Lustre fixes

index 36ca935..3cd4a25 100644
@@ -2322,7 +2322,8 @@ void cl_lock_descr_print(const struct lu_env *env, void *cookie,
  */
 struct cl_client_cache {
 	/**
-	 * # of users (OSCs)
+	 * # of client cache refcount
+	 * # of users (OSCs) + 2 (held by llite and lov)
 	 */
 	atomic_t		ccc_users;
 	/**

@@ -2357,6 +2358,13 @@ struct cl_client_cache {
 
 };
 
+/**
+ * cl_cache functions
+ */
+struct cl_client_cache *cl_cache_init(unsigned long lru_page_max);
+void cl_cache_incref(struct cl_client_cache *cache);
+void cl_cache_decref(struct cl_client_cache *cache);
+
 /** @} cl_page */
 
 /** \defgroup cl_lock cl_lock

index e654d42..ed1081a 100644
@@ -415,7 +415,7 @@ struct lov_obd {
 	enum lustre_sec_part    lov_sp_me;
 
 	/* Cached LRU and unstable data from upper layer */
-	void		       *lov_cache;
+	struct cl_client_cache *lov_cache;
 
 	struct rw_semaphore     lov_notify_lock;
 

index 7c1a3254..74cd241 100644
@@ -493,7 +493,7 @@ struct ll_sb_info {
 	 * any page which is sent to a server as part of a bulk request,
 	 * but is uncommitted to stable storage.
 	 */
-	struct cl_client_cache    ll_cache;
+	struct cl_client_cache    *ll_cache;
 
 	struct lprocfs_stats     *ll_ra_stats;
 

index ac833db..83f4e1a 100644
@@ -83,15 +83,11 @@ static struct ll_sb_info *ll_init_sbi(struct super_block *sb)
 	pages = si.totalram - si.totalhigh;
 	lru_page_max = pages / 2;
 
-	/* initialize ll_cache data */
-	atomic_set(&sbi->ll_cache.ccc_users, 0);
-	sbi->ll_cache.ccc_lru_max = lru_page_max;
-	atomic_set(&sbi->ll_cache.ccc_lru_left, lru_page_max);
-	spin_lock_init(&sbi->ll_cache.ccc_lru_lock);
-	INIT_LIST_HEAD(&sbi->ll_cache.ccc_lru);
-
-	atomic_set(&sbi->ll_cache.ccc_unstable_nr, 0);
-	init_waitqueue_head(&sbi->ll_cache.ccc_unstable_waitq);
+	sbi->ll_cache = cl_cache_init(lru_page_max);
+	if (!sbi->ll_cache) {
+		kfree(sbi);
+		return NULL;
+	}
 
 	sbi->ll_ra_info.ra_max_pages_per_file = min(pages / 32,
 					   SBI_DEFAULT_READAHEAD_MAX);

@@ -131,6 +127,11 @@ static void ll_free_sbi(struct super_block *sb)
 {
 	struct ll_sb_info *sbi = ll_s2sbi(sb);
 
+	if (sbi->ll_cache) {
+		cl_cache_decref(sbi->ll_cache);
+		sbi->ll_cache = NULL;
+	}
+
 	kfree(sbi);
 }
 

@@ -514,8 +515,8 @@ static int client_common_fill_super(struct super_block *sb, char *md, char *dt,
 	cl_sb_init(sb);
 
 	err = obd_set_info_async(NULL, sbi->ll_dt_exp, sizeof(KEY_CACHE_SET),
-				 KEY_CACHE_SET, sizeof(sbi->ll_cache),
-				 &sbi->ll_cache, NULL);
+				 KEY_CACHE_SET, sizeof(*sbi->ll_cache),
+				 sbi->ll_cache, NULL);
 
 	sb->s_root = d_make_root(root);
 	if (!sb->s_root) {

@@ -560,8 +561,6 @@ out_lock_cn_cb:
 out_dt:
 	obd_disconnect(sbi->ll_dt_exp);
 	sbi->ll_dt_exp = NULL;
-	/* Make sure all OScs are gone, since cl_cache is accessing sbi. */
-	obd_zombie_barrier();
 out_md_fid:
 	obd_fid_fini(sbi->ll_md_exp->exp_obd);
 out_md:

@@ -618,10 +617,6 @@ static void client_common_put_super(struct super_block *sb)
 	obd_fid_fini(sbi->ll_dt_exp->exp_obd);
 	obd_disconnect(sbi->ll_dt_exp);
 	sbi->ll_dt_exp = NULL;
-	/* wait till all OSCs are gone, since cl_cache is accessing sbi.
-	 * see LU-2543.
-	 */
-	obd_zombie_barrier();
 
 	ldebugfs_unregister_mountpoint(sbi);
 

@@ -962,12 +957,12 @@ void ll_put_super(struct super_block *sb)
 	if (!force) {
 		struct l_wait_info lwi = LWI_INTR(LWI_ON_SIGNAL_NOOP, NULL);
 
-		rc = l_wait_event(sbi->ll_cache.ccc_unstable_waitq,
-				  !atomic_read(&sbi->ll_cache.ccc_unstable_nr),
+		rc = l_wait_event(sbi->ll_cache->ccc_unstable_waitq,
+				  !atomic_read(&sbi->ll_cache->ccc_unstable_nr),
 				  &lwi);
 	}
 
-	ccc_count = atomic_read(&sbi->ll_cache.ccc_unstable_nr);
+	ccc_count = atomic_read(&sbi->ll_cache->ccc_unstable_nr);
 	if (!force && rc != -EINTR)
 		LASSERTF(!ccc_count, "count: %i\n", ccc_count);
 

index 6e9a8a5..1f00bce 100644
@@ -360,7 +360,7 @@ static int ll_max_cached_mb_seq_show(struct seq_file *m, void *v)
 {
 	struct super_block     *sb    = m->private;
 	struct ll_sb_info      *sbi   = ll_s2sbi(sb);
-	struct cl_client_cache *cache = &sbi->ll_cache;
+	struct cl_client_cache *cache = sbi->ll_cache;
 	int shift = 20 - PAGE_SHIFT;
 	int max_cached_mb;
 	int unused_mb;

@@ -387,7 +387,7 @@ static ssize_t ll_max_cached_mb_seq_write(struct file *file,
 {
 	struct super_block *sb = ((struct seq_file *)file->private_data)->private;
 	struct ll_sb_info *sbi = ll_s2sbi(sb);
-	struct cl_client_cache *cache = &sbi->ll_cache;
+	struct cl_client_cache *cache = sbi->ll_cache;
 	struct lu_env *env;
 	int refcheck;
 	int mult, rc, pages_number;

@@ -826,7 +826,7 @@ static ssize_t unstable_stats_show(struct kobject *kobj,
 {
 	struct ll_sb_info *sbi = container_of(kobj, struct ll_sb_info,
 					      ll_kobj);
-	struct cl_client_cache *cache = &sbi->ll_cache;
+	struct cl_client_cache *cache = sbi->ll_cache;
 	int pages, mb;
 
 	pages = atomic_read(&cache->ccc_unstable_nr);

index c87096e..9b92d55 100644
@@ -892,6 +892,12 @@ static int lov_cleanup(struct obd_device *obd)
 		kfree(lov->lov_tgts);
 		lov->lov_tgt_size = 0;
 	}
+
+	if (lov->lov_cache) {
+		cl_cache_decref(lov->lov_cache);
+		lov->lov_cache = NULL;
+	}
+
 	return 0;
 }
 

@@ -2121,6 +2127,7 @@ static int lov_set_info_async(const struct lu_env *env, struct obd_export *exp,
 		LASSERT(!lov->lov_cache);
 		lov->lov_cache = val;
 		do_inactive = 1;
+		cl_cache_incref(lov->lov_cache);
 	}
 
 	for (i = 0; i < count; i++, val = (char *)val + incr) {

49 lines not on this page · raw message

index 57d8a5a..c1aa11e 100644
@@ -414,7 +414,7 @@ static int osc_cache_too_much(struct client_obd *cli)
 	int pages = atomic_read(&cli->cl_lru_in_list);
 	unsigned long budget;
 
-	budget = cache->ccc_lru_max / atomic_read(&cache->ccc_users);
+	budget = cache->ccc_lru_max / (atomic_read(&cache->ccc_users) - 2);
 
 	/* if it's going to run out LRU slots, we should free some, but not
 	 * too much to maintain fairness among OSCs.

@@ -714,7 +714,7 @@ int osc_lru_reclaim(struct client_obd *cli)
 	cache->ccc_lru_shrinkers++;
 	list_move_tail(&cli->cl_lru_osc, &cache->ccc_lru);
 
-	max_scans = atomic_read(&cache->ccc_users);
+	max_scans = atomic_read(&cache->ccc_users) - 2;
 	while (--max_scans > 0 && !list_empty(&cache->ccc_lru)) {
 		cli = list_entry(cache->ccc_lru.next, struct client_obd,
 				 cl_lru_osc);

index 7260027..9334349 100644
@@ -2913,7 +2913,7 @@ static int osc_set_info_async(const struct lu_env *env, struct obd_export *exp,
 
 		LASSERT(!cli->cl_cache); /* only once */
 		cli->cl_cache = val;
-		atomic_inc(&cli->cl_cache->ccc_users);
+		cl_cache_incref(cli->cl_cache);
 		cli->cl_lru_left = &cli->cl_cache->ccc_lru_left;
 
 		/* add this osc into entity list */

@@ -3293,7 +3293,7 @@ static int osc_cleanup(struct obd_device *obd)
 		list_del_init(&cli->cl_lru_osc);
 		spin_unlock(&cli->cl_cache->ccc_lru_lock);
 		cli->cl_lru_left = NULL;
-		atomic_dec(&cli->cl_cache->ccc_users);
+		cl_cache_decref(cli->cl_cache);
 		cli->cl_cache = NULL;
 	}
 

index d7459bd..6414d52 100644
@@ -622,13 +622,10 @@ static int ll_atomic_open(struct inode *dir, struct dentry *dentry,
 		if (d_really_is_positive(dentry) && it_disposition(it, DISP_OPEN_OPEN)) {
 			/* Open dentry. */
 			if (S_ISFIFO(d_inode(dentry)->i_mode)) {
-				/* We cannot call open here as it would
-				 * deadlock.
+				/* We cannot call open here as it might
+				 * deadlock. This case is unreachable in
+				 * practice because of OBD_CONNECT_NODEVOH.
 				 */
-				if (it_disposition(it, DISP_ENQ_OPEN_REF))
-					ptlrpc_req_finished(
-						       (struct ptlrpc_request *)
-							  it->d.lustre.it_data);
 				rc = finish_no_open(file, de);
 			} else {
 				file->private_data = it;

index 9d13d5e..f002b3a 100644
@@ -249,7 +249,7 @@ void ll_invalidate_aliases(struct inode *inode)
 	CDEBUG(D_INODE, "marking dentries for ino "DFID"(%p) invalid\n",
 	       PFID(ll_inode2fid(inode)), inode);
 
-	ll_lock_dcache(inode);
+	spin_lock(&inode->i_lock);
 	hlist_for_each_entry(dentry, &inode->i_dentry, d_u.d_alias) {
 		CDEBUG(D_DENTRY, "dentry in drop %pd (%p) parent %p inode %p flags %d\n",
 		       dentry, dentry, dentry->d_parent,

@@ -257,7 +257,7 @@ void ll_invalidate_aliases(struct inode *inode)
 
 		d_lustre_invalidate(dentry, 0);
 	}
-	ll_unlock_dcache(inode);
+	spin_unlock(&inode->i_lock);
 }
 
 int ll_revalidate_it_finish(struct ptlrpc_request *request,

index 74cd241..098155f 100644
@@ -1313,16 +1313,6 @@ static inline void ll_set_lock_data(struct obd_export *exp, struct inode *inode,
 		*bits = it->d.lustre.it_lock_bits;
 }
 
-static inline void ll_lock_dcache(struct inode *inode)
-{
-	spin_lock(&inode->i_lock);
-}
-
-static inline void ll_unlock_dcache(struct inode *inode)
-{
-	spin_unlock(&inode->i_lock);
-}
-
 static inline int d_lustre_invalid(const struct dentry *dentry)
 {
 	struct ll_dentry_data *lld = ll_d2d(dentry);

index 6414d52..e4df510 100644
@@ -140,7 +140,7 @@ static void ll_invalidate_negative_children(struct inode *dir)
 {
 	struct dentry *dentry, *tmp_subdir;
 
-	ll_lock_dcache(dir);
+	spin_lock(&dir->i_lock);
 	hlist_for_each_entry(dentry, &dir->i_dentry, d_u.d_alias) {
 		spin_lock(&dentry->d_lock);
 		if (!list_empty(&dentry->d_subdirs)) {

@@ -155,7 +155,7 @@ static void ll_invalidate_negative_children(struct inode *dir)
 		}
 		spin_unlock(&dentry->d_lock);
 	}
-	ll_unlock_dcache(dir);
+	spin_unlock(&dir->i_lock);
 }
 
 int ll_md_blocking_ast(struct ldlm_lock *lock, struct ldlm_lock_desc *desc,

@@ -317,7 +317,7 @@ static struct dentry *ll_find_alias(struct inode *inode, struct dentry *dentry)
 	discon_alias = NULL;
 	invalid_alias = NULL;
 
-	ll_lock_dcache(inode);
+	spin_lock(&inode->i_lock);
 	hlist_for_each_entry(alias, &inode->i_dentry, d_u.d_alias) {
 		LASSERT(alias != dentry);
 

