diff options
Diffstat (limited to 'fs/gfs2/glops.c')
| -rw-r--r-- | fs/gfs2/glops.c | 157 |
1 files changed, 130 insertions, 27 deletions
diff --git a/fs/gfs2/glops.c b/fs/gfs2/glops.c index 061d22e1ceb6..9e9c7a4b8c66 100644 --- a/fs/gfs2/glops.c +++ b/fs/gfs2/glops.c @@ -29,6 +29,8 @@ struct workqueue_struct *gfs2_freeze_wq; +extern struct workqueue_struct *gfs2_control_wq; + static void gfs2_ail_error(struct gfs2_glock *gl, const struct buffer_head *bh) { fs_err(gl->gl_name.ln_sbd, @@ -39,7 +41,8 @@ static void gfs2_ail_error(struct gfs2_glock *gl, const struct buffer_head *bh) fs_err(gl->gl_name.ln_sbd, "AIL glock %u:%llu mapping %p\n", gl->gl_name.ln_type, gl->gl_name.ln_number, gfs2_glock2aspace(gl)); - gfs2_lm_withdraw(gl->gl_name.ln_sbd, "AIL error\n"); + gfs2_lm(gl->gl_name.ln_sbd, "AIL error\n"); + gfs2_withdraw(gl->gl_name.ln_sbd); } /** @@ -79,34 +82,62 @@ static void __gfs2_ail_flush(struct gfs2_glock *gl, bool fsync, } -static void gfs2_ail_empty_gl(struct gfs2_glock *gl) +static int gfs2_ail_empty_gl(struct gfs2_glock *gl) { struct gfs2_sbd *sdp = gl->gl_name.ln_sbd; struct gfs2_trans tr; + int ret; memset(&tr, 0, sizeof(tr)); INIT_LIST_HEAD(&tr.tr_buf); INIT_LIST_HEAD(&tr.tr_databuf); tr.tr_revokes = atomic_read(&gl->gl_ail_count); - if (!tr.tr_revokes) - return; + if (!tr.tr_revokes) { + bool have_revokes; + bool log_in_flight; + + /* + * We have nothing on the ail, but there could be revokes on + * the sdp revoke queue, in which case, we still want to flush + * the log and wait for it to finish. + * + * If the sdp revoke list is empty too, we might still have an + * io outstanding for writing revokes, so we should wait for + * it before returning. + * + * If none of these conditions are true, our revokes are all + * flushed and we can return. + */ + gfs2_log_lock(sdp); + have_revokes = !list_empty(&sdp->sd_log_revokes); + log_in_flight = atomic_read(&sdp->sd_log_in_flight); + gfs2_log_unlock(sdp); + if (have_revokes) + goto flush; + if (log_in_flight) + log_flush_wait(sdp); + return 0; + } /* A shortened, inline version of gfs2_trans_begin() * tr->alloced is not set since the transaction structure is * on the stack */ tr.tr_reserved = 1 + gfs2_struct2blk(sdp, tr.tr_revokes); tr.tr_ip = _RET_IP_; - if (gfs2_log_reserve(sdp, tr.tr_reserved) < 0) - return; + ret = gfs2_log_reserve(sdp, tr.tr_reserved); + if (ret < 0) + return ret; WARN_ON_ONCE(current->journal_info); current->journal_info = &tr; __gfs2_ail_flush(gl, 0, tr.tr_revokes); gfs2_trans_end(sdp); +flush: gfs2_log_flush(sdp, NULL, GFS2_LOG_HEAD_FLUSH_NORMAL | GFS2_LFC_AIL_EMPTY_GL); + return 0; } void gfs2_ail_flush(struct gfs2_glock *gl, bool fsync) @@ -140,35 +171,32 @@ void gfs2_ail_flush(struct gfs2_glock *gl, bool fsync) * return to caller to demote/unlock the glock until I/O is complete. */ -static void rgrp_go_sync(struct gfs2_glock *gl) +static int rgrp_go_sync(struct gfs2_glock *gl) { struct gfs2_sbd *sdp = gl->gl_name.ln_sbd; struct address_space *mapping = &sdp->sd_aspace; - struct gfs2_rgrpd *rgd; + struct gfs2_rgrpd *rgd = gfs2_glock2rgrp(gl); int error; - spin_lock(&gl->gl_lockref.lock); - rgd = gl->gl_object; - if (rgd) - gfs2_rgrp_brelse(rgd); - spin_unlock(&gl->gl_lockref.lock); - if (!test_and_clear_bit(GLF_DIRTY, &gl->gl_flags)) - return; + return 0; GLOCK_BUG_ON(gl, gl->gl_state != LM_ST_EXCLUSIVE); gfs2_log_flush(sdp, gl, GFS2_LOG_HEAD_FLUSH_NORMAL | GFS2_LFC_RGRP_GO_SYNC); filemap_fdatawrite_range(mapping, gl->gl_vm.start, gl->gl_vm.end); error = filemap_fdatawait_range(mapping, gl->gl_vm.start, gl->gl_vm.end); + WARN_ON_ONCE(error); mapping_set_error(mapping, error); - gfs2_ail_empty_gl(gl); + if (!error) + error = gfs2_ail_empty_gl(gl); spin_lock(&gl->gl_lockref.lock); rgd = gl->gl_object; if (rgd) gfs2_free_clones(rgd); spin_unlock(&gl->gl_lockref.lock); + return error; } /** @@ -191,7 +219,6 @@ static void rgrp_go_inval(struct gfs2_glock *gl, int flags) gfs2_rgrp_brelse(rgd); WARN_ON_ONCE(!(flags & DIO_METADATA)); - gfs2_assert_withdraw(sdp, !atomic_read(&gl->gl_ail_count)); truncate_inode_pages_range(mapping, gl->gl_vm.start, gl->gl_vm.end); if (rgd) @@ -236,12 +263,12 @@ static void gfs2_clear_glop_pending(struct gfs2_inode *ip) * */ -static void inode_go_sync(struct gfs2_glock *gl) +static int inode_go_sync(struct gfs2_glock *gl) { struct gfs2_inode *ip = gfs2_glock2inode(gl); int isreg = ip && S_ISREG(ip->i_inode.i_mode); struct address_space *metamapping = gfs2_glock2aspace(gl); - int error; + int error = 0; if (isreg) { if (test_and_clear_bit(GIF_SW_PAGED, &ip->i_flags)) @@ -274,6 +301,7 @@ static void inode_go_sync(struct gfs2_glock *gl) out: gfs2_clear_glop_pending(ip); + return error; } /** @@ -291,8 +319,6 @@ static void inode_go_inval(struct gfs2_glock *gl, int flags) { struct gfs2_inode *ip = gfs2_glock2inode(gl); - gfs2_assert_withdraw(gl->gl_name.ln_sbd, !atomic_read(&gl->gl_ail_count)); - if (flags & DIO_METADATA) { struct address_space *mapping = gfs2_glock2aspace(gl); truncate_inode_pages(mapping, 0); @@ -496,24 +522,29 @@ static void inode_go_dump(struct seq_file *seq, struct gfs2_glock *gl, * */ -static void freeze_go_sync(struct gfs2_glock *gl) +static int freeze_go_sync(struct gfs2_glock *gl) { int error = 0; struct gfs2_sbd *sdp = gl->gl_name.ln_sbd; - if (gl->gl_state == LM_ST_SHARED && + if (gl->gl_state == LM_ST_SHARED && !gfs2_withdrawn(sdp) && test_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags)) { atomic_set(&sdp->sd_freeze_state, SFS_STARTING_FREEZE); error = freeze_super(sdp->sd_vfs); if (error) { fs_info(sdp, "GFS2: couldn't freeze filesystem: %d\n", error); + if (gfs2_withdrawn(sdp)) { + atomic_set(&sdp->sd_freeze_state, SFS_UNFROZEN); + return 0; + } gfs2_assert_withdraw(sdp, 0); } queue_work(gfs2_freeze_wq, &sdp->sd_freeze_work); gfs2_log_flush(sdp, NULL, GFS2_LOG_HEAD_FLUSH_FREEZE | GFS2_LFC_FREEZE_GO_SYNC); } + return 0; } /** @@ -582,8 +613,76 @@ static void iopen_go_callback(struct gfs2_glock *gl, bool remote) } } +/** + * inode_go_free - wake up anyone waiting for dlm's unlock ast to free it + * @gl: glock being freed + * + * For now, this is only used for the journal inode glock. In withdraw + * situations, we need to wait for the glock to be freed so that we know + * other nodes may proceed with recovery / journal replay. + */ +static void inode_go_free(struct gfs2_glock *gl) +{ + /* Note that we cannot reference gl_object because it's already set + * to NULL by this point in its lifecycle. */ + if (!test_bit(GLF_FREEING, &gl->gl_flags)) + return; + clear_bit_unlock(GLF_FREEING, &gl->gl_flags); + wake_up_bit(&gl->gl_flags, GLF_FREEING); +} + +/** + * nondisk_go_callback - used to signal when a