* Copyright (c) 2008, 2010, Oracle and/or its affiliates. All rights reserved.
* Use is subject to license terms.
*
- * Copyright (c) 2011, 2013, Intel Corporation.
+ * Copyright (c) 2011, 2014, Intel Corporation.
*/
/*
* This file is part of Lustre, http://www.lustre.org/
#define DEBUG_SUBSYSTEM S_LOV
#include "lov_cl_internal.h"
-#include "lclient.h"
+
+static inline struct lov_device *lov_object_dev(struct lov_object *obj)
+{
+ return lu2lov_dev(obj->lo_cl.co_lu.lo_dev);
+}
/** \addtogroup lov
* @{
*/
struct lov_layout_operations {
- int (*llo_init)(const struct lu_env *env, struct lov_device *dev,
- struct lov_object *lov,
- const struct cl_object_conf *conf,
- union lov_layout_state *state);
+ int (*llo_init)(const struct lu_env *env, struct lov_device *dev,
+ struct lov_object *lov, struct lov_stripe_md *lsm,
+ const struct cl_object_conf *conf,
+ union lov_layout_state *state);
int (*llo_delete)(const struct lu_env *env, struct lov_object *lov,
union lov_layout_state *state);
void (*llo_fini)(const struct lu_env *env, struct lov_object *lov,
struct cl_object *obj, struct cl_io *io);
int (*llo_getattr)(const struct lu_env *env, struct cl_object *obj,
struct cl_attr *attr);
+ int (*llo_find_cbdata)(const struct lu_env *env, struct cl_object *obj,
+ ldlm_iterator_t iter, void *data);
};
static int lov_layout_wait(const struct lu_env *env, struct lov_object *lov);
+static void lov_lsm_put(struct lov_stripe_md *lsm)
+{
+ if (lsm != NULL)
+ lov_free_memmd(&lsm);
+}
+
/*****************************************************************************
*
* Lov object layout operations.
*/
}
-static int lov_init_empty(const struct lu_env *env,
- struct lov_device *dev, struct lov_object *lov,
- const struct cl_object_conf *conf,
- union lov_layout_state *state)
+static int lov_init_empty(const struct lu_env *env, struct lov_device *dev,
+ struct lov_object *lov, struct lov_stripe_md *lsm,
+ const struct cl_object_conf *conf,
+ union lov_layout_state *state)
{
- return 0;
+ return 0;
}
static void lov_install_raid0(const struct lu_env *env,
return cl_object_header(stripe)->coh_page_bufsize;
}
-static int lov_init_raid0(const struct lu_env *env,
- struct lov_device *dev, struct lov_object *lov,
- const struct cl_object_conf *conf,
- union lov_layout_state *state)
+static int lov_init_raid0(const struct lu_env *env, struct lov_device *dev,
+ struct lov_object *lov, struct lov_stripe_md *lsm,
+ const struct cl_object_conf *conf,
+ union lov_layout_state *state)
{
int result;
int i;
struct cl_object *stripe;
struct lov_thread_info *lti = lov_env_info(env);
struct cl_object_conf *subconf = <i->lti_stripe_conf;
- struct lov_stripe_md *lsm = conf->u.coc_md->lsm;
struct lu_fid *ofid = <i->lti_fid;
struct lov_layout_raid0 *r0 = &state->raid0;
LASSERT(lov->lo_lsm == NULL);
lov->lo_lsm = lsm_addref(lsm);
- r0->lo_nr = lsm->lsm_stripe_count;
+ r0->lo_nr = lsm->lsm_stripe_count;
LASSERT(r0->lo_nr <= lov_targets_nr(dev));
lov->lo_layout_invalid = true;
}
static int lov_init_released(const struct lu_env *env,
- struct lov_device *dev, struct lov_object *lov,
- const struct cl_object_conf *conf,
- union lov_layout_state *state)
+ struct lov_device *dev, struct lov_object *lov,
+ struct lov_stripe_md *lsm,
+ const struct cl_object_conf *conf,
+ union lov_layout_state *state)
{
- struct lov_stripe_md *lsm = conf->u.coc_md->lsm;
-
LASSERT(lsm != NULL);
LASSERT(lsm_is_released(lsm));
LASSERT(lov->lo_lsm == NULL);
return 0;
}
+static struct cl_object *lov_find_subobj(const struct lu_env *env,
+ struct lov_object *lov,
