diff options
Diffstat (limited to 'fs')
78 files changed, 3674 insertions, 2066 deletions
diff --git a/fs/dlm/dlm_internal.h b/fs/dlm/dlm_internal.h index 74901e981e1..d2fc2384c3b 100644 --- a/fs/dlm/dlm_internal.h +++ b/fs/dlm/dlm_internal.h @@ -491,6 +491,7 @@ struct dlm_ls { uint64_t ls_recover_seq; struct dlm_recover *ls_recover_args; struct rw_semaphore ls_in_recovery; /* block local requests */ + struct rw_semaphore ls_recv_active; /* block dlm_recv */ struct list_head ls_requestqueue;/* queue remote requests */ struct mutex ls_requestqueue_mutex; char *ls_recover_buf; diff --git a/fs/dlm/lock.c b/fs/dlm/lock.c index 2082daf083d..3915b8e1414 100644 --- a/fs/dlm/lock.c +++ b/fs/dlm/lock.c @@ -3638,55 +3638,8 @@ static void receive_lookup_reply(struct dlm_ls *ls, struct dlm_message *ms) dlm_put_lkb(lkb); } -int dlm_receive_message(struct dlm_header *hd, int nodeid, int recovery) +static void _receive_message(struct dlm_ls *ls, struct dlm_message *ms) { - struct dlm_message *ms = (struct dlm_message *) hd; - struct dlm_ls *ls; - int error = 0; - - if (!recovery) - dlm_message_in(ms); - - ls = dlm_find_lockspace_global(hd->h_lockspace); - if (!ls) { - log_print("drop message %d from %d for unknown lockspace %d", - ms->m_type, nodeid, hd->h_lockspace); - return -EINVAL; - } - - /* recovery may have just ended leaving a bunch of backed-up requests - in the requestqueue; wait while dlm_recoverd clears them */ - - if (!recovery) - dlm_wait_requestqueue(ls); - - /* recovery may have just started while there were a bunch of - in-flight requests -- save them in requestqueue to be processed - after recovery. we can't let dlm_recvd block on the recovery - lock. if dlm_recoverd is calling this function to clear the - requestqueue, it needs to be interrupted (-EINTR) if another - recovery operation is starting. */ - - while (1) { - if (dlm_locking_stopped(ls)) { - if (recovery) { - error = -EINTR; - goto out; - } - error = dlm_add_requestqueue(ls, nodeid, hd); - if (error == -EAGAIN) - continue; - else { - error = -EINTR; - goto out; - } - } - - if (dlm_lock_recovery_try(ls)) - break; - schedule(); - } - switch (ms->m_type) { /* messages sent to a master node */ @@ -3761,17 +3714,90 @@ int dlm_receive_message(struct dlm_header *hd, int nodeid, int recovery) log_error(ls, "unknown message type %d", ms->m_type); } - dlm_unlock_recovery(ls); - out: - dlm_put_lockspace(ls); dlm_astd_wake(); - return error; } +/* If the lockspace is in recovery mode (locking stopped), then normal + messages are saved on the requestqueue for processing after recovery is + done. When not in recovery mode, we wait for dlm_recoverd to drain saved + messages off the requestqueue before we process new ones. This occurs right + after recovery completes when we transition from saving all messages on + requestqueue, to processing all the saved messages, to processing new + messages as they arrive. */ -/* - * Recovery related - */ +static void dlm_receive_message(struct dlm_ls *ls, struct dlm_message *ms, + int nodeid) +{ + if (dlm_locking_stopped(ls)) { + dlm_add_requestqueue(ls, nodeid, (struct dlm_header *) ms); + } else { + dlm_wait_requestqueue(ls); + _receive_message(ls, ms); + } +} + +/* This is called by dlm_recoverd to process messages that were saved on + the requestqueue. */ + +void dlm_receive_message_saved(struct dlm_ls *ls, struct dlm_message *ms) +{ + _receive_message(ls, ms); +} + +/* This is called by the midcomms layer when something is received for + the lockspace. It could be either a MSG (normal message sent as part of + standard locking activity) or an RCOM (recovery message sent as part of + lockspace recovery). */ + +void dlm_receive_buffer(struct dlm_header *hd, int nodeid) +{ + struct dlm_message *ms = (struct dlm_message *) hd; + struct dlm_rcom *rc = (struct dlm_rcom *) hd; + struct dlm_ls *ls; + int type = 0; + + switch (hd->h_cmd) { + case DLM_MSG: + dlm_message_in(ms); + type = ms->m_type; + break; + case DLM_RCOM: + dlm_rcom_in(rc); + type = rc->rc_type; + break; + default: + log_print("invalid h_cmd %d from %u", hd->h_cmd, nodeid); + return; + } + + if (hd->h_nodeid != nodeid) { + log_print("invalid h_nodeid %d from %d lockspace %x", + hd->h_nodeid, nodeid, hd->h_lockspace); + return; + } + + ls = dlm_find_lockspace_global(hd->h_lockspace); + if (!ls) { + log_print("invalid h_lockspace %x from %d cmd %d type %d", + hd->h_lockspace, nodeid, hd->h_cmd, type); + + if (hd->h_cmd == DLM_RCOM && type == DLM_RCOM_STATUS) + dlm_send_ls_not_ready(nodeid, rc); + return; + } + + /* this rwsem allows dlm_ls_stop() to wait for all dlm_recv threads to + be inactive (in this ls) before transitioning to recovery mode */ + + down_read(&ls->ls_recv_active); + if (hd->h_cmd == DLM_MSG) + dlm_receive_message(ls, ms, nodeid); + else + dlm_receive_rcom(ls, rc, nodeid); + up_read(&ls->ls_recv_active); + + dlm_put_lockspace(ls); +} static void recover_convert_waiter(struct dlm_ls *ls, struct dlm_lkb *lkb) { @@ -4429,7 +4455,8 @@ int dlm_user_unlock(struct dlm_ls *ls, struct dlm_user_args *ua_tmp, if (lvb_in && ua->lksb.sb_lvbptr) memcpy(ua->lksb.sb_lvbptr, lvb_in, DLM_USER_LVB_LEN); - ua->castparam = ua_tmp->castparam; + if (ua_tmp->castparam) + ua->castparam = ua_tmp->castparam; ua->user_lksb = ua_tmp->user_lksb; error = set_unlock_args(flags, ua, &args); @@ -4474,7 +4501,8 @@ int dlm_user_cancel(struct dlm_ls *ls, struct dlm_user_args *ua_tmp, goto out; ua = (struct dlm_user_args *)lkb->lkb_astparam; - ua->castparam = ua_tmp->castparam; + if (ua_tmp->castparam) + ua->castparam = ua_tmp->castparam; ua->user_lksb = ua_tmp->user_lksb; error = set_unlock_args(flags, ua, &args); diff --git a/fs/dlm/lock.h b/fs/dlm/lock.h index 1720313c22d..ada04680a1e 100644 --- a/fs/dlm/lock.h +++ b/fs/dlm/lock.h @@ -16,7 +16,8 @@ void dlm_print_rsb(struct dlm_rsb *r); void dlm_dump_rsb(struct dlm_rsb *r); void dlm_print_lkb(struct dlm_lkb *lkb); -int dlm_receive_message(struct dlm_header *hd, int nodeid, int recovery); +void dlm_receive_message_saved(struct dlm_ls *ls, struct dlm_message *ms); +void dlm_receive_buffer(struct dlm_header *hd, int nodeid); int dlm_modes_compat(int mode1, int mode2); int dlm_find_rsb(struct dlm_ls *ls, char *name, int namelen, unsigned int flags, struct dlm_rsb **r_ret); diff --git a/fs/dlm/lockspace.c b/fs/dlm/lockspace.c index f88f88fdedf..6353a838452 100644 --- a/fs/dlm/lockspace.c +++ b/fs/dlm/lockspace.c @@ -519,6 +519,7 @@ static int new_lockspace(char *name, int namelen, void **lockspace, ls->ls_recover_seq = 0; ls->ls_recover_args = NULL; init_rwsem(&ls->ls_in_recovery); + init_rwsem(&ls->ls_recv_active); INIT_LIST_HEAD(&ls->ls_requestqueue); mutex_init(&ls->ls_requestqueue_mutex); mutex_init(&ls->ls_clear_proc_locks); diff --git a/fs/dlm/lowcomms.c b/fs/dlm/lowcomms.c index 9e9d2e82f40..58bf3f5cdbe 100644 --- a/fs/dlm/lowcomms.c +++ b/fs/dlm/lowcomms.c @@ -334,18 +334,8 @@ static void close_connection(struct connection *con, bool and_other) con->rx_page = NULL; } - /* If we are an 'othercon' then NULL the pointer to us - from the parent and tidy ourself up */ - if (test_bit(CF_IS_OTHERCON, &con->flags)) { - struct connection *parent = __nodeid2con(con->nodeid, 0); - parent->othercon = NULL; - kmem_cache_free(con_cache, con); - } - else { - /* Parent connections get reused */ - con->retries = 0; - mutex_unlock(&con->sock_mutex); - } + con->retries = 0; + mutex_unlock(&con->sock_mutex); } /* We only send shutdown messages to nodes that are not part of the cluster */ @@ -731,6 +721,8 @@ static int tcp_accept_from_sock(struct connection *con) INIT_WORK(&othercon->swork, process_send_sockets); INIT_WORK(&othercon->rwork, process_recv_sockets); set_bit(CF_IS_OTHERCON, &othercon->flags); + } + if (!othercon->sock) { newcon->othercon = othercon; othercon->sock = newsock; newsock->sk->sk_user_data = othercon; @@ -1272,14 +1264,15 @@ static void send_to_sock(struct connection *con) if (len) { ret = sendpage(con->sock, e->page, offset, len, msg_flags); - if (ret == -EAGAIN || ret == 0) + if (ret == -EAGAIN || ret == 0) { + cond_resched(); goto out; + } if (ret <= 0) goto send_error; - } else { + } /* Don't starve people filling buffers */ cond_resched(); - } spin_lock(&con->writequeue_lock); e->offset += ret; diff --git a/fs/dlm/member.c b/fs/dlm/member.c index d09977528f6..e9cdcab306e 100644 --- a/fs/dlm/member.c +++ b/fs/dlm/member.c @@ -18,10 +18,6 @@ #include "rcom.h" #include "config.h" -/* - * Following called by dlm_recoverd thread - */ - static void add_ordered_member(struct dlm_ls *ls, struct dlm_member *new) { struct dlm_member *memb = NULL; @@ -250,18 +246,30 @@ int dlm_recover_members(struct dlm_ls *ls, struct dlm_recover *rv, int *neg_out) return error; } -/* - * Following called from lockspace.c - */ +/* Userspace guarantees that dlm_ls_stop() has completed on all nodes before + dlm_ls_start() is called on any of them to start the new recovery. */ int dlm_ls_stop(struct dlm_ls *ls) { int new; /* - * A stop cancels any recovery that's in progress (see RECOVERY_STOP, - * dlm_recovery_stopped()) and prevents any new locks from being - * processed (see RUNNING, dlm_locking_stopped()). + * Prevent dlm_recv from being in the middle of something when we do + * the stop. This includes ensuring dlm_recv isn't processing a + * recovery message (rcom), while dlm_recoverd is aborting and + * resetting things from an in-progress recovery. i.e. we want + * dlm_recoverd to abort its recovery without worrying about dlm_recv + * processing an rcom at the same time. Stopping dlm_recv also makes + * it easy for dlm_receive_message() to check locking stopped and add a + * message to the requestqueue without races. + */ + + down_write(&ls->ls_recv_active); + + /* + * Abort any recovery that's in progress (see RECOVERY_STOP, + * dlm_recovery_stopped()) and tell any other threads running in the + * dlm to quit any processing (see RUNNING, dlm_locking_stopped()). */ spin_lock(&ls->ls_recover_lock); @@ -271,8 +279,14 @@ int dlm_ls_stop(struct dlm_ls *ls) spin_unlock(&ls->ls_recover_lock); /* + * Let dlm_recv run again, now any normal messages will be saved on the + * requestqueue for later. + */ + + up_write(&ls->ls_recv_active); + + /* * This in_recovery lock does two things: - * * 1) Keeps this function from returning until all threads are out * of locking routines and locking is truely stopped. * 2) Keeps any new requests from being processed until it's unlocked @@ -284,9 +298,8 @@ int dlm_ls_stop(struct dlm_ls *ls) /* * The recoverd suspend/resume makes sure that dlm_recoverd (if - * running) has noticed the clearing of RUNNING above and quit - * processing the previous recovery. This will be true for all nodes - * before any nodes start the new recovery. + * running) has noticed RECOVERY_STOP above and quit processing the + * previous recovery. */ dlm_recoverd_suspend(ls); diff --git a/fs/dlm/midcomms.c b/fs/dlm/midcomms.c index a5126e0c68a..f8c69dda16a 100644 --- a/fs/dlm/midcomms.c +++ b/fs/dlm/midcomms.c @@ -2,7 +2,7 @@ ******************************************************************************* ** ** Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved. -** Copyright (C) 2004-2005 Red Hat, Inc. All rights reserved. +** Copyright (C) 2004-2007 Red Hat, Inc. All rights reserved. ** ** This copyrighted material is made available to anyone wishing to use, ** modify, copy, or redistribute it subject to the terms and conditions @@ -27,7 +27,6 @@ #include "dlm_internal.h" #include "lowcomms.h" #include "config.h" -#include "rcom.h" #include "lock.h" #include "midcomms.h" @@ -117,19 +116,7 @@ int dlm_process_incoming_buffer(int nodeid, const void *base, offset &= (limit - 1); len -= msglen; - switch (msg->h_cmd) { - case DLM_MSG: - dlm_receive_message(msg, nodeid, 0); - break; - - case DLM_RCOM: - dlm_receive_rcom(msg, nodeid); - break; - - default: - log_print("unknown msg type %x from %u: %u %u %u %u", - msg->h_cmd, nodeid, msglen, len, offset, ret); - } + dlm_receive_buffer(msg, nodeid); } if (msg != (struct dlm_header *) __tmp) diff --git a/fs/dlm/rcom.c b/fs/dlm/rcom.c index 188b91c027e..ae2fd97fa4a 100644 --- a/fs/dlm/rcom.c +++ b/fs/dlm/rcom.c @@ -2,7 +2,7 @@ ******************************************************************************* ** ** Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved. -** Copyright (C) 2005 Red Hat, Inc. All rights reserved. +** Copyright (C) 2005-2007 Red Hat, Inc. All rights reserved. ** ** This copyrighted material is made available to anyone wishing to use, ** modify, copy, or redistribute it subject to the terms and conditions @@ -386,7 +386,10 @@ static void receive_rcom_lock_reply(struct dlm_ls *ls, struct dlm_rcom *rc_in) dlm_recover_process_copy(ls, rc_in); } -static int send_ls_not_ready(int nodeid, struct dlm_rcom *rc_in) +/* If the lockspace doesn't exist then still send a status message + back; it's possible that it just doesn't have its global_id yet. */ + +int dlm_send_ls_not_ready(int nodeid, struct dlm_rcom *rc_in) { struct dlm_rcom *rc; struct rcom_config *rf; @@ -446,28 +449,11 @@ static int is_old_reply(struct dlm_ls *ls, struct dlm_rcom *rc) return rv; } -/* Called by dlm_recvd; corresponds to dlm_receive_message() but special +/* Called by dlm_recv; corresponds to dlm_receive_message() but special recovery-only comms are sent through here. */ -void dlm_receive_rcom(struct dlm_header *hd, int nodeid) +void dlm_receive_rcom(struct dlm_ls *ls, struct dlm_rcom *rc, int nodeid) { - struct dlm_rcom *rc = (struct dlm_rcom *) hd; - struct dlm_ls *ls; - - dlm_rcom_in(rc); - - /* If the lockspace doesn't exist then still send a status message - back; it's possible that it just doesn't have its global_id yet. */ - - ls = dlm_find_lockspace_global(hd->h_lockspace); - if (!ls) { - log_print("lockspace %x from %d type %x not found", - hd->h_lockspace, nodeid, rc->rc_type); - if (rc->rc_type == DLM_RCOM_STATUS) - send_ls_not_ready(nodeid, rc); - return; - } - if (dlm_recovery_stopped(ls) && (rc->rc_type != DLM_RCOM_STATUS)) { log_debug(ls, "ignoring recovery message %x from %d", rc->rc_type, nodeid); @@ -477,12 +463,6 @@ void dlm_receive_rcom(struct dlm_header *hd, int nodeid) if (is_old_reply(ls, rc)) goto out; - if (nodeid != rc->rc_header.h_nodeid) { - log_error(ls, "bad rcom nodeid %d from %d", - rc->rc_header.h_nodeid, nodeid); - goto out; - } - switch (rc->rc_type) { case DLM_RCOM_STATUS: receive_rcom_status(ls, rc); @@ -520,6 +500,6 @@ void dlm_receive_rcom(struct dlm_header *hd, int nodeid) DLM_ASSERT(0, printk("rc_type=%x\n", rc->rc_type);); } out: - dlm_put_lockspace(ls); + return; } diff --git a/fs/dlm/rcom.h b/fs/dlm/rcom.h index d7984321ff4..b09abd29ba3 100644 --- a/fs/dlm/rcom.h +++ b/fs/dlm/rcom.h @@ -2,7 +2,7 @@ ******************************************************************************* ** ** Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved. -** Copyright (C) 2005 Red Hat, Inc. All rights reserved. +** Copyright (C) 2005-2007 Red Hat, Inc. All rights reserved. ** ** This copyrighted material is made available to anyone wishing to use, ** modify, copy, or redistribute it subject to the terms and conditions @@ -18,7 +18,8 @@ int dlm_rcom_status(struct dlm_ls *ls, int nodeid); int dlm_rcom_names(struct dlm_ls *ls, int nodeid, char *last_name,int last_len); int dlm_send_rcom_lookup(struct dlm_rsb *r, int dir_nodeid); int dlm_send_rcom_lock(struct dlm_rsb *r, struct dlm_lkb *lkb); -void dlm_receive_rcom(struct dlm_header *hd, int nodeid); +void dlm_receive_rcom(struct dlm_ls *ls, struct dlm_rcom *rc, int nodeid); +int dlm_send_ls_not_ready(int nodeid, struct dlm_rcom *rc_in); #endif diff --git a/fs/dlm/recoverd.c b/fs/dlm/recoverd.c index 66575997861..4b89e20eebe 100644 --- a/fs/dlm/recoverd.c +++ b/fs/dlm/recoverd.c @@ -24,19 +24,28 @@ /* If the start for which we're re-enabling locking (seq) has been superseded - by a newer stop (ls_recover_seq), we need to leave locking disabled. */ + by a newer stop (ls_recover_seq), we need to leave locking disabled. + + We suspend dlm_recv threads here to avoid the race where dlm_recv a) sees + locking stopped and b) adds a message to the requestqueue, but dlm_recoverd + enables locking and clears the requestqueue between a and b. */ static int enable_locking(struct dlm_ls *ls, uint64_t seq) { int error = -EINTR; + down_write(&ls->ls_recv_active); + spin_lock(&ls->ls_recover_lock); if (ls->ls_recover_seq == seq) { set_bit(LSFL_RUNNING, &ls->ls_flags); + /* unblocks processes waiting to enter the dlm */ up_write(&ls->ls_in_recovery); error = 0; } spin_unlock(&ls->ls_recover_lock); + + up_write(&ls->ls_recv_active); return error; } diff --git a/fs/dlm/requestqueue.c b/fs/dlm/requestqueue.c index 65008d79c96..0de04f17cce 100644 --- a/fs/dlm/requestqueue.c +++ b/fs/dlm/requestqueue.c @@ -1,7 +1,7 @@ /****************************************************************************** ******************************************************************************* ** -** Copyright (C) 2005 Red Hat, Inc. All rights reserved. +** Copyright (C) 2005-2007 Red Hat, Inc. All rights reserved. ** ** This copyrighted material is made available to anyone wishing to use, ** modify, copy, or redistribute it subject to the terms and conditions @@ -20,7 +20,7 @@ struct rq_entry { struct list_head list; int nodeid; - char request[1]; + char request[0]; }; /* @@ -30,42 +30,39 @@ struct rq_entry { * lockspace is enabled on some while still suspended on others. */ -int dlm_add_requestqueue(struct dlm_ls *ls, int nodeid, struct dlm_header *hd) +void dlm_add_requestqueue(struct dlm_ls *ls, int nodeid, struct dlm_header *hd) { struct rq_entry *e; int length = hd->h_length; - int rv = 0; e = kmalloc(sizeof(struct rq_entry) + length, GFP_KERNEL); if (!e) { - log_print("dlm_add_requestqueue: out of memory\n"); - return 0; + log_print("dlm_add_requestqueue: out of memory len %d", length); + return; } e->nodeid = nodeid; memcpy(e->request, hd, length); - /* We need to check dlm_locking_stopped() after taking the mutex to - avoid a race where dlm_recoverd enables locking and runs - process_requestqueue between our earlier dlm_locking_stopped check - and this addition to the requestqueue. */ - mutex_lock(&ls->ls_requestqueue_mutex); - if (dlm_locking_stopped(ls)) - list_add_tail(&e->list, &ls->ls_requestqueue); - else { - log_debug(ls, "dlm_add_requestqueue skip from %d", nodeid); - kfree(e); - rv = -EAGAIN; - } + list_add_tail(&e->list, &ls->ls_requestqueue); mutex_unlock(&ls->ls_requestqueue_mutex); - return rv; } +/* + * Called by dlm_recoverd to process normal messages saved while recovery was + * happening. Normal locking has been enabled before this is called. dlm_recv + * upon receiving a message, will wait for all saved messages to be drained + * here before processing the message it got. If a new dlm_ls_stop() arrives + * while we're processing these saved messages, it may block trying to suspend + * dlm_recv if dlm_recv is waiting for us in dlm_wait_requestqueue. In that + * case, we don't abort since locking_stopped is still 0. If dlm_recv is not + * waiting for us, then this processing may be aborted due to locking_stopped. + */ + int dlm_process_requestqueue(struct dlm_ls *ls) { struct rq_entry *e; - struct dlm_header *hd; int error = 0; mutex_lock(&ls->ls_requestqueue_mutex); @@ -79,14 +76,7 @@ int dlm_process_requestqueue(struct dlm_ls *ls) e = list_entry(ls->ls_requestqueue.next, struct rq_entry, list); mutex_unlock(&ls->ls_requestqueue_mutex); - hd = (struct dlm_header *) e->request; - error = dlm_receive_message(hd, e->nodeid, 1); - - if (error == -EINTR) { - /* entry is left on requestqueue */ - log_debug(ls, "process_requestqueue abort eintr"); - break; - } + dlm_receive_message_saved(ls, (struct dlm_message *)e->request); mutex_lock(&ls->ls_requestqueue_mutex); list_del(&e->list); @@ -106,10 +96,12 @@ int dlm_process_requestqueue(struct dlm_ls *ls) /* * After recovery is done, locking is resumed and dlm_recoverd takes all the - * saved requests and processes them as they would have been by dlm_recvd. At - * the same time, dlm_recvd will start receiving new requests from remote - * nodes. We want to delay dlm_recvd processing new requests until - * dlm_recoverd has finished processing the old saved requests. + * saved requests and processes them as they would have been by dlm_recv. At + * the same time, dlm_recv will start receiving new requests from remote nodes. + * We want to delay dlm_recv processing new requests until dlm_recoverd has + * finished processing the old saved requests. We don't check for locking + * stopped here because dlm_ls_stop won't stop locking until it's suspended us + * (dlm_recv). */ void dlm_wait_requestqueue(struct dlm_ls *ls) @@ -118,8 +110,6 @@ void dlm_wait_requestqueue(struct dlm_ls *ls) mutex_lock(&ls->ls_requestqueue_mutex); if (list_empty(&ls->ls_requestqueue)) break; - if (dlm_locking_stopped(ls)) - break; mutex_unlock(&ls->ls_requestqueue_mutex); schedule(); } diff --git a/fs/dlm/requestqueue.h b/fs/dlm/requestqueue.h index 6a53ea03335..aba34fc05ee 100644 --- a/fs/dlm/requestqueue.h +++ b/fs/dlm/requestqueue.h @@ -1,7 +1,7 @@ /****************************************************************************** ******************************************************************************* ** -** Copyright (C) 2005 Red Hat, Inc. All rights reserved. +** Copyright (C) 2005-2007 Red Hat, Inc. All rights reserved. ** ** This copyrighted material is made available to anyone wishing to use, ** modify, copy, or redistribute it subject to the terms and conditions @@ -13,7 +13,7 @@ #ifndef __REQUESTQUEUE_DOT_H__ #define __REQUESTQUEUE_DOT_H__ -int dlm_add_requestqueue(struct dlm_ls *ls, int nodeid, struct dlm_header *hd); +void dlm_add_requestqueue(struct dlm_ls *ls, int nodeid, struct dlm_header *hd); int dlm_process_requestqueue(struct dlm_ls *ls); void dlm_wait_requestqueue(struct dlm_ls *ls); void dlm_purge_requestqueue(struct dlm_ls *ls); diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c index cd805a66880..93fa427bb5f 100644 --- a/fs/gfs2/bmap.c +++ b/fs/gfs2/bmap.c @@ -93,9 +93,10 @@ static int gfs2_unstuffer_page(struct gfs2_inode *ip, struct buffer_head *dibh, map_bh(bh, inode->i_sb, block); set_buffer_uptodate(bh); + if (!gfs2_is_jdata(ip)) + mark_buffer_dirty(bh); if (sdp->sd_args.ar_data == GFS2_DATA_ORDERED || gfs2_is_jdata(ip)) gfs2_trans_add_bh(ip->i_gl, bh, 0); - mark_buffer_dirty(bh); if (release) { unlock_page(page); @@ -1085,6 +1086,33 @@ static int do_shrink(struct gfs2_inode *ip, u64 size) return error; } +static int do_touch(struct gfs2_inode *ip, u64 size) +{ + struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode); + struct buffer_head *dibh; + int error; + + error = gfs2_trans_begin(sdp, RES_DINODE, 0); + if (error) + return error; + + down_write(&ip->i_rw_mutex); + + error = gfs2_meta_inode_buffer(ip, &dibh); + if (error) + goto do_touch_out; + + ip->i_inode.i_mtime = ip->i_inode.i_ctime = CURRENT_TIME; + gfs2_trans_add_bh(ip->i_gl, dibh, 1); + gfs2_dinode_out(ip, dibh->b_data); + brelse(dibh); + +do_touch_out: + up_write(&ip->i_rw_mutex); + gfs2_trans_end(sdp); + return error; +} + /** * gfs2_truncatei - make a file a given size * @ip: the inode @@ -1105,8 +1133,11 @@ int gfs2_truncatei(struct gfs2_inode *ip, u64 size) if (size > ip->i_di.di_size) error = do_grow(ip, size); - else + else if (size < ip->i_di.di_size) error = do_shrink(ip, size); + else + /* update time stamps */ + error = do_touch(ip, size); return error; } diff --git a/fs/gfs2/daemon.c b/fs/gfs2/daemon.c index 3548d9f31e0..3731ab0771d 100644 --- a/fs/gfs2/daemon.c +++ b/fs/gfs2/daemon.c @@ -35,30 +35,6 @@ The kthread functions used to start these daemons block and flush signals. */ /** - * gfs2_scand - Look for cached glocks and inodes to toss from memory - * @sdp: Pointer to GFS2 superblock - * - * One of these daemons runs, finding candidates to add to sd_reclaim_list. - * See gfs2_glockd() - */ - -int gfs2_scand(void *data) -{ - struct gfs2_sbd *sdp = data; - unsigned long t; - - while (!kthread_should_stop()) { - gfs2_scand_internal(sdp); - t = gfs2_tune_get(sdp, gt_scand_secs) * HZ; - if (freezing(current)) - refrigerator(); - schedule_timeout_interruptible(t); - } - - return 0; -} - -/** * gfs2_glockd - Reclaim unused glock structures * @sdp: Pointer to GFS2 superblock * diff --git a/fs/gfs2/daemon.h b/fs/gfs2/daemon.h index 801007120fb..0de9b355795 100644 --- a/fs/gfs2/daemon.h +++ b/fs/gfs2/daemon.h @@ -10,7 +10,6 @@ #ifndef __DAEMON_DOT_H__ #define __DAEMON_DOT_H__ -int gfs2_scand(void *data); int gfs2_glockd(void *data); int gfs2_recoverd(void *data); int gfs2_logd(void *data); diff --git a/fs/gfs2/dir.c b/fs/gfs2/dir.c index 2beb2f401aa..9949bb746a5 100644 --- a/fs/gfs2/dir.c +++ b/fs/gfs2/dir.c @@ -1043,6 +1043,7 @@ static int dir_split_leaf(struct inode *inode, const struct qstr *name) error = gfs2_meta_inode_buffer(dip, &dibh); if (!gfs2_assert_withdraw(GFS2_SB(&dip->i_inode), !error)) { + gfs2_trans_add_bh(dip->i_gl, dibh, 1); dip->i_di.di_blocks++; gfs2_set_inode_blocks(&dip->i_inode); gfs2_dinode_out(dip, dibh->b_data); @@ -1501,7 +1502,7 @@ struct inode *gfs2_dir_search(struct inode *dir, const struct qstr *name) inode = gfs2_inode_lookup(dir->i_sb, be16_to_cpu(dent->de_type), be64_to_cpu(dent->de_inum.no_addr), - be64_to_cpu(dent->de_inum.no_formal_ino)); + be64_to_cpu(dent->de_inum.no_formal_ino), 0); brelse(bh); return inode; } diff --git a/fs/gfs2/eaops.c b/fs/gfs2/eaops.c index 1ab3e9d7388..aa8dbf303f6 100644 --- a/fs/gfs2/eaops.c +++ b/fs/gfs2/eaops.c @@ -200,28 +200,28 @@ static int security_eo_remove(struct gfs2_inode *ip, struct gfs2_ea_request *er) return gfs2_ea_remove_i(ip, er); } -static struct gfs2_eattr_operations gfs2_user_eaops = { +static const struct gfs2_eattr_operations gfs2_user_eaops = { .eo_get = user_eo_get, .eo_set = user_eo_set, .eo_remove = user_eo_remove, .eo_name = "user", }; -struct gfs2_eattr_operations gfs2_system_eaops = { +const struct gfs2_eattr_operations gfs2_system_eaops = { .eo_get = system_eo_get, .eo_set = system_eo_set, .eo_remove = system_eo_remove, .eo_name = "system", }; -static struct gfs2_eattr_operations gfs2_security_eaops = { +static const struct gfs2_eattr_operations gfs2_security_eaops = { .eo_get = security_eo_get, .eo_set = security_eo_set, .eo_remove = security_eo_remove, .eo_name = "security", }; -struct gfs2_eattr_operations *gfs2_ea_ops[] = { +const struct gfs2_eattr_operations *gfs2_ea_ops[] = { NULL, &gfs2_user_eaops, &gfs2_system_eaops, diff --git a/fs/gfs2/eaops.h b/fs/gfs2/eaops.h index 508b4f7a244..da2f7fbbb40 100644 --- a/fs/gfs2/eaops.h +++ b/fs/gfs2/eaops.h @@ -22,9 +22,9 @@ struct gfs2_eattr_operations { unsigned int gfs2_ea_name2type(const char *name, const char **truncated_name); -extern struct gfs2_eattr_operations gfs2_system_eaops; +extern const struct gfs2_eattr_operations gfs2_system_eaops; -extern struct gfs2_eattr_operations *gfs2_ea_ops[]; +extern const struct gfs2_eattr_operations *gfs2_ea_ops[]; #endif /* __EAOPS_DOT_H__ */ diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c index 3f0974e1afe..a37efe4aae6 100644 --- a/fs/gfs2/glock.c +++ b/fs/gfs2/glock.c @@ -25,8 +25,10 @@ #include <asm/uaccess.h> #include <linux/seq_file.h> #include <linux/debugfs.h> -#include <linux/module.h> -#include <linux/kallsyms.h> +#include <linux/kthread.h> +#include <linux/freezer.h> +#include <linux/workqueue.h> +#include <linux/jiffies.h> #include "gfs2.h" #include "incore.h" @@ -48,7 +50,6 @@ struct glock_iter { int hash; /* hash bucket index */ struct gfs2_sbd *sdp; /* incore superblock */ struct gfs2_glock *gl; /* current glock struct */ - struct hlist_head *hb_list; /* current hash bucket ptr */ struct seq_file *seq; /* sequence file for debugfs */ char string[512]; /* scratch space */ }; @@ -59,8 +60,13 @@ static int gfs2_dump_lockstate(struct gfs2_sbd *sdp); static int dump_glock(struct glock_iter *gi, struct gfs2_glock *gl); static