@@ -342,7 +342,7 @@ static struct dentry *ll_find_alias(struct inode *inode, struct dentry *dentry)
 		dget_dlock(alias);
 		spin_unlock(&alias->d_lock);
 	}
-	ll_unlock_dcache(inode);
+	spin_unlock(&inode->i_lock);
 
 	return alias;
 }

index b0c4548..5436a54 100644
@@ -2975,8 +2975,11 @@ static int __ll_inode_revalidate(struct dentry *dentry, __u64 ibits)
 		 * here to preserve get_cwd functionality on 2.6.
 		 * Bug 10503
 		 */
-		if (!d_inode(dentry)->i_nlink)
+		if (!d_inode(dentry)->i_nlink) {
+			spin_lock(&inode->i_lock);
 			d_lustre_invalidate(dentry, 0);
+			spin_unlock(&inode->i_lock);
+		}
 
 		ll_lookup_finish_locks(&oit, inode);
 	} else if (!ll_have_md_lock(d_inode(dentry), &ibits, LCK_MINMODE)) {

index 42def38..d856775 100644
@@ -634,11 +634,10 @@ static int weigh_cb(const struct lu_env *env, struct cl_io *io,
 
 	if (cl_page_is_vmlocked(env, page) ||
 	    PageDirty(page->cp_vmpage) || PageWriteback(page->cp_vmpage)
-	   ) {
-		(*(unsigned long *)cbdata)++;
+	   )
 		return CLP_GANG_ABORT;
-	}
 
+	*(pgoff_t *)cbdata = osc_index(ops) + 1;
 	return CLP_GANG_OKAY;
 }
 

@@ -648,7 +647,7 @@ static unsigned long osc_lock_weight(const struct lu_env *env,
 {
 	struct cl_io *io = &osc_env_info(env)->oti_io;
 	struct cl_object *obj = cl_object_top(&oscobj->oo_cl);
-	unsigned long npages = 0;
+	pgoff_t page_index;
 	int result;
 
 	io->ci_obj = obj;

@@ -657,11 +656,12 @@ static unsigned long osc_lock_weight(const struct lu_env *env,
 	if (result != 0)
 		return result;
 
+	page_index = cl_index(obj, extent->start);
 	do {
 		result = osc_page_gang_lookup(env, io, oscobj,
-					      cl_index(obj, extent->start),
+					      page_index,
 					      cl_index(obj, extent->end),
-					      weigh_cb, (void *)&npages);
+					      weigh_cb, (void *)&page_index);
 		if (result == CLP_GANG_ABORT)
 			break;
 		if (result == CLP_GANG_RESCHED)

@@ -669,7 +669,7 @@ static unsigned long osc_lock_weight(const struct lu_env *env,
 	} while (result != CLP_GANG_OKAY);
 	cl_io_fini(env, io);
 
-	return npages;
+	return result == CLP_GANG_ABORT ? 1 : 0;
 }
 
 /**

index d856775..5455d9d 100644
@@ -699,7 +699,7 @@ unsigned long osc_ldlm_weigh_ast(struct ldlm_lock *dlmlock)
 
 	LASSERT(dlmlock->l_resource->lr_type == LDLM_EXTENT);
 	obj = dlmlock->l_ast_data;
-	if (obj) {
+	if (!obj) {
 		weight = 1;
 		goto out;
 	}

index dba4d1d..5968c3c 100644
@@ -266,6 +266,11 @@
 /* Macro to hide a typecast. */
 #define ptlrpc_req_async_args(req) ((void *)&req->rq_async_args)
 
+struct ptlrpc_replay_async_args {
+	int		praa_old_state;
+	int		praa_old_status;
+};
+
 /**
  * Structure to single define portal connection.
  */

@@ -1243,22 +1248,100 @@ struct ptlrpc_hpreq_ops {
 	void (*hpreq_fini)(struct ptlrpc_request *);
 };
 
-/**
- * Represents remote procedure call.
- *
- * This is a staple structure used by everybody wanting to send a request
- * in Lustre.
- */
-struct ptlrpc_request {
-	/* Request type: one of PTL_RPC_MSG_* */
-	int rq_type;
-	/** Result of request processing */
-	int rq_status;
+struct ptlrpc_cli_req {
+	/** For bulk requests on client only: bulk descriptor */
+	struct ptlrpc_bulk_desc		*cr_bulk;
+	/** optional time limit for send attempts */
+	long				 cr_delay_limit;
+	/** time request was first queued */
+	time_t				 cr_queued_time;
+	/** request sent timeval */
+	struct timespec64		 cr_sent_tv;
+	/** time for request really sent out */
+	time_t				 cr_sent_out;
+	/** when req reply unlink must finish. */
+	time_t				 cr_reply_deadline;
+	/** when req bulk unlink must finish. */
+	time_t				 cr_bulk_deadline;
+	/** Portal to which this request would be sent */
+	short				 cr_req_ptl;
+	/** Portal where to wait for reply and where reply would be sent */
+	short				 cr_rep_ptl;
+	/** request resending number */
+	unsigned int			 cr_resend_nr;
+	/** What was import generation when this request was sent */
+	int				 cr_imp_gen;
+	enum lustre_imp_state		 cr_send_state;
+	/** Per-request waitq introduced by bug 21938 for recovery waiting */
+	wait_queue_head_t		 cr_set_waitq;
+	/** Link item for request set lists */
+	struct list_head		 cr_set_chain;
+	/** link to waited ctx */
+	struct list_head		 cr_ctx_chain;
+
+	/** client's half ctx */
+	struct ptlrpc_cli_ctx		*cr_cli_ctx;
+	/** Link back to the request set */
+	struct ptlrpc_request_set	*cr_set;
+	/** outgoing request MD handle */
+	lnet_handle_md_t		 cr_req_md_h;
+	/** request-out callback parameter */
+	struct ptlrpc_cb_id		 cr_req_cbid;
+	/** incoming reply MD handle */
+	lnet_handle_md_t		 cr_reply_md_h;
+	wait_queue_head_t		 cr_reply_waitq;
+	/** reply callback parameter */
+	struct ptlrpc_cb_id		 cr_reply_cbid;
+	/** Async completion handler, called when reply is received */
+	ptlrpc_interpterer_t		 cr_reply_interp;
+	/** Async completion context */
+	union ptlrpc_async_args		 cr_async_args;
+	/** Opaq data for replay and commit callbacks. */
+	void				*cr_cb_data;
 	/**
-	 * Linkage item through which this request is included into
-	 * sending/delayed lists on client and into rqbd list on server
+	 * Commit callback, called when request is committed and about to be
+	 * freed.
 	 */
-	struct list_head rq_list;
+	void (*cr_commit_cb)(struct ptlrpc_request *);
+	/** Replay callback, called after request is replayed at recovery */
+	void (*cr_replay_cb)(struct ptlrpc_request *);
+};
+
+/** client request member alias */
+/* NB: these alias should NOT be used by any new code, instead they should
+ * be removed step by step to avoid potential abuse
+ */
+#define rq_bulk			rq_cli.cr_bulk
+#define rq_delay_limit		rq_cli.cr_delay_limit
+#define rq_queued_time		rq_cli.cr_queued_time
+#define rq_sent_tv		rq_cli.cr_sent_tv
+#define rq_real_sent		rq_cli.cr_sent_out
+#define rq_reply_deadline	rq_cli.cr_reply_deadline
+#define rq_bulk_deadline	rq_cli.cr_bulk_deadline
+#define rq_nr_resend		rq_cli.cr_resend_nr
+#define rq_request_portal	rq_cli.cr_req_ptl
+#define rq_reply_portal		rq_cli.cr_rep_ptl
+#define rq_import_generation	rq_cli.cr_imp_gen
+#define rq_send_state		rq_cli.cr_send_state
+#define rq_set_chain		rq_cli.cr_set_chain
+#define rq_ctx_chain		rq_cli.cr_ctx_chain
+#define rq_set			rq_cli.cr_set
+#define rq_set_waitq		rq_cli.cr_set_waitq
+#define rq_cli_ctx		rq_cli.cr_cli_ctx
+#define rq_req_md_h		rq_cli.cr_req_md_h
+#define rq_req_cbid		rq_cli.cr_req_cbid
+#define rq_reply_md_h		rq_cli.cr_reply_md_h
+#define rq_reply_waitq		rq_cli.cr_reply_waitq
+#define rq_reply_cbid		rq_cli.cr_reply_cbid
+#define rq_interpret_reply	rq_cli.cr_reply_interp
+#define rq_async_args		rq_cli.cr_async_args
+#define rq_cb_data		rq_cli.cr_cb_data
+#define rq_commit_cb		rq_cli.cr_commit_cb
+#define rq_replay_cb		rq_cli.cr_replay_cb
+
+struct ptlrpc_srv_req {
+	/** initial thread servicing this request */
+	struct ptlrpc_thread		*sr_svc_thread;
 	/**
 	 * Server side list of incoming unserved requests sorted by arrival
 	 * time.  Traversed from time to time to notice about to expire

@@ -1266,27 +1349,81 @@ struct ptlrpc_request {
 	 * know server is alive and well, just very busy to service their
 	 * requests in time
 	 */
-	struct list_head rq_timed_list;
-	/** server-side history, used for debugging purposes. */
-	struct list_head rq_history_list;
+	struct list_head		sr_timed_list;
 	/** server-side per-export list */
-	struct list_head rq_exp_list;
-	/** server-side hp handlers */
-	struct ptlrpc_hpreq_ops *rq_ops;
-
-	/** initial thread servicing this request */
-	struct ptlrpc_thread *rq_svc_thread;
-
+	struct list_head		sr_exp_list;
+	/** server-side history, used for debuging purposes. */
+	struct list_head		sr_hist_list;
 	/** history sequence # */
-	__u64 rq_history_seq;
+	__u64				sr_hist_seq;
+	/** the index of service's srv_at_array into which request is linked */
+	time_t				sr_at_index;
+	/** authed uid */
+	uid_t				sr_auth_uid;
+	/** authed uid mapped to */
+	uid_t				sr_auth_mapped_uid;
+	/** RPC is generated from what part of Lustre */
+	enum lustre_sec_part		sr_sp_from;
+	/** request session context */
+	struct lu_context		sr_ses;
 	/** \addtogroup  nrs
 	 * @{
 	 */
 	/** stub for NRS request */
-	struct ptlrpc_nrs_request rq_nrq;
+	struct ptlrpc_nrs_request	sr_nrq;
 	/** @} nrs */
-	/** the index of service's srv_at_array into which request is linked */
-	u32 rq_at_index;
+	/** request arrival time */
+	struct timespec64		sr_arrival_time;
+	/** server's half ctx */
+	struct ptlrpc_svc_ctx		*sr_svc_ctx;
+	/** (server side), pointed directly into req buffer */
+	struct ptlrpc_user_desc		*sr_user_desc;
+	/** separated reply state */
+	struct ptlrpc_reply_state	*sr_reply_state;
+	/** server-side hp handlers */
+	struct ptlrpc_hpreq_ops		*sr_ops;
+	/** incoming request buffer */
+	struct ptlrpc_request_buffer_desc *sr_rqbd;
+};
+
+/** server request member alias */
+/* NB: these alias should NOT be used by any new code, instead they should
+ * be removed step by step to avoid potential abuse
+ */
+#define rq_svc_thread		rq_srv.sr_svc_thread
+#define rq_timed_list		rq_srv.sr_timed_list
+#define rq_exp_list		rq_srv.sr_exp_list
+#define rq_history_list		rq_srv.sr_hist_list
+#define rq_history_seq		rq_srv.sr_hist_seq
+#define rq_at_index		rq_srv.sr_at_index
+#define rq_auth_uid		rq_srv.sr_auth_uid
+#define rq_auth_mapped_uid	rq_srv.sr_auth_mapped_uid
+#define rq_sp_from		rq_srv.sr_sp_from
+#define rq_session		rq_srv.sr_ses
+#define rq_nrq			rq_srv.sr_nrq
+#define rq_arrival_time		rq_srv.sr_arrival_time
+#define rq_reply_state		rq_srv.sr_reply_state
+#define rq_svc_ctx		rq_srv.sr_svc_ctx
+#define rq_user_desc		rq_srv.sr_user_desc
+#define rq_ops			rq_srv.sr_ops
+#define rq_rqbd			rq_srv.sr_rqbd
+
+/**
+ * Represents remote procedure call.
+ *
+ * This is a staple structure used by everybody wanting to send a request
+ * in Lustre.
+ */
+struct ptlrpc_request {
+	/* Request type: one of PTL_RPC_MSG_* */
+	int				 rq_type;
+	/** Result of request processing */
+	int				 rq_status;
+	/**
+	 * Linkage item through which this request is included into
+	 * sending/delayed lists on client and into rqbd list on server
+	 */
+	struct list_head		 rq_list;
 	/** Lock to protect request flags and some other important bits, like
 	 * rq_list
 	 */

@@ -1327,19 +1464,15 @@ struct ptlrpc_request {
 		/* bulk request, sent to server, but uncommitted */
 		rq_unstable:1;
 
-	unsigned int rq_nr_resend;
-
-	enum rq_phase rq_phase; /* one of RQ_PHASE_* */
-	enum rq_phase rq_next_phase; /* one of RQ_PHASE_* to be used next */
-	atomic_t rq_refcount; /* client-side refcount for SENT race,
-			       * server-side refcount for multiple replies
-			       */
-
-	/** Portal to which this request would be sent */
-	short rq_request_portal;  /* XXX FIXME bug 249 */
-	/** Portal where to wait for reply and where reply would be sent */
-	short rq_reply_portal;    /* XXX FIXME bug 249 */
-
+	/** one of RQ_PHASE_* */
+	enum rq_phase			rq_phase;
+	/** one of RQ_PHASE_* to be used next */
+	enum rq_phase			rq_next_phase;
+	/**
+	 * client-side refcount for SENT race, server-side refcount
+	 * for multiple replies
+	 */
+	atomic_t			rq_refcount;
 	/**
 	 * client-side:
 	 * !rq_truncate : # reply bytes actually received,

@@ -1350,6 +1483,8 @@ struct ptlrpc_request {
 	int rq_reqlen;
 	/** Reply length */
 	int rq_replen;
+	/** Pool if request is from preallocated list */
+	struct ptlrpc_request_pool     *rq_pool;
 	/** Request message - what client sent */
 	struct lustre_msg *rq_reqmsg;
 	/** Reply message - server response */