+ struct lov_stripe_md *lsm,
+ int stripe_idx)
+{
+ struct lov_device *dev = lu2lov_dev(lov2lu(lov)->lo_dev);
+ struct lov_oinfo *oinfo = lsm->lsm_oinfo[stripe_idx];
+ struct lov_thread_info *lti = lov_env_info(env);
+ struct lu_fid *ofid = <i->lti_fid;
+ struct cl_device *subdev;
+ int ost_idx;
+ int rc;
+ struct cl_object *result;
+
+ if (lov->lo_type != LLT_RAID0)
+ GOTO(out, result = NULL);
+
+ ost_idx = oinfo->loi_ost_idx;
+ rc = ostid_to_fid(ofid, &oinfo->loi_oi, ost_idx);
+ if (rc != 0)
+ GOTO(out, result = NULL);
+
+ subdev = lovsub2cl_dev(dev->ld_target[ost_idx]);
+ result = lov_sub_find(env, subdev, ofid, NULL);
+out:
+ if (result == NULL)
+ result = ERR_PTR(-EINVAL);
+ return result;
+}
+
static int lov_delete_empty(const struct lu_env *env, struct lov_object *lov,
union lov_layout_state *state)
{
* ->lo_sub[] slot in lovsub_object_fini() */
if (r0->lo_sub[idx] == los) {
waiter = &lov_env_info(env)->lti_waiter;
- init_waitqueue_entry_current(waiter);
+ init_waitqueue_entry(waiter, current);
add_wait_queue(&bkt->lsb_marche_funebre, waiter);
set_current_state(TASK_UNINTERRUPTIBLE);
while (1) {
spin_lock(&r0->lo_sub_lock);
if (r0->lo_sub[idx] == los) {
spin_unlock(&r0->lo_sub_lock);
- waitq_wait(waiter, TASK_UNINTERRUPTIBLE);
+ schedule();
} else {
spin_unlock(&r0->lo_sub_lock);
set_current_state(TASK_RUNNING);
RETURN(result);
}
+static int lov_find_cbdata_empty(const struct lu_env *env,
+ struct cl_object *obj, ldlm_iterator_t iter,
+ void *data)
+{
+ return 0;
+}
+
+static int lov_find_cbdata_raid0(const struct lu_env *env,
+ struct cl_object *obj, ldlm_iterator_t iter,
+ void *data)
+{
+ struct lov_object *lov = cl2lov(obj);
+ struct lov_layout_raid0 *r0 = lov_r0(lov);
+ struct cl_object *subobj;
+ int i;
+ int rc = 0;
+
+ for (i = 0; i < r0->lo_nr; ++i) {
+ if (r0->lo_sub[i] == NULL)
+ continue;
+
+ subobj = lovsub2cl(r0->lo_sub[i]);
+
+ rc = cl_object_find_cbdata(env, subobj, iter, data);
+ if (rc != 0)
+ break;
+ }
+
+ return rc;
+}
+
const static struct lov_layout_operations lov_dispatch[] = {
[LLT_EMPTY] = {
.llo_init = lov_init_empty,
.llo_page_init = lov_page_init_empty,
.llo_lock_init = lov_lock_init_empty,
.llo_io_init = lov_io_init_empty,
- .llo_getattr = lov_attr_get_empty
+ .llo_getattr = lov_attr_get_empty,
+ .llo_find_cbdata = lov_find_cbdata_empty
},
[LLT_RAID0] = {
.llo_init = lov_init_raid0,
.llo_page_init = lov_page_init_raid0,
.llo_lock_init = lov_lock_init_raid0,
.llo_io_init = lov_io_init_raid0,
- .llo_getattr = lov_attr_get_raid0
+ .llo_getattr = lov_attr_get_raid0,
+ .llo_find_cbdata = lov_find_cbdata_raid0
},
[LLT_RELEASED] = {
.llo_init = lov_init_released,
.llo_page_init = lov_page_init_empty,
.llo_lock_init = lov_lock_init_empty,
.llo_io_init = lov_io_init_released,
- .llo_getattr = lov_attr_get_empty
+ .llo_getattr = lov_attr_get_empty,
+ .llo_find_cbdata = lov_find_cbdata_empty
}
};
}
static int lov_layout_change(const struct lu_env *unused,
- struct lov_object *lov,
+ struct lov_object *lov, struct lov_stripe_md *lsm,
const struct cl_object_conf *conf)
{
- int result;
- enum lov_layout_type llt = LLT_EMPTY;
+ enum lov_layout_type llt = lov_type(lsm);
union lov_layout_state *state = &lov->u;
const struct lov_layout_operations *old_ops;
const struct lov_layout_operations *new_ops;
-
void *cookie;
struct lu_env *env;
int refcheck;
+ int rc;
ENTRY;
LASSERT(0 <= lov->lo_type && lov->lo_type < ARRAY_SIZE(lov_dispatch));
- if (conf->u.coc_md != NULL)
- llt = lov_type(conf->u.coc_md->lsm);
- LASSERT(0 <= llt && llt < ARRAY_SIZE(lov_dispatch));
-
