* Copyright (c) 2003, 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/
#include <obd_cksum.h>
#include "llite_internal.h"
-cfs_mem_cache_t *ll_file_data_slab;
+struct kmem_cache *ll_file_data_slab;
CFS_LIST_HEAD(ll_super_blocks);
DEFINE_SPINLOCK(ll_sb_lock);
si_meminfo(&si);
pages = si.totalram - si.totalhigh;
- if (pages >> (20 - CFS_PAGE_SHIFT) < 512) {
+ if (pages >> (20 - PAGE_CACHE_SHIFT) < 512) {
lru_page_max = pages / 2;
} else {
lru_page_max = (pages / 4) * 3;
}
- /* initialize ll_cache data */
+ /* initialize lru data */
cfs_atomic_set(&sbi->ll_cache.ccc_users, 0);
sbi->ll_cache.ccc_lru_max = lru_page_max;
cfs_atomic_set(&sbi->ll_cache.ccc_lru_left, lru_page_max);
spin_lock_init(&sbi->ll_cache.ccc_lru_lock);
CFS_INIT_LIST_HEAD(&sbi->ll_cache.ccc_lru);
- cfs_atomic_set(&sbi->ll_cache.ccc_unstable_nr, 0);
- cfs_waitq_init(&sbi->ll_cache.ccc_unstable_waitq);
-
sbi->ll_ra_info.ra_max_pages_per_file = min(pages / 32,
SBI_DEFAULT_READAHEAD_MAX);
sbi->ll_ra_info.ra_max_pages = sbi->ll_ra_info.ra_max_pages_per_file;
EXIT;
}
-static struct dentry_operations ll_d_root_ops = {
- .d_compare = ll_dcompare,
- .d_revalidate = ll_revalidate_nd,
-};
-
static int client_common_fill_super(struct super_block *sb, char *md, char *dt,
struct vfsmount *mnt)
{
OBD_CONNECT_FULL20 | OBD_CONNECT_64BITHASH|
OBD_CONNECT_EINPROGRESS |
OBD_CONNECT_JOBSTATS | OBD_CONNECT_LVB_TYPE |
- OBD_CONNECT_LAYOUTLOCK | OBD_CONNECT_PINGLESS;
+ OBD_CONNECT_LAYOUTLOCK | OBD_CONNECT_PINGLESS |
+ OBD_CONNECT_MAX_EASIZE |
+ OBD_CONNECT_FLOCK_DEAD;
if (sbi->ll_flags & LL_SBI_SOM_PREVIEW)
data->ocd_connect_flags |= OBD_CONNECT_SOM;
valid != CLIENT_CONNECT_MDT_REQD) {
char *buf;
- OBD_ALLOC_WAIT(buf, CFS_PAGE_SIZE);
- obd_connect_flags2str(buf, CFS_PAGE_SIZE,
+ OBD_ALLOC_WAIT(buf, PAGE_CACHE_SIZE);
+ obd_connect_flags2str(buf, PAGE_CACHE_SIZE,
valid ^ CLIENT_CONNECT_MDT_REQD, ",");
LCONSOLE_ERROR_MSG(0x170, "Server %s does not support "
"feature(s) needed for correct operation "
"of this client (%s). Please upgrade "
"server or downgrade client.\n",
sbi->ll_md_exp->exp_obd->obd_name, buf);
- OBD_FREE(buf, CFS_PAGE_SIZE);
+ OBD_FREE(buf, PAGE_CACHE_SIZE);
GOTO(out_md_fid, err = -EPROTO);
}
if (data->ocd_connect_flags & OBD_CONNECT_BRW_SIZE)
sbi->ll_md_brw_size = data->ocd_brw_size;
else
- sbi->ll_md_brw_size = CFS_PAGE_SIZE;
+ sbi->ll_md_brw_size = PAGE_CACHE_SIZE;
if (data->ocd_connect_flags & OBD_CONNECT_LAYOUTLOCK) {
LCONSOLE_INFO("Layout lock feature supported.\n");
sbi->ll_flags |= LL_SBI_LAYOUT_LOCK;
}
+ if (data->ocd_ibits_known & MDS_INODELOCK_XATTR) {
+ if (!(data->ocd_connect_flags & OBD_CONNECT_MAX_EASIZE)) {
