X-Git-Url: https://git.whamcloud.com/?p=fs%2Flustre-release.git;a=blobdiff_plain;f=lustre%2Fllite%2Ffile.c;h=f835a850547409706006081f045bc81dfb3f5f13;hp=9debc22f5ae45666a77bc88444a8b8a4b8073b25;hb=49b17944e1a61f88bddb5595bb053a555c8c08da;hpb=26422c384c301ec81345292fd30e5924c37305b6 diff --git a/lustre/llite/file.c b/lustre/llite/file.c index 9debc22..f835a85 100644 --- a/lustre/llite/file.c +++ b/lustre/llite/file.c @@ -27,7 +27,7 @@ * Copyright (c) 2002, 2010, Oracle and/or its affiliates. All rights reserved. * Use is subject to license terms. * - * Copyright (c) 2011, 2013, Intel Corporation. + * Copyright (c) 2011, 2014, Intel Corporation. */ /* * This file is part of Lustre, http://www.lustre.org/ @@ -42,9 +42,9 @@ #define DEBUG_SUBSYSTEM S_LLITE #include -#include #include #include +#include #include "llite_internal.h" #include #include @@ -90,9 +90,7 @@ void ll_pack_inode2opdata(struct inode *inode, struct md_op_data *op_data, op_data->op_attr.ia_ctime = inode->i_ctime; op_data->op_attr.ia_size = i_size_read(inode); op_data->op_attr_blocks = inode->i_blocks; - ((struct ll_iattr *)&op_data->op_attr)->ia_attr_flags = - ll_inode_to_ext_flags(inode->i_flags); - op_data->op_ioepoch = ll_i2info(inode)->lli_ioepoch; + op_data->op_attr_flags = ll_inode_to_ext_flags(inode->i_flags); if (fh) op_data->op_handle = *fh; op_data->op_capa1 = ll_mdscapa_get(inode); @@ -102,8 +100,7 @@ void ll_pack_inode2opdata(struct inode *inode, struct md_op_data *op_data, } /** - * Closes the IO epoch and packs all the attributes into @op_data for - * the CLOSE rpc. + * Packs all the attributes into @op_data for the CLOSE rpc. */ static void ll_prepare_close(struct inode *inode, struct md_op_data *op_data, struct obd_client_handle *och) @@ -117,10 +114,7 @@ static void ll_prepare_close(struct inode *inode, struct md_op_data *op_data, if (!(och->och_flags & FMODE_WRITE)) goto out; - if (!exp_connect_som(ll_i2mdexp(inode)) || !S_ISREG(inode->i_mode)) - op_data->op_attr.ia_valid |= ATTR_SIZE | ATTR_BLOCKS; - else - ll_ioepoch_close(inode, op_data, &och, 0); + op_data->op_attr.ia_valid |= ATTR_SIZE | ATTR_BLOCKS; out: ll_pack_inode2opdata(inode, op_data, &och->och_fh); @@ -138,7 +132,6 @@ static int ll_close_inode_openhandle(struct obd_export *md_exp, struct md_op_data *op_data; struct ptlrpc_request *req = NULL; struct obd_device *obd = class_exp2obd(exp); - int epoch_close = 1; int rc; ENTRY; @@ -164,22 +157,9 @@ static int ll_close_inode_openhandle(struct obd_export *md_exp, op_data->op_lease_handle = och->och_lease_handle; op_data->op_attr.ia_valid |= ATTR_SIZE | ATTR_BLOCKS; } - epoch_close = (op_data->op_flags & MF_EPOCH_CLOSE); + rc = md_close(md_exp, op_data, och->och_mod, &req); - if (rc == -EAGAIN) { - /* This close must have the epoch closed. */ - LASSERT(epoch_close); - /* MDS has instructed us to obtain Size-on-MDS attribute from - * OSTs and send setattr to back to MDS. */ - rc = ll_som_update(inode, op_data); - if (rc) { - CERROR("%s: inode "DFID" mdc Size-on-MDS update" - " failed: rc = %d\n", - ll_i2mdexp(inode)->exp_obd->obd_name, - PFID(ll_inode2fid(inode)), rc); - rc = 0; - } - } else if (rc) { + if (rc) { CERROR("%s: inode "DFID" mdc close failed: rc = %d\n", ll_i2mdexp(inode)->exp_obd->obd_name, PFID(ll_inode2fid(inode)), rc); @@ -195,19 +175,10 @@ static int ll_close_inode_openhandle(struct obd_export *md_exp, spin_unlock(&lli->lli_lock); } - if (rc == 0) { - rc = ll_objects_destroy(req, inode); - if (rc) - CERROR("%s: inode "DFID - " ll_objects destroy: rc = %d\n", - ll_i2mdexp(inode)->exp_obd->obd_name, - PFID(ll_inode2fid(inode)), rc); - } - if (rc == 0 && op_data->op_bias & MDS_HSM_RELEASE) { struct mdt_body *body; body = req_capsule_server_get(&req->rq_pill, &RMF_MDT_BODY); - if (!(body->valid & OBD_MD_FLRELEASED)) + if (!(body->mbo_valid & OBD_MD_FLRELEASED)) rc = -EBUSY; } @@ -215,15 +186,10 @@ static int ll_close_inode_openhandle(struct obd_export *md_exp, EXIT; out: - if (exp_connect_som(exp) && !epoch_close && - S_ISREG(inode->i_mode) && (och->och_flags & FMODE_WRITE)) { - ll_queue_done_writing(inode, LLIF_DONE_WRITING); - } else { - md_clear_open_replay_data(md_exp, och); - /* Free @och if it is not waiting for DONE_WRITING. */ - och->och_fh.cookie = DEAD_HANDLE_MAGIC; - OBD_FREE_PTR(och); - } + md_clear_open_replay_data(md_exp, och); + och->och_fh.cookie = DEAD_HANDLE_MAGIC; + OBD_FREE_PTR(och); + if (req) /* This is close request */ ptlrpc_req_finished(req); return rc; @@ -333,10 +299,11 @@ static int ll_md_close(struct obd_export *md_exp, struct inode *inode, rc = ll_md_real_close(file->f_dentry->d_inode, fd->fd_omode); } - } else { - CERROR("Releasing a file %p with negative dentry %p. Name %s", - file, file->f_dentry, file->f_dentry->d_name.name); - } + } else { + CERROR("released file has negative dentry: file = %p, " + "dentry = %p, name = %s\n", + file, file->f_dentry, file->f_dentry->d_name.name); + } out: LUSTRE_FPRIVATE(file) = NULL; @@ -381,12 +348,10 @@ int ll_file_release(struct inode *inode, struct file *file) fd = LUSTRE_FPRIVATE(file); LASSERT(fd != NULL); - /* The last ref on @file, maybe not the the owner pid of statahead. - * Different processes can open the same dir, "ll_opendir_key" means: - * it is me that should stop the statahead thread. */ - if (S_ISDIR(inode->i_mode) && lli->lli_opendir_key == fd && - lli->lli_opendir_pid != 0) - ll_stop_statahead(inode, lli->lli_opendir_key); + /* The last ref on @file, maybe not the the owner pid of statahead, + * because parent and child process can share the same file handle. */ + if (S_ISDIR(inode->i_mode) && lli->lli_opendir_key == fd) + ll_deauthorize_statahead(inode, fd); if (inode->i_sb->s_root == file->f_dentry) { LUSTRE_FPRIVATE(file) = NULL; @@ -408,91 +373,69 @@ int ll_file_release(struct inode *inode, struct file *file) RETURN(rc); } -static int ll_intent_file_open(struct file *file, void *lmm, - int lmmsize, struct lookup_intent *itp) +static int ll_intent_file_open(struct file *file, void *lmm, int lmmsize, + struct lookup_intent *itp) { - struct ll_sb_info *sbi = ll_i2sbi(file->f_dentry->d_inode); - struct dentry *parent = file->f_dentry->d_parent; - const char *name = file->f_dentry->d_name.name; - const int len = file->f_dentry->d_name.len; - struct md_op_data *op_data; - struct ptlrpc_request *req; - __u32 opc = LUSTRE_OPC_ANY; - int rc; - ENTRY; + struct dentry *de = file->f_dentry; + struct ll_sb_info *sbi = ll_i2sbi(de->d_inode); + struct dentry *parent = de->d_parent; + const char *name = NULL; + int len = 0; + struct md_op_data *op_data; + struct ptlrpc_request *req = NULL; + int rc; + ENTRY; - if (!parent) - RETURN(-ENOENT); - - /* Usually we come here only for NFSD, and we want open lock. - But we can also get here with pre 2.6.15 patchless kernels, and in - that case that lock is also ok */ - /* We can also get here if there was cached open handle in revalidate_it - * but it disappeared while we were getting from there to ll_file_open. - * But this means this file was closed and immediatelly opened which - * makes a good candidate for using OPEN lock */ - /* If lmmsize & lmm are not 0, we are just setting stripe info - * parameters. No need for the open lock */ - if (lmm == NULL && lmmsize == 0) { - itp->it_flags |= MDS_OPEN_LOCK; - if (itp->it_flags & FMODE_WRITE) - opc = LUSTRE_OPC_CREATE; - } + LASSERT(parent != NULL); + LASSERT(itp->it_flags & MDS_OPEN_BY_FID); - op_data = ll_prep_md_op_data(NULL, parent->d_inode, - file->f_dentry->d_inode, name, len, - O_RDWR, opc, NULL); - if (IS_ERR(op_data)) - RETURN(PTR_ERR(op_data)); + /* if server supports open-by-fid, or file name is invalid, don't pack + * name in open request */ + if (!