*/
/*
* This file is part of Lustre, http://www.lustre.org/
- * Lustre is a trademark of Sun Microsystems, Inc.
*/
/*
* lustre/include/lustre_osc.h
#include <libcfs/libcfs.h>
#include <obd.h>
#include <cl_object.h>
+#include <lustre_crypto.h>
/** \defgroup osc osc
* @{
return container_of(pga, struct osc_async_page, oap_brw_page);
}
-struct osc_cache_waiter {
- struct list_head ocw_entry;
- wait_queue_head_t ocw_waitq;
- struct osc_async_page *ocw_oap;
- int ocw_grant;
- int ocw_rc;
-};
-
struct osc_device {
struct cl_device od_cl;
struct obd_export *od_exp;
/* Write stats is actually protected by client_obd's lock. */
struct osc_stats {
+ ktime_t os_init;
uint64_t os_lockless_writes; /* by bytes */
uint64_t os_lockless_reads; /* by bytes */
- uint64_t os_lockless_truncates; /* by times */
} od_stats;
/* configuration item(s) */
time64_t od_contention_time;
- int od_lockless_truncate;
};
struct osc_extent;
/** true if this io is counted as active IO */
oi_is_active:1,
/** true if this io has CAP_SYS_RESOURCE */
- oi_cap_sys_resource:1;
+ oi_cap_sys_resource:1,
+ /** true if this io issued by readahead */
+ oi_is_readahead:1;
/** how many LRU pages are reserved for this IO */
unsigned long oi_lru_reserved;
*/
pgoff_t oti_next_index;
pgoff_t oti_fn_index; /* first non-overlapped index */
+ pgoff_t oti_ng_index; /* negative lock caching */
struct cl_sync_io oti_anchor;
struct cl_req_attr oti_req_attr;
struct lu_buf oti_ladvise_buf;
if (enqflags & CEF_NONBLOCK)
result |= LDLM_FL_BLOCK_NOWAIT;
if (enqflags & CEF_GLIMPSE)
- result |= LDLM_FL_HAS_INTENT;
+ result |= LDLM_FL_HAS_INTENT|LDLM_FL_CBPENDING;
if (enqflags & CEF_DISCARD_DATA)
result |= LDLM_FL_AST_DISCARD_DATA;
if (enqflags & CEF_PEEK)
* Just check if the desired lock exists, it won't hold reference
* count on lock.
*/
- OSC_DAP_FL_TEST_LOCK = 1 << 0,
+ OSC_DAP_FL_TEST_LOCK = BIT(0),
/**
* Return the lock even if it is being canceled.
*/
- OSC_DAP_FL_CANCELING = 1 << 1
+ OSC_DAP_FL_CANCELING = BIT(1),
+ /**
+ * check ast data is present, requested to cancel cb
+ */
+ OSC_DAP_FL_AST = BIT(2),
+ /**
+ * look at right region for the desired lock
+ */
+ OSC_DAP_FL_RIGHT = BIT(3),
};
/*
* An offset within page from which next transfer starts. This is used
* by cl_page_clip() to submit partial page transfers.
*/
- int ops_from;
+ unsigned int ops_from:PAGE_SHIFT,
/**
- * An offset within page at which next transfer ends.
+ * An offset within page at which next transfer ends(inclusive).
*
* \see osc_page::ops_from.
*/
- int ops_to;
+ ops_to:PAGE_SHIFT,
/**
* Boolean, true iff page is under transfer. Used for sanity checking.
*/
- unsigned ops_transfer_pinned:1,
+ ops_transfer_pinned:1,
/**
* in LRU?
