X-Git-Url: https://git.whamcloud.com/?p=fs%2Flustre-release.git;a=blobdiff_plain;f=lustre%2Fllite%2Flcommon_cl.c;h=c4b6cc9bca916e3cf96d691cb3d7b61874253119;hp=983c74c1f493b2cd95e1a0bf6f3a1e19f3cf3d95;hb=0baa3eb1a4abe6e1e882cf03b0edfabda20142b7;hpb=ae37991bcc117adfb5bb31a46aa635d396b24694 diff --git a/lustre/llite/lcommon_cl.c b/lustre/llite/lcommon_cl.c index 983c74c..c4b6cc9 100644 --- a/lustre/llite/lcommon_cl.c +++ b/lustre/llite/lcommon_cl.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 */ @@ -27,15 +23,12 @@ * Copyright (c) 2008, 2010, Oracle and/or its affiliates. All rights reserved. * Use is subject to license terms. * - * Copyright (c) 2011, 2014, Intel Corporation. + * Copyright (c) 2011, 2017, Intel Corporation. */ /* * This file is part of Lustre, http://www.lustre.org/ * Lustre is a trademark of Sun Microsystems, Inc. * - * cl code shared between vvp and liblustre (and other Lustre clients in the - * future). - * * Author: Nikita Danilov */ @@ -54,716 +47,33 @@ #include #include #include -#include #include #include #include "llite_internal.h" - -static const struct cl_req_operations ccc_req_ops; - -/* - * ccc_ prefix stands for "Common Client Code". - */ - -static struct kmem_cache *ccc_lock_kmem; -static struct kmem_cache *ccc_object_kmem; -static struct kmem_cache *ccc_thread_kmem; -static struct kmem_cache *ccc_session_kmem; -static struct kmem_cache *ccc_req_kmem; - -static struct lu_kmem_descr ccc_caches[] = { - { - .ckd_cache = &ccc_lock_kmem, - .ckd_name = "ccc_lock_kmem", - .ckd_size = sizeof (struct ccc_lock) - }, - { - .ckd_cache = &ccc_object_kmem, - .ckd_name = "ccc_object_kmem", - .ckd_size = sizeof (struct ccc_object) - }, - { - .ckd_cache = &ccc_thread_kmem, - .ckd_name = "ccc_thread_kmem", - .ckd_size = sizeof (struct ccc_thread_info), - }, - { - .ckd_cache = &ccc_session_kmem, - .ckd_name = "ccc_session_kmem", - .ckd_size = sizeof (struct ccc_session) - }, - { - .ckd_cache = &ccc_req_kmem, - .ckd_name = "ccc_req_kmem", - .ckd_size = sizeof (struct ccc_req) - }, - { - .ckd_cache = NULL - } -}; - -/***************************************************************************** - * - * Vvp device and device type functions. - * - */ - -void *ccc_key_init(const struct lu_context *ctx, struct lu_context_key *key) -{ - struct ccc_thread_info *info; - - OBD_SLAB_ALLOC_PTR_GFP(info, ccc_thread_kmem, GFP_NOFS); - if (info == NULL) - info = ERR_PTR(-ENOMEM); - return info; -} - -void ccc_key_fini(const struct lu_context *ctx, - struct lu_context_key *key, void *data) -{ - struct ccc_thread_info *info = data; - OBD_SLAB_FREE_PTR(info, ccc_thread_kmem); -} - -void *ccc_session_key_init(const struct lu_context *ctx, - struct lu_context_key *key) -{ - struct ccc_session *session; - - OBD_SLAB_ALLOC_PTR_GFP(session, ccc_session_kmem, GFP_NOFS); - if (session == NULL) - session = ERR_PTR(-ENOMEM); - return session; -} - -void ccc_session_key_fini(const struct lu_context *ctx, - struct lu_context_key *key, void *data) -{ - struct ccc_session *session = data; - OBD_SLAB_FREE_PTR(session, ccc_session_kmem); -} - -struct lu_context_key ccc_key = { - .lct_tags = LCT_CL_THREAD, - .lct_init = ccc_key_init, - .lct_fini = ccc_key_fini -}; - -struct lu_context_key ccc_session_key = { - .lct_tags = LCT_SESSION, - .lct_init = ccc_session_key_init, - .lct_fini = ccc_session_key_fini -}; - -int ccc_req_init(const struct lu_env *env, struct cl_device *dev, - struct cl_req *req) -{ - struct ccc_req *vrq; - int result; - - OBD_SLAB_ALLOC_PTR_GFP(vrq, ccc_req_kmem, GFP_NOFS); - if (vrq != NULL) { - cl_req_slice_add(req, &vrq->crq_cl, dev, &ccc_req_ops); - result = 0; - } else - result = -ENOMEM; - return result; -} +#include "vvp_internal.h" /** - * An `emergency' environment used by ccc_inode_fini() when cl_env_get() - * fails. Access to this environment is serialized