(exp_connect_flags(sbi->ll_md_exp) & OBD_CONNECT_OPEN_BY_FID) && + lu_name_is_valid_2(de->d_name.name, de->d_name.len)) { + name = de->d_name.name; + len = de->d_name.len; + } - itp->it_flags |= MDS_OPEN_BY_FID; - rc = md_intent_lock(sbi->ll_md_exp, op_data, lmm, lmmsize, itp, - 0 /*unused */, &req, ll_md_blocking_ast, 0); - ll_finish_md_op_data(op_data); - if (rc == -ESTALE) { - /* reason for keep own exit path - don`t flood log - * with messages with -ESTALE errors. - */ - if (!it_disposition(itp, DISP_OPEN_OPEN) || - it_open_error(DISP_OPEN_OPEN, itp)) - GOTO(out, rc); - ll_release_openhandle(file->f_dentry, itp); - GOTO(out, rc); - } + op_data = ll_prep_md_op_data(NULL, parent->d_inode, de->d_inode, + name, len, 0, LUSTRE_OPC_ANY, NULL); + if (IS_ERR(op_data)) + RETURN(PTR_ERR(op_data)); + op_data->op_data = lmm; + op_data->op_data_size = lmmsize; - if (it_disposition(itp, DISP_LOOKUP_NEG)) - GOTO(out, rc = -ENOENT); + rc = md_intent_lock(sbi->ll_md_exp, op_data, itp, &req, + &ll_md_blocking_ast, 0); + ll_finish_md_op_data(op_data); + if (rc == -ESTALE) { + /* reason for keep own exit path - don`t flood log + * with messages with -ESTALE errors. + */ + if (!it_disposition(itp, DISP_OPEN_OPEN) || + it_open_error(DISP_OPEN_OPEN, itp)) + GOTO(out, rc); + ll_release_openhandle(de, itp); + GOTO(out, rc); + } - if (rc != 0 || it_open_error(DISP_OPEN_OPEN, itp)) { - rc = rc ? rc : it_open_error(DISP_OPEN_OPEN, itp); - CDEBUG(D_VFSTRACE, "lock enqueue: err: %d\n", rc); - GOTO(out, rc); - } + if (it_disposition(itp, DISP_LOOKUP_NEG)) + GOTO(out, rc = -ENOENT); - rc = ll_prep_inode(&file->f_dentry->d_inode, req, NULL, itp); - if (!rc && itp->d.lustre.it_lock_mode) - ll_set_lock_data(sbi->ll_md_exp, file->f_dentry->d_inode, - itp, NULL); + if (rc != 0 || it_open_error(DISP_OPEN_OPEN, itp)) { + rc = rc ? rc : it_open_error(DISP_OPEN_OPEN, itp); + CDEBUG(D_VFSTRACE, "lock enqueue: err: %d\n", rc); + GOTO(out, rc); + } + + rc = ll_prep_inode(&de->d_inode, req, NULL, itp); + if (!rc && itp->d.lustre.it_lock_mode) + ll_set_lock_data(sbi->ll_md_exp, de->d_inode, itp, NULL); out: ptlrpc_req_finished(req); - ll_intent_drop_lock(itp); + ll_intent_drop_lock(itp); - RETURN(rc); -} - -/** - * Assign an obtained @ioepoch to client's inode. No lock is needed, MDS does - * not believe attributes if a few ioepoch holders exist. Attributes for - * previous ioepoch if new one is opened are also skipped by MDS. - */ -void ll_ioepoch_open(struct ll_inode_info *lli, __u64 ioepoch) -{ - if (ioepoch && lli->lli_ioepoch != ioepoch) { - lli->lli_ioepoch = ioepoch; - CDEBUG(D_INODE, "Epoch "LPU64" opened on "DFID"\n", - ioepoch, PFID(&lli->lli_fid)); - } + RETURN(rc); } static int ll_och_fill(struct obd_export *md_exp, struct lookup_intent *it, @@ -502,8 +445,8 @@ static int ll_och_fill(struct obd_export *md_exp, struct lookup_intent *it, struct mdt_body *body; body = req_capsule_server_get(&req->rq_pill, &RMF_MDT_BODY); - och->och_fh = body->handle; - och->och_fid = body->fid1; + och->och_fh = body->mbo_handle; + och->och_fid = body->mbo_fid1; och->och_lease_handle.cookie = it->d.lustre.it_lock_handle; och->och_magic = OBD_CLIENT_HANDLE_MAGIC; och->och_flags = it->it_flags; @@ -514,31 +457,29 @@ static int ll_och_fill(struct obd_export *md_exp, struct lookup_intent *it, static int ll_local_open(struct file *file, struct lookup_intent *it, struct ll_file_data *fd, struct obd_client_handle *och) { - struct inode *inode = file->f_dentry->d_inode; - struct ll_inode_info *lli = ll_i2info(inode); - ENTRY; + struct inode *inode = file->f_dentry->d_inode; + ENTRY; - LASSERT(!LUSTRE_FPRIVATE(file)); + LASSERT(!LUSTRE_FPRIVATE(file)); - LASSERT(fd != NULL); + LASSERT(fd != NULL); - if (och) { - struct ptlrpc_request *req = it->d.lustre.it_data; - struct mdt_body *body; - int rc; + if (och) { + int rc; rc = ll_och_fill(ll_i2sbi(inode)->ll_md_exp, it, och); if (rc != 0) RETURN(rc); - - body = req_capsule_server_get(&req->rq_pill, &RMF_MDT_BODY); - ll_ioepoch_open(lli, body->ioepoch); } LUSTRE_FPRIVATE(file) = fd; ll_readahead_init(inode, &fd->fd_ras); fd->fd_omode = it->it_flags & (FMODE_READ | FMODE_WRITE | FMODE_EXEC); + /* ll_cl_context initialize */ + rwlock_init(&fd->fd_lock); + INIT_LIST_HEAD(&fd->fd_lccs); + RETURN(0); } @@ -557,36 +498,28 @@ static int ll_local_open(struct file *file, struct lookup_intent *it, */ int ll_file_open(struct inode *inode, struct file *file) { - struct ll_inode_info *lli = ll_i2info(inode); - struct lookup_intent *it, oit = { .it_op = IT_OPEN, - .it_flags = file->f_flags }; - struct obd_client_handle **och_p = NULL; - __u64 *och_usecount = NULL; - struct ll_file_data *fd; - int rc = 0, opendir_set = 0; - ENTRY; + struct ll_inode_info *lli = ll_i2info(inode); + struct lookup_intent *it, oit = { .it_op = IT_OPEN, + .it_flags = file->f_flags }; + struct obd_client_handle **och_p = NULL; + __u64 *och_usecount = NULL; + struct ll_file_data *fd; + int rc = 0; + ENTRY; CDEBUG(D_VFSTRACE, "VFS Op:inode="DFID"(%p), flags %o\n", PFID(ll_inode2fid(inode)), inode, file->f_flags); - it = file->private_data; /* XXX: compat macro */ - file->private_data = NULL; /* prevent ll_local_open assertion */ + it = file->private_data; /* XXX: compat macro */ + file->private_data = NULL; /* prevent ll_local_open assertion */ fd = ll_file_data_get(); if (fd == NULL) GOTO(out_openerr, rc = -ENOMEM); fd->fd_file = file; - if (S_ISDIR(inode->i_mode)) { - spin_lock(&lli->lli_sa_lock); - if (lli->lli_opendir_key == NULL && lli->lli_sai == NULL && - lli->lli_opendir_pid == 0) { - lli->lli_opendir_key = fd; - lli->lli_opendir_pid = current_pid(); - opendir_set = 1; - } - spin_unlock(&lli->lli_sa_lock); - } + if (S_ISDIR(inode->i_mode)) + ll_authorize_statahead(inode, fd); if (inode->i_sb->s_root == file->f_dentry) { LUSTRE_FPRIVATE(file) = fd; @@ -665,9 +598,20 @@ restart: would attempt to grab och_mutex as well, that would result in a deadlock */ mutex_unlock(&lli->lli_och_mutex); - it->it_create_mode |= M_CHECK_STALE; + /* + * Normally called under two situations: + * 1. NFS export. + * 2. A race/condition on MDS resulting in no open + * handle to be returned from LOOKUP|OPEN request, + * for example if the target entry was a symlink. + * + * Always fetch MDS_OPEN_LOCK if this is not setstripe. + * + * Always specify MDS_OPEN_BY_FID because we don't want + * to get file with different fid. + */ + it->it_flags |= MDS_OPEN_LOCK | MDS_OPEN_BY_FID; rc = ll_intent_file_open(file, NULL, 0, it); - it->it_create_mode &= ~M_CHECK_STALE; if (rc) GOTO(out_openerr, rc); @@ -726,10 +670,10 @@ out_och_free: mutex_unlock(&lli->lli_och_mutex); out_openerr: - if (opendir_set != 0) - ll_stop_statahead(inode, lli->lli_opendir_key); - if (fd != NULL) - ll_file_data_put(fd); + if (lli->lli_opendir_key == fd) + ll_deauthorize_statahead(inode, fd); + if (fd != NULL) + ll_file_data_put(fd); } else { ll_stats_ops_tally(ll_i2sbi(inode), LPROC_LL_OPEN, 1); } @@ -775,7 +719,7 @@ ll_lease_open(struct inode *inode, struct file *file, fmode_t fmode, struct lookup_intent it = { .it_op = IT_OPEN }; struct ll_sb_info *sbi = ll_i2sbi(inode); struct md_op_data *op_data; - struct ptlrpc_request *req; + struct ptlrpc_request *req = NULL; struct lustre_handle old_handle = { 0 }; struct obd_client_handle *och = NULL; int rc; @@ -841,15 +785,15 @@ ll_lease_open(struct inode *inode, struct file *file, fmode_t fmode, it.it_flags = fmode | open_flags; it.it_flags |= MDS_OPEN_LOCK | MDS_OPEN_BY_FID | MDS_OPEN_LEASE; - rc = md_intent_lock(sbi->ll_md_exp, op_data, NULL, 0, &it, 0, &req, - ll_md_blocking_lease_ast, + rc = md_intent_lock(sbi->ll_md_exp, op_data, &it, &req, + &ll_md_blocking_lease_ast, /* LDLM_FL_NO_LRU: To not put the lease