static int lov_object_layout_get(const struct lu_env *env,
struct cl_object *obj,
struct cl_layout *cl)
{
struct lov_object *lov = cl2lov(obj);
struct lov_stripe_md *lsm = lov_lsm_addref(lov);
struct lu_buf *buf = &cl->cl_buf;
ssize_t rc;
ENTRY;
if (lsm == NULL) {
cl->cl_size = 0;
cl->cl_layout_gen = CL_LAYOUT_GEN_EMPTY;
RETURN(0);
}
cl->cl_size = lov_mds_md_size(lsm->lsm_stripe_count, lsm->lsm_magic);
cl->cl_layout_gen = lsm->lsm_layout_gen;
rc = lov_lsm_pack(lsm, buf->lb_buf, buf->lb_len);
lov_lsm_put(lsm);
RETURN(rc < 0 ? rc : 0);
}
static loff_t lov_object_maxbytes(struct cl_object *obj)
{
struct lov_object *lov = cl2lov(obj);
struct lov_stripe_md *lsm = lov_lsm_addref(lov);
loff_t maxbytes;
if (lsm == NULL)
return LLONG_MAX;
maxbytes = lsm->lsm_maxbytes;
lov_lsm_put(lsm);
return maxbytes;
}
static int lov_object_getstripe(const struct lu_env *env, struct cl_object *obj,
struct lov_user_md __user *lum)
{
struct lov_object *lov = cl2lov(obj);
struct lov_stripe_md *lsm;
int rc = 0;
lsm = lov_lsm_addref(lov);
if (!lsm)
return -ENODATA;
rc = lov_getstripe(cl2lov(obj), lsm, lum);
lov_lsm_put(obj, lsm);
return rc;
}
static int lov_object_getstripe(const struct lu_env *env, struct cl_object *obj,
struct lov_user_md __user *lum)
{
struct lov_object *lov = cl2lov(obj);
struct lov_stripe_md *lsm;
int rc = 0;
ENTRY;
lsm = lov_lsm_addref(lov);
if (lsm == NULL)
RETURN(-ENODATA);
rc = lov_getstripe(cl2lov(obj), lsm, lum);
lov_lsm_put(lsm);
RETURN(rc);
}
/*****************************************************************************
*
* Lov object operations.
*
*/
int lov_object_init(const struct lu_env *env, struct lu_object *obj,
const struct lu_object_conf *conf)
{
struct lov_object *lov = lu2lov(obj);
struct lov_device *dev = lov_object_dev(lov);
const struct cl_object_conf *cconf = lu2cl_conf(conf);
union lov_layout_state *set = &lov->u;
const struct lov_layout_operations *ops;
struct lov_stripe_md *lsm = NULL;
int rc;
ENTRY;
init_rwsem(&lov->lo_type_guard);
atomic_set(&lov->lo_active_ios, 0);
init_waitqueue_head(&lov->lo_waitq);
cl_object_page_init(lu2cl(obj), sizeof(struct lov_page));
lov->lo_type = LLT_EMPTY;
if (cconf->u.coc_layout.lb_buf != NULL) {
lsm = lov_unpackmd(dev->ld_lov,
cconf->u.coc_layout.lb_buf,
cconf->u.coc_layout.lb_len);
if (IS_ERR(lsm))
RETURN(PTR_ERR(lsm));
}
/* no locking is necessary, as object is being created */
lov->lo_type = lov_type(lsm);
ops = &lov_dispatch[lov->lo_type];
rc = ops->llo_init(env, dev, lov, lsm, cconf, set);
if (rc != 0)
GOTO(out_lsm, rc);
ops->llo_install(env, lov, set);
out_lsm:
lov_lsm_put(lsm);
RETURN(rc);
}
static int lov_conf_set(const struct lu_env *env, struct cl_object *obj,
const struct cl_object_conf *conf)
{
struct lov_stripe_md *lsm = NULL;
struct lov_object *lov = cl2lov(obj);
int result = 0;
ENTRY;
if (conf->coc_opc == OBJECT_CONF_SET &&
conf->u.coc_layout.lb_buf != NULL) {
lsm = lov_unpackmd(lov_object_dev(lov)->ld_lov,
conf->u.coc_layout.lb_buf,
conf->u.coc_layout.lb_len);
