*
* You should have received a copy of the GNU General Public License
* version 2 along with this program; If not, see
- * http://www.sun.com/software/products/lustre/docs/GPLv2.pdf
- *
- * Please contact Sun Microsystems, Inc., 4150 Network Circle, Santa Clara,
- * CA 95054 USA or visit www.sun.com if you need additional information or
- * have any questions.
+ * http://www.gnu.org/licenses/gpl-2.0.html
*
* GPL HEADER END
*/
* 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, 2016, 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,
static int lov_layout_wait(const struct lu_env *env, struct lov_object *lov);
-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)
+static void lov_lsm_put(struct lov_stripe_md *lsm)
{
if (lsm != NULL)
lov_free_memmd(&lsm);
}
-EXPORT_SYMBOL(lov_lsm_put);
/*****************************************************************************
*
*/
}
-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,
}
LU_OBJECT_DEBUG(mask, env, &stripe->co_lu,
- "stripe %d is already owned.\n", idx);
- LU_OBJECT_DEBUG(mask, env, old_obj, "owned.\n");
+ "stripe %d is already owned.", idx);
+ LU_OBJECT_DEBUG(mask, env, old_obj, "owned.");
LU_OBJECT_HEADER(mask, env, lov2lu(lov), "try to own.\n");
cl_object_put(env, stripe);
}
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;
if (result != 0)
GOTO(out, result);
+ if (dev->ld_target[ost_idx] == NULL) {
+ CERROR("%s: OST %04x is not initialized\n",
+ lov2obd(dev->ld_lov)->obd_name, ost_idx);
+ GOTO(out, result = -EIO);
+ }
+
subdev = lovsub2cl_dev(dev->ld_target[ost_idx]);
subconf->u.coc_oinfo = oinfo;
LASSERTF(subdev != NULL, "not init ost %d\n", ost_idx);
}
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);
.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,
},
[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,
},
[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,
}
};
/**
* Performs a double-dispatch based on the layout type of an object.
*/
-#define LOV_2DISPATCH_NOLOCK(obj, op, ...) \
-({ \
- struct lov_object *__obj = (obj); \
- enum lov_layout_type __llt; \
- \
- __llt = __obj->lo_type; \
- LASSERT(0 <= __llt && __llt < ARRAY_SIZE(lov_dispatch)); \
- lov_dispatch[__llt].op(__VA_ARGS__); \
+#define LOV_2DISPATCH_NOLOCK(obj, op, ...) \
+({ \
+ struct lov_object *__obj = (obj); \
+ enum lov_layout_type __llt; \
+ \
+ __llt = __obj->lo_type; \
+ LASSERT(__llt < ARRAY_SIZE(lov_dispatch)); \
+ lov_dispatch[__llt].op(__VA_ARGS__); \
})
/**
static inline void lov_conf_freeze(struct lov_object *lov)
{
+ CDEBUG(D_INODE, "To take share lov(%p) owner %p/%p\n",
+ lov, lov->lo_owner, current);
if (lov->lo_owner != current)
down_read(&lov->lo_type_guard);
}
static inline void lov_conf_thaw(struct lov_object *lov)
{
+ CDEBUG(D_INODE, "To release share lov(%p) owner %p/%p\n",
+ lov, lov->lo_owner, current);
if (lov->lo_owner != current)
up_read(&lov->lo_type_guard);
}
\
lov_conf_freeze(__obj); \
__llt = __obj->lo_type; \
- LASSERT(0 <= __llt && __llt < ARRAY_SIZE(lov_dispatch)); \
+ LASSERT(__llt < ARRAY_SIZE(lov_dispatch)); \