lock into LRU list, otherwise * it can be cancelled which may mislead applications that the lease is * broken; * LDLM_FL_EXCL: Set this flag so that it won't be matched by normal * open in ll_md_blocking_ast(). Otherwise as ll_md_blocking_lease_ast * doesn't deal with openhandle, so normal openhandle will be leaked. */ - LDLM_FL_NO_LRU | LDLM_FL_EXCL); + LDLM_FL_NO_LRU | LDLM_FL_EXCL); ll_finish_md_op_data(op_data); ptlrpc_req_finished(req); if (rc < 0) @@ -940,7 +884,7 @@ static int ll_lease_close(struct obd_client_handle *och, struct inode *inode, /* Fills the obdo with the attributes for the lsm */ static int ll_lsm_getattr(struct lov_stripe_md *lsm, struct obd_export *exp, struct obd_capa *capa, struct obdo *obdo, - __u64 ioepoch, int dv_flags) + int dv_flags) { struct ptlrpc_request_set *set; struct obd_info oinfo = { { { 0 } } }; @@ -954,13 +898,11 @@ static int ll_lsm_getattr(struct lov_stripe_md *lsm, struct obd_export *exp, oinfo.oi_oa = obdo; oinfo.oi_oa->o_oi = lsm->lsm_oi; oinfo.oi_oa->o_mode = S_IFREG; - oinfo.oi_oa->o_ioepoch = ioepoch; oinfo.oi_oa->o_valid = OBD_MD_FLID | OBD_MD_FLTYPE | OBD_MD_FLSIZE | OBD_MD_FLBLOCKS | OBD_MD_FLBLKSZ | OBD_MD_FLATIME | OBD_MD_FLMTIME | OBD_MD_FLCTIME | - OBD_MD_FLGROUP | OBD_MD_FLEPOCH | - OBD_MD_FLDATAVERSION; + OBD_MD_FLGROUP | OBD_MD_FLDATAVERSION; oinfo.oi_capa = capa; if (dv_flags & (LL_DV_WR_FLUSH | LL_DV_RD_FLUSH)) { oinfo.oi_oa->o_valid |= OBD_MD_FLFLAGS; @@ -969,11 +911,11 @@ static int ll_lsm_getattr(struct lov_stripe_md *lsm, struct obd_export *exp, oinfo.oi_oa->o_flags |= OBD_FL_FLUSH; } - set = ptlrpc_prep_set(); - if (set == NULL) { - CERROR("can't allocate ptlrpc set\n"); - rc = -ENOMEM; - } else { + set = ptlrpc_prep_set(); + if (set == NULL) { + CERROR("cannot allocate ptlrpc set: rc = %d\n", -ENOMEM); + rc = -ENOMEM; + } else { rc = obd_getattr_async(exp, &oinfo, set); if (rc == 0) rc = ptlrpc_set_wait(set); @@ -992,75 +934,57 @@ static int ll_lsm_getattr(struct lov_stripe_md *lsm, struct obd_export *exp, RETURN(rc); } -/** - * Performs the getattr on the inode and updates its fields. - * If @sync != 0, perform the getattr under the server-side lock. - */ -int ll_inode_getattr(struct inode *inode, struct obdo *obdo, - __u64 ioepoch, int sync) -{ - struct obd_capa *capa = ll_mdscapa_get(inode); - struct lov_stripe_md *lsm; - int rc; - ENTRY; - - lsm = ccc_inode_lsm_get(inode); - rc = ll_lsm_getattr(lsm, ll_i2dtexp(inode), - capa, obdo, ioepoch, sync ? LL_DV_RD_FLUSH : 0); - capa_put(capa); - if (rc == 0) { - struct ost_id *oi = lsm ? &lsm->lsm_oi : &obdo->o_oi; - - obdo_refresh_inode(inode, obdo, obdo->o_valid); - CDEBUG(D_INODE, "objid "DOSTID" size %llu, blocks %llu," - " blksize %lu\n", POSTID(oi), i_size_read(inode), - (unsigned long long)inode->i_blocks, - (unsigned long)ll_inode_blksize(inode)); - } - ccc_inode_lsm_put(inode, lsm); - RETURN(rc); -} - -int ll_merge_lvb(const struct lu_env *env, struct inode *inode) +int ll_merge_attr(const struct lu_env *env, struct inode *inode) { struct ll_inode_info *lli = ll_i2info(inode); struct cl_object *obj = lli->lli_clob; struct cl_attr *attr = ccc_env_thread_attr(env); - struct ost_lvb lvb; + s64 atime; + s64 mtime; + s64 ctime; int rc = 0; ENTRY; ll_inode_size_lock(inode); + /* merge timestamps the most recently obtained from mds with timestamps obtained from osts */ - LTIME_S(inode->i_atime) = lli->lli_lvb.lvb_atime; - LTIME_S(inode->i_mtime) = lli->lli_lvb.lvb_mtime; - LTIME_S(inode->i_ctime) = lli->lli_lvb.lvb_ctime; - inode_init_lvb(inode, &lvb); + LTIME_S(inode->i_atime) = lli->lli_atime; + LTIME_S(inode->i_mtime) = lli->lli_mtime; + LTIME_S(inode->i_ctime) = lli->lli_ctime; + + atime = LTIME_S(inode->i_atime); + mtime = LTIME_S(inode->i_mtime); + ctime = LTIME_S(inode->i_ctime); cl_object_attr_lock(obj); rc = cl_object_attr_get(env, obj, attr); cl_object_attr_unlock(obj); - if (rc == 0) { - if (lvb.lvb_atime < attr->cat_atime) - lvb.lvb_atime = attr->cat_atime; - if (lvb.lvb_ctime < attr->cat_ctime) - lvb.lvb_ctime = attr->cat_ctime; - if (lvb.lvb_mtime < attr->cat_mtime) - lvb.lvb_mtime = attr->cat_mtime; + if (rc != 0) + GOTO(out_size_unlock, rc); - CDEBUG(D_VFSTRACE, DFID" updating i_size "LPU64"\n", - PFID(&lli->lli_fid), attr->cat_size); - cl_isize_write_nolock(inode, attr->cat_size); + if (atime < attr->cat_atime) + atime = attr->cat_atime; - inode->i_blocks = attr->cat_blocks; + if (ctime < attr->cat_ctime) + ctime = attr->cat_ctime; - LTIME_S(inode->i_mtime) = lvb.lvb_mtime; - LTIME_S(inode->i_atime) = lvb.lvb_atime; - LTIME_S(inode->i_ctime) = lvb.lvb_ctime; - } + if (mtime < attr->cat_mtime) + mtime = attr->cat_mtime; + + CDEBUG(D_VFSTRACE, DFID" updating i_size "LPU64"\n", + PFID(&lli->lli_fid), attr->cat_size); + + i_size_write(inode, attr->cat_size); + inode->i_blocks = attr->cat_blocks; + + LTIME_S(inode->i_atime) = atime; + LTIME_S(inode->i_mtime) = mtime; + LTIME_S(inode->i_ctime) = ctime; + +out_size_unlock: ll_inode_size_unlock(inode); RETURN(rc); @@ -1072,7 +996,7 @@ int ll_glimpse_ioctl(struct ll_sb_info *sbi, struct lov_stripe_md *lsm, struct obdo obdo = { 0 }; int rc; - rc = ll_lsm_getattr(lsm, sbi->ll_dt_exp, NULL, &obdo, 0, 0); + rc = ll_lsm_getattr(lsm, sbi->ll_dt_exp, NULL, &obdo, 0); if (rc == 0) { st->st_size = obdo.o_size; st->st_blocks = obdo.o_blocks; @@ -1138,55 +1062,86 @@ ll_file_io_generic(const struct lu_env *env, struct vvp_io_args *args, struct file *file, enum cl_io_type iot, loff_t *ppos, size_t count) { - struct ll_inode_info *lli = ll_i2info(file->f_dentry->d_inode); + struct inode *inode = file->f_dentry->d_inode; + struct ll_inode_info *lli = ll_i2info(inode); + loff_t end; struct ll_file_data *fd = LUSTRE_FPRIVATE(file); struct cl_io *io; ssize_t result; + struct range_lock range; ENTRY; - CDEBUG(D_VFSTRACE, "file: %s, type: %d ppos: "LPU64", count: %zd\n", + CDEBUG(D_VFSTRACE, "file: %s, type: %d ppos: "LPU64", count: %zu\n", file->f_dentry->d_name.name, iot, *ppos, count); restart: io = ccc_env_thread_io(env); ll_io_init(io, file, iot == CIT_WRITE); + /* The maximum Lustre file size is variable, based on the + * OST maximum object size and number of stripes. This + * needs another check in addition to the VFS checks earlier. */ + end = (io->u.ci_wr.wr_append ? i_size_read(inode) : *ppos) + count; + if (end > ll_file_maxbytes(inode)) { + result = -EFBIG; + CDEBUG(D_INODE, "%s: file "DFID" offset %llu > maxbytes "LPU64 + ": rc = %zd\n", ll_get_fsname(inode->i_sb, NULL, 0), + PFID(&lli->lli_fid), end, ll_file_maxbytes(inode), + result); + RETURN(result); + } + if (cl_io_rw_init(env, io, iot, *ppos, count) == 0) { - struct vvp_io *vio = vvp_env_io(env); - struct ccc_io *cio = ccc_env_io(env); - int write_mutex_locked = 0; - - cio->cui_fd = LUSTRE_FPRIVATE(file); - vio->cui_io_subtype = args->via_io_subtype; - - switch (vio->cui_io_subtype) { - case IO_NORMAL: - cio->cui_iov = args->u.normal.via_iov; - cio->cui_nrsegs = args->u.normal.via_nrsegs; - cio->cui_tot_nrsegs = cio->cui_nrsegs; - cio->cui_iocb = args->u.normal.via_iocb; - if ((iot == CIT_WRITE) && - !(cio->cui_fd->fd_flags & LL_FILE_GROUP_LOCKED)) { - if (mutex_lock_interruptible(&lli-> - lli_write_mutex)) - GOTO(out, result = -ERESTARTSYS); - write_mutex_locked = 1; + struct vvp_io *vio = vvp_env_io(env); + bool range_locked = false; + + if (file->f_flags & O_APPEND) + range_lock_init(&range, 0, LUSTRE_EOF); + else + range_lock_init(&range, *ppos, *ppos + count - 1); + + vio->vui_fd = LUSTRE_FPRIVATE(file); + vio->vui_io_subtype = args->via_io_subtype; + + switch (vio->vui_io_subtype) { + case IO_NORMAL: + vio->vui_iov = args->u.normal.via_iov; + vio->vui_nrsegs = args->u.normal.via_nrsegs; + vio->vui_tot_nrsegs = vio->vui_nrsegs; + vio->vui_iocb = args->u.normal.via_iocb; + if ((iot == CIT_WRITE) && + !