void gfs2_glock_xmote_th(struct gfs2_glock *gl, struct gfs2_holder *gh); static void gfs2_glock_drop_th(struct gfs2_glock *gl); +static void run_queue(struct gfs2_glock *gl); + static DECLARE_RWSEM(gfs2_umount_flush_sem); static struct dentry *gfs2_root; +static struct task_struct *scand_process; +static unsigned int scand_secs = 5; +static struct workqueue_struct *glock_workqueue; #define GFS2_GL_HASH_SHIFT 15 #define GFS2_GL_HASH_SIZE (1 << GFS2_GL_HASH_SHIFT) @@ -276,6 +282,18 @@ static struct gfs2_glock *gfs2_glock_find(const struct gfs2_sbd *sdp, return gl; } +static void glock_work_func(struct work_struct *work) +{ + struct gfs2_glock *gl = container_of(work, struct gfs2_glock, gl_work.work); + + spin_lock(&gl->gl_spin); + if (test_and_clear_bit(GLF_PENDING_DEMOTE, &gl->gl_flags)) + set_bit(GLF_DEMOTE, &gl->gl_flags); + run_queue(gl); + spin_unlock(&gl->gl_spin); + gfs2_glock_put(gl); +} + /** * gfs2_glock_get() - Get a glock, or create one if one doesn't exist * @sdp: The GFS2 superblock @@ -315,6 +333,7 @@ int gfs2_glock_get(struct gfs2_sbd *sdp, u64 number, gl->gl_name = name; atomic_set(&gl->gl_ref, 1); gl->gl_state = LM_ST_UNLOCKED; + gl->gl_demote_state = LM_ST_EXCLUSIVE; gl->gl_hash = hash; gl->gl_owner_pid = 0; gl->gl_ip = 0; @@ -323,10 +342,12 @@ int gfs2_glock_get(struct gfs2_sbd *sdp, u64 number, gl->gl_req_bh = NULL; gl->gl_vn = 0; gl->gl_stamp = jiffies; + gl->gl_tchange = jiffies; gl->gl_object = NULL; gl->gl_sbd = sdp; gl->gl_aspace = NULL; lops_init_le(&gl->gl_le, &gfs2_glock_lops); + INIT_DELAYED_WORK(&gl->gl_work, glock_work_func); /* If this glock protects actual on-disk data or metadata blocks, create a VFS inode to manage the pages/buffers holding them. */ @@ -440,6 +461,8 @@ static void wait_on_holder(struct gfs2_holder *gh) static void gfs2_demote_wake(struct gfs2_glock *gl) { + BUG_ON(!spin_is_locked(&gl->gl_spin)); + gl->gl_demote_state = LM_ST_EXCLUSIVE; clear_bit(GLF_DEMOTE, &gl->gl_flags); smp_mb__after_clear_bit(); wake_up_bit(&gl->gl_flags, GLF_DEMOTE); @@ -545,12 +568,14 @@ static int rq_demote(struct gfs2_glock *gl) return 0; } set_bit(GLF_LOCK, &gl->gl_flags); - spin_unlock(&gl->gl_spin); if (gl->gl_demote_state == LM_ST_UNLOCKED || - gl->gl_state != LM_ST_EXCLUSIVE) + gl->gl_state != LM_ST_EXCLUSIVE) { + spin_unlock(&gl->gl_spin); gfs2_glock_drop_th(gl); - else + } else { + spin_unlock(&gl->gl_spin); gfs2_glock_xmote_th(gl, NULL); + } spin_lock(&gl->gl_spin); return 0; @@ -679,24 +704,25 @@ static void gfs2_glmutex_unlock(struct gfs2_glock *gl) * practise: LM_ST_SHARED and LM_ST_UNLOCKED */ -static void handle_callback(struct gfs2_glock *gl, unsigned int state, int remote) +static void handle_callback(struct gfs2_glock *gl, unsigned int state, + int remote, unsigned long delay) { + int bit = delay ? GLF_PENDING_DEMOTE : GLF_DEMOTE; + spin_lock(&gl->gl_spin); - if (test_and_set_bit(GLF_DEMOTE, &gl->gl_flags) == 0) { + set_bit(bit, &gl->gl_flags); + if (gl->gl_demote_state == LM_ST_EXCLUSIVE) { gl->gl_demote_state = state; gl->gl_demote_time = jiffies; if (remote && gl->gl_ops->go_type == LM_TYPE_IOPEN && gl->gl_object) { - struct inode *inode = igrab(gl->gl_object); + gfs2_glock_schedule_for_reclaim(gl); spin_unlock(&gl->gl_spin); - if (inode) { - d_prune_aliases(inode); - iput(inode); - } return; } - } else if (gl->gl_demote_state != LM_ST_UNLOCKED) { - gl->gl_demote_state = state; + } else if (gl->gl_demote_state != LM_ST_UNLOCKED && + gl->gl_demote_state != state) { + gl->gl_demote_state = LM_ST_UNLOCKED; } spin_unlock(&gl->gl_spin); } @@ -723,6 +749,7 @@ static void state_change(struct gfs2_glock *gl, unsigned int new_state) } gl->gl_state = new_state; + gl->gl_tchange = jiffies; } /** @@ -760,10 +787,20 @@ static void xmote_bh(struct gfs2_glock *gl, unsigned int ret) if (!gh) { gl->gl_stamp = jiffies; - if (ret & LM_OUT_CANCELED) + if (ret & LM_OUT_CANCELED) { op_done = 0; - else + } else { + spin_lock(&gl->gl_spin); + if (gl->gl_state != gl->gl_demote_state) { + gl->gl_req_bh = NULL; + spin_unlock(&gl->gl_spin); + gfs2_glock_drop_th(gl); + gfs2_glock_put(gl); + return; + } gfs2_demote_wake(gl); + spin_unlock(&gl->gl_spin); + } } else { spin_lock(&gl->gl_spin); list_del_init(&gh->gh_list); @@ -799,7 +836,6 @@ out: gl->gl_req_gh = NULL; gl->gl_req_bh = NULL; clear_bit(GLF_LOCK, &gl->gl_flags); - run_queue(gl); spin_unlock(&gl->gl_spin); } @@ -817,7 +853,7 @@ out: * */ -void gfs2_glock_xmote_th(struct gfs2_glock *gl, struct gfs2_holder *gh) +static void gfs2_glock_xmote_th(struct gfs2_glock *gl, struct gfs2_holder *gh) { struct gfs2_sbd *sdp = gl->gl_sbd; int flags = gh ? gh->gh_flags : 0; @@ -871,7 +907,6 @@ static void drop_bh(struct gfs2_glock *gl, unsigned int ret) gfs2_assert_warn(sdp, !ret); state_change(gl, LM_ST_UNLOCKED); - gfs2_demote_wake(gl); if (glops->go_inval) glops->go_inval(gl, DIO_METADATA); @@ -884,10 +919,10 @@ static void drop_bh(struct gfs2_glock *gl, unsigned int ret) } spin_lock(&gl->gl_spin); + gfs2_demote_wake(gl); gl->gl_req_gh = NULL; gl->gl_req_bh = NULL; clear_bit(GLF_LOCK, &gl->gl_flags); - run_queue(gl); spin_unlock(&gl->gl_spin); gfs2_glock_put(gl); @@ -1067,24 +1102,31 @@ static void add_to_queue(struct gfs2_holder *gh) if (test_and_set_bit(HIF_WAIT, &gh->gh_iflags)) BUG(); - existing = find_holder_by_owner(&gl->gl_holders, gh->gh_owner_pid); - if (existing) { - print_symbol(KERN_WARNING "original: %s\n", existing->gh_ip); - printk(KERN_INFO "pid : %d\n", existing->gh_owner_pid); - printk(KERN_INFO "lock type : %d lock state : %d\n", - existing->gh_gl->gl_name.ln_type, existing->gh_gl->gl_state); - print_symbol(KERN_WARNING "new: %s\n", gh->gh_ip); - printk(KERN_INFO "pid : %d\n", gh->gh_owner_pid); - printk(KERN_INFO "lock type : %d lock state : %d\n", - gl->gl_name.ln_type, gl->gl_state); - BUG(); - } - - existing = find_holder_by_owner(&gl->gl_waiters3, gh->gh_owner_pid); - if (existing) { - print_symbol(KERN_WARNING "original: %s\n", existing->gh_ip); - print_symbol(KERN_WARNING "new: %s\n", gh->gh_ip); - BUG(); + if (!(gh->gh_flags & GL_FLOCK)) { + existing = find_holder_by_owner(&gl->gl_holders, + gh->gh_owner_pid); + if (existing) { + print_symbol(KERN_WARNING "original: %s\n", + existing->gh_ip); + printk(KERN_INFO "pid : %d\n", existing->gh_owner_pid); + printk(KERN_INFO "lock type : %d lock state : %d\n", + existing->gh_gl->gl_name.ln_type, + existing->gh_gl->gl_state); + print_symbol(KERN_WARNING "new: %s\n", gh->gh_ip); + printk(KERN_INFO "pid : %d\n", gh->gh_owner_pid); + printk(KERN_INFO "lock type : %d lock state : %d\n", + gl->gl_name.ln_type, gl->gl_state); + BUG(); + } + + existing = find_holder_by_owner(&gl->gl_waiters3, + gh->gh_owner_pid); + if (existing) { + print_symbol(KERN_WARNING "original: %s\n", + existing->gh_ip); + print_symbol(KERN_WARNING "new: %s\n", gh->gh_ip); + BUG(); + } } if (gh->gh_flags & LM_FLAG_PRIORITY) @@ -1195,9 +1237,10 @@ void gfs2_glock_dq(struct gfs2_holder *gh) { struct gfs2_glock *gl = gh->gh_gl; const struct gfs2_glock_operations *glops = gl->gl_ops; + unsigned delay = 0; if (gh->gh_flags & GL_NOCACHE) - handle_callback(gl, LM_ST_UNLOCKED, 0); + handle_callback(gl, LM_ST_UNLOCKED, 0, 0); gfs2_glmutex_lock(gl); @@ -1215,8 +1258,14 @@ void gfs2_glock_dq(struct gfs2_holder *gh) } clear_bit(GLF_LOCK, &gl->gl_flags); - run_queue(gl); spin_unlock(&gl->gl_spin); + + gfs2_glock_hold(gl); + if (test_bit(GLF_PENDING_DEMOTE, &gl->gl_flags) && + !test_bit(GLF_DEMOTE, &gl->gl_flags)) + delay = gl->gl_ops->go_min_hold_time; + if (queue_delayed_work(glock_workqueue, &gl->gl_work, delay) == 0) + gfs2_glock_put(gl); } void gfs2_glock_dq_wait(struct gfs2_holder *gh) @@ -1443,18 +1492,21 @@ static void blocking_cb(struct gfs2_sbd *sdp, struct lm_lockname *name, unsigned int state) { struct gfs2_glock *gl; + unsigned long delay = 0; + unsigned long holdtime; + unsigned long now = jiffies; gl = gfs2_glock_find(sdp, name); if (!gl) return; - handle_callback(gl, state, 1); - - spin_lock(&gl->gl_spin); - run_queue(gl); - spin_unlock(&gl->gl_spin); + holdtime = gl->gl_tchange + gl->gl_ops->go_min_hold_time; + if (time_before(now, holdtime)) + delay = holdtime - now; - gfs2_glock_put(gl); + handle_callback(gl, state, 1, delay); + if (queue_delayed_work(glock_workqueue, &gl->gl_work, delay) == 0) + gfs2_glock_put(gl); } /** @@ -1495,7 +1547,8 @@ void gfs2_glock_cb(void *cb_data, unsigned int type, void *data) return; if (!gfs2_assert_warn(sdp, gl->gl_req_bh)) gl->gl_req_bh(gl, async->lc_ret); - gfs2_glock_put(gl); + if (queue_delayed_work(glock_workqueue, &gl->gl_work, 0) == 0) + gfs2_glock_put(gl); up_read(&gfs2_umount_flush_sem); return; } @@ -1588,7 +1641,7 @@ void gfs2_reclaim_glock(struct gfs2_sbd *sdp) if (gfs2_glmutex_trylock(gl)) { if (list_empty(&gl->gl_holders) && gl->gl_state != LM_ST_UNLOCKED && demote_ok(gl)) - handle_callback(gl, LM_ST_UNLOCKED, 0); + handle_callback(gl, LM_ST_UNLOCKED, 0, 0); gfs2_glmutex_unlock(gl); } @@ -1617,7 +1670,7 @@ static int examine_bucket(glock_examiner examiner, struct gfs2_sbd *sdp, goto out; gl = list_entry(head->first, struct gfs2_glock, gl_list); while(1) { - if (gl->gl_sbd == sdp) { + if (!sdp || gl->gl_sbd == sdp) { gfs2_glock_hold(gl); read_unlock(gl_lock_addr(hash)); if (prev) @@ -1635,6 +1688,7 @@ out: read_unlock(gl_lock_addr(hash)); if (prev) gfs2_glock_put(prev); + cond_resched(); return has_entries; } @@ -1663,20 +1717,6 @@ out_schedule: } /** - * gfs2_scand_internal - Look for glocks and inodes to toss from memory - * @sdp: the filesystem - * - */ - -void gfs2_scand_internal(struct gfs2_sbd *sdp) -{ - unsigned int x; - - for (x = 0; x < GFS2_GL_HASH_SIZE; x++) - examine_bucket(scan_glock, sdp, x); -} - -/** * clear_glock - look at a glock and see if we can free it from glock cache * @gl: the glock to look at * @@ -1701,7 +1741,7 @@ static void clear_glock(struct gfs2_glock *gl) if (gfs2_glmutex_trylock(gl)) { if (list_empty(&gl->gl_holders) && gl->gl_state != LM_ST_UNLOCKED) - handle_callback(gl, LM_ST_UNLOCKED, 0); + handle_callback(gl, LM_ST_UNLOCKED, 0, 0); gfs2_glmutex_unlock(gl); } } @@ -1843,7 +1883,7 @@ static int dump_glock(struct glock_iter *gi, struct gfs2_glock *gl) spin_lock(&gl->gl_spin); - print_dbg(gi, "Glock 0x%p (%u, %llu)\n", gl, gl->gl_name.ln_type, + print_dbg(gi, "Glock 0x%p (%u, 0x%llx)\n", gl, gl->gl_name.ln_type, (unsigned long long)gl->gl_name.ln_number); print_dbg(gi, " gl_flags ="); for (x = 0; x < 32; x++) { @@ -1963,6 +2003,35 @@ static int gfs2_dump_lockstate(struct gfs2_sbd *sdp) return error; } +/** + * gfs2_scand - Look for cached glocks and inodes to toss from memory + * @sdp: Pointer to GFS2 superblock + * + * One of these daemons runs, finding candidates to add to sd_reclaim_list. + * See gfs2_glockd() + */ + +static int gfs2_scand(void *data) +{ + unsigned x; + unsigned delay; + + while (!kthread_should_stop()) { + for (x = 0; x < GFS2_GL_HASH_SIZE; x++) + examine_bucket(scan_glock, NULL, x); + if (freezing(current)) + refrigerator(); + delay = scand_secs; + if (delay < 1) + delay = 1; + schedule_timeout_interruptible(delay * HZ); + } + + return 0; +} + + + int __init gfs2_glock_init(void) { unsigned i; @@ -1974,52 +2043,69 @@ int __init gfs2_glock_init(void) rwlock_init(&gl_hash_locks[i]); } #endif + + scand_process = kthread_run(gfs2_scand, NULL, "gfs2_scand"); + if (IS_ERR(scand_process)) + return PTR_ERR(scand_process); + + glock_workqueue = create_workqueue("glock_workqueue"); + if (IS_ERR(glock_workqueue)) { + kthread_stop(scand_process); + return PTR_ERR(glock_workqueue); + } + return 0; } +void gfs2_glock_exit(void) +{ + destroy_workqueue(glock_workqueue); + kthread_stop(scand_process); +} + +module_param(scand_secs, uint, S_IRUGO|S_IWUSR); +MODULE_PARM_DESC(scand_secs, "The number of seconds between scand runs"); + static int gfs2_glock_iter_next(struct glock_iter *gi) { + struct gfs2_glock *gl; + +restart: read_lock(gl_lock_addr(gi->hash)); - while (1) { - if (!gi->hb_list) { /* If we don't have a hash bucket yet */ - gi->hb_list = &gl_hash_table[gi->hash].hb_list; - if (hlist_empty(gi->hb_list)) { - read_unlock(gl_lock_addr(gi->hash)); - gi->hash++; - read_lock(gl_lock_addr(gi->hash)); - gi->hb_list = NULL; - if (gi->hash >= GFS2_GL_HASH_SIZE) { - read_unlock(gl_lock_addr(gi->hash)); - return 1; - } - else - continue; - } - if (!hlist_empty(gi->hb_list)) { - gi->gl = list_entry(gi->hb_list->first, - struct gfs2_glock, - gl_list); - } - } else { - if (gi->gl->gl_list.next == NULL) { - read_unlock(gl_lock_addr(gi->hash)); - gi->hash++; - read_lock(gl_lock_addr(gi->hash)); - gi->hb_list = NULL; - continue; - } - gi->gl = list_entry(gi->gl->gl_list.next, - struct gfs2_glock, gl_list); - } + gl = gi->gl; + if (gl) { + gi->gl = hlist_entry(gl->gl_list.next, + struct gfs2_glock, gl_list); if (gi->gl) - break; + gfs2_glock_hold(gi->gl); } read_unlock(gl_lock_addr(gi->hash)); + if (gl) + gfs2_glock_put(gl); + if (gl && gi->gl == NULL) + gi->hash++; + while(gi->gl == NULL) { + if (gi->hash >= GFS2_GL_HASH_SIZE) + return 1; + read_lock(gl_lock_addr(gi->hash)); + gi->gl = hlist_entry(gl_hash_table[gi->hash].hb_list.first, + struct gfs2_glock, gl_list); + if (gi->gl) + gfs2_glock_hold(gi->gl); + read_unlock(gl_lock_addr(gi->hash)); + gi->hash++; + } + + if (gi->sdp != gi->gl->gl_sbd) + goto restart; + return 0; } static void gfs2_glock_iter_free(struct glock_iter *gi) { + if (gi->gl) + gfs2_glock_put(gi->gl); kfree(gi); } @@ -2033,9 +2119,8 @@ static struct glock_iter *gfs2_glock_iter_init(struct gfs2_sbd *sdp) gi->sdp = sdp; gi->hash = 0; - gi->gl = NULL; - gi->hb_list = NULL; gi->seq = NULL; + gi->gl = NULL; memset(gi->string, 0, sizeof(gi->string)); if (gfs2_glock_iter_next(gi)) { @@ -2055,7 +2140,7 @@ static void *gfs2_glock_seq_start(struct seq_file *file, loff_t *pos) if (!gi) return NULL; - while (n--) { + while(n--) { if (gfs2_glock_iter_next(gi)) { gfs2_glock_iter_free(gi); return NULL; @@ -2082,7 +2167,9 @@ static void *gfs2_glock_seq_next(struct seq_file *file, void *iter_ptr, static void