* Copyright (c) 2002, 2010, Oracle and/or its affiliates. All rights reserved.
* Use is subject to license terms.
*
- * Copyright (c) 2011, 2012, Intel Corporation.
+ * Copyright (c) 2011, 2013, Intel Corporation.
*/
/*
* This file is part of Lustre, http://www.lustre.org/
{
struct ll_file_data *fd;
- OBD_SLAB_ALLOC_PTR_GFP(fd, ll_file_data_slab, CFS_ALLOC_IO);
+ OBD_SLAB_ALLOC_PTR_GFP(fd, ll_file_data_slab, __GFP_IO);
+ if (fd == NULL)
+ return NULL;
+
fd->fd_write_failed = false;
+
return fd;
}
{
ENTRY;
- op_data->op_attr.ia_valid = ATTR_MODE | ATTR_ATIME_SET |
- ATTR_MTIME_SET | ATTR_CTIME_SET;
+ op_data->op_attr.ia_valid = ATTR_MODE | ATTR_ATIME | ATTR_ATIME_SET |
+ ATTR_MTIME | ATTR_MTIME_SET |
+ ATTR_CTIME | ATTR_CTIME_SET;
if (!(och->och_flags & FMODE_WRITE))
goto out;
}
}
-static int ll_och_fill(struct obd_export *md_exp, struct ll_inode_info *lli,
- struct lookup_intent *it, struct obd_client_handle *och)
+static int ll_och_fill(struct obd_export *md_exp, struct lookup_intent *it,
+ struct obd_client_handle *och)
{
- struct ptlrpc_request *req = it->d.lustre.it_data;
- struct mdt_body *body;
-
- LASSERT(och);
-
- body = req_capsule_server_get(&req->rq_pill, &RMF_MDT_BODY);
- LASSERT(body != NULL); /* reply already checked out */
+ struct ptlrpc_request *req = it->d.lustre.it_data;
+ struct mdt_body *body;
- memcpy(&och->och_fh, &body->handle, sizeof(body->handle));
- och->och_magic = OBD_CLIENT_HANDLE_MAGIC;
- och->och_fid = lli->lli_fid;
- och->och_flags = it->it_flags;
- ll_ioepoch_open(lli, body->ioepoch);
+ body = req_capsule_server_get(&req->rq_pill, &RMF_MDT_BODY);
+ och->och_fh = body->handle;
+ och->och_fid = body->fid1;
+ och->och_magic = OBD_CLIENT_HANDLE_MAGIC;
+ och->och_flags = it->it_flags;
- return md_set_open_replay_data(md_exp, och, req);
+ return md_set_open_replay_data(md_exp, och, req);
}
int ll_local_open(struct file *file, struct lookup_intent *it,
struct mdt_body *body;
int rc;
- rc = ll_och_fill(ll_i2sbi(inode)->ll_md_exp, lli, it, och);
- if (rc)
- RETURN(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);
- if ((it->it_flags & FMODE_WRITE) &&
- (body->valid & OBD_MD_FLSIZE))
- CDEBUG(D_INODE, "Epoch "LPU64" opened on "DFID"\n",
- lli->lli_ioepoch, PFID(&lli->lli_fid));
- }
+ 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;
- LUSTRE_FPRIVATE(file) = fd;
- ll_readahead_init(inode, &fd->fd_ras);
- fd->fd_omode = it->it_flags;
- RETURN(0);
+ RETURN(0);
}
/* Open a file, and (for the very first open) create objects on the OSTs at
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_och_free, rc = -ENOMEM);
+ fd = ll_file_data_get();
+ if (fd == NULL)
+ GOTO(out_openerr, rc = -ENOMEM);
- fd->fd_file = file;
- if (S_ISDIR(inode->i_mode)) {
+ 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) {
opendir_set = 1;
}
spin_unlock(&lli->lli_sa_lock);
- }