@@ -1362,19 +1497,20 @@ struct ptlrpc_request {
 	 * List item to for replay list. Not yet committed requests get linked
 	 * there.
 	 * Also see \a rq_replay comment above.
+	 * It's also link chain on obd_export::exp_req_replay_queue
 	 */
 	struct list_head rq_replay_list;
-
+	/** non-shared members for client & server request*/
+	union {
+		struct ptlrpc_cli_req    rq_cli;
+		struct ptlrpc_srv_req    rq_srv;
+	};
 	/**
 	 * security and encryption data
 	 * @{
 	 */
-	struct ptlrpc_cli_ctx   *rq_cli_ctx;     /**< client's half ctx */
-	struct ptlrpc_svc_ctx   *rq_svc_ctx;     /**< server's half ctx */
-	struct list_head	       rq_ctx_chain;   /**< link to waited ctx */
-
-	struct sptlrpc_flavor    rq_flvr;	/**< for client & server */
-	enum lustre_sec_part     rq_sp_from;
+	/** description of flavors for client & server */
+	struct sptlrpc_flavor		rq_flvr;
 
 	/* client/server security flags */
 	unsigned int

@@ -1393,19 +1529,15 @@ struct ptlrpc_request {
 				 rq_pack_bulk:1,
 				 /* doesn't expect reply FIXME */
 				 rq_no_reply:1,
-				 rq_pill_init:1;     /* pill initialized */
-
-	uid_t		    rq_auth_uid;	/* authed uid */
-	uid_t		    rq_auth_mapped_uid; /* authed uid mapped to */
-
-	/* (server side), pointed directly into req buffer */
-	struct ptlrpc_user_desc *rq_user_desc;
-
-	/* various buffer pointers */
-	struct lustre_msg       *rq_reqbuf;      /* req wrapper */
-	char		    *rq_repbuf;      /* rep buffer */
-	struct lustre_msg       *rq_repdata;     /* rep wrapper msg */
-	struct lustre_msg       *rq_clrbuf;      /* only in priv mode */
+				 rq_pill_init:1, /* pill initialized */
+				 rq_srv_req:1; /* server request */
+
+	/** various buffer pointers */
+	struct lustre_msg       *rq_reqbuf;	/**< req wrapper */
+	char			*rq_repbuf;	/**< rep buffer */
+	struct lustre_msg       *rq_repdata;	/**< rep wrapper msg */
+	/** only in priv mode */
+	struct lustre_msg       *rq_clrbuf;
 	int		      rq_reqbuf_len;  /* req wrapper buf len */
 	int		      rq_reqdata_len; /* req wrapper msg len */
 	int		      rq_repbuf_len;  /* rep buffer len */

@@ -1422,97 +1554,28 @@ struct ptlrpc_request {
 	__u32 rq_req_swab_mask;
 	__u32 rq_rep_swab_mask;
 
-	/** What was import generation when this request was sent */
-	int rq_import_generation;
-	enum lustre_imp_state rq_send_state;
-
 	/** how many early replies (for stats) */
 	int rq_early_count;
 
-	/** client+server request */
-	lnet_handle_md_t     rq_req_md_h;
-	struct ptlrpc_cb_id  rq_req_cbid;
-	/** optional time limit for send attempts */
-	long       rq_delay_limit;
-	/** time request was first queued */
-	unsigned long	   rq_queued_time;
-
-	/* server-side... */
-	/** request arrival time */
-	struct timespec64	rq_arrival_time;
-	/** separated reply state */
-	struct ptlrpc_reply_state *rq_reply_state;
-	/** incoming request buffer */
-	struct ptlrpc_request_buffer_desc *rq_rqbd;
-
-	/** client-only incoming reply */
-	lnet_handle_md_t     rq_reply_md_h;
-	wait_queue_head_t	  rq_reply_waitq;
-	struct ptlrpc_cb_id  rq_reply_cbid;
-
+	/** Server-side, export on which request was received */
+	struct obd_export		*rq_export;
+	/** import where request is being sent */
+	struct obd_import		*rq_import;
 	/** our LNet NID */
 	lnet_nid_t	   rq_self;
 	/** Peer description (the other side) */
 	lnet_process_id_t    rq_peer;
-	/** Server-side, export on which request was received */
-	struct obd_export   *rq_export;
-	/** Client side, import where request is being sent */
-	struct obd_import   *rq_import;
-
-	/** Replay callback, called after request is replayed@recovery */
-	void (*rq_replay_cb)(struct ptlrpc_request *);
 	/**
-	 * Commit callback, called when request is committed and about to be
-	 * freed.
+	 * service time estimate (secs)
+	 * If the request is not served by this time, it is marked as timed out.
 	 */
-	void (*rq_commit_cb)(struct ptlrpc_request *);
-	/** Opaq data for replay and commit callbacks. */
-	void  *rq_cb_data;
-
-	/** For bulk requests on client only: bulk descriptor */
-	struct ptlrpc_bulk_desc *rq_bulk;
-
-	/** client outgoing req */
+	int			rq_timeout;
 	/**
 	 * when request/reply sent (secs), or time when request should be sent
 	 */
 	time64_t rq_sent;
-	/** time for request really sent out */
-	time64_t rq_real_sent;
-
-	/** when request must finish. volatile
-	 * so that servers' early reply updates to the deadline aren't
-	 * kept in per-cpu cache
-	 */
-	volatile time64_t rq_deadline;
-	/** when req reply unlink must finish. */
-	time64_t rq_reply_deadline;
-	/** when req bulk unlink must finish. */
-	time64_t rq_bulk_deadline;
-	/**
-	 * service time estimate (secs)
-	 * If the requestsis not served by this time, it is marked as timed out.
-	 */
-	int    rq_timeout;
-
-	/** Multi-rpc bits */
-	/** Per-request waitq introduced by bug 21938 for recovery waiting */
-	wait_queue_head_t rq_set_waitq;
-	/** Link item for request set lists */
-	struct list_head  rq_set_chain;
-	/** Link back to the request set */
-	struct ptlrpc_request_set *rq_set;
-	/** Async completion handler, called when reply is received */
-	ptlrpc_interpterer_t rq_interpret_reply;
-	/** Async completion context */
-	union ptlrpc_async_args rq_async_args;
-
-	/** Pool if request is from preallocated list */
-	struct ptlrpc_request_pool *rq_pool;
-
-	struct lu_context	   rq_session;
-	struct lu_context	   rq_recov_session;
-
+	/** when request must finish. */
+	time64_t		  rq_deadline;
 	/** request format description */
 	struct req_capsule	  rq_pill;
 };

110 lines not on this page · raw message

index b8ca7d6..95be4aa 100644
@@ -324,6 +324,7 @@ void request_in_callback(lnet_event_t *ev)
 		}
 	}
 
+	ptlrpc_srv_req_init(req);
 	/* NB we ABSOLUTELY RELY on req being zeroed, so pointers are NULL,
 	 * flags are reset and scalars are zero.  We only set the message
 	 * size to non-zero if this was a successful receive.

@@ -337,10 +338,6 @@ void request_in_callback(lnet_event_t *ev)
 	req->rq_self = ev->target.nid;
 	req->rq_rqbd = rqbd;
 	req->rq_phase = RQ_PHASE_NEW;
-	spin_lock_init(&req->rq_lock);
-	INIT_LIST_HEAD(&req->rq_timed_list);
-	INIT_LIST_HEAD(&req->rq_exp_list);
-	atomic_set(&req->rq_refcount, 1);
 	if (ev->type == LNET_EVENT_PUT)
 		CDEBUG(D_INFO, "incoming req@%p x%llu msgsize %u\n",
 		       req, req->rq_xid, ev->mlength);

index ff9a95c..4e7d68f 100644
@@ -633,7 +633,7 @@ int ptl_send_rpc(struct ptlrpc_request *request, int noreply)
 
 	OBD_FAIL_TIMEOUT(OBD_FAIL_PTLRPC_DELAY_SEND, request->rq_timeout + 5);
 
-	ktime_get_real_ts64(&request->rq_arrival_time);
+	ktime_get_real_ts64(&request->rq_sent_tv);
 	request->rq_sent = ktime_get_real_seconds();
 	/* We give the server rq_timeout secs to process the req, and
 	 * add the network latency for our local timeout.

index 97e97e2..d3674cb 100644
@@ -288,4 +288,38 @@ static inline void ptlrpc_reqset_put(struct ptlrpc_request_set *set)
 	if (atomic_dec_and_test(&set->set_refcount))
 		kfree(set);
 }
+
+/** initialise ptlrpc common fields */
+static inline void ptlrpc_req_comm_init(struct ptlrpc_request *req)
+{
+	spin_lock_init(&req->rq_lock);
+	atomic_set(&req->rq_refcount, 1);
+	INIT_LIST_HEAD(&req->rq_list);
+	INIT_LIST_HEAD(&req->rq_replay_list);
+}
+
+/** initialise client side ptlrpc request */
+static inline void ptlrpc_cli_req_init(struct ptlrpc_request *req)
+{
+	struct ptlrpc_cli_req *cr = &req->rq_cli;
+
+	ptlrpc_req_comm_init(req);
+	INIT_LIST_HEAD(&cr->cr_set_chain);
+	INIT_LIST_HEAD(&cr->cr_ctx_chain);
+	init_waitqueue_head(&cr->cr_reply_waitq);
+	init_waitqueue_head(&cr->cr_set_waitq);
+}
+
+/** initialise server side ptlrpc request */
+static inline void ptlrpc_srv_req_init(struct ptlrpc_request *req)
+{
+	struct ptlrpc_srv_req *sr = &req->rq_srv;
+
+	ptlrpc_req_comm_init(req);
+	req->rq_srv_req = 1;
+	INIT_LIST_HEAD(&sr->sr_exp_list);
+	INIT_LIST_HEAD(&sr->sr_timed_list);
+	INIT_LIST_HEAD(&sr->sr_hist_list);
+}
+
 #endif /* PTLRPC_INTERNAL_H */

index b0cf585..0a374b6 100644
@@ -157,9 +157,9 @@ static int ptlrpcd_users;
 
 void ptlrpcd_wake(struct ptlrpc_request *req)
 {
-	struct ptlrpc_request_set *rq_set = req->rq_set;
+	struct ptlrpc_request_set *set = req->rq_set;
 
-	wake_up(&rq_set->set_waitq);
+	wake_up(&set->set_waitq);
 }
 EXPORT_SYMBOL(ptlrpcd_wake);
 

index f3b4773..dbd819f 100644
@@ -863,11 +863,9 @@ int sptlrpc_import_check_ctx(struct obd_import *imp)
 	if (!req)
 		return -ENOMEM;
 
-	spin_lock_init(&req->rq_lock);
+	ptlrpc_cli_req_init(req);
 	atomic_set(&req->rq_refcount, 10000);
-	INIT_LIST_HEAD(&req->rq_ctx_chain);
-	init_waitqueue_head(&req->rq_reply_waitq);
-	init_waitqueue_head(&req->rq_set_waitq);
+
 	req->rq_import = imp;
 	req->rq_flvr = sec->ps_flvr;
 	req->rq_cli_ctx = ctx;

@@ -1047,6 +1045,8 @@ int sptlrpc_cli_unwrap_early_reply(struct ptlrpc_request *req,
 	if (!early_req)
 		return -ENOMEM;
 
+	ptlrpc_cli_req_init(early_req);
+
 	early_size = req->rq_nob_received;
 	early_bufsz = size_roundup_power2(early_size);
 	early_buf = libcfs_kvzalloc(early_bufsz, GFP_NOFS);

@@ -1095,7 +1095,6 @@ int sptlrpc_cli_unwrap_early_reply(struct ptlrpc_request *req,
 	memcpy(early_buf, req->rq_repbuf, early_size);
 	spin_unlock(&req->rq_lock);
 
-	spin_lock_init(&early_req->rq_lock);
 	early_req->rq_cli_ctx = sptlrpc_cli_ctx_get(req->rq_cli_ctx);
 	early_req->rq_flvr = req->rq_flvr;
 	early_req->rq_repbuf = early_buf;

index 5968c3c..523d082 100644
@@ -1428,7 +1428,7 @@ struct ptlrpc_request {
 	 * rq_list
 	 */
 	spinlock_t rq_lock;
-	/** client-side flags are serialized by rq_lock */
+	/** client-side flags are serialized by rq_lock @{ */
 	unsigned int rq_intr:1, rq_replied:1, rq_err:1,
 		rq_timedout:1, rq_resend:1, rq_restart:1,
 		/**

@@ -1444,18 +1444,15 @@ struct ptlrpc_request {
 		rq_no_resend:1, rq_waiting:1, rq_receiving_reply:1,
 		rq_no_delay:1, rq_net_err:1, rq_wait_ctx:1,
 		rq_early:1,
-		rq_req_unlink:1, rq_reply_unlink:1,
+		rq_req_unlinked:1,	/* unlinked request buffer from lnet */
+		rq_reply_unlinked:1,	/* unlinked reply buffer from lnet */
 		rq_memalloc:1,      /* req originated from "kswapd" */
-		/* server-side flags */
-		rq_packed_final:1,  /* packed final reply */
-		rq_hp:1,	    /* high priority RPC */
-		rq_at_linked:1,     /* link into service's srv_at_array */
-		rq_reply_truncate:1,
 		rq_committed:1,
-		/* whether the "rq_set" is a valid one */
+		rq_reply_truncated:1,
+		/** whether the "rq_set" is a valid one */
 		rq_invalid_rqset:1,
 		rq_generation_set:1,
-		/* do not resend request on -EINPROGRESS */
+		/** do not resend request on -EINPROGRESS */
 		rq_no_retry_einprogress:1,
 		/* allow the req to be sent if the import is in recovery
 		 * status

@@ -1463,6 +1460,14 @@ struct ptlrpc_request {
 		rq_allow_replay:1,
 		/* bulk request, sent to server, but uncommitted */
 		rq_unstable:1;
+	/** @} */
+
+	/** server-side flags @{ */
+	unsigned int
+		rq_hp:1,		/**< high priority RPC */
+		rq_at_linked:1,		/**< link into service's srv_at_array */
+		rq_packed_final:1;	/**< packed final reply */
+	/** @} */
 
 	/** one of RQ_PHASE_* */
 	enum rq_phase			rq_phase;

@@ -2785,8 +2790,8 @@ ptlrpc_client_recv_or_unlink(struct ptlrpc_request *req)
 		spin_unlock(&req->rq_lock);
 		return 1;
 	}
-	rc = req->rq_receiving_reply;
-	rc = rc || req->rq_req_unlink || req->rq_reply_unlink;
+	rc = !req->rq_req_unlinked || !req->rq_reply_unlinked ||
+	     req->rq_receiving_reply;
 	spin_unlock(&req->rq_lock);
 	return rc;
 }

index 9abd469..ae1cef3 100644
@@ -1148,9 +1148,9 @@ static int after_reply(struct ptlrpc_request *req)
 