by ccc_inode_fini_guard + * An `emergency' environment used by cl_inode_fini() when cl_env_get() + * fails. Access to this environment is serialized by cl_inode_fini_guard * mutex. */ -static struct lu_env *ccc_inode_fini_env = NULL; +struct lu_env *cl_inode_fini_env; +__u16 cl_inode_fini_refcheck; /** * A mutex serializing calls to slp_inode_fini() under extreme memory * pressure, when environments cannot be allocated. */ -static DEFINE_MUTEX(ccc_inode_fini_guard); -static int dummy_refcheck; - -int ccc_global_init(struct lu_device_type *device_type) -{ - int result; - - result = lu_kmem_init(ccc_caches); - if (result) - return result; - - result = lu_device_type_init(device_type); - if (result) - goto out_kmem; - - ccc_inode_fini_env = cl_env_alloc(&dummy_refcheck, - LCT_REMEMBER|LCT_NOREF); - if (IS_ERR(ccc_inode_fini_env)) { - result = PTR_ERR(ccc_inode_fini_env); - goto out_device; - } - - ccc_inode_fini_env->le_ctx.lc_cookie = 0x4; - return 0; -out_device: - lu_device_type_fini(device_type); -out_kmem: - lu_kmem_fini(ccc_caches); - return result; -} - -void ccc_global_fini(struct lu_device_type *device_type) -{ - if (ccc_inode_fini_env != NULL) { - cl_env_put(ccc_inode_fini_env, &dummy_refcheck); - ccc_inode_fini_env = NULL; - } - lu_device_type_fini(device_type); - lu_kmem_fini(ccc_caches); -} - -/***************************************************************************** - * - * Object operations. - * - */ - -struct lu_object *ccc_object_alloc(const struct lu_env *env, - const struct lu_object_header *unused, - struct lu_device *dev, - const struct cl_object_operations *clops, - const struct lu_object_operations *luops) -{ - struct ccc_object *vob; - struct lu_object *obj; - - OBD_SLAB_ALLOC_PTR_GFP(vob, ccc_object_kmem, GFP_NOFS); - if (vob != NULL) { - struct cl_object_header *hdr; - - obj = ccc2lu(vob); - hdr = &vob->cob_header; - cl_object_header_init(hdr); - hdr->coh_page_bufsize = cfs_size_round(sizeof(struct cl_page)); - - lu_object_init(obj, &hdr->coh_lu, dev); - lu_object_add_top(&hdr->coh_lu, obj); - - vob->cob_cl.co_ops = clops; - obj->lo_ops = luops; - } else - obj = NULL; - return obj; -} - -int ccc_object_init0(const struct lu_env *env, - struct ccc_object *vob, - const struct cl_object_conf *conf) -{ - vob->cob_inode = conf->coc_inode; - atomic_set(&vob->cob_transient_pages, 0); - cl_object_page_init(&vob->cob_cl, sizeof(struct ccc_page)); - return 0; -} - -int ccc_object_init(const struct lu_env *env, struct lu_object *obj, - const struct lu_object_conf *conf) -{ - struct vvp_device *dev = lu2vvp_dev(obj->lo_dev); - struct ccc_object *vob = lu2ccc(obj); - struct lu_object *below; - struct lu_device *under; - int result; - - under = &dev->vdv_next->cd_lu_dev; - below = under->ld_ops->ldo_object_alloc(env, obj->lo_header, under); - if (below != NULL) { - const struct cl_object_conf *cconf; - - cconf = lu2cl_conf(conf); - INIT_LIST_HEAD(&vob->cob_pending_list); - lu_object_add(obj, below); - result = ccc_object_init0(env, vob, cconf); - } else - result = -ENOMEM; - return result; -} - -void ccc_object_free(const struct lu_env *env, struct lu_object *obj) -{ - struct ccc_object *vob = lu2ccc(obj); - - lu_object_fini(obj); - lu_object_header_fini(obj->lo_header); - OBD_SLAB_FREE_PTR(vob, ccc_object_kmem); -} - -int ccc_lock_init(const struct lu_env *env, - struct cl_object *obj, struct cl_lock *lock, - const struct cl_io *unused, - const struct cl_lock_operations *lkops) -{ - struct ccc_lock *clk; - int result; - - CLOBINVRNT(env, obj, ccc_object_invariant(obj)); - - OBD_SLAB_ALLOC_PTR_GFP(clk, ccc_lock_kmem, GFP_NOFS); - if (clk != NULL) { - cl_lock_slice_add(lock, &clk->clk_cl, obj, lkops); - result = 0; - } else - result = -ENOMEM; - return result; -} - -int ccc_attr_set(const struct lu_env *env, struct cl_object *obj, - const struct cl_attr *attr, unsigned valid) -{ - return 0; -} - -int ccc_object_glimpse(const struct lu_env *env, - const struct cl_object *obj, struct ost_lvb *lvb) -{ - struct inode *inode = ccc_object_inode(obj); - - ENTRY; - lvb->lvb_mtime = LTIME_S(inode->i_mtime); - lvb->lvb_atime = LTIME_S(inode->i_atime); - lvb->lvb_ctime = LTIME_S(inode->i_ctime); - /* - * LU-417: Add dirty pages block count lest i_blocks reports 0, some - * "cp" or "tar" on remote node may think it's a completely sparse file - * and skip it. - */ - if (lvb->lvb_size > 0 && lvb->lvb_blocks == 0) - lvb->lvb_blocks = dirty_cnt(inode); - RETURN(0); -} - - - -int ccc_conf_set(const struct lu_env *env, struct cl_object *obj, - const struct cl_object_conf *conf) -{ - /* TODO: destroy all pages attached to this object. */ - return 0; -} - -static void ccc_object_size_lock(struct cl_object *obj) -{ - struct inode *inode = ccc_object_inode(obj); - - ll_inode_size_lock(inode); - cl_object_attr_lock(obj); -} - -static void ccc_object_size_unlock(struct cl_object *obj) -{ - struct inode *inode = ccc_object_inode(obj); - - cl_object_attr_unlock(obj); - ll_inode_size_unlock(inode); -} - -/***************************************************************************** - * - * Page operations. - * - */ - -int ccc_fail(const struct lu_env *env, const struct cl_page_slice *slice) -{ - /* - * Cached read? - */ - LBUG(); - return 0; -} - -void ccc_transient_page_verify(const struct cl_page *page) -{ -} - -int ccc_transient_page_own(const struct lu_env *env, - const struct cl_page_slice *slice, - struct cl_io *unused, - int nonblock) -{ - ccc_transient_page_verify(slice->cpl_page); - return 0; -} - -void ccc_transient_page_assume(const struct lu_env *env, - const struct cl_page_slice *slice, - struct cl_io *unused) -{ - ccc_transient_page_verify(slice->cpl_page); -} - -void ccc_transient_page_unassume(const struct lu_env *env, - const struct cl_page_slice *slice, - struct cl_io *unused) -{ - ccc_transient_page_verify(slice->cpl_page); -} - -void ccc_transient_page_disown(const struct lu_env *env, - const struct cl_page_slice *slice, - struct cl_io *unused) -{ - ccc_transient_page_verify(slice->cpl_page); -} - -void ccc_transient_page_discard(const struct lu_env *env, - const struct cl_page_slice *slice, - struct cl_io *unused) -{ - struct cl_page *page = slice->cpl_page; - - ccc_transient_page_verify(slice->cpl_page); - - /* - * For transient pages, remove it from the radix tree. - */ - cl_page_delete(env, page); -} - -int ccc_transient_page_prep(const struct lu_env *env, - const struct cl_page_slice *slice, - struct cl_io *unused) -{ - ENTRY; - /* transient page should always be sent. */ - RETURN(0); -} - -/***************************************************************************** - * - * Lock operations. - * - */ +static DEFINE_MUTEX(cl_inode_fini_guard); -void ccc_lock_fini(const struct lu_env *env, struct cl_lock_slice *slice) -{ - struct ccc_lock *clk = cl2ccc_lock(slice); - OBD_SLAB_FREE_PTR(clk, ccc_lock_kmem); -} - -int ccc_lock_enqueue(const struct lu_env *env, - const struct cl_lock_slice *slice, - struct cl_io *unused, struct cl_sync_io *anchor) -{ - CLOBINVRNT(env, slice->cls_obj, ccc_object_invariant(slice->cls_obj)); - return 0; -} - -/***************************************************************************** - * - * io operations. - * - */ - -void ccc_io_fini(const struct lu_env *env, const struct cl_io_slice *ios) -{ - struct cl_io *io = ios->cis_io; - - CLOBINVRNT(env, io->ci_obj, ccc_object_invariant(io->ci_obj)); -} - -int ccc_io_one_lock_index(const struct lu_env *env, struct cl_io *io, - __u32 enqflags, enum cl_lock_mode mode, - pgoff_t start, pgoff_t end) -{ - struct ccc_io *cio = ccc_env_io(env); - struct cl_lock_descr *descr = &cio->cui_link.cill_descr; - struct cl_object *obj = io->ci_obj; - - CLOBINVRNT(env, obj, ccc_object_invariant(obj)); - ENTRY; - - CDEBUG(D_VFSTRACE, "lock: %d [%lu, %lu]\n", mode, start, end); - - memset(&cio->cui_link, 0, sizeof cio->cui_link); - - if (cio->cui_fd && (cio->cui_fd->fd_flags & LL_FILE_GROUP_LOCKED)) { - descr->cld_mode = CLM_GROUP; - descr->cld_gid = cio->cui_fd->fd_grouplock.cg_gid; - } else { - descr->cld_mode = mode; - } - descr->cld_obj = obj; - descr->cld_start = start; - descr->cld_end = end; - descr->cld_enq_flags = enqflags; - - cl_io_lock_add(env, io, &cio->cui_link); - RETURN(0); -} - -void ccc_io_update_iov(const struct lu_env *env, - struct ccc_io *cio, struct cl_io *io) -{ - int i; - size_t size = io->u.ci_rw.crw_count; - - cio->cui_iov_olen = 0; - if (!cl_is_normalio(env, io) || cio->cui_tot_nrsegs == 0) - return; - - for (i = 0; i < cio->cui_tot_nrsegs; i++) { - struct iovec *iv = &cio->cui_iov[i]; - - if (iv->iov_len < size) - size -= iv->iov_len; - else { - if (iv->iov_len > size) { - cio->cui_iov_olen = iv->iov_len; - iv->iov_len = size; - } - break; - } - } - - cio->cui_nrsegs = i + 1; - LASSERTF(cio->cui_tot_nrsegs >= cio->cui_nrsegs, - "tot_nrsegs: %lu, nrsegs: %lu\n", - cio->cui_tot_nrsegs, cio->cui_nrsegs); -} - -int ccc_io_one_lock(const struct lu_env *env, struct cl_io *io, - __u32 enqflags, enum cl_lock_mode mode, - loff_t start, loff_t end) -{ - struct cl_object *obj = io->ci_obj; - return ccc_io_one_lock_index(env, io, enqflags, mode, - cl_index(obj, start), cl_index(obj, end)); -} - -void ccc_io_end(const struct lu_env *env, const struct cl_io_slice *ios) -{ - CLOBINVRNT(env, ios->cis_io->ci_obj, - ccc_object_invariant(ios->cis_io->ci_obj)); -} - -void ccc_io_advance(const struct lu_env *env, - const struct cl_io_slice *ios, - size_t nob) -{ - struct ccc_io *cio = cl2ccc_io(env, ios); - struct cl_io *io = ios->cis_io; - struct cl_object *obj = ios->cis_io->ci_obj; - - CLOBINVRNT(env, obj, ccc_object_invariant(obj)); - - if (!cl_is_normalio(env, io)) - return; - - LASSERT(cio->cui_tot_nrsegs >= cio->cui_nrsegs); - LASSERT(cio->cui_tot_count >= nob); - - cio->cui_iov += cio->cui_nrsegs; - cio->cui_tot_nrsegs -= cio->cui_nrsegs; - cio->cui_tot_count -= nob; - - /* update the iov */ - if (cio->cui_iov_olen > 0) { - struct iovec *iv; - - cio->cui_iov--; - cio->cui_tot_nrsegs++; - iv = &cio->cui_iov[0]; - if (io->ci_continue) { - iv->iov_base += iv->iov_len; - LASSERT(cio->cui_iov_olen > iv->iov_len); - iv->iov_len = cio->cui_iov_olen - iv->iov_len; - } else { - /* restore the iov_len, in case of restart io. */ - iv->iov_len = cio->cui_iov_olen; - } - cio->cui_iov_olen = 0; - } -} - -/** - * Helper function that if necessary adjusts file size (inode->i_size), when - * position at the offset \a pos is accessed. File size can be arbitrary stale - * on a Lustre client, but client at least knows KMS. If accessed area is - * inside [0, KMS], set file size to KMS, otherwise glimpse file size. - * - * Locking: cl_isize_lock is used to serialize changes to inode size and to - * protect consistency between inode size and cl_object - * attributes. cl_object_size_lock() protects consistency between cl_attr's of - * top-object and sub-objects. - */ -int ccc_prep_size(const struct lu_env *env, struct cl_object *obj, - struct cl_io *io, loff_t start, size_t count, int *exceed) -{ - struct cl_attr *attr = ccc_env_thread_attr(env); - struct inode *inode = ccc_object_inode(obj); - loff_t pos = start + count - 1; - loff_t kms; - int result; - - /* - * Consistency guarantees: following possibilities exist for the - * relation between region being accessed and real file size at this - * moment: - * - * (A): the region is completely inside of the file; - * - * (B-x): x bytes of region are inside of the file, the rest is - * outside; - * - * (C): the region is completely outside of the file. - * - * This classification is stable under