+ }
if (inode->i_sb->s_root == file->f_dentry) {
LUSTRE_FPRIVATE(file) = fd;
cl_io_fini(env, io);
/* If any bit been read/written (result != 0), we just return
* short read/write instead of restart io. */
- if (result == 0 && io->ci_need_restart) {
+ if ((result == 0 || result == -ENODATA) && io->ci_need_restart) {
CDEBUG(D_VFSTRACE, "Restart %s on %s from %lld, count:%zd\n",
iot == CIT_READ ? "read" : "write",
file->f_dentry->d_name.name, *ppos, count);
}
#endif
-
-#ifdef HAVE_KERNEL_SENDFILE
-/*
- * Send file content (through pagecache) somewhere with helper
- */
-static ssize_t ll_file_sendfile(struct file *in_file, loff_t *ppos,size_t count,
- read_actor_t actor, void *target)
-{
- struct lu_env *env;
- struct vvp_io_args *args;
- ssize_t result;
- int refcheck;
- ENTRY;
-
- env = cl_env_get(&refcheck);
- if (IS_ERR(env))
- RETURN(PTR_ERR(env));
-
- args = vvp_env_args(env, IO_SENDFILE);
- args->u.sendfile.via_target = target;
- args->u.sendfile.via_actor = actor;
-
- result = ll_file_io_generic(env, args, in_file, CIT_READ, ppos, count);
- cl_env_put(env, &refcheck);
- RETURN(result);
-}
-#endif
-
-#ifdef HAVE_KERNEL_SPLICE_READ
/*
* Send file content (through pagecache) somewhere with helper
*/
cl_env_put(env, &refcheck);
RETURN(result);
}
-#endif
static int ll_lov_recreate(struct inode *inode, struct ost_id *oi,
obd_count ost_idx)
RETURN(-ENOMEM);
lsm = ccc_inode_lsm_get(inode);
- if (lsm == NULL)
+ if (!lsm_has_objects(lsm))
GOTO(out, rc = -ENOENT);
lsm_size = sizeof(*lsm) + (sizeof(struct lov_oinfo) *
* passing it to userspace.
*/
if (LOV_MAGIC != cpu_to_le32(LOV_MAGIC)) {
+ int stripe_count;
+
+ stripe_count = le16_to_cpu(lmm->lmm_stripe_count);
+ if (le32_to_cpu(lmm->lmm_pattern) & LOV_PATTERN_F_RELEASED)
+ stripe_count = 0;
+
/* if function called for directory - we should
* avoid swab not existent lsm objects */
if (lmm->lmm_magic == cpu_to_le32(LOV_MAGIC_V1)) {
if (S_ISREG(body->mode))
lustre_swab_lov_user_md_objects(
((struct lov_user_md_v1 *)lmm)->lmm_objects,
- ((struct lov_user_md_v1 *)lmm)->lmm_stripe_count);
+ 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))
lustre_swab_lov_user_md_objects(
((struct lov_user_md_v3 *)lmm)->lmm_objects,
- ((struct lov_user_md_v3 *)lmm)->lmm_stripe_count);
+ stripe_count);
}
}
if (!och)
GOTO(out, rc = -ENOMEM);
- ll_och_fill(ll_i2sbi(inode)->ll_md_exp,
- ll_i2info(inode), it, och);
+ ll_och_fill(ll_i2sbi(inode)->ll_md_exp, it, och);
rc = ll_close_inode_openhandle(ll_i2sbi(inode)->ll_md_exp,
inode, och);
/* If no stripe, we consider version is 0. */
lsm = ccc_inode_lsm_get(inode);
- if (lsm == NULL) {
+ if (!lsm_has_objects(lsm)) {
*data_version = 0;
CDEBUG(D_INODE, "No object for inode\n");
- RETURN(0);
+ GOTO(out, rc = 0);
}
OBD_ALLOC_PTR(obdo);
- if (obdo == NULL) {
- ccc_inode_lsm_put(inode, lsm);
- RETURN(-ENOMEM);
- }