+ LCONSOLE_INFO("%s: disabling xattr cache due to "
+ "unknown maximum xattr size.\n", dt);
+ } else {
+ sbi->ll_flags |= LL_SBI_XATTR_CACHE;
+ sbi->ll_xattr_cache_enabled = 1;
+ }
+ }
+
obd = class_name2obd(dt);
if (!obd) {
CERROR("DT %s: not setup or attached\n", dt);
LASSERT(fid_is_sane(&sbi->ll_root_fid));
root = ll_iget(sb, cl_fid_build_ino(&sbi->ll_root_fid,
- ll_need_32bit_api(sbi)),
+ sbi->ll_flags & LL_SBI_32BIT_API),
&lmd);
md_free_lustre_md(sbi->ll_md_exp, &lmd);
ptlrpc_req_finished(request);
ll_get_fsname(sb, NULL, 0));
GOTO(out_root, err = -ENOMEM);
}
-
#ifdef HAVE_DCACHE_LOCK
- sb->s_root->d_op = &ll_d_root_ops;
-#else
- /* kernel >= 2.6.38 store dentry operations in sb->s_d_op. */
- d_set_d_op(sb->s_root, &ll_d_root_ops);
- sb->s_d_op = &ll_d_ops;
+ sb->s_root->d_op = &ll_d_ops;
#endif
sbi->ll_sdev_orig = sb->s_dev;
/* s_dev is also used in lt_compare() to compare two fs, but that is
* only a node-local comparison. */
uuid = obd_get_uuid(sbi->ll_md_exp);
- if (uuid != NULL)
- sb->s_dev = get_uuid2int(uuid->uuid, strlen(uuid->uuid));
+ if (uuid != NULL) {
+ sb->s_dev = get_uuid2int(uuid->uuid, strlen(uuid->uuid));
+ get_uuid2fsid(uuid->uuid, strlen(uuid->uuid), &sbi->ll_fsid);
+ }
if (data != NULL)
OBD_FREE_PTR(data);
lli->lli_layout_gen = LL_LAYOUT_GEN_NONE;
lli->lli_clob = NULL;
+ init_rwsem(&lli->lli_xattrs_list_rwsem);
+ mutex_init(&lli->lli_xattrs_enq_lock);
+
LASSERT(lli->lli_vfs_inode.i_mode != 0);
if (S_ISDIR(lli->lli_vfs_inode.i_mode)) {
mutex_init(&lli->lli_readdir_mutex);
static inline int ll_bdi_register(struct backing_dev_info *bdi)
{
-#ifdef HAVE_BDI_REGISTER
static atomic_t ll_bdi_num = ATOMIC_INIT(0);
-#ifdef HAVE_BDI_NAME
bdi->name = "lustre";
-#endif
return bdi_register(bdi, NULL, "lustre-%d",
atomic_inc_return(&ll_bdi_num));
-#else
- return 0;
-#endif
}
int ll_fill_super(struct super_block *sb, struct vfsmount *mnt)
if (err)
GOTO(out_free, err);
-#ifdef HAVE_SB_BDI
sb->s_bdi = &lsi->lsi_bdi;
+#ifndef HAVE_DCACHE_LOCK
+ /* kernel >= 2.6.38 store dentry operations in sb->s_d_op. */
+ sb->s_d_op = &ll_d_ops;
#endif
/* Generate a string unique to this super, in case some joker tries
void ll_put_super(struct super_block *sb)
{
- struct config_llog_instance cfg;
+ struct config_llog_instance cfg, params_cfg;
struct obd_device *obd;
struct lustre_sb_info *lsi = s2lsi(sb);
struct ll_sb_info *sbi = ll_s2sbi(sb);
char *profilenm = get_profile_name(sb);
- int ccc_count, next, force = 1, rc = 0;
+ int force = 1, next;
ENTRY;
CDEBUG(D_VFSTRACE, "VFS Op: sb %p - %s\n", sb, profilenm);
cfg.cfg_instance = sb;
lustre_end_log(sb, profilenm, &cfg);
+ params_cfg.cfg_instance = sb;
+ lustre_end_log(sb, PARAMS_FILENAME, ¶ms_cfg);
