cap_lower(cred->cap_effective, CAP_SYS_RESOURCE);
init_rwsem(&super->pccs_rw_sem);
INIT_LIST_HEAD(&super->pccs_datasets);
+ super->pccs_generation = 1;
return 0;
}
{
struct pcc_match_fname *fname;
- OBD_ALLOC(fname, sizeof(struct pcc_match_fname));
+ OBD_ALLOC_PTR(fname);
if (fname == NULL)
return -ENOMEM;
OBD_ALLOC(fname->pmf_name, id->ls_len + 1);
if (fname->pmf_name == NULL) {
- OBD_FREE(fname, sizeof(struct pcc_match_fname));
+ OBD_FREE_PTR(fname);
return -ENOMEM;
}
struct cfs_lstr field;
int rc = 0;
- OBD_ALLOC(expr, sizeof(struct pcc_expression));
+ OBD_ALLOC_PTR(expr);
if (expr == NULL)
return -ENOMEM;
struct cfs_lstr expr;
int rc = 0;
- OBD_ALLOC(conjunction, sizeof(struct pcc_conjunction));
+ OBD_ALLOC_PTR(conjunction);
if (conjunction == NULL)
return -ENOMEM;
*/
if ((cmd->u.pccc_add.pccc_flags & PCC_DATASET_PCC_ALL) == 0)
cmd->u.pccc_add.pccc_flags |= PCC_DATASET_PCC_ALL;
+
+ /* For RW-PCC, the value of @rwid must be non zero. */
+ if (cmd->u.pccc_add.pccc_flags & PCC_DATASET_RWPCC &&
+ cmd->u.pccc_add.pccc_rwid == 0)
+ return -EINVAL;
+
break;
case PCC_DEL_DATASET:
case PCC_CLEAR_ALL:
if (strcmp(dataset->pccd_pathname, pathname) == 0) {
list_del_init(&dataset->pccd_linkage);
pcc_dataset_put(dataset);
+ super->pccs_generation++;
rc = 0;
break;
}
list_del(&dataset->pccd_linkage);
pcc_dataset_put(dataset);
}
+ super->pccs_generation++;
up_write(&super->pccs_rw_sem);
}
pccf->pccf_type = LU_PCC_NONE;
}
-static inline bool pcc_auto_attach_enabled(struct pcc_dataset *dataset)
+static inline bool pcc_auto_attach_enabled(enum pcc_dataset_flags flags,
+ enum pcc_io_type iot)
{
- return dataset->pccd_flags & PCC_DATASET_AUTO_ATTACH;
+ if (iot == PIT_OPEN)
+ return flags & PCC_DATASET_OPEN_ATTACH;
+ if (iot == PIT_GETATTR)
+ return flags & PCC_DATASET_STAT_ATTACH;
+ else
+ return flags & PCC_DATASET_AUTO_ATTACH;
}
static const char pcc_xattr_layout[] = XATTR_USER_PREFIX "PCC.layout";
ENTRY;
- if (!(lli->lli_pcc_state & PCC_STATE_FL_AUTO_ATTACH))
+ if (!(lli->lli_pcc_dsflags & PCC_DATASET_AUTO_ATTACH))
RETURN(0);
#ifndef HAVE_VFS_SETXATTR
struct dentry *dentry,
enum lu_pcc_type type)
{
- struct ll_inode_info *lli = pcci->pcci_lli;
-
pcci->pcci_path.mnt = mntget(dataset->pccd_path.mnt);
pcci->pcci_path.dentry = dentry;
LASSERT(atomic_read(&pcci->pcci_refcount) == 0);
atomic_set(&pcci->pcci_refcount, 1);
pcci->pcci_type = type;
pcci->pcci_attr_valid = false;
+}
- if (dataset->pccd_flags & PCC_DATASET_OPEN_ATTACH)
- lli->lli_pcc_state |= PCC_STATE_FL_OPEN_ATTACH;
- if (dataset->pccd_flags & PCC_DATASET_IO_ATTACH)
- lli->lli_pcc_state |= PCC_STATE_FL_IO_ATTACH;
- if (dataset->pccd_flags & PCC_DATASET_STAT_ATTACH)
- lli->lli_pcc_state |= PCC_STATE_FL_STAT_ATTACH;
+static inline void pcc_inode_dsflags_set(struct ll_inode_info *lli,
+ struct pcc_dataset *dataset)
+{
+ lli->lli_pcc_generation = ll_info2pccs(lli)->pccs_generation;
+ lli->lli_pcc_dsflags = dataset->pccd_flags;
+}
+
+static void pcc_inode_attach_set(struct pcc_super *super,
+ struct pcc_dataset *dataset,
+ struct ll_inode_info *lli,
+ struct pcc_inode *pcci,
