfs) { @@ -1876,7 +1995,7 @@ int ll_statfs(struct dentry *de, struct kstatfs *sfs) int rc; CDEBUG(D_VFSTRACE, "VFS Op: at %llu jiffies\n", get_jiffies_64()); - ll_stats_ops_tally(ll_s2sbi(sb), LPROC_LL_STAFS, 1); + ll_stats_ops_tally(ll_s2sbi(sb), LPROC_LL_STATFS, 1); /* Some amount of caching on the client is allowed */ rc = ll_statfs_internal(ll_s2sbi(sb), &osfs, OBD_STATFS_SUM); @@ -1967,24 +2086,25 @@ int ll_update_inode(struct inode *inode, struct lustre_md *md) inode->i_generation = cl_fid_build_gen(&body->mbo_fid1); if (body->mbo_valid & OBD_MD_FLATIME) { - if (body->mbo_atime > LTIME_S(inode->i_atime)) - LTIME_S(inode->i_atime) = body->mbo_atime; + if (body->mbo_atime > inode->i_atime.tv_sec) + inode->i_atime.tv_sec = body->mbo_atime; lli->lli_atime = body->mbo_atime; } if (body->mbo_valid & OBD_MD_FLMTIME) { - if (body->mbo_mtime > LTIME_S(inode->i_mtime)) { - CDEBUG(D_INODE, "setting ino %lu mtime from %lu " - "to %llu\n", inode->i_ino, - LTIME_S(inode->i_mtime), body->mbo_mtime); - LTIME_S(inode->i_mtime) = body->mbo_mtime; + if (body->mbo_mtime > inode->i_mtime.tv_sec) { + CDEBUG(D_INODE, + "setting ino %lu mtime from %lld to %llu\n", + inode->i_ino, (s64)inode->i_mtime.tv_sec, + body->mbo_mtime); + inode->i_mtime.tv_sec = body->mbo_mtime; } lli->lli_mtime = body->mbo_mtime; } if (body->mbo_valid & OBD_MD_FLCTIME) { - if (body->mbo_ctime > LTIME_S(inode->i_ctime)) - LTIME_S(inode->i_ctime) = body->mbo_ctime; + if (body->mbo_ctime > inode->i_ctime.tv_sec) + inode->i_ctime.tv_sec = body->mbo_ctime; lli->lli_ctime = body->mbo_ctime; } @@ -2070,11 +2190,12 @@ int ll_read_inode2(struct inode *inode, void *opaque) /* Core attributes from the MDS first. This is a new inode, and * the VFS doesn't zero times in the core inode so we have to do * it ourselves. They will be overwritten by either MDS or OST - * attributes - we just need to make sure they aren't newer. */ - LTIME_S(inode->i_mtime) = 0; - LTIME_S(inode->i_atime) = 0; - LTIME_S(inode->i_ctime) = 0; - inode->i_rdev = 0; + * attributes - we just need to make sure they aren't newer. + */ + inode->i_mtime.tv_sec = 0; + inode->i_atime.tv_sec = 0; + inode->i_ctime.tv_sec = 0; + inode->i_rdev = 0; rc = ll_update_inode(inode, md); if (rc != 0) RETURN(rc); @@ -2113,18 +2234,41 @@ int ll_read_inode2(struct inode *inode, void *opaque) void ll_delete_inode(struct inode *inode) { struct ll_inode_info *lli = ll_i2info(inode); + struct address_space *mapping = &inode->i_data; + unsigned long nrpages; ENTRY; - if (S_ISREG(inode->i_mode) && lli->lli_clob != NULL) + if (S_ISREG(inode->i_mode) && lli->lli_clob != NULL) { /* It is last chance to write out dirty pages, - * otherwise we may lose data while umount */ - cl_sync_file_range(inode, 0, OBD_OBJECT_EOF, CL_FSYNC_LOCAL, 1); - - truncate_inode_pages_final(&inode->i_data); + * otherwise we may lose data while umount. + * + * If i_nlink is 0 then just discard data. This is safe because + * local inode gets i_nlink 0 from server only for the last + * unlink, so