 	LASSERT(obd);
 	/* repbuf must be unlinked */
-	LASSERT(!req->rq_receiving_reply && !req->rq_reply_unlink);
+	LASSERT(!req->rq_receiving_reply && req->rq_reply_unlinked);
 
-	if (req->rq_reply_truncate) {
+	if (req->rq_reply_truncated) {
 		if (ptlrpc_no_resend(req)) {
 			DEBUG_REQ(D_ERROR, req, "reply buffer overflow, expected: %d, actual size: %d",
 				  req->rq_nob_received, req->rq_repbuf_len);

@@ -2342,9 +2342,10 @@ int ptlrpc_unregister_reply(struct ptlrpc_request *request, int async)
 
 		LASSERT(rc == -ETIMEDOUT);
 		DEBUG_REQ(D_WARNING, request,
-			  "Unexpectedly long timeout rvcng=%d unlnk=%d/%d",
+			  "Unexpectedly long timeout receiving_reply=%d req_ulinked=%d reply_unlinked=%d",
 			  request->rq_receiving_reply,
-			  request->rq_req_unlink, request->rq_reply_unlink);
+			  request->rq_req_unlinked,
+			  request->rq_reply_unlinked);
 	}
 	return 0;
 }

@@ -3002,9 +3003,6 @@ void *ptlrpcd_alloc_work(struct obd_import *imp,
 	req->rq_import = class_import_get(imp);
 	req->rq_interpret_reply = work_interpreter;
 	/* don't want reply */
-	req->rq_receiving_reply = 0;
-	req->rq_req_unlink = 0;
-	req->rq_reply_unlink = 0;
 	req->rq_no_delay = 1;
 	req->rq_no_resend = 1;
 	req->rq_pill.rc_fmt = (void *)&worker_format;

index 95be4aa..a243342 100644
@@ -51,27 +51,33 @@ void request_out_callback(lnet_event_t *ev)
 {
 	struct ptlrpc_cb_id *cbid = ev->md.user_ptr;
 	struct ptlrpc_request *req = cbid->cbid_arg;
+	bool wakeup = false;
 
-	LASSERT(ev->type == LNET_EVENT_SEND ||
-		ev->type == LNET_EVENT_UNLINK);
+	LASSERT(ev->type == LNET_EVENT_SEND || ev->type == LNET_EVENT_UNLINK);
 	LASSERT(ev->unlinked);
 
 	DEBUG_REQ(D_NET, req, "type %d, status %d", ev->type, ev->status);
 
 	sptlrpc_request_out_callback(req);
+
 	spin_lock(&req->rq_lock);
 	req->rq_real_sent = ktime_get_real_seconds();
-	if (ev->unlinked)
-		req->rq_req_unlink = 0;
+	req->rq_req_unlinked = 1;
+	/* reply_in_callback happened before request_out_callback? */
+	if (req->rq_reply_unlinked)
+		wakeup = true;
 
 	if (ev->type == LNET_EVENT_UNLINK || ev->status != 0) {
 		/* Failed send: make it seem like the reply timed out, just
 		 * like failing sends in client.c does currently...
 		 */
-
 		req->rq_net_err = 1;
-		ptlrpc_client_wake_req(req);
+		wakeup = true;
 	}
+
+	if (wakeup)
+		ptlrpc_client_wake_req(req);
+
 	spin_unlock(&req->rq_lock);
 
 	ptlrpc_req_finished(req);

@@ -100,7 +106,7 @@ void reply_in_callback(lnet_event_t *ev)
 	req->rq_receiving_reply = 0;
 	req->rq_early = 0;
 	if (ev->unlinked)
-		req->rq_reply_unlink = 0;
+		req->rq_reply_unlinked = 1;
 
 	if (ev->status)
 		goto out_wake;

@@ -114,7 +120,7 @@ void reply_in_callback(lnet_event_t *ev)
 	if (ev->mlength < ev->rlength) {
 		CDEBUG(D_RPCTRACE, "truncate req %p rpc %d - %d+%d\n", req,
 		       req->rq_replen, ev->rlength, ev->offset);
-		req->rq_reply_truncate = 1;
+		req->rq_reply_truncated = 1;
 		req->rq_replied = 1;
 		req->rq_status = -EOVERFLOW;
 		req->rq_nob_received = ev->rlength + ev->offset;

index 4e7d68f..8c49f5e 100644
@@ -577,19 +577,18 @@ int ptl_send_rpc(struct ptlrpc_request *request, int noreply)
 	}
 
 	spin_lock(&request->rq_lock);
-	/* If the MD attach succeeds, there _will_ be a reply_in callback */
-	request->rq_receiving_reply = !noreply;
-	request->rq_req_unlink = 1;
 	/* We are responsible for unlinking the reply buffer */
-	request->rq_reply_unlink = !noreply;
+	request->rq_reply_unlinked = noreply;
+	request->rq_receiving_reply = !noreply;
 	/* Clear any flags that may be present from previous sends. */
+	request->rq_req_unlinked = 0;
 	request->rq_replied = 0;
 	request->rq_err = 0;
 	request->rq_timedout = 0;
 	request->rq_net_err = 0;
 	request->rq_resend = 0;
 	request->rq_restart = 0;
-	request->rq_reply_truncate = 0;
+	request->rq_reply_truncated = 0;
 	spin_unlock(&request->rq_lock);
 
 	if (!noreply) {

@@ -604,7 +603,7 @@ int ptl_send_rpc(struct ptlrpc_request *request, int noreply)
 		reply_md.user_ptr = &request->rq_reply_cbid;
 		reply_md.eq_handle = ptlrpc_eq_h;
 
-		/* We must see the unlink callback to unset rq_reply_unlink,
+		/* We must see the unlink callback to set rq_reply_unlinked,
 		 * so we can't auto-unlink
 		 */
 		rc = LNetMDAttach(reply_me_h, reply_md, LNET_RETAIN,

@@ -651,9 +650,10 @@ int ptl_send_rpc(struct ptlrpc_request *request, int noreply)
 			  connection,
 			  request->rq_request_portal,
 			  request->rq_xid, 0);
-	if (rc == 0)
+	if (likely(rc == 0))
 		goto out;
 
+	request->rq_req_unlinked = 1;
 	ptlrpc_req_finished(request);
 	if (noreply)
 		goto out;

index d3674cb..a9831fa 100644
@@ -304,6 +304,15 @@ static inline void ptlrpc_cli_req_init(struct ptlrpc_request *req)
 	struct ptlrpc_cli_req *cr = &req->rq_cli;
 
 	ptlrpc_req_comm_init(req);
+
+	req->rq_receiving_reply = 0;
+	req->rq_req_unlinked = 1;
+	req->rq_reply_unlinked = 1;
+
+	req->rq_receiving_reply = 0;
+	req->rq_req_unlinked = 1;
+	req->rq_reply_unlinked = 1;
+
 	INIT_LIST_HEAD(&cr->cr_set_chain);
 	INIT_LIST_HEAD(&cr->cr_ctx_chain);
 	init_waitqueue_head(&cr->cr_reply_waitq);

index a243342..b1ce725 100644
@@ -137,7 +137,8 @@ void reply_in_callback(lnet_event_t *ev)
 
 		req->rq_early_count++; /* number received, client side */
 
-		if (req->rq_replied)   /* already got the real reply */
+		/* already got the real reply or buffers are already unlinked */
+		if (req->rq_replied || req->rq_reply_unlinked == 1)
 			goto out_wake;
 
 		req->rq_early = 1;

index ae1cef3..5d832eb 100644
@@ -583,14 +583,19 @@ static void __ptlrpc_free_req_to_pool(struct ptlrpc_request *request)
 	spin_unlock(&pool->prp_lock);
 }
 
-static int __ptlrpc_request_bufs_pack(struct ptlrpc_request *request,
-				      __u32 version, int opcode,
-				      int count, __u32 *lengths, char **bufs,
-				      struct ptlrpc_cli_ctx *ctx)
+int ptlrpc_request_bufs_pack(struct ptlrpc_request *request,
+			     __u32 version, int opcode, char **bufs,
+			     struct ptlrpc_cli_ctx *ctx)
 {
-	struct obd_import *imp = request->rq_import;
+	int count;
+	struct obd_import *imp;
+	__u32 *lengths;
 	int rc;
 
+	count = req_capsule_filled_sizes(&request->rq_pill, RCL_CLIENT);
+	imp = request->rq_import;
+	lengths = request->rq_pill.rc_area[RCL_CLIENT];
+
 	if (unlikely(ctx)) {
 		request->rq_cli_ctx = sptlrpc_cli_ctx_get(ctx);
 	} else {

@@ -598,15 +603,12 @@ static int __ptlrpc_request_bufs_pack(struct ptlrpc_request *request,
 		if (rc)
 			goto out_free;
 	}
-
 	sptlrpc_req_set_flavor(request, opcode);
 
 	rc = lustre_pack_request(request, imp->imp_msg_magic, count,
 				 lengths, bufs);
-	if (rc) {
-		LASSERT(!request->rq_pool);
+	if (rc)
 		goto out_ctx;
-	}
 
 	lustre_msg_add_version(request->rq_reqmsg, version);
 	request->rq_send_state = LUSTRE_IMP_FULL;

@@ -631,24 +633,14 @@ static int __ptlrpc_request_bufs_pack(struct ptlrpc_request *request,
 	lustre_msg_set_opc(request->rq_reqmsg, opcode);
 
 	return 0;
+
 out_ctx:
+	LASSERT(!request->rq_pool);
 	sptlrpc_cli_ctx_put(request->rq_cli_ctx, 1);
 out_free:
 	class_import_put(imp);
 	return rc;
 }
-
-int ptlrpc_request_bufs_pack(struct ptlrpc_request *request,
-			     __u32 version, int opcode, char **bufs,
-			     struct ptlrpc_cli_ctx *ctx)
-{
-	int count;
-
-	count = req_capsule_filled_sizes(&request->rq_pill, RCL_CLIENT);
-	return __ptlrpc_request_bufs_pack(request, version, opcode, count,
-					  request->rq_pill.rc_area[RCL_CLIENT],
-					  bufs, ctx);
-}
 EXPORT_SYMBOL(ptlrpc_request_bufs_pack);
 
 /**

index 523d082..3f43664 100644
@@ -480,8 +480,9 @@ enum rq_phase {
 	RQ_PHASE_BULK	   = 0xebc0de02,
 	RQ_PHASE_INTERPRET      = 0xebc0de03,
 	RQ_PHASE_COMPLETE       = 0xebc0de04,
-	RQ_PHASE_UNREGISTERING  = 0xebc0de05,
-	RQ_PHASE_UNDEFINED      = 0xebc0de06
+	RQ_PHASE_UNREG_RPC	= 0xebc0de05,
+	RQ_PHASE_UNREG_BULK	= 0xebc0de06,
+	RQ_PHASE_UNDEFINED	= 0xebc0de07
 };
 
 /** Type of request interpreter call-back */

@@ -1263,6 +1264,8 @@ struct ptlrpc_cli_req {
 	time_t				 cr_reply_deadline;
 	/** when req bulk unlink must finish. */
 	time_t				 cr_bulk_deadline;
+	/** when req unlink must finish. */
+	time_t				 cr_req_deadline;
 	/** Portal to which this request would be sent */
 	short				 cr_req_ptl;
 	/** Portal where to wait for reply and where reply would be sent */

@@ -1318,6 +1321,7 @@ struct ptlrpc_cli_req {
 #define rq_real_sent		rq_cli.cr_sent_out
 #define rq_reply_deadline	rq_cli.cr_reply_deadline
 #define rq_bulk_deadline	rq_cli.cr_bulk_deadline
+#define rq_req_deadline		rq_cli.cr_req_deadline
 #define rq_nr_resend		rq_cli.cr_resend_nr
 #define rq_request_portal	rq_cli.cr_req_ptl
 #define rq_reply_portal		rq_cli.cr_rep_ptl

@@ -1693,8 +1697,10 @@ ptlrpc_phase2str(enum rq_phase phase)
 		return "Interpret";
 	case RQ_PHASE_COMPLETE:
 		return "Complete";
-	case RQ_PHASE_UNREGISTERING:
-		return "Unregistering";
+	case RQ_PHASE_UNREG_RPC:
+		return "UnregRPC";
+	case RQ_PHASE_UNREG_BULK:
+		return "UnregBULK";
 	default:
 		return "?Phase?";
 	}

@@ -1721,7 +1727,7 @@ ptlrpc_rqphase2str(struct ptlrpc_request *req)
 #define DEBUG_REQ_FLAGS(req)						    \
 	ptlrpc_rqphase2str(req),						\
 	FLAG(req->rq_intr, "I"), FLAG(req->rq_replied, "R"),		    \
-	FLAG(req->rq_err, "E"),						 \
+	FLAG(req->rq_err, "E"),	FLAG(req->rq_net_err, "e"),		    \
 	FLAG(req->rq_timedout, "X") /* eXpired */, FLAG(req->rq_resend, "S"),   \
 	FLAG(req->rq_restart, "T"), FLAG(req->rq_replay, "P"),		  \
 	FLAG(req->rq_no_resend, "N"),					   \

@@ -1729,7 +1735,7 @@ ptlrpc_rqphase2str(struct ptlrpc_request *req)
 	FLAG(req->rq_wait_ctx, "C"), FLAG(req->rq_hp, "H"),		     \
 	FLAG(req->rq_committed, "M")
 
-#define REQ_FLAGS_FMT "%s:%s%s%s%s%s%s%s%s%s%s%s%s"
+#define REQ_FLAGS_FMT "%s:%s%s%s%s%s%s%s%s%s%s%s%s%s"
 
 void _debug_req(struct ptlrpc_request *req,
 		struct libcfs_debug_msg_data *data, const char *fmt, ...)

