[linux-2.6-block.git] / drivers / staging / lustre / lustre / llite / glimpse.c

/*
 * GPL HEADER START
 *
 * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
 *
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License version 2 only,
 * as published by the Free Software Foundation.
 *
 * This program is distributed in the hope that it will be useful, but
 * WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
 * General Public License version 2 for more details (a copy is included
 * in the LICENSE file that accompanied this code).
 *
 * You should have received a copy of the GNU General Public License
 * version 2 along with this program; If not, see
 * http://www.sun.com/software/products/lustre/docs/GPLv2.pdf
 *
 * Please contact Sun Microsystems, Inc., 4150 Network Circle, Santa Clara,
 * CA 95054 USA or visit www.sun.com if you need additional information or
 * have any questions.
 *
 * GPL HEADER END
 */
/*
 * Copyright (c) 2008, 2010, Oracle and/or its affiliates. All rights reserved.
 * Use is subject to license terms.
 *
 * Copyright (c) 2011, 2012, Intel Corporation.
 */
/*
 * This file is part of Lustre, http://www.lustre.org/
 * Lustre is a trademark of Sun Microsystems, Inc.
 *
 * glimpse code shared between vvp and liblustre (and other Lustre clients in
 * the future).
 *
 *   Author: Nikita Danilov <nikita.danilov@sun.com>
 *   Author: Oleg Drokin <oleg.drokin@sun.com>
 */

#include "../../include/linux/libcfs/libcfs.h"
#include "../include/obd_class.h"
#include "../include/obd_support.h"
#include "../include/obd.h"

#include "../include/lustre_dlm.h"
#include "../include/lustre_lite.h"
#include "../include/lustre_mdc.h"
#include <linux/pagemap.h>
#include <linux/file.h>

#include "../include/cl_object.h"
#include "../include/lclient.h"
#include "../llite/llite_internal.h"

static const struct cl_lock_descr whole_file = {
	.cld_start = 0,
	.cld_end   = CL_PAGE_EOF,
	.cld_mode  = CLM_READ
};

/*
 * Check whether file has possible unwriten pages.
 *
 * \retval 1    file is mmap-ed or has dirty pages
 *	 0    otherwise
 */
blkcnt_t dirty_cnt(struct inode *inode)
{
	blkcnt_t cnt = 0;
	struct ccc_object *vob = cl_inode2ccc(inode);
	void	      *results[1];

	if (inode->i_mapping)
		cnt += radix_tree_gang_lookup_tag(&inode->i_mapping->page_tree,
						  results, 0, 1,
						  PAGECACHE_TAG_DIRTY);
	if (cnt == 0 && atomic_read(&vob->cob_mmap_cnt) > 0)
		cnt = 1;

	return (cnt > 0) ? 1 : 0;
}

int cl_glimpse_lock(const struct lu_env *env, struct cl_io *io,
		    struct inode *inode, struct cl_object *clob, int agl)
{
	struct cl_lock_descr *descr = &ccc_env_info(env)->cti_descr;
	struct cl_inode_info *lli   = cl_i2info(inode);
	const struct lu_fid  *fid   = lu_object_fid(&clob->co_lu);
	struct ccc_io	*cio   = ccc_env_io(env);
	struct cl_lock       *lock;
	int result;

	result = 0;
	if (!(lli->lli_flags & LLIF_MDS_SIZE_LOCK)) {
		CDEBUG(D_DLMTRACE, "Glimpsing inode " DFID "\n", PFID(fid));
		if (lli->lli_has_smd) {
			/* NOTE: this looks like DLM lock request, but it may
			 *       not be one. Due to CEF_ASYNC flag (translated
			 *       to LDLM_FL_HAS_INTENT by osc), this is
			 *       glimpse request, that won't revoke any
			 *       conflicting DLM locks held. Instead,
			 *       ll_glimpse_callback() will be called on each
			 *       client holding a DLM lock against this file,
			 *       and resulting size will be returned for each
			 *       stripe. DLM lock on [0, EOF] is acquired only
			 *       if there were no conflicting locks. If there
			 *       were conflicting locks, enqueuing or waiting
			 *       fails with -ENAVAIL, but valid inode
			 *       attributes are returned anyway.
			 */
			*descr = whole_file;
			descr->cld_obj   = clob;
			descr->cld_mode  = CLM_PHANTOM;
			descr->cld_enq_flags = CEF_ASYNC | CEF_MUST;
			if (agl)
				descr->cld_enq_flags |= CEF_AGL;
			cio->cui_glimpse = 1;
			/*
			 * CEF_ASYNC is used because glimpse sub-locks cannot
			 * deadlock (because they never conflict with other
			 * locks) and, hence, can be enqueued out-of-order.
			 *
			 * CEF_MUST protects glimpse lock from conversion into
			 * a lockless mode.
			 */
			lock = cl_lock_request(env, io, descr, "glimpse",
					       current);
			cio->cui_glimpse = 0;