lov_dispatch[__llt].op(__VA_ARGS__); \
lov_conf_thaw(__obj); \
} while (0)
down_write(&lov->lo_type_guard);
LASSERT(lov->lo_owner == NULL);
lov->lo_owner = current;
+ CDEBUG(D_INODE, "Took exclusive lov(%p) owner %p\n",
+ lov, lov->lo_owner);
}
static void lov_conf_unlock(struct lov_object *lov)
{
+ CDEBUG(D_INODE, "To release exclusive lov(%p) owner %p\n",
+ lov, lov->lo_owner);
lov->lo_owner = NULL;
up_write(&lov->lo_type_guard);
}
}
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 lov_device *lov_dev = lov_object_dev(lov);
struct lu_env *env;
- int refcheck;
+ __u16 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));
+ LASSERT(lov->lo_type < ARRAY_SIZE(lov_dispatch));
- cookie = cl_env_reenter();
env = cl_env_get(&refcheck);
- if (IS_ERR(env)) {
- cl_env_reexit(cookie);
+ if (IS_ERR(env))
RETURN(PTR_ERR(env));
- }
+
+ LASSERT(llt < ARRAY_SIZE(lov_dispatch));
CDEBUG(D_INODE, DFID" from %s to %s\n",
PFID(lu_object_fid(lov2lu(lov))),
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. */
- }
+ CDEBUG(D_INODE, DFID "Apply new layout lov %p, type %d\n",
+ PFID(lu_object_fid(lov2lu(lov))), lov, llt);
+
+ 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_dev, lov, lsm, conf, state);
+ if (rc != 0) {
+ struct obd_device *obd = lov2obd(lov_dev->ld_lov);
+
+ CERROR("%s: cannot apply new layout on "DFID" : rc = %d\n",
+ obd->obd_name, PFID(lu_object_fid(lov2lu(lov))), rc);
+ 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);
+ 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,
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);
struct cl_io *io)
{
CL_IO_SLICE_CLEAN(lov_env_io(env), lis_cl);
+
+ CDEBUG(D_INODE, DFID "io %p type %d ignore/verify layout %d/%d\n",
+ PFID(lu_object_fid(&obj->co_lu)), io, io->ci_type,
+ io->ci_ignore_layout, io->ci_verify_layout);
+
return LOV_2DISPATCH_MAYLOCK(cl2lov(obj), llo_io_init,
!io->ci_ignore_layout, env, obj, io);
}
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,
+ u64 fm_start, u64 fm_end,
+ int start_stripe, int *stripe_count)
+{
+ int last_stripe;
+ u64 obd_start;
+ u64 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 u64 fiemap_calc_fm_end_offset(struct fiemap *fiemap,
+ struct lov_stripe_md *lsm,
+ u64 fm_start, u64 fm_end,
+ int *start_stripe)
+{
+ u64 local_end = fiemap->fm_extents[0].fe_logical;
+ u64 lun_start;
+ u64 lun_end;
+ u64 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;
+}
+
+struct fiemap_state {
+ struct fiemap *fs_fm;
+ u64 fs_start;
+ u64 fs_length;
+ u64 fs_end;
+ u64 fs_end_offset;
+ int fs_cur_extent;
+ int fs_cnt_need;
+ int fs_start_stripe;
+ int fs_last_stripe;
+ bool fs_device_done;
+ bool fs_finish;
+ bool fs_enough;
+};
+
+int fiemap_for_stripe(const struct lu_env *env, struct cl_object *obj,
+ struct lov_stripe_md *lsm,
+ struct fiemap *fiemap, size_t *buflen,
+ struct ll_fiemap_info_key *fmkey, int stripeno,
+ struct fiemap_state *fs)
+{
+ struct cl_object *subobj;
+ struct lov_obd *lov = lu2lov_dev(obj->co_lu.lo_dev)->ld_lov;
+ struct fiemap_extent *fm_ext = &fs->fs_fm->fm_extents[0];