+
if (sbi->ll_md_exp) {
obd = class_exp2obd(sbi->ll_md_exp);
if (obd)
force = obd->obd_force;
}
- /* Wait for unstable pages to be committed to stable storage */
- if (force == 0) {
- struct l_wait_info lwi = LWI_INTR(LWI_ON_SIGNAL_NOOP, NULL);
- rc = l_wait_event(sbi->ll_cache.ccc_unstable_waitq,
- cfs_atomic_read(&sbi->ll_cache.ccc_unstable_nr) == 0,
- &lwi);
- }
-
- ccc_count = cfs_atomic_read(&sbi->ll_cache.ccc_unstable_nr);
- if (force == 0 && rc != -EINTR)
- LASSERTF(ccc_count == 0, "count: %i\n", ccc_count);
-
-
/* We need to set force before the lov_disconnect in
lustre_common_put_super, since l_d cleans up osc's as well. */
if (force) {
LASSERT(lli->lli_opendir_pid == 0);
}
+ spin_lock(&lli->lli_lock);
ll_i2info(inode)->lli_flags &= ~LLIF_MDS_SIZE_LOCK;
+ spin_unlock(&lli->lli_lock);
md_null_inode(sbi->ll_md_exp, ll_inode2fid(inode));
LASSERT(!lli->lli_open_fd_write_count);
lli->lli_symlink_name = NULL;
}
+ ll_xattr_cache_destroy(inode);
+
if (sbi->ll_flags & LL_SBI_RMT_CLIENT) {
LASSERT(lli->lli_posix_acl == NULL);
if (lli->lli_remote_perms) {
return rc;
}
-#ifndef HAVE_VFS_INODE_NEWSIZE_OK
-/**
- * inode_newsize_ok - may this inode be truncated to a given size
- * @inode: the inode to be truncated
- * @offset: the new size to assign to the inode
- * @Returns: 0 on success, -ve errno on failure
- *
- * inode_newsize_ok will check filesystem limits and ulimits to check that the
- * new inode size is within limits. inode_newsize_ok will also send SIGXFSZ
- * when necessary. Caller must not proceed with inode size change if failure is
- * returned. @inode must be a file (not directory), with appropriate
- * permissions to allow truncate (inode_newsize_ok does NOT check these
- * conditions).
- *
- * inode_newsize_ok must be called with i_mutex held.
- */
-int inode_newsize_ok(const struct inode *inode, loff_t offset)
-{
- if (inode->i_size < offset) {
- unsigned long limit;
-
- limit = rlimit(RLIMIT_FSIZE);
- if (limit != RLIM_INFINITY && offset > limit)
- goto out_sig;
- if (offset > inode->i_sb->s_maxbytes)
- goto out_big;
- } else {
- /*
- * truncation of in-use swapfiles is disallowed - it would
- * cause subsequent swapout to scribble on the now-freed
- * blocks.
- */
- if (IS_SWAPFILE(inode))
- return -ETXTBSY;
- }
-
- return 0;
-out_sig:
- send_sig(SIGXFSZ, current, 0);
-out_big:
- return -EFBIG;
-}
-#endif
-
/* 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.
* to the OST with the punch RPC, otherwise we do an explicit setattr RPC.
* I don't believe it is possible to get e.g. ATTR_MTIME_SET and ATTR_SIZE
* at the same time.
+ *
+ * In case of HSMimport, we only set attr on MDS.