if (IS_ERR(lsm))
RETURN(PTR_ERR(lsm));
}
lov_conf_lock(lov);
if (conf->coc_opc == OBJECT_CONF_INVALIDATE) {
lov->lo_layout_invalid = true;
GOTO(out, result = 0);
}
if (conf->coc_opc == OBJECT_CONF_WAIT) {
if (lov->lo_layout_invalid &&
atomic_read(&lov->lo_active_ios) > 0) {
lov_conf_unlock(lov);
result = lov_layout_wait(env, lov);
lov_conf_lock(lov);
}
GOTO(out, result);
}
LASSERT(conf->coc_opc == OBJECT_CONF_SET);
if ((lsm == NULL && lov->lo_lsm == NULL) ||
((lsm != NULL && lov->lo_lsm != NULL) &&
(lov->lo_lsm->lsm_layout_gen == lsm->lsm_layout_gen) &&
(lov->lo_lsm->lsm_pattern == lsm->lsm_pattern))) {
/* same version of layout */
lov->lo_layout_invalid = false;
GOTO(out, result = 0);
}
/* will change layout - check if there still exists active IO. */
if (atomic_read(&lov->lo_active_ios) > 0) {
lov->lo_layout_invalid = true;
GOTO(out, result = -EBUSY);
}
result = lov_layout_change(env, lov, lsm, conf);
lov->lo_layout_invalid = result != 0;
EXIT;
out:
lov_conf_unlock(lov);
lov_lsm_put(lsm);
CDEBUG(D_INODE, DFID" lo_layout_invalid=%d\n",
PFID(lu_object_fid(lov2lu(lov))), lov->lo_layout_invalid);
RETURN(result);
}
/**
* Break down the FIEMAP request and send appropriate calls to individual OSTs.
* This also handles the restarting of FIEMAP calls in case mapping overflows
* the available number of extents in single call.
*
* \param env [in] lustre environment
* \param obj [in] file object
* \param fmkey [in] fiemap request header and other info
* \param fiemap [out] fiemap buffer holding retrived map extents
* \param buflen [in/out] max buffer length of @fiemap, when iterate
* each OST, it is used to limit max map needed
* \retval 0 success
* \retval < 0 error
*/
static int lov_object_fiemap(const struct lu_env *env, struct cl_object *obj,
struct ll_fiemap_info_key *fmkey,
struct fiemap *fiemap, size_t *buflen)
{
struct lov_stripe_md *lsm;
struct cl_object *subobj = NULL;
struct lov_obd *lov = lu2lov_dev(obj->co_lu.lo_dev)->ld_lov;
struct fiemap *fm_local = NULL;
struct fiemap_extent *lcl_fm_ext;
loff_t fm_start;
loff_t fm_end;
loff_t fm_length;
loff_t fm_end_offset;
int count_local;
int ost_index = 0;
int start_stripe;
int current_extent = 0;
int rc = 0;
int last_stripe;
int cur_stripe = 0;
int cur_stripe_wrap = 0;
int stripe_count;
unsigned int buffer_size = FIEMAP_BUFFER_SIZE;
/* Whether have we collected enough extents */
bool enough = false;
/* EOF for object */
bool ost_eof = false;
/* done with required mapping for this OST? */
bool ost_done = false;
ENTRY;
lsm = lov_lsm_addref(cl2lov(obj));
if (lsm == NULL)
RETURN(-ENODATA);
/**
* If the stripe_count > 1 and the application does not understand
* DEVICE_ORDER flag, it cannot interpret the extents correctly.
*/
if (lsm->lsm_stripe_count > 1 && !(fiemap->fm_flags &
FIEMAP_FLAG_DEVICE_ORDER))
GOTO(out_lsm, rc = -ENOTSUPP);
if (lsm_is_released(lsm)) {
if (fiemap->fm_start < fmkey->lfik_oa.o_size) {
/**
* released file, return a minimal FIEMAP if
* request fits in file-size.
