123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232233234235236237238239240241242243244245246247248249250251252253254255256257258259260261262263264265266267268269270271272273274275276277278279280281282283284285286287288289290291292293294295296297298299300301302303304305306307308309310311312313314315316317318319320321322323324325326327328329330331332333334335336337338339340341342343344345346347348349350351352353354355356357358359360361362363364365366367368369370371372373374375376377378379380381382383384385386387388389390391392393394395396397398399400401402403404405406407408409410411412413414415416417418419420421422423424425426427428429430431432433434435436437438439440441442443444445446447448449450451452453454455456457458459460461462463464465466467468469470471472473474475476477478479480481482483484485486487488489490491492493494495496497498499500501502503504505506507508509510511512513514515516517518519520521522523524525526527528529530531532533534535536537538539540541542543544545546547548549550551552553554555556557558559560561562563564565566567568569570 |
- // SPDX-License-Identifier: GPL-2.0-only
- /*
- * Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved.
- * Copyright (C) 2004-2006 Red Hat, Inc. All rights reserved.
- */
- #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
- #include <linux/spinlock.h>
- #include <linux/completion.h>
- #include <linux/buffer_head.h>
- #include <linux/crc32.h>
- #include <linux/gfs2_ondisk.h>
- #include <linux/delay.h>
- #include <linux/uaccess.h>
- #include "gfs2.h"
- #include "incore.h"
- #include "glock.h"
- #include "glops.h"
- #include "log.h"
- #include "lops.h"
- #include "recovery.h"
- #include "rgrp.h"
- #include "super.h"
- #include "util.h"
- struct kmem_cache *gfs2_glock_cachep __read_mostly;
- struct kmem_cache *gfs2_glock_aspace_cachep __read_mostly;
- struct kmem_cache *gfs2_inode_cachep __read_mostly;
- struct kmem_cache *gfs2_bufdata_cachep __read_mostly;
- struct kmem_cache *gfs2_rgrpd_cachep __read_mostly;
- struct kmem_cache *gfs2_quotad_cachep __read_mostly;
- struct kmem_cache *gfs2_qadata_cachep __read_mostly;
- struct kmem_cache *gfs2_trans_cachep __read_mostly;
- mempool_t *gfs2_page_pool __read_mostly;
- void gfs2_assert_i(struct gfs2_sbd *sdp)
- {
- fs_emerg(sdp, "fatal assertion failed\n");
- }
- /**
- * check_journal_clean - Make sure a journal is clean for a spectator mount
- * @sdp: The GFS2 superblock
- * @jd: The journal descriptor
- * @verbose: Show more prints in the log
- *
- * Returns: 0 if the journal is clean or locked, else an error
- */
- int check_journal_clean(struct gfs2_sbd *sdp, struct gfs2_jdesc *jd,
- bool verbose)
- {
- int error;
- struct gfs2_holder j_gh;
- struct gfs2_log_header_host head;
- struct gfs2_inode *ip;
- ip = GFS2_I(jd->jd_inode);
- error = gfs2_glock_nq_init(ip->i_gl, LM_ST_SHARED, LM_FLAG_NOEXP |
- GL_EXACT | GL_NOCACHE, &j_gh);
- if (error) {
- if (verbose)
- fs_err(sdp, "Error %d locking journal for spectator "
- "mount.\n", error);
- return -EPERM;
- }
- error = gfs2_jdesc_check(jd);
- if (error) {
- if (verbose)
- fs_err(sdp, "Error checking journal for spectator "
- "mount.\n");
- goto out_unlock;
- }
- error = gfs2_find_jhead(jd, &head, false);
- if (error) {
- if (verbose)
- fs_err(sdp, "Error parsing journal for spectator "
- "mount.\n");
- goto out_unlock;
- }
- if (!(head.lh_flags & GFS2_LOG_HEAD_UNMOUNT)) {
- error = -EPERM;
- if (verbose)
- fs_err(sdp, "jid=%u: Journal is dirty, so the first "
- "mounter must not be a spectator.\n",
- jd->jd_jid);
- }
- out_unlock:
- gfs2_glock_dq_uninit(&j_gh);
- return error;
- }
- /**
- * gfs2_freeze_lock - hold the freeze glock
- * @sdp: the superblock
- * @freeze_gh: pointer to the requested holder
