static int osc_lock_upcall_agl(void *cookie, struct lustre_handle *lockh,
int errcode)
{
struct osc_object *osc = cookie;
struct ldlm_lock *dlmlock;
struct lu_env *env;
struct cl_env_nest nest;
ENTRY;
env = cl_env_nested_get(&nest);
LASSERT(!IS_ERR(env));
if (errcode == ELDLM_LOCK_MATCHED)
GOTO(out, errcode = ELDLM_OK);
if (errcode != ELDLM_OK)
GOTO(out, errcode);
dlmlock = ldlm_handle2lock(lockh);
LASSERT(dlmlock != NULL);
lock_res_and_lock(dlmlock);
LASSERT(dlmlock->l_granted_mode == dlmlock->l_req_mode);
/* there is no osc_lock associated with AGL lock */
osc_lock_lvb_update(env, osc, dlmlock, NULL);
unlock_res_and_lock(dlmlock);
LDLM_LOCK_PUT(dlmlock);
out:
cl_object_put(env, osc2cl(osc));
cl_env_nested_put(&nest, env);
RETURN(ldlm_error2errno(errcode));
}
/**
* Helper for osc_dlm_blocking_ast() handling discrepancies between cl_lock
* and ldlm_lock caches.
*/
static int mdc_dlm_blocking_ast0(const struct lu_env *env,
struct ldlm_lock *dlmlock,
void *data, int flag)
{
struct cl_object *obj = NULL;
int result = 0;
bool discard;
enum cl_lock_mode mode = CLM_READ;
ENTRY;
LASSERT(flag == LDLM_CB_CANCELING);
LASSERT(dlmlock != NULL);
lock_res_and_lock(dlmlock);
if (dlmlock->l_granted_mode != dlmlock->l_req_mode) {
dlmlock->l_ast_data = NULL;
unlock_res_and_lock(dlmlock);
RETURN(0);
}
discard = ldlm_is_discard_data(dlmlock);
if (dlmlock->l_granted_mode & (LCK_PW | LCK_GROUP))
mode = CLM_WRITE;
if (dlmlock->l_ast_data != NULL) {
obj = osc2cl(dlmlock->l_ast_data);
dlmlock->l_ast_data = NULL;
cl_object_get(obj);
}
ldlm_set_kms_ignore(dlmlock);
unlock_res_and_lock(dlmlock);
/* if l_ast_data is NULL, the dlmlock was enqueued by AGL or
* the object has been destroyed. */
if (obj != NULL) {
struct cl_attr *attr = &osc_env_info(env)->oti_attr;
/* Destroy pages covered by the extent of the DLM lock */
result = mdc_lock_flush(env, cl2osc(obj), cl_index(obj, 0),
CL_PAGE_EOF, mode, discard);
/* Losing a lock, set KMS to 0.
* NB: assumed that DOM lock covers whole data on MDT.
*/
/* losing a lock, update kms */
lock_res_and_lock(dlmlock);
cl_object_attr_lock(obj);
attr->cat_kms = 0;
cl_object_attr_update(env, obj, attr, CAT_KMS);
cl_object_attr_unlock(obj);
unlock_res_and_lock(dlmlock);
cl_object_put(env, obj);
}
RETURN(result);
}
static void lov_subobject_kill(const struct lu_env *env, struct lov_object *lov,
struct lovsub_object *los, int idx)
{
struct cl_object *sub;
struct lov_layout_raid0 *r0;
struct lu_site *site;
struct lu_site_bkt_data *bkt;
wait_queue_t *waiter;
r0 = &lov->u.raid0;
LASSERT(r0->lo_sub[idx] == los);
sub = lovsub2cl(los);
site = sub->co_lu.lo_dev->ld_site;
bkt = lu_site_bkt_from_fid(site, &sub->co_lu.lo_header->loh_fid);
cl_object_kill(env, sub);
/* release a reference to the sub-object and ... */
lu_object_ref_del(&sub->co_lu, "lov-parent", lov);
cl_object_put(env, sub);
/* ... wait until it is actually destroyed---sub-object clears its
* ->lo_sub[] slot in lovsub_object_fini()
*/
if (r0->lo_sub[idx] == los) {
waiter = &lov_env_info(env)->lti_waiter;
init_waitqueue_entry(waiter, current);
add_wait_queue(&bkt->lsb_marche_funebre, waiter);
set_current_state(TASK_UNINTERRUPTIBLE);
while (1) {
/* this wait-queue is signaled at the end of
* lu_object_free().
*/
set_current_state(TASK_UNINTERRUPTIBLE);
spin_lock(&r0->lo_sub_lock);
if (r0->lo_sub[idx] == los) {
spin_unlock(&r0->lo_sub_lock);
schedule();
} else {
spin_unlock(&r0->lo_sub_lock);
set_current_state(TASK_RUNNING);
break;
}
}
remove_wait_queue(&bkt->lsb_marche_funebre, waiter);
}
LASSERT(!r0->lo_sub[idx]);
}
static int osc_lock_upcall_agl(void *cookie, struct lustre_handle *lockh,
int errcode)
{
struct osc_object *osc = cookie;
struct ldlm_lock *dlmlock;
struct lu_env *env;
u16 refcheck;
env = cl_env_get(&refcheck);
LASSERT(!IS_ERR(env));
if (errcode == ELDLM_LOCK_MATCHED) {
errcode = ELDLM_OK;
goto out;
}
if (errcode != ELDLM_OK)
goto out;
dlmlock = ldlm_handle2lock(lockh);
LASSERT(dlmlock);
lock_res_and_lock(dlmlock);
LASSERT(dlmlock->l_granted_mode == dlmlock->l_req_mode);
/* there is no osc_lock associated with AGL lock */
osc_lock_lvb_update(env, osc, dlmlock, NULL);
unlock_res_and_lock(dlmlock);
LDLM_LOCK_PUT(dlmlock);
out:
cl_object_put(env, osc2cl(osc));
cl_env_put(env, &refcheck);
return ldlm_error2errno(errcode);
}
static int lov_init_sub(const struct lu_env *env, struct lov_object *lov,
struct cl_object *stripe, struct lov_layout_raid0 *r0,
int idx)
{
struct cl_object_header *hdr;
struct cl_object_header *subhdr;
struct cl_object_header *parent;
struct lov_oinfo *oinfo;
int result;
if (OBD_FAIL_CHECK(OBD_FAIL_LOV_INIT)) {
/* For sanity:test_206.