*/
fiemap->fm_mapped_extents = 1;
fiemap->fm_extents[0].fe_logical = fiemap->fm_start;
if (fiemap->fm_start + fiemap->fm_length <
fmkey->lfik_oa.o_size)
fiemap->fm_extents[0].fe_length =
fiemap->fm_length;
else
fiemap->fm_extents[0].fe_length =
fmkey->lfik_oa.o_size -
fiemap->fm_start;
fiemap->fm_extents[0].fe_flags |=
FIEMAP_EXTENT_UNKNOWN | FIEMAP_EXTENT_LAST;
}
GOTO(out_lsm, rc = 0);
}
if (fiemap_count_to_size(fiemap->fm_extent_count) < buffer_size)
buffer_size = fiemap_count_to_size(fiemap->fm_extent_count);
OBD_ALLOC_LARGE(fm_local, buffer_size);
if (fm_local == NULL)
GOTO(out_lsm, rc = -ENOMEM);
lcl_fm_ext = &fm_local->fm_extents[0];
count_local = fiemap_size_to_count(buffer_size);
fm_start = fiemap->fm_start;
fm_length = fiemap->fm_length;
/* Calculate start stripe, last stripe and length of mapping */
start_stripe = lov_stripe_number(lsm, fm_start);
fm_end = (fm_length == ~0ULL) ? fmkey->lfik_oa.o_size :
fm_start + fm_length - 1;
/* If fm_length != ~0ULL but fm_start_fm_length-1 exceeds file size */
if (fm_end > fmkey->lfik_oa.o_size)
fm_end = fmkey->lfik_oa.o_size;
last_stripe = fiemap_calc_last_stripe(lsm, fm_start, fm_end,
start_stripe, &stripe_count);
fm_end_offset = fiemap_calc_fm_end_offset(fiemap, lsm, fm_start, fm_end,
&start_stripe);
if (fm_end_offset == -EINVAL)
GOTO(out_fm_local, rc = -EINVAL);
/**
* Requested extent count exceeds the fiemap buffer size, shrink our
* ambition.
*/
if (fiemap_count_to_size(fiemap->fm_extent_count) > *buflen)
fiemap->fm_extent_count = fiemap_size_to_count(*buflen);
if (fiemap->fm_extent_count == 0)
count_local = 0;
/* Check each stripe */
for (cur_stripe = start_stripe; stripe_count > 0;
--stripe_count,
cur_stripe = (cur_stripe + 1) % lsm->lsm_stripe_count) {
loff_t req_fm_len; /* Stores length of required mapping */
loff_t len_mapped_single_call;
loff_t lun_start;
loff_t lun_end;
loff_t obd_object_end;
unsigned int ext_count;
cur_stripe_wrap = cur_stripe;
/* Find out range of mapping on this stripe */
if ((lov_stripe_intersects(lsm, cur_stripe, fm_start, fm_end,
&lun_start, &obd_object_end)) == 0)
continue;
if (lov_oinfo_is_dummy(lsm->lsm_oinfo[cur_stripe]))
GOTO(out_fm_local, rc = -EIO);
/* If this is a continuation FIEMAP call and we are on
* starting stripe then lun_start needs to be set to
* fm_end_offset */
if (fm_end_offset != 0 && cur_stripe == start_stripe)
lun_start = fm_end_offset;
if (fm_length != ~0ULL) {
/* Handle fm_start + fm_length overflow */
if (fm_start + fm_length < fm_start)
fm_length = ~0ULL - fm_start;
lun_end = lov_size_to_stripe(lsm, fm_start + fm_length,
cur_stripe);
} else {
lun_end = ~0ULL;
}
if (lun_start == lun_end)
continue;
req_fm_len = obd_object_end - lun_start;
fm_local->fm_length = 0;
len_mapped_single_call = 0;
/* find lobsub object */
subobj = lov_find_subobj(env, cl2lov(obj), lsm,
cur_stripe);
if (IS_ERR(subobj))
GOTO(out_fm_local, rc = PTR_ERR(subobj));
/* If the output buffer is very large and the objects have many
* extents we may need to loop on a single OST repeatedly */
ost_eof = false;
ost_done = false;
do {
if (fiemap->fm_extent_count > 0) {
/* Don't get too many extents. */
if (current_extent + count_local >
fiemap->fm_extent_count)
count_local = fiemap->fm_extent_count -
