#include <linux/random.h>
#include <linux/statfs.h>
#include <linux/time.h>
+#include <linux/file.h>
#include <linux/types.h>
#include <libcfs/linux/linux-uuid.h>
#include <linux/version.h>
unsigned long lru_page_max;
struct sysinfo si;
int rc;
- int i;
ENTRY;
#endif
set_bit(LL_SBI_LAZYSTATFS, sbi->ll_flags);
- for (i = 0; i <= LL_PROCESS_HIST_MAX; i++) {
- spin_lock_init(&sbi->ll_rw_extents_info.pp_extents[i].
- pp_r_hist.oh_lock);
- spin_lock_init(&sbi->ll_rw_extents_info.pp_extents[i].
- pp_w_hist.oh_lock);
- }
-
/* metadata statahead is enabled by default */
sbi->ll_sa_running_max = LL_SA_RUNNING_DEF;
sbi->ll_sa_max = LL_SA_RPC_DEF;
sizeof(struct ll_foreign_symlink_upcall_item));
sbi->ll_foreign_symlink_upcall_items = NULL;
}
+ ll_free_rw_stats_info(sbi);
pcc_super_fini(&sbi->ll_pcc_super);
OBD_FREE(sbi, sizeof(*sbi));
}
u64 valid;
int size, err, checksum;
bool api32;
+ void *encctx;
+ int encctxlen;
ENTRY;
sbi->ll_md_obd = class_name2obd(md);
sb->s_maxbytes = MAX_LFS_FILESIZE;
sbi->ll_namelen = osfs->os_namelen;
sbi->ll_mnt.mnt = current->fs->root.mnt;
+ sbi->ll_mnt_ns = current->nsproxy->mnt_ns;
if (test_bit(LL_SBI_USER_XATTR, sbi->ll_flags) &&
!(data->ocd_connect_flags & OBD_CONNECT_XATTR)) {
/* make root inode
* XXX: move this to after cbd setup? */
- valid = OBD_MD_FLGETATTR | OBD_MD_FLBLOCKS | OBD_MD_FLMODEASIZE;
+ valid = OBD_MD_FLGETATTR | OBD_MD_FLBLOCKS | OBD_MD_FLMODEASIZE |
+ OBD_MD_ENCCTX;
if (test_bit(LL_SBI_ACL, sbi->ll_flags))
valid |= OBD_MD_FLACL;
err = md_getattr(sbi->ll_md_exp, op_data, &request);
+ /* We need enc ctx info, so reset it in op_data to
+ * prevent it from being freed.
+ */
+ encctx = op_data->op_file_encctx;
+ encctxlen = op_data->op_file_encctx_size;
+ op_data->op_file_encctx = NULL;
+ op_data->op_file_encctx_size = 0;
OBD_FREE_PTR(op_data);
if (err) {
CERROR("%s: md_getattr failed for root: rc = %d\n",
api32 = test_bit(LL_SBI_32BIT_API, sbi->ll_flags);
root = ll_iget(sb, cl_fid_build_ino(&sbi->ll_root_fid, api32), &lmd);
md_free_lustre_md(sbi->ll_md_exp, &lmd);
- ptlrpc_req_finished(request);
if (IS_ERR(root)) {
lmd_clear_acl(&lmd);
root = NULL;
CERROR("%s: bad ll_iget() for root: rc = %d\n",
sbi->ll_fsname, err);
+ ptlrpc_req_finished(request);
GOTO(out_root, err);
}
+ if (encctxlen) {
+ CDEBUG(D_SEC,
+ "server returned encryption ctx for root inode "DFID"\n",
+ PFID(&sbi->ll_root_fid));
+ err = ll_set_encflags(root, encctx, encctxlen, true);
+ if (err)
+ CWARN("%s: cannot set enc ctx for "DFID": rc = %d\n",
+ sbi->ll_fsname,
+ PFID(&sbi->ll_root_fid), err);
+ }
+ ptlrpc_req_finished(request);
+
checksum = test_bit(LL_SBI_CHECKSUM, sbi->ll_flags);
if (sbi->ll_checksum_set) {
err = obd_set_info_async(NULL, sbi->ll_dt_exp,
if (err)
GOTO(out_free_cfg, err);
+ /* disable kernel readahead */
+ sb->s_bdi->ra_pages = 0;
+
/* Call ll_debugfs_register_super() before lustre_process_log()
* so that "llite.*.*" params can be processed correctly.