cookie = cl_env_reenter();
env = cl_env_get(&refcheck);
if (IS_ERR(env)) {
RETURN(PTR_ERR(env));
}
+ LASSERT(0 <= llt && llt < ARRAY_SIZE(lov_dispatch));
+
CDEBUG(D_INODE, DFID" from %s to %s\n",
PFID(lu_object_fid(lov2lu(lov))),
llt2str(lov->lo_type), llt2str(llt));
old_ops = &lov_dispatch[lov->lo_type];
new_ops = &lov_dispatch[llt];
- result = cl_object_prune(env, &lov->lo_cl);
- if (result != 0)
- GOTO(out, result);
+ rc = cl_object_prune(env, &lov->lo_cl);
+ if (rc != 0)
+ GOTO(out, rc);
- result = old_ops->llo_delete(env, lov, &lov->u);
- if (result == 0) {
- old_ops->llo_fini(env, lov, &lov->u);
+ rc = old_ops->llo_delete(env, lov, &lov->u);
+ if (rc != 0)
+ GOTO(out, rc);
- LASSERT(atomic_read(&lov->lo_active_ios) == 0);
+ old_ops->llo_fini(env, lov, &lov->u);
- lov->lo_type = LLT_EMPTY;
- /* page bufsize fixup */
- cl_object_header(&lov->lo_cl)->coh_page_bufsize -=
- lov_page_slice_fixup(lov, NULL);
+ LASSERT(atomic_read(&lov->lo_active_ios) == 0);
- result = new_ops->llo_init(env,
- lu2lov_dev(lov->lo_cl.co_lu.lo_dev),
- lov, conf, state);
- if (result == 0) {
- new_ops->llo_install(env, lov, state);
- lov->lo_type = llt;
- } else {
- new_ops->llo_delete(env, lov, state);
- new_ops->llo_fini(env, lov, state);
- /* this file becomes an EMPTY file. */
- }
+ lov->lo_type = LLT_EMPTY;
+
+ /* page bufsize fixup */
+ cl_object_header(&lov->lo_cl)->coh_page_bufsize -=
+ lov_page_slice_fixup(lov, NULL);
+
+ rc = new_ops->llo_init(env, lov_object_dev(lov), lov, lsm, conf, state);
+ if (rc != 0) {
+ new_ops->llo_delete(env, lov, state);
+ new_ops->llo_fini(env, lov, state);
+ /* this file becomes an EMPTY file. */
+ GOTO(out, rc);
}
+ new_ops->llo_install(env, lov, state);
+ lov->lo_type = llt;
+
out:
cl_env_put(env, &refcheck);
cl_env_reexit(cookie);
- RETURN(result);
+
+ RETURN(rc);
}
/*****************************************************************************
*
*/
int lov_object_init(const struct lu_env *env, struct lu_object *obj,
- const struct lu_object_conf *conf)
+ const struct lu_object_conf *conf)
{
- struct lov_device *dev = lu2lov_dev(obj->lo_dev);
- struct lov_object *lov = lu2lov(obj);
- const struct cl_object_conf *cconf = lu2cl_conf(conf);
- union lov_layout_state *set = &lov->u;
- const struct lov_layout_operations *ops;
- int result;
+ 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;
- 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));
- /* no locking is necessary, as object is being created */
- lov->lo_type = lov_type(cconf->u.coc_md->lsm);
- ops = &lov_dispatch[lov->lo_type];
- result = ops->llo_init(env, dev, lov, cconf, set);
- if (result == 0)
- ops->llo_install(env, lov, set);
- RETURN(result);
+ 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,
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;
LASSERT(conf->coc_opc == OBJECT_CONF_SET);
- if (conf->u.coc_md != NULL)
- lsm = conf->u.coc_md->lsm;
if ((lsm == NULL && lov->lo_lsm == NULL) ||
((lsm != NULL && lov->lo_lsm != NULL) &&
(lov->lo_lsm->lsm_layout_gen == lsm->lsm_layout_gen) &&
GOTO(out, result = -EBUSY);
}
- result = lov_layout_change(env, lov, conf);
+ 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);
return LOV_2DISPATCH_NOLOCK(cl2lov(obj), llo_getattr, env, obj, attr);
}
-static int lov_attr_set(const struct lu_env *env, struct cl_object *obj,
- const struct cl_attr *attr, unsigned valid)
+static int lov_attr_update(const struct lu_env *env, struct cl_object *obj,
+ const struct cl_attr *attr, unsigned valid)
{
- /*
- * No dispatch is required here, as no layout implements this.
