*/
/*
* This file is part of Lustre, http://www.lustre.org/
- * Lustre is a trademark of Sun Microsystems, Inc.
*/
#include <linux/fs.h>
#include <linux/sched.h>
#include <linux/mm.h>
+#include <linux/file.h>
#include <linux/quotaops.h>
#include <linux/highmem.h>
#include <linux/pagemap.h>
-#include <linux/security.h>
#include <linux/user_namespace.h>
#include <linux/uidgid.h>
RETURN(inode);
}
-static void ll_invalidate_negative_children(struct inode *dir)
+/* mark negative sub file dentries invalid and prune unused dentries */
+static void ll_prune_negative_children(struct inode *dir)
{
- struct dentry *dentry, *tmp_subdir;
+ struct dentry *dentry;
+ struct dentry *child;
+ ENTRY;
+
+restart:
spin_lock(&dir->i_lock);
hlist_for_each_entry(dentry, &dir->i_dentry, d_alias) {
spin_lock(&dentry->d_lock);
- if (!list_empty(&dentry->d_subdirs)) {
- struct dentry *child;
-
- list_for_each_entry_safe(child, tmp_subdir,
- &dentry->d_subdirs,
- d_child) {
- if (child->d_inode == NULL)
- d_lustre_invalidate(child, 1);
+ list_for_each_entry(child, &dentry->d_subdirs, d_child) {
+ if (child->d_inode)
+ continue;
+
+ spin_lock_nested(&child->d_lock, DENTRY_D_LOCK_NESTED);
+ __d_lustre_invalidate(child);
+ if (!ll_d_count(child)) {
+ dget_dlock(child);
+ __d_drop(child);
+ spin_unlock(&child->d_lock);
+ spin_unlock(&dentry->d_lock);
+ spin_unlock(&dir->i_lock);
+
+ CDEBUG(D_DENTRY, "prune negative dentry %pd\n",
+ child);
+
+ dput(child);
+ goto restart;
}
+ spin_unlock(&child->d_lock);
}
spin_unlock(&dentry->d_lock);
}
spin_unlock(&dir->i_lock);
+
+ EXIT;
}
int ll_test_inode_by_fid(struct inode *inode, void *opaque)
int rc;
ENTRY;
- if (!lli->lli_clob) {
- /* due to DoM read on open, there may exist pages for Lustre
- * regular file even though cl_object is not set up yet. */
- truncate_inode_pages(inode->i_mapping, 0);
- RETURN(0);
- }
-
env = cl_env_get(&refcheck);
if (IS_ERR(env))
RETURN(PTR_ERR(env));
+ OBD_FAIL_TIMEOUT(OBD_FAIL_LDLM_REPLAY_PAUSE, cfs_fail_val);
+
/* reach MDC layer to flush data under the DoM ldlm lock */
rc = cl_object_flush(env, lli->lli_clob, lock);
if (rc == -ENODATA) {
lli = ll_i2info(inode);
if (bits & MDS_INODELOCK_UPDATE)
- ll_file_set_flag(lli, LLIF_UPDATE_ATIME);
+ set_bit(LLIF_UPDATE_ATIME, &lli->lli_flags);
if ((bits & MDS_INODELOCK_UPDATE) && S_ISDIR(inode->i_mode)) {
CDEBUG(D_INODE, "invalidating inode "DFID" lli = %p, "
ll_test_inode_by_fid,
(void *)&lli->lli_pfid);
if (master_inode) {
- ll_invalidate_negative_children(master_inode);
+ ll_prune_negative_children(master_inode);
iput(master_inode);
}
} else {
- ll_invalidate_negative_children(inode);
+ ll_prune_negative_children(inode);
}
}
if ((bits & (MDS_INODELOCK_LOOKUP | MDS_INODELOCK_PERM)) &&
- inode->i_sb->s_root != NULL &&
- inode != inode->i_sb->s_root->d_inode)
- ll_invalidate_aliases(inode);
+ !is_root_inode(inode))
+ ll_prune_aliases(inode);
if (bits & (MDS_INODELOCK_LOOKUP | MDS_INODELOCK_PERM))
forget_all_cached_acls(inode);
if (rc < 0)
return ERR_PTR(rc);
d_add(de, inode);
+