*/
!S_ISDIR(inode->i_mode)) {
ia_valid = op_data->op_attr.ia_valid;
op_data->op_attr.ia_valid &= ~TIMES_SET_FLAGS;
- rc = simple_setattr(dentry, &op_data->op_attr);
+ rc = simple_setattr(&init_user_ns, dentry,
+ &op_data->op_attr);
op_data->op_attr.ia_valid = ia_valid;
}
} else if (rc != -EPERM && rc != -EACCES && rc != -ETXTBSY) {
op_data->op_attr.ia_valid &= ~(TIMES_SET_FLAGS | ATTR_SIZE);
if (S_ISREG(inode->i_mode))
inode_lock(inode);
- rc = simple_setattr(dentry, &op_data->op_attr);
+ rc = simple_setattr(&init_user_ns, dentry, &op_data->op_attr);
if (S_ISREG(inode->i_mode))
inode_unlock(inode);
op_data->op_attr.ia_valid = ia_valid;
RETURN(rc);
}
+/**
+ * Get reference file from volatile file name.
+ * Volatile file name may look like:
+ * <parent>/LUSTRE_VOLATILE_HDR:<mdt_index>:<random>:fd=<fd>
+ * where fd is opened descriptor of reference file.
+ *
+ * \param[in] volatile_name volatile file name
+ * \param[in] volatile_len volatile file name length
+ * \param[out] ref_file pointer to struct file of reference file
+ *
+ * \retval 0 on success
+ * \retval negative errno on failure
+ */
+int volatile_ref_file(const char *volatile_name, int volatile_len,
+ struct file **ref_file)
+{
+ char *p, *q, *fd_str;
+ int fd, rc;
+
+ p = strnstr(volatile_name, ":fd=", volatile_len);
+ if (!p || strlen(p + 4) == 0)
+ return -EINVAL;
+
+ q = strchrnul(p + 4, ':');
+ fd_str = kstrndup(p + 4, q - p - 4, GFP_NOFS);
+ if (!fd_str)
+ return -ENOMEM;
+ rc = kstrtouint(fd_str, 10, &fd);
+ kfree(fd_str);
+ if (rc)
+ return -EINVAL;
+
+ *ref_file = fget(fd);
+ if (!(*ref_file))
+ return -EINVAL;
+ return 0;
+}
+
/* If this inode has objects allocated to it (lsm != NULL), then the OST
* object(s) determine the file size and mtime. Otherwise, the MDS will
* keep these values until such a time that objects are allocated for it.
if (rc)
GOTO(out, rc);
}
+ /* If encrypted volatile file without the key,
+ * we need to fetch size from reference file,
+ * and set it on OST objects. This happens when
+ * migrating or extending an encrypted file
+ * without the key.