current_extent;
}
lun_start += len_mapped_single_call;
fm_local->fm_length = req_fm_len -
len_mapped_single_call;
req_fm_len = fm_local->fm_length;
fm_local->fm_extent_count = enough ? 1 : count_local;
fm_local->fm_mapped_extents = 0;
fm_local->fm_flags = fiemap->fm_flags;
ost_index = lsm->lsm_oinfo[cur_stripe]->loi_ost_idx;
if (ost_index < 0 ||
ost_index >= lov->desc.ld_tgt_count)
GOTO(obj_put, rc = -EINVAL);
/* If OST is inactive, return extent with UNKNOWN
* flag. */
if (!lov->lov_tgts[ost_index]->ltd_active) {
fm_local->fm_flags |= FIEMAP_EXTENT_LAST;
fm_local->fm_mapped_extents = 1;
lcl_fm_ext[0].fe_logical = lun_start;
lcl_fm_ext[0].fe_length = obd_object_end -
lun_start;
lcl_fm_ext[0].fe_flags |= FIEMAP_EXTENT_UNKNOWN;
goto inactive_tgt;
}
fm_local->fm_start = lun_start;
fm_local->fm_flags &= ~FIEMAP_FLAG_DEVICE_ORDER;
memcpy(&fmkey->lfik_fiemap, fm_local,
sizeof(*fm_local));
*buflen = fiemap_count_to_size(
fm_local->fm_extent_count);
rc = cl_object_fiemap(env, subobj, fmkey, fm_local,
buflen);
if (rc != 0)
GOTO(obj_put, rc);
inactive_tgt:
ext_count = fm_local->fm_mapped_extents;
if (ext_count == 0) {
ost_done = true;
/* If last stripe has hold at the end,
* we need to return */
if (cur_stripe_wrap == last_stripe) {
fiemap->fm_mapped_extents = 0;
goto finish;
}
break;
} else if (enough) {
/*
* We've collected enough extents and there are
* more extents after it.
*/
goto finish;
}
/* If we just need num of extents, got to next device */
if (fiemap->fm_extent_count == 0) {
current_extent += ext_count;
break;
}
/* prepare to copy retrived map extents */
len_mapped_single_call =
lcl_fm_ext[ext_count - 1].fe_logical -
lun_start + lcl_fm_ext[ext_count - 1].fe_length;
/* Have we finished mapping on this device? */
if (req_fm_len <= len_mapped_single_call)
ost_done = true;
/* Clear the EXTENT_LAST flag which can be present on
* the last extent */
if (lcl_fm_ext[ext_count - 1].fe_flags &
FIEMAP_EXTENT_LAST)
lcl_fm_ext[ext_count - 1].fe_flags &=
~FIEMAP_EXTENT_LAST;
if (lov_stripe_size(lsm,
lcl_fm_ext[ext_count - 1].fe_logical +
lcl_fm_ext[ext_count - 1].fe_length,
cur_stripe) >= fmkey->lfik_oa.o_size)
ost_eof = true;
fiemap_prepare_and_copy_exts(fiemap, lcl_fm_ext,
ost_index, ext_count,
current_extent);
current_extent += ext_count;
/* Ran out of available extents? */
if (current_extent >= fiemap->fm_extent_count)
enough = true;
} while (!ost_done && !ost_eof);
cl_object_put(env, subobj);
subobj = NULL;
if (cur_stripe_wrap == last_stripe)
goto finish;
} /* for each stripe */
finish:
/* Indicate that we are returning device offsets unless file just has
* single stripe */
if (lsm->lsm_stripe_count > 1)
fiemap->fm_flags |= FIEMAP_FLAG_DEVICE_ORDER;
if (fiemap->fm_extent_count == 0)
goto skip_last_device_calc;
/* Check if we have reached the last stripe and whether mapping for that
* stripe is done. */
if ((cur_stripe_wrap == last_stripe) && (ost_done || ost_eof))
fiemap->fm_extents[current_extent - 1].fe_flags |=
FIEMAP_EXTENT_LAST;
skip_last_device_calc:
fiemap->fm_mapped_extents = current_extent;
obj_put:
if (subobj != NULL)
cl_object_put(env, subobj);
out_fm_local:
OBD_FREE_LARGE(fm_local, buffer_size);
out_lsm:
lov_lsm_put(lsm);
return rc;
}