+ /* this needs only to be done for foreign symlink dirs as
+ * DCACHE_SYMLINK_TYPE is already set by d_flags_for_inode()
+ * kernel routine for files with symlink ops (ie, real symlink)
+ */
+ if (inode && S_ISDIR(inode->i_mode) &&
+ ll_sbi_has_foreign_symlink(ll_i2sbi(inode)) &&
+#ifdef HAVE_IOP_GET_LINK
+ inode->i_op->get_link) {
+#else
+ inode->i_op->follow_link) {
+#endif
+ CDEBUG(D_INFO, "%s: inode "DFID": faking foreign dir as a symlink\n",
+ ll_i2sbi(inode)->ll_fsname, PFID(ll_inode2fid(inode)));
+ spin_lock(&de->d_lock);
+ /* like d_flags_for_inode() already does for files */
+ de->d_flags = (de->d_flags & ~DCACHE_ENTRY_TYPE) |
+ DCACHE_SYMLINK_TYPE;
+ spin_unlock(&de->d_lock);
+ }
+
CDEBUG(D_DENTRY, "Add dentry %p inode %p refc %d flags %#x\n",
de, de->d_inode, ll_d_count(de), de->d_flags);
return de;
struct mdt_body *body = req_capsule_server_get(pill,
&RMF_MDT_BODY);
- rc = ll_prep_inode(&inode, request, (*de)->d_sb, it);
+ rc = ll_prep_inode(&inode, &request->rq_pill, (*de)->d_sb, it);
if (rc)
RETURN(rc);
- if (it->it_op & IT_OPEN)
- ll_dom_finish_open(inode, request, it);
+ /* If encryption context was returned by MDT, put it in
+ * inode now to save an extra getxattr and avoid deadlock.
+ */
+ if (body->mbo_valid & OBD_MD_ENCCTX) {
+ encctx = req_capsule_server_get(pill, &RMF_FILE_ENCCTX);
+ encctxlen = req_capsule_get_size(pill,
+ &RMF_FILE_ENCCTX,
+ RCL_SERVER);
+
+ if (encctxlen) {
+ CDEBUG(D_SEC,
+ "server returned encryption ctx for "DFID"\n",
+ PFID(ll_inode2fid(inode)));
+ rc = ll_xattr_cache_insert(inode,
+ LL_XATTR_NAME_ENCRYPTION_CONTEXT,
+ encctx, encctxlen);
+ if (rc)
+ CWARN("%s: cannot set enc ctx for "DFID": rc = %d\n",
+ ll_i2sbi(inode)->ll_fsname,
+ PFID(ll_inode2fid(inode)), rc);
+ else if (encrypt) {
+ rc = llcrypt_get_encryption_info(inode);
+ if (rc)
+ CDEBUG(D_SEC,
+ "cannot get enc info for "DFID": rc = %d\n",
+ PFID(ll_inode2fid(inode)), rc);
+ }
+ }
+ }
ll_set_lock_data(ll_i2sbi(parent)->ll_md_exp, inode, it, &bits);
+ /* OPEN can return data if lock has DoM+LAYOUT bits set */
+ if (it->it_op & IT_OPEN &&
+ bits & MDS_INODELOCK_DOM && bits & MDS_INODELOCK_LAYOUT)
+ ll_dom_finish_open(inode, request);
/* We used to query real size from OSTs here, but actually
* this is not needed. For stat() calls size would be updated
PFID(ll_inode2fid(inode)),
rc);
}
-
- /* If encryption context was returned by MDT, put it in
- * inode now to save an extra getxattr and avoid deadlock.
- */
- if (body->mbo_valid & OBD_MD_ENCCTX) {
- encctx = req_capsule_server_get(pill, &RMF_FILE_ENCCTX);
- encctxlen = req_capsule_get_size(pill,
- &RMF_FILE_ENCCTX,
- RCL_SERVER);
-
- if (encctxlen) {
- CDEBUG(D_SEC,
- "server returned encryption ctx for "DFID"\n",
- PFID(ll_inode2fid(inode)));
- rc = ll_xattr_cache_insert(inode,
- LL_XATTR_NAME_ENCRYPTION_CONTEXT,
- encctx, encctxlen);
- if (rc)
- CWARN("%s: cannot set enc ctx for "DFID": rc = %d\n",
- ll_i2sbi(inode)->ll_fsname,
- PFID(ll_inode2fid(inode)), rc);
- }
- }
}
/* Only hash *de if it is unhashed (new dentry).