+ */
+ if (filename_is_volatile(dentry->d_name.name,
+ dentry->d_name.len,
+ NULL) &&
+ llcrypt_require_key(inode) == -ENOKEY) {
+ struct file *ref_file;
+ struct inode *ref_inode;
+ struct ll_inode_info *ref_lli;
+ struct cl_object *ref_obj;
+ struct cl_attr ref_attr = { 0 };
+ struct lu_env *env;
+ __u16 refcheck;
+
+ rc = volatile_ref_file(
+ dentry->d_name.name,
+ dentry->d_name.len,
+ &ref_file);
+ if (rc)
+ GOTO(out, rc);
+
+ ref_inode = file_inode(ref_file);
+ if (!ref_inode) {
+ fput(ref_file);
+ GOTO(out, rc = -EINVAL);
+ }
+
+ env = cl_env_get(&refcheck);
+ if (IS_ERR(env))
+ GOTO(out, rc = PTR_ERR(env));
+
+ ref_lli = ll_i2info(ref_inode);
+ ref_obj = ref_lli->lli_clob;
+ cl_object_attr_lock(ref_obj);
+ rc = cl_object_attr_get(env, ref_obj,
+ &ref_attr);
+ cl_object_attr_unlock(ref_obj);
+ cl_env_put(env, &refcheck);
+ fput(ref_file);
+ if (rc)
+ GOTO(out, rc);
+
+ attr->ia_valid |= ATTR_SIZE;
+ attr->ia_size = ref_attr.cat_size;
+ }
}
rc = cl_setattr_ost(lli->lli_clob, attr, xvalid, flags);
}
LPROC_LL_TRUNC : LPROC_LL_SETATTR,
ktime_us_delta(ktime_get(), kstart));
- return rc;
+ RETURN(rc);
}
-int ll_setattr(struct dentry *de, struct iattr *attr)
+int ll_setattr(struct user_namespace *mnt_userns, struct dentry *de,
+ struct iattr *attr)
{
int mode = de->d_inode->i_mode;
enum op_xvalid xvalid = 0;
LASSERT(fid_seq(&lli->lli_fid) != 0);
- lli->lli_attr_valid = body->mbo_valid;
+ /* In case of encrypted file without the key, please do not lose
+ * clear text size stored into lli_lazysize in ll_merge_attr(),
+ * we will need it in ll_prepare_close().
+ */
+ if (lli->lli_attr_valid & OBD_MD_FLLAZYSIZE && lli->lli_lazysize &&
+ llcrypt_require_key(inode) == -ENOKEY)
+ lli->lli_attr_valid = body->mbo_valid | OBD_MD_FLLAZYSIZE;
+ else
+ lli->lli_attr_valid = body->mbo_valid;
if (body->mbo_valid & OBD_MD_FLSIZE) {
i_size_write(inode, body->mbo_size);
return;
lli = ll_i2info(inode);
- lli->lli_depth = ll_i2info(dir)->lli_depth + 1;
- CDEBUG(D_INODE, DFID" depth %hu\n", PFID(&lli->lli_fid), lli->lli_depth);
+ lli->lli_dir_depth = ll_i2info(dir)->lli_dir_depth + 1;
+ CDEBUG(D_INODE, DFID" depth %hu\n",
+ PFID(&lli->lli_fid), lli->lli_dir_depth);
}
void ll_truncate_inode_pages_final(struct inode *inode)
if (namelen != 0)
return ERR_PTR(-EINVAL);
} else {
- if (namelen > ll_i2sbi(i1)->ll_namelen)
+ if ((!IS_ENCRYPTED(i1) ||
+ (opc != LUSTRE_OPC_LOOKUP && opc != LUSTRE_OPC_CREATE)) &&
+ namelen > ll_i2sbi(i1)->ll_namelen)
return ERR_PTR(-ENAMETOOLONG);
/* "/" is not valid name, but it's allowed */
if (ll_need_32bit_api(ll_i2sbi(i1)))
op_data->op_cli_flags |= CLI_API32;
- if (opc == LUSTRE_OPC_LOOKUP || opc == LUSTRE_OPC_CREATE) {
+ if ((i2 && is_root_inode(i2)) ||
+ opc == LUSTRE_OPC_LOOKUP || opc == LUSTRE_OPC_CREATE) {
/* In case of lookup, ll_setup_filename() has already been
* called in ll_lookup_it(), so just take provided name.
+ * Also take provided name if we are dealing with root inode.
*/
fname.disk_name.name = (unsigned char *)name;
fname.disk_name.len = namelen;
op_data->op_flags |= MF_OPNAME_KMALLOCED;
}
- /* In fact LUSTRE_OPC_LOOKUP, LUSTRE_OPC_OPEN, LUSTRE_OPC_MIGR
+ /* In fact LUSTRE_OPC_LOOKUP, LUSTRE_OPC_OPEN
* are LUSTRE_OPC_ANY
*/
- if (opc == LUSTRE_OPC_LOOKUP || opc == LUSTRE_OPC_OPEN ||
- opc == LUSTRE_OPC_MIGR)
+ if (opc == LUSTRE_OPC_LOOKUP || opc == LUSTRE_OPC_OPEN)
op_data->op_code = LUSTRE_OPC_ANY;
else
op_data->op_code = opc;