			if (!lock)
				return 0;

			if (IS_ERR(lock))
				return PTR_ERR(lock);

			LASSERT(agl == 0);
			result = cl_wait(env, lock);
			if (result == 0) {
				ll_merge_attr(env, inode);
				if (cl_isize_read(inode) > 0 &&
				    inode->i_blocks == 0) {
					/*
					 * LU-417: Add dirty pages block count
					 * lest i_blocks reports 0, some "cp" or
					 * "tar" may think it's a completely
					 * sparse file and skip it.
					 */
					inode->i_blocks = dirty_cnt(inode);
				}
				cl_unuse(env, lock);
			}
			cl_lock_release(env, lock, "glimpse", current);
		} else {
			CDEBUG(D_DLMTRACE, "No objects for inode\n");
			ll_merge_attr(env, inode);
		}
	}

	return result;
}

static int cl_io_get(struct inode *inode, struct lu_env **envout,
		     struct cl_io **ioout, int *refcheck)
{
	struct lu_env	  *env;
	struct cl_io	   *io;
	struct cl_inode_info   *lli = cl_i2info(inode);
	struct cl_object       *clob = lli->lli_clob;
	int result;

	if (S_ISREG(cl_inode_mode(inode))) {
		env = cl_env_get(refcheck);
		if (!IS_ERR(env)) {
			io = ccc_env_thread_io(env);
			io->ci_obj = clob;
			*envout = env;
			*ioout  = io;
			result = 1;
		} else {
			result = PTR_ERR(env);
		}
	} else {
		result = 0;
	}
	return result;
}

int cl_glimpse_size0(struct inode *inode, int agl)
{
	/*
	 * We don't need ast_flags argument to cl_glimpse_size(), because
	 * osc_lock_enqueue() takes care of the possible deadlock that said
	 * argument was introduced to avoid.
	 */
	/*
	 * XXX but note that ll_file_seek() passes LDLM_FL_BLOCK_NOWAIT to
	 * cl_glimpse_size(), which doesn't make sense: glimpse locks are not
	 * blocking anyway.
	 */
	struct lu_env	  *env = NULL;
	struct cl_io	   *io  = NULL;
	int		     result;
	int		     refcheck;

	result = cl_io_get(inode, &env, &io, &refcheck);
	if (result > 0) {
again:
		io->ci_verify_layout = 1;
		result = cl_io_init(env, io, CIT_MISC, io->ci_obj);
		if (result > 0)
			/*
			 * nothing to do for this io. This currently happens
			 * when stripe sub-object's are not yet created.
			 */
			result = io->ci_result;
		else if (result == 0)
			result = cl_glimpse_lock(env, io, inode, io->ci_obj,
						 agl);

		OBD_FAIL_TIMEOUT(OBD_FAIL_GLIMPSE_DELAY, 2);
		cl_io_fini(env, io);
		if (unlikely(io->ci_need_restart))
			goto again;
		cl_env_put(env, &refcheck);
	}
	return result;
}

int cl_local_size(struct inode *inode)
{
	struct lu_env	   *env = NULL;
	struct cl_io	    *io  = NULL;
	struct ccc_thread_info  *cti;
	struct cl_object	*clob;
	struct cl_lock_descr    *descr;
	struct cl_lock	  *lock;
	int		      result;
	int		      refcheck;

	if (!cl_i2info(inode)->lli_has_smd)
		return 0;

	result = cl_io_get(inode, &env, &io, &refcheck);
	if (result <= 0)
		return result;

	clob = io->ci_obj;
	result = cl_io_init(env, io, CIT_MISC, clob);
	if (result > 0) {
		result = io->ci_result;
	} else if (result == 0) {
		cti = ccc_env_info(env);
		descr = &cti->cti_descr;