*/
int aa_requested_nob;
int aa_nio_count;
u32 aa_page_count;
- int aa_resends;
+ s32 aa_resends;
struct brw_page **aa_ppga;
struct client_obd *aa_cli;
struct list_head aa_oaps;
pgoff_t start, pgoff_t end);
void osc_lru_add_batch(struct client_obd *cli, struct list_head *list);
void osc_page_submit(const struct lu_env *env, struct osc_page *opg,
- enum cl_req_type crt, int brw_flags);
+ enum cl_req_type crt, int brw_flags, ktime_t submit_time);
int lru_queue_work(const struct lu_env *env, void *data);
long osc_lru_shrink(const struct lu_env *env, struct client_obd *cli,
long target, bool force);
int osc_set_async_flags(struct osc_object *obj, struct osc_page *opg,
u32 async_flags);
int osc_prep_async_page(struct osc_object *osc, struct osc_page *ops,
- struct page *page, loff_t offset);
+ struct cl_page *page, loff_t offset);
int osc_queue_async_io(const struct lu_env *env, struct cl_io *io,
struct osc_page *ops, cl_commit_cbt cb);
int osc_page_cache_add(const struct lu_env *env, struct osc_page *opg,
struct osc_page *ops);
int osc_flush_async_page(const struct lu_env *env, struct cl_io *io,
struct osc_page *ops);
-int osc_queue_sync_pages(const struct lu_env *env, const struct cl_io *io,
+int osc_queue_sync_pages(const struct lu_env *env, struct cl_io *io,
struct osc_object *obj, struct list_head *list,
int brw_flags);
int osc_cache_truncate_start(const struct lu_env *env, struct osc_object *obj,
pgoff_t start, pgoff_t end);
int osc_io_unplug0(const struct lu_env *env, struct client_obd *cli,
struct osc_object *osc, int async);
-void osc_wake_cache_waiters(struct client_obd *cli);
+static inline void osc_wake_cache_waiters(struct client_obd *cli)
+{
+ wake_up(&cli->cl_cache_waiters);
+}
static inline int osc_io_unplug_async(const struct lu_env *env,
struct client_obd *cli,
}
typedef bool (*osc_page_gang_cbt)(const struct lu_env *, struct cl_io *,
- struct osc_page *, void *);
+ void**, int, void *);
bool osc_page_gang_lookup(const struct lu_env *env, struct cl_io *io,
struct osc_object *osc, pgoff_t start, pgoff_t end,
osc_page_gang_cbt cb, void *cbdata);
bool osc_discard_cb(const struct lu_env *env, struct cl_io *io,
- struct osc_page *ops, void *cbdata);
+ void**, int, void *cbdata);
/* osc_dev.c */
int osc_device_init(const struct lu_env *env, struct lu_device *d,
int osc_object_glimpse(const struct lu_env *env, const struct cl_object *obj,
struct ost_lvb *lvb);
int osc_object_invalidate(const struct lu_env *env, struct osc_object *osc);
-int osc_object_is_contended(struct osc_object *obj);
int osc_object_find_cbdata(const struct lu_env *env, struct cl_object *obj,
ldlm_iterator_t iter, void *data);
int osc_object_prune(const struct lu_env *env, struct cl_object *obj);
int osc_disconnect(struct obd_export *exp);
int osc_punch_send(struct obd_export *exp, struct obdo *oa,
obd_enqueue_update_f upcall, void *cookie);
+int osc_fallocate_base(struct obd_export *exp, struct obdo *oa,
+ obd_enqueue_update_f upcall, void *cookie, int mode);
+void osc_update_next_shrink(struct client_obd *cli);
+void osc_schedule_grant_work(void);
/* osc_io.c */
int osc_io_submit(const struct lu_env *env, const struct cl_io_slice *ios,
const struct cl_io_slice *ios,
struct cl_page_list *qin, int from, int to,
cl_commit_cbt cb);
+void osc_io_extent_release(const struct lu_env *env,
+ const struct cl_io_slice *ios);
int osc_io_iter_init(const struct lu_env *env, const struct cl_io_slice *ios);
void osc_io_iter_fini(const struct lu_env *env,
const struct cl_io_slice *ios);
-int osc_io_rw_iter_init(const struct lu_env *env,
- const struct cl_io_slice *ios);
void osc_io_rw_iter_fini(const struct lu_env *env,
const struct cl_io_slice *ios);
int osc_io_fault_start(const struct lu_env *env, const struct cl_io_slice *ios);
struct cl_fsync_io *fio);
void osc_io_fsync_end(const struct lu_env *env,
const struct cl_io_slice *slice);