out:
if (rc != 0 && it->it_op & IT_OPEN) {
ll_intent_drop_lock(it);
- ll_open_cleanup((*de)->d_sb, request);
+ ll_open_cleanup((*de)->d_sb, &request->rq_pill);
}
return rc;
*secctxlen = 0;
}
if (it->it_op & IT_CREAT && encrypt) {
- rc = llcrypt_inherit_context(parent, NULL, op_data, false);
- if (rc)
- GOTO(out, retval = ERR_PTR(rc));
+ /* Volatile file name may look like:
+ * <parent>/LUSTRE_VOLATILE_HDR:<mdt_index>:<random>:fd=<fd>
+ * where fd is opened descriptor of reference file.
+ */
+ if (unlikely(filename_is_volatile(dentry->d_name.name,
+ dentry->d_name.len, NULL))) {
+ int ctx_size = LLCRYPT_ENC_CTX_SIZE;
+ struct lustre_sb_info *lsi;
+ struct file *ref_file;
+ struct inode *ref_inode;
+ char *p, *q, *fd_str;
+ void *ctx;
+ int fd;
+
+ p = strnstr(dentry->d_name.name, ":fd=",
+ dentry->d_name.len);
+ if (!p || strlen(p + 4) == 0)
+ GOTO(out, retval = ERR_PTR(-EINVAL));
+
+ q = strchrnul(p + 4, ':');
+ fd_str = kstrndup(p + 4, q - p - 4, GFP_NOFS);
+ if (!fd_str)
+ GOTO(out, retval = ERR_PTR(-ENOMEM));
+ rc = kstrtouint(fd_str, 10, &fd);
+ kfree(fd_str);
+ if (rc)
+ GOTO(inherit, rc = -EINVAL);
+
+ ref_file = fget(fd);
+ if (!ref_file)
+ GOTO(inherit, rc = -EINVAL);
+
+ ref_inode = file_inode(ref_file);
+ if (!ref_inode) {
+ fput(ref_file);
+ GOTO(inherit, rc = -EINVAL);
+ }
+
+ lsi = s2lsi(ref_inode->i_sb);
+
+getctx:
+ OBD_ALLOC(ctx, ctx_size);
+ if (!ctx)
+ GOTO(out, retval = ERR_PTR(-ENOMEM));
+
+#ifdef CONFIG_LL_ENCRYPTION
+ rc = lsi->lsi_cop->get_context(ref_inode,
+ ctx, ctx_size);
+#else
+ rc = -ENODATA;
+#endif
+ if (rc == -ERANGE) {
+ OBD_FREE(ctx, ctx_size);
+ ctx_size *= 2;
+ goto getctx;
+ }
+ fput(ref_file);
+ if (rc < 0) {
+ OBD_FREE(ctx, ctx_size);
+ GOTO(inherit, rc);
+ }
+
+ op_data->op_file_encctx_size = rc;
+ if (rc == ctx_size) {
+ op_data->op_file_encctx = ctx;
+ } else {
+ OBD_ALLOC(op_data->op_file_encctx,
+ op_data->op_file_encctx_size);
+ if (!op_data->op_file_encctx) {
+ OBD_FREE(ctx, ctx_size);
+ GOTO(out, retval = ERR_PTR(-ENOMEM));
+ }
+ memcpy(op_data->op_file_encctx, ctx,
+ op_data->op_file_encctx_size);
+ OBD_FREE(ctx, ctx_size);
+ }
+
+ } else {
+inherit:
+ rc = llcrypt_inherit_context(parent, NULL, op_data,
+ false);
+ if (rc)
+ GOTO(out, retval = ERR_PTR(rc));
+ }
if (encctx != NULL)
*encctx = op_data->op_file_encctx;
if (encctxlen != NULL)
}
if (pca && pca->pca_dataset) {
- struct pcc_dataset *dataset = pca->pca_dataset;
-
OBD_ALLOC_PTR(lum);
if (lum == NULL)
GOTO(out, retval = ERR_PTR(-ENOMEM));
lum->lmm_pattern = LOV_PATTERN_F_RELEASED | LOV_PATTERN_RAID0;
op_data->op_data = lum;
op_data->op_data_size = sizeof(*lum);
- op_data->op_archive_id = dataset->pccd_rwid;
-
- rc = obd_fid_alloc(NULL, ll_i2mdexp(parent), &op_data->op_fid2,
- op_data);
- if (rc)
- GOTO(out, retval = ERR_PTR(rc));
-