		*descr = whole_file;
		descr->cld_obj = clob;
		lock = cl_lock_peek(env, io, descr, "localsize", current);
		if (lock) {
			ll_merge_attr(env, inode);
			cl_unuse(env, lock);
			cl_lock_release(env, lock, "localsize", current);
			result = 0;
		} else {
			result = -ENODATA;
		}
	}
	cl_io_fini(env, io);
	cl_env_put(env, &refcheck);
	return result;
}
Commit	Line	Data
d7e09d03 PT	1	/*
	2	* GPL HEADER START
	3	*
	4	* DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
	5	*
	6	* This program is free software; you can redistribute it and/or modify
	7	* it under the terms of the GNU General Public License version 2 only,
	8	* as published by the Free Software Foundation.
	9	*
	10	* This program is distributed in the hope that it will be useful, but
	11	* WITHOUT ANY WARRANTY; without even the implied warranty of
	12	* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
	13	* General Public License version 2 for more details (a copy is included
	14	* in the LICENSE file that accompanied this code).
	15	*
	16	* You should have received a copy of the GNU General Public License
	17	* version 2 along with this program; If not, see
	18	* http://www.sun.com/software/products/lustre/docs/GPLv2.pdf
	19	*
	20	* Please contact Sun Microsystems, Inc., 4150 Network Circle, Santa Clara,
	21	* CA 95054 USA or visit www.sun.com if you need additional information or
	22	* have any questions.
	23	*
	24	* GPL HEADER END
	25	*/
	26	/*
	27	* Copyright (c) 2008, 2010, Oracle and/or its affiliates. All rights reserved.
	28	* Use is subject to license terms.
	29	*
	30	* Copyright (c) 2011, 2012, Intel Corporation.
	31	*/
	32	/*
	33	* This file is part of Lustre, http://www.lustre.org/
	34	* Lustre is a trademark of Sun Microsystems, Inc.
	35	*
	36	* glimpse code shared between vvp and liblustre (and other Lustre clients in
	37	* the future).
	38	*
	39	* Author: Nikita Danilov <nikita.danilov@sun.com>
	40	* Author: Oleg Drokin <oleg.drokin@sun.com>
	41	*/
	42
9fdaf8c0	43	#include "../../include/linux/libcfs/libcfs.h"
67a235f5 GKH	44	#include "../include/obd_class.h"
	45	#include "../include/obd_support.h"
	46	#include "../include/obd.h"
d7e09d03	47
67a235f5 GKH	48	#include "../include/lustre_dlm.h"
	49	#include "../include/lustre_lite.h"
	50	#include "../include/lustre_mdc.h"
	51	#include <linux/pagemap.h>
	52	#include <linux/file.h>
d7e09d03	53
67a235f5 GKH	54	#include "../include/cl_object.h"
	55	#include "../include/lclient.h"
	56	#include "../llite/llite_internal.h"
d7e09d03 PT	57
	58	static const struct cl_lock_descr whole_file = {
	59	.cld_start = 0,
	60	.cld_end = CL_PAGE_EOF,
	61	.cld_mode = CLM_READ
	62	};
	63
	64	/*
	65	* Check whether file has possible unwriten pages.
	66	*
	67	* \retval 1 file is mmap-ed or has dirty pages
	68	* 0 otherwise
	69	*/
	70	blkcnt_t dirty_cnt(struct inode *inode)
	71	{
	72	blkcnt_t cnt = 0;
	73	struct ccc_object *vob = cl_inode2ccc(inode);
	74	void *results[1];
	75
03a7fc24	76	if (inode->i_mapping)
d7e09d03 PT	77	cnt += radix_tree_gang_lookup_tag(&inode->i_mapping->page_tree,