(vio->vui_fd->fd_flags & LL_FILE_GROUP_LOCKED)) { + CDEBUG(D_VFSTRACE, "Range lock "RL_FMT"\n", + RL_PARA(&range)); + result = range_lock(&lli->lli_write_tree, + &range); + if (result < 0) + GOTO(out, result); + + range_locked = true; } down_read(&lli->lli_trunc_sem); - break; - case IO_SPLICE: - vio->u.splice.cui_pipe = args->u.splice.via_pipe; - vio->u.splice.cui_flags = args->u.splice.via_flags; - break; - default: - CERROR("Unknow IO type - %u\n", vio->cui_io_subtype); - LBUG(); - } + break; + case IO_SPLICE: + vio->u.splice.vui_pipe = args->u.splice.via_pipe; + vio->u.splice.vui_flags = args->u.splice.via_flags; + break; + default: + CERROR("unknown IO subtype %u\n", vio->vui_io_subtype); + LBUG(); + } + + ll_cl_add(file, env, io); result = cl_io_loop(env, io); + ll_cl_remove(file, env); + if (args->via_io_subtype == IO_NORMAL) up_read(&lli->lli_trunc_sem); - if (write_mutex_locked) - mutex_unlock(&lli->lli_write_mutex); + if (range_locked) { + CDEBUG(D_VFSTRACE, "Range unlock "RL_FMT"\n", + RL_PARA(&range)); + range_unlock(&lli->lli_write_tree, &range); + } } else { /* cl_io_rw_init() handled IO */ result = io->ci_result; @@ -1202,10 +1157,10 @@ out: /* If any bit been read/written (result != 0), we just return * short read/write instead of restart io. */ if ((result == 0 || result == -ENODATA) && io->ci_need_restart) { - CDEBUG(D_VFSTRACE, "Restart %s on %s from %lld, count:%zd\n", + CDEBUG(D_VFSTRACE, "Restart %s on %s from %lld, count:%zu\n", iot == CIT_READ ? "read" : "write", file->f_dentry->d_name.name, *ppos, count); - LASSERTF(io->ci_nob == 0, "%zd", io->ci_nob); + LASSERTF(io->ci_nob == 0, "%zd\n", io->ci_nob); goto restart; } @@ -1288,7 +1243,7 @@ static ssize_t ll_file_aio_read(struct kiocb *iocb, const struct iovec *iov, RETURN(result); } -static ssize_t ll_file_read(struct file *file, char *buf, size_t count, +static ssize_t ll_file_read(struct file *file, char __user *buf, size_t count, loff_t *ppos) { struct lu_env *env; @@ -1354,8 +1309,8 @@ static ssize_t ll_file_aio_write(struct kiocb *iocb, const struct iovec *iov, RETURN(result); } -static ssize_t ll_file_write(struct file *file, const char *buf, size_t count, - loff_t *ppos) +static ssize_t ll_file_write(struct file *file, const char __user *buf, + size_t count, loff_t *ppos) { struct lu_env *env; struct iovec *local_iov; @@ -1413,95 +1368,16 @@ static ssize_t ll_file_splice_read(struct file *in_file, loff_t *ppos, RETURN(result); } -static int ll_lov_recreate(struct inode *inode, struct ost_id *oi, - obd_count ost_idx) -{ - struct obd_export *exp = ll_i2dtexp(inode); - struct obd_trans_info oti = { 0 }; - struct obdo *oa = NULL; - int lsm_size; - int rc = 0; - struct lov_stripe_md *lsm = NULL, *lsm2; - ENTRY; - - OBDO_ALLOC(oa); - if (oa == NULL) - RETURN(-ENOMEM); - - lsm = ccc_inode_lsm_get(inode); - if (!lsm_has_objects(lsm)) - GOTO(out, rc = -ENOENT); - - lsm_size = sizeof(*lsm) + (sizeof(struct lov_oinfo) * - (lsm->lsm_stripe_count)); - - OBD_ALLOC_LARGE(lsm2, lsm_size); - if (lsm2 == NULL) - GOTO(out, rc = -ENOMEM); - - oa->o_oi = *oi; - oa->o_nlink = ost_idx; - oa->o_flags |= OBD_FL_RECREATE_OBJS; - oa->o_valid = OBD_MD_FLID | OBD_MD_FLFLAGS | OBD_MD_FLGROUP; - obdo_from_inode(oa, inode, OBD_MD_FLTYPE | OBD_MD_FLATIME | - OBD_MD_FLMTIME | OBD_MD_FLCTIME); - obdo_set_parent_fid(oa, &ll_i2info(inode)->lli_fid); - memcpy(lsm2, lsm, lsm_size); - ll_inode_size_lock(inode); - rc = obd_create(NULL, exp, oa, &lsm2, &oti); - ll_inode_size_unlock(inode); - - OBD_FREE_LARGE(lsm2, lsm_size); - GOTO(out, rc); -out: - ccc_inode_lsm_put(inode, lsm); - OBDO_FREE(oa); - return rc; -} - -static int ll_lov_recreate_obj(struct inode *inode, unsigned long arg) -{ - struct ll_recreate_obj ucreat; - struct ost_id oi; - ENTRY; - - if (!cfs_capable(CFS_CAP_SYS_ADMIN)) - RETURN(-EPERM); - - if (copy_from_user(&ucreat, (struct ll_recreate_obj *)arg, - sizeof(ucreat))) - RETURN(-EFAULT); - - ostid_set_seq_mdt0(&oi); - ostid_set_id(&oi, ucreat.lrc_id); - RETURN(ll_lov_recreate(inode, &oi, ucreat.lrc_ost_idx)); -} - -static int ll_lov_recreate_fid(struct inode *inode, unsigned long arg) -{ - struct lu_fid fid; - struct ost_id oi; - obd_count ost_idx; - ENTRY; - - if (!cfs_capable(CFS_CAP_SYS_ADMIN)) - RETURN(-EPERM); - - if (copy_from_user(&fid, (struct lu_fid *)arg, sizeof(fid))) - RETURN(-EFAULT); - - fid_to_ostid(&fid, &oi); - ost_idx = (fid_seq(&fid) >> 16) & 0xffff; - RETURN(ll_lov_recreate(inode, &oi, ost_idx)); -} - int ll_lov_setstripe_ea_info(struct inode *inode, struct file *file, __u64 flags, struct lov_user_md *lum, int lum_size) { struct lov_stripe_md *lsm = NULL; - struct lookup_intent oit = {.it_op = IT_OPEN, .it_flags = flags}; - int rc = 0; + struct lookup_intent oit = { + .it_op = IT_OPEN, + .it_flags = flags | MDS_OPEN_BY_FID, + }; + int rc; ENTRY; lsm = ccc_inode_lsm_get(inode); @@ -1514,11 +1390,12 @@ int ll_lov_setstripe_ea_info(struct inode *inode, struct file *file, ll_inode_size_lock(inode); rc = ll_intent_file_open(file, lum, lum_size, &oit); - if (rc) + if (rc < 0) GOTO(out_unlock, rc); + rc = oit.d.lustre.it_status; if (rc < 0) - GOTO(out_req_free, rc); + GOTO(out_unlock, rc); ll_release_openhandle(file->f_dentry, &oit); @@ -1528,10 +1405,8 @@ out_unlock: ccc_inode_lsm_put(inode, lsm); out: cl_lov_delay_create_clear(&file->f_flags); + RETURN(rc); -out_req_free: - ptlrpc_req_finished((struct ptlrpc_request *) oit.d.lustre.it_data); - goto out; } int ll_lov_getstripe_ea_info(struct inode *inode, const char *filename, @@ -1567,9 +1442,9 @@ int ll_lov_getstripe_ea_info(struct inode *inode, const char *filename, body = req_capsule_server_get(&req->rq_pill, &RMF_MDT_BODY); LASSERT(body != NULL); /* checked by mdc_getattr_name */ - lmmsize = body->eadatasize; + lmmsize = body->mbo_eadatasize; - if (!(body->valid & (OBD_MD_FLEASIZE | OBD_MD_FLDIREA)) || + if (!(body->mbo_valid & (OBD_MD_FLEASIZE | OBD_MD_FLDIREA)) || lmmsize == 0) { GOTO(out, rc = -ENODATA); } @@ -1598,13 +1473,14 @@ int ll_lov_getstripe_ea_info(struct inode *inode, const char *filename, * avoid swab not existent lsm objects */ if (lmm->lmm_magic == cpu_to_le32(LOV_MAGIC_V1)) { lustre_swab_lov_user_md_v1((struct lov_user_md_v1 *)lmm); - if (S_ISREG(body->mode)) - lustre_swab_lov_user_md_objects( - ((struct lov_user_md_v1 *)lmm)->lmm_objects, - stripe_count); - } else if (lmm->lmm_magic == cpu_to_le32(LOV_MAGIC_V3)) { - lustre_swab_lov_user_md_v3((struct lov_user_md_v3 *)lmm); - if (S_ISREG(body->mode)) + if (S_ISREG(body->mbo_mode)) + lustre_swab_lov_user_md_objects( + ((struct lov_user_md_v1 *)lmm)->lmm_objects, + stripe_count); + } else if (lmm->lmm_magic == cpu_to_le32(LOV_MAGIC_V3)) { + lustre_swab_lov_user_md_v3( + (struct lov_user_md_v3 *)lmm); + if (S_ISREG(body->mbo_mode)) lustre_swab_lov_user_md_objects( ((struct lov_user_md_v3 *)lmm)->lmm_objects, stripe_count); @@ -1635,7 +1511,7 @@ static int ll_lov_setea(struct inode *inode, struct file *file, if (lump == NULL) RETURN(-ENOMEM); - if (copy_from_user(lump, (struct lov_user_md *)arg, lum_size)) { + if (copy_from_user(lump, (struct lov_user_md __user *)arg, lum_size)) { OBD_FREE_LARGE(lump, lum_size); RETURN(-EFAULT); } @@ -1646,55 +1522,48 @@ static int ll_lov_setea(struct inode *inode, struct file *file, RETURN(rc); } +static int ll_file_getstripe(struct inode *inode, + struct lov_user_md __user *lum) +{ + struct lu_env *env; + int refcheck; + int rc; + ENTRY; + + env = cl_env_get(&refcheck); + if (IS_ERR(env)) + RETURN(PTR_ERR(env)); + + rc = cl_object_getstripe(env, ll_i2info(inode)->lli_clob, lum); + cl_env_put(env, &refcheck); + RETURN(rc); +} + static