- rc = pcc_inode_create(parent->i_sb, dataset, &op_data->op_fid2,
- &pca->pca_dentry);
- if (rc)
- GOTO(out, retval = ERR_PTR(rc));
-
+ op_data->op_archive_id = pca->pca_dataset->pccd_rwid;
it->it_flags |= MDS_OPEN_PCC;
}
if (rc < 0)
GOTO(out, retval = ERR_PTR(rc));
+ if (pca && pca->pca_dataset) {
+ rc = pcc_inode_create(parent->i_sb, pca->pca_dataset,
+ &op_data->op_fid2,
+ &pca->pca_dentry);
+ if (rc)
+ GOTO(out, retval = ERR_PTR(rc));
+ }
+
/* dir layout may change */
ll_unlock_md_op_lsm(op_data);
rc = ll_lookup_it_finish(req, it, parent, &dentry,
it->it_flags &= ~MDS_OPEN_FL_INTERNAL;
if (ll_sbi_has_encrypt(ll_i2sbi(dir)) && IS_ENCRYPTED(dir)) {
- /* we know that we are going to create a regular file because
+ /* in case of create, this is going to be a regular file because
* we set S_IFREG bit on it->it_create_mode above
*/
rc = llcrypt_get_encryption_info(dir);
if (rc)
GOTO(out_release, rc);
- if (!llcrypt_has_encryption_key(dir))
- GOTO(out_release, rc = -ENOKEY);
- encrypt = true;
- rc = 0;
+ if (open_flags & O_CREAT) {
+ if (!llcrypt_has_encryption_key(dir))
+ GOTO(out_release, rc = -ENOKEY);
+ encrypt = true;
+ }
}
+ OBD_FAIL_TIMEOUT(OBD_FAIL_LLITE_CREATE_FILE_PAUSE2, cfs_fail_val);
+
+ /* We can only arrive at this path when we have no inode, so
+ * we only need to request open lock if it was requested
+ * for every open
+ */
+ if (ll_i2sbi(dir)->ll_oc_thrsh_count == 1 &&
+ exp_connect_flags2(ll_i2mdexp(dir)) &
+ OBD_CONNECT2_ATOMIC_OPEN_LOCK)
+ it->it_flags |= MDS_OPEN_LOCK;
+
/* Dentry added to dcache tree in ll_lookup_it */
de = ll_lookup_it(dir, dentry, it, &secctx, &secctxlen, &pca, encrypt,
&encctx, &encctxlen);
/* Dentry instantiated in ll_create_it. */
rc = ll_create_it(dir, dentry, it, secctx, secctxlen,
encrypt, encctx, encctxlen);
- security_release_secctx(secctx, secctxlen);
+ ll_security_release_secctx(secctx, secctxlen);
llcrypt_free_ctx(encctx, encctxlen);
if (rc) {
/* We dget in ll_splice_alias. */
}
}
- if (dentry->d_inode && it_disposition(it, DISP_OPEN_OPEN)) {
+ /* check also if a foreign file is openable */
+ if (dentry->d_inode && it_disposition(it, DISP_OPEN_OPEN) &&
+ ll_foreign_is_openable(dentry, open_flags)) {
/* Open dentry. */
if (S_ISFIFO(dentry->d_inode->i_mode)) {
/* We cannot call open here as it might
LASSERT(it_disposition(it, DISP_ENQ_CREATE_REF));
request = it->it_request;
- it_clear_disposition(it, DISP_ENQ_CREATE_REF);
- rc = ll_prep_inode(&inode, request, dir->i_sb, it);
- if (rc)
- GOTO(out, inode = ERR_PTR(rc));
+ it_clear_disposition(it, DISP_ENQ_CREATE_REF);
+ rc = ll_prep_inode(&inode, &request->rq_pill, dir->i_sb, it);
+ if (rc)
+ GOTO(out, inode = ERR_PTR(rc));
/* Pause to allow for a race with concurrent access by fid */
OBD_FAIL_TIMEOUT(OBD_FAIL_LLITE_CREATE_NODE_PAUSE, cfs_fail_val);
md.default_lmv->lsm_md_master_mdt_index =