@@ -2380,8 +2386,7 @@ static inline int ptlrpc_client_bulk_active(struct ptlrpc_request *req)
 
 	desc = req->rq_bulk;
 
-	if (OBD_FAIL_CHECK(OBD_FAIL_PTLRPC_LONG_BULK_UNLINK) &&
-	    req->rq_bulk_deadline > ktime_get_real_seconds())
+	if (req->rq_bulk_deadline > ktime_get_real_seconds())
 		return 1;
 
 	if (!desc)

@@ -2728,13 +2733,20 @@ ptlrpc_rqphase_move(struct ptlrpc_request *req, enum rq_phase new_phase)
 	if (req->rq_phase == new_phase)
 		return;
 
-	if (new_phase == RQ_PHASE_UNREGISTERING) {
+	if (new_phase == RQ_PHASE_UNREG_RPC ||
+	    new_phase == RQ_PHASE_UNREG_BULK) {
+		/* No embedded unregistering phases */
+		if (req->rq_phase == RQ_PHASE_UNREG_RPC ||
+		    req->rq_phase == RQ_PHASE_UNREG_BULK)
+			return;
+
 		req->rq_next_phase = req->rq_phase;
 		if (req->rq_import)
 			atomic_inc(&req->rq_import->imp_unregistering);
 	}
 
-	if (req->rq_phase == RQ_PHASE_UNREGISTERING) {
+	if (req->rq_phase == RQ_PHASE_UNREG_RPC ||
+	    req->rq_phase == RQ_PHASE_UNREG_BULK) {
 		if (req->rq_import)
 			atomic_dec(&req->rq_import->imp_unregistering);
 	}

@@ -2751,9 +2763,6 @@ ptlrpc_rqphase_move(struct ptlrpc_request *req, enum rq_phase new_phase)
 static inline int
 ptlrpc_client_early(struct ptlrpc_request *req)
 {
-	if (OBD_FAIL_CHECK(OBD_FAIL_PTLRPC_LONG_REPL_UNLINK) &&
-	    req->rq_reply_deadline > ktime_get_real_seconds())
-		return 0;
 	return req->rq_early;
 }
 

@@ -2763,8 +2772,7 @@ ptlrpc_client_early(struct ptlrpc_request *req)
 static inline int
 ptlrpc_client_replied(struct ptlrpc_request *req)
 {
-	if (OBD_FAIL_CHECK(OBD_FAIL_PTLRPC_LONG_REPL_UNLINK) &&
-	    req->rq_reply_deadline > ktime_get_real_seconds())
+	if (req->rq_reply_deadline > ktime_get_real_seconds())
 		return 0;
 	return req->rq_replied;
 }

@@ -2773,8 +2781,7 @@ ptlrpc_client_replied(struct ptlrpc_request *req)
 static inline int
 ptlrpc_client_recv(struct ptlrpc_request *req)
 {
-	if (OBD_FAIL_CHECK(OBD_FAIL_PTLRPC_LONG_REPL_UNLINK) &&
-	    req->rq_reply_deadline > ktime_get_real_seconds())
+	if (req->rq_reply_deadline > ktime_get_real_seconds())
 		return 1;
 	return req->rq_receiving_reply;
 }

@@ -2785,8 +2792,11 @@ ptlrpc_client_recv_or_unlink(struct ptlrpc_request *req)
 	int rc;
 
 	spin_lock(&req->rq_lock);
-	if (OBD_FAIL_CHECK(OBD_FAIL_PTLRPC_LONG_REPL_UNLINK) &&
-	    req->rq_reply_deadline > ktime_get_real_seconds()) {
+	if (req->rq_reply_deadline > ktime_get_real_seconds()) {
+		spin_unlock(&req->rq_lock);
+		return 1;
+	}
+	if (req->rq_req_deadline > ktime_get_real_seconds()) {
 		spin_unlock(&req->rq_lock);
 		return 1;
 	}

index cdf20d6..845e64a 100644
@@ -364,6 +364,9 @@ extern char obd_jobid_var[];
 #define OBD_FAIL_PTLRPC_CLIENT_BULK_CB2  0x515
 #define OBD_FAIL_PTLRPC_DELAY_IMP_FULL   0x516
 #define OBD_FAIL_PTLRPC_CANCEL_RESEND    0x517
+#define OBD_FAIL_PTLRPC_DROP_BULK	 0x51a
+#define OBD_FAIL_PTLRPC_LONG_REQ_UNLINK	 0x51b
+#define OBD_FAIL_PTLRPC_LONG_BOTH_UNLINK 0x51c
 
 #define OBD_FAIL_OBD_PING_NET	    0x600
 #define OBD_FAIL_OBD_LOG_CANCEL_NET      0x601

120 lines not on this page · raw message

index 914bbd2..3292e6e 100644
@@ -356,9 +356,8 @@ void ptlrpc_invalidate_import(struct obd_import *imp)
 						  "still on delayed list");
 				}
 
-				CERROR("%s: RPCs in \"%s\" phase found (%d). Network is sluggish? Waiting them to error out.\n",
+				CERROR("%s: Unregistering RPCs found (%d). Network is sluggish? Waiting them to error out.\n",
 				       cli_tgt,
-				       ptlrpc_phase2str(RQ_PHASE_UNREGISTERING),
 				       atomic_read(&imp->
 						   imp_unregistering));
 			}

index 8c49f5e..11ec825 100644
@@ -247,7 +247,7 @@ int ptlrpc_unregister_bulk(struct ptlrpc_request *req, int async)
 
 	/* Let's setup deadline for reply unlink. */
 	if (OBD_FAIL_CHECK(OBD_FAIL_PTLRPC_LONG_BULK_UNLINK) &&
-	    async && req->rq_bulk_deadline == 0)
+	    async && req->rq_bulk_deadline == 0 && cfs_fail_val == 0)
 		req->rq_bulk_deadline = ktime_get_real_seconds() + LONG_UNLINK;
 
 	if (ptlrpc_client_bulk_active(req) == 0)	/* completed or */

@@ -266,7 +266,7 @@ int ptlrpc_unregister_bulk(struct ptlrpc_request *req, int async)
 		return 1;				/* never registered */
 
 	/* Move to "Unregistering" phase as bulk was not unlinked yet. */
-	ptlrpc_rqphase_move(req, RQ_PHASE_UNREGISTERING);
+	ptlrpc_rqphase_move(req, RQ_PHASE_UNREG_BULK);
 
 	/* Do not wait for unlink to finish. */
 	if (async)

index fb1c3b6..66ee5db 100644
@@ -196,18 +196,11 @@ static int ll_page_mkwrite0(struct vm_area_struct *vma, struct page *vmpage,
 
 	set = cfs_block_sigsinv(sigmask(SIGKILL) | sigmask(SIGTERM));
 
-	/* we grab lli_trunc_sem to exclude truncate case.
-	 * Otherwise, we could add dirty pages into osc cache
-	 * while truncate is on-going.
-	 */
 	inode = vvp_object_inode(io->ci_obj);
 	lli = ll_i2info(inode);
-	down_read(&lli->lli_trunc_sem);
 
 	result = cl_io_loop(env, io);
 
-	up_read(&lli->lli_trunc_sem);
-
 	cfs_restore_sigs(set);
 
 	if (result == 0) {

index 1ecdfa2..b7254eb 100644
@@ -1440,7 +1440,7 @@ int ldlm_fill_lvb(struct ldlm_lock *lock, struct req_capsule *pill,
 		memcpy(data, lvb, size);
 		break;
 	default:
-		LDLM_ERROR(lock, "Unknown LVB type: %d\n", lock->l_lvb_type);
+		LDLM_ERROR(lock, "Unknown LVB type: %d", lock->l_lvb_type);
 		dump_stack();
 		return -EINVAL;
 	}

index 3eab059..8294703 100644
@@ -637,7 +637,8 @@ static int ldlm_callback_handler(struct ptlrpc_request *req)
 		 */
 		if ((ldlm_is_canceling(lock) && ldlm_is_bl_done(lock)) ||
 		    ldlm_is_failed(lock)) {
-			LDLM_DEBUG(lock, "callback on lock %#llx - lock disappeared\n",
+			LDLM_DEBUG(lock,
+				   "callback on lock %#llx - lock disappeared",
 				   dlm_req->lock_handle[0].cookie);
 			unlock_res_and_lock(lock);
 			LDLM_LOCK_RELEASE(lock);

index 471ab08..d3a376e 100644
@@ -711,7 +711,7 @@ int ldlm_cli_enqueue(struct obd_export *exp, struct ptlrpc_request **reqp,
 
 			lock->l_req_extent = policy->l_extent;
 		}
-		LDLM_DEBUG(lock, "client-side enqueue START, flags %llx\n",
+		LDLM_DEBUG(lock, "client-side enqueue START, flags %llx",
 			   *flags);
 	}
 

index f7c95b7..51a28d9 100644
@@ -1275,7 +1275,7 @@ void ldlm_resource_add_lock(struct ldlm_resource *res, struct list_head *head,
 {
 	check_res_locked(res);
 
-	LDLM_DEBUG(lock, "About to add this lock:\n");
+	LDLM_DEBUG(lock, "About to add this lock:");
 
 	if (ldlm_is_destroyed(lock)) {
 		CDEBUG(D_OTHER, "Lock destroyed, not adding to resource\n");

index ec55b88..f9621b0 100644
@@ -181,8 +181,8 @@ static int lov_init_sub(const struct lu_env *env, struct lov_object *lov,
 		}
 
 		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);
 	}

index b395420..19b549c 100644
@@ -711,7 +711,7 @@ static int mdc_finish_enqueue(struct obd_export *exp,
 	if (lock && ldlm_has_layout(lock) && lvb_data) {
 		void *lmm;
 
-		LDLM_DEBUG(lock, "layout lock returned by: %s, lvb_len: %d\n",
+		LDLM_DEBUG(lock, "layout lock returned by: %s, lvb_len: %d",
 			   ldlm_it2str(it->it_op), lvb_len);
 
 		lmm = libcfs_kvzalloc(lvb_len, GFP_NOFS);

index 1a6df43..e3b9f9d 100644
@@ -123,9 +123,9 @@ static const char *oes_strings[] = {
 		/* ----- part 4 ----- */				      \
 		## __VA_ARGS__);					      \
 	if (lvl == D_ERROR && __ext->oe_dlmlock)			      \
-		LDLM_ERROR(__ext->oe_dlmlock, "extent: %p\n", __ext);	      \
+		LDLM_ERROR(__ext->oe_dlmlock, "extent: %p", __ext);	      \
 	else								      \
-		LDLM_DEBUG(__ext->oe_dlmlock, "extent: %p\n", __ext);	      \
+		LDLM_DEBUG(__ext->oe_dlmlock, "extent: %p", __ext);	      \
 } while (0)
 
 #undef EASSERTF

index 5455d9d..717d3ff 100644
@@ -1168,7 +1168,7 @@ int osc_lock_init(const struct lu_env *env,
 		osc_lock_set_writer(env, io, obj, oscl);
 
 
-	LDLM_DEBUG_NOLOCK("lock %p, osc lock %p, flags %llx\n",
+	LDLM_DEBUG_NOLOCK("lock %p, osc lock %p, flags %llx",
 			  lock, oscl, oscl->ols_flags);
 
 	return 0;

index c6281e6..6e25c1b 100644
@@ -779,7 +779,7 @@ do {								      \
 	if (cfs_cdebug_show(mask, DEBUG_SUBSYSTEM)) {		     \
 		LIBCFS_DEBUG_MSG_DATA_DECL(msgdata, mask, NULL);		\
 		lu_object_print(env, &msgdata, lu_cdebug_printer, object);\
-		CDEBUG(mask, format, ## __VA_ARGS__);		    \
+		CDEBUG(mask, format "\n", ## __VA_ARGS__);		    \
 	}								 \
 } while (0)
 

index fdc6236..41c03d7 100644
@@ -34,7 +34,11 @@
 #define LUSTRE_INTENT_H
 
 /* intent IT_XXX are defined in lustre/include/obd.h */
-struct lustre_intent_data {
+
+struct lookup_intent {
+	int		it_op;
+	int		it_create_mode;
+	__u64		it_flags;
 	int		it_disposition;
 	int		it_status;
 	__u64		it_lock_handle;

@@ -46,13 +50,4 @@ struct lustre_intent_data {
 	unsigned int    it_lock_set:1;
 };
 
-struct lookup_intent {
-	int     it_op;
-	int     it_create_mode;
-	__u64   it_flags;
-	union {
-		struct lustre_intent_data lustre;
-	} d;
-};
-
 #endif

index f002b3a..c5789f7 100644
@@ -202,27 +202,27 @@ int ll_d_init(struct dentry *de)
 
 void ll_intent_drop_lock(struct lookup_intent *it)
 {
-	if (it->it_op && it->d.lustre.it_lock_mode) {
+	if (it->it_op && it->it_lock_mode) {
 		struct lustre_handle handle;
 
-		handle.cookie = it->d.lustre.it_lock_handle;
+		handle.cookie = it->it_lock_handle;
 
 		CDEBUG(D_DLMTRACE, "releasing lock with cookie %#llx from it %p\n",
 		       handle.cookie, it);
-		ldlm_lock_decref(&handle, it->d.lustre.it_lock_mode);
+		ldlm_lock_decref(&handle, it->it_lock_mode);
 
 		/* bug 494: intent_release may be called multiple times, from
 		 * this thread and we don't want to double-decref this lock
 		 */
-		it->d.lustre.it_lock_mode = 0;
-		if (it->d.lustre.it_remote_lock_mode != 0) {
-			handle.cookie = it->d.lustre.it_remote_lock_handle;
+		it->it_lock_mode = 0;
+		if (it->it_remote_lock_mode != 0) {
+			handle.cookie = it->it_remote_lock_handle;
 
 			CDEBUG(D_DLMTRACE, "releasing remote lock with cookie%#llx from it %p\n",
 			       handle.cookie, it);
 			ldlm_lock_decref(&handle,
-					 it->d.lustre.it_remote_lock_mode);
-			it->d.lustre.it_remote_lock_mode = 0;
+					 it->it_remote_lock_mode);
+			it->it_remote_lock_mode = 0;
 		}
 	}
 }