int ll_lov_setstripe(struct inode *inode, struct file *file, unsigned long arg) { - struct lov_user_md_v3 lumv3; - struct lov_user_md_v1 *lumv1 = (struct lov_user_md_v1 *)&lumv3; - struct lov_user_md_v1 *lumv1p = (struct lov_user_md_v1 *)arg; - struct lov_user_md_v3 *lumv3p = (struct lov_user_md_v3 *)arg; - int lum_size, rc; - __u64 flags = FMODE_WRITE; + struct lov_user_md __user *lum = (struct lov_user_md __user *)arg; + struct lov_user_md *klum; + int lum_size, rc; + __u64 flags = FMODE_WRITE; ENTRY; - /* first try with v1 which is smaller than v3 */ - lum_size = sizeof(struct lov_user_md_v1); - if (copy_from_user(lumv1, lumv1p, lum_size)) - RETURN(-EFAULT); - - if (lumv1->lmm_magic == LOV_USER_MAGIC_V3) { - lum_size = sizeof(struct lov_user_md_v3); - if (copy_from_user(&lumv3, lumv3p, lum_size)) - RETURN(-EFAULT); - } + rc = ll_copy_user_md(lum, &klum); + if (rc < 0) + RETURN(rc); - rc = ll_lov_setstripe_ea_info(inode, file, flags, lumv1, lum_size); + lum_size = rc; + rc = ll_lov_setstripe_ea_info(inode, file, flags, klum, lum_size); if (rc == 0) { - struct lov_stripe_md *lsm; __u32 gen; - put_user(0, &lumv1p->lmm_stripe_count); + put_user(0, &lum->lmm_stripe_count); ll_layout_refresh(inode, &gen); - lsm = ccc_inode_lsm_get(inode); - rc = obd_iocontrol(LL_IOC_LOV_GETSTRIPE, ll_i2dtexp(inode), - 0, lsm, (void *)arg); - ccc_inode_lsm_put(inode, lsm); + rc = ll_file_getstripe(inode, (struct lov_user_md __user *)arg); } - RETURN(rc); -} - -static int ll_lov_getstripe(struct inode *inode, unsigned long arg) -{ - struct lov_stripe_md *lsm; - int rc = -ENODATA; - ENTRY; - lsm = ccc_inode_lsm_get(inode); - if (lsm != NULL) - rc = obd_iocontrol(LL_IOC_LOV_GETSTRIPE, ll_i2dtexp(inode), 0, - lsm, (void *)arg); - ccc_inode_lsm_put(inode, lsm); + OBD_FREE(klum, lum_size); RETURN(rc); } @@ -1707,6 +1576,11 @@ ll_get_grouplock(struct inode *inode, struct file *file, unsigned long arg) int rc; ENTRY; + if (arg == 0) { + CWARN("group id for group lock must not be 0\n"); + RETURN(-EINVAL); + } + if (ll_file_nolock(file)) RETURN(-EOPNOTSUPP); @@ -1720,7 +1594,7 @@ ll_get_grouplock(struct inode *inode, struct file *file, unsigned long arg) LASSERT(fd->fd_grouplock.cg_lock == NULL); spin_unlock(&lli->lli_lock); - rc = cl_get_grouplock(cl_i2info(inode)->lli_clob, + rc = cl_get_grouplock(ll_i2info(inode)->lli_clob, arg, (file->f_flags & O_NONBLOCK), &grouplock); if (rc) RETURN(rc); @@ -1741,7 +1615,8 @@ ll_get_grouplock(struct inode *inode, struct file *file, unsigned long arg) RETURN(0); } -int ll_put_grouplock(struct inode *inode, struct file *file, unsigned long arg) +static int ll_put_grouplock(struct inode *inode, struct file *file, + unsigned long arg) { struct ll_inode_info *lli = ll_i2info(inode); struct ll_file_data *fd = LUSTRE_FPRIVATE(file); @@ -1821,96 +1696,93 @@ out: /** * Get size for inode for which FIEMAP mapping is requested. * Make the FIEMAP get_info call and returns the result. + * \param fiemap kernel buffer to hold extens + * \param num_bytes kernel buffer size */ -static int ll_do_fiemap(struct inode *inode, struct ll_user_fiemap *fiemap, +static int ll_do_fiemap(struct inode *inode, struct fiemap *fiemap, size_t num_bytes) { - struct obd_export *exp = ll_i2dtexp(inode); - struct lov_stripe_md *lsm = NULL; - struct ll_fiemap_info_key fm_key = { .name = KEY_FIEMAP, }; - __u32 vallen = num_bytes; - int rc; - ENTRY; + struct lu_env *env; + int refcheck; + int rc = 0; + struct ll_fiemap_info_key fmkey = { .name = KEY_FIEMAP, }; + ENTRY; - /* Checks for fiemap flags */ - if (fiemap->fm_flags & ~LUSTRE_FIEMAP_FLAGS_COMPAT) { - fiemap->fm_flags &= ~LUSTRE_FIEMAP_FLAGS_COMPAT; - return -EBADR; - } + /* Checks for fiemap flags */ + if (fiemap->fm_flags & ~LUSTRE_FIEMAP_FLAGS_COMPAT) { + fiemap->fm_flags &= ~LUSTRE_FIEMAP_FLAGS_COMPAT; + return -EBADR; + } - /* Check for FIEMAP_FLAG_SYNC */ - if (fiemap->fm_flags & FIEMAP_FLAG_SYNC) { - rc = filemap_fdatawrite(inode->i_mapping); - if (rc) - return rc; - } + /* Check for FIEMAP_FLAG_SYNC */ + if (fiemap->fm_flags & FIEMAP_FLAG_SYNC) { + rc = filemap_fdatawrite(inode->i_mapping); + if (rc) + return rc; + } - lsm = ccc_inode_lsm_get(inode); - if (lsm == NULL) - return -ENOENT; - - /* If the stripe_count > 1 and the application does not understand - * DEVICE_ORDER flag, then it cannot interpret the extents correctly. - */ - if (lsm->lsm_stripe_count > 1 && - !(fiemap->fm_flags & FIEMAP_FLAG_DEVICE_ORDER)) - GOTO(out, rc = -EOPNOTSUPP); - - fm_key.oa.o_oi = lsm->lsm_oi; - fm_key.oa.o_valid = OBD_MD_FLID | OBD_MD_FLGROUP; - - obdo_from_inode(&fm_key.oa, inode, OBD_MD_FLSIZE); - obdo_set_parent_fid(&fm_key.oa, &ll_i2info(inode)->lli_fid); - /* If filesize is 0, then there would be no objects for mapping */ - if (fm_key.oa.o_size == 0) { - fiemap->fm_mapped_extents = 0; - GOTO(out, rc = 0); - } + env = cl_env_get(&refcheck); + if (IS_ERR(env)) + RETURN(PTR_ERR(env)); - memcpy(&fm_key.fiemap, fiemap, sizeof(*fiemap)); + if (i_size_read(inode) == 0) { + rc = ll_glimpse_size(inode); + if (rc) + GOTO(out, rc); + } + + fmkey.oa.o_valid = OBD_MD_FLID | OBD_MD_FLGROUP; + obdo_from_inode(&fmkey.oa, inode, OBD_MD_FLSIZE); + obdo_set_parent_fid(&fmkey.oa, &ll_i2info(inode)->lli_fid); + + /* If filesize is 0, then there would be no objects for mapping */ + if (fmkey.oa.o_size == 0) { + fiemap->fm_mapped_extents = 0; + GOTO(out, rc = 0); + } - rc = obd_get_info(NULL, exp, sizeof(fm_key), &fm_key, &vallen, - fiemap, lsm); - if (rc) - CERROR("obd_get_info failed: rc = %d\n", rc); + fmkey.fiemap = *fiemap; + rc = cl_object_fiemap(env, ll_i2info(inode)->lli_clob, + &fmkey, fiemap, &num_bytes); out: - ccc_inode_lsm_put(inode, lsm); + cl_env_put(env, &refcheck); RETURN(rc); } -int ll_fid2path(struct inode *inode, void *arg) +int ll_fid2path(struct inode *inode, void __user *arg) { struct obd_export *exp = ll_i2mdexp(inode); - struct getinfo_fid2path *gfout, *gfin; - int outsize, rc; + const struct getinfo_fid2path __user *gfin = arg; + __u32 pathlen; + struct getinfo_fid2path *gfout; + size_t outsize; + int rc; + ENTRY; if (!cfs_capable(CFS_CAP_DAC_READ_SEARCH) && !(ll_i2sbi(inode)->ll_flags & LL_SBI_USER_FID2PATH)) RETURN(-EPERM); - /* Need to get the buflen */ - OBD_ALLOC_PTR(gfin); - if (gfin == NULL) - RETURN(-ENOMEM); - if (copy_from_user(gfin, arg, sizeof(*gfin))) { - OBD_FREE_PTR(gfin); + /* Only need to get the buflen */ + if (get_user(pathlen, &gfin->gf_pathlen)) RETURN(-EFAULT); - } - outsize = sizeof(*gfout) + gfin->gf_pathlen; + if (pathlen > PATH_MAX) + RETURN(-EINVAL); + + outsize = sizeof(*gfout) + pathlen; OBD_ALLOC(gfout, outsize); - if (gfout == NULL) { - OBD_FREE_PTR(gfin); + if (gfout == NULL) RETURN(-ENOMEM); - } - memcpy(gfout, gfin, sizeof(*gfout)); - OBD_FREE_PTR(gfin); + + if (copy_from_user(gfout, arg, sizeof(*gfout))) + GOTO(gf_free, rc = -EFAULT); /* Call mdc_iocontrol */ rc = obd_iocontrol(OBD_IOC_FID2PATH, exp, outsize, gfout, NULL); - if (rc) + if (rc != 0) GOTO(gf_free, rc); if (copy_to_user(arg, gfout, outsize)) @@ -1921,56 +1793,59 @@ gf_free: RETURN(rc); } -static int ll_ioctl_fiemap(struct inode *inode, unsigned long arg) +static int ll_ioctl_fiemap(struct inode *inode, struct fiemap __user *arg) { - struct ll_user_fiemap *fiemap_s; - size_t num_bytes, ret_bytes; - unsigned int extent_count; - int rc = 0; + struct fiemap *fiemap; + size_t num_bytes; + size_t ret_bytes; + __u32 extent_count; + int rc = 0; - /* Get the extent count so we can calculate the size of - * required fiemap buffer */ - if (get_user(extent_count, - &((struct ll_user_fiemap __user *)arg)->fm_extent_count)) - RETURN(-EFAULT); - num_bytes = sizeof(*fiemap_s) + (extent_count * - sizeof(struct ll_fiemap_extent)); + /* Get