*/
-int ll_setattr_raw(struct dentry *dentry, struct iattr *attr)
+int ll_setattr_raw(struct dentry *dentry, struct iattr *attr, bool hsm_import)
{
struct inode *inode = dentry->d_inode;
struct ll_inode_info *lli = ll_i2info(inode);
struct md_op_data *op_data = NULL;
struct md_open_data *mod = NULL;
+ bool file_is_released = false;
int rc = 0, rc1 = 0;
ENTRY;
CDEBUG(D_VFSTRACE, "%s: setattr inode %p/fid:"DFID" from %llu to %llu, "
- "valid %x\n", ll_get_fsname(inode->i_sb, NULL, 0), inode,
+ "valid %x, hsm_import %d\n",
+ ll_get_fsname(inode->i_sb, NULL, 0), inode,
PFID(&lli->lli_fid), i_size_read(inode), attr->ia_size,
- attr->ia_valid);
+ attr->ia_valid, hsm_import);
if (attr->ia_valid & ATTR_SIZE) {
/* Check new size against VFS/VM file size limit and rlimit */
(attr->ia_valid & (ATTR_SIZE | ATTR_MTIME | ATTR_MTIME_SET)))
op_data->op_flags = MF_EPOCH_OPEN;
+ /* truncate on a released file must failed with -ENODATA,
+ * so size must not be set on MDS for released file
+ * but other attributes must be set
+ */
+ if (S_ISREG(inode->i_mode)) {
+ struct lov_stripe_md *lsm;
+ __u32 gen;
+
+ ll_layout_refresh(inode, &gen);
+ lsm = ccc_inode_lsm_get(inode);
+ if (lsm && lsm->lsm_pattern & LOV_PATTERN_F_RELEASED)
+ file_is_released = true;
+ ccc_inode_lsm_put(inode, lsm);
+ }
+
+ /* if not in HSM import mode, clear size attr for released file
+ * we clear the attribute send to MDT in op_data, not the original
+ * received from caller in attr which is used later to
+ * decide return code */
+ if (file_is_released && (attr->ia_valid & ATTR_SIZE) && !hsm_import)
+ op_data->op_attr.ia_valid &= ~ATTR_SIZE;
+
rc = ll_md_setattr(dentry, op_data, &mod);
if (rc)
GOTO(out, rc);
+ /* truncate failed (only when non HSM import), others succeed */
+ if (file_is_released) {
+ if ((attr->ia_valid & ATTR_SIZE) && !hsm_import)
+ GOTO(out, rc = -ENODATA);
+ else
+ GOTO(out, rc = 0);
+ }
+
/* RPC to MDT is sent, cancel data modification flag */
if (rc == 0 && (op_data->op_bias & MDS_DATA_MODIFIED)) {
spin_lock(&lli->lli_lock);
if (attr->ia_valid & (ATTR_SIZE |
ATTR_ATIME | ATTR_ATIME_SET |
- ATTR_MTIME | ATTR_MTIME_SET))
+ ATTR_MTIME | ATTR_MTIME_SET)) {
/* For truncate and utimes sending attributes to OSTs, setting
* mtime/atime to the past will be performed under PW [0:EOF]
* extent lock (new_size:EOF for truncate). It may seem
* setting times to past, but it is necessary due to possible
* time de-synchronization between MDT inode and OST objects */
rc = ll_setattr_ost(inode, attr);
+ }
EXIT;
out:
if (op_data) {
if (!S_ISDIR(inode->i_mode)) {