	78	results, 0, 1,
	79	PAGECACHE_TAG_DIRTY);
	80	if (cnt == 0 && atomic_read(&vob->cob_mmap_cnt) > 0)
	81	cnt = 1;
	82
	83	return (cnt > 0) ? 1 : 0;
	84	}
	85
	86	int cl_glimpse_lock(const struct lu_env env, struct cl_io io,
	87	struct inode inode, struct cl_object clob, int agl)
	88	{
	89	struct cl_lock_descr *descr = &ccc_env_info(env)->cti_descr;
	90	struct cl_inode_info *lli = cl_i2info(inode);
	91	const struct lu_fid *fid = lu_object_fid(&clob->co_lu);
	92	struct ccc_io *cio = ccc_env_io(env);
	93	struct cl_lock *lock;
	94	int result;
	95
d7e09d03 PT	96	result = 0;
d7e09d03 PT	97	if (!(lli->lli_flags & LLIF_MDS_SIZE_LOCK)) {
a7d516d6	98	CDEBUG(D_DLMTRACE, "Glimpsing inode " DFID "\n", PFID(fid));
d7e09d03 PT	99	if (lli->lli_has_smd) {
	100	/* NOTE: this looks like DLM lock request, but it may
	101	* not be one. Due to CEF_ASYNC flag (translated
	102	* to LDLM_FL_HAS_INTENT by osc), this is
	103	* glimpse request, that won't revoke any
	104	* conflicting DLM locks held. Instead,
	105	* ll_glimpse_callback() will be called on each
	106	* client holding a DLM lock against this file,
	107	* and resulting size will be returned for each
	108	* stripe. DLM lock on [0, EOF] is acquired only
	109	* if there were no conflicting locks. If there
	110	* were conflicting locks, enqueuing or waiting
	111	* fails with -ENAVAIL, but valid inode
ec9a1ac2 OD	112	* attributes are returned anyway.
ec9a1ac2 OD	113	*/
d7e09d03 PT	114	*descr = whole_file;
	115	descr->cld_obj = clob;
	116	descr->cld_mode = CLM_PHANTOM;
	117	descr->cld_enq_flags = CEF_ASYNC \| CEF_MUST;
	118	if (agl)
	119	descr->cld_enq_flags \|= CEF_AGL;
	120	cio->cui_glimpse = 1;
	121	/*
	122	* CEF_ASYNC is used because glimpse sub-locks cannot
	123	* deadlock (because they never conflict with other
	124	* locks) and, hence, can be enqueued out-of-order.
	125	*
	126	* CEF_MUST protects glimpse lock from conversion into
	127	* a lockless mode.
	128	*/
	129	lock = cl_lock_request(env, io, descr, "glimpse",
	130	current);
	131	cio->cui_glimpse = 0;
	132
03a7fc24	133	if (!lock)
0a3bdb00	134	return 0;
d7e09d03 PT	135
d7e09d03 PT	136	if (IS_ERR(lock))
0a3bdb00	137	return PTR_ERR(lock);
d7e09d03 PT	138
	139	LASSERT(agl == 0);
	140	result = cl_wait(env, lock);
	141	if (result == 0) {
d2995737	142	ll_merge_attr(env, inode);
d7e09d03 PT	143	if (cl_isize_read(inode) > 0 &&
	144	inode->i_blocks == 0) {
	145	/*
	146	* LU-417: Add dirty pages block count
	147	* lest i_blocks reports 0, some "cp" or
	148	* "tar" may think it's a completely
	149	* sparse file and skip it.
	150	*/
	151	inode->i_blocks = dirty_cnt(inode);
	152	}
	153	cl_unuse(env, lock);
	154	}
	155	cl_lock_release(env, lock, "glimpse", current);
	156	} else {
	157	CDEBUG(D_DLMTRACE, "No objects for inode\n");
d2995737	158	ll_merge_attr(env, inode);
d7e09d03 PT	159	}
	160	}
	161
0a3bdb00	162	return result;
d7e09d03 PT	163	}
	164
	165	static int cl_io_get(struct inode inode, struct lu_env *envout,
	166	struct cl_io *ioout, int refcheck)
	167	{
	168	struct lu_env *env;