gfs2_glock_seq_stop(struct seq_file *file, void *iter_ptr) { - /* nothing for now */ + struct glock_iter *gi = iter_ptr; + if (gi) + gfs2_glock_iter_free(gi); } static int gfs2_glock_seq_show(struct seq_file *file, void *iter_ptr) @@ -2095,7 +2182,7 @@ static int gfs2_glock_seq_show(struct seq_file *file, void *iter_ptr) return 0; } -static struct seq_operations gfs2_glock_seq_ops = { +static const struct seq_operations gfs2_glock_seq_ops = { .start = gfs2_glock_seq_start, .next = gfs2_glock_seq_next, .stop = gfs2_glock_seq_stop, diff --git a/fs/gfs2/glock.h b/fs/gfs2/glock.h index 7721ca3fff9..b16f604eea9 100644 --- a/fs/gfs2/glock.h +++ b/fs/gfs2/glock.h @@ -26,6 +26,7 @@ #define GL_SKIP 0x00000100 #define GL_ATIME 0x00000200 #define GL_NOCACHE 0x00000400 +#define GL_FLOCK 0x00000800 #define GL_NOCANCEL 0x00001000 #define GLR_TRYFAILED 13 @@ -132,11 +133,11 @@ void gfs2_glock_cb(void *cb_data, unsigned int type, void *data); void gfs2_glock_schedule_for_reclaim(struct gfs2_glock *gl); void gfs2_reclaim_glock(struct gfs2_sbd *sdp); - -void gfs2_scand_internal(struct gfs2_sbd *sdp); void gfs2_gl_hash_clear(struct gfs2_sbd *sdp, int wait); int __init gfs2_glock_init(void); +void gfs2_glock_exit(void); + int gfs2_create_debugfs_file(struct gfs2_sbd *sdp); void gfs2_delete_debugfs_file(struct gfs2_sbd *sdp); int gfs2_register_debugfs(void); diff --git a/fs/gfs2/glops.c b/fs/gfs2/glops.c index 777ca46010e..4670dcb2a87 100644 --- a/fs/gfs2/glops.c +++ b/fs/gfs2/glops.c @@ -41,7 +41,6 @@ static void gfs2_ail_empty_gl(struct gfs2_glock *gl) struct list_head *head = &gl->gl_ail_list; struct gfs2_bufdata *bd; struct buffer_head *bh; - u64 blkno; int error; blocks = atomic_read(&gl->gl_ail_count); @@ -57,19 +56,12 @@ static void gfs2_ail_empty_gl(struct gfs2_glock *gl) bd = list_entry(head->next, struct gfs2_bufdata, bd_ail_gl_list); bh = bd->bd_bh; - blkno = bh->b_blocknr; + gfs2_remove_from_ail(NULL, bd); + bd->bd_bh = NULL; + bh->b_private = NULL; + bd->bd_blkno = bh->b_blocknr; gfs2_assert_withdraw(sdp, !buffer_busy(bh)); - - bd->bd_ail = NULL; - list_del(&bd->bd_ail_st_list); - list_del(&bd->bd_ail_gl_list); - atomic_dec(&gl->gl_ail_count); - brelse(bh); - gfs2_log_unlock(sdp); - - gfs2_trans_add_revoke(sdp, blkno); - - gfs2_log_lock(sdp); + gfs2_trans_add_revoke(sdp, bd); } gfs2_assert_withdraw(sdp, !atomic_read(&gl->gl_ail_count)); gfs2_log_unlock(sdp); @@ -156,9 +148,11 @@ static void inode_go_sync(struct gfs2_glock *gl) ip = NULL; if (test_bit(GLF_DIRTY, &gl->gl_flags)) { - if (ip) + if (ip && !gfs2_is_jdata(ip)) filemap_fdatawrite(ip->i_inode.i_mapping); gfs2_log_flush(gl->gl_sbd, gl); + if (ip && gfs2_is_jdata(ip)) + filemap_fdatawrite(ip->i_inode.i_mapping); gfs2_meta_sync(gl); if (ip) { struct address_space *mapping = ip->i_inode.i_mapping; @@ -452,6 +446,7 @@ const struct gfs2_glock_operations gfs2_inode_glops = { .go_lock = inode_go_lock, .go_unlock = inode_go_unlock, .go_type = LM_TYPE_INODE, + .go_min_hold_time = HZ / 10, }; const struct gfs2_glock_operations gfs2_rgrp_glops = { @@ -462,6 +457,7 @@ const struct gfs2_glock_operations gfs2_rgrp_glops = { .go_lock = rgrp_go_lock, .go_unlock = rgrp_go_unlock, .go_type = LM_TYPE_RGRP, + .go_min_hold_time = HZ / 10, }; const struct gfs2_glock_operations gfs2_trans_glops = { diff --git a/fs/gfs2/incore.h b/fs/gfs2/incore.h index 170ba93829c..eaddfb5a8e6 100644 --- a/fs/gfs2/incore.h +++ b/fs/gfs2/incore.h @@ -11,6 +11,7 @@ #define __INCORE_DOT_H__ #include <linux/fs.h> +#include <linux/workqueue.h> #define DIO_WAIT 0x00000010 #define DIO_METADATA 0x00000020 @@ -113,7 +114,13 @@ struct gfs2_bufdata { struct buffer_head *bd_bh; struct gfs2_glock *bd_gl; - struct list_head bd_list_tr; + union { + struct list_head list_tr; + u64 blkno; + } u; +#define bd_list_tr u.list_tr +#define bd_blkno u.blkno + struct gfs2_log_element bd_le; struct gfs2_ail *bd_ail; @@ -130,6 +137,7 @@ struct gfs2_glock_operations { int (*go_lock) (struct gfs2_holder *gh); void (*go_unlock) (struct gfs2_holder *gh); const int go_type; + const unsigned long go_min_hold_time; }; enum { @@ -161,6 +169,7 @@ enum { GLF_LOCK = 1, GLF_STICKY = 2, GLF_DEMOTE = 3, + GLF_PENDING_DEMOTE = 4, GLF_DIRTY = 5, }; @@ -193,6 +202,7 @@ struct gfs2_glock { u64 gl_vn; unsigned long gl_stamp; + unsigned long gl_tchange; void *gl_object; struct list_head gl_reclaim; @@ -203,6 +213,7 @@ struct gfs2_glock { struct gfs2_log_element gl_le; struct list_head gl_ail_list; atomic_t gl_ail_count; + struct delayed_work gl_work; }; struct gfs2_alloc { @@ -293,11 +304,6 @@ struct gfs2_file { struct gfs2_holder f_fl_gh; }; -struct gfs2_revoke { - struct gfs2_log_element rv_le; - u64 rv_blkno; -}; - struct gfs2_revoke_replay { struct list_head rr_list; u64 rr_blkno; @@ -335,12 +341,6 @@ struct gfs2_quota_data { unsigned long qd_last_touched; }; -struct gfs2_log_buf { - struct list_head lb_list; - struct buffer_head *lb_bh; - struct buffer_head *lb_real; -}; - struct gfs2_trans { unsigned long tr_ip; @@ -429,7 +429,6 @@ struct gfs2_tune { unsigned int gt_log_flush_secs; unsigned int gt_jindex_refresh_secs; /* Check for new journal index */ - unsigned int gt_scand_secs; unsigned int gt_recoverd_secs; unsigned int gt_logd_secs; unsigned int gt_quotad_secs; @@ -574,7 +573,6 @@ struct gfs2_sbd { /* Daemon stuff */ - struct task_struct *sd_scand_process; struct task_struct *sd_recoverd_process; struct task_struct *sd_logd_process; struct task_struct *sd_quotad_process; @@ -609,13 +607,13 @@ struct gfs2_sbd { unsigned int sd_log_num_revoke; unsigned int sd_log_num_rg; unsigned int sd_log_num_databuf; - unsigned int sd_log_num_jdata; struct list_head sd_log_le_gl; struct list_head sd_log_le_buf; struct list_head sd_log_le_revoke; struct list_head sd_log_le_rg; struct list_head sd_log_le_databuf; + struct list_head sd_log_le_ordered; unsigned int sd_log_blks_free; struct mutex sd_log_reserve_mutex; @@ -627,7 +625,8 @@ struct gfs2_sbd { unsigned long sd_log_flush_time; struct rw_semaphore sd_log_flush_lock; - struct list_head sd_log_flush_list; + atomic_t sd_log_in_flight; + wait_queue_head_t sd_log_flush_wait; unsigned int sd_log_flush_head; u64 sd_log_flush_wrapped; diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c index 34f7bcdea1e..5f6dc32946c 100644 --- a/fs/gfs2/inode.c +++ b/fs/gfs2/inode.c @@ -77,6 +77,49 @@ static struct inode *gfs2_iget(struct super_block *sb, u64 no_addr) return iget5_locked(sb, hash, iget_test, iget_set, &no_addr); } +struct gfs2_skip_data { + u64 no_addr; + int skipped; +}; + +static int iget_skip_test(struct inode *inode, void *opaque) +{ + struct gfs2_inode *ip = GFS2_I(inode); + struct gfs2_skip_data *data = opaque; + + if (ip->i_no_addr == data->no_addr && inode->i_private != NULL){ + if (inode->i_state & (I_FREEING|I_CLEAR|I_WILL_FREE)){ + data->skipped = 1; + return 0; + } + return 1; + } + return 0; +} + +static int iget_skip_set(struct inode *inode, void *opaque) +{ + struct gfs2_inode *ip = GFS2_I(inode); + struct gfs2_skip_data *data = opaque; + + if (data->skipped) + return 1; + inode->i_ino = (unsigned long)(data->no_addr); + ip->i_no_addr = data->no_addr; + return 0; +} + +static struct inode *gfs2_iget_skip(struct super_block *sb, + u64 no_addr) +{ + struct gfs2_skip_data data; + unsigned long hash = (unsigned long)no_addr; + + data.no_addr = no_addr; + data.skipped = 0; + return iget5_locked(sb, hash, iget_skip_test, iget_skip_set, &data); +} + /** * GFS2 lookup code fills in vfs inode contents based on info obtained * from directory entry inside gfs2_inode_lookup(). This has caused issues @@ -112,6 +155,7 @@ void gfs2_set_iop(struct inode *inode) * @sb: The super block * @no_addr: The inode number * @type: The type of the inode + * @skip_freeing: set this not return an inode if it is currently being freed. * * Returns: A VFS inode, or an error */ @@ -119,13 +163,19 @@ void gfs2_set_iop(struct inode *inode) struct inode *gfs2_inode_lookup(struct super_block *sb, unsigned int type, u64 no_addr, - u64 no_formal_ino) + u64 no_formal_ino, int skip_freeing) { - struct inode *inode = gfs2_iget(sb, no_addr); - struct gfs2_inode *ip = GFS2_I(inode); + struct inode *inode; + struct gfs2_inode *ip; struct gfs2_glock *io_gl; int error; + if (skip_freeing) + inode = gfs2_iget_skip(sb, no_addr); + else + inode = gfs2_iget(sb, no_addr); + ip = GFS2_I(inode); + if (!inode) return ERR_PTR(-ENOBUFS); @@ -244,6 +294,11 @@ static int gfs2_dinode_in(struct gfs2_inode *ip, const void *buf) return 0; } +static void gfs2_inode_bh(struct gfs2_inode *ip, struct buffer_head *bh) +{ + ip->i_cache[0] = bh; +} + /** * gfs2_inode_refresh - Refresh the incore copy of the dinode * @ip: The GFS2 inode @@ -688,7 +743,7 @@ out: static void init_dinode(struct gfs2_inode *dip, struct gfs2_glock *gl, const struct gfs2_inum_host *inum, unsigned int mode, unsigned int uid, unsigned int gid, - const u64 *generation, dev_t dev) + const u64 *generation, dev_t dev, struct buffer_head **bhp) { struct gfs2_sbd *sdp = GFS2_SB(&dip->i_inode); struct gfs2_dinode *di; @@ -743,13 +798,15 @@ static void init_dinode(struct gfs2_inode *dip, struct gfs2_glock *gl, di->di_mtime_nsec = cpu_to_be32(tv.tv_nsec); di->di_ctime_nsec = cpu_to_be32(tv.tv_nsec); memset(&di->di_reserved, 0, sizeof(di->di_reserved)); + + set_buffer_uptodate(dibh); - brelse(dibh); + *bhp = dibh; } static int make_dinode(struct gfs2_inode *dip, struct gfs2_glock *gl, unsigned int mode, const struct gfs2_inum_host *inum, - const u64 *generation, dev_t dev) + const u64 *generation, dev_t dev, struct buffer_head **bhp) { struct gfs2_sbd *sdp = GFS2_SB(&dip->i_inode); unsigned int uid, gid; @@ -770,7 +827,7 @@ static int make_dinode(struct gfs2_inode *dip, struct gfs2_glock *gl, if (error) goto out_quota; - init_dinode(dip, gl, inum, mode, uid, gid, generation, dev); + init_dinode(dip, gl, inum, mode, uid, gid, generation, dev, bhp); gfs2_quota_change(dip, +1, uid, gid); gfs2_trans_end(sdp); @@ -909,6 +966,7 @@ struct inode *gfs2_createi(struct gfs2_holder *ghs, const struct qstr *name, struct gfs2_inum_host inum = { .no_addr = 0, .no_formal_ino = 0 }; int error; u64 generation; + struct buffer_head *bh=NULL; if (!name->len || name->len > GFS2_FNAMESIZE) return ERR_PTR(-ENAMETOOLONG); @@ -935,16 +993,18 @@ struct inode *gfs2_createi(struct gfs2_holder *ghs, const struct qstr *name, if (error) goto fail_gunlock; - error = make_dinode(dip, ghs[1].gh_gl, mode, &inum, &generation, dev); + error = make_dinode(dip, ghs[1].gh_gl, mode, &inum, &generation, dev, &bh); if (error) goto fail_gunlock2; inode = gfs2_inode_lookup(dir->i_sb, IF2DT(mode), inum.no_addr, - inum.no_formal_ino); + inum.no_formal_ino, 0); if (IS_ERR(inode)) goto fail_gunlock2; + gfs2_inode_bh(GFS2_I(inode), bh); + error = gfs2_inode_refresh(GFS2_I(inode)); if (error) goto fail_gunlock2; diff --git a/fs/gfs2/inode.h b/fs/gfs2/inode.h index 4517ac82c01..351ac87ab38 100644 --- a/fs/gfs2/inode.h +++ b/fs/gfs2/inode.h @@ -49,7 +49,8 @@ static inline void gfs2_inum_out(const struct gfs2_inode *ip, void gfs2_inode_attr_in(struct gfs2_inode *ip); void gfs2_set_iop(struct inode *inode); struct inode *gfs2_inode_lookup(struct super_block *sb, unsigned type, - u64 no_addr, u64 no_formal_ino); + u64 no_addr, u64 no_formal_ino, + int skip_freeing); struct inode *gfs2_ilookup(struct super_block *sb, u64 no_addr); int gfs2_inode_refresh(struct gfs2_inode *ip); diff --git a/fs/gfs2/locking/dlm/lock_dlm.h b/fs/gfs2/locking/dlm/lock_dlm.h index 24d70f73b65..9e8265d2837 100644 --- a/fs/gfs2/locking/dlm/lock_dlm.h +++ b/fs/gfs2/locking/dlm/lock_dlm.h @@ -13,7 +13,6 @@ #include <linux/module.h> #include <linux/slab.h> #include <linux/spinlock.h> -#include <linux/module.h> #include <linux/types.h> #include <linux/string.h> #include <linux/list.h> diff --git a/fs/gfs2/locking/dlm/plock.c b/fs/gfs2/locking/dlm/plock.c index fba1f1d87e4..1f7b038530b 100644 --- a/fs/gfs2/locking/dlm/plock.c +++ b/fs/gfs2/locking/dlm/plock.c @@ -346,15 +346,16 @@ static ssize_t dev_write(struct file *file, const char __user *u, size_t count, static unsigned int dev_poll(struct file *file, poll_table *wait) { + unsigned int mask = 0; + poll_wait(file, &send_wq, wait); spin_lock(&ops_lock); - if (!list_empty(&send_list)) { - spin_unlock(&ops_lock); - return POLLIN | POLLRDNORM; - } + if (!list_empty(&send_list)) + mask = POLLIN | POLLRDNORM; spin_unlock(&ops_lock); - return 0; + + return mask; } static const struct file_operations dev_fops = { diff --git a/fs/gfs2/locking/dlm/thread.c b/fs/gfs2/locking/dlm/thread.c index 1aca51e4509..bd938f06481 100644 --- a/fs/gfs2/locking/dlm/thread.c +++ b/fs/gfs2/locking/dlm/thread.c @@ -268,20 +268,16 @@ static inline int check_drop(struct gdlm_ls *ls) return 0; } -static int gdlm_thread(void *data) +static int gdlm_thread(void *data, int blist) { struct gdlm_ls *ls = (struct gdlm_ls *) data; struct gdlm_lock *lp = NULL; - int blist = 0; uint8_t complete, blocking, submit, drop; DECLARE_WAITQUEUE(wait, current); /* Only thread1 is allowed to do blocking callbacks since gfs may wait for a completion callback within a blocking cb. */ - if (current == ls->thread1) - blist = 1; - while (!kthread_should_stop()) { set_current_state(TASK_INTERRUPTIBLE); add_wait_queue(&ls->thread_wait, &wait); @@ -333,12 +329,22 @@ static int gdlm_thread(void *data) return 0; } +static int gdlm_thread1(void *data) +{ + return gdlm_thread(data, 1); +} + +static int gdlm_thread2(void *data) +{ + return gdlm_thread(data, 0); +} + int gdlm_init_threads(struct gdlm_ls *ls) { struct task_struct *p; int error; - p = kthread_run(gdlm_thread, ls, "lock_dlm1"); + p = kthread_run(gdlm_thread1, ls, "lock_dlm1"); error = IS_ERR(p); if (error) { log_error("can't start lock_dlm1 thread %d", error); @@ -346,7 +352,7 @@ int gdlm_init_threads(struct gdlm_ls *ls) } ls->thread1 = p; - p = kthread_run(gdlm_thread, ls, "lock_dlm2"); + p = kthread_run(gdlm_thread2, ls, "lock_dlm2"); error = IS_ERR(p); if (error) { log_error("can't start lock_dlm2 thread %d", error); diff --git a/fs/gfs2/locking/nolock/main.c b/fs/gfs2/locking/nolock/main.c index 0d149c8c493..d3b8ce6fbbe 100644 --- a/fs/gfs2/locking/nolock/main.c +++ b/fs/gfs2/locking/nolock/main.c @@ -9,7 +9,6 @@ #include <linux/module.h> #include <linux/slab.h> -#include <linux/module.h> #include <linux/init.h> #include <linux/types.h> #include <linux/fs.h> diff --git a/fs/gfs2/log.c b/fs/gfs2/log.c index f49a12e2408..7df70247325 100644 --- a/fs/gfs2/log.c +++ b/fs/gfs2/log.c @@ -60,6 +60,26 @@ unsigned int gfs2_struct2blk(struct gfs2_sbd *sdp, unsigned int nstruct, } /** + * gfs2_remove_from_ail - Remove an entry from the ail lists, updating counters + * @mapping: The associated mapping (maybe NULL) + * @bd: The gfs2_bufdata to remove + * + * The log lock _must_ be held when calling this function + * + */ + +void gfs2_remove_from_ail(struct address_space *mapping, struct gfs2_bufdata *bd) +{ + bd->bd_ail = NULL; + list_del_init(&bd->bd_ail_st_list); + list_del_init(&bd->bd_ail_gl_list); + atomic_dec(&bd->bd_gl->gl_ail_count); + if (mapping) + gfs2_meta_cache_flush(GFS2_I(mapping->host)); + brelse(bd->bd_bh); +} + +/** * gfs2_ail1_start_one - Start I/O on a part of the AIL * @sdp: the filesystem * @tr: the part of the AIL @@ -83,17 +103,9 @@ static void gfs2_ail1_start_one(struct gfs2_sbd *sdp, struct gfs2_ail *ai) gfs2_assert(sdp, bd->bd_ail == ai); - if (!bh){ - list_move(&bd->bd_ail_st_list, &ai->ai_ail2_list); - continue; - } - if (!buffer_busy(bh)) { - if (!buffer_uptodate(bh)) { - gfs2_log_unlock(sdp); + if (!buffer_uptodate(bh)) gfs2_io_error_bh(sdp, bh); - gfs2_log_lock(sdp); - } list_move(&bd->bd_ail_st_list, &ai->ai_ail2_list); continue; } @@ -103,9 +115,16 @@ static void gfs2_ail1_start_one(struct gfs2_sbd *sdp, struct gfs2_ail *ai) list_move(&bd->bd_ail_st_list, &ai->ai_ail1_list); + get_bh(bh); gfs2_log_unlock(sdp); - wait_on_buffer(bh); - ll_rw_block(WRITE, 1, &bh); + lock_buffer(bh); + if (test_clear_buffer_dirty(bh)) { + bh->b_end_io = end_buffer_write_sync; + submit_bh(WRITE, bh); + } else { + unlock_buffer(bh); + brelse(bh); + } gfs2_log_lock(sdp); retry = 1; @@ -130,11 +149,6 @@ static int gfs2_ail1_empty_one(struct gfs2_sbd *sdp, struct gfs2_ail *ai, int fl bd_ail_st_list) { bh = bd->bd_bh; - if (!bh){ - list_move(&bd->bd_ail_st_list, &ai->ai_ail2_list); - continue; - } - gfs2_assert(sdp, bd->bd_ail == ai); if (buffer_busy(bh)) { @@ -155,13 +169,14 @@ static int gfs2_ail1_empty_one(struct gfs2_sbd *sdp, struct gfs2_ail *ai, int fl static void gfs2_ail1_start(struct gfs2_sbd *sdp, int flags) { - struct list_head *head = &sdp->sd_ail1_list; + struct list_head *head; u64 sync_gen; struct list_head *first; struct gfs2_ail *first_ai, *ai, *tmp; int done = 0; gfs2_log_lock(sdp); + head = &sdp->sd_ail1_list; if (list_empty(head)) { gfs2_log_unlock(sdp); return; @@ -233,11 +248,7 @@ static void gfs2_ail2_empty_one(struct gfs2_sbd *sdp, struct gfs2_ail *ai) bd = list_entry(head->prev, struct gfs2_bufdata, bd_ail_st_list); gfs2_assert(sdp, bd->bd_ail == ai); - bd->bd_ail = NULL; - list_del(&bd->bd_ail_st_list); - list_del(&bd->bd_ail_gl_list); - atomic_dec(&bd->bd_gl->gl_ail_count); - brelse(bd->bd_bh); + gfs2_remove_from_ail(bd->bd_bh->b_page->mapping, bd); } } @@ -439,10 +450,10 @@ static unsigned int current_tail(struct gfs2_sbd *sdp) return tail; } -static inline void log_incr_head(struct gfs2_sbd *sdp) +void gfs2_log_incr_head(struct gfs2_sbd *sdp) { if (sdp->sd_log_flush_head == sdp->sd_log_tail) - gfs2_assert_withdraw(sdp, sdp->sd_log_flush_head == sdp->sd_log_head); + BUG_ON(sdp->sd_log_flush_head != sdp->sd_log_head); if (++sdp->sd_log_flush_head == sdp->sd_jdesc->jd_blocks) { sdp->sd_log_flush_head = 0; @@ -451,6 +462,23 @@ static inline void log_incr_head(struct gfs2_sbd *sdp) } /** + * gfs2_log_write_endio - End of I/O for a log buffer + * @bh: The buffer head + * @uptodate: I/O Status + * + */ + +static void gfs2_log_write_endio(struct buffer_head *bh, int uptodate) +{ + struct gfs2_sbd *sdp = bh->b_private; + bh->b_private = NULL; + + end_buffer_write_sync(bh, uptodate); + if (atomic_dec_and_test(&sdp->sd_log_in_flight)) + wake_up(&sdp->sd_log_flush_wait); +} + +/** * gfs2_log_get_buf - Get and initialize a buffer to use for log control data * @sdp: The GFS2 superblock * @@ -460,25 +488,43 @@ static inline void log_incr_head(struct gfs2_sbd *sdp) struct buffer_head *gfs2_log_get_buf(struct gfs2_sbd *sdp) { u64 blkno = log_bmap(sdp, sdp->sd_log_flush_head); - struct gfs2_log_buf *lb; struct buffer_head *bh; - lb = kzalloc(sizeof(struct gfs2_log_buf), GFP_NOFS | __GFP_NOFAIL); - list_add(&lb->lb_list, &sdp->sd_log_flush_list); - - bh = lb->lb_bh = sb_getblk(sdp->sd_vfs, blkno); + bh = sb_getblk(sdp->sd_vfs, blkno); lock_buffer(bh); memset(bh->b_data, 0, bh->b_size); set_buffer_uptodate(bh); clear_buffer_dirty(bh); - unlock_buffer(bh); - - log_incr_head(sdp); + gfs2_log_incr_head(sdp); + atomic_inc(&sdp->sd_log_in_flight); + bh->b_private = sdp; + bh->b_end_io = gfs2_log_write_endio; return bh; } /** + * gfs2_fake_write_endio - + * @bh: The buffer head + * @uptodate: The I/O Status + * + */ + +static void gfs2_fake_write_endio(struct buffer_head *bh, int uptodate) +{ + struct buffer_head *real_bh = bh->b_private; + struct gfs2_bufdata *bd = real_bh->b_private; + struct gfs2_sbd *sdp = bd->bd_gl->gl_sbd; + + end_buffer_write_sync(bh, uptodate); + free_buffer_head(bh); + unlock_buffer(real_bh); + brelse(real_bh); + if (atomic_dec_and_test(&sdp->sd_log_in_flight)) + wake_up(&sdp->sd_log_flush_wait); +} + +/** * gfs2_log_fake_buf - Build a fake buffer head to write metadata buffer to log * @sdp: the filesystem * @data: the data the buffer_head should point to @@ -490,22 +536,20 @@ struct buffer_head *gfs2_log_fake_buf(struct gfs2_sbd *sdp, struct buffer_head *real) { u64 blkno = log_bmap(sdp, sdp->sd_log_flush_head); - struct gfs2_log_buf *lb; struct buffer_head *bh; - lb = kzalloc(sizeof(struct gfs2_log_buf), GFP_NOFS | __GFP_NOFAIL); - list_add(&lb->lb_list, &sdp->sd_log_flush_list); - lb->lb_real = real; - - bh = lb->lb_bh = alloc_buffer_head(GFP_NOFS | __GFP_NOFAIL); + bh = alloc_buffer_head(GFP_NOFS | __GFP_NOFAIL); atomic_set(&bh->b_count, 1); - bh->b_state = (1 << BH_Mapped) | (1 << BH_Uptodate); + bh->b_state = (1 << BH_Mapped) | (1 << BH_Uptodate) | (1 << BH_Lock); set_bh_page(bh, real->b_page, bh_offset(real)); bh->b_blocknr = blkno; bh->b_size = sdp->sd_sb.sb_bsize; bh->b_bdev = sdp->sd_vfs->s_bdev; + bh->b_private = real; + bh->b_end_io = gfs2_fake_write_endio; - log_incr_head(sdp); + gfs2_log_incr_head(sdp); + atomic_inc(&sdp->sd_log_in_flight); return bh; } @@ -572,45 +616,75 @@ static void log_write_header(struct gfs2_sbd *sdp, u32 flags, int pull) gfs2_assert_withdraw(sdp, !pull); sdp->sd_log_idle = (tail == sdp->sd_log_flush_head); - log_incr_head(sdp); + gfs2_log_incr_head(sdp); } static void log_flush_commit(struct gfs2_sbd *sdp) { - struct list_head *head = &sdp->sd_log_flush_list; - struct gfs2_log_buf *lb; - struct buffer_head *bh; - int flushcount = 0; + DEFINE_WAIT(wait); + + if (atomic_read(&sdp->sd_log_in_flight)) { + do { + prepare_to_wait(&sdp->sd_log_flush_wait, &wait, + TASK_UNINTERRUPTIBLE); + if (atomic_read(&sdp->sd_log_in_flight)) + io_schedule(); + } while(atomic_read(&sdp->sd_log_in_flight)); + finish_wait(&sdp->sd_log_flush_wait, &wait); + } - while (!list_empty(head)) { - lb = list_entry(head->next, struct gfs2_log_buf, lb_list); - list_del(&lb->lb_list); - bh = lb->lb_bh; + log_write_header(sdp, 0, 0); +} - wait_on_buffer(bh); - if (!buffer_uptodate(bh)) - gfs2_io_error_bh(sdp, bh); - if (lb->lb_real) { - while (atomic_read(&bh->b_count) != 1) /* Grrrr... */ - schedule(); - free_buffer_head(bh); - } else +static void gfs2_ordered_write(struct gfs2_sbd *sdp) +{ + struct gfs2_bufdata *bd; + struct buffer_head *bh; + LIST_HEAD(written); + + gfs2_log_lock(sdp); + while (!list_empty(&sdp->sd_log_le_ordered)) { + bd = list_entry(sdp->sd_log_le_ordered.next, struct gfs2_bufdata, bd_le.le_list); + list_move(&bd->bd_le.le_list, &written); + bh = bd->bd_bh; + if (!buffer_dirty(bh)) + continue; + get_bh(bh); + gfs2_log_unlock(sdp); + lock_buffer(bh); + if (test_clear_buffer_dirty(bh)) { + bh->b_end_io = end_buffer_write_sync; + submit_bh(WRITE, bh); + } else { + unlock_buffer(bh); brelse(bh); - kfree(lb); - flushcount++; + } + gfs2_log_lock(sdp); } + list_splice(&written, &sdp->sd_log_le_ordered); + gfs2_log_unlock(sdp); +} - /* If nothing was journaled, the header is unplanned and unwanted. */ - if (flushcount) { - log_write_header(sdp, 0, 0); - } else { - unsigned int tail; - tail = current_tail(sdp); +static void gfs2_ordered_wait(struct gfs2_sbd *sdp) +{ + struct gfs2_bufdata *bd; + struct buffer_head *bh; - gfs2_ail1_empty(sdp, 0); - if (sdp->sd_log_tail != tail) - log_pull_tail(sdp, tail); + gfs2_log_lock(sdp); + while (!list_empty(&sdp->sd_log_le_ordered)) { + bd = list_entry(sdp->sd_log_le_ordered.prev, struct gfs2_bufdata, bd_le.le_list); + bh = bd->bd_bh; + if (buffer_locked(bh)) { + get_bh(bh); + gfs2_log_unlock(sdp); + wait_on_buffer(bh); + brelse(bh); + gfs2_log_lock(sdp); + continue; + } + list_del_init(&bd->bd_le.le_list); } + gfs2_log_unlock(sdp); } /** @@ -640,10 +714,16 @@ void gfs2_log_flush(struct gfs2_sbd *sdp, struct gfs2_glock *gl) INIT_LIST_HEAD(&ai->ai_ail1_list); INIT_LIST_HEAD(&ai->ai_ail2_list); - gfs2_assert_withdraw(sdp, - sdp->sd_log_num_buf + sdp->sd_log_num_jdata == - sdp->sd_log_commited_buf + - sdp->sd_log_commited_databuf); + if (sdp->sd_log_num_buf != sdp->sd_log_commited_buf) { + printk(KERN_INFO "GFS2: log buf %u %u\n", sdp->sd_log_num_buf, + sdp->sd_log_commited_buf); + gfs2_assert_withdraw(sdp, 0); + } + if (sdp->sd_log_num_databuf != sdp->sd_log_commited_databuf) { + printk(KERN_INFO "GFS2: log databuf %u %u\n", + sdp->sd_log_num_databuf, sdp->sd_log_commited_databuf); + gfs2_assert_withdraw(sdp, 0); + } gfs2_assert_withdraw(sdp, sdp->sd_log_num_revoke == sdp->sd_log_commited_revoke); @@ -651,8 +731,11 @@ void gfs2_log_flush(struct gfs2_sbd *sdp, struct gfs2_glock *gl) sdp->sd_log_flush_wrapped = 0; ai->ai_first = sdp->sd_log_flush_head; + gfs2_ordered_write(sdp); lops_before_commit(sdp); - if (!list_empty(&sdp->sd_log_flush_list)) + gfs2_ordered_wait(sdp); + + if (sdp->sd_log_head != sdp->sd_log_flush_head) log_flush_commit(sdp); else if (sdp->sd_log_tail != current_tail(sdp) && !sdp->sd_log_idle){ gfs2_log_lock(sdp); @@ -744,7 +827,6 @@ void gfs2_log_shutdown(struct gfs2_sbd *sdp) gfs2_assert_withdraw(sdp, !sdp->sd_log_blks_reserved); gfs2_assert_withdraw(sdp, !sdp->sd_log_num_gl); gfs2_assert_withdraw(sdp, !sdp->sd_log_num_buf); - gfs2_assert_withdraw(sdp, !sdp->sd_log_num_jdata); gfs2_assert_withdraw(sdp, !sdp->sd_log_num_revoke); gfs2_assert_withdraw(sdp, !sdp->sd_log_num_rg); gfs2_assert_withdraw(sdp, !sdp->sd_log_num_databuf); diff --git a/fs/gfs2/log.h b/fs/gfs2/log.h index 8e7aa0f2910..dae28240062 100644 --- a/fs/gfs2/log.h +++ b/fs/gfs2/log.h @@ -52,12 +52,14 @@ int gfs2_ail1_empty(struct gfs2_sbd *sdp, int flags); int gfs2_log_reserve(struct gfs2_sbd *sdp, unsigned int blks); void gfs2_log_release(struct gfs2_sbd *sdp, unsigned int blks); +void gfs2_log_incr_head(struct gfs2_sbd *sdp); struct buffer_head *gfs2_log_get_buf(struct gfs2_sbd *sdp); struct buffer_head *gfs2_log_fake_buf(struct gfs2_sbd *sdp, struct buffer_head *real); void gfs2_log_flush(struct gfs2_sbd *sdp, struct gfs2_glock *gl); void gfs2_log_commit(struct gfs2_sbd *sdp, struct gfs2_trans *trans); +void gfs2_remove_from_ail(struct address_space *mapping, struct gfs2_bufdata *bd); void gfs2_log_shutdown(struct gfs2_sbd *sdp); void gfs2_meta_syncfs(struct gfs2_sbd *sdp); diff --git a/fs/gfs2/lops.c b/fs/gfs2/lops.c index 3b395c41b2f..6c27cea761c 100644 --- a/fs/gfs2/lops.c +++ b/fs/gfs2/lops.c @@ -27,7 +27,104 @@ #include "trans.h" #include "util.h" -static void glock_lo_add(struct gfs2_sbd *sdp, struct gfs2_log_element *le) +/** + * gfs2_pin - Pin a buffer in memory + * @sdp: The superblock + * @bh: The buffer to be pinned + * + * The log lock must be held when calling this function + */ +static void gfs2_pin(struct gfs2_sbd *sdp, struct buffer_head *bh) +{ + struct gfs2_bufdata *bd; + + gfs2_assert_withdraw(sdp, test_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags)); + + clear_buffer_dirty(bh); + if (test_set_buffer_pinned(bh)) + gfs2_assert_withdraw(sdp, 0); + if (!buffer_uptodate(bh)) + gfs2_io_error_bh(sdp, bh); + bd = bh->b_private; + /* If this buffer is in the AIL and it has already been written + * to in-place disk block, remove it from the AIL. + */ + if (bd->bd_ail) + list_move(&bd->bd_ail_st_list, &bd->bd_ail->ai_ail2_list); + get_bh(bh); +} + +/** + * gfs2_unpin - Unpin a buffer + * @sdp: the filesystem the buffer belongs to + * @bh: The buffer to unpin + * @ai: + * + */ + +static void gfs2_unpin(struct gfs2_sbd *sdp, struct buffer_head *bh, + struct gfs2_ail *ai) +{ + struct gfs2_bufdata *bd = bh->b_private; + + gfs2_assert_withdraw(sdp, buffer_uptodate(bh)); + + if (!buffer_pinned(bh)) + gfs2_assert_withdraw(sdp, 0); + + lock_buffer(bh); + mark_buffer_dirty(bh); + clear_buffer_pinned(bh); + + gfs2_log_lock(sdp); + if (bd->bd_ail) { + list_del(&bd->bd_ail_st_list); + brelse(bh); + } else { + struct gfs2_glock *gl = bd->bd_gl; + list_add(&bd->bd_ail_gl_list, &gl->gl_ail_list); + atomic_inc(&gl->gl_ail_count); + } + bd->bd_ail = ai; + list_add(&bd->bd_ail_st_list, &ai->ai_ail1_list); + gfs2_log_unlock(sdp); + unlock_buffer(bh); +} + + +static inline struct gfs2_log_descriptor *bh_log_desc(struct buffer_head *bh) +{ + return (struct gfs2_log_descriptor *)bh->b_data; +} + +static inline __be64 *bh_log_ptr(struct buffer_head *bh) +{ + struct gfs2_log_descriptor *ld = bh_log_desc(bh); + return (__force __be64 *)(ld + 1); +} + +static inline __be64 *bh_ptr_end(struct buffer_head *bh) +{ + return (__force __be64 *)(bh->b_data + bh->b_size); +} + + +static struct buffer_head *gfs2_get_log_desc(struct gfs2_sbd *sdp, u32 ld_type) +{ + struct buffer_head *bh = gfs2_log_get_buf(sdp); + struct gfs2_log_descriptor *ld = bh_log_desc(bh); + ld->ld_header.mh_magic = cpu_to_be32(GFS2_MAGIC); + ld->ld_header.mh_type = cpu_to_be32(GFS2_METATYPE_LD); + ld->ld_header.mh_format = cpu_to_be32(GFS2_FORMAT_LD); + ld->ld_type = cpu_to_be32(ld_type); + ld->ld_length = 0; + ld->ld_data1 = 0; + ld->ld_data2 = 0; + memset(ld->ld_reserved, 0, sizeof(ld->ld_reserved)); + return bh; +} + +static void __glock_lo_add(struct gfs2_sbd *sdp, struct gfs2_log_element *le) { struct gfs2_glock *gl; struct gfs2_trans *tr = current->journal_info; @@ -38,15 +135,19 @@ static void glock_lo_add(struct gfs2_sbd *sdp, struct gfs2_log_element *le) if (gfs2_assert_withdraw(sdp, gfs2_glock_is_held_excl(gl))) return; - gfs2_log_lock(sdp); - if (!list_empty(&le->le_list)){ - gfs2_log_unlock(sdp); + if (!list_empty(&le->le_list)) return; - } + gfs2_glock_hold(gl); set_bit(GLF_DIRTY, &gl->gl_flags); sdp->sd_log_num_gl++; list_add(&le->le_list, &sdp->sd_log_le_gl); +} + +static void glock_lo_add(struct gfs2_sbd *sdp, struct gfs2_log_element *le) +{ + gfs2_log_lock(sdp); + __glock_lo_add(sdp, le); gfs2_log_unlock(sdp); } @@ -71,30 +172,25 @@ static void buf_lo_add(struct gfs2_sbd *sdp, struct gfs2_log_element *le) struct gfs2_bufdata *bd = container_of(le, struct gfs2_bufdata, bd_le); struct gfs2_trans *tr; + lock_buffer(bd->bd_bh); gfs2_log_lock(sdp); - if (!list_empty(&bd->bd_list_tr)) { - gfs2_log_unlock(sdp); - return; - } + if (!list_empty(&bd->bd_list_tr)) + goto out; tr = current->journal_info; tr->tr_touched = 1; tr->tr_num_buf++; list_add(&bd->bd_list_tr, &tr->tr_list_buf); - gfs2_log_unlock(sdp); - if (!list_empty(&le->le_list)) - return; - - gfs2_trans_add_gl(bd->bd_gl); - + goto out; + __glock_lo_add(sdp, &bd->bd_gl->gl_le); gfs2_meta_check(sdp, bd->bd_bh); gfs2_pin(sdp, bd->bd_bh); - gfs2_log_lock(sdp); sdp->sd_log_num_buf++; list_add(&le->le_list, &sdp->sd_log_le_buf); - gfs2_log_unlock(sdp); - tr->tr_num_buf_new++; +out: + gfs2_log_unlock(sdp); + unlock_buffer(bd->bd_bh); } static void buf_lo_incore_commit(struct gfs2_sbd *sdp, struct gfs2_trans *tr) @@ -117,8 +213,7 @@ static void buf_lo_before_commit(struct gfs2_sbd *sdp) struct buffer_head *bh; struct gfs2_log_descriptor *ld; struct gfs2_bufdata *bd1 = NULL, *bd2; - unsigned int total = sdp->sd_log_num_buf; - unsigned int offset = BUF_OFFSET; + unsigned int total; unsigned int limit; unsigned int num; unsigned n; @@ -127,22 +222,20 @@ static void buf_lo_before_commit(struct gfs2_sbd *sdp) limit = buf_limit(sdp); /* for 4k blocks, limit = 503 */ + gfs2_log_lock(sdp); + total = sdp->sd_log_num_buf; bd1 = bd2 = list_prepare_entry(bd1, &sdp->sd_log_le_buf, bd_le.le_list); while(total) { num = total; if (total > limit) num = limit; - bh = gfs2_log_get_buf(sdp); - ld = (struct gfs2_log_descriptor *)bh->b_data; - ptr = (__be64 *)(bh->b_data + offset); - ld->ld_header.mh_magic = cpu_to_be32(GFS2_MAGIC); - ld->ld_header.mh_type = cpu_to_be32(GFS2_METATYPE_LD); - ld->ld_header.mh_format = cpu_to_be32(GFS2_FORMAT_LD); - ld->ld_type = cpu_to_be32(GFS2_LOG_DESC_METADATA); + gfs2_log_unlock(sdp); + bh = gfs2_get_log_desc(sdp, GFS2_LOG_DESC_METADATA); + gfs2_log_lock(sdp); + ld = bh_log_desc(bh); + ptr = bh_log_ptr(bh); ld->ld_length = cpu_to_be32(num + 1); ld->ld_data1 = cpu_to_be32(num); - ld->ld_data2 = cpu_to_be32(0); - memset(ld->ld_reserved, 0, sizeof(ld->ld_reserved)); n = 0; list_for_each_entry_continue(bd1, &sdp->sd_log_le_buf, @@ -152,21 +245,27 @@ static void buf_lo_before_commit(struct gfs2_sbd *sdp) break; } - set_buffer_dirty(bh); - ll_rw_block(WRITE, 1, &bh); + gfs2_log_unlock(sdp); + submit_bh(WRITE, bh); + gfs2_log_lock(sdp); n = 0; list_for_each_entry_continue(bd2, &sdp->sd_log_le_buf, bd_le.le_list) { + get_bh(bd2->bd_bh); + gfs2_log_unlock(sdp); + lock_buffer(bd2->bd_bh); bh = gfs2_log_fake_buf(sdp, bd2->bd_bh); - set_buffer_dirty(bh); - ll_rw_block(WRITE, 1, &bh); + submit_bh(WRITE, bh); + gfs2_log_lock(sdp); if (++n >= num) break; } + BUG_ON(total < num); total -= num; } + gfs2_log_unlock(sdp); } static void buf_lo_after_commit(struct gfs2_sbd *sdp, struct gfs2_ail *ai) @@ -270,11 +369,8 @@ static void revoke_lo_add(struct gfs2_sbd *sdp, struct gfs2_log_element *le) tr = current->journal_info; tr->tr_touched = 1; tr->tr_num_revoke++; - - gfs2_log_lock(sdp); sdp->sd_log_num_revoke++; list_add(&le->le_list, &sdp->sd_log_le_revoke); - gfs2_log_unlock(sdp); } static void revoke_lo_before_commit(struct gfs2_sbd *sdp) @@ -284,32 +380,25 @@ static void revoke_lo_before_commit(struct gfs2_sbd *sdp) struct buffer_head *bh; unsigned int offset; struct list_head *head = &sdp->sd_log_le_revoke; - struct gfs2_revoke *rv; + struct gfs2_bufdata *bd; if (!sdp->sd_log_num_revoke) return; - bh = gfs2_log_get_buf(sdp); - ld = (struct gfs2_log_descriptor *)bh->b_data; - ld->ld_header.mh_magic = cpu_to_be32(GFS2_MAGIC); - ld->ld_header.mh_type = cpu_to_be32(GFS2_METATYPE_LD); - ld->ld_header.mh_format = cpu_to_be32(GFS2_FORMAT_LD); - ld->ld_type = cpu_to_be32(GFS2_LOG_DESC_REVOKE); + bh = gfs2_get_log_desc(sdp, GFS2_LOG_DESC_REVOKE); + ld = bh_log_desc(bh); ld->ld_length = cpu_to_be32(gfs2_struct2blk(sdp, sdp->sd_log_num_revoke, sizeof(u64))); ld->ld_data1 = cpu_to_be32(sdp->sd_log_num_revoke); - ld->ld_data2 = cpu_to_be32(0); - memset(ld->ld_reserved, 0, sizeof(ld->ld_reserved)); offset = sizeof(struct gfs2_log_descriptor); while (!list_empty(head)) { - rv = list_entry(head->next, struct gfs2_revoke, rv_le.le_list); - list_del_init(&rv->rv_le.le_list); + bd = list_entry(head->next, struct gfs2_bufdata, bd_le.le_list); + list_del_init(&bd->bd_le.le_list); sdp->sd_log_num_revoke--; if (offset + sizeof(u64) > sdp->sd_sb.sb_bsize) { - set_buffer_dirty(bh); - ll_rw_block(WRITE, 1, &bh); + submit_bh(WRITE, bh); bh = gfs2_log_get_buf(sdp); mh = (struct gfs2_meta_header *)bh->b_data; @@ -319,15 +408,14 @@ static void revoke_lo_before_commit(struct gfs2_sbd *sdp) offset = sizeof(struct gfs2_meta_header); } - *(__be64 *)(bh->b_data + offset) = cpu_to_be64(rv->rv_blkno); - kfree(rv); + *(__be64 *)(bh->b_data + offset) = cpu_to_be64(bd->bd_blkno); + kmem_cache_free(gfs2_bufdata_cachep, bd); offset += sizeof(u64); } gfs2_assert_withdraw(sdp, !sdp->sd_log_num_revoke); - set_buffer_dirty(bh); - ll_rw_block(WRITE, 1, &bh); + submit_bh(WRITE, bh); } static void revoke_lo_before_scan(struct gfs2_jdesc *jd, @@ -466,222 +554,136 @@ static void databuf_lo_add(struct gfs2_sbd *sdp, struct gfs2_log_element *le) struct address_space *mapping = bd->bd_bh->b_page->mapping; struct gfs2_inode *ip = GFS2_I(mapping->host); + lock_buffer(bd->bd_bh); gfs2_log_lock(sdp); - if (!list_empty(&bd->bd_list_tr)) { - gfs2_log_unlock(sdp); - return; - } + if (!list_empty(&bd->bd_list_tr)) + goto out; tr->tr_touched = 1; if (gfs2_is_jdata(ip)) { tr->tr_num_buf++; list_add(&bd->bd_list_tr, &tr->tr_list_buf); } - gfs2_log_unlock(sdp); if (!list_empty(&le->le_list)) - return; + goto out; - gfs2_trans_add_gl(bd->bd_gl); + __glock_lo_add(sdp, &bd->bd_gl->gl_le); if (gfs2_is_jdata(ip)) { - sdp->sd_log_num_jdata++; gfs2_pin(sdp, bd->bd_bh); tr->tr_num_databuf_new++; + sdp->sd_log_num_databuf++; + list_add(&le->le_list, &sdp->sd_log_le_databuf); + } else { + list_add(&le->le_list, &sdp->sd_log_le_ordered); } - gfs2_log_lock(sdp); - sdp->sd_log_num_databuf++; - list_add(&le->le_list, &sdp->sd_log_le_databuf); +out: gfs2_log_unlock(sdp); + unlock_buffer(bd->bd_bh); } -static int gfs2_check_magic(struct buffer_head *bh) +static void gfs2_check_magic(struct buffer_head *bh) { - struct page *page = bh->b_page; void *kaddr; __be32 *ptr; - int rv = 0; - kaddr = kmap_atomic(page, KM_USER0); + clear_buffer_escaped(bh); + kaddr = kmap_atomic(bh->b_page, KM_USER0); ptr = kaddr + bh_offset(bh); if (*ptr == cpu_to_be32(GFS2_MAGIC)) - rv = 1; + set_buffer_escaped(bh); kunmap_atomic(kaddr, KM_USER0); - - return rv; } -/** - * databuf_lo_before_commit - Scan the data buffers, writing as we go - * - * Here we scan through the lists of buffers and make the assumption - * that any buffer thats been pinned is being journaled, and that - * any unpinned buffer is an ordered write data buffer and therefore - * will be written back rather than journaled. - */ -static void databuf_lo_before_commit(struct gfs2_sbd *sdp) +static void gfs2_write_blocks(struct gfs2_sbd *sdp, struct buffer_head *bh, + struct list_head *list, struct list_head *done, + unsigned int n) { - LIST_HEAD(started); - struct gfs2_bufdata *bd1 = NULL, *bd2, *bdt; - struct buffer_head *bh = NULL,*bh1 = NULL; + struct buffer_head *bh1; struct gfs2_log_descriptor *ld; - unsigned int limit; - unsigned int total_dbuf; - unsigned int total_jdata = sdp->sd_log_num_jdata; - unsigned int num, n; - __be64 *ptr = NULL; + struct gfs2_bufdata *bd; + __be64 *ptr; + + if (!bh) + return; - limit = databuf_limit(sdp); + ld = bh_log_desc(bh); + ld->ld_length = cpu_to_be32(n + 1); + ld->ld_data1 = cpu_to_be32(n); - /* - * Start writing ordered buffers, write journaled buffers - * into the log along with a header - */ + ptr = bh_log_ptr(bh); + + get_bh(bh); + submit_bh(WRITE, bh); gfs2_log_lock(sdp); - total_dbuf = sdp->sd_log_num_databuf; - bd2 = bd1 = list_prepare_entry(bd1, &sdp->sd_log_le_databuf, - bd_le.le_list); - while(total_dbuf) { - num = total_jdata; - if (num > limit) - num = limit; - n = 0; - list_for_each_entry_safe_continue(bd1, bdt, - &sdp->sd_log_le_databuf, - bd_le.le_list) { - /* store off the buffer head in a local ptr since - * gfs2_bufdata might change when we drop the log lock - */ - bh1 = bd1->bd_bh; - - /* An ordered write buffer */ - if (bh1 && !buffer_pinned(bh1)) { - list_move(&bd1->bd_le.le_list, &started); - if (bd1 == bd2) { - bd2 = NULL; - bd2 = list_prepare_entry(bd2, - &sdp->sd_log_le_databuf, - bd_le.le_list); - } - total_dbuf--; - if (bh1) { - if (buffer_dirty(bh1)) { - get_bh(bh1); - - gfs2_log_unlock(sdp); - - ll_rw_block(SWRITE, 1, &bh1); - brelse(bh1); - - gfs2_log_lock(sdp); - } - continue; - } - continue; - } else if (bh1) { /* A journaled buffer */ - int magic; - gfs2_log_unlock(sdp); - if (!bh) { - bh = gfs2_log_get_buf(sdp); - ld = (struct gfs2_log_descriptor *) - bh->b_data; - ptr = (__be64 *)(bh->b_data + - DATABUF_OFFSET); - ld->ld_header.mh_magic = - cpu_to_be32(GFS2_MAGIC); - ld->ld_header.mh_type = - cpu_to_be32(GFS2_METATYPE_LD); - ld->ld_header.mh_format = - cpu_to_be32(GFS2_FORMAT_LD); - ld->ld_type = - cpu_to_be32(GFS2_LOG_DESC_JDATA); - ld->ld_length = cpu_to_be32(num + 1); - ld->ld_data1 = cpu_to_be32(num); - ld->ld_data2 = cpu_to_be32(0); - memset(ld->ld_reserved, 0, sizeof(ld->ld_reserved)); - } - magic = gfs2_check_magic(bh1); - *ptr++ = cpu_to_be64(bh1->b_blocknr); - *ptr++ = cpu_to_be64((__u64)magic); - clear_buffer_escaped(bh1); - if (unlikely(magic != 0)) - set_buffer_escaped(bh1); - gfs2_log_lock(sdp); - if (++n >= num) - break; - } else if (!bh1) { - total_dbuf--; - sdp->sd_log_num_databuf--; - list_del_init(&bd1->bd_le.le_list); - if (bd1 == bd2) { - bd2 = NULL; - bd2 = list_prepare_entry(bd2, - &sdp->sd_log_le_databuf, - bd_le.le_list); - } - kmem_cache_free(gfs2_bufdata_cachep, bd1); - } + while(!list_empty(list)) { + bd = list_entry(list->next, struct gfs2_bufdata, bd_le.le_list); + list_move_tail(&bd->bd_le.le_list, done); + get_bh(bd->bd_bh); + while (be64_to_cpu(*ptr) != bd->bd_bh->b_blocknr) { + gfs2_log_incr_head(sdp); + ptr += 2; } gfs2_log_unlock(sdp); - if (bh) { - set_buffer_mapped(bh); - set_buffer_dirty(bh); - ll_rw_block(WRITE, 1, &bh); - bh = NULL; + lock_buffer(bd->bd_bh); + if (buffer_escaped(bd->bd_bh)) { + void *kaddr; + bh1 = gfs2_log_get_buf(sdp); + kaddr = kmap_atomic(bd->bd_bh->b_page, KM_USER0); + memcpy(bh1->b_data, kaddr + bh_offset(bd->bd_bh), + bh1->b_size); + kunmap_atomic(kaddr, KM_USER0); + *(__be32 *)bh1->b_data = 0; + clear_buffer_escaped(bd->bd_bh); + unlock_buffer(bd->bd_bh); + brelse(bd->bd_bh); + } else { + bh1 = gfs2_log_fake_buf(sdp, bd->bd_bh); } - n = 0; + submit_bh(WRITE, bh1); gfs2_log_lock(sdp); - list_for_each_entry_continue(bd2, &sdp->sd_log_le_databuf, - bd_le.le_list) { - if (!bd2->bd_bh) - continue; - /* copy buffer if it needs escaping */ - gfs2_log_unlock(sdp); - if (unlikely(buffer_escaped(bd2->bd_bh))) { - void *kaddr; - struct page *page = bd2->bd_bh->b_page; - bh = gfs2_log_get_buf(sdp); - kaddr = kmap_atomic(page, KM_USER0); - memcpy(bh->b_data, - kaddr + bh_offset(bd2->bd_bh), - sdp->sd_sb.sb_bsize); - kunmap_atomic(kaddr, KM_USER0); - *(__be32 *)bh->b_data = 0; - } else { - bh = gfs2_log_fake_buf(sdp, bd2->bd_bh); - } - set_buffer_dirty(bh); - ll_rw_block(WRITE, 1, &bh); - gfs2_log_lock(sdp); - if (++n >= num) - break; - } - bh = NULL; - BUG_ON(total_dbuf < num); - total_dbuf -= num; - total_jdata -= num; + ptr += 2; } gfs2_log_unlock(sdp); + brelse(bh); +} - /* Wait on all ordered buffers */ - while (!list_empty(&started)) { - gfs2_log_lock(sdp); - bd1 = list_entry(started.next, struct gfs2_bufdata, - bd_le.le_list); - list_del_init(&bd1->bd_le.le_list); - sdp->sd_log_num_databuf--; - bh = bd1->bd_bh; - if (bh) { - bh->b_private = NULL; - get_bh(bh); - gfs2_log_unlock(sdp); - wait_on_buffer(bh); - brelse(bh); - } else - gfs2_log_unlock(sdp); +/** + * databuf_lo_before_commit - Scan the data buffers, writing as we go + * + */ - kmem_cache_free(gfs2_bufdata_cachep, bd1); - } +static void databuf_lo_before_commit(struct gfs2_sbd *sdp) +{ + struct gfs2_bufdata *bd = NULL; + struct buffer_head *bh = NULL; + unsigned int n = 0; + __be64 *ptr = NULL, *end = NULL; + LIST_HEAD(processed); + LIST_HEAD(in_progress); - /* We've removed all the ordered write bufs here, so only jdata left */ - gfs2_assert_warn(sdp, sdp->sd_log_num_databuf == sdp->sd_log_num_jdata); + gfs2_log_lock(sdp); + while (!list_empty(&sdp->sd_log_le_databuf)) { + if (ptr == end) { + gfs2_log_unlock(sdp); + gfs2_write_blocks(sdp, bh, &in_progress, &processed, n); + n = 0; + bh = gfs2_get_log_desc(sdp, GFS2_LOG_DESC_JDATA); + ptr = bh_log_ptr(bh); + end = bh_ptr_end(bh) - 1; + gfs2_log_lock(sdp); + continue; + } + bd = list_entry(sdp->sd_log_le_databuf.next, struct gfs2_bufdata, bd_le.le_list); + list_move_tail(&bd->bd_le.le_list, &in_progress); + gfs2_check_magic(bd->bd_bh); + *ptr++ = cpu_to_be64(bd->bd_bh->b_blocknr); + *ptr++ = cpu_to_be64(buffer_escaped(bh) ? 