+ u64 req_fm_len; /* Stores length of required mapping */
+ u64 len_mapped_single_call;
+ u64 lun_start;
+ u64 lun_end;
+ u64 obd_object_end;
+ unsigned int ext_count;
+ /* EOF for object */
+ bool ost_eof = false;
+ /* done with required mapping for this OST? */
+ bool ost_done = false;
+ int ost_index;
+ int rc = 0;
+
+ fs->fs_device_done = false;
+ /* Find out range of mapping on this stripe */
+ if ((lov_stripe_intersects(lsm, stripeno, fs->fs_start, fs->fs_end,
+ &lun_start, &obd_object_end)) == 0)
+ return 0;
+
+ if (lov_oinfo_is_dummy(lsm->lsm_oinfo[stripeno]))
+ return -EIO;
+
+ /* If this is a continuation FIEMAP call and we are on
+ * starting stripe then lun_start needs to be set to
+ * end_offset */
+ if (fs->fs_end_offset != 0 && stripeno == fs->fs_start_stripe)
+ lun_start = fs->fs_end_offset;
+
+ lun_end = fs->fs_length;
+ if (lun_end != ~0ULL) {
+ /* Handle fs->fs_start + fs->fs_length overflow */
+ if (fs->fs_start + fs->fs_length < fs->fs_start)
+ fs->fs_length = ~0ULL - fs->fs_start;
+ lun_end = lov_size_to_stripe(lsm, fs->fs_start + fs->fs_length,
+ stripeno);
+ }
+
+ if (lun_start == lun_end)
+ return 0;
+
+ req_fm_len = obd_object_end - lun_start;
+ fs->fs_fm->fm_length = 0;
+ len_mapped_single_call = 0;
+
+ /* find lobsub object */
+ subobj = lov_find_subobj(env, cl2lov(obj), lsm, stripeno);
+ if (IS_ERR(subobj))
+ return 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 */
+ do {
+ if (fiemap->fm_extent_count > 0) {
+ /* Don't get too many extents. */
+ if (fs->fs_cur_extent + fs->fs_cnt_need >
+ fiemap->fm_extent_count)
+ fs->fs_cnt_need = fiemap->fm_extent_count -
+ fs->fs_cur_extent;
+ }
+
+ lun_start += len_mapped_single_call;
+ fs->fs_fm->fm_length = req_fm_len - len_mapped_single_call;
+ req_fm_len = fs->fs_fm->fm_length;
+ fs->fs_fm->fm_extent_count = fs->fs_enough ?
+ 1 : fs->fs_cnt_need;
+ fs->fs_fm->fm_mapped_extents = 0;
+ fs->fs_fm->fm_flags = fiemap->fm_flags;
+
+ ost_index = lsm->lsm_oinfo[stripeno]->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) {
+ fs->fs_fm->fm_flags |= FIEMAP_EXTENT_LAST;
+ fs->fs_fm->fm_mapped_extents = 1;
+
+ fm_ext[0].fe_logical = lun_start;
+ fm_ext[0].fe_length = obd_object_end - lun_start;
+ fm_ext[0].fe_flags |= FIEMAP_EXTENT_UNKNOWN;
+
+ goto inactive_tgt;
+ }
+
+ fs->fs_fm->fm_start = lun_start;
+ fs->fs_fm->fm_flags &= ~FIEMAP_FLAG_DEVICE_ORDER;
+ memcpy(&fmkey->lfik_fiemap, fs->fs_fm, sizeof(*fs->fs_fm));
+ *buflen = fiemap_count_to_size(fs->fs_fm->fm_extent_count);
+
+ rc = cl_object_fiemap(env, subobj, fmkey, fs->fs_fm, buflen);
+ if (rc != 0)
+ GOTO(obj_put, rc);
+inactive_tgt:
+ ext_count = fs->fs_fm->fm_mapped_extents;
+ if (ext_count == 0) {
+ ost_done = true;
+ fs->fs_device_done = true;
+ /* If last stripe has hold at the end,
+ * we need to return */
+ if (stripeno == fs->fs_last_stripe) {
+ fiemap->fm_mapped_extents = 0;
+ fs->fs_finish = true;
+ GOTO(obj_put, rc);
+ }
+ break;
+ } else if (fs->fs_enough) {
+ /*
+ * We've collected enough extents and there are
+ * more extents after it.