the extent count so we can calculate the size of + * required fiemap buffer */ + if (get_user(extent_count, &arg->fm_extent_count)) + RETURN(-EFAULT); - OBD_ALLOC_LARGE(fiemap_s, num_bytes); - if (fiemap_s == NULL) - RETURN(-ENOMEM); + if (extent_count >= + (SIZE_MAX - sizeof(*fiemap)) / sizeof(struct ll_fiemap_extent)) + RETURN(-EINVAL); + num_bytes = sizeof(*fiemap) + (extent_count * + sizeof(struct ll_fiemap_extent)); + + OBD_ALLOC_LARGE(fiemap, num_bytes); + if (fiemap == NULL) + RETURN(-ENOMEM); /* get the fiemap value */ - if (copy_from_user(fiemap_s, (struct ll_user_fiemap __user *)arg, - sizeof(*fiemap_s))) + if (copy_from_user(fiemap, arg, sizeof(*fiemap))) GOTO(error, rc = -EFAULT); - /* If fm_extent_count is non-zero, read the first extent since - * it is used to calculate end_offset and device from previous - * fiemap call. */ - if (extent_count) { - if (copy_from_user(&fiemap_s->fm_extents[0], - (char __user *)arg + sizeof(*fiemap_s), - sizeof(struct ll_fiemap_extent))) - GOTO(error, rc = -EFAULT); - } + /* If fm_extent_count is non-zero, read the first extent since + * it is used to calculate end_offset and device from previous + * fiemap call. */ + if (extent_count != 0) { + if (copy_from_user(&fiemap->fm_extents[0], + (char __user *)arg + sizeof(*fiemap), + sizeof(struct ll_fiemap_extent))) + GOTO(error, rc = -EFAULT); + } - rc = ll_do_fiemap(inode, fiemap_s, num_bytes); - if (rc) - GOTO(error, rc); + rc = ll_do_fiemap(inode, fiemap, num_bytes); + if (rc) + GOTO(error, rc); - ret_bytes = sizeof(struct ll_user_fiemap); + ret_bytes = sizeof(struct fiemap); - if (extent_count != 0) - ret_bytes += (fiemap_s->fm_mapped_extents * - sizeof(struct ll_fiemap_extent)); + if (extent_count != 0) + ret_bytes += (fiemap->fm_mapped_extents * + sizeof(struct ll_fiemap_extent)); - if (copy_to_user((void *)arg, fiemap_s, ret_bytes)) + if (copy_to_user((void __user *)arg, fiemap, ret_bytes)) rc = -EFAULT; error: - OBD_FREE_LARGE(fiemap_s, num_bytes); - RETURN(rc); + OBD_FREE_LARGE(fiemap, num_bytes); + RETURN(rc); } /* @@ -1979,43 +1854,31 @@ error: * This value is computed using stripe object version on OST. * Version is computed using server side locking. * - * @param sync if do sync on the OST side; + * @param flags if do sync on the OST side; * 0: no sync * LL_DV_RD_FLUSH: flush dirty pages, LCK_PR on OSTs * LL_DV_WR_FLUSH: drop all caching pages, LCK_PW on OSTs */ int ll_data_version(struct inode *inode, __u64 *data_version, int flags) { - struct lov_stripe_md *lsm = NULL; - struct ll_sb_info *sbi = ll_i2sbi(inode); - struct obdo *obdo = NULL; - int rc; + struct lu_env *env; + int refcheck; + int rc; ENTRY; - /* If no stripe, we consider version is 0. */ - lsm = ccc_inode_lsm_get(inode); - if (!lsm_has_objects(lsm)) { + /* If no file object initialized, we consider its version is 0. */ + if (ll_i2info(inode)->lli_clob == NULL) { *data_version = 0; - CDEBUG(D_INODE, "No object for inode\n"); - GOTO(out, rc = 0); + RETURN(0); } - OBD_ALLOC_PTR(obdo); - if (obdo == NULL) - GOTO(out, rc = -ENOMEM); - - rc = ll_lsm_getattr(lsm, sbi->ll_dt_exp, NULL, obdo, 0, flags); - if (rc == 0) { - if (!(obdo->o_valid & OBD_MD_FLDATAVERSION)) - rc = -EOPNOTSUPP; - else - *data_version = obdo->o_data_version; - } + env = cl_env_get(&refcheck); + if (IS_ERR(env)) + RETURN(PTR_ERR(env)); - OBD_FREE_PTR(obdo); - EXIT; -out: - ccc_inode_lsm_put(inode, lsm); + rc = cl_object_data_version(env, ll_i2info(inode)->lli_clob, + data_version, flags); + cl_env_put(env, &refcheck); RETURN(rc); } @@ -2048,7 +1911,7 @@ int ll_hsm_release(struct inode *inode) if (IS_ERR(env)) GOTO(out, rc = PTR_ERR(env)); - ll_merge_lvb(env, inode); + ll_merge_attr(env, inode); cl_env_nested_put(&nest, env); /* Release the file. @@ -2231,6 +2094,11 @@ static int ll_hsm_state_set(struct inode *inode, struct hsm_state_set *hss) { struct md_op_data *op_data; int rc; + ENTRY; + + /* Detect out-of range masks */ + if ((hss->hss_setmask | hss->hss_clearmask) & ~HSM_FLAGS_MASK) + RETURN(-EINVAL); /* Non-root users are forbidden to set or clear flags which are * NOT defined in HSM_USER_MASK. */ @@ -2238,6 +2106,11 @@ static int ll_hsm_state_set(struct inode *inode, struct hsm_state_set *hss) !cfs_capable(CFS_CAP_SYS_ADMIN)) RETURN(-EPERM); + /* Detect out-of range archive id */ + if ((hss->hss_valid & HSS_ARCHIVE_ID) && + (hss->hss_archive_id > LL_HSM_MAX_ARCHIVE)) + RETURN(-EINVAL); + op_data = ll_prep_md_op_data(NULL, inode, NULL, NULL, 0, 0, LUSTRE_OPC_ANY, hss); if (IS_ERR(op_data)) @@ -2293,10 +2166,14 @@ static int ll_hsm_import(struct inode *inode, struct file *file, ATTR_MTIME | ATTR_MTIME_SET | ATTR_ATIME | ATTR_ATIME_SET; + mutex_lock(&inode->i_mutex); + rc = ll_setattr_raw(file->f_dentry, attr, true); if (rc == -ENODATA) rc = 0; + mutex_unlock(&inode->i_mutex); + out: if (hss != NULL) OBD_FREE_PTR(hss); @@ -2307,6 +2184,12 @@ out: RETURN(rc); } +static inline long ll_lease_type_from_fmode(fmode_t fmode) +{ + return ((fmode & FMODE_READ) ? LL_LEASE_RDLCK : 0) | + ((fmode & FMODE_WRITE) ? LL_LEASE_WRLCK : 0); +} + static long ll_file_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { @@ -2326,14 +2209,14 @@ ll_file_ioctl(struct file *file, unsigned int cmd, unsigned long arg) switch(cmd) { case LL_IOC_GETFLAGS: /* Get the current value of the file flags */ - return put_user(fd->fd_flags, (int *)arg); + return put_user(fd->fd_flags, (int __user *)arg); case LL_IOC_SETFLAGS: case LL_IOC_CLRFLAGS: /* Set or clear specific file flags */ /* XXX This probably needs checks to ensure the flags are * not abused, and to handle any flag side effects. */ - if (get_user(flags, (int *) arg)) + if (get_user(flags, (int __user *) arg)) RETURN(-EFAULT); if (cmd == LL_IOC_SETFLAGS) { @@ -2357,7 +2240,7 @@ ll_file_ioctl(struct file *file, unsigned int cmd, unsigned long arg) struct file *file2; struct lustre_swap_layouts lsl; - if (copy_from_user(&lsl, (char *)arg, + if (copy_from_user(&lsl, (char __user *)arg, sizeof(struct lustre_swap_layouts))) RETURN(-EFAULT); @@ -2374,26 +2257,23 @@ ll_file_ioctl(struct file *file, unsigned int cmd, unsigned long arg) fput(file2); RETURN(rc); } - case LL_IOC_LOV_GETSTRIPE: - RETURN(ll_lov_getstripe(inode, arg)); - case LL_IOC_RECREATE_OBJ: - RETURN(ll_lov_recreate_obj(inode, arg)); - case LL_IOC_RECREATE_FID: - RETURN(ll_lov_recreate_fid(inode, arg)); - case FSFILT_IOC_FIEMAP: - RETURN(ll_ioctl_fiemap(inode, arg)); + case LL_IOC_LOV_GETSTRIPE: + RETURN(ll_file_getstripe(inode, + (struct lov_user_md __user *)arg)); + case FSFILT_IOC_FIEMAP: + RETURN(ll_ioctl_fiemap(inode, (struct fiemap __user *)arg)); case FSFILT_IOC_GETFLAGS: case FSFILT_IOC_SETFLAGS: RETURN(ll_iocontrol(inode, file, cmd, arg)); case FSFILT_IOC_GETVERSION_OLD: case FSFILT_IOC_GETVERSION: - RETURN(put_user(inode->i_generation, (int *)arg)); + RETURN(put_user(inode->i_generation, (int __user *)arg)); case LL_IOC_GROUP_LOCK: RETURN(ll_get_grouplock(inode, file, arg)); case LL_IOC_GROUP_UNLOCK: RETURN(ll_put_grouplock(inode, file, arg)); case IOC_OBD_STATFS: - RETURN(ll_obd_statfs(inode, (void *)arg)); + RETURN(ll_obd_statfs(inode, (void __user *)arg)); /* We need to special case any other ioctls we want to handle, * to send them to the MDS/OST as appropriate and to properly @@ -2404,25 +2284,29 @@ ll_file_ioctl(struct file *file, unsigned int cmd, unsigned long arg) case LL_IOC_FLUSHCTX: RETURN(ll_flush_ctx(inode)); case LL_IOC_PATH2FID: { - if (copy_to_user((void *)arg, ll_inode2fid(inode), + if (copy_to_user((void __user *)arg, ll_inode2fid(inode), sizeof(struct lu_fid))) RETURN(-EFAULT); RETURN(0); } + case LL_IOC_GETPARENT: + RETURN(ll_getparent(file, (struct getparent __user *)arg)); + case