1 : 0); + n++; + } + gfs2_log_unlock(sdp); + gfs2_write_blocks(sdp, bh, &in_progress, &processed, n); + gfs2_log_lock(sdp); + list_splice(&processed, &sdp->sd_log_le_databuf); + gfs2_log_unlock(sdp); } static int databuf_lo_scan_elements(struct gfs2_jdesc *jd, unsigned int start, @@ -765,11 +767,9 @@ static void databuf_lo_after_commit(struct gfs2_sbd *sdp, struct gfs2_ail *ai) bd = list_entry(head->next, struct gfs2_bufdata, bd_le.le_list); list_del_init(&bd->bd_le.le_list); sdp->sd_log_num_databuf--; - sdp->sd_log_num_jdata--; gfs2_unpin(sdp, bd->bd_bh, ai); } gfs2_assert_warn(sdp, !sdp->sd_log_num_databuf); - gfs2_assert_warn(sdp, !sdp->sd_log_num_jdata); } @@ -817,10 +817,10 @@ const struct gfs2_log_operations gfs2_databuf_lops = { const struct gfs2_log_operations *gfs2_log_ops[] = { &gfs2_glock_lops, + &gfs2_databuf_lops, &gfs2_buf_lops, - &gfs2_revoke_lops, &gfs2_rg_lops, - &gfs2_databuf_lops, + &gfs2_revoke_lops, NULL, }; diff --git a/fs/gfs2/main.c b/fs/gfs2/main.c index d5d4e68b880..79c91fd8381 100644 --- a/fs/gfs2/main.c +++ b/fs/gfs2/main.c @@ -107,6 +107,8 @@ static int __init init_gfs2_fs(void) fail_unregister: unregister_filesystem(&gfs2_fs_type); fail: + gfs2_glock_exit(); + if (gfs2_bufdata_cachep) kmem_cache_destroy(gfs2_bufdata_cachep); @@ -127,6 +129,7 @@ fail: static void __exit exit_gfs2_fs(void) { + gfs2_glock_exit(); gfs2_unregister_debugfs(); unregister_filesystem(&gfs2_fs_type); unregister_filesystem(&gfs2meta_fs_type); diff --git a/fs/gfs2/meta_io.c b/fs/gfs2/meta_io.c index 8da343b34ae..4da423985e4 100644 --- a/fs/gfs2/meta_io.c +++ b/fs/gfs2/meta_io.c @@ -297,74 +297,35 @@ void gfs2_attach_bufdata(struct gfs2_glock *gl, struct buffer_head *bh, unlock_page(bh->b_page); } -/** - * gfs2_pin - Pin a buffer in memory - * @sdp: the filesystem the buffer belongs to - * @bh: The buffer to be pinned - * - */ - -void gfs2_pin(struct gfs2_sbd *sdp, struct buffer_head *bh) +void gfs2_remove_from_journal(struct buffer_head *bh, struct gfs2_trans *tr, int meta) { + struct gfs2_sbd *sdp = GFS2_SB(bh->b_page->mapping->host); struct gfs2_bufdata *bd = bh->b_private; - - gfs2_assert_withdraw(sdp, test_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags)); - - if (test_set_buffer_pinned(bh)) - gfs2_assert_withdraw(sdp, 0); - - wait_on_buffer(bh); - - /* If this buffer is in the AIL and it has already been written - to in-place disk block, remove it from the AIL. */ - - gfs2_log_lock(sdp); - if (bd->bd_ail && !buffer_in_io(bh)) - list_move(&bd->bd_ail_st_list, &bd->bd_ail->ai_ail2_list); - gfs2_log_unlock(sdp); - - clear_buffer_dirty(bh); - wait_on_buffer(bh); - - if (!buffer_uptodate(bh)) - gfs2_io_error_bh(sdp, bh); - - get_bh(bh); -} - -/** - * gfs2_unpin - Unpin a buffer - * @sdp: the filesystem the buffer belongs to - * @bh: The buffer to unpin - * @ai: - * - */ - -void gfs2_unpin(struct gfs2_sbd *sdp, struct buffer_head *bh, - struct gfs2_ail *ai) -{ - struct gfs2_bufdata *bd = bh->b_private; - - gfs2_assert_withdraw(sdp, buffer_uptodate(bh)); - - if (!buffer_pinned(bh)) - gfs2_assert_withdraw(sdp, 0); - - mark_buffer_dirty(bh); - clear_buffer_pinned(bh); - - gfs2_log_lock(sdp); - if (bd->bd_ail) { - list_del(&bd->bd_ail_st_list); + if (test_clear_buffer_pinned(bh)) { + list_del_init(&bd->bd_le.le_list); + if (meta) { + gfs2_assert_warn(sdp, sdp->sd_log_num_buf); + sdp->sd_log_num_buf--; + tr->tr_num_buf_rm++; + } else { + gfs2_assert_warn(sdp, sdp->sd_log_num_databuf); + sdp->sd_log_num_databuf--; + tr->tr_num_databuf_rm++; + } + tr->tr_touched = 1; brelse(bh); - } else { - struct gfs2_glock *gl = bd->bd_gl; - list_add(&bd->bd_ail_gl_list, &gl->gl_ail_list); - atomic_inc(&gl->gl_ail_count); } - bd->bd_ail = ai; - list_add(&bd->bd_ail_st_list, &ai->ai_ail1_list); - gfs2_log_unlock(sdp); + if (bd) { + if (bd->bd_ail) { + gfs2_remove_from_ail(NULL, bd); + bh->b_private = NULL; + bd->bd_bh = NULL; + bd->bd_blkno = bh->b_blocknr; + gfs2_trans_add_revoke(sdp, bd); + } + } + clear_buffer_dirty(bh); + clear_buffer_uptodate(bh); } /** @@ -383,44 +344,11 @@ void gfs2_meta_wipe(struct gfs2_inode *ip, u64 bstart, u32 blen) while (blen) { bh = getbuf(ip->i_gl, bstart, NO_CREATE); if (bh) { - struct gfs2_bufdata *bd = bh->b_private; - - if (test_clear_buffer_pinned(bh)) { - struct gfs2_trans *tr = current->journal_info; - struct gfs2_inode *bh_ip = - GFS2_I(bh->b_page->mapping->host); - - gfs2_log_lock(sdp); - list_del_init(&bd->bd_le.le_list); - gfs2_assert_warn(sdp, sdp->sd_log_num_buf); - sdp->sd_log_num_buf--; - gfs2_log_unlock(sdp); - if (bh_ip->i_inode.i_private != NULL) - tr->tr_num_databuf_rm++; - else - tr->tr_num_buf_rm++; - brelse(bh); - } - if (bd) { - gfs2_log_lock(sdp); - if (bd->bd_ail) { - u64 blkno = bh->b_blocknr; - bd->bd_ail = NULL; - list_del(&bd->bd_ail_st_list); - list_del(&bd->bd_ail_gl_list); - atomic_dec(&bd->bd_gl->gl_ail_count); - brelse(bh); - gfs2_log_unlock(sdp); - gfs2_trans_add_revoke(sdp, blkno); - } else - gfs2_log_unlock(sdp); - } - lock_buffer(bh); - clear_buffer_dirty(bh); - clear_buffer_uptodate(bh); + gfs2_log_lock(sdp); + gfs2_remove_from_journal(bh, current->journal_info, 1); + gfs2_log_unlock(sdp); unlock_buffer(bh); - brelse(bh); } @@ -446,10 +374,10 @@ void gfs2_meta_cache_flush(struct gfs2_inode *ip) for (x = 0; x < GFS2_MAX_META_HEIGHT; x++) { bh_slot = &ip->i_cache[x]; - if (!*bh_slot) - break; - brelse(*bh_slot); - *bh_slot = NULL; + if (*bh_slot) { + brelse(*bh_slot); + *bh_slot = NULL; + } } spin_unlock(&ip->i_spin); diff --git a/fs/gfs2/meta_io.h b/fs/gfs2/meta_io.h index 527bf19d969..b7048222ebb 100644 --- a/fs/gfs2/meta_io.h +++ b/fs/gfs2/meta_io.h @@ -50,9 +50,9 @@ int gfs2_meta_wait(struct gfs2_sbd *sdp, struct buffer_head *bh); void gfs2_attach_bufdata(struct gfs2_glock *gl, struct buffer_head *bh, int meta); -void gfs2_pin(struct gfs2_sbd *sdp, struct buffer_head *bh); -void gfs2_unpin(struct gfs2_sbd *sdp, struct buffer_head *bh, - struct gfs2_ail *ai); + +void gfs2_remove_from_journal(struct buffer_head *bh, struct gfs2_trans *tr, + int meta); void gfs2_meta_wipe(struct gfs2_inode *ip, u64 bstart, u32 blen); diff --git a/fs/gfs2/mount.c b/fs/gfs2/mount.c index 4864659555d..b941f9f9f95 100644 --- a/fs/gfs2/mount.c +++ b/fs/gfs2/mount.c @@ -42,6 +42,7 @@ enum { Opt_nosuiddir, Opt_data_writeback, Opt_data_ordered, + Opt_err, }; static match_table_t tokens = { @@ -64,7 +65,8 @@ static match_table_t tokens = { {Opt_suiddir, "suiddir"}, {Opt_nosuiddir, "nosuiddir"}, {Opt_data_writeback, "data=writeback"}, - {Opt_data_ordered, "data=ordered"} + {Opt_data_ordered, "data=ordered"}, + {Opt_err, NULL} }; /** @@ -237,6 +239,7 @@ int gfs2_mount_args(struct gfs2_sbd *sdp, char *data_arg, int remount) case Opt_data_ordered: args->ar_data = GFS2_DATA_ORDERED; break; + case Opt_err: default: fs_info(sdp, "unknown option: %s\n", o); error = -EINVAL; diff --git a/fs/gfs2/ops_address.c b/fs/gfs2/ops_address.c index 42a5f58f6fc..873a511ef2b 100644 --- a/fs/gfs2/ops_address.c +++ b/fs/gfs2/ops_address.c @@ -90,7 +90,7 @@ static int gfs2_get_block_noalloc(struct inode *inode, sector_t lblock, error = gfs2_block_map(inode, lblock, 0, bh_result); if (error) return error; - if (bh_result->b_blocknr == 0) + if (!buffer_mapped(bh_result)) return -EIO; return 0; } @@ -414,7 +414,8 @@ static int gfs2_prepare_write(struct file *file, struct page *page, if (ind_blocks || data_blocks) rblocks += RES_STATFS + RES_QUOTA; - error = gfs2_trans_begin(sdp, rblocks, 0); + error = gfs2_trans_begin(sdp, rblocks, + PAGE_CACHE_SIZE/sdp->sd_sb.sb_bsize); if (error) goto out_trans_fail; @@ -616,58 +617,50 @@ static sector_t gfs2_bmap(struct address_space *mapping, sector_t lblock) return dblock; } -static void discard_buffer(struct gfs2_sbd *sdp, struct buffer_head *bh) +static void gfs2_discard(struct gfs2_sbd *sdp, struct buffer_head *bh) { struct gfs2_bufdata *bd; + lock_buffer(bh); gfs2_log_lock(sdp); + clear_buffer_dirty(bh); bd = bh->b_private; if (bd) { - bd->bd_bh = NULL; - bh->b_private = NULL; - if (!bd->bd_ail && list_empty(&bd->bd_le.le_list)) - kmem_cache_free(gfs2_bufdata_cachep, bd); + if (!list_empty(&bd->bd_le.le_list) && !buffer_pinned(bh)) + list_del_init(&bd->bd_le.le_list); + else + gfs2_remove_from_journal(bh, current->journal_info, 0); } - gfs2_log_unlock(sdp); - - lock_buffer(bh); - clear_buffer_dirty(bh); bh->b_bdev = NULL; clear_buffer_mapped(bh); clear_buffer_req(bh); clear_buffer_new(bh); - clear_buffer_delay(bh); + gfs2_log_unlock(sdp); unlock_buffer(bh); } static void gfs2_invalidatepage(struct page *page, unsigned long offset) { struct gfs2_sbd *sdp = GFS2_SB(page->mapping->host); - struct buffer_head *head, *bh, *next; - unsigned int curr_off = 0; + struct buffer_head *bh, *head; + unsigned long pos = 0; BUG_ON(!PageLocked(page)); if (offset == 0) ClearPageChecked(page); if (!page_has_buffers(page)) - return; + goto out; bh = head = page_buffers(page); do { - unsigned int next_off = curr_off + bh->b_size; - next = bh->b_this_page; - - if (offset <= curr_off) - discard_buffer(sdp, bh); - - curr_off = next_off; - bh = next; + if (offset <= pos) + gfs2_discard(sdp, bh); + pos += bh->b_size; + bh = bh->b_this_page; } while (bh != head); - - if (!offset) +out: + if (offset == 0) try_to_release_page(page, 0); - - return; } /** @@ -736,59 +729,6 @@ out: } /** - * stuck_releasepage - We're stuck in gfs2_releasepage(). Print stuff out. - * @bh: the buffer we're stuck on - * - */ - -static void stuck_releasepage(struct buffer_head *bh) -{ - struct inode *inode = bh->b_page->mapping->host; - struct gfs2_sbd *sdp = inode->i_sb->s_fs_info; - struct gfs2_bufdata *bd = bh->b_private; - struct gfs2_glock *gl; -static unsigned limit = 0; - - if (limit > 3) - return; - limit++; - - fs_warn(sdp, "stuck in gfs2_releasepage() %p\n", inode); - fs_warn(sdp, "blkno = %llu, bh->b_count = %d\n", - (unsigned long long)bh->b_blocknr, atomic_read(&bh->b_count)); - fs_warn(sdp, "pinned = %u\n", buffer_pinned(bh)); - fs_warn(sdp, "bh->b_private = %s\n", (bd) ? "!NULL" : "NULL"); - - if (!bd) - return; - - gl = bd->bd_gl; - - fs_warn(sdp, "gl = (%u, %llu)\n", - gl->gl_name.ln_type, (unsigned long long)gl->gl_name.ln_number); - - fs_warn(sdp, "bd_list_tr = %s, bd_le.le_list = %s\n", - (list_empty(&bd->bd_list_tr)) ? "no" : "yes", - (list_empty(&bd->bd_le.le_list)) ? "no" : "yes"); - - if (gl->gl_ops == &gfs2_inode_glops) { - struct gfs2_inode *ip = gl->gl_object; - unsigned int x; - - if (!ip) - return; - - fs_warn(sdp, "ip = %llu %llu\n", - (unsigned long long)ip->i_no_formal_ino, - (unsigned long long)ip->i_no_addr); - - for (x = 0; x < GFS2_MAX_META_HEIGHT; x++) - fs_warn(sdp, "ip->i_cache[%u] = %s\n", - x, (ip->i_cache[x]) ? "!NULL" : "NULL"); - } -} - -/** * gfs2_releasepage - free the metadata associated with a page * @page: the page that's being released * @gfp_mask: passed from Linux VFS, ignored by us @@ -805,41 +745,39 @@ int gfs2_releasepage(struct page *page, gfp_t gfp_mask) struct gfs2_sbd *sdp = aspace->i_sb->s_fs_info; struct buffer_head *bh, *head; struct gfs2_bufdata *bd; - unsigned long t = jiffies + gfs2_tune_get(sdp, gt_stall_secs) * HZ; if (!page_has_buffers(page)) - goto out; + return 0; + gfs2_log_lock(sdp); head = bh = page_buffers(page); do { - while (atomic_read(&bh->b_count)) { - if (!atomic_read(&aspace->i_writecount)) - return 0; - - if (!(gfp_mask & __GFP_WAIT)) - return 0; - - if (time_after_eq(jiffies, t)) { - stuck_releasepage(bh); - /* should we withdraw here? */ - return 0; - } - - yield(); - } - + if (atomic_read(&bh->b_count)) + goto cannot_release; + bd = bh->b_private; + if (bd && bd->bd_ail) + goto cannot_release; gfs2_assert_warn(sdp, !buffer_pinned(bh)); gfs2_assert_warn(sdp, !buffer_dirty(bh)); + bh = bh->b_this_page; + } while(bh != head); + gfs2_log_unlock(sdp); + head = bh = page_buffers(page); + do { gfs2_log_lock(sdp); bd = bh->b_private; if (bd) { gfs2_assert_warn(sdp, bd->bd_bh == bh); gfs2_assert_warn(sdp, list_empty(&bd->bd_list_tr)); - gfs2_assert_warn(sdp, !bd->bd_ail); - bd->bd_bh = NULL; - if (!list_empty(&bd->bd_le.le_list)) - bd = NULL; + if (!list_empty(&bd->bd_le.le_list)) { + if (!buffer_pinned(bh)) + list_del_init(&bd->bd_le.le_list); + else + bd = NULL; + } + if (bd) + bd->bd_bh = NULL; bh->b_private = NULL; } gfs2_log_unlock(sdp); @@ -849,8 +787,10 @@ int gfs2_releasepage(struct page *page, gfp_t gfp_mask) bh = bh->b_this_page; } while (bh != head); -out: return try_to_free_buffers(page); +cannot_release: + gfs2_log_unlock(sdp); + return 0; } const struct address_space_operations gfs2_file_aops = { diff --git a/fs/gfs2/ops_export.c b/fs/gfs2/ops_export.c index b8312edee0e..e2d1347796a 100644 --- a/fs/gfs2/ops_export.c +++ b/fs/gfs2/ops_export.c @@ -237,7 +237,7 @@ static struct dentry *gfs2_get_dentry(struct super_block *sb, void *inum_obj) inode = gfs2_inode_lookup(sb, DT_UNKNOWN, inum->no_addr, - 0); + 0, 0); if (!inode) goto fail; if (IS_ERR(inode)) { diff --git a/fs/gfs2/ops_file.c b/fs/gfs2/ops_file.c index 94d76ace0b9..46a9e10ff17 100644 --- a/fs/gfs2/ops_file.c +++ b/fs/gfs2/ops_file.c @@ -571,7 +571,8 @@ static int do_flock(struct file *file, int cmd, struct file_lock *fl) int error = 0; state = (fl->fl_type == F_WRLCK) ? LM_ST_EXCLUSIVE : LM_ST_SHARED; - flags = (IS_SETLKW(cmd) ? 0 : LM_FLAG_TRY) | GL_EXACT | GL_NOCACHE; + flags = (IS_SETLKW(cmd) ? 