-void osc_read_ahead_release(const struct lu_env *env, void *cbdata);
+void osc_read_ahead_release(const struct lu_env *env, struct cl_read_ahead *ra);
+int osc_io_lseek_start(const struct lu_env *env,
+ const struct cl_io_slice *slice);
+void osc_io_lseek_end(const struct lu_env *env,
+ const struct cl_io_slice *slice);
+int osc_io_lru_reserve(const struct lu_env *env, const struct cl_io_slice *ios,
+ loff_t pos, size_t count);
+int osc_punch_start(const struct lu_env *env, struct cl_io *io,
+ struct cl_object *obj);
/* osc_lock.c */
void osc_lock_to_lockless(const struct lu_env *env, struct osc_lock *ols,
static inline struct osc_device *lu2osc_dev(const struct lu_device *d)
{
- return container_of0(d, struct osc_device, od_cl.cd_lu_dev);
+ return container_of_safe(d, struct osc_device, od_cl.cd_lu_dev);
}
static inline struct obd_export *osc_export(const struct osc_object *obj)
static inline struct osc_object *cl2osc(const struct cl_object *obj)
{
- return container_of0(obj, struct osc_object, oo_cl);
+ return container_of_safe(obj, struct osc_object, oo_cl);
}
static inline struct cl_object *osc2cl(const struct osc_object *obj)
return (struct cl_object *)&obj->oo_cl;
}
-static inline struct osc_device *obd2osc_dev(const struct obd_device *d)
+static inline struct osc_device *obd2osc_dev(const struct obd_device *obd)
{
- return container_of0(d->obd_lu_dev, struct osc_device,
- od_cl.cd_lu_dev);
+ return container_of_safe(obd->obd_lu_dev, struct osc_device,
+ od_cl.cd_lu_dev);
}
static inline struct lu_device *osc2lu_dev(struct osc_device *osc)
static inline struct osc_object *lu2osc(const struct lu_object *obj)
{
- return container_of0(obj, struct osc_object, oo_cl.co_lu);
+ return container_of_safe(obj, struct osc_object, oo_cl.co_lu);
}
static inline struct osc_io *cl2osc_io(const struct lu_env *env,
const struct cl_io_slice *slice)
{
- struct osc_io *oio = container_of0(slice, struct osc_io, oi_cl);
+ struct osc_io *oio = container_of(slice, struct osc_io, oi_cl);
LINVRNT(oio == osc_env_io(env));
return oio;
static inline struct osc_page *cl2osc_page(const struct cl_page_slice *slice)
{
- return container_of0(slice, struct osc_page, ops_cl);
+ return container_of_safe(slice, struct osc_page, ops_cl);
}
static inline struct osc_page *oap2osc(struct osc_async_page *oap)
{
- return container_of0(oap, struct osc_page, ops_oap);
+ return container_of_safe(oap, struct osc_page, ops_oap);
}
static inline pgoff_t osc_index(struct osc_page *opg)
{
- return opg->ops_cl.cpl_index;
+ return opg->ops_cl.cpl_page->cp_osc_index;
}
static inline struct cl_page *oap2cl_page(struct osc_async_page *oap)
static inline struct osc_lock *cl2osc_lock(const struct cl_lock_slice *slice)
{
- return container_of0(slice, struct osc_lock, ols_cl);
+ return container_of_safe(slice, struct osc_lock, ols_cl);
}
static inline int osc_io_srvlock(struct osc_io *oio)
/** osc_object of this extent */
struct osc_object *oe_obj;
/** refcount, removed from red-black tree if reaches zero. */
- atomic_t oe_refc;
+ struct kref oe_refc;
/** busy if non-zero */
atomic_t oe_users;
/** link list of osc_object's oo_{hp|urgent|locking}_exts. */
/** state of this extent */
enum osc_extent_state oe_state;
/** flags for this extent. */
- unsigned int oe_intree:1,
/** 0 is write, 1 is read */
- oe_rw:1,
+ unsigned int oe_rw:1,
/** sync extent, queued by osc_queue_sync_pages() */
oe_sync:1,
/** set if this extent has partial, sync pages.
/** Non-delay RPC should be used for this extent. */
oe_ndelay:1,
/** direct IO pages */
- oe_dio:1;
+ oe_dio:1,
+ /** this extent consists of pages that are not directly accessible
+ * from the CPU */
+ oe_is_rdma_only:1;
/** how many grants allocated for this extent.
* Grant allocated for this extent. There is no grant allocated
* for reading extents and sync write extents. */
git://git.whamcloud.com / fs / lustre-release.git / blobdiff