- * @caller_flags: any additional flags needed by the caller
- */
- int gfs2_freeze_lock(struct gfs2_sbd *sdp, struct gfs2_holder *freeze_gh,
- int caller_flags)
- {
- int flags = LM_FLAG_NOEXP | GL_EXACT | caller_flags;
- int error;
- error = gfs2_glock_nq_init(sdp->sd_freeze_gl, LM_ST_SHARED, flags,
- freeze_gh);
- if (error && error != GLR_TRYFAILED)
- fs_err(sdp, "can't lock the freeze lock: %d\n", error);
- return error;
- }
- void gfs2_freeze_unlock(struct gfs2_holder *freeze_gh)
- {
- if (gfs2_holder_initialized(freeze_gh))
- gfs2_glock_dq_uninit(freeze_gh);
- }
- static void signal_our_withdraw(struct gfs2_sbd *sdp)
- {
- struct gfs2_glock *live_gl = sdp->sd_live_gh.gh_gl;
- struct inode *inode;
- struct gfs2_inode *ip;
- struct gfs2_glock *i_gl;
- u64 no_formal_ino;
- int log_write_allowed = test_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags);
- int ret = 0;
- int tries;
- if (test_bit(SDF_NORECOVERY, &sdp->sd_flags) || !sdp->sd_jdesc)
- return;
- gfs2_ail_drain(sdp); /* frees all transactions */
- inode = sdp->sd_jdesc->jd_inode;
- ip = GFS2_I(inode);
- i_gl = ip->i_gl;
- no_formal_ino = ip->i_no_formal_ino;
- /* Prevent any glock dq until withdraw recovery is complete */
- set_bit(SDF_WITHDRAW_RECOVERY, &sdp->sd_flags);
- /*
- * Don't tell dlm we're bailing until we have no more buffers in the
- * wind. If journal had an IO error, the log code should just purge
- * the outstanding buffers rather than submitting new IO. Making the
- * file system read-only will flush the journal, etc.
- *
- * During a normal unmount, gfs2_make_fs_ro calls gfs2_log_shutdown
- * which clears SDF_JOURNAL_LIVE. In a withdraw, we must not write
- * any UNMOUNT log header, so we can't call gfs2_log_shutdown, and
- * therefore we need to clear SDF_JOURNAL_LIVE manually.
- */
- clear_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags);
- if (!sb_rdonly(sdp->sd_vfs)) {
- struct gfs2_holder freeze_gh;
- gfs2_holder_mark_uninitialized(&freeze_gh);
- if (sdp->sd_freeze_gl &&
- !gfs2_glock_is_locked_by_me(sdp->sd_freeze_gl)) {
- ret = gfs2_freeze_lock(sdp, &freeze_gh,
- log_write_allowed ? 0 : LM_FLAG_TRY);
- if (ret == GLR_TRYFAILED)
- ret = 0;
- }
- if (!ret)
- gfs2_make_fs_ro(sdp);
- /*
- * Dequeue any pending non-system glock holders that can no
- * longer be granted because the file system is withdrawn.
- */
- gfs2_gl_dq_holders(sdp);
- gfs2_freeze_unlock(&freeze_gh);
- }
- if (sdp->sd_lockstruct.ls_ops->lm_lock == NULL) { /* lock_nolock */
- if (!ret)
- ret = -EIO;
- clear_bit(SDF_WITHDRAW_RECOVERY, &sdp->sd_flags);
- goto skip_recovery;
- }
- /*
- * Drop the glock for our journal so another node can recover it.
- */
- if (gfs2_holder_initialized(&sdp->sd_journal_gh)) {
- gfs2_glock_dq_wait(&sdp->sd_journal_gh);
- gfs2_holder_uninit(&sdp->sd_journal_gh);
- }
- sdp->sd_jinode_gh.gh_flags |= GL_NOCACHE;
- gfs2_glock_dq(&sdp->sd_jinode_gh);
- if (test_bit(SDF_FS_FROZEN, &sdp->sd_flags)) {
- /* Make sure gfs2_unfreeze works if partially-frozen */
- flush_work(&sdp->sd_freeze_work);
- atomic_set(&sdp->sd_freeze_state, SFS_FROZEN);
- thaw_super(sdp->sd_vfs);
- } else {
- wait_on_bit(&i_gl->gl_flags, GLF_DEMOTE,
- TASK_UNINTERRUPTIBLE);
- }
- /*
- * holder_uninit to force glock_put, to force dlm to let go
- */
- gfs2_holder_uninit(&sdp->sd_jinode_gh);
- /*
- * Note: We need to be careful here:
- * Our iput of jd_inode will evict it. The evict will dequeue its
- * glock, but the glock dq will wait for the withdraw unless we have
- * exception code in glock_dq.
- */
- iput(inode);
- sdp->sd_jdesc->jd_inode = NULL;
- /*
- * Wait until the journal inode's glock is freed. This allows try locks
- * on other nodes to be successful, otherwise we remain the owner of
- * the glock as far as dlm is concerned.
