Loading...
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 | /*
* 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.gnu.org/licenses/gpl-2.0.html
*
* GPL HEADER END
*/
/*
* Copyright (c) 2008, 2010, Oracle and/or its affiliates. All rights reserved.
* Use is subject to license terms.
*
* Copyright (c) 2011, 2015, Intel Corporation.
*/
/*
* This file is part of Lustre, http://www.lustre.org/
* Lustre is a trademark of Sun Microsystems, Inc.
*
* cl code shared between vvp and liblustre (and other Lustre clients in the
* future).
*
* Author: Nikita Danilov <nikita.danilov@sun.com>
*/
#define DEBUG_SUBSYSTEM S_LLITE
#include "../../include/linux/libcfs/libcfs.h"
# include <linux/fs.h>
# include <linux/sched.h>
# include <linux/mm.h>
# include <linux/quotaops.h>
# include <linux/highmem.h>
# include <linux/pagemap.h>
# include <linux/rbtree.h>
#include "../include/obd.h"
#include "../include/obd_support.h"
#include "../include/lustre_fid.h"
#include "../include/lustre_dlm.h"
#include "../include/lustre_ver.h"
#include "../include/lustre_mdc.h"
#include "../include/cl_object.h"
#include "../llite/llite_internal.h"
/*
* ccc_ prefix stands for "Common Client Code".
*/
/*****************************************************************************
*
* Vvp device and device type functions.
*
*/
/**
* An `emergency' environment used by cl_inode_fini() when cl_env_get()
* fails. Access to this environment is serialized by cl_inode_fini_guard
* mutex.
*/
struct lu_env *cl_inode_fini_env;
int cl_inode_fini_refcheck;
/**
* A mutex serializing calls to slp_inode_fini() under extreme memory
* pressure, when environments cannot be allocated.
*/
static DEFINE_MUTEX(cl_inode_fini_guard);
int cl_setattr_ost(struct inode *inode, const struct iattr *attr)
{
struct lu_env *env;
struct cl_io *io;
int result;
int refcheck;
env = cl_env_get(&refcheck);
if (IS_ERR(env))
return PTR_ERR(env);
io = vvp_env_thread_io(env);
io->ci_obj = ll_i2info(inode)->lli_clob;
io->u.ci_setattr.sa_attr.lvb_atime = LTIME_S(attr->ia_atime);
io->u.ci_setattr.sa_attr.lvb_mtime = LTIME_S(attr->ia_mtime);
io->u.ci_setattr.sa_attr.lvb_ctime = LTIME_S(attr->ia_ctime);
io->u.ci_setattr.sa_attr.lvb_size = attr->ia_size;
io->u.ci_setattr.sa_valid = attr->ia_valid;
io->u.ci_setattr.sa_parent_fid = ll_inode2fid(inode);
again:
if (cl_io_init(env, io, CIT_SETATTR, io->ci_obj) == 0) {
struct vvp_io *vio = vvp_env_io(env);
if (attr->ia_valid & ATTR_FILE)
/* populate the file descriptor for ftruncate to honor
* group lock - see LU-787
*/
vio->vui_fd = LUSTRE_FPRIVATE(attr->ia_file);
result = cl_io_loop(env, io);
} else {
result = io->ci_result;
}
cl_io_fini(env, io);
if (unlikely(io->ci_need_restart))
goto again;
/* HSM import case: file is released, cannot be restored
* no need to fail except if restore registration failed
* with -ENODATA
*/
if (result == -ENODATA && io->ci_restore_needed &&
io->ci_result != -ENODATA)
result = 0;
cl_env_put(env, &refcheck);
return result;
}
/**
* Initialize or update CLIO structures for regular files when new
* meta-data arrives from the server.
*
* \param inode regular file inode
* \param md new file metadata from MDS
* - allocates cl_object if necessary,
* - updated layout, if object was already here.
*/
int cl_file_inode_init(struct inode *inode, struct lustre_md *md)
{
struct lu_env *env;
struct ll_inode_info *lli;
struct cl_object *clob;
struct lu_site *site;
struct lu_fid *fid;
struct cl_object_conf conf = {
.coc_inode = inode,
.u = {
.coc_md = md
}
};
int result = 0;
int refcheck;
LASSERT(md->body->mbo_valid & OBD_MD_FLID);
LASSERT(S_ISREG(inode->i_mode));
env = cl_env_get(&refcheck);
if (IS_ERR(env))
return PTR_ERR(env);
site = ll_i2sbi(inode)->ll_site;
lli = ll_i2info(inode);
fid = &lli->lli_fid;
LASSERT(fid_is_sane(fid));
if (!lli->lli_clob) {
/* clob is slave of inode, empty lli_clob means for new inode,
* there is no clob in cache with the given fid, so it is
* unnecessary to perform lookup-alloc-lookup-insert, just
* alloc and insert directly.