@@ -233,13 +233,13 @@ void ll_intent_release(struct lookup_intent *it)
 	ll_intent_drop_lock(it);
 	/* We are still holding extra reference on a request, need to free it */
 	if (it_disposition(it, DISP_ENQ_OPEN_REF))
-		ptlrpc_req_finished(it->d.lustre.it_data); /* ll_file_open */
+		ptlrpc_req_finished(it->it_data); /* ll_file_open */
 
 	if (it_disposition(it, DISP_ENQ_CREATE_REF)) /* create rec */
-		ptlrpc_req_finished(it->d.lustre.it_data);
+		ptlrpc_req_finished(it->it_data);
 
-	it->d.lustre.it_disposition = 0;
-	it->d.lustre.it_data = NULL;
+	it->it_disposition = 0;
+	it->it_data = NULL;
 }
 
 void ll_invalidate_aliases(struct inode *inode)

@@ -279,7 +279,7 @@ int ll_revalidate_it_finish(struct ptlrpc_request *request,
 
 void ll_lookup_finish_locks(struct lookup_intent *it, struct inode *inode)
 {
-	if (it->d.lustre.it_lock_mode && inode) {
+	if (it->it_lock_mode && inode) {
 		struct ll_sb_info *sbi = ll_i2sbi(inode);
 
 		CDEBUG(D_DLMTRACE, "setting l_data to inode "DFID"(%p)\n",

index 99735f6..a62df87 100644
@@ -362,7 +362,7 @@ struct page *ll_get_dir_page(struct inode *dir, __u64 hash,
 
 		ll_finish_md_op_data(op_data);
 
-		request = (struct ptlrpc_request *)it.d.lustre.it_data;
+		request = (struct ptlrpc_request *)it.it_data;
 		if (request)
 			ptlrpc_req_finished(request);
 		if (rc < 0) {

@@ -374,7 +374,7 @@ struct page *ll_get_dir_page(struct inode *dir, __u64 hash,
 		CDEBUG(D_INODE, "setting lr_lvb_inode to inode "DFID"(%p)\n",
 		       PFID(ll_inode2fid(dir)), dir);
 		md_set_lock_data(ll_i2sbi(dir)->ll_md_exp,
-				 &it.d.lustre.it_lock_handle, dir, NULL);
+				 &it.it_lock_handle, dir, NULL);
 	} else {
 		/* for cross-ref object, l_ast_data of the lock may not be set,
 		 * we reset it here

133 lines not on this page · raw message

index 098155f..3692102 100644
@@ -1280,7 +1280,7 @@ static inline int ll_file_nolock(const struct file *file)
 static inline void ll_set_lock_data(struct obd_export *exp, struct inode *inode,
 				    struct lookup_intent *it, __u64 *bits)
 {
-	if (!it->d.lustre.it_lock_set) {
+	if (!it->it_lock_set) {
 		struct lustre_handle handle;
 
 		/* If this inode is a remote object, it will get two

@@ -1291,26 +1291,26 @@ static inline void ll_set_lock_data(struct obd_export *exp, struct inode *inode,
 		 * LOOKUP and PERM locks, so revoking either locks will
 		 * case the dcache being cleared
 		 */
-		if (it->d.lustre.it_remote_lock_mode) {
-			handle.cookie = it->d.lustre.it_remote_lock_handle;
+		if (it->it_remote_lock_mode) {
+			handle.cookie = it->it_remote_lock_handle;
 			CDEBUG(D_DLMTRACE, "setting l_data to inode "DFID"%p for remote lock %#llx\n",
 			       PFID(ll_inode2fid(inode)), inode,
 			       handle.cookie);
 			md_set_lock_data(exp, &handle.cookie, inode, NULL);
 		}
 
-		handle.cookie = it->d.lustre.it_lock_handle;
+		handle.cookie = it->it_lock_handle;
 
 		CDEBUG(D_DLMTRACE, "setting l_data to inode "DFID"%p for lock %#llx\n",
 		       PFID(ll_inode2fid(inode)), inode, handle.cookie);
 
 		md_set_lock_data(exp, &handle.cookie, inode,
-				 &it->d.lustre.it_lock_bits);
-		it->d.lustre.it_lock_set = 1;
+				 &it->it_lock_bits);
+		it->it_lock_set = 1;
 	}
 
 	if (bits)
-		*bits = it->d.lustre.it_lock_bits;
+		*bits = it->it_lock_bits;
 }
 
 static inline int d_lustre_invalid(const struct dentry *dentry)

index 83f4e1a..539fdd1 100644
@@ -1998,11 +1998,11 @@ int ll_prep_inode(struct inode **inode, struct ptlrpc_request *req,
 	 * 3. proc2: refresh layout and layout lock granted
 	 * 4. proc1: to apply a stale layout
 	 */
-	if (it && it->d.lustre.it_lock_mode != 0) {
+	if (it && it->it_lock_mode != 0) {
 		struct lustre_handle lockh;
 		struct ldlm_lock *lock;
 
-		lockh.cookie = it->d.lustre.it_lock_handle;
+		lockh.cookie = it->it_lock_handle;
 		lock = ldlm_handle2lock(&lockh);
 		LASSERT(lock);
 		if (ldlm_has_layout(lock)) {

index e4df510..7a6da02 100644
@@ -393,7 +393,7 @@ static int ll_lookup_it_finish(struct ptlrpc_request *request,
 	 * when I return
 	 */
 	CDEBUG(D_DENTRY, "it %p it_disposition %x\n", it,
-	       it->d.lustre.it_disposition);
+	       it->it_disposition);
 	if (!it_disposition(it, DISP_LOOKUP_NEG)) {
 		rc = ll_prep_inode(&inode, request, (*de)->d_sb, it);
 		if (rc)

@@ -445,7 +445,7 @@ static int ll_lookup_it_finish(struct ptlrpc_request *request,
 		/* Check that parent has UPDATE lock. */
 		struct lookup_intent parent_it = {
 					.it_op = IT_GETATTR,
-					.d.lustre.it_lock_handle = 0 };
+					.it_lock_handle = 0 };
 
 		if (md_revalidate_lock(ll_i2mdexp(parent), &parent_it,
 				       &ll_i2info(parent)->lli_fid, NULL)) {

@@ -656,10 +656,10 @@ static struct inode *ll_create_node(struct inode *dir, struct lookup_intent *it)
 	struct ll_sb_info *sbi = ll_i2sbi(dir);
 	int rc;
 
-	LASSERT(it && it->d.lustre.it_disposition);
+	LASSERT(it && it->it_disposition);
 
 	LASSERT(it_disposition(it, DISP_ENQ_CREATE_REF));
-	request = it->d.lustre.it_data;
+	request = it->it_data;
 	it_clear_disposition(it, DISP_ENQ_CREATE_REF);
 	rc = ll_prep_inode(&inode, request, dir->i_sb, it);
 	if (rc) {

index 03ad858..f775242 100644
@@ -646,7 +646,7 @@ static void ll_post_statahead(struct ll_statahead_info *sai)
 		}
 	}
 
-	it->d.lustre.it_lock_handle = entry->se_handle;
+	it->it_lock_handle = entry->se_handle;
 	rc = md_revalidate_lock(ll_i2mdexp(dir), it, ll_inode2fid(dir), NULL);
 	if (rc != 1) {
 		rc = -EAGAIN;

@@ -700,7 +700,7 @@ static int ll_statahead_interpret(struct ptlrpc_request *req,
 		 * process enqueues lock on child with parent lock held, eg.
 		 * unlink.
 		 */
-		handle = it->d.lustre.it_lock_handle;
+		handle = it->it_lock_handle;
 		ll_intent_drop_lock(it);
 	}
 

@@ -850,7 +850,7 @@ static int do_sa_revalidate(struct inode *dir, struct ll_sa_entry *entry,
 {
 	struct inode	     *inode = d_inode(dentry);
 	struct lookup_intent      it = { .it_op = IT_GETATTR,
-					 .d.lustre.it_lock_handle = 0 };
+					 .it_lock_handle = 0 };
 	struct md_enqueue_info   *minfo;
 	struct ldlm_enqueue_info *einfo;
 	int rc;

@@ -865,7 +865,7 @@ static int do_sa_revalidate(struct inode *dir, struct ll_sa_entry *entry,
 	rc = md_revalidate_lock(ll_i2mdexp(dir), &it, ll_inode2fid(inode),
 				NULL);
 	if (rc == 1) {
-		entry->se_handle = it.d.lustre.it_lock_handle;
+		entry->se_handle = it.it_lock_handle;
 		ll_intent_release(&it);
 		return 1;
 	}

@@ -1569,7 +1569,7 @@ int do_statahead_enter(struct inode *dir, struct dentry **dentryp,
 		if (entry->se_stat == SA_ENTRY_SUCC && entry->se_inode) {
 			struct inode *inode = entry->se_inode;
 			struct lookup_intent it = { .it_op = IT_GETATTR,
-						    .d.lustre.it_lock_handle =
+						    .it_lock_handle =
 						     entry->se_handle };
 			__u64 bits;
 

index d7e17ab..0d19645 100644
@@ -288,8 +288,8 @@ static int ll_xattr_find_get_lock(struct inode *inode,
 				       LCK_PR);
 		if (mode != 0) {
 			/* fake oit in mdc_revalidate_lock() manner */
-			oit->d.lustre.it_lock_handle = lockh.cookie;
-			oit->d.lustre.it_lock_mode = mode;
+			oit->it_lock_handle = lockh.cookie;
+			oit->it_lock_mode = mode;
 			goto out;
 		}
 	}

@@ -315,7 +315,7 @@ static int ll_xattr_find_get_lock(struct inode *inode,
 		return rc;
 	}
 
-	*req = (struct ptlrpc_request *)oit->d.lustre.it_data;
+	*req = (struct ptlrpc_request *)oit->it_data;
 out:
 	down_write(&lli->lli_xattrs_list_rwsem);
 	mutex_unlock(&lli->lli_xattrs_enq_lock);

@@ -362,10 +362,10 @@ static int ll_xattr_cache_refill(struct inode *inode, struct lookup_intent *oit)
 		goto out_maybe_drop;
 	}
 
-	if (oit->d.lustre.it_status < 0) {
+	if (oit->it_status < 0) {
 		CDEBUG(D_CACHE, "getxattr intent returned %d for fid "DFID"\n",
-		       oit->d.lustre.it_status, PFID(ll_inode2fid(inode)));
-		rc = oit->d.lustre.it_status;
+		       oit->it_status, PFID(ll_inode2fid(inode)));
+		rc = oit->it_status;
 		/* xattr data is so large that we don't want to cache it */
 		if (rc == -ERANGE)
 			rc = -EAGAIN;

@@ -448,8 +448,8 @@ out_destroy:
 	up_write(&lli->lli_xattrs_list_rwsem);
 
 	ldlm_lock_decref_and_cancel((struct lustre_handle *)
-					&oit->d.lustre.it_lock_handle,
-					oit->d.lustre.it_lock_mode);
+					&oit->it_lock_handle,
+					oit->it_lock_mode);
 
 	goto out_no_unlock;
 }

index 980c9d4..b3cff23 100644
@@ -80,11 +80,11 @@ static int lmv_intent_remote(struct obd_export *exp, void *lmm,
 	/*
 	 * We got LOOKUP lock, but we really need attrs.
 	 */
-	pmode = it->d.lustre.it_lock_mode;
+	pmode = it->it_lock_mode;
 	if (pmode) {
-		plock.cookie = it->d.lustre.it_lock_handle;
-		it->d.lustre.it_lock_mode = 0;
-		it->d.lustre.it_data = NULL;
+		plock.cookie = it->it_lock_handle;
+		it->it_lock_mode = 0;
+		it->it_data = NULL;
 	}
 
 	LASSERT(fid_is_sane(&body->fid1));

@@ -130,14 +130,14 @@ static int lmv_intent_remote(struct obd_export *exp, void *lmm,
 	 * maintain dcache consistency. Thus drop UPDATE|PERM lock here
 	 * and put LOOKUP in request.
 	 */
-	if (it->d.lustre.it_lock_mode != 0) {
-		it->d.lustre.it_remote_lock_handle =
-					it->d.lustre.it_lock_handle;
-		it->d.lustre.it_remote_lock_mode = it->d.lustre.it_lock_mode;
+	if (it->it_lock_mode != 0) {
+		it->it_remote_lock_handle =
+					it->it_lock_handle;
+		it->it_remote_lock_mode = it->it_lock_mode;
 	}
 
-	it->d.lustre.it_lock_handle = plock.cookie;
-	it->d.lustre.it_lock_mode = pmode;
+	it->it_lock_handle = plock.cookie;
+	it->it_lock_mode = pmode;
 
 out_free_op_data:
 	kfree(op_data);

@@ -197,9 +197,9 @@ static int lmv_intent_open(struct obd_export *exp, struct md_op_data *op_data,
 	 * Nothing is found, do not access body->fid1 as it is zero and thus
 	 * pointless.
 	 */
-	if ((it->d.lustre.it_disposition & DISP_LOOKUP_NEG) &&
-	    !(it->d.lustre.it_disposition & DISP_OPEN_CREATE) &&
-	    !(it->d.lustre.it_disposition & DISP_OPEN_OPEN))
+	if ((it->it_disposition & DISP_LOOKUP_NEG) &&
+	    !(it->it_disposition & DISP_OPEN_CREATE) &&
+	    !(it->it_disposition & DISP_OPEN_OPEN))
 		return rc;
 
 	body = req_capsule_server_get(&(*reqp)->rq_pill, &RMF_MDT_BODY);

index ab4f4fb..eb675fa 100644
@@ -1679,7 +1679,7 @@ lmv_enqueue_remote(struct obd_export *exp, struct ldlm_enqueue_info *einfo,
 		   struct lustre_handle *lockh, void *lmm, int lmmsize,
 		   __u64 extra_lock_flags)
 {
-	struct ptlrpc_request      *req = it->d.lustre.it_data;
+	struct ptlrpc_request      *req = it->it_data;
 	struct obd_device	  *obd = exp->exp_obd;
 	struct lmv_obd	     *lmv = &obd->u.lmv;
 	struct lustre_handle	plock;