up_write(&lli->lli_trunc_sem);
mutex_lock(&inode->i_mutex);
- if (attr->ia_valid & ATTR_SIZE)
+ if ((attr->ia_valid & ATTR_SIZE) && !hsm_import)
inode_dio_wait(inode);
}
int ll_setattr(struct dentry *de, struct iattr *attr)
{
- int mode = de->d_inode->i_mode;
-
- if ((attr->ia_valid & (ATTR_CTIME|ATTR_SIZE|ATTR_MODE)) ==
- (ATTR_CTIME|ATTR_SIZE|ATTR_MODE))
- attr->ia_valid |= MDS_OPEN_OWNEROVERRIDE;
-
- if (((attr->ia_valid & (ATTR_MODE|ATTR_FORCE|ATTR_SIZE)) ==
- (ATTR_SIZE|ATTR_MODE)) &&
- (((mode & S_ISUID) && !(attr->ia_mode & S_ISUID)) ||
- (((mode & (S_ISGID|S_IXGRP)) == (S_ISGID|S_IXGRP)) &&
- !(attr->ia_mode & S_ISGID))))
- attr->ia_valid |= ATTR_FORCE;
-
- if ((mode & S_ISUID) &&
- !(attr->ia_mode & S_ISUID) &&
- !(attr->ia_valid & ATTR_KILL_SUID))
- attr->ia_valid |= ATTR_KILL_SUID;
-
- if (((mode & (S_ISGID|S_IXGRP)) == (S_ISGID|S_IXGRP)) &&
- !(attr->ia_mode & S_ISGID) &&
- !(attr->ia_valid & ATTR_KILL_SGID))
- attr->ia_valid |= ATTR_KILL_SGID;
-
- return ll_setattr_raw(de, attr);
+ int mode = de->d_inode->i_mode;
+
+ if ((attr->ia_valid & (ATTR_CTIME|ATTR_SIZE|ATTR_MODE)) ==
+ (ATTR_CTIME|ATTR_SIZE|ATTR_MODE))
+ attr->ia_valid |= MDS_OPEN_OWNEROVERRIDE;
+
+ if (((attr->ia_valid & (ATTR_MODE|ATTR_FORCE|ATTR_SIZE)) ==
+ (ATTR_SIZE|ATTR_MODE)) &&
+ (((mode & S_ISUID) && !(attr->ia_mode & S_ISUID)) ||
+ (((mode & (S_ISGID|S_IXGRP)) == (S_ISGID|S_IXGRP)) &&
+ !(attr->ia_mode & S_ISGID))))
+ attr->ia_valid |= ATTR_FORCE;
+
+ if ((mode & S_ISUID) &&
+ !(attr->ia_mode & S_ISUID) &&
+ !(attr->ia_valid & ATTR_KILL_SUID))
+ attr->ia_valid |= ATTR_KILL_SUID;
+
+ if (((mode & (S_ISGID|S_IXGRP)) == (S_ISGID|S_IXGRP)) &&
+ !(attr->ia_mode & S_ISGID) &&
+ !(attr->ia_valid & ATTR_KILL_SGID))
+ attr->ia_valid |= ATTR_KILL_SGID;
+
+ return ll_setattr_raw(de, attr, false);
}
int ll_statfs_internal(struct super_block *sb, struct obd_statfs *osfs,
sfs->f_blocks = osfs.os_blocks;
sfs->f_bfree = osfs.os_bfree;
sfs->f_bavail = osfs.os_bavail;
-
- return 0;
+ sfs->f_fsid = ll_s2sbi(sb)->ll_fsid;
+ return 0;
}
void ll_inode_size_lock(struct inode *inode)
spin_unlock(&lli->lli_lock);
}
#endif
- inode->i_ino = cl_fid_build_ino(&body->fid1, ll_need_32bit_api(sbi));
+ inode->i_ino = cl_fid_build_ino(&body->fid1,
+ sbi->ll_flags & LL_SBI_32BIT_API);
inode->i_generation = cl_fid_build_gen(&body->fid1);
if (body->valid & OBD_MD_FLATIME) {
* lock on the client and set LLIF_MDS_SIZE_LOCK holding
* it. */
mode = ll_take_md_lock(inode, MDS_INODELOCK_UPDATE,
- &lockh, LDLM_FL_CBPENDING);
+ &lockh, LDLM_FL_CBPENDING,