+ if (obdo == NULL)
+ GOTO(out, rc = -ENOMEM);
rc = ll_lsm_getattr(lsm, sbi->ll_dt_exp, NULL, obdo, 0, extent_lock);
- if (!rc) {
+ if (rc == 0) {
if (!(obdo->o_valid & OBD_MD_FLDATAVERSION))
rc = -EOPNOTSUPP;
else
}
OBD_FREE_PTR(obdo);
+ EXIT;
+out:
ccc_inode_lsm_put(inode, lsm);
-
RETURN(rc);
}
if (!S_ISREG(llss->inode2->i_mode))
GOTO(free, rc = -EINVAL);
- if (ll_permission(llss->inode1, MAY_WRITE, NULL) ||
- ll_permission(llss->inode2, MAY_WRITE, NULL))
+ if (inode_permission(llss->inode1, MAY_WRITE) ||
+ inode_permission(llss->inode2, MAY_WRITE))
GOTO(free, rc = -EPERM);
if (llss->inode2->i_sb != llss->inode1->i_sb)
rc = -ENOMEM;
op_data = ll_prep_md_op_data(NULL, llss->inode1, llss->inode2, NULL, 0,
0, LUSTRE_OPC_ANY, &msl);
- if (op_data != NULL) {
- rc = obd_iocontrol(LL_IOC_LOV_SWAP_LAYOUTS,
- ll_i2mdexp(llss->inode1),
- sizeof(*op_data), op_data, NULL);
- ll_finish_md_op_data(op_data);
- }
+ if (IS_ERR(op_data))
+ GOTO(free, rc = PTR_ERR(op_data));
+
+ rc = obd_iocontrol(LL_IOC_LOV_SWAP_LAYOUTS, ll_i2mdexp(llss->inode1),
+ sizeof(*op_data), op_data, NULL);
+ ll_finish_md_op_data(op_data);
putgl:
if (gid != 0) {
struct file *file2;
struct lustre_swap_layouts lsl;
- if (cfs_copy_from_user(&lsl, (char *)arg,
+ if (copy_from_user(&lsl, (char *)arg,
sizeof(struct lustre_swap_layouts)))
RETURN(-EFAULT);
op_data = ll_prep_md_op_data(NULL, inode, NULL, NULL, 0, 0,
LUSTRE_OPC_ANY, hus);
- if (op_data == NULL) {
+ if (IS_ERR(op_data)) {
OBD_FREE_PTR(hus);
- RETURN(-ENOMEM);
+ RETURN(PTR_ERR(op_data));
}
rc = obd_iocontrol(cmd, ll_i2mdexp(inode), sizeof(*op_data),
op_data = ll_prep_md_op_data(NULL, inode, NULL, NULL, 0, 0,
LUSTRE_OPC_ANY, hss);
- if (op_data == NULL) {
+ if (IS_ERR(op_data)) {
OBD_FREE_PTR(hss);
- RETURN(-ENOMEM);
+ RETURN(PTR_ERR(op_data));
}
rc = obd_iocontrol(cmd, ll_i2mdexp(inode), sizeof(*op_data),
op_data = ll_prep_md_op_data(NULL, inode, NULL, NULL, 0, 0,
LUSTRE_OPC_ANY, hca);
- if (op_data == NULL) {
+ if (IS_ERR(op_data)) {
OBD_FREE_PTR(hca);
- RETURN(-ENOMEM);
+ RETURN(PTR_ERR(op_data));
}
rc = obd_iocontrol(cmd, ll_i2mdexp(inode), sizeof(*op_data),
op_data, NULL);
- if (cfs_copy_to_user((char *)arg, hca, sizeof(*hca)))
+ if (copy_to_user((char *)arg, hca, sizeof(*hca)))
rc = -EFAULT;
ll_finish_md_op_data(op_data);
int ll_file_flock(struct file *file, int cmd, struct file_lock *file_lock)
{
- struct inode *inode = file->f_dentry->d_inode;
- struct ll_sb_info *sbi = ll_i2sbi(inode);
- struct ldlm_enqueue_info einfo = { .ei_type = LDLM_FLOCK,
- .ei_cb_cp =ldlm_flock_completion_ast,
- .ei_cbdata = file_lock };
- struct md_op_data *op_data;
- struct lustre_handle lockh = {0};
- ldlm_policy_data_t flock = {{0}};
- int flags = 0;
- int rc;
+ struct inode *inode = file->f_dentry->d_inode;
+ struct ll_sb_info *sbi = ll_i2sbi(inode);
+ struct ldlm_enqueue_info einfo = {