OBD_IOC_FID2PATH: - RETURN(ll_fid2path(inode, (void *)arg)); + RETURN(ll_fid2path(inode, (void __user *)arg)); case LL_IOC_DATA_VERSION: { struct ioc_data_version idv; int rc; - if (copy_from_user(&idv, (char *)arg, sizeof(idv))) + if (copy_from_user(&idv, (char __user *)arg, sizeof(idv))) RETURN(-EFAULT); idv.idv_flags &= LL_DV_RD_FLUSH | LL_DV_WR_FLUSH; rc = ll_data_version(inode, &idv.idv_version, idv.idv_flags); - if (rc == 0 && copy_to_user((char *) arg, &idv, sizeof(idv))) + if (rc == 0 && + copy_to_user((char __user *)arg, &idv, sizeof(idv))) RETURN(-EFAULT); RETURN(rc); @@ -2435,7 +2319,7 @@ ll_file_ioctl(struct file *file, unsigned int cmd, unsigned long arg) if (mdtidx < 0) RETURN(mdtidx); - if (put_user((int)mdtidx, (int*)arg)) + if (put_user((int)mdtidx, (int __user *)arg)) RETURN(-EFAULT); RETURN(0); @@ -2462,7 +2346,7 @@ ll_file_ioctl(struct file *file, unsigned int cmd, unsigned long arg) rc = obd_iocontrol(cmd, ll_i2mdexp(inode), sizeof(*op_data), op_data, NULL); - if (copy_to_user((void *)arg, hus, sizeof(*hus))) + if (copy_to_user((void __user *)arg, hus, sizeof(*hus))) rc = -EFAULT; ll_finish_md_op_data(op_data); @@ -2477,7 +2361,7 @@ ll_file_ioctl(struct file *file, unsigned int cmd, unsigned long arg) if (hss == NULL) RETURN(-ENOMEM); - if (copy_from_user(hss, (char *)arg, sizeof(*hss))) { + if (copy_from_user(hss, (char __user *)arg, sizeof(*hss))) { OBD_FREE_PTR(hss); RETURN(-EFAULT); } @@ -2506,7 +2390,7 @@ ll_file_ioctl(struct file *file, unsigned int cmd, unsigned long arg) rc = obd_iocontrol(cmd, ll_i2mdexp(inode), sizeof(*op_data), op_data, NULL); - if (copy_to_user((char *)arg, hca, sizeof(*hca))) + if (copy_to_user((char __user *)arg, hca, sizeof(*hca))) rc = -EFAULT; ll_finish_md_op_data(op_data); @@ -2517,20 +2401,20 @@ ll_file_ioctl(struct file *file, unsigned int cmd, unsigned long arg) struct ll_inode_info *lli = ll_i2info(inode); struct obd_client_handle *och = NULL; bool lease_broken; - fmode_t mode = 0; + fmode_t fmode; switch (arg) { - case F_WRLCK: + case LL_LEASE_WRLCK: if (!(file->f_mode & FMODE_WRITE)) RETURN(-EPERM); - mode = FMODE_WRITE; + fmode = FMODE_WRITE; break; - case F_RDLCK: + case LL_LEASE_RDLCK: if (!(file->f_mode & FMODE_READ)) RETURN(-EPERM); - mode = FMODE_READ; + fmode = FMODE_READ; break; - case F_UNLCK: + case LL_LEASE_UNLCK: mutex_lock(&lli->lli_och_mutex); if (fd->fd_lease_och != NULL) { och = fd->fd_lease_och; @@ -2538,25 +2422,26 @@ ll_file_ioctl(struct file *file, unsigned int cmd, unsigned long arg) } mutex_unlock(&lli->lli_och_mutex); - if (och != NULL) { - mode = och->och_flags &(FMODE_READ|FMODE_WRITE); - rc = ll_lease_close(och, inode, &lease_broken); - if (rc == 0 && lease_broken) - mode = 0; - } else { - rc = -ENOLCK; - } + if (och == NULL) + RETURN(-ENOLCK); - /* return the type of lease or error */ - RETURN(rc < 0 ? rc : (int)mode); + fmode = och->och_flags; + rc = ll_lease_close(och, inode, &lease_broken); + if (rc < 0) + RETURN(rc); + + if (lease_broken) + fmode = 0; + + RETURN(ll_lease_type_from_fmode(fmode)); default: RETURN(-EINVAL); } - CDEBUG(D_INODE, "Set lease with mode %d\n", mode); + CDEBUG(D_INODE, "Set lease with mode %u\n", fmode); /* apply for lease */ - och = ll_lease_open(inode, file, mode, 0); + och = ll_lease_open(inode, file, fmode, 0); if (IS_ERR(och)) RETURN(PTR_ERR(och)); @@ -2577,8 +2462,8 @@ ll_file_ioctl(struct file *file, unsigned int cmd, unsigned long arg) case LL_IOC_GET_LEASE: { struct ll_inode_info *lli = ll_i2info(inode); struct ldlm_lock *lock = NULL; + fmode_t fmode = 0; - rc = 0; mutex_lock(&lli->lli_och_mutex); if (fd->fd_lease_och != NULL) { struct obd_client_handle *och = fd->fd_lease_och; @@ -2587,14 +2472,15 @@ ll_file_ioctl(struct file *file, unsigned int cmd, unsigned long arg) if (lock != NULL) { lock_res_and_lock(lock); if (!ldlm_is_cancel(lock)) - rc = och->och_flags & - (FMODE_READ | FMODE_WRITE); + fmode = och->och_flags; + unlock_res_and_lock(lock); LDLM_LOCK_PUT(lock); } } mutex_unlock(&lli->lli_och_mutex); - RETURN(rc); + + RETURN(ll_lease_type_from_fmode(fmode)); } case LL_IOC_HSM_IMPORT: { struct hsm_user_import *hui; @@ -2603,7 +2489,7 @@ ll_file_ioctl(struct file *file, unsigned int cmd, unsigned long arg) if (hui == NULL) RETURN(-ENOMEM); - if (copy_from_user(hui, (void *)arg, sizeof(*hui))) { + if (copy_from_user(hui, (void __user *)arg, sizeof(*hui))) { OBD_FREE_PTR(hui); RETURN(-EFAULT); } @@ -2622,7 +2508,7 @@ ll_file_ioctl(struct file *file, unsigned int cmd, unsigned long arg) RETURN(err); RETURN(obd_iocontrol(cmd, ll_i2dtexp(inode), 0, NULL, - (void *)arg)); + (void __user *)arg)); } } } @@ -2773,7 +2659,7 @@ int cl_sync_file_range(struct inode *inode, loff_t start, loff_t end, capa = ll_osscapa_get(inode, CAPA_OPC_OSS_WRITE); io = ccc_env_thread_io(env); - io->ci_obj = cl_i2info(inode)->lli_clob; + io->ci_obj = ll_i2info(inode)->lli_clob; io->ci_ignore_layout = ignore_layout; /* initialize parameters for sync */ @@ -2990,8 +2876,8 @@ ll_file_flock(struct file *file, int cmd, struct file_lock *file_lock) flock.l_flock.pid, flags, einfo.ei_mode, flock.l_flock.start, flock.l_flock.end); - rc = md_enqueue(sbi->ll_md_exp, &einfo, NULL, - op_data, &lockh, &flock, 0, NULL /* req */, flags); + rc = md_enqueue(sbi->ll_md_exp, &einfo, &flock, NULL, op_data, &lockh, + flags); /* Restore the file lock type if not TEST lock. */ if (!(flags & LDLM_FL_TEST_LOCK)) @@ -3007,8 +2893,8 @@ ll_file_flock(struct file *file, int cmd, struct file_lock *file_lock) if (rc2 && file_lock->fl_type != F_UNLCK) { einfo.ei_mode = LCK_NL; - md_enqueue(sbi->ll_md_exp, &einfo, NULL, - op_data, &lockh, &flock, 0, NULL /* req */, flags); + md_enqueue(sbi->ll_md_exp, &einfo, &flock, NULL, op_data, + &lockh, flags); rc = rc2; } @@ -3041,7 +2927,7 @@ int ll_get_fid_by_name(struct inode *parent, const char *name, if (body == NULL) GOTO(out_req, rc = -EFAULT); if (fid != NULL) - *fid = body->fid1; + *fid = body->mbo_fid1; out_req: ptlrpc_req_finished(req); RETURN(rc); @@ -3071,11 +2957,14 @@ int ll_migrate(struct inode *parent, struct file *file, int mdtidx, qstr.name = name; qstr.len = namelen; dchild = d_lookup(file->f_dentry, &qstr); - if (dchild != NULL && dchild->d_inode != NULL) { - op_data->op_fid3 = *ll_inode2fid(dchild->d_inode); + if (dchild != NULL) { if (dchild->d_inode != NULL) { child_inode = igrab(dchild->d_inode); - ll_invalidate_aliases(child_inode); + if (child_inode != NULL) { + mutex_lock(&child_inode->i_mutex); + op_data->op_fid3 = *ll_inode2fid(child_inode); + ll_invalidate_aliases(child_inode); + } } dput(dchild); } else { @@ -3116,6 +3005,7 @@ int ll_migrate(struct inode *parent, struct file *file, int mdtidx, out_free: if (child_inode != NULL) { clear_nlink(child_inode); + mutex_unlock(&child_inode->i_mutex); iput(child_inode); } @@ -3252,14 +3142,9 @@ static int __ll_inode_revalidate(struct dentry *dentry, __u64 ibits) if (IS_ERR(op_data)) RETURN(PTR_ERR(op_data)); - oit.it_create_mode |= M_CHECK_STALE; - rc = md_intent_lock(exp, op_data, NULL, 0, - /* we are not interested in name - based lookup */ - &oit, 0, &req, - ll_md_blocking_ast, 0); + rc = md_intent_lock(exp, op_data, &oit, &req, + &ll_md_blocking_ast, 0); ll_finish_md_op_data(op_data); - oit.it_create_mode &= ~M_CHECK_STALE; if (rc < 0) { rc = ll_inode_revalidate_fini(inode, rc); GOTO (out, rc); @@ -3280,10 +3165,10 @@ static int __ll_inode_revalidate(struct dentry *dentry, __u64 ibits) ll_lookup_finish_locks(&oit, dentry); } else if (!ll_have_md_lock(dentry->d_inode, &ibits, LCK_MINMODE)) { - struct ll_sb_info *sbi = ll_i2sbi(dentry->d_inode); - obd_valid valid = OBD_MD_FLGETATTR; - struct md_op_data *op_data; - int ealen = 0; + struct ll_sb_info *sbi = ll_i2sbi(dentry->d_inode); + u64 valid = OBD_MD_FLGETATTR; + struct md_op_data *op_data; + int ealen = 0; if (S_ISREG(inode->i_mode)) { rc = ll_get_default_mdsize(sbi, &ealen); @@ -3323,16 +3208,17 @@ static int ll_merge_md_attr(struct inode *inode) LASSERT(ll_i2info(inode)->lli_lsm_md != NULL); rc = md_merge_attr(ll_i2mdexp(inode), ll_i2info(inode)->lli_lsm_md, - &attr); + &attr, ll_md_blocking_ast); if (rc != 0) RETURN(rc); - ll_i2info(inode)->lli_stripe_dir_size = attr.cat_size; - ll_i2info(inode)->lli_stripe_dir_nlink = attr.cat_nlink; + set_nlink(inode, attr.cat_nlink); + inode->i_blocks = attr.cat_blocks; + i_size_write(inode, attr.cat_size); - ll_i2info(inode)->lli_lvb.lvb_atime = attr.cat_atime; - ll_i2info(inode)->lli_lvb.lvb_mtime = attr.cat_mtime; - ll_i2info(inode)->lli_lvb.lvb_ctime = attr.cat_ctime; + ll_i2info(inode)->lli_atime = attr.cat_atime; + ll_i2info(inode)->lli_mtime = attr.cat_mtime; + ll_i2info(inode)->lli_ctime = attr.cat_ctime; RETURN(0); } @@ -3357,9 +3243,9 @@ ll_inode_revalidate(struct dentry *dentry, __u64 ibits) RETURN(rc); } - LTIME_S(inode->i_atime) = ll_i2info(inode)->lli_lvb.lvb_atime; - LTIME_S(inode->i_mtime) = ll_i2info(inode)->lli_lvb.lvb_mtime; - LTIME_S(inode->i_ctime) = ll_i2info(inode)->lli_lvb.lvb_ctime; + LTIME_S(inode->i_atime) = ll_i2info(inode)->lli_atime; + LTIME_S(inode->i_mtime) = ll_i2info(inode)->lli_mtime; + LTIME_S(inode->i_ctime) = ll_i2info(inode)->lli_ctime; } else { /* In case of restore, the MDT has the right size and has * already send it back without granting the layout lock, @@ -3401,16 +3287,10 @@ int ll_getattr(struct vfsmount *mnt, struct dentry *de, struct kstat *stat) stat->mtime = inode->i_mtime; stat->ctime = inode->i_ctime; stat->blksize = 1 << inode->i_blkbits; - stat->blocks = inode->i_blocks; - if (S_ISDIR(inode->i_mode) && - ll_i2info(inode)->lli_lsm_md != NULL) { - stat->nlink = lli->lli_stripe_dir_nlink; - stat->size = lli->lli_stripe_dir_size; - } else { - stat->nlink = inode->i_nlink; - stat->size = i_size_read(inode); - } + stat->nlink = inode->i_nlink; + stat->size = i_size_read(inode); + stat->blocks = inode->i_blocks; return 0; } @@ -3507,8 +3387,14 @@ int ll_inode_permission(struct inode *inode, int mask, struct nameidata *nd) # endif #endif { - int rc = 0; - ENTRY; + int rc = 0; + struct ll_sb_info *sbi; + struct root_squash_info *squash; + struct cred *cred = NULL; + const struct cred *old_cred = NULL; + cfs_cap_t cap; + bool squash_id = false; + ENTRY; #ifdef MAY_NOT_BLOCK if (mask & MAY_NOT_BLOCK) @@ -3531,11 +3417,46 @@ int ll_inode_permission(struct inode *inode, int mask, struct nameidata *nd) CDEBUG(D_VFSTRACE, "VFS Op:inode="DFID"(%p), inode mode %x mask %o\n", PFID(ll_inode2fid(inode)), inode, inode->i_mode, mask); - if (ll_i2sbi(inode)->ll_flags & LL_SBI_RMT_CLIENT) - return lustre_check_remote_perm(inode, mask); + /* squash fsuid/fsgid if needed */ + sbi = ll_i2sbi(inode); + squash = &sbi->ll_squash; + if (unlikely(squash->rsi_uid != 0 && + uid_eq(current_fsuid(), GLOBAL_ROOT_UID) && + !(sbi->ll_flags & LL_SBI_NOROOTSQUASH))) { + squash_id = true; + } + if (squash_id) { + CDEBUG(D_OTHER, "squash creds (%d:%d)=>(%d:%d)\n", + __kuid_val(current_fsuid()), __kgid_val(current_fsgid()), + squash->rsi_uid, squash->rsi_gid); + + /* update current process's credentials + * and FS capability */ + cred = prepare_creds(); + if (cred == NULL) + RETURN(-ENOMEM); - ll_stats_ops_tally(ll_i2sbi(inode), LPROC_LL_INODE_PERM, 1); - rc = ll_generic_permission(inode, mask, flags, ll_check_acl); + cred->fsuid = make_kuid(&init_user_ns, squash->rsi_uid); + cred->fsgid = make_kgid(&init_user_ns, squash->rsi_gid); + for (cap = 0; cap < sizeof(cfs_cap_t) * 8; cap++) { + if ((1 << cap) & CFS_CAP_FS_MASK) + cap_lower(cred->cap_effective, cap); + } + old_cred = override_creds(cred); + } + + ll_stats_ops_tally(sbi, LPROC_LL_INODE_PERM, 1); + + if (sbi->ll_flags & LL_SBI_RMT_CLIENT) + rc = lustre_check_remote_perm(inode, mask); + else + rc = ll_generic_permission(inode, mask, flags, ll_check_acl); + + /* restore current process's credentials and FS capability */ + if (squash_id) { + revert_creds(old_cred); + put_cred(cred); + } RETURN(rc); } @@ -3608,15 +3529,15 @@ struct inode_operations ll_file_inode_operations = { /* dynamic ioctl number support routins */ static struct llioc_ctl_data { struct rw_semaphore ioc_sem; - cfs_list_t ioc_head; + struct list_head ioc_head; } llioc = { - __RWSEM_INITIALIZER(llioc.ioc_sem), - CFS_LIST_HEAD_INIT(llioc.ioc_head) + __RWSEM_INITIALIZER(llioc.ioc_sem), + LIST_HEAD_INIT(llioc.ioc_head) }; struct llioc_data { - cfs_list_t iocd_list; + struct list_head iocd_list; unsigned int iocd_size; llioc_callback_t iocd_cb; unsigned int iocd_count; @@ -3645,7 +3566,7 @@ void *ll_iocontrol_register(llioc_callback_t cb, int count, unsigned int *cmd) memcpy(in_data->iocd_cmd, cmd, sizeof(unsigned int) * count); down_write(&llioc.ioc_sem); - cfs_list_add_tail(&in_data->iocd_list, &llioc.ioc_head); + list_add_tail(&in_data->iocd_list, &llioc.ioc_head); up_write(&llioc.ioc_sem); RETURN(in_data); @@ -3659,11 +3580,11 @@ void ll_iocontrol_unregister(void *magic) return; down_write(&llioc.ioc_sem); - cfs_list_for_each_entry(tmp, &llioc.ioc_head, iocd_list) { + list_for_each_entry(tmp, &llioc.ioc_head, iocd_list) { if (tmp == magic) { unsigned int size = tmp->iocd_size; - cfs_list_del(&tmp->iocd_list); + list_del(&tmp->iocd_list); up_write(&llioc.ioc_sem); OBD_FREE(tmp, size); @@ -3687,7 +3608,7 @@ ll_iocontrol_call(struct inode *inode, struct file *file, int rc = -EINVAL, i; down_read(&llioc.ioc_sem); - cfs_list_for_each_entry(data, &llioc.ioc_head, iocd_list) { + list_for_each_entry(data, &llioc.ioc_head, iocd_list) { for (i = 0; i < data->iocd_count; i++) { if (cmd != data->iocd_cmd[i]) continue; @@ -3793,7 +3714,7 @@ static int ll_layout_fetch(struct inode *inode, struct ldlm_lock *lock) if (body == NULL) GOTO(out, rc = -EPROTO); - lmmsize = body->eadatasize; + lmmsize = body->mbo_eadatasize; if (lmmsize == 0) /* empty layout */ GOTO(out, rc = 0); @@ -3844,7 +3765,7 @@ static int ll_layout_lock_set(struct lustre_handle *lockh, ldlm_mode_t mode, LASSERT(lock != NULL); LASSERT(ldlm_has_layout(lock)); - LDLM_DEBUG(lock, "file "DFID"(%p) being reconfigured: %d\n", + LDLM_DEBUG(lock, "file "DFID"(%p) being reconfigured: %d", PFID(&lli->lli_fid), inode, reconf); /* in case this is a caching lock and reinstate with new inode */ @@ -3956,8 +3877,8 @@ int ll_layout_refresh(struct inode *inode, __u32 *gen) struct ldlm_enqueue_info einfo = { .ei_type = LDLM_IBITS, .ei_mode = LCK_CR, - .ei_cb_bl = ll_md_blocking_ast, - .ei_cb_cp = ldlm_completion_ast, + .ei_cb_bl = &ll_md_blocking_ast, + .ei_cb_cp = &ldlm_completion_ast, }; int rc; ENTRY; @@ -3999,12 +3920,11 @@ again: it.it_op = IT_LAYOUT; lockh.cookie = 0ULL; - LDLM_DEBUG_NOLOCK("%s: requeue layout lock for file "DFID"(%p)\n", + LDLM_DEBUG_NOLOCK("%s: requeue layout lock for file "DFID"(%p)", ll_get_fsname(inode->i_sb, NULL, 0), PFID(&lli->lli_fid), inode); - rc = md_enqueue(sbi->ll_md_exp, &einfo, &it, op_data, &lockh, - NULL, 0, NULL, 0); + rc = md_enqueue(sbi->ll_md_exp, &einfo, NULL, &it, op_data, &lockh, 0); if (it.d.lustre.it_data != NULL) ptlrpc_req_finished(it.d.lustre.it_data); it.d.lustre.it_data = NULL; @@ -4050,9 +3970,8 @@ int ll_layout_restore(struct inode *inode, loff_t offset, __u64 length) hur->hur_user_item[0].hui_extent.offset = offset; hur->hur_user_item[0].hui_extent.length = length; hur->hur_request.hr_itemcount = 1; - rc = obd_iocontrol(LL_IOC_HSM_REQUEST, cl_i2sbi(inode)->ll_md_exp, + rc = obd_iocontrol(LL_IOC_HSM_REQUEST, ll_i2sbi(inode)->ll_md_exp, len, hur, NULL); OBD_FREE(hur, len); RETURN(rc); } -