+ struct dentry *dentry,
+ enum lu_pcc_type type)
+{
+ pcc_inode_init(pcci, lli);
+ pcc_inode_attach_init(dataset, pcci, dentry, type);
+ down_read(&super->pccs_rw_sem);
+ pcc_inode_dsflags_set(lli, dataset);
+ up_read(&super->pccs_rw_sem);
}
static inline void pcc_layout_gen_set(struct pcc_inode *pcci,
pcc_inode_get(pcci);
pcci->pcci_type = type;
}
+ pcc_inode_dsflags_set(lli, dataset);
pcc_layout_gen_set(pcci, gen);
*cached = true;
}
RETURN(rc);
}
-static int pcc_try_datasets_attach(struct inode *inode, __u32 gen,
- enum lu_pcc_type type, bool *cached)
+static int pcc_try_datasets_attach(struct inode *inode, enum pcc_io_type iot,
+ __u32 gen, enum lu_pcc_type type,
+ bool *cached)
{
- struct pcc_dataset *dataset, *tmp;
struct pcc_super *super = &ll_i2sbi(inode)->ll_pcc_super;
+ struct ll_inode_info *lli = ll_i2info(inode);
+ struct pcc_dataset *dataset = NULL, *tmp;
int rc = 0;
ENTRY;
down_read(&super->pccs_rw_sem);
list_for_each_entry_safe(dataset, tmp,
&super->pccs_datasets, pccd_linkage) {
- if (!pcc_auto_attach_enabled(dataset))
- continue;
+ if (!pcc_auto_attach_enabled(dataset->pccd_flags, iot))
+ break;
+
rc = pcc_try_dataset_attach(inode, gen, type, dataset, cached);
if (rc < 0 || (!rc && *cached))
break;
}
+
+ /*
+ * Update the saved dataset flags for the inode accordingly if failed.
+ */
+ if (!rc && !*cached) {
+ /*
+ * Currently auto attach strategy for a PCC backend is
+ * unchangeable once once it was added into the PCC datasets on
+ * a client as the support to change auto attach strategy is
+ * not implemented yet.
+ */
+ /*
+ * If tried to attach from one PCC backend:
+ * @lli_pcc_generation > 0:
+ * 1) The file was once attached into PCC, but now the
+ * corresponding PCC backend should be removed from the client;
+ * 2) The layout generation was changed, the data has been
+ * restored;
+ * 3) The corresponding PCC copy is not existed on PCC
+ * @lli_pcc_generation == 0:
+ * The file is never attached into PCC but in a HSM released
+ * state, or once attached into PCC but the inode was evicted
+ * from icache later.
+ * Set the saved dataset flags with PCC_DATASET_NONE. Then this
+ * file will skip from the candidates to try auto attach until
+ * the file is attached into PCC again.
+ *
+ * If the file was never attached into PCC, or once attached but
+ * its inode was evicted from icache (lli_pcc_generation == 0),
+ * or the corresponding dataset was removed from the client,
+ * set the saved dataset flags with PCC_DATASET_NONE.
+ *
+ * TODO: If the file was once attached into PCC but not try to
+ * auto attach due to the change of the configuration parameters
+ * for this dataset (i.e. change from auto attach enabled to
+ * auto attach disabled for this dataset), update the saved
+ * dataset flags with the found one.
+ */
+ lli->lli_pcc_dsflags = PCC_DATASET_NONE;
+ }
up_read(&super->pccs_rw_sem);
RETURN(rc);
}
-static int pcc_try_auto_attach(struct inode *inode, bool *cached, bool is_open)
+/*
+ * TODO: For RW-PCC, it is desirable to store HSM info as a layout (LU-10606).