DLM lock already acquired by - * the caller, because to change the class, other client has to take - * DLM lock conflicting with our lock. Also, any updates to ->i_size - * by other threads on this client are serialized by - * ll_inode_size_lock(). This guarantees that short reads are handled - * correctly in the face of concurrent writes and truncates. - */ - ccc_object_size_lock(obj); - result = cl_object_attr_get(env, obj, attr); - if (result == 0) { - kms = attr->cat_kms; - if (pos > kms) { - /* - * A glimpse is necessary to determine whether we - * return a short read (B) or some zeroes at the end - * of the buffer (C) - */ - ccc_object_size_unlock(obj); - result = cl_glimpse_lock(env, io, inode, obj, 0); - if (result == 0 && exceed != NULL) { - /* If objective page index exceed end-of-file - * page index, return directly. Do not expect - * kernel will check such case correctly. - * linux-2.6.18-128.1.1 miss to do that. - * --bug 17336 */ - loff_t size = i_size_read(inode); - unsigned long cur_index = start >> - PAGE_CACHE_SHIFT; - - if ((size == 0 && cur_index != 0) || - (((size - 1) >> PAGE_CACHE_SHIFT) < - cur_index)) - *exceed = 1; - } - return result; - } else { - /* - * region is within kms and, hence, within real file - * size (A). We need to increase i_size to cover the - * read region so that generic_file_read() will do its - * job, but that doesn't mean the kms size is - * _correct_, it is only the _minimum_ size. If - * someone does a stat they will get the correct size - * which will always be >= the kms value here. - * b=11081 - */ - if (i_size_read(inode) < kms) { - i_size_write(inode, kms); - CDEBUG(D_VFSTRACE, - DFID" updating i_size "LPU64"\n", - PFID(lu_object_fid(&obj->co_lu)), - (__u64)i_size_read(inode)); - - } - } - } - ccc_object_size_unlock(obj); - return result; -} - -/***************************************************************************** - * - * Transfer operations. - * - */ - -void ccc_req_completion(const struct lu_env *env, - const struct cl_req_slice *slice, int ioret) -{ - struct ccc_req *vrq; - - if (ioret > 0) - cl_stats_tally(slice->crs_dev, slice->crs_req->crq_type, ioret); - - vrq = cl2ccc_req(slice); - OBD_SLAB_FREE_PTR(vrq, ccc_req_kmem); -} - -/** - * Implementation of struct cl_req_operations::cro_attr_set() for ccc - * layer. ccc is responsible for - * - * - o_[mac]time - * - * - o_mode - * - * - o_parent_seq - * - * - o_[ug]id - * - * - o_parent_oid - * - * - o_parent_ver - * - * - o_ioepoch, - * - * and capability. - */ -void ccc_req_attr_set(const struct lu_env *env, - const struct cl_req_slice *slice, - const struct cl_object *obj, - struct cl_req_attr *attr, obd_valid flags) -{ - struct inode *inode; - struct obdo *oa; - obd_flag valid_flags; - - oa = attr->cra_oa; - inode = ccc_object_inode(obj); - valid_flags = OBD_MD_FLTYPE; - - if ((flags & OBD_MD_FLOSSCAPA) != 0) { - LASSERT(attr->cra_capa == NULL); - attr->cra_capa = cl_capa_lookup(inode, - slice->crs_req->crq_type); - } - - if (slice->crs_req->crq_type == CRT_WRITE) { - if (flags & OBD_MD_FLEPOCH) { - oa->o_valid |= OBD_MD_FLEPOCH; - oa->o_ioepoch = ll_i2info(inode)->lli_ioepoch; - valid_flags |= OBD_MD_FLMTIME | OBD_MD_FLCTIME | - OBD_MD_FLUID | OBD_MD_FLGID; - } - } - obdo_from_inode(oa, inode, valid_flags & flags); - obdo_set_parent_fid(oa, &ll_i2info(inode)->lli_fid); - if (OBD_FAIL_CHECK(OBD_FAIL_LFSCK_INVALID_PFID)) - oa->o_parent_oid++; - memcpy(attr->cra_jobid, ll_i2info(inode)->lli_jobid, - LUSTRE_JOBID_SIZE); -} - -static const struct cl_req_operations ccc_req_ops = { - .cro_attr_set = ccc_req_attr_set, - .cro_completion = ccc_req_completion -}; - -int cl_setattr_ost(struct inode *inode, const struct iattr *attr, - struct obd_capa *capa) +int cl_setattr_ost(struct cl_object *obj, const struct iattr *attr, + enum op_xvalid xvalid, unsigned int