	169	struct cl_io *io;
	170	struct cl_inode_info *lli = cl_i2info(inode);
	171	struct cl_object *clob = lli->lli_clob;
	172	int result;
	173
	174	if (S_ISREG(cl_inode_mode(inode))) {
	175	env = cl_env_get(refcheck);
	176	if (!IS_ERR(env)) {
	177	io = ccc_env_thread_io(env);
	178	io->ci_obj = clob;
	179	*envout = env;
	180	*ioout = io;
df47bd43	181	result = 1;
a7d516d6	182	} else {
d7e09d03	183	result = PTR_ERR(env);
a7d516d6 JH	184	}
a7d516d6 JH	185	} else {
d7e09d03	186	result = 0;
a7d516d6	187	}
d7e09d03 PT	188	return result;
	189	}
	190
	191	int cl_glimpse_size0(struct inode *inode, int agl)
	192	{
	193	/*
	194	* We don't need ast_flags argument to cl_glimpse_size(), because
	195	* osc_lock_enqueue() takes care of the possible deadlock that said
	196	* argument was introduced to avoid.
	197	*/
	198	/*
	199	* XXX but note that ll_file_seek() passes LDLM_FL_BLOCK_NOWAIT to
	200	* cl_glimpse_size(), which doesn't make sense: glimpse locks are not
	201	* blocking anyway.
	202	*/
	203	struct lu_env *env = NULL;
	204	struct cl_io *io = NULL;
	205	int result;
	206	int refcheck;
	207
d7e09d03 PT	208	result = cl_io_get(inode, &env, &io, &refcheck);
d7e09d03 PT	209	if (result > 0) {
641cff77	210	again:
d7e09d03 PT	211	io->ci_verify_layout = 1;
	212	result = cl_io_init(env, io, CIT_MISC, io->ci_obj);
	213	if (result > 0)
	214	/*
	215	* nothing to do for this io. This currently happens
	216	* when stripe sub-object's are not yet created.
	217	*/
	218	result = io->ci_result;
	219	else if (result == 0)
	220	result = cl_glimpse_lock(env, io, inode, io->ci_obj,
	221	agl);
	222
	223	OBD_FAIL_TIMEOUT(OBD_FAIL_GLIMPSE_DELAY, 2);
	224	cl_io_fini(env, io);
	225	if (unlikely(io->ci_need_restart))
	226	goto again;
	227	cl_env_put(env, &refcheck);
	228	}
0a3bdb00	229	return result;
d7e09d03 PT	230	}
	231
	232	int cl_local_size(struct inode *inode)
	233	{
	234	struct lu_env *env = NULL;
	235	struct cl_io *io = NULL;
	236	struct ccc_thread_info *cti;
	237	struct cl_object *clob;
	238	struct cl_lock_descr *descr;
	239	struct cl_lock *lock;
	240	int result;
	241	int refcheck;
	242
d7e09d03	243	if (!cl_i2info(inode)->lli_has_smd)
0a3bdb00	244	return 0;
d7e09d03 PT	245
	246	result = cl_io_get(inode, &env, &io, &refcheck);
	247	if (result <= 0)
0a3bdb00	248	return result;
d7e09d03 PT	249
	250	clob = io->ci_obj;
	251	result = cl_io_init(env, io, CIT_MISC, clob);
a7d516d6	252	if (result > 0) {
d7e09d03	253	result = io->ci_result;
a7d516d6	254	} else if (result == 0) {
d7e09d03 PT	255	cti = ccc_env_info(env);
	256	descr = &cti->cti_descr;
	257
	258	*descr = whole_file;
	259	descr->cld_obj = clob;
	260	lock = cl_lock_peek(env, io, descr, "localsize", current);
03a7fc24	261	if (lock) {
d2995737	262	ll_merge_attr(env, inode);
d7e09d03 PT	263	cl_unuse(env, lock);
	264	cl_lock_release(env, lock, "localsize", current);
	265	result = 0;
a7d516d6	266	} else {
d7e09d03	267	result = -ENODATA;
a7d516d6	268	}
d7e09d03 PT	269	}
	270	cl_io_fini(env, io);
	271	cl_env_put(env, &refcheck);
0a3bdb00	272	return result;
d7e09d03	273	}