+ * Thus the client can get archive ID from the layout directly. When try to
+ * attach the file automatically which is in HSM released state (according to
+ * LOV_PATTERN_F_RELEASED in the layout), it can determine whether the file is
+ * valid cached on PCC more precisely according to the @rwid (archive ID) in
+ * the PCC dataset and the archive ID in HSM attrs.
+ */
+static int pcc_try_auto_attach(struct inode *inode, bool *cached,
+ enum pcc_io_type iot)
{
struct pcc_super *super = &ll_i2sbi(inode)->ll_pcc_super;
struct cl_layout clt = {
* obtain valid layout lock from MDT (i.e. the file is being
* HSM restoring).
*/
- if (is_open) {
+ if (iot == PIT_OPEN) {
if (ll_layout_version_get(lli) == CL_LAYOUT_GEN_NONE)
RETURN(0);
} else {
if (rc)
RETURN(rc);
- if (!is_open && gen != clt.cl_layout_gen) {
+ if (iot != PIT_OPEN && gen != clt.cl_layout_gen) {
CDEBUG(D_CACHE, DFID" layout changed from %d to %d.\n",
PFID(ll_inode2fid(inode)), gen, clt.cl_layout_gen);
RETURN(-EINVAL);
}
if (clt.cl_is_released)
- rc = pcc_try_datasets_attach(inode, clt.cl_layout_gen,
+ rc = pcc_try_datasets_attach(inode, iot, clt.cl_layout_gen,
LU_PCC_READWRITE, cached);
RETURN(rc);
}
+static inline bool pcc_may_auto_attach(struct inode *inode,
+ enum pcc_io_type iot)
+{
+ struct ll_inode_info *lli = ll_i2info(inode);
+ struct pcc_super *super = ll_i2pccs(inode);
+
+ /* Known the file was not in any PCC backend. */
+ if (lli->lli_pcc_dsflags & PCC_DATASET_NONE)
+ return false;
+
+ /*
+ * lli_pcc_generation == 0 means that the file was never attached into
+ * PCC, or may be once attached into PCC but detached as the inode is
+ * evicted from icache (i.e. "echo 3 > /proc/sys/vm/drop_caches" or
+ * icache shrinking due to the memory pressure), which will cause the
+ * file detach from PCC when releasing the inode from icache.
+ * In either case, we still try to attach.
+ */
+ /* lli_pcc_generation == 0, or the PCC setting was changed,
+ * or there is no PCC setup on the client and the try will return
+ * immediately in pcc_try_auto_attach().
+ */
+ if (super->pccs_generation != lli->lli_pcc_generation)
+ return true;
+
+ /* The cached setting @lli_pcc_dsflags is valid */
+ if (iot == PIT_OPEN)
+ return lli->lli_pcc_dsflags & PCC_DATASET_OPEN_ATTACH;
+
+ if (iot == PIT_GETATTR)
+ return lli->lli_pcc_dsflags & PCC_DATASET_STAT_ATTACH;
+
+ return lli->lli_pcc_dsflags & PCC_DATASET_IO_ATTACH;
+}
+
int pcc_file_open(struct inode *inode, struct file *file)
{
struct pcc_inode *pcci;
struct ll_inode_info *lli = ll_i2info(inode);
- struct ll_file_data *fd = LUSTRE_FPRIVATE(file);
+ struct ll_file_data *fd = file->private_data;
struct pcc_file *pccf = &fd->fd_pcc_file;
struct file *pcc_file;
struct path *path;
GOTO(out_unlock, rc = 0);
if (!pcci || !pcc_inode_has_layout(pcci)) {
- if (lli->lli_pcc_state & PCC_STATE_FL_OPEN_ATTACH)
- rc = pcc_try_auto_attach(inode, &cached, true);
+ if (pcc_may_auto_attach(inode, PIT_OPEN))
+ rc = pcc_try_auto_attach(inode, &cached, PIT_OPEN);
if (rc < 0 || !cached)
GOTO(out_unlock, rc);
void pcc_file_release(struct inode *inode, struct file *file)
{
struct pcc_inode *pcci;
- struct ll_file_data *fd = LUSTRE_FPRIVATE(file);
+ struct ll_file_data *fd = file->private_data;
struct pcc_file *pccf;
struct path *path;
struct qstr *dname;
static void pcc_io_init(struct inode *inode, enum pcc_io_type iot, bool *cached)
{
- struct ll_inode_info *lli = ll_i2info(inode);
struct pcc_inode *pcci;
pcc_inode_lock(inode);
*cached = true;
} else {
*cached = false;
- if ((lli->lli_pcc_state & PCC_STATE_FL_IO_ATTACH &&
- iot != PIT_GETATTR) ||
- (iot == PIT_GETATTR &&
- lli->lli_pcc_state & PCC_STATE_FL_STAT_ATTACH)) {