+ .ei_type = LDLM_FLOCK,
+ .ei_cb_cp = ldlm_flock_completion_ast,
+ .ei_cbdata = file_lock,
+ };
+ struct md_op_data *op_data;
+ struct lustre_handle lockh = {0};
+ ldlm_policy_data_t flock = {{0}};
+ int flags = 0;
+ int rc;
int rc2 = 0;
- ENTRY;
+ ENTRY;
CDEBUG(D_VFSTRACE, "VFS Op:inode=%lu file_lock=%p\n",
inode->i_ino, file_lock);
CDEBUG(D_INFO, "trying to match res "DFID" mode %s\n", PFID(fid),
ldlm_lockname[mode]);
- flags = LDLM_FL_BLOCK_GRANTED | LDLM_FL_CBPENDING | LDLM_FL_TEST_LOCK;
- for (i = 0; i < MDS_INODELOCK_MAXSHIFT && *bits != 0; i++) {
- policy.l_inodebits.bits = *bits & (1 << i);
- if (policy.l_inodebits.bits == 0)
- continue;
+ flags = LDLM_FL_BLOCK_GRANTED | LDLM_FL_CBPENDING | LDLM_FL_TEST_LOCK;
+ for (i = 0; i <= MDS_INODELOCK_MAXSHIFT && *bits != 0; i++) {
+ policy.l_inodebits.bits = *bits & (1 << i);
+ if (policy.l_inodebits.bits == 0)
+ continue;
if (md_lock_match(ll_i2mdexp(inode), flags, fid, LDLM_IBITS,
&policy, mode, &lockh)) {
here to preserve get_cwd functionality on 2.6.
Bug 10503 */
if (!dentry->d_inode->i_nlink)
- d_lustre_invalidate(dentry);
+ d_lustre_invalidate(dentry, 0);
ll_lookup_finish_locks(&oit, dentry);
} else if (!ll_have_md_lock(dentry->d_inode, &ibits, LCK_MINMODE)) {
}
int ll_inode_revalidate_it(struct dentry *dentry, struct lookup_intent *it,
- __u64 ibits)
+ __u64 ibits)
{
- struct inode *inode = dentry->d_inode;
- int rc;
- ENTRY;
+ struct inode *inode = dentry->d_inode;
+ int rc;
+ ENTRY;
- rc = __ll_inode_revalidate_it(dentry, it, ibits);
+ rc = __ll_inode_revalidate_it(dentry, it, ibits);
if (rc != 0)
RETURN(rc);
LTIME_S(inode->i_mtime) = ll_i2info(inode)->lli_lvb.lvb_mtime;
LTIME_S(inode->i_ctime) = ll_i2info(inode)->lli_lvb.lvb_ctime;
} else {
- rc = ll_glimpse_size(inode);
+ /* In case of restore, the MDT has the right size and has
+ * already send it back without granting the layout lock,
+ * inode is up-to-date so glimpse is useless.
+ * Also to glimpse we need the layout, in case of a running
+ * restore the MDT holds the layout lock so the glimpse will
+ * block up to the end of restore (getattr will block)
+ */
+ if (!(ll_i2info(inode)->lli_flags & LLIF_FILE_RESTORING))
+ rc = ll_glimpse_size(inode);
}
- RETURN(rc);
+ RETURN(rc);
}
int ll_getattr_it(struct vfsmount *mnt, struct dentry *de,
.release = ll_file_release,
.mmap = ll_file_mmap,
.llseek = ll_file_seek,
-#ifdef HAVE_KERNEL_SENDFILE
- .sendfile = ll_file_sendfile,
-#endif
-#ifdef HAVE_KERNEL_SPLICE_READ
.splice_read = ll_file_splice_read,
-#endif
.fsync = ll_fsync,
.flush = ll_flush
};
.release = ll_file_release,
.mmap = ll_file_mmap,
.llseek = ll_file_seek,
-#ifdef HAVE_KERNEL_SENDFILE
- .sendfile = ll_file_sendfile,
-#endif
-#ifdef HAVE_KERNEL_SPLICE_READ
.splice_read = ll_file_splice_read,
-#endif
.fsync = ll_fsync,
.flush = ll_flush,
.flock = ll_file_flock,