* Do not leave the object in cache to avoid accessing
* freed memory. This is because osc_object is referring to
* lov_oinfo of lsm_stripe_data which will be freed due to
* this failure. */
cl_object_kill(env, stripe);
cl_object_put(env, stripe);
return -EIO;
}
hdr = cl_object_header(lov2cl(lov));
subhdr = cl_object_header(stripe);
oinfo = lov->lo_lsm->lsm_oinfo[idx];
CDEBUG(D_INODE, DFID"@%p[%d] -> "DFID"@%p: ostid: "DOSTID
" idx: %d gen: %d\n",
PFID(&subhdr->coh_lu.loh_fid), subhdr, idx,
PFID(&hdr->coh_lu.loh_fid), hdr, POSTID(&oinfo->loi_oi),
oinfo->loi_ost_idx, oinfo->loi_ost_gen);
/* reuse ->coh_attr_guard to protect coh_parent change */
spin_lock(&subhdr->coh_attr_guard);
parent = subhdr->coh_parent;
if (parent == NULL) {
subhdr->coh_parent = hdr;
spin_unlock(&subhdr->coh_attr_guard);
subhdr->coh_nesting = hdr->coh_nesting + 1;
lu_object_ref_add(&stripe->co_lu, "lov-parent", lov);
r0->lo_sub[idx] = cl2lovsub(stripe);
r0->lo_sub[idx]->lso_super = lov;
r0->lo_sub[idx]->lso_index = idx;
result = 0;
} else {
struct lu_object *old_obj;
struct lov_object *old_lov;
unsigned int mask = D_INODE;
spin_unlock(&subhdr->coh_attr_guard);
old_obj = lu_object_locate(&parent->coh_lu, &lov_device_type);
LASSERT(old_obj != NULL);
old_lov = cl2lov(lu2cl(old_obj));
if (old_lov->lo_layout_invalid) {
/* the object's layout has already changed but isn't
* refreshed */
lu_object_unhash(env, &stripe->co_lu);
result = -EAGAIN;
} else {
mask = D_ERROR;
result = -EIO;
}
LU_OBJECT_DEBUG(mask, env, &stripe->co_lu,
"stripe %d is already owned.\n", idx);
LU_OBJECT_DEBUG(mask, env, old_obj, "owned.\n");
LU_OBJECT_HEADER(mask, env, lov2lu(lov), "try to own.\n");
cl_object_put(env, stripe);
}
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;
}
/**
* Helper for osc_dlm_blocking_ast() handling discrepancies between cl_lock
* and ldlm_lock caches.
*/
static int osc_dlm_blocking_ast0(const struct lu_env *env,
struct ldlm_lock *dlmlock,
void *data, int flag)
{
struct cl_object *obj = NULL;
int result = 0;
int discard;
enum cl_lock_mode mode = CLM_READ;
LASSERT(flag == LDLM_CB_CANCELING);
lock_res_and_lock(dlmlock);
if (dlmlock->l_granted_mode != dlmlock->l_req_mode) {
dlmlock->l_ast_data = NULL;
unlock_res_and_lock(dlmlock);
return 0;
}
discard = ldlm_is_discard_data(dlmlock);
if (dlmlock->l_granted_mode & (LCK_PW | LCK_GROUP))
mode = CLM_WRITE;
if (dlmlock->l_ast_data) {
obj = osc2cl(dlmlock->l_ast_data);
dlmlock->l_ast_data = NULL;
cl_object_get(obj);
}
unlock_res_and_lock(dlmlock);
/* if l_ast_data is NULL, the dlmlock was enqueued by AGL or
* the object has been destroyed.
*/
if (obj) {
struct ldlm_extent *extent = &dlmlock->l_policy_data.l_extent;
struct cl_attr *attr = &osc_env_info(env)->oti_attr;
__u64 old_kms;
/* Destroy pages covered by the extent of the DLM lock */
result = osc_lock_flush(cl2osc(obj),
cl_index(obj, extent->start),
cl_index(obj, extent->end),
mode, discard);
/* losing a lock, update kms */
lock_res_and_lock(dlmlock);
cl_object_attr_lock(obj);
/* Must get the value under the lock to avoid race. */
old_kms = cl2osc(obj)->oo_oinfo->loi_kms;
/* Update the kms. Need to loop all granted locks.
* Not a problem for the client
*/
attr->cat_kms = ldlm_extent_shift_kms(dlmlock, old_kms);
cl_object_attr_set(env, obj, attr, CAT_KMS);
cl_object_attr_unlock(obj);
unlock_res_and_lock(dlmlock);
cl_object_put(env, obj);
}
return result;
}