*/
LASSERT(inode->i_state & I_NEW);
conf.coc_lu.loc_flags = LOC_F_NEW;
clob = cl_object_find(env, lu2cl_dev(site->ls_top_dev),
fid, &conf);
if (!IS_ERR(clob)) {
/*
* No locking is necessary, as new inode is
* locked by I_NEW bit.
*/
lli->lli_clob = clob;
lli->lli_has_smd = lsm_has_objects(md->lsm);
lu_object_ref_add(&clob->co_lu, "inode", inode);
} else {
result = PTR_ERR(clob);
}
} else {
result = cl_conf_set(env, lli->lli_clob, &conf);
}
cl_env_put(env, &refcheck);
if (result != 0)
CERROR("Failure to initialize cl object " DFID ": %d\n",
PFID(fid), result);
return result;
}
/**
* Wait for others drop their references of the object at first, then we drop
* the last one, which will lead to the object be destroyed immediately.
* Must be called after cl_object_kill() against this object.
*
* The reason we want to do this is: destroying top object will wait for sub
* objects being destroyed first, so we can't let bottom layer (e.g. from ASTs)
* to initiate top object destroying which may deadlock. See bz22520.
*/
static void cl_object_put_last(struct lu_env *env, struct cl_object *obj)
{
struct lu_object_header *header = obj->co_lu.lo_header;
wait_queue_t waiter;
if (unlikely(atomic_read(&header->loh_ref) != 1)) {
struct lu_site *site = obj->co_lu.lo_dev->ld_site;
struct lu_site_bkt_data *bkt;
bkt = lu_site_bkt_from_fid(site, &header->loh_fid);
init_waitqueue_entry(&waiter, current);
add_wait_queue(&bkt->lsb_marche_funebre, &waiter);
while (1) {
set_current_state(TASK_UNINTERRUPTIBLE);
if (atomic_read(&header->loh_ref) == 1)
break;
schedule();
}
set_current_state(TASK_RUNNING);
remove_wait_queue(&bkt->lsb_marche_funebre, &waiter);
}
cl_object_put(env, obj);
}
void cl_inode_fini(struct inode *inode)
{
struct lu_env *env;
struct ll_inode_info *lli = ll_i2info(inode);
struct cl_object *clob = lli->lli_clob;
int refcheck;
int emergency;
if (clob) {
void *cookie;
cookie = cl_env_reenter();
env = cl_env_get(&refcheck);
emergency = IS_ERR(env);
if (emergency) {
mutex_lock(&cl_inode_fini_guard);
LASSERT(cl_inode_fini_env);
cl_env_implant(cl_inode_fini_env, &refcheck);
env = cl_inode_fini_env;
}
/*
* cl_object cache is a slave to inode cache (which, in turn
* is a slave to dentry cache), don't keep cl_object in memory
* when its master is evicted.
*/
cl_object_kill(env, clob);
lu_object_ref_del(&clob->co_lu, "inode", inode);
cl_object_put_last(env, clob);
lli->lli_clob = NULL;
if (emergency) {
cl_env_unplant(cl_inode_fini_env, &refcheck);
mutex_unlock(&cl_inode_fini_guard);
} else {
cl_env_put(env, &refcheck);
}
cl_env_reexit(cookie);
}
}
/**
* build inode number from passed @fid
*/
__u64 cl_fid_build_ino(const struct lu_fid *fid, int api32)
{
if (BITS_PER_LONG == 32 || api32)
return fid_flatten32(fid);
else
return fid_flatten(fid);
}
/**
* build inode generation from passed @fid. If our FID overflows the 32-bit
* inode number then return a non-zero generation to distinguish them.
*/
__u32 cl_fid_build_gen(const struct lu_fid *fid)
{
__u32 gen;
if (fid_is_igif(fid)) {
gen = lu_igif_gen(fid);
return gen;
}
gen = fid_flatten(fid) >> 32;
return gen;
}
/* lsm is unreliable after hsm implementation as layout can be changed at
* any time. This is only to support old, non-clio-ized interfaces. It will
* cause deadlock if clio operations are called with this extra layout refcount
* because in case the layout changed during the IO, ll_layout_refresh() will
* have to wait for the refcount to become zero to destroy the older layout.
*
* Notice that the lsm returned by this function may not be valid unless called
* inside layout lock - MDS_INODELOCK_LAYOUT.
*/
struct lov_stripe_md *ccc_inode_lsm_get(struct inode *inode)
{
return lov_lsm_get(ll_i2info(inode)->lli_clob);
}
inline void ccc_inode_lsm_put(struct inode *inode, struct lov_stripe_md *lsm)
{
lov_lsm_put(ll_i2info(inode)->lli_clob, lsm);
}
|