+ LCK_CR | LCK_CW |
+ LCK_PR | LCK_PW);
if (mode) {
if (lli->lli_flags & (LLIF_DONE_WRITING |
LLIF_EPOCH_PENDING |
/* Use old size assignment to avoid
* deadlock bz14138 & bz14326 */
i_size_write(inode, body->size);
+ spin_lock(&lli->lli_lock);
lli->lli_flags |= LLIF_MDS_SIZE_LOCK;
+ spin_unlock(&lli->lli_lock);
}
ldlm_lock_decref(&lockh, mode);
}
LASSERT(md->oss_capa);
ll_add_capa(inode, md->oss_capa);
}
+
+ if (body->valid & OBD_MD_TSTATE) {
+ if (body->t_state & MS_RESTORE)
+ lli->lli_flags |= LLIF_FILE_RESTORING;
+ }
}
void ll_read_inode2(struct inode *inode, void *opaque)
inode->i_flags = ll_ext_to_inode_flags(flags);
lsm = ccc_inode_lsm_get(inode);
- if (lsm == NULL)
+ if (!lsm_has_objects(lsm)) {
+ ccc_inode_lsm_put(inode, lsm);
RETURN(0);
+ }
OBDO_ALLOC(oinfo.oi_oa);
if (!oinfo.oi_oa) {
}
/* umount -f client means force down, don't save state */
-#ifdef HAVE_UMOUNTBEGIN_VFSMOUNT
-void ll_umount_begin(struct vfsmount *vfsmnt, int flags)
-{
- struct super_block *sb = vfsmnt->mnt_sb;
-#else
void ll_umount_begin(struct super_block *sb)
{
-#endif
struct ll_sb_info *sbi = ll_s2sbi(sb);
struct obd_device *obd;
struct obd_ioctl_data *ioc_data;
ENTRY;
-#ifdef HAVE_UMOUNTBEGIN_VFSMOUNT
- if (!(flags & MNT_FORCE)) {
- EXIT;
- return;
- }
-#endif
-
CDEBUG(D_VFSTRACE, "VFS Op: superblock %p count %d active %d\n", sb,
sb->s_count, atomic_read(&sb->s_active));
* schedule() and sleep one second if needed, and hope.
*/
cfs_schedule();
-#ifdef HAVE_UMOUNTBEGIN_VFSMOUNT
- if (atomic_read(&vfsmnt->mnt_count) > 2) {
- cfs_schedule_timeout_and_set_state(CFS_TASK_INTERRUPTIBLE,
- cfs_time_seconds(1));
- if (atomic_read(&vfsmnt->mnt_count) > 2)
- LCONSOLE_WARN("Mount still busy with %d refs! You "
- "may try to umount it a bit later\n",
- atomic_read(&vfsmnt->mnt_count));
- }
-#endif
-
EXIT;
}
LASSERT(fid_is_sane(&md.body->fid1));
*inode = ll_iget(sb, cl_fid_build_ino(&md.body->fid1,
- ll_need_32bit_api(sbi)),
+ sbi->ll_flags & LL_SBI_32BIT_API),
&md);
if (*inode == NULL || IS_ERR(*inode)) {
#ifdef CONFIG_FS_POSIX_ACL
if (!obd)
RETURN(-ENOENT);
- if (cfs_copy_to_user((void *)arg, obd->obd_name,
- strlen(obd->obd_name) + 1))
- RETURN(-EFAULT);
+ if (copy_to_user((void *)arg, obd->obd_name,
+ strlen(obd->obd_name) + 1))
+ RETURN(-EFAULT);
- RETURN(0);
+ RETURN(0);
}
/**
return path;
}
-void ll_dirty_page_discard_warn(cfs_page_t *page, int ioret)
+void ll_dirty_page_discard_warn(struct page *page, int ioret)
{
char *buf, *path = NULL;
struct dentry *dentry = NULL;
git://git.whamcloud.com / fs / lustre-release.git / blobdiff