lum->lum_stripe_offset;
md.default_lmv->lsm_md_hash_type = lum->lum_hash_type;
+ md.default_lmv->lsm_md_max_inherit =
+ lum->lum_max_inherit;
+ md.default_lmv->lsm_md_max_inherit_rr =
+ lum->lum_max_inherit_rr;
err = ll_update_inode(dir, &md);
md_free_lustre_md(sbi->ll_md_exp, &md);
CFS_FAIL_TIMEOUT(OBD_FAIL_LLITE_NEWNODE_PAUSE, cfs_fail_val);
- err = ll_prep_inode(&inode, request, dchild->d_sb, NULL);
+ err = ll_prep_inode(&inode, &request->rq_pill, dchild->d_sb, NULL);
if (err)
GOTO(err_exit, err);
if (unlikely(d_mountpoint(dchild)))
RETURN(-EBUSY);
+ /* some foreign dir may not be allowed to be removed */
+ if (!ll_foreign_is_removable(dchild, false))
+ RETURN(-EPERM);
+
op_data = ll_prep_md_op_data(NULL, dir, NULL, name->name, name->len,
S_IFDIR, LUSTRE_OPC_ANY, NULL);
if (IS_ERR(op_data))
op_data->op_fid2 = op_data->op_fid3;
rc = md_unlink(ll_i2sbi(dir)->ll_md_exp, op_data, &request);
ll_finish_md_op_data(op_data);
- if (!rc)
- ll_update_times(request, dir);
+ if (!rc) {
+ struct mdt_body *body;
- ptlrpc_req_finished(request);
- if (!rc)
+ ll_update_times(request, dir);
ll_stats_ops_tally(ll_i2sbi(dir), LPROC_LL_RMDIR,
ktime_us_delta(ktime_get(), kstart));
+
+ /*
+ * The server puts attributes in on the last unlink, use them
+ * to update the link count so the inode can be freed
+ * immediately.
+ */
+ body = req_capsule_server_get(&request->rq_pill, &RMF_MDT_BODY);
+ if (body->mbo_valid & OBD_MD_FLNLINK)
+ set_nlink(dchild->d_inode, body->mbo_nlink);
+ }
+
+ ptlrpc_req_finished(request);
+
RETURN(rc);
}
if (unlikely(d_mountpoint(dchild)))
RETURN(-EBUSY);
+ /* some foreign file/dir may not be allowed to be unlinked */
+ if (!ll_foreign_is_removable(dchild, false))
+ RETURN(-EPERM);
+
op_data = ll_prep_md_op_data(NULL, dir, NULL, name->name, name->len, 0,
LUSTRE_OPC_ANY, NULL);
if (IS_ERR(op_data))
struct ll_sb_info *sbi = ll_i2sbi(src);
struct md_op_data *op_data;
ktime_t kstart = ktime_get();
+ umode_t mode = 0;
int err;
ENTRY;
#endif
if (err)
RETURN(err);
+ /* we prevent an encrypted file from being renamed
+ * into an unencrypted dir
+ */
+ if (IS_ENCRYPTED(src) && !IS_ENCRYPTED(tgt))
+ RETURN(-EXDEV);
+
+ if (src_dchild->d_inode)
+ mode = src_dchild->d_inode->i_mode;
+
+ if (tgt_dchild->d_inode)
+ mode = tgt_dchild->d_inode->i_mode;
- op_data = ll_prep_md_op_data(NULL, src, tgt, NULL, 0, 0,
+ op_data = ll_prep_md_op_data(NULL, src, tgt, NULL, 0, mode,
LUSTRE_OPC_ANY, NULL);
if (IS_ERR(op_data))
RETURN(PTR_ERR(op_data));
- if (src_dchild->d_inode != NULL)
+ if (src_dchild->d_inode)
op_data->op_fid3 = *ll_inode2fid(src_dchild->d_inode);
- if (tgt_dchild->d_inode != NULL)
+ if (tgt_dchild->d_inode)
op_data->op_fid4 = *ll_inode2fid(tgt_dchild->d_inode);
err = md_rename(sbi->ll_md_exp, op_data,
git://git.whamcloud.com / fs / lustre-release.git / blobdiff