node did a withdraw + * @gl: the nondisk glock + * @remote: true if this came from a different cluster node + * + */ +static void nondisk_go_callback(struct gfs2_glock *gl, bool remote) +{ + struct gfs2_sbd *sdp = gl->gl_name.ln_sbd; + + /* Ignore the callback unless it's from another node, and it's the + live lock. */ + if (!remote || gl->gl_name.ln_number != GFS2_LIVE_LOCK) + return; + + /* First order of business is to cancel the demote request. We don't + * really want to demote a nondisk glock. At best it's just to inform + * us of another node's withdraw. We'll keep it in SH mode. */ + clear_bit(GLF_DEMOTE, &gl->gl_flags); + clear_bit(GLF_PENDING_DEMOTE, &gl->gl_flags); + + /* Ignore the unlock if we're withdrawn, unmounting, or in recovery. */ + if (test_bit(SDF_NORECOVERY, &sdp->sd_flags) || + test_bit(SDF_WITHDRAWN, &sdp->sd_flags) || + test_bit(SDF_REMOTE_WITHDRAW, &sdp->sd_flags)) + return; + + /* We only care when a node wants us to unlock, because that means + * they want a journal recovered. */ + if (gl->gl_demote_state != LM_ST_UNLOCKED) + return; + + if (sdp->sd_args.ar_spectator) { + fs_warn(sdp, "Spectator node cannot recover journals.\n"); + return; + } + + fs_warn(sdp, "Some node has withdrawn; checking for recovery.\n"); + set_bit(SDF_REMOTE_WITHDRAW, &sdp->sd_flags); + /* + * We can't call remote_withdraw directly here or gfs2_recover_journal + * because this is called from the glock unlock function and the + * remote_withdraw needs to enqueue and dequeue the same "live" glock + * we were called from. So we queue it to the control work queue in + * lock_dlm. + */ + queue_delayed_work(gfs2_control_wq, &sdp->sd_control_work, 0); +} + const struct gfs2_glock_operations gfs2_meta_glops = { .go_type = LM_TYPE_META, + .go_flags = GLOF_NONDISK, }; const struct gfs2_glock_operations gfs2_inode_glops = { @@ -594,13 +693,13 @@ const struct gfs2_glock_operations gfs2_inode_glops = { .go_dump = inode_go_dump, .go_type = LM_TYPE_INODE, .go_flags = GLOF_ASPACE | GLOF_LRU, + .go_free = inode_go_free, }; const struct gfs2_glock_operations gfs2_rgrp_glops = { .go_sync = rgrp_go_sync, .go_inval = rgrp_go_inval, .go_lock = gfs2_rgrp_go_lock, - .go_unlock = gfs2_rgrp_go_unlock, .go_dump = gfs2_rgrp_dump, .go_type = LM_TYPE_RGRP, .go_flags = GLOF_LVB, @@ -611,30 +710,34 @@ const struct gfs2_glock_operations gfs2_freeze_glops = { .go_xmote_bh = freeze_go_xmote_bh, .go_demote_ok = freeze_go_demote_ok, .go_type = LM_TYPE_NONDISK, + .go_flags = GLOF_NONDISK, }; const struct gfs2_glock_operations gfs2_iopen_glops = { .go_type = LM_TYPE_IOPEN, .go_callback = iopen_go_callback, - .go_flags = GLOF_LRU, + .go_flags = GLOF_LRU | GLOF_NONDISK, }; const struct gfs2_glock_operations gfs2_flock_glops = { .go_type = LM_TYPE_FLOCK, - .go_flags = GLOF_LRU, + .go_flags = GLOF_LRU | GLOF_NONDISK, }; const struct gfs2_glock_operations gfs2_nondisk_glops = { .go_type = LM_TYPE_NONDISK, + .go_flags = GLOF_NONDISK, + .go_callback = nondisk_go_callback, }; const struct gfs2_glock_operations gfs2_quota_glops = { .go_type = LM_TYPE_QUOTA, - .go_flags = GLOF_LVB | GLOF_LRU, + .go_flags = GLOF_LVB | GLOF_LRU | GLOF_NONDISK, }; const struct gfs2_glock_operations gfs2_journal_glops = { .go_type = LM_TYPE_JOURNAL, + .go_flags = GLOF_NONDISK, }; const struct gfs2_glock_operations *gfs2_glops_list[] = { |