.release = ll_file_release,
.mmap = ll_file_mmap,
.llseek = ll_file_seek,
-#ifdef HAVE_KERNEL_SENDFILE
- .sendfile = ll_file_sendfile,
-#endif
-#ifdef HAVE_KERNEL_SPLICE_READ
.splice_read = ll_file_splice_read,
-#endif
.fsync = ll_fsync,
.flush = ll_flush,
.flock = ll_file_noflock,
int rc;
ENTRY;
- if (lock->l_lvb_data != NULL)
+ CDEBUG(D_INODE, DFID" LVB_READY=%d l_lvb_data=%p l_lvb_len=%d\n",
+ PFID(ll_inode2fid(inode)), !!(lock->l_flags & LDLM_FL_LVB_READY),
+ lock->l_lvb_data, lock->l_lvb_len);
+
+ if ((lock->l_lvb_data != NULL) && (lock->l_flags & LDLM_FL_LVB_READY))
RETURN(0);
/* if layout lock was granted right away, the layout is returned
memcpy(lvbdata, lmm, lmmsize);
lock_res_and_lock(lock);
- if (lock->l_lvb_data == NULL) {
- lock->l_lvb_data = lvbdata;
- lock->l_lvb_len = lmmsize;
- lvbdata = NULL;
- }
+ if (lock->l_lvb_data != NULL)
+ OBD_FREE_LARGE(lock->l_lvb_data, lock->l_lvb_len);
+
+ lock->l_lvb_data = lvbdata;
+ lock->l_lvb_len = lmmsize;
unlock_res_and_lock(lock);
- if (lvbdata != NULL)
- OBD_FREE_LARGE(lvbdata, lmmsize);
EXIT;
out:
LASSERT(ldlm_has_layout(lock));
LDLM_DEBUG(lock, "File %p/"DFID" being reconfigured: %d.\n",
- inode, PFID(&lli->lli_fid), reconf);
+ inode, PFID(&lli->lli_fid), reconf);
+
+ /* in case this is a caching lock and reinstate with new inode */
+ md_set_lock_data(sbi->ll_md_exp, &lockh->cookie, inode, NULL);
lock_res_and_lock(lock);
lvb_ready = !!(lock->l_flags & LDLM_FL_LVB_READY);
unlock_res_and_lock(lock);
/* checking lvb_ready is racy but this is okay. The worst case is
* that multi processes may configure the file on the same time. */
+
if (lvb_ready || !reconf) {
rc = -ENODATA;
if (lvb_ready) {
struct lookup_intent it;
struct lustre_handle lockh;
ldlm_mode_t mode;
- 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_cbdata = NULL };
+ 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,
+ };
int rc;
ENTRY;
ll_finish_md_op_data(op_data);
- md_set_lock_data(sbi->ll_md_exp, &it.d.lustre.it_lock_handle, inode, NULL);
-
mode = it.d.lustre.it_lock_mode;
it.d.lustre.it_lock_mode = 0;
ll_intent_drop_lock(&it);
RETURN(rc);
}
+
+/**
+ * This function send a restore request to the MDT
+ */
+int ll_layout_restore(struct inode *inode)
+{
+ struct hsm_user_request *hur;
+ int len, rc;
+ ENTRY;
+
+ len = sizeof(struct hsm_user_request) +
+ sizeof(struct hsm_user_item);
+ OBD_ALLOC(hur, len);
+ if (hur == NULL)
+ RETURN(-ENOMEM);
+
+ hur->hur_request.hr_action = HUA_RESTORE;
+ hur->hur_request.hr_archive_id = 0;
+ hur->hur_request.hr_flags = 0;
+ memcpy(&hur->hur_user_item[0].hui_fid, &ll_i2info(inode)->lli_fid,
+ sizeof(hur->hur_user_item[0].hui_fid));
+ hur->hur_user_item[0].hui_extent.length = -1;
+ hur->hur_request.hr_itemcount = 1;
+ rc = obd_iocontrol(LL_IOC_HSM_REQUEST, cl_i2sbi(inode)->ll_md_exp,
+ len, hur, NULL);
+ OBD_FREE(hur, len);
+ RETURN(rc);
+}
+