- */
- return 0;
+ /*
+ * No dispatch is required here, as no layout implements this.
+ */
+ return 0;
}
int lov_lock_init(const struct lu_env *env, struct cl_object *obj,
io);
}
+/**
+ * We calculate on which OST the mapping will end. If the length of mapping
+ * is greater than (stripe_size * stripe_count) then the last_stripe will
+ * will be one just before start_stripe. Else we check if the mapping
+ * intersects each OST and find last_stripe.
+ * This function returns the last_stripe and also sets the stripe_count
+ * over which the mapping is spread
+ *
+ * \param lsm [in] striping information for the file
+ * \param fm_start [in] logical start of mapping
+ * \param fm_end [in] logical end of mapping
+ * \param start_stripe [in] starting stripe of the mapping
+ * \param stripe_count [out] the number of stripes across which to map is
+ * returned
+ *
+ * \retval last_stripe return the last stripe of the mapping
+ */
+static int fiemap_calc_last_stripe(struct lov_stripe_md *lsm,
+ loff_t fm_start, loff_t fm_end,
+ int start_stripe, int *stripe_count)
+{
+ int last_stripe;
+ loff_t obd_start;
+ loff_t obd_end;
+ int i, j;
+
+ if (fm_end - fm_start > lsm->lsm_stripe_size * lsm->lsm_stripe_count) {
+ last_stripe = (start_stripe < 1 ? lsm->lsm_stripe_count - 1 :
+ start_stripe - 1);
+ *stripe_count = lsm->lsm_stripe_count;
+ } else {
+ for (j = 0, i = start_stripe; j < lsm->lsm_stripe_count;
+ i = (i + 1) % lsm->lsm_stripe_count, j++) {
+ if ((lov_stripe_intersects(lsm, i, fm_start, fm_end,
+ &obd_start, &obd_end)) == 0)
+ break;
+ }
+ *stripe_count = j;
+ last_stripe = (start_stripe + j - 1) % lsm->lsm_stripe_count;
+ }
+
+ return last_stripe;
+}
+
+/**
+ * Set fe_device and copy extents from local buffer into main return buffer.
+ *
+ * \param fiemap [out] fiemap to hold all extents
+ * \param lcl_fm_ext [in] array of fiemap extents get from OSC layer
+ * \param ost_index [in] OST index to be written into the fm_device
+ * field for each extent
+ * \param ext_count [in] number of extents to be copied
+ * \param current_extent [in] where to start copying in the extent array
+ */
+static void fiemap_prepare_and_copy_exts(struct fiemap *fiemap,
+ struct fiemap_extent *lcl_fm_ext,
+ int ost_index, unsigned int ext_count,
+ int current_extent)
+{
+ char *to;
+ unsigned int ext;
+
+ for (ext = 0; ext < ext_count; ext++) {
+ lcl_fm_ext[ext].fe_device = ost_index;
+ lcl_fm_ext[ext].fe_flags |= FIEMAP_EXTENT_NET;
+ }
+
+ /* Copy fm_extent's from fm_local to return buffer */
+ to = (char *)fiemap + fiemap_count_to_size(current_extent);
+ memcpy(to, lcl_fm_ext, ext_count * sizeof(struct fiemap_extent));
+}
+
+#define FIEMAP_BUFFER_SIZE 4096
+
+/**
+ * Non-zero fe_logical indicates that this is a continuation FIEMAP
+ * call. The local end offset and the device are sent in the first
+ * fm_extent. This function calculates the stripe number from the index.
+ * This function returns a stripe_no on which mapping is to be restarted.
+ *
+ * This function returns fm_end_offset which is the in-OST offset at which
+ * mapping should be restarted. If fm_end_offset=0 is returned then caller
+ * will re-calculate proper offset in next stripe.
+ * Note that the first extent is passed to lov_get_info via the value field.