- */
- if (i_gl->gl_ops->go_free) {
- set_bit(GLF_FREEING, &i_gl->gl_flags);
- wait_on_bit(&i_gl->gl_flags, GLF_FREEING, TASK_UNINTERRUPTIBLE);
- }
- /*
- * Dequeue the "live" glock, but keep a reference so it's never freed.
- */
- gfs2_glock_hold(live_gl);
- gfs2_glock_dq_wait(&sdp->sd_live_gh);
- /*
- * We enqueue the "live" glock in EX so that all other nodes
- * get a demote request and act on it. We don't really want the
- * lock in EX, so we send a "try" lock with 1CB to produce a callback.
- */
- fs_warn(sdp, "Requesting recovery of jid %d.\n",
- sdp->sd_lockstruct.ls_jid);
- gfs2_holder_reinit(LM_ST_EXCLUSIVE,
- LM_FLAG_TRY_1CB | LM_FLAG_NOEXP | GL_NOPID,
- &sdp->sd_live_gh);
- msleep(GL_GLOCK_MAX_HOLD);
- /*
- * This will likely fail in a cluster, but succeed standalone:
- */
- ret = gfs2_glock_nq(&sdp->sd_live_gh);
- /*
- * If we actually got the "live" lock in EX mode, there are no other
- * nodes available to replay our journal. So we try to replay it
- * ourselves. We hold the "live" glock to prevent other mounters
- * during recovery, then just dequeue it and reacquire it in our
- * normal SH mode. Just in case the problem that caused us to
- * withdraw prevents us from recovering our journal (e.g. io errors
- * and such) we still check if the journal is clean before proceeding
- * but we may wait forever until another mounter does the recovery.
- */
- if (ret == 0) {
- fs_warn(sdp, "No other mounters found. Trying to recover our "
- "own journal jid %d.\n", sdp->sd_lockstruct.ls_jid);
- if (gfs2_recover_journal(sdp->sd_jdesc, 1))
- fs_warn(sdp, "Unable to recover our journal jid %d.\n",
- sdp->sd_lockstruct.ls_jid);
- gfs2_glock_dq_wait(&sdp->sd_live_gh);
- gfs2_holder_reinit(LM_ST_SHARED,
- LM_FLAG_NOEXP | GL_EXACT | GL_NOPID,
- &sdp->sd_live_gh);
- gfs2_glock_nq(&sdp->sd_live_gh);
- }
- gfs2_glock_queue_put(live_gl); /* drop extra reference we acquired */
- clear_bit(SDF_WITHDRAW_RECOVERY, &sdp->sd_flags);
- /*
- * At this point our journal is evicted, so we need to get a new inode
- * for it. Once done, we need to call gfs2_find_jhead which
- * calls gfs2_map_journal_extents to map it for us again.
- *
- * Note that we don't really want it to look up a FREE block. The
- * GFS2_BLKST_FREE simply overrides a block check in gfs2_inode_lookup
- * which would otherwise fail because it requires grabbing an rgrp
- * glock, which would fail with -EIO because we're withdrawing.
- */
- inode = gfs2_inode_lookup(sdp->sd_vfs, DT_UNKNOWN,
- sdp->sd_jdesc->jd_no_addr, no_formal_ino,
- GFS2_BLKST_FREE);
- if (IS_ERR(inode)) {
- fs_warn(sdp, "Reprocessing of jid %d failed with %ld.\n",
- sdp->sd_lockstruct.ls_jid, PTR_ERR(inode));
- goto skip_recovery;
- }
- sdp->sd_jdesc->jd_inode = inode;
- d_mark_dontcache(inode);
- /*
- * Now wait until recovery is complete.
- */
- for (tries = 0; tries < 10; tries++) {
- ret = check_journal_clean(sdp, sdp->sd_jdesc, false);
- if (!ret)
- break;
- msleep(HZ);
- fs_warn(sdp, "Waiting for journal recovery jid %d.\n",
- sdp->sd_lockstruct.ls_jid);
- }
- skip_recovery:
- if (!ret)
- fs_warn(sdp, "Journal recovery complete for jid %d.\n",
- sdp->sd_lockstruct.ls_jid);
- else
- fs_warn(sdp, "Journal recovery skipped for jid %d until next "
- "mount.\n", sdp->sd_lockstruct.ls_jid);
- fs_warn(sdp, "Glock dequeues delayed: %lu\n", sdp->sd_glock_dqs_held);
- sdp->sd_glock_dqs_held = 0;
- wake_up_bit(&sdp->sd_flags, SDF_WITHDRAW_RECOVERY);
- }
- void gfs2_lm(struct gfs2_sbd *sdp, const char *fmt, ...)