attr_flags) { struct lu_env *env; struct cl_io *io; int result; - int refcheck; + __u16 refcheck; ENTRY; @@ -771,24 +81,30 @@ int cl_setattr_ost(struct inode *inode, const struct iattr *attr, if (IS_ERR(env)) RETURN(PTR_ERR(env)); - io = ccc_env_thread_io(env); - io->ci_obj = ll_i2info(inode)->lli_clob; + io = vvp_env_thread_io(env); + io->ci_obj = obj; + io->ci_verify_layout = 1; - io->u.ci_setattr.sa_attr.lvb_atime = LTIME_S(attr->ia_atime); - io->u.ci_setattr.sa_attr.lvb_mtime = LTIME_S(attr->ia_mtime); - io->u.ci_setattr.sa_attr.lvb_ctime = LTIME_S(attr->ia_ctime); - io->u.ci_setattr.sa_attr.lvb_size = attr->ia_size; - io->u.ci_setattr.sa_valid = attr->ia_valid; - io->u.ci_setattr.sa_capa = capa; + io->u.ci_setattr.sa_attr.lvb_atime = LTIME_S(attr->ia_atime); + io->u.ci_setattr.sa_attr.lvb_mtime = LTIME_S(attr->ia_mtime); + io->u.ci_setattr.sa_attr.lvb_ctime = LTIME_S(attr->ia_ctime); + io->u.ci_setattr.sa_attr.lvb_size = attr->ia_size; + io->u.ci_setattr.sa_attr_flags = attr_flags; + io->u.ci_setattr.sa_avalid = attr->ia_valid; + io->u.ci_setattr.sa_xvalid = xvalid; + io->u.ci_setattr.sa_parent_fid = lu_object_fid(&obj->co_lu); again: + if (attr->ia_valid & ATTR_FILE) + ll_io_set_mirror(io, attr->ia_file); + if (cl_io_init(env, io, CIT_SETATTR, io->ci_obj) == 0) { - struct ccc_io *cio = ccc_env_io(env); + struct vvp_io *vio = vvp_env_io(env); - if (attr->ia_valid & ATTR_FILE) - /* populate the file descriptor for ftruncate to honor - * group lock - see LU-787 */ - cio->cui_fd = LUSTRE_FPRIVATE(attr->ia_file); + if (attr->ia_valid & ATTR_FILE) + /* populate the file descriptor for ftruncate to honor + * group lock - see LU-787 */ + vio->vui_fd = LUSTRE_FPRIVATE(attr->ia_file); result = cl_io_loop(env, io); } else { @@ -797,92 +113,11 @@ again: cl_io_fini(env, io); if (unlikely(io->ci_need_restart)) goto again; - /* HSM import case: file is released, cannot be restored - * no need to fail except if restore registration failed - * with -ENODATA */ - if (result == -ENODATA && io->ci_restore_needed && - io->ci_result != -ENODATA) - result = 0; + cl_env_put(env, &refcheck); RETURN(result); } -/***************************************************************************** - * - * Type conversions. - * - */ - -struct lu_object *ccc2lu(struct ccc_object *vob) -{ - return &vob->cob_cl.co_lu; -} - -struct ccc_object *lu2ccc(const struct lu_object *obj) -{ - return container_of0(obj, struct ccc_object, cob_cl.co_lu); -} - -struct ccc_object *cl2ccc(const struct cl_object *obj) -{ - return container_of0(obj, struct ccc_object, cob_cl); -} - -struct ccc_lock *cl2ccc_lock(const struct cl_lock_slice *slice) -{ - return container_of(slice, struct ccc_lock, clk_cl); -} - -struct ccc_io *cl2ccc_io(const struct lu_env *env, - const struct cl_io_slice *slice) -{ - struct ccc_io *cio; - - cio = container_of(slice, struct ccc_io, cui_cl); - LASSERT(cio == ccc_env_io(env)); - return cio; -} - -struct ccc_req *cl2ccc_req(const struct cl_req_slice *slice) -{ - return container_of0(slice, struct ccc_req, crq_cl); -} - -struct page *cl2vm_page(const struct cl_page_slice *slice) -{ - return cl2ccc_page(slice)->cpg_page; -} - -/***************************************************************************** - * - * Accessors. - * - */ -int ccc_object_invariant(const struct cl_object *obj) -{ - struct inode *inode = ccc_object_inode(obj); - struct ll_inode_info *lli = ll_i2info(inode); - - return (S_ISREG(inode->i_mode) || inode->i_mode == 0) && - lli->lli_clob == obj; -} - -struct inode *ccc_object_inode(const struct cl_object *obj) -{ - return cl2ccc(obj)->cob_inode; -} - -/** - * Returns a pointer to cl_page associated with \a vmpage, without acquiring - * additional reference to the resulting page. This is an unsafe version of - * cl_vmpage_page() that can only be used under vmpage lock. - */ -struct