- (void) pcc_try_auto_attach(inode, cached, false);
+ if (pcc_may_auto_attach(inode, iot)) {
+ (void) pcc_try_auto_attach(inode, cached, iot);
if (*cached) {
pcci = ll_i2pcci(inode);
LASSERT(atomic_read(&pcci->pcci_refcount) > 0);
struct iov_iter *iter, bool *cached)
{
struct file *file = iocb->ki_filp;
- struct ll_file_data *fd = LUSTRE_FPRIVATE(file);
+ struct ll_file_data *fd = file->private_data;
struct pcc_file *pccf = &fd->fd_pcc_file;
struct inode *inode = file_inode(file);
ssize_t result;
struct iov_iter *iter, bool *cached)
{
struct file *file = iocb->ki_filp;
- struct ll_file_data *fd = LUSTRE_FPRIVATE(file);
+ struct ll_file_data *fd = file->private_data;
struct pcc_file *pccf = &fd->fd_pcc_file;
struct inode *inode = file_inode(file);
ssize_t result;
GOTO(out, rc);
ll_inode_size_lock(inode);
- if (inode->i_atime.tv_sec < lli->lli_atime ||
- lli->lli_update_atime) {
+ if (ll_file_test_and_clear_flag(lli, LLIF_UPDATE_ATIME) ||
+ inode->i_atime.tv_sec < lli->lli_atime)
inode->i_atime.tv_sec = lli->lli_atime;
- lli->lli_update_atime = 0;
- }
+
inode->i_mtime.tv_sec = lli->lli_mtime;
inode->i_ctime.tv_sec = lli->lli_ctime;
bool *cached)
{
struct inode *inode = file_inode(in_file);
- struct ll_file_data *fd = LUSTRE_FPRIVATE(in_file);
+ struct ll_file_data *fd = in_file->private_data;
struct file *pcc_file = fd->fd_pcc_file.pccf_file;
ssize_t result;
int datasync, bool *cached)
{
struct inode *inode = file_inode(file);
- struct ll_file_data *fd = LUSTRE_FPRIVATE(file);
+ struct ll_file_data *fd = file->private_data;
struct file *pcc_file = fd->fd_pcc_file.pccf_file;
int rc;
bool *cached)
{
struct inode *inode = file_inode(file);
- struct ll_file_data *fd = LUSTRE_FPRIVATE(file);
+ struct ll_file_data *fd = file->private_data;
struct file *pcc_file = fd->fd_pcc_file.pccf_file;
struct pcc_inode *pcci;
int rc = 0;
struct pcc_inode *pcci;
struct file *file = vma->vm_file;
struct inode *inode = file_inode(file);
- struct ll_file_data *fd = LUSTRE_FPRIVATE(file);
+ struct ll_file_data *fd = file->private_data;
struct file *pcc_file = fd->fd_pcc_file.pccf_file;
struct vm_operations_struct *pcc_vm_ops = vma->vm_private_data;
{
struct file *file = vma->vm_file;
struct inode *inode = file_inode(file);
- struct ll_file_data *fd = LUSTRE_FPRIVATE(file);
+ struct ll_file_data *fd = file->private_data;
struct file *pcc_file = fd->fd_pcc_file.pccf_file;
struct vm_operations_struct *pcc_vm_ops = vma->vm_private_data;
struct mm_struct *mm = vma->vm_mm;
struct file *file = vma->vm_file;
struct inode *inode = file_inode(file);
- struct ll_file_data *fd = LUSTRE_FPRIVATE(file);
+ struct ll_file_data *fd = file->private_data;
struct file *pcc_file = fd->fd_pcc_file.pccf_file;
struct vm_operations_struct *pcc_vm_ops = vma->vm_private_data;
int rc;
{
struct file *file = vma->vm_file;
struct inode *inode = file_inode(file);
- struct ll_file_data *fd = LUSTRE_FPRIVATE(file);
+ struct ll_file_data *fd = file->private_data;
struct file *pcc_file = fd->fd_pcc_file.pccf_file;
struct vm_operations_struct *pcc_vm_ops = vma->vm_private_data;
int rc;
static void pcc_layout_wait(struct pcc_inode *pcci)
{
- struct l_wait_info lwi = { 0 };
while (atomic_read(&pcci->pcci_active_ios) > 0) {
CDEBUG(D_CACHE, "Waiting for IO completion: %d\n",
atomic_read(&pcci->pcci_active_ios));
- l_wait_event(pcci->pcci_waitq,
- atomic_read(&pcci->pcci_active_ios) == 0, &lwi);
+ wait_event_idle(pcci->pcci_waitq,
+ atomic_read(&pcci->pcci_active_ios) == 0);
}
}
return rc;
}
-/* TODO: Set the project ID for PCC copy */
-int pcc_inode_store_ugpid(struct dentry *dentry, kuid_t uid, kgid_t gid)
+/*
+ * Reset uid, gid or size for the PCC copy masked by @valid.