- {
- struct va_format vaf;
- va_list args;
- if (sdp->sd_args.ar_errors == GFS2_ERRORS_WITHDRAW &&
- test_bit(SDF_WITHDRAWN, &sdp->sd_flags))
- return;
- va_start(args, fmt);
- vaf.fmt = fmt;
- vaf.va = &args;
- fs_err(sdp, "%pV", &vaf);
- va_end(args);
- }
- int gfs2_withdraw(struct gfs2_sbd *sdp)
- {
- struct lm_lockstruct *ls = &sdp->sd_lockstruct;
- const struct lm_lockops *lm = ls->ls_ops;
- if (sdp->sd_args.ar_errors == GFS2_ERRORS_WITHDRAW &&
- test_and_set_bit(SDF_WITHDRAWN, &sdp->sd_flags)) {
- if (!test_bit(SDF_WITHDRAW_IN_PROG, &sdp->sd_flags))
- return -1;
- wait_on_bit(&sdp->sd_flags, SDF_WITHDRAW_IN_PROG,
- TASK_UNINTERRUPTIBLE);
- return -1;
- }
- set_bit(SDF_WITHDRAW_IN_PROG, &sdp->sd_flags);
- if (sdp->sd_args.ar_errors == GFS2_ERRORS_WITHDRAW) {
- fs_err(sdp, "about to withdraw this file system\n");
- BUG_ON(sdp->sd_args.ar_debug);
- signal_our_withdraw(sdp);
- kobject_uevent(&sdp->sd_kobj, KOBJ_OFFLINE);
- if (!strcmp(sdp->sd_lockstruct.ls_ops->lm_proto_name, "lock_dlm"))
- wait_for_completion(&sdp->sd_wdack);
- if (lm->lm_unmount) {
- fs_err(sdp, "telling LM to unmount\n");
- lm->lm_unmount(sdp);
- }
- set_bit(SDF_SKIP_DLM_UNLOCK, &sdp->sd_flags);
- fs_err(sdp, "File system withdrawn\n");
- dump_stack();
- clear_bit(SDF_WITHDRAW_IN_PROG, &sdp->sd_flags);
- smp_mb__after_atomic();
- wake_up_bit(&sdp->sd_flags, SDF_WITHDRAW_IN_PROG);
- }
- if (sdp->sd_args.ar_errors == GFS2_ERRORS_PANIC)
- panic("GFS2: fsid=%s: panic requested\n", sdp->sd_fsname);
- return -1;
- }
- /*
- * gfs2_assert_withdraw_i - Cause the machine to withdraw if @assertion is false
- */
- void gfs2_assert_withdraw_i(struct gfs2_sbd *sdp, char *assertion,
- const char *function, char *file, unsigned int line,
- bool delayed)
- {
- if (gfs2_withdrawn(sdp))
- return;
- fs_err(sdp,
- "fatal: assertion \"%s\" failed\n"
- " function = %s, file = %s, line = %u\n",
- assertion, function, file, line);
- /*
- * If errors=panic was specified on mount, it won't help to delay the
- * withdraw.