cl_page *ccc_vmpage_page_transient(struct page *vmpage) -{ - KLASSERT(PageLocked(vmpage)); - return (struct cl_page *)vmpage->private; -} - /** * Initialize or update CLIO structures for regular files when new * meta-data arrives from the server. @@ -899,14 +134,14 @@ int cl_file_inode_init(struct inode *inode, struct lustre_md *md) struct cl_object *clob; struct lu_site *site; struct lu_fid *fid; - struct cl_object_conf conf = { - .coc_inode = inode, - .u = { - .coc_md = md - } - }; + struct cl_object_conf conf = { + .coc_inode = inode, + .u = { + .coc_layout = md->layout, + } + }; int result = 0; - int refcheck; + __u16 refcheck; LASSERT(md->body->mbo_valid & OBD_MD_FLID); LASSERT(S_ISREG(inode->i_mode)); @@ -917,38 +152,52 @@ int cl_file_inode_init(struct inode *inode, struct lustre_md *md) site = ll_i2sbi(inode)->ll_site; lli = ll_i2info(inode); - fid = &lli->lli_fid; - LASSERT(fid_is_sane(fid)); + fid = &lli->lli_fid; + LASSERT(fid_is_sane(fid)); + + if (lli->lli_clob == NULL) { + /* clob is slave of inode, empty lli_clob means for new inode, + * there is no clob in cache with the given fid, so it is + * unnecessary to perform lookup-alloc-lookup-insert, just + * alloc and insert directly. + */ + if (!(inode->i_state & I_NEW)) { + result = -EIO; + CERROR("%s: unexpected not-NEW inode "DFID": rc = %d\n", + ll_get_fsname(inode->i_sb, NULL, 0), PFID(fid), + result); + goto out; + } - if (lli->lli_clob == NULL) { - /* clob is slave of inode, empty lli_clob means for new inode, - * there is no clob in cache with the given fid, so it is - * unnecessary to perform lookup-alloc-lookup-insert, just - * alloc and insert directly. */ - LASSERT(inode->i_state & I_NEW); - conf.coc_lu.loc_flags = LOC_F_NEW; - clob = cl_object_find(env, lu2cl_dev(site->ls_top_dev), - fid, &conf); - if (!IS_ERR(clob)) { - /* - * No locking is necessary, as new inode is - * locked by I_NEW bit. - */ - lli->lli_clob = clob; - lli->lli_has_smd = lsm_has_objects(md->lsm); - lu_object_ref_add(&clob->co_lu, "inode", inode); - } else - result = PTR_ERR(clob); + conf.coc_lu.loc_flags = LOC_F_NEW; + clob = cl_object_find(env, lu2cl_dev(site->ls_top_dev), + fid, &conf); + if (!IS_ERR(clob)) { + /* + * No locking is necessary, as new inode is + * locked by I_NEW bit. + */ + lli->lli_clob = clob; + lu_object_ref_add(&clob->co_lu, "inode", inode); + } else { + result = PTR_ERR(clob); + } } else { result = cl_conf_set(env, lli->lli_clob, &conf); + if (result == -EBUSY) { + /* ignore the error since I/O will handle it later */ + result = 0; + } } - cl_env_put(env, &refcheck); + if (result != 0) + CERROR("%s: failed to initialize cl_object "DFID": rc = %d\n", + ll_get_fsname(inode->i_sb, NULL, 0), PFID(fid), result); - if (result != 0) - CERROR("Failure to initialize cl object "DFID": %d\n", - PFID(fid), result); - return result; +out: + cl_env_put(env, &refcheck); + + return result; } /** @@ -963,26 +212,26 @@ int cl_file_inode_init(struct inode *inode, struct lustre_md *md) static void cl_object_put_last(struct lu_env *env, struct cl_object *obj) { struct lu_object_header *header = obj->co_lu.lo_header; - wait_queue_t waiter; + wait_queue_entry_t waiter; if (unlikely(atomic_read(&header->loh_ref) != 1)) { struct lu_site *site = obj->co_lu.lo_dev->ld_site; - struct lu_site_bkt_data *bkt; + wait_queue_head_t *wq; - bkt = lu_site_bkt_from_fid(site, &header->loh_fid); + wq = lu_site_wq_from_fid(site, &header->loh_fid); - init_waitqueue_entry_current(&waiter); - add_wait_queue(&bkt->lsb_marche_funebre, &waiter); + init_waitqueue_entry(&waiter, current); + add_wait_queue(wq, &waiter); while (1) { set_current_state(TASK_UNINTERRUPTIBLE); if (atomic_read(&header->loh_ref) == 1) break; - waitq_wait(&waiter, TASK_UNINTERRUPTIBLE); + schedule(); } set_current_state(TASK_RUNNING); - remove_wait_queue(&bkt->lsb_marche_funebre, &waiter); + remove_wait_queue(wq, &waiter); } cl_object_put(env, obj); @@ -992,22 +241,19 @@ void cl_inode_fini(struct inode *inode) { struct lu_env *env; struct ll_inode_info *lli = ll_i2info(inode); - struct cl_object *clob = lli->lli_clob; - int refcheck; - int emergency; - - if (clob != NULL) { - void *cookie; + struct cl_object *clob = lli->lli_clob; + __u16 refcheck; + int emergency; + + if (clob != NULL) { + env = cl_env_get(&refcheck); + emergency = IS_ERR(env); + if (emergency) { + mutex_lock(&cl_inode_fini_guard); + LASSERT(cl_inode_fini_env != NULL); + env = cl_inode_fini_env; + } - cookie = cl_env_reenter(); - env = cl_env_get(&refcheck); - emergency = IS_ERR(env); - if (emergency) { - mutex_lock(&ccc_inode_fini_guard); - LASSERT(ccc_inode_fini_env != NULL); - cl_env_implant(ccc_inode_fini_env, &refcheck); - env = ccc_inode_fini_env; - } /* * cl_object cache is a slave to inode cache (which, in turn * is a slave to dentry cache), don't keep cl_object in memory @@ -1017,78 +263,36 @@ void cl_inode_fini(struct inode *inode) lu_object_ref_del(&clob->co_lu, "inode", inode); cl_object_put_last(env, clob); lli->lli_clob = NULL; - if (emergency) { - cl_env_unplant(ccc_inode_fini_env, &refcheck); - mutex_unlock(&ccc_inode_fini_guard); - } else - cl_env_put(env, &refcheck); - cl_env_reexit(cookie); - } -} - -/** - * return IF_* type for given lu_dirent entry. - * IF_* flag shld be converted to particular OS file type in - * platform llite module. - */ -__u16 ll_dirent_type_get(struct lu_dirent *ent) -{ - __u16 type = 0; - struct luda_type *lt; - int len = 0; - - if (le32_to_cpu(ent->lde_attrs) & LUDA_TYPE) { - const unsigned align = sizeof(struct luda_type) - 1; - - len = le16_to_cpu(ent->lde_namelen); - len = (len + align) & ~align; - lt = (void *)ent->lde_name + len; - type = IFTODT(le16_to_cpu(lt->lt_type)); + if (emergency) + mutex_unlock(&cl_inode_fini_guard); + else + cl_env_put(env, &refcheck); } - return type; } /** - * build inode number from passed @fid */ + * build inode number from passed @fid. + * + * For 32-bit systems or syscalls limit the inode number to a 32-bit value + * to avoid EOVERFLOW errors. This will inevitably result in inode number + * collisions, but fid_flatten32() tries hard to avoid this if possible. + */ __u64 cl_fid_build_ino(const struct lu_fid *fid, int api32) { - if (BITS_PER_LONG == 32 || api32) - RETURN(fid_flatten32(fid)); - else - RETURN(fid_flatten(fid)); + if (BITS_PER_LONG == 32 || api32) + RETURN(fid_flatten32(fid)); + + RETURN(fid_flatten(fid)); } /** * build inode generation from passed @fid. If our FID overflows the 32-bit - * inode number then return a non-zero generation to distinguish them. */ + * inode number then return a non-zero generation to distinguish them. + */ __u32 cl_fid_build_gen(const struct lu_fid *fid) { - __u32 gen; - ENTRY; - - if (fid_is_igif(fid)) { - gen = lu_igif_gen(fid); - RETURN(gen); - } - - gen = (fid_flatten(fid) >> 32); - RETURN(gen); -} - -/* lsm is unreliable after hsm implementation as layout can be changed at - * any time. This is only to support old, non-clio-ized interfaces. It will - * cause deadlock if clio operations are called with this extra layout refcount - * because in case the layout changed during the IO, ll_layout_refresh() will - * have to wait for the refcount to become zero to destroy the older layout. - * - * Notice that the lsm returned by this function may not be valid unless called - * inside layout lock - MDS_INODELOCK_LAYOUT. */ -struct lov_stripe_md *ccc_inode_lsm_get(struct inode *inode) -{ - return lov_lsm_get(ll_i2info(inode)->lli_clob); -} + if (fid_is_igif(fid)) + RETURN(lu_igif_gen(fid)); -void inline ccc_inode_lsm_put(struct inode *inode, struct lov_stripe_md *lsm) -{ - lov_lsm_put(ll_i2info(inode)->lli_clob, lsm); + RETURN(fid_flatten(fid) >> 32); }