@@ -1701,11 +1701,11 @@ lmv_enqueue_remote(struct obd_export *exp, struct ldlm_enqueue_info *einfo,
 	/*
 	 * We got LOOKUP lock, but we really need attrs.
 	 */
-	pmode = it->d.lustre.it_lock_mode;
+	pmode = it->it_lock_mode;
 	LASSERT(pmode != 0);
 	memcpy(&plock, lockh, sizeof(plock));
-	it->d.lustre.it_lock_mode = 0;
-	it->d.lustre.it_data = NULL;
+	it->it_lock_mode = 0;
+	it->it_data = NULL;
 	fid1 = body->fid1;
 
 	ptlrpc_req_finished(req);

212 lines not on this page · raw message

index f371e1d..7f5dfb0 100644
@@ -661,7 +661,7 @@ int mdc_set_open_replay_data(struct obd_export *exp,
 	struct md_open_data   *mod;
 	struct mdt_rec_create *rec;
 	struct mdt_body       *body;
-	struct ptlrpc_request *open_req = it->d.lustre.it_data;
+	struct ptlrpc_request *open_req = it->it_data;
 	struct obd_import     *imp = open_req->rq_import;
 
 	if (!open_req->rq_replay)

index 41c03d7..3aed810 100644
@@ -50,4 +50,19 @@ struct lookup_intent {
 	unsigned int    it_lock_set:1;
 };
 
+static inline int it_disposition(struct lookup_intent *it, int flag)
+{
+	return it->it_disposition & flag;
+}
+
+static inline void it_set_disposition(struct lookup_intent *it, int flag)
+{
+	it->it_disposition |= flag;
+}
+
+static inline void it_clear_disposition(struct lookup_intent *it, int flag)
+{
+	it->it_disposition &= ~flag;
+}
+
 #endif

index 0ef4226..fa62b95 100644
@@ -185,9 +185,6 @@ struct mdc_cache_waiter {
 };
 
 /* mdc/mdc_locks.c */
-int it_disposition(struct lookup_intent *it, int flag);
-void it_clear_disposition(struct lookup_intent *it, int flag);
-void it_set_disposition(struct lookup_intent *it, int flag);
 int it_open_error(int phase, struct lookup_intent *it);
 
 static inline bool cl_is_lov_delay_create(unsigned int flags)

index 5da2a1e..c43b3a2 100644
@@ -50,24 +50,6 @@ struct mdc_getattr_args {
 	struct ldlm_enqueue_info    *ga_einfo;
 };
 
-int it_disposition(struct lookup_intent *it, int flag)
-{
-	return it->it_disposition & flag;
-}
-EXPORT_SYMBOL(it_disposition);
-
-void it_set_disposition(struct lookup_intent *it, int flag)
-{
-	it->it_disposition |= flag;
-}
-EXPORT_SYMBOL(it_set_disposition);
-
-void it_clear_disposition(struct lookup_intent *it, int flag)
-{
-	it->it_disposition &= ~flag;
-}
-EXPORT_SYMBOL(it_clear_disposition);
-
 int it_open_error(int phase, struct lookup_intent *it)
 {
 	if (it_disposition(it, DISP_OPEN_LEASE)) {

index 3aed810..ed2b6c6 100644
@@ -46,7 +46,7 @@ struct lookup_intent {
 	int		it_lock_mode;
 	int		it_remote_lock_mode;
 	__u64	   it_remote_lock_handle;
-	void	   *it_data;
+	struct ptlrpc_request *it_request;
 	unsigned int    it_lock_set:1;
 };
 

index c5789f7..d964f4f 100644
@@ -233,13 +233,13 @@ void ll_intent_release(struct lookup_intent *it)
 	ll_intent_drop_lock(it);
 	/* We are still holding extra reference on a request, need to free it */
 	if (it_disposition(it, DISP_ENQ_OPEN_REF))
-		ptlrpc_req_finished(it->it_data); /* ll_file_open */
+		ptlrpc_req_finished(it->it_request); /* ll_file_open */
 
 	if (it_disposition(it, DISP_ENQ_CREATE_REF)) /* create rec */
-		ptlrpc_req_finished(it->it_data);
+		ptlrpc_req_finished(it->it_request);
 
 	it->it_disposition = 0;
-	it->it_data = NULL;
+	it->it_request = NULL;
 }
 
 void ll_invalidate_aliases(struct inode *inode)

index a62df87..f0eb64b 100644
@@ -362,7 +362,7 @@ struct page *ll_get_dir_page(struct inode *dir, __u64 hash,
 
 		ll_finish_md_op_data(op_data);
 
-		request = (struct ptlrpc_request *)it.it_data;
+		request = (struct ptlrpc_request *)it.it_request;
 		if (request)
 			ptlrpc_req_finished(request);
 		if (rc < 0) {

index 92fab63..a188366 100644
@@ -476,10 +476,9 @@ void ll_ioepoch_open(struct ll_inode_info *lli, __u64 ioepoch)
 static int ll_och_fill(struct obd_export *md_exp, struct lookup_intent *it,
 		       struct obd_client_handle *och)
 {
-	struct ptlrpc_request *req = it->it_data;
 	struct mdt_body *body;
 
-	body = req_capsule_server_get(&req->rq_pill, &RMF_MDT_BODY);
+	body = req_capsule_server_get(&it->it_request->rq_pill, &RMF_MDT_BODY);
 	och->och_fh = body->handle;
 	och->och_fid = body->fid1;
 	och->och_lease_handle.cookie = it->it_lock_handle;

@@ -500,7 +499,6 @@ static int ll_local_open(struct file *file, struct lookup_intent *it,
 	LASSERT(fd);
 
 	if (och) {
-		struct ptlrpc_request *req = it->it_data;
 		struct mdt_body *body;
 		int rc;
 

@@ -508,7 +506,8 @@ static int ll_local_open(struct file *file, struct lookup_intent *it,
 		if (rc != 0)
 			return rc;
 
-		body = req_capsule_server_get(&req->rq_pill, &RMF_MDT_BODY);
+		body = req_capsule_server_get(&it->it_request->rq_pill,
+					      &RMF_MDT_BODY);
 		ll_ioepoch_open(lli, body->ioepoch);
 	}
 

@@ -725,7 +724,7 @@ out_openerr:
 	}
 
 	if (it && it_disposition(it, DISP_ENQ_OPEN_REF)) {
-		ptlrpc_req_finished(it->it_data);
+		ptlrpc_req_finished(it->it_request);
 		it_clear_disposition(it, DISP_ENQ_OPEN_REF);
 	}
 

@@ -1413,7 +1412,7 @@ out_unlock:
 out:
 	return rc;
 out_req_free:
-	ptlrpc_req_finished((struct ptlrpc_request *)oit.it_data);
+	ptlrpc_req_finished((struct ptlrpc_request *)oit.it_request);
 	goto out;
 }
 

@@ -1701,7 +1700,7 @@ int ll_release_openhandle(struct inode *inode, struct lookup_intent *it)
 out:
 	/* this one is in place of ll_file_open */
 	if (it_disposition(it, DISP_ENQ_OPEN_REF)) {
-		ptlrpc_req_finished(it->it_data);
+		ptlrpc_req_finished(it->it_request);
 		it_clear_disposition(it, DISP_ENQ_OPEN_REF);
 	}
 	return rc;

@@ -3610,8 +3609,8 @@ again:
 
 	rc = md_enqueue(sbi->ll_md_exp, &einfo, &it, op_data, &lockh,
 			NULL, 0, NULL, 0);
-	ptlrpc_req_finished(it.it_data);
-	it.it_data = NULL;
+	ptlrpc_req_finished(it.it_request);
+	it.it_request = NULL;
 
 	ll_finish_md_op_data(op_data);
 

index 7a6da02..3664bfd 100644
@@ -659,7 +659,7 @@ static struct inode *ll_create_node(struct inode *dir, struct lookup_intent *it)
 	LASSERT(it && it->it_disposition);
 
 	LASSERT(it_disposition(it, DISP_ENQ_CREATE_REF));
-	request = it->it_data;
+	request = it->it_request;
 	it_clear_disposition(it, DISP_ENQ_CREATE_REF);
 	rc = ll_prep_inode(&inode, request, dir->i_sb, it);
 	if (rc) {

index 0d19645..8089da8 100644
@@ -315,7 +315,7 @@ static int ll_xattr_find_get_lock(struct inode *inode,
 		return rc;
 	}
 
-	*req = (struct ptlrpc_request *)oit->it_data;
+	*req = oit->it_request;
 out:
 	down_write(&lli->lli_xattrs_list_rwsem);
 	mutex_unlock(&lli->lli_xattrs_enq_lock);

index b3cff23..2f58fda 100644
@@ -84,7 +84,7 @@ static int lmv_intent_remote(struct obd_export *exp, void *lmm,
 	if (pmode) {
 		plock.cookie = it->it_lock_handle;
 		it->it_lock_mode = 0;
-		it->it_data = NULL;
+		it->it_request = NULL;
 	}
 
 	LASSERT(fid_is_sane(&body->fid1));

index eb675fa..210ed1e 100644
@@ -1679,7 +1679,7 @@ lmv_enqueue_remote(struct obd_export *exp, struct ldlm_enqueue_info *einfo,
 		   struct lustre_handle *lockh, void *lmm, int lmmsize,
 		   __u64 extra_lock_flags)
 {
-	struct ptlrpc_request      *req = it->it_data;
+	struct ptlrpc_request      *req = it->it_request;
 	struct obd_device	  *obd = exp->exp_obd;
 	struct lmv_obd	     *lmv = &obd->u.lmv;
 	struct lustre_handle	plock;

@@ -1705,7 +1705,7 @@ lmv_enqueue_remote(struct obd_export *exp, struct ldlm_enqueue_info *einfo,
 	LASSERT(pmode != 0);
 	memcpy(&plock, lockh, sizeof(plock));
 	it->it_lock_mode = 0;
-	it->it_data = NULL;
+	it->it_request = NULL;
 	fid1 = body->fid1;
 
 	ptlrpc_req_finished(req);

index c43b3a2..c1f8da6 100644
@@ -570,7 +570,7 @@ static int mdc_finish_enqueue(struct obd_export *exp,
 	it->it_status = (int)lockrep->lock_policy_res2;
 	it->it_lock_mode = einfo->ei_mode;
 	it->it_lock_handle = lockh->cookie;
-	it->it_data = req;
+	it->it_request = req;
 
 	/* Technically speaking rq_transno must already be zero if
 	 * it_status is in error, so the check is a bit redundant

@@ -902,7 +902,7 @@ resend:
 
 		it->it_lock_handle = 0;
 		it->it_lock_mode = 0;
-		it->it_data = NULL;
+		it->it_request = NULL;
 	}
 
 	return rc;

@@ -1165,7 +1165,7 @@ int mdc_intent_lock(struct obd_export *exp, struct md_op_data *op_data,
 	if (rc < 0)
 		return rc;
 
-	*reqp = it->it_data;
+	*reqp = it->it_request;
 	rc = mdc_finish_intent_lock(exp, *reqp, op_data, it, &lockh);
 	return rc;
 }

index 7f5dfb0..2622eb3 100644
@@ -661,7 +661,7 @@ int mdc_set_open_replay_data(struct obd_export *exp,
 	struct md_open_data   *mod;
 	struct mdt_rec_create *rec;
 	struct mdt_body       *body;
-	struct ptlrpc_request *open_req = it->it_data;
+	struct ptlrpc_request *open_req = it->it_request;
 	struct obd_import     *imp = open_req->rq_import;
 
 	if (!open_req->rq_replay)

index 63085a0..60051a5 100644
@@ -1073,7 +1073,7 @@ void ldlm_lock2handle(const struct ldlm_lock *lock,
 struct ldlm_lock *__ldlm_handle2lock(const struct lustre_handle *, __u64 flags);
 void ldlm_cancel_callback(struct ldlm_lock *);
 int ldlm_lock_remove_from_lru(struct ldlm_lock *);
-int ldlm_lock_set_data(struct lustre_handle *, void *);
+int ldlm_lock_set_data(const struct lustre_handle *lockh, void *data);
 
 /**
  * Obtain a lock reference by its handle.

@@ -1162,10 +1162,10 @@ do {					    \
 struct ldlm_lock *ldlm_lock_get(struct ldlm_lock *lock);
 void ldlm_lock_put(struct ldlm_lock *lock);
 void ldlm_lock2desc(struct ldlm_lock *lock, struct ldlm_lock_desc *desc);
-void ldlm_lock_addref(struct lustre_handle *lockh, __u32 mode);
-int  ldlm_lock_addref_try(struct lustre_handle *lockh, __u32 mode);
-void ldlm_lock_decref(struct lustre_handle *lockh, __u32 mode);
-void ldlm_lock_decref_and_cancel(struct lustre_handle *lockh, __u32 mode);
+void ldlm_lock_addref(const struct lustre_handle *lockh, __u32 mode);
+int  ldlm_lock_addref_try(const struct lustre_handle *lockh, __u32 mode);
+void ldlm_lock_decref(const struct lustre_handle *lockh, __u32 mode);
+void ldlm_lock_decref_and_cancel(const struct lustre_handle *lockh, __u32 mode);
 void ldlm_lock_fail_match_locked(struct ldlm_lock *lock);
 void ldlm_lock_allow_match(struct ldlm_lock *lock);
 void ldlm_lock_allow_match_locked(struct ldlm_lock *lock);

@@ -1174,10 +1174,10 @@ enum ldlm_mode ldlm_lock_match(struct ldlm_namespace *ns, __u64 flags,
 			       enum ldlm_type type, ldlm_policy_data_t *,
 			       enum ldlm_mode mode, struct lustre_handle *,
 			       int unref);
-enum ldlm_mode ldlm_revalidate_lock_handle(struct lustre_handle *lockh,
+enum ldlm_mode ldlm_revalidate_lock_handle(const struct lustre_handle *lockh,
 					   __u64 *bits);
 void ldlm_lock_cancel(struct ldlm_lock *lock);
-void ldlm_lock_dump_handle(int level, struct lustre_handle *);
+void ldlm_lock_dump_handle(int level, const struct lustre_handle *);
 void ldlm_unlink_lock_skiplist(struct ldlm_lock *req);
 