- */
- if (sdp->sd_args.ar_errors == GFS2_ERRORS_PANIC)
- delayed = false;
- if (delayed)
- gfs2_withdraw_delayed(sdp);
- else
- gfs2_withdraw(sdp);
- dump_stack();
- }
- /*
- * gfs2_assert_warn_i - Print a message to the console if @assertion is false
- */
- void gfs2_assert_warn_i(struct gfs2_sbd *sdp, char *assertion,
- const char *function, char *file, unsigned int line)
- {
- if (time_before(jiffies,
- sdp->sd_last_warning +
- gfs2_tune_get(sdp, gt_complain_secs) * HZ))
- return;
- if (sdp->sd_args.ar_errors == GFS2_ERRORS_WITHDRAW)
- fs_warn(sdp, "warning: assertion \"%s\" failed at function = %s, file = %s, line = %u\n",
- assertion, function, file, line);
- if (sdp->sd_args.ar_debug)
- BUG();
- else
- dump_stack();
- if (sdp->sd_args.ar_errors == GFS2_ERRORS_PANIC)
- panic("GFS2: fsid=%s: warning: assertion \"%s\" failed\n"
- "GFS2: fsid=%s: function = %s, file = %s, line = %u\n",
- sdp->sd_fsname, assertion,
- sdp->sd_fsname, function, file, line);
- sdp->sd_last_warning = jiffies;
- }
- /*
- * gfs2_consist_i - Flag a filesystem consistency error and withdraw
- */
- void gfs2_consist_i(struct gfs2_sbd *sdp, const char *function,
- char *file, unsigned int line)
- {
- gfs2_lm(sdp,
- "fatal: filesystem consistency error - function = %s, file = %s, line = %u\n",
- function, file, line);
- gfs2_withdraw(sdp);
- }
- /*
- * gfs2_consist_inode_i - Flag an inode consistency error and withdraw
- */
- void gfs2_consist_inode_i(struct gfs2_inode *ip,
- const char *function, char *file, unsigned int line)
- {
- struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
- gfs2_lm(sdp,
- "fatal: filesystem consistency error\n"
- " inode = %llu %llu\n"
- " function = %s, file = %s, line = %u\n",
- (unsigned long long)ip->i_no_formal_ino,
- (unsigned long long)ip->i_no_addr,
- function, file, line);
- gfs2_dump_glock(NULL, ip->i_gl, 1);
- gfs2_withdraw(sdp);
- }
- /*
- * gfs2_consist_rgrpd_i - Flag a RG consistency error and withdraw
- */
- void gfs2_consist_rgrpd_i(struct gfs2_rgrpd *rgd,
- const char *function, char *file, unsigned int line)
- {
- struct gfs2_sbd *sdp = rgd->rd_sbd;
- char fs_id_buf[sizeof(sdp->sd_fsname) + 7];
- sprintf(fs_id_buf, "fsid=%s: ", sdp->sd_fsname);
- gfs2_rgrp_dump(NULL, rgd, fs_id_buf);
- gfs2_lm(sdp,
- "fatal: filesystem consistency error\n"
- " RG = %llu\n"
- " function = %s, file = %s, line = %u\n",
- (unsigned long long)rgd->rd_addr,
- function, file, line);
- gfs2_dump_glock(NULL, rgd->rd_gl, 1);
- gfs2_withdraw(sdp);
- }
- /*
- * gfs2_meta_check_ii - Flag a magic number consistency error and withdraw
- * Returns: -1 if this call withdrew the machine,
- * -2 if it was already withdrawn
- */
- int gfs2_meta_check_ii(struct gfs2_sbd *sdp, struct buffer_head *bh,
- const char *type, const char *function, char *file,
- unsigned int line)
- {
- int me;
- gfs2_lm(sdp,
- "fatal: invalid metadata block\n"
- " bh = %llu (%s)\n"
- " function = %s, file = %s, line = %u\n",
- (unsigned long long)bh->b_blocknr, type,
- function, file, line);
- me = gfs2_withdraw(sdp);
- return (me) ? -1 : -2;
- }
- /*
- * gfs2_metatype_check_ii - Flag a metadata type consistency error and withdraw
- * Returns: -1 if this call withdrew the machine,
- * -2 if it was already withdrawn
- */
- int gfs2_metatype_check_ii(struct gfs2_sbd *sdp, struct buffer_head *bh,
- u16 type, u16 t, const char *function,
- char *file, unsigned int line)
- {
- int me;
- gfs2_lm(sdp,
- "fatal: invalid metadata block\n"
- " bh = %llu (type: exp=%u, found=%u)\n"
- " function = %s, file = %s, line = %u\n",
- (unsigned long long)bh->b_blocknr, type, t,
- function, file, line);
- me = gfs2_withdraw(sdp);
- return (me) ? -1 : -2;
- }
- /*
- * gfs2_io_error_i - Flag an I/O error and withdraw
- * Returns: -1 if this call withdrew the machine,
- * 0 if it was already withdrawn
- */
- int gfs2_io_error_i(struct gfs2_sbd *sdp, const char *function, char *file,
- unsigned int line)
- {
- gfs2_lm(sdp,
- "fatal: I/O error\n"
- " function = %s, file = %s, line = %u\n",
- function, file, line);
- return gfs2_withdraw(sdp);
- }
- /*
- * gfs2_io_error_bh_i - Flag a buffer I/O error
- * @withdraw: withdraw the filesystem
- */
- void gfs2_io_error_bh_i(struct gfs2_sbd *sdp, struct buffer_head *bh,
- const char *function, char *file, unsigned int line,
- bool withdraw)
- {
- if (gfs2_withdrawn(sdp))
- return;
- fs_err(sdp, "fatal: I/O error\n"
- " block = %llu\n"
- " function = %s, file = %s, line = %u\n",
- (unsigned long long)bh->b_blocknr, function, file, line);
- if (withdraw)
- gfs2_withdraw(sdp);
- }
|