+ * TODO: Set the project ID for PCC copy.
+ */
+int pcc_inode_reset_iattr(struct dentry *dentry, unsigned int valid,
+ kuid_t uid, kgid_t gid, loff_t size)
{
struct inode *inode = dentry->d_inode;
struct iattr attr;
ENTRY;
- attr.ia_valid = ATTR_UID | ATTR_GID;
+ attr.ia_valid = valid;
attr.ia_uid = uid;
attr.ia_gid = gid;
+ attr.ia_size = size;
inode_lock(inode);
rc = notify_change(dentry, &attr, NULL);
int pcc_inode_create_fini(struct inode *inode, struct pcc_create_attach *pca)
{
struct dentry *pcc_dentry = pca->pca_dentry;
+ struct pcc_super *super = ll_i2pccs(inode);
const struct cred *old_cred;
struct pcc_inode *pcci;
int rc;
LASSERT(pcc_dentry);
- old_cred = override_creds(pcc_super_cred(inode->i_sb));
+ old_cred = override_creds(super->pccs_cred);
pcc_inode_lock(inode);
LASSERT(ll_i2pcci(inode) == NULL);
OBD_SLAB_ALLOC_PTR_GFP(pcci, pcc_inode_slab, GFP_NOFS);
if (pcci == NULL)
GOTO(out_put, rc = -ENOMEM);
- rc = pcc_inode_store_ugpid(pcc_dentry, old_cred->suid,
- old_cred->sgid);
+ rc = pcc_inode_reset_iattr(pcc_dentry, ATTR_UID | ATTR_GID,
+ old_cred->suid, old_cred->sgid, 0);
if (rc)
GOTO(out_put, rc);
- pcc_inode_init(pcci, ll_i2info(inode));
- pcc_inode_attach_init(pca->pca_dataset, pcci, pcc_dentry,
- LU_PCC_READWRITE);
+ pcc_inode_attach_set(super, pca->pca_dataset, ll_i2info(inode),
+ pcci, pcc_dentry, LU_PCC_READWRITE);
rc = pcc_layout_xattr_set(pcci, 0);
if (rc) {
return 0;
}
-static int pcc_copy_data(struct file *src, struct file *dst)
+static ssize_t pcc_copy_data(struct file *src, struct file *dst)
{
- int rc = 0;
+ ssize_t rc = 0;
ssize_t rc2;
loff_t pos, offset = 0;
size_t buf_len = 1048576;
RETURN(-ENOMEM);
while (1) {
+ if (signal_pending(current))
+ GOTO(out_free, rc = -EINTR);
+
pos = offset;
rc2 = cfs_kernel_read(src, buf, buf_len, &pos);
if (rc2 < 0)
offset += rc2;
}
+ rc = offset;
out_free:
OBD_FREE_LARGE(buf, buf_len);
RETURN(rc);
{
struct pcc_dataset *dataset;
struct ll_inode_info *lli = ll_i2info(inode);
+ struct pcc_super *super = ll_i2pccs(inode);
struct pcc_inode *pcci;
const struct cred *old_cred;
struct dentry *dentry;
struct file *pcc_filp;
struct path path;
+ ssize_t ret;
int rc;
ENTRY;
if (dataset == NULL)
RETURN(-ENOENT);
- old_cred = override_creds(pcc_super_cred(inode->i_sb));
+ old_cred = override_creds(super->pccs_cred);
rc = __pcc_inode_create(dataset, &lli->lli_fid, &dentry);
- if (rc) {
- revert_creds(old_cred);
+ if (rc)
GOTO(out_dataset_put, rc);
- }