that file is not opened somewhere else + */ + cl_sync_file_range(inode, 0, OBD_OBJECT_EOF, inode->i_nlink ? + CL_FSYNC_LOCAL : CL_FSYNC_DISCARD, 1); + } + truncate_inode_pages_final(mapping); - LASSERTF(inode->i_data.nrpages == 0, "inode="DFID"(%p) nrpages=%lu, " + /* Workaround for LU-118: Note nrpages may not be totally updated when + * truncate_inode_pages() returns, as there can be a page in the process + * of deletion (inside __delete_from_page_cache()) in the specified + * range. Thus mapping->nrpages can be non-zero when this function + * returns even after truncation of the whole mapping. Only do this if + * npages isn't already zero. + */ + nrpages = mapping->nrpages; + if (nrpages) { + xa_lock_irq(&mapping->i_pages); + nrpages = mapping->nrpages; + xa_unlock_irq(&mapping->i_pages); + } /* Workaround end */ + + LASSERTF(nrpages == 0, "%s: inode="DFID"(%p) nrpages=%lu, " "see https://jira.whamcloud.com/browse/LU-118\n", - PFID(ll_inode2fid(inode)), inode, inode->i_data.nrpages); + ll_i2sbi(inode)->ll_fsname, + PFID(ll_inode2fid(inode)), inode, nrpages); #ifdef HAVE_SBOPS_EVICT_INODE ll_clear_inode(inode); @@ -2175,10 +2319,19 @@ int ll_iocontrol(struct inode *inode, struct file *file, struct iattr *attr; struct md_op_data *op_data; struct cl_object *obj; + struct fsxattr fa = { 0 }; if (get_user(flags, (int __user *)arg)) RETURN(-EFAULT); + fa.fsx_projid = ll_i2info(inode)->lli_projid; + if (flags & LUSTRE_PROJINHERIT_FL) + fa.fsx_xflags = FS_XFLAG_PROJINHERIT; + + rc = ll_ioctl_check_project(inode, &fa); + if (rc) + RETURN(rc); + op_data = ll_prep_md_op_data(NULL, inode, NULL, NULL, 0, 0, LUSTRE_OPC_ANY, NULL); if (IS_ERR(op_data)) @@ -2286,34 +2439,34 @@ void ll_umount_begin(struct super_block *sb) int ll_remount_fs(struct super_block *sb, int *flags, char *data) { - struct ll_sb_info *sbi = ll_s2sbi(sb); - char *profilenm = get_profile_name(sb); - int err; - __u32 read_only; - - if ((*flags & MS_RDONLY) != (sb->s_flags & MS_RDONLY)) { - read_only = *flags & MS_RDONLY; - err = obd_set_info_async(NULL, sbi->ll_md_exp, - sizeof(KEY_READ_ONLY), - KEY_READ_ONLY, sizeof(read_only), - &read_only, NULL); - if (err) { - LCONSOLE_WARN("Failed to remount %s %s (%d)\n", - profilenm, read_only ? - "read-only" : "read-write", err); - return err; - } + struct ll_sb_info *sbi = ll_s2sbi(sb); + char *profilenm = get_profile_name(sb); + int err; + __u32 read_only; + + if ((*flags & MS_RDONLY) != (sb->s_flags & SB_RDONLY)) { + read_only = *flags & MS_RDONLY; + err = obd_set_info_async(NULL, sbi->ll_md_exp, + sizeof(KEY_READ_ONLY), + KEY_READ_ONLY, sizeof(read_only), + &read_only, NULL); + if (err) { + LCONSOLE_WARN("Failed to remount %s %s (%d)\n", + profilenm, read_only ? + "read-only" : "read-write", err); + return err; + } - if (read_only) - sb->s_flags |= MS_RDONLY; - else - sb->s_flags &= ~MS_RDONLY; + if (read_only) + sb->s_flags |= SB_RDONLY; + else + sb->s_flags &= ~SB_RDONLY; - if (sbi->ll_flags & LL_SBI_VERBOSE) - LCONSOLE_WARN("Remounted %s %s\n", profilenm, - read_only ? "read-only" : "read-write"); - } - return 0; + if (sbi->ll_flags & LL_SBI_VERBOSE) + LCONSOLE_WARN("Remounted %s %s\n", profilenm, + read_only ? "read-only" : "read-write"); + } + return 0; } /** @@ -2343,8 +2496,7 @@ void ll_open_cleanup(struct super_block *sb, struct ptlrpc_request *open_req) OBD_ALLOC_PTR(op_data); if (op_data == NULL) { CWARN("%s: cannot allocate op_data to release open handle for " - DFID"\n", - ll_get_fsname(sb, NULL, 0), PFID(&body->mbo_fid1)); + DFID"\n", ll_s2sbi(sb)->ll_fsname, PFID(&body->mbo_fid1)); RETURN_EXIT; } @@ -2364,7 +2516,9 @@ int ll_prep_inode(struct inode **inode, struct ptlrpc_request *req, { struct ll_sb_info *sbi = NULL; struct lustre_md md = { NULL }; + bool default_lmv_deleted = false; int rc; + ENTRY; LASSERT(*inode || sb); @@ -2372,7 +2526,16 @@ int ll_prep_inode(struct inode **inode, struct ptlrpc_request *req, rc = md_get_lustre_md(sbi->ll_md_exp, req, sbi->ll_dt_exp, sbi->ll_md_exp, &md); if (rc != 0) - GOTO(cleanup, rc); + GOTO(out, rc); + + /* + * clear default_lmv only if intent_getattr reply doesn't contain it. + * but it needs to be done after iget, check this early because + * ll_update_lsm_md() may change md. + */ + if (it && (it->it_op & (IT_LOOKUP | IT_GETATTR)) && + S_ISDIR(md.body->mbo_mode) && !md.default_lmv) + default_lmv_deleted = true; if (*inode) { rc = ll_update_inode(*inode, &md); @@ -2387,7 +2550,7 @@ int ll_prep_inode(struct inode **inode, struct ptlrpc_request *req, */ if (!fid_is_sane(&md.body->mbo_fid1)) { CERROR("%s: Fid is insane "DFID"\n", - ll_get_fsname(sb, NULL, 0), + sbi->ll_fsname, PFID(&md.body->mbo_fid1)); GOTO(out, rc = -EINVAL); } @@ -2437,12 +2600,15 @@ int ll_prep_inode(struct inode **inode, struct ptlrpc_request *req, LDLM_LOCK_PUT(lock); } + if (default_lmv_deleted) + ll_update_default_lsm_md(*inode, &md); + GOTO(out, rc = 0); out: + /* cleanup will be done if necessary */ md_free_lustre_md(sbi->ll_md_exp, &md); -cleanup: if (rc != 0 && it != NULL && it->it_op & IT_OPEN) ll_open_cleanup(sb != NULL ? sb : (*inode)->i_sb, req); @@ -2492,11 +2658,29 @@ out_statfs: return rc; } +/* + * this is normally called in ll_fini_md_op_data(), but sometimes it needs to + * be called early to avoid deadlock. + */ +void ll_unlock_md_op_lsm(struct md_op_data *op_data) +{ + if (op_data->op_mea2_sem) { + up_read(op_data->op_mea2_sem); + op_data->op_mea2_sem = NULL; + } + + if (op_data->op_mea1_sem) { + up_read(op_data->op_mea1_sem); + op_data->op_mea1_sem = NULL; + } +} + /* this function prepares md_op_data hint for passing it down to MD stack. */ struct md_op_data *ll_prep_md_op_data(struct md_op_data *op_data, struct inode *i1, struct inode *i2, const char *name, size_t namelen, - __u32 mode, __u32 opc, void *data) + __u32 mode, enum md_op_code opc, + void *data) { LASSERT(i1 != NULL); @@ -2520,18 +2704,25 @@ struct md_op_data *ll_prep_md_op_data(struct md_op_data *op_data, ll_i2gids(op_data->op_suppgids, i1, i2); op_data->op_fid1 = *ll_inode2fid(i1); - op_data->op_default_stripe_offset = -1; + op_data->op_code = opc; + if (S_ISDIR(i1->i_mode)) { + down_read(&ll_i2info(i1)->lli_lsm_sem); + op_data->op_mea1_sem = &ll_i2info(i1)->lli_lsm_sem; op_data->op_mea1 = ll_i2info(i1)->lli_lsm_md; - if (opc == LUSTRE_OPC_MKDIR) - op_data->op_default_stripe_offset = - ll_i2info(i1)->lli_def_stripe_offset; + op_data->op_default_mea1 = ll_i2info(i1)->lli_default_lsm_md; } if (i2) { op_data->op_fid2 = *ll_inode2fid(i2); - if (S_ISDIR(i2->i_mode)) + if (S_ISDIR(i2->i_mode)) { + if (i2 != i1) { + down_read(&ll_i2info(i2)->lli_lsm_sem); + op_data->op_mea2_sem = + &ll_i2info(i2)->lli_lsm_sem; + } op_data->op_mea2 = ll_i2info(i2)->lli_lsm_md; + } } else { fid_zero(&op_data->op_fid2); } @@ -2561,6 +2752,7 @@ struct md_op_data *ll_prep_md_op_data(struct md_op_data *op_data, void ll_finish_md_op_data(struct md_op_data *op_data) { + ll_unlock_md_op_lsm(op_data); security_release_secctx(op_data->op_file_secctx, op_data->op_file_secctx_size); OBD_FREE_PTR(op_data); @@ -2632,39 +2824,6 @@ int ll_get_obd_name(struct inode *inode, unsigned int cmd, unsigned long arg) RETURN(0); } -/** - * Get lustre file system name by \a sbi. If \a buf is provided(non-NULL), the - * fsname will be returned in this buffer; otherwise, a static buffer will be - * used to store the fsname and returned to caller. - */ -char *ll_get_fsname(struct super_block *sb, char *buf, int buflen) -{ - static char fsname_static[MTI_NAME_MAXLEN]; - struct lustre_sb_info *lsi = s2lsi(sb); - char *ptr; - int len; - - if (buf == NULL) { - /* this means the caller wants to use static buffer - * and it doesn't care about race. Usually this is - * in error reporting path */ - buf = fsname_static; - buflen = sizeof(fsname_static); - } - - len = strlen(lsi->lsi_lmd->lmd_profile); - ptr = strrchr(lsi->lsi_lmd->lmd_profile, '-'); - if (ptr && (strcmp(ptr, "-client") == 0)) - len -= 7; - - if (unlikely(len >= buflen)) - len = buflen - 1; - strncpy(buf, lsi->lsi_lmd->lmd_profile, len); - buf[len] = '\0'; - - return buf; -} - static char* ll_d_path(struct dentry *dentry, char *buf, int bufsize) { char *path = NULL; @@ -2695,7 +2854,7 @@ void ll_dirty_page_discard_warn(struct page *page, int ioret) CDEBUG(D_WARNING, "%s: dirty page discard: %s/fid: "DFID"/%s may get corrupted " - "(rc %d)\n", ll_get_fsname(page->mapping->host->i_sb, NULL, 0), + "(rc %d)\n", ll_i2sbi(inode)->ll_fsname, s2lsi(page->mapping->host->i_sb)->lsi_lmd->lmd_dev, PFID(ll_inode2fid(inode)), (path && !IS_ERR(path)) ? path : "", ioret); @@ -2745,7 +2904,7 @@ void ll_compute_rootsquash_state(struct ll_sb_info *sbi) struct lnet_process_id id; /* Update norootsquash flag */ - down_write(&squash->rsi_sem); + spin_lock(&squash->rsi_lock); if (list_empty(&squash->rsi_nosquash_nids)) sbi->ll_flags &= ~LL_SBI_NOROOTSQUASH; else { @@ -2766,7 +2925,7 @@ void ll_compute_rootsquash_state(struct ll_sb_info *sbi) else sbi->ll_flags &= ~LL_SBI_NOROOTSQUASH; } - up_write(&squash->rsi_sem); + spin_unlock(&squash->rsi_lock); } /**