 /* resource.c */

@@ -1251,9 +1251,9 @@ int ldlm_cli_enqueue_fini(struct obd_export *exp, struct ptlrpc_request *req,
 			  enum ldlm_type type, __u8 with_policy,
 			  enum ldlm_mode mode,
 			  __u64 *flags, void *lvb, __u32 lvb_len,
-			  struct lustre_handle *lockh, int rc);
+			  const struct lustre_handle *lockh, int rc);
 int ldlm_cli_update_pool(struct ptlrpc_request *req);
-int ldlm_cli_cancel(struct lustre_handle *lockh,
+int ldlm_cli_cancel(const struct lustre_handle *lockh,
 		    enum ldlm_cancel_flags cancel_flags);
 int ldlm_cli_cancel_unused(struct ldlm_namespace *, const struct ldlm_res_id *,
 			   enum ldlm_cancel_flags flags, void *opaque);

index b7254eb..a5993f7 100644
@@ -658,7 +658,7 @@ static void ldlm_add_ast_work_item(struct ldlm_lock *lock,
  * r/w reference type is determined by \a mode
  * Calls ldlm_lock_addref_internal.
  */
-void ldlm_lock_addref(struct lustre_handle *lockh, __u32 mode)
+void ldlm_lock_addref(const struct lustre_handle *lockh, __u32 mode)
 {
 	struct ldlm_lock *lock;
 

@@ -700,7 +700,7 @@ void ldlm_lock_addref_internal_nolock(struct ldlm_lock *lock, __u32 mode)
  *
  * \retval -EAGAIN lock is being canceled.
  */
-int ldlm_lock_addref_try(struct lustre_handle *lockh, __u32 mode)
+int ldlm_lock_addref_try(const struct lustre_handle *lockh, __u32 mode)
 {
 	struct ldlm_lock *lock;
 	int	       result;

@@ -832,7 +832,7 @@ void ldlm_lock_decref_internal(struct ldlm_lock *lock, __u32 mode)
 /**
  * Decrease reader/writer refcount for LDLM lock with handle \a lockh
  */
-void ldlm_lock_decref(struct lustre_handle *lockh, __u32 mode)
+void ldlm_lock_decref(const struct lustre_handle *lockh, __u32 mode)
 {
 	struct ldlm_lock *lock = __ldlm_handle2lock(lockh, 0);
 

@@ -849,7 +849,7 @@ EXPORT_SYMBOL(ldlm_lock_decref);
  *
  * Typical usage is for GROUP locks which we cannot allow to be cached.
  */
-void ldlm_lock_decref_and_cancel(struct lustre_handle *lockh, __u32 mode)
+void ldlm_lock_decref_and_cancel(const struct lustre_handle *lockh, __u32 mode)
 {
 	struct ldlm_lock *lock = __ldlm_handle2lock(lockh, 0);
 

@@ -1318,7 +1318,7 @@ enum ldlm_mode ldlm_lock_match(struct ldlm_namespace *ns, __u64 flags,
 }
 EXPORT_SYMBOL(ldlm_lock_match);
 
-enum ldlm_mode ldlm_revalidate_lock_handle(struct lustre_handle *lockh,
+enum ldlm_mode ldlm_revalidate_lock_handle(const struct lustre_handle *lockh,
 					   __u64 *bits)
 {
 	struct ldlm_lock *lock;

@@ -1849,7 +1849,7 @@ EXPORT_SYMBOL(ldlm_lock_cancel);
 /**
  * Set opaque data into the lock that only makes sense to upper layer.
  */
-int ldlm_lock_set_data(struct lustre_handle *lockh, void *data)
+int ldlm_lock_set_data(const struct lustre_handle *lockh, void *data)
 {
 	struct ldlm_lock *lock = ldlm_handle2lock(lockh);
 	int rc = -EINVAL;

@@ -1875,7 +1875,7 @@ struct export_cl_data {
  *
  * Used when printing all locks on a resource for debug purposes.
  */
-void ldlm_lock_dump_handle(int level, struct lustre_handle *lockh)
+void ldlm_lock_dump_handle(int level, const struct lustre_handle *lockh)
 {
 	struct ldlm_lock *lock;
 

index 8294703..821939f 100644
@@ -499,7 +499,7 @@ static int ldlm_handle_setinfo(struct ptlrpc_request *req)
 
 static inline void ldlm_callback_errmsg(struct ptlrpc_request *req,
 					const char *msg, int rc,
-					struct lustre_handle *handle)
+					const struct lustre_handle *handle)
 {
 	DEBUG_REQ((req->rq_no_reply || rc) ? D_WARNING : D_DLMTRACE, req,
 		  "%s: [nid %s] [rc %d] [lock %#llx]",

index d3a376e..af487f9 100644
@@ -336,7 +336,7 @@ int ldlm_cli_enqueue_fini(struct obd_export *exp, struct ptlrpc_request *req,
 			  enum ldlm_type type, __u8 with_policy,
 			  enum ldlm_mode mode,
 			  __u64 *flags, void *lvb, __u32 lvb_len,
-			  struct lustre_handle *lockh, int rc)
+			  const struct lustre_handle *lockh, int rc)
 {
 	struct ldlm_namespace *ns = exp->exp_obd->obd_namespace;
 	int is_replay = *flags & LDLM_FL_REPLAY;

@@ -1023,7 +1023,7 @@ EXPORT_SYMBOL(ldlm_cli_update_pool);
  *
  * Lock must not have any readers or writers by this time.
  */
-int ldlm_cli_cancel(struct lustre_handle *lockh,
+int ldlm_cli_cancel(const struct lustre_handle *lockh,
 		    enum ldlm_cancel_flags cancel_flags)
 {
 	struct obd_export *exp;

index 8a508ed..f6be105 100644
@@ -96,7 +96,8 @@ int cl_ocd_update(struct obd_device *host,
 	__u64 flags;
 	int   result;
 
-	if (!strcmp(watched->obd_type->typ_name, LUSTRE_OSC_NAME)) {
+	if (!strcmp(watched->obd_type->typ_name, LUSTRE_OSC_NAME) &&
+	    watched->obd_set_up && !watched->obd_stopping) {
 		cli = &watched->u.cli;
 		lco = owner;
 		flags = cli->cl_import->imp_connect_data.ocd_connect_flags;

@@ -111,9 +112,10 @@ int cl_ocd_update(struct obd_device *host,
 		mutex_unlock(&lco->lco_lock);
 		result = 0;
 	} else {
-		CERROR("unexpected notification from %s %s!\n",
+		CERROR("unexpected notification from %s %s (setup:%d,stopping:%d)!\n",
 		       watched->obd_type->typ_name,
-		       watched->obd_name);
+		       watched->obd_name, watched->obd_set_up,
+		       watched->obd_stopping);
 		result = -EINVAL;
 	}
 	return result;

index 2703113..143bd76 100644
@@ -467,6 +467,18 @@ void mdc_close_pack(struct ptlrpc_request *req, struct md_op_data *op_data)
 	rec = req_capsule_client_get(&req->rq_pill, &RMF_REC_REINT);
 
 	mdc_setattr_pack_rec(rec, op_data);
+	/*
+	 * The client will zero out local timestamps when losing the IBITS lock
+	 * so any new RPC timestamps will update the client inode's timestamps.
+	 * There was a defect on the server side which allowed the atime to be
+	 * overwritten by a zeroed-out atime packed into the close RPC.
+	 *
+	 * Proactively clear the MDS_ATTR_ATIME flag in the RPC in this case
+	 * to avoid zeroing the atime on old unpatched servers.  See LU-8041.
+	 */
+	if (rec->sa_atime == 0)
+		rec->sa_valid &= ~MDS_ATTR_ATIME;
+
 	mdc_ioepoch_pack(epoch, op_data);
 	mdc_hsm_release_pack(req, op_data);
 }

index e32e43b..a585d22 100644
@@ -2525,12 +2525,14 @@ kiblnd_passive_connect(struct rdma_cm_id *cmid, void *priv, int priv_nob)
 	return 0;
 
  failed:
-	if (ni)
+	if (ni) {
 		lnet_ni_decref(ni);
+		rej.ibr_cp.ibcp_queue_depth =
+			kiblnd_msg_queue_size(version, ni);
+		rej.ibr_cp.ibcp_max_frags = kiblnd_rdma_frags(version, ni);
+	}
 
 	rej.ibr_version             = version;
-	rej.ibr_cp.ibcp_queue_depth = kiblnd_msg_queue_size(version, ni);
-	rej.ibr_cp.ibcp_max_frags = kiblnd_rdma_frags(version, ni);
 	kiblnd_reject(cmid, &rej);
 
 	return -ECONNREFUSED;

index 539fdd1..118e41d 100644
@@ -1971,7 +1971,13 @@ int ll_prep_inode(struct inode **inode, struct ptlrpc_request *req,
 		 * At this point server returns to client's same fid as client
 		 * generated for creating. So using ->fid1 is okay here.
 		 */
-		LASSERT(fid_is_sane(&md.body->fid1));
+		if (!fid_is_sane(&md.body->fid1)) {
+			CERROR("%s: Fid is insane " DFID "\n",
+			       ll_get_fsname(sb, NULL, 0),
+			       PFID(&md.body->fid1));
+			rc = -EINVAL;
+			goto out;
+		}
 
 		*inode = ll_iget(sb, cl_fid_build_ino(&md.body->fid1,
 					     sbi->ll_flags & LL_SBI_32BIT_API),

index a188366..6a5e8c7 100644
@@ -411,7 +411,19 @@ static int ll_intent_file_open(struct dentry *dentry, void *lmm,
 	 * parameters. No need for the open lock
 	 */
 	if (!lmm && lmmsize == 0) {
-		itp->it_flags |= MDS_OPEN_LOCK;
+		struct ll_dentry_data *ldd = ll_d2d(dentry);
+		/*
+		 * If we came via ll_iget_for_nfs, then we need to request
+		 * struct ll_dentry_data *ldd = ll_d2d(file->f_dentry);
+		 *
+		 * NB: when ldd is NULL, it must have come via normal
+		 * lookup path only, since ll_iget_for_nfs always calls
+		 * ll_d_init().
+		 */
+		if (ldd && ldd->lld_nfs_dentry) {
+			ldd->lld_nfs_dentry = 0;
+			itp->it_flags |= MDS_OPEN_LOCK;
+		}
 		if (itp->it_flags & FMODE_WRITE)
 			opc = LUSTRE_OPC_CREATE;
 	}

index 3692102..1d4e91e 100644
@@ -64,6 +64,7 @@ struct ll_dentry_data {
 	struct lookup_intent		*lld_it;
 	unsigned int			lld_sa_generation;
 	unsigned int			lld_invalid:1;
+	unsigned int			lld_nfs_dentry:1;
 	struct rcu_head			lld_rcu_head;
 };
 

index d7878e5..65972c8 100644
@@ -168,6 +168,24 @@ ll_iget_for_nfs(struct super_block *sb, struct lu_fid *fid, struct lu_fid *paren
 
 	/* N.B. d_obtain_alias() drops inode ref on error */
 	result = d_obtain_alias(inode);
+	if (!IS_ERR(result)) {
+		int rc;
+
+		rc = ll_d_init(result);
+		if (rc < 0) {
+			dput(result);
+			result = ERR_PTR(rc);
+		} else {
+			struct ll_dentry_data *ldd = ll_d2d(result);
+
+			/*
+			 * Need to signal to the ll_intent_file_open that
+			 * we came from NFS and so opencache needs to be
+			 * enabled for this one
+			 */
+			ldd->lld_nfs_dentry = 1;
+		}
+	}
 
 	return result;
 }

index d964f4f..581a63a 100644
@@ -302,6 +302,17 @@ static int ll_revalidate_dentry(struct dentry *dentry,
 {
 	struct inode *dir = d_inode(dentry->d_parent);
 
+	/* If this is intermediate component path lookup and we were able to get
+	 * to this dentry, then its lock has not been revoked and the
+	 * path component is valid.
+	 */
+	if (lookup_flags & LOOKUP_PARENT)
+		return 1;
+
+	/* Symlink - always valid as long as the dentry was found */
+	if (dentry->d_inode && S_ISLNK(dentry->d_inode->i_mode))
+		return 1;
+
 	/*
 	 * if open&create is set, talk to MDS to make sure file is created if
 	 * necessary, because we can't do this in ->open() later since that's

index f0eb64b..7e7425d 100644
@@ -1528,7 +1528,9 @@ skip_lmm:
 			st.st_atime   = body->atime;
 			st.st_mtime   = body->mtime;
 			st.st_ctime   = body->ctime;
-			st.st_ino     = inode->i_ino;
+			st.st_ino     = cl_fid_build_ino(&body->fid1,
+							 sbi->ll_flags &
+							 LL_SBI_32BIT_API);
 
 			lmdp = (struct lov_user_mds_data __user *)arg;
 			if (copy_to_user(&lmdp->lmd_st, &st, sizeof(st))) {

index 437c659..c8c3f1c 100644
@@ -62,7 +62,7 @@ struct osc_io {
 	/** super class */
 	struct cl_io_slice oi_cl;
 	/** true if this io is lockless. */
-	int		oi_lockless;
+	unsigned int		oi_lockless;
 	/** how many LRU pages are reserved for this IO */
 	int oi_lru_reserved;
 

index 9334349..536b868 100644
@@ -2246,7 +2246,7 @@ int osc_enqueue_base(struct obd_export *exp, struct ldlm_res_id *res_id,
 	struct lustre_handle lockh = { 0 };
 	struct ptlrpc_request *req = NULL;
 	int intent = *flags & LDLM_FL_HAS_INTENT;
-	__u64 match_lvb = agl ? 0 : LDLM_FL_LVB_READY;
+	__u64 match_flags = *flags;
 	enum ldlm_mode mode;
 	int rc;
 

@@ -2281,7 +2281,11 @@ int osc_enqueue_base(struct obd_export *exp, struct ldlm_res_id *res_id,
 	mode = einfo->ei_mode;
 	if (einfo->ei_mode == LCK_PR)
 		mode |= LCK_PW;
-	mode = ldlm_lock_match(obd->obd_namespace, *flags | match_lvb, res_id,
+	if (agl == 0)
+		match_flags |= LDLM_FL_LVB_READY;
+	if (intent != 0)
+		match_flags |= LDLM_FL_BLOCK_GRANTED;
+	mode = ldlm_lock_match(obd->obd_namespace, match_flags, res_id,
 			       einfo->ei_type, policy, mode, &lockh, 0);
 	if (mode) {
 		struct ldlm_lock *matched;