path.mnt = dataset->pccd_path.mnt;
path.dentry = dentry;
#ifdef HAVE_DENTRY_OPEN_USE_PATH
- pcc_filp = dentry_open(&path, O_TRUNC | O_WRONLY | O_LARGEFILE,
- current_cred());
+ pcc_filp = dentry_open(&path, O_WRONLY | O_LARGEFILE, current_cred());
#else
- pcc_filp = dentry_open(path.dentry, path.mnt,
- O_TRUNC | O_WRONLY | O_LARGEFILE,
+ pcc_filp = dentry_open(path.dentry, path.mnt, O_WRONLY | O_LARGEFILE,
current_cred());
#endif
if (IS_ERR_OR_NULL(pcc_filp)) {
rc = pcc_filp == NULL ? -EINVAL : PTR_ERR(pcc_filp);
- revert_creds(old_cred);
GOTO(out_dentry, rc);
}
- rc = pcc_inode_store_ugpid(dentry, old_cred->uid, old_cred->gid);
- revert_creds(old_cred);
+ rc = pcc_inode_reset_iattr(dentry, ATTR_UID | ATTR_GID,
+ old_cred->uid, old_cred->gid, 0);
if (rc)
GOTO(out_fput, rc);
- rc = pcc_copy_data(file, pcc_filp);
+ ret = pcc_copy_data(file, pcc_filp);
+ if (ret < 0)
+ GOTO(out_fput, rc = ret);
+
+ /*
+ * It must to truncate the PCC copy to the same size of the Lustre
+ * copy after copy data. Otherwise, it may get wrong file size after
+ * re-attach a file. See LU-13023 for details.
+ */
+ rc = pcc_inode_reset_iattr(dentry, ATTR_SIZE, KUIDT_INIT(0),
+ KGIDT_INIT(0), ret);
if (rc)
GOTO(out_fput, rc);
if (pcci == NULL)
GOTO(out_unlock, rc = -ENOMEM);
- pcc_inode_init(pcci, lli);
- pcc_inode_attach_init(dataset, pcci, dentry, LU_PCC_READWRITE);
+ pcc_inode_attach_set(super, dataset, lli, pcci,
+ dentry, LU_PCC_READWRITE);
out_unlock:
pcc_inode_unlock(inode);
out_fput:
fput(pcc_filp);
out_dentry:
if (rc) {
- old_cred = override_creds(pcc_super_cred(inode->i_sb));
(void) pcc_inode_remove(inode, dentry);
- revert_creds(old_cred);
dput(dentry);
}
out_dataset_put:
pcc_dataset_put(dataset);
+ revert_creds(old_cred);
+
RETURN(rc);
}
LASSERT(atomic_read(&pcci->pcci_refcount) > 0);
if (pcci->pcci_type == LU_PCC_READWRITE) {
- if (opt == PCC_DETACH_OPT_UNCACHE)
+ if (opt == PCC_DETACH_OPT_UNCACHE) {
hsm_remove = true;
+ /*
+ * The file will be removed from PCC, set the flags
+ * with PCC_DATASET_NONE even the later removal of the
+ * PCC copy fails.
+ */
+ lli->lli_pcc_dsflags = PCC_DATASET_NONE;
+ }
__pcc_layout_invalidate(pcci);
pcc_inode_put(pcci);
char *buf;
char *path;
int buf_len = sizeof(state->pccs_path);
- struct ll_file_data *fd = LUSTRE_FPRIVATE(file);
+ struct ll_file_data *fd = file->private_data;
struct pcc_file *pccf = &fd->fd_pcc_file;
struct pcc_inode *pcci;
git://git.whamcloud.com / fs / lustre-release.git / blobdiff