+ *
+ * \param fiemap [in] fiemap request header
+ * \param lsm [in] striping information for the file
+ * \param fm_start [in] logical start of mapping
+ * \param fm_end [in] logical end of mapping
+ * \param start_stripe [out] starting stripe will be returned in this
+ */
+static loff_t fiemap_calc_fm_end_offset(struct fiemap *fiemap,
+ struct lov_stripe_md *lsm,
+ loff_t fm_start, loff_t fm_end,
+ int *start_stripe)
+{
+ loff_t local_end = fiemap->fm_extents[0].fe_logical;
+ loff_t lun_start;
+ loff_t lun_end;
+ loff_t fm_end_offset;
+ int stripe_no = -1;
+ int i;
+
+ if (fiemap->fm_extent_count == 0 ||
+ fiemap->fm_extents[0].fe_logical == 0)
+ return 0;
+
+ /* Find out stripe_no from ost_index saved in the fe_device */
+ for (i = 0; i < lsm->lsm_stripe_count; i++) {
+ struct lov_oinfo *oinfo = lsm->lsm_oinfo[i];
+
+ if (lov_oinfo_is_dummy(oinfo))
+ continue;
+
+ if (oinfo->loi_ost_idx == fiemap->fm_extents[0].fe_device) {
+ stripe_no = i;
+ break;
+ }
+ }
+
+ if (stripe_no == -1)
+ return -EINVAL;
+
+ /* If we have finished mapping on previous device, shift logical
+ * offset to start of next device */
+ if (lov_stripe_intersects(lsm, stripe_no, fm_start, fm_end,
+ &lun_start, &lun_end) != 0 &&
+ local_end < lun_end) {
+ fm_end_offset = local_end;
+ *start_stripe = stripe_no;
+ } else {
+ /* This is a special value to indicate that caller should
+ * calculate offset in next stripe. */
+ fm_end_offset = 0;
+ *start_stripe = (stripe_no + 1) % lsm->lsm_stripe_count;
+ }
+
+ return fm_end_offset;
+}
+
+/**
+ * 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, 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, 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, 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, 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, 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, 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:
+ if (fm_local != NULL)
+ OBD_FREE_LARGE(fm_local, buffer_size);
+
+ lov_lsm_put(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);
+}
+
+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;
+ cl->cl_is_released = false;
+
+ RETURN(0);
+ }
+
+ cl->cl_size = lov_mds_md_size(lsm->lsm_stripe_count, lsm->lsm_magic);
+ cl->cl_layout_gen = lsm->lsm_layout_gen;
+ cl->cl_is_released = lsm_is_released(lsm);
+
+ 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_find_cbdata(const struct lu_env *env,
+ struct cl_object *obj, ldlm_iterator_t iter,
+ void *data)
+{
+ int rc;
+ ENTRY;
+
+ /* call cl_object_find_cbdata for sub obj */
+ rc = LOV_2DISPATCH_NOLOCK(cl2lov(obj), llo_find_cbdata,
+ env, obj, iter, data);
+ RETURN(rc);
+}
+
static const struct cl_object_operations lov_ops = {
- .coo_page_init = lov_page_init,
- .coo_lock_init = lov_lock_init,
- .coo_io_init = lov_io_init,
- .coo_attr_get = lov_attr_get,
- .coo_attr_set = lov_attr_set,
- .coo_conf_set = lov_conf_set
+ .coo_page_init = lov_page_init,
+ .coo_lock_init = lov_lock_init,
+ .coo_io_init = lov_io_init,
+ .coo_attr_get = lov_attr_get,
+ .coo_attr_update = lov_attr_update,
+ .coo_conf_set = lov_conf_set,
+ .coo_getstripe = lov_object_getstripe,
+ .coo_layout_get = lov_object_layout_get,
+ .coo_maxbytes = lov_object_maxbytes,
+ .coo_find_cbdata = lov_object_find_cbdata,
+ .coo_fiemap = lov_object_fiemap,
};
static const struct lu_object_operations lov_lu_obj_ops = {
return lsm;
}
-struct lov_stripe_md *lov_lsm_get(struct cl_object *clobj)
-{
- struct lu_object *luobj;
- struct lov_stripe_md *lsm = NULL;
-
- if (clobj == NULL)
- return NULL;
-
- luobj = lu_object_locate(&cl_object_header(clobj)->coh_lu,
- &lov_device_type);
- if (luobj != NULL)
- lsm = lov_lsm_addref(lu2lov(luobj));
- return lsm;
-}
-EXPORT_SYMBOL(lov_lsm_get);
-
-void lov_lsm_put(struct cl_object *unused, struct lov_stripe_md *lsm)
-{
- if (lsm != NULL)
- lov_free_memmd(&lsm);
-}
-EXPORT_SYMBOL(lov_lsm_put);
-
int lov_read_and_clear_async_rc(struct cl_object *clob)
{
struct lu_object *luobj;