+ */
+ fs->fs_finish = true;
+ GOTO(obj_put, rc);
+ }
+
+ /* If we just need num of extents, got to next device */
+ if (fiemap->fm_extent_count == 0) {
+ fs->fs_cur_extent += ext_count;
+ break;
+ }
+
+ /* prepare to copy retrived map extents */
+ len_mapped_single_call = fm_ext[ext_count - 1].fe_logical +
+ fm_ext[ext_count - 1].fe_length -
+ lun_start;
+
+ /* Have we finished mapping on this device? */
+ if (req_fm_len <= len_mapped_single_call) {
+ ost_done = true;
+ fs->fs_device_done = true;
+ }
+
+ /* Clear the EXTENT_LAST flag which can be present on
+ * the last extent */
+ if (fm_ext[ext_count - 1].fe_flags & FIEMAP_EXTENT_LAST)
+ fm_ext[ext_count - 1].fe_flags &= ~FIEMAP_EXTENT_LAST;
+ if (lov_stripe_size(lsm, fm_ext[ext_count - 1].fe_logical +
+ fm_ext[ext_count - 1].fe_length,
+ stripeno) >= fmkey->lfik_oa.o_size) {
+ ost_eof = true;
+ fs->fs_device_done = true;
+ }
+
+ fiemap_prepare_and_copy_exts(fiemap, fm_ext, ost_index,
+ ext_count, fs->fs_cur_extent);
+ fs->fs_cur_extent += ext_count;
+
+ /* Ran out of available extents? */
+ if (fs->fs_cur_extent >= fiemap->fm_extent_count)
+ fs->fs_enough = true;
+ } while (!ost_done && !ost_eof);
+
+ if (stripeno == fs->fs_last_stripe)
+ fs->fs_finish = true;
+obj_put:
+ cl_object_put(env, subobj);
+
+ return rc;
+}
+
+/**
+ * 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 fiemap *fm_local = NULL;
+ int cur_stripe;
+ int stripe_count;
+ unsigned int buffer_size = FIEMAP_BUFFER_SIZE;
+ int rc = 0;
+ struct fiemap_state fs = { 0 };
+ 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);
+
+ fs.fs_fm = fm_local;
+ fs.fs_cnt_need = fiemap_size_to_count(buffer_size);
+
+ fs.fs_start = fiemap->fm_start;
+ /* fs.fs_start is beyond the end of the file */
+ if (fs.fs_start > fmkey->lfik_oa.o_size)
+ GOTO(out_fm_local, rc = -EINVAL);
+
+ fs.fs_length = fiemap->fm_length;
+ /* Calculate start stripe, last stripe and length of mapping */
+ fs.fs_start_stripe = lov_stripe_number(lsm, fs.fs_start);
+ fs.fs_end = (fs.fs_length == ~0ULL) ? fmkey->lfik_oa.o_size :
+ fs.fs_start + fs.fs_length - 1;
+ /* If fs_length != ~0ULL but fs_start+fs_length-1 exceeds file size */
+ if (fs.fs_end > fmkey->lfik_oa.o_size) {
+ fs.fs_end = fmkey->lfik_oa.o_size;
+ fs.fs_length = fs.fs_end - fs.fs_start;
+ }
+
+ fs.fs_last_stripe = fiemap_calc_last_stripe(lsm, fs.fs_start, fs.fs_end,
+ fs.fs_start_stripe,
+ &stripe_count);
+ fs.fs_end_offset = fiemap_calc_fm_end_offset(fiemap, lsm, fs.fs_start,
+ fs.fs_end,
+ &fs.fs_start_stripe);
+ if (fs.fs_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)
+ fs.fs_cnt_need = 0;
+
+ fs.fs_finish = false;
+ fs.fs_enough = false;
+ fs.fs_cur_extent = 0;
+
+ /* Check each stripe */
+ for (cur_stripe = fs.fs_start_stripe; stripe_count > 0;
+ --stripe_count,
+ cur_stripe = (cur_stripe + 1) % lsm->lsm_stripe_count) {
+ rc = fiemap_for_stripe(env, obj, lsm, fiemap, buflen, fmkey,
+ cur_stripe, &fs);
+ if (rc < 0)
+ GOTO(out_fm_local, rc);
+ if (fs.fs_finish)
+ break;
+ } /* for each stripe */
+
+ /* 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 == fs.fs_last_stripe) && fs.fs_device_done)
+ fiemap->fm_extents[fs.fs_cur_extent - 1].fe_flags |=
+ FIEMAP_EXTENT_LAST;
+skip_last_device_calc:
+ fiemap->fm_mapped_extents = fs.fs_cur_extent;
+out_fm_local:
+ OBD_FREE_LARGE(fm_local, buffer_size);
+
+out_lsm:
+ 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)
{
RETURN(-ENODATA);
rc = lov_getstripe(cl2lov(obj), lsm, lum);
- lov_lsm_put(obj, lsm);
+ 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;
+
+ 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 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_getstripe = lov_object_getstripe
+ .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_fiemap = lov_object_fiemap,
};
static const struct lu_object_operations lov_lu_obj_ops = {
git://git.whamcloud.com / fs / lustre-release.git / blobdiff