0 : LM_FLAG_TRY) | GL_EXACT | GL_NOCACHE + | GL_FLOCK; mutex_lock(&fp->f_fl_mutex); @@ -579,21 +580,19 @@ static int do_flock(struct file *file, int cmd, struct file_lock *fl) if (gl) { if (fl_gh->gh_state == state) goto out; - gfs2_glock_hold(gl); flock_lock_file_wait(file, &(struct file_lock){.fl_type = F_UNLCK}); - gfs2_glock_dq_uninit(fl_gh); + gfs2_glock_dq_wait(fl_gh); + gfs2_holder_reinit(state, flags, fl_gh); } else { error = gfs2_glock_get(GFS2_SB(&ip->i_inode), ip->i_no_addr, &gfs2_flock_glops, CREATE, &gl); if (error) goto out; + gfs2_holder_init(gl, state, flags, fl_gh); + gfs2_glock_put(gl); } - - gfs2_holder_init(gl, state, flags, fl_gh); - gfs2_glock_put(gl); - error = gfs2_glock_nq(fl_gh); if (error) { gfs2_holder_uninit(fl_gh); diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c index cf5aa505054..17de58e83d9 100644 --- a/fs/gfs2/ops_fstype.c +++ b/fs/gfs2/ops_fstype.c @@ -28,18 +28,18 @@ #include "lm.h" #include "mount.h" #include "ops_fstype.h" +#include "ops_dentry.h" #include "ops_super.h" #include "recovery.h" #include "rgrp.h" #include "super.h" #include "sys.h" #include "util.h" +#include "log.h" #define DO 0 #define UNDO 1 -extern struct dentry_operations gfs2_dops; - static struct gfs2_sbd *init_sbd(struct super_block *sb) { struct gfs2_sbd *sdp; @@ -82,13 +82,15 @@ static struct gfs2_sbd *init_sbd(struct super_block *sb) INIT_LIST_HEAD(&sdp->sd_log_le_revoke); INIT_LIST_HEAD(&sdp->sd_log_le_rg); INIT_LIST_HEAD(&sdp->sd_log_le_databuf); + INIT_LIST_HEAD(&sdp->sd_log_le_ordered); mutex_init(&sdp->sd_log_reserve_mutex); INIT_LIST_HEAD(&sdp->sd_ail1_list); INIT_LIST_HEAD(&sdp->sd_ail2_list); init_rwsem(&sdp->sd_log_flush_lock); - INIT_LIST_HEAD(&sdp->sd_log_flush_list); + atomic_set(&sdp->sd_log_in_flight, 0); + init_waitqueue_head(&sdp->sd_log_flush_wait); INIT_LIST_HEAD(&sdp->sd_revoke_list); @@ -145,7 +147,8 @@ static int init_names(struct gfs2_sbd *sdp, int silent) snprintf(sdp->sd_proto_name, GFS2_FSNAME_LEN, "%s", proto); snprintf(sdp->sd_table_name, GFS2_FSNAME_LEN, "%s", table); - while ((table = strchr(sdp->sd_table_name, '/'))) + table = sdp->sd_table_name; + while ((table = strchr(table, '/'))) *table = '_'; out: @@ -161,14 +164,6 @@ static int init_locking(struct gfs2_sbd *sdp, struct gfs2_holder *mount_gh, if (undo) goto fail_trans; - p = kthread_run(gfs2_scand, sdp, "gfs2_scand"); - error = IS_ERR(p); - if (error) { - fs_err(sdp, "can't start scand thread: %d\n", error); - return error; - } - sdp->sd_scand_process = p; - for (sdp->sd_glockd_num = 0; sdp->sd_glockd_num < sdp->sd_args.ar_num_glockd; sdp->sd_glockd_num++) { @@ -229,14 +224,13 @@ fail: while (sdp->sd_glockd_num--) kthread_stop(sdp->sd_glockd_process[sdp->sd_glockd_num]); - kthread_stop(sdp->sd_scand_process); return error; } static inline struct inode *gfs2_lookup_root(struct super_block *sb, u64 no_addr) { - return gfs2_inode_lookup(sb, DT_DIR, no_addr, 0); + return gfs2_inode_lookup(sb, DT_DIR, no_addr, 0, 0); } static int init_sb(struct gfs2_sbd *sdp, int silent, int undo) @@ -301,8 +295,9 @@ static int init_sb(struct gfs2_sbd *sdp, int silent, int undo) fs_err(sdp, "can't get root dentry\n"); error = -ENOMEM; iput(inode); - } - sb->s_root->d_op = &gfs2_dops; + } else + sb->s_root->d_op = &gfs2_dops; + out: gfs2_glock_dq_uninit(&sb_gh); return error; @@ -368,7 +363,7 @@ static int init_journal(struct gfs2_sbd *sdp, int undo) ip = GFS2_I(sdp->sd_jdesc->jd_inode); error = gfs2_glock_nq_init(ip->i_gl, LM_ST_SHARED, - LM_FLAG_NOEXP | GL_EXACT, + LM_FLAG_NOEXP | GL_EXACT | GL_NOCACHE, &sdp->sd_jinode_gh); if (error) { fs_err(sdp, "can't acquire journal inode glock: %d\n", @@ -818,7 +813,6 @@ static struct super_block* get_gfs2_sb(const char *dev_name) struct nameidata nd; struct file_system_type *fstype; struct super_block *sb = NULL, *s; - struct list_head *l; int error; error = path_lookup(dev_name, LOOKUP_FOLLOW, &nd); @@ -830,8 +824,7 @@ static struct super_block* get_gfs2_sb(const char *dev_name) error = vfs_getattr(nd.mnt, nd.dentry, &stat); fstype = get_fs_type("gfs2"); - list_for_each(l, &fstype->fs_supers) { - s = list_entry(l, struct super_block, s_instances); + list_for_each_entry(s, &fstype->fs_supers, s_instances) { if ((S_ISBLK(stat.mode) && s->s_dev == stat.rdev) || (S_ISDIR(stat.mode) && s == nd.dentry->d_inode->i_sb)) { sb = s; @@ -861,7 +854,7 @@ static int gfs2_get_sb_meta(struct file_system_type *fs_type, int flags, error = -ENOENT; goto error; } - sdp = (struct gfs2_sbd*) sb->s_fs_info; + sdp = sb->s_fs_info; if (sdp->sd_vfs_meta) { printk(KERN_WARNING "GFS2: gfs2meta mount already exists\n"); error = -EBUSY; @@ -896,7 +889,10 @@ error: static void gfs2_kill_sb(struct super_block *sb) { - gfs2_delete_debugfs_file(sb->s_fs_info); + if (sb->s_fs_info) { + gfs2_delete_debugfs_file(sb->s_fs_info); + gfs2_meta_syncfs(sb->s_fs_info); + } kill_block_super(sb); } diff --git a/fs/gfs2/ops_inode.c b/fs/gfs2/ops_inode.c index 911c115b5c6..291f0c7eaa3 100644 --- a/fs/gfs2/ops_inode.c +++ b/fs/gfs2/ops_inode.c @@ -69,7 +69,7 @@ static int gfs2_create(struct inode *dir, struct dentry *dentry, mark_inode_dirty(inode); break; } else if (PTR_ERR(inode) != -EEXIST || - (nd->intent.open.flags & O_EXCL)) { + (nd && (nd->intent.open.flags & O_EXCL))) { gfs2_holder_uninit(ghs); return PTR_ERR(inode); } @@ -278,17 +278,25 @@ static int gfs2_unlink(struct inode *dir, struct dentry *dentry) gfs2_holder_init(rgd->rd_gl, LM_ST_EXCLUSIVE, 0, ghs + 2); - error = gfs2_glock_nq_m(3, ghs); + error = gfs2_glock_nq(ghs); /* parent */ if (error) - goto out; + goto out_parent; + + error = gfs2_glock_nq(ghs + 1); /* child */ + if (error) + goto out_child; + + error = gfs2_glock_nq(ghs + 2); /* rgrp */ + if (error) + goto out_rgrp; error = gfs2_unlink_ok(dip, &dentry->d_name, ip); if (error) - goto out_gunlock; + goto out_rgrp; error = gfs2_trans_begin(sdp, 2*RES_DINODE + RES_LEAF + RES_RG_BIT, 0); if (error) - goto out_gunlock; + goto out_rgrp; error = gfs2_dir_del(dip, &dentry->d_name); if (error) @@ -298,12 +306,15 @@ static int gfs2_unlink(struct inode *dir, struct dentry *dentry) out_end_trans: gfs2_trans_end(sdp); -out_gunlock: - gfs2_glock_dq_m(3, ghs); -out: - gfs2_holder_uninit(ghs); - gfs2_holder_uninit(ghs + 1); + gfs2_glock_dq(ghs + 2); +out_rgrp: gfs2_holder_uninit(ghs + 2); + gfs2_glock_dq(ghs + 1); +out_child: + gfs2_holder_uninit(ghs + 1); + gfs2_glock_dq(ghs); +out_parent: + gfs2_holder_uninit(ghs); gfs2_glock_dq_uninit(&ri_gh); return error; } @@ -894,12 +905,17 @@ static int gfs2_permission(struct inode *inode, int mask, struct nameidata *nd) static int setattr_size(struct inode *inode, struct iattr *attr) { struct gfs2_inode *ip = GFS2_I(inode); + struct gfs2_sbd *sdp = GFS2_SB(inode); int error; if (attr->ia_size != ip->i_di.di_size) { - error = vmtruncate(inode, attr->ia_size); + error = gfs2_trans_begin(sdp, 0, sdp->sd_jdesc->jd_blocks); if (error) return error; + error = vmtruncate(inode, attr->ia_size); + gfs2_trans_end(sdp); + if (error) + return error; } error = gfs2_truncatei(ip, attr->ia_size); diff --git a/fs/gfs2/ops_super.c b/fs/gfs2/ops_super.c index 603d940f115..950f31460e8 100644 --- a/fs/gfs2/ops_super.c +++ b/fs/gfs2/ops_super.c @@ -92,7 +92,6 @@ static void gfs2_put_super(struct super_block *sb) kthread_stop(sdp->sd_recoverd_process); while (sdp->sd_glockd_num--) kthread_stop(sdp->sd_glockd_process[sdp->sd_glockd_num]); - kthread_stop(sdp->sd_scand_process); if (!(sb->s_flags & MS_RDONLY)) { error = gfs2_make_fs_ro(sdp); @@ -456,12 +455,15 @@ static void gfs2_delete_inode(struct inode *inode) } error = gfs2_dinode_dealloc(ip); - /* - * Must do this before unlock to avoid trying to write back - * potentially dirty data now that inode no longer exists - * on disk. - */ + if (error) + goto out_unlock; + + error = gfs2_trans_begin(sdp, 0, sdp->sd_jdesc->jd_blocks); + if (error) + goto out_unlock; + /* Needs to be done before glock release & also in a transaction */ truncate_inode_pages(&inode->i_data, 0); + gfs2_trans_end(sdp); out_unlock: gfs2_glock_dq(&ip->i_iopen_gh); diff --git a/fs/gfs2/quota.c b/fs/gfs2/quota.c index 6e546ee8f3d..addb51e0f13 100644 --- a/fs/gfs2/quota.c +++ b/fs/gfs2/quota.c @@ -70,6 +70,7 @@ struct gfs2_quota_host { u64 qu_limit; u64 qu_warn; s64 qu_value; + u32 qu_ll_next; }; struct gfs2_quota_change_host { @@ -580,6 +581,7 @@ static void gfs2_quota_in(struct gfs2_quota_host *qu, const void *buf) qu->qu_limit = be64_to_cpu(str->qu_limit); qu->qu_warn = be64_to_cpu(str->qu_warn); qu->qu_value = be64_to_cpu(str->qu_value); + qu->qu_ll_next = be32_to_cpu(str->qu_ll_next); } static void gfs2_quota_out(const struct gfs2_quota_host *qu, void *buf) @@ -589,6 +591,7 @@ static void gfs2_quota_out(const struct gfs2_quota_host *qu, void *buf) str->qu_limit = cpu_to_be64(qu->qu_limit); str->qu_warn = cpu_to_be64(qu->qu_warn); str->qu_value = cpu_to_be64(qu->qu_value); + str->qu_ll_next = cpu_to_be32(qu->qu_ll_next); memset(&str->qu_reserved, 0, sizeof(str->qu_reserved)); } @@ -614,6 +617,16 @@ static int gfs2_adjust_quota(struct gfs2_inode *ip, loff_t loc, s64 value; int err = -EIO; + if (gfs2_is_stuffed(ip)) { + struct gfs2_alloc *al = NULL; + al = gfs2_alloc_get(ip); + /* just request 1 blk */ + al->al_requested = 1; + gfs2_inplace_reserve(ip); + gfs2_unstuff_dinode(ip, NULL); + gfs2_inplace_release(ip); + gfs2_alloc_put(ip); + } page = grab_cache_page(mapping, index); if (!page) return -ENOMEM; diff --git a/fs/gfs2/recovery.c b/fs/gfs2/recovery.c index 5ada38c99a2..beb6c7ac008 100644 --- a/fs/gfs2/recovery.c +++ b/fs/gfs2/recovery.c @@ -469,7 +469,7 @@ int gfs2_recover_journal(struct gfs2_jdesc *jd) }; error = gfs2_glock_nq_init(ip->i_gl, LM_ST_SHARED, - LM_FLAG_NOEXP, &ji_gh); + LM_FLAG_NOEXP | GL_NOCACHE, &ji_gh); if (error) goto fail_gunlock_j; } else { diff --git a/fs/gfs2/rgrp.c b/fs/gfs2/rgrp.c index ce48c4594ec..708c287e1d0 100644 --- a/fs/gfs2/rgrp.c +++ b/fs/gfs2/rgrp.c @@ -31,6 +31,7 @@ #include "inode.h" #define BFITNOENT ((u32)~0) +#define NO_BLOCK ((u64)~0) /* * These routines are used by the resource group routines (rgrp.c) @@ -116,8 +117,7 @@ static unsigned char gfs2_testbit(struct gfs2_rgrpd *rgd, unsigned char *buffer, * @buffer: the buffer that holds the bitmaps * @buflen: the length (in bytes) of the buffer * @goal: start search at this block's bit-pair (within @buffer) - * @old_state: GFS2_BLKST_XXX the state of the block we're looking for; - * bit 0 = alloc(1)/free(0), bit 1 = meta(1)/data(0) + * @old_state: GFS2_BLKST_XXX the state of the block we're looking for. * * Scope of @goal and returned block number is only within this bitmap buffer, * not entire rgrp or filesystem. @buffer will be offset from the actual @@ -137,9 +137,13 @@ static u32 gfs2_bitfit(struct gfs2_rgrpd *rgd, unsigned char *buffer, byte = buffer + (goal / GFS2_NBBY); bit = (goal % GFS2_NBBY) * GFS2_BIT_SIZE; end = buffer + buflen; - alloc = (old_state & 1) ? 0 : 0x55; + alloc = (old_state == GFS2_BLKST_FREE) ? 0x55 : 0; while (byte < end) { + /* If we're looking for a free block we can eliminate all + bitmap settings with 0x55, which represents four data + blocks in a row. If we're looking for a data block, we can + eliminate 0x00 which corresponds to four free blocks. */ if ((*byte & 0x55) == alloc) { blk += (8 - bit) >> 1; @@ -859,23 +863,28 @@ static int try_rgrp_fit(struct gfs2_rgrpd *rgd, struct gfs2_alloc *al) static struct inode *try_rgrp_unlink(struct gfs2_rgrpd *rgd, u64 *last_unlinked) { struct inode *inode; - u32 goal = 0; + u32 goal = 0, block; u64 no_addr; + struct gfs2_sbd *sdp = rgd->rd_sbd; for(;;) { if (goal >= rgd->rd_data) break; - goal = rgblk_search(rgd, goal, GFS2_BLKST_UNLINKED, - GFS2_BLKST_UNLINKED); - if (goal == BFITNOENT) + down_write(&sdp->sd_log_flush_lock); + block = rgblk_search(rgd, goal, GFS2_BLKST_UNLINKED, + GFS2_BLKST_UNLINKED); + up_write(&sdp->sd_log_flush_lock); + if (block == BFITNOENT) break; - no_addr = goal + rgd->rd_data0; + /* rgblk_search can return a block < goal, so we need to + keep it marching forward. */ + no_addr = block + rgd->rd_data0; goal++; - if (no_addr < *last_unlinked) + if (*last_unlinked != NO_BLOCK && no_addr <= *last_unlinked) continue; *last_unlinked = no_addr; inode = gfs2_inode_lookup(rgd->rd_sbd->sd_vfs, DT_UNKNOWN, - no_addr, -1); + no_addr, -1, 1); if (!IS_ERR(inode)) return inode; } @@ -1152,7 +1161,7 @@ int gfs2_inplace_reserve_i(struct gfs2_inode *ip, char *file, unsigned int line) struct gfs2_alloc *al = &ip->i_alloc; struct inode *inode; int error = 0; - u64 last_unlinked = 0; + u64 last_unlinked = NO_BLOCK; if (gfs2_assert_warn(sdp, al->al_requested)) return -EINVAL; @@ -1289,7 +1298,9 @@ static u32 rgblk_search(struct gfs2_rgrpd *rgd, u32 goal, allocatable block anywhere else, we want to be able wrap around and search in the first part of our first-searched bit block. */ for (x = 0; x <= length; x++) { - if (bi->bi_clone) + /* The GFS2_BLKST_UNLINKED state doesn't apply to the clone + bitmaps, so we must search the originals for that. */ + if (old_state != GFS2_BLKST_UNLINKED && bi->bi_clone) blk = gfs2_bitfit(rgd, bi->bi_clone + bi->bi_offset, bi->bi_len, goal, old_state); else @@ -1305,9 +1316,7 @@ static u32 rgblk_search(struct gfs2_rgrpd *rgd, u32 goal, goal = 0; } - if (old_state != new_state) { - gfs2_assert_withdraw(rgd->rd_sbd, blk != BFITNOENT); - + if (blk != BFITNOENT && old_state != new_state) { gfs2_trans_add_bh(rgd->rd_gl, bi->bi_bh, 1); gfs2_setbit(rgd, bi->bi_bh->b_data + bi->bi_offset, bi->bi_len, blk, new_state); diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c index a2da76b5ae4..dd3e737f528 100644 --- a/fs/gfs2/super.c +++ b/fs/gfs2/super.c @@ -58,7 +58,6 @@ void gfs2_tune_init(struct gfs2_tune *gt) gt->gt_incore_log_blocks = 1024; gt->gt_log_flush_secs = 60; gt->gt_jindex_refresh_secs = 60; - gt->gt_scand_secs = 15; gt->gt_recoverd_secs = 60; gt->gt_logd_secs = 1; gt->gt_quotad_secs = 5; diff --git a/fs/gfs2/sys.c b/fs/gfs2/sys.c index 640cb6a6fc4..06e0b7768d9 100644 --- a/fs/gfs2/sys.c +++ b/fs/gfs2/sys.c @@ -441,7 +441,6 @@ TUNE_ATTR(quota_simul_sync, 1); TUNE_ATTR(quota_cache_secs, 1); TUNE_ATTR(stall_secs, 1); TUNE_ATTR(statfs_quantum, 1); -TUNE_ATTR_DAEMON(scand_secs, scand_process); TUNE_ATTR_DAEMON(recoverd_secs, recoverd_process); TUNE_ATTR_DAEMON(logd_secs, logd_process); TUNE_ATTR_DAEMON(quotad_secs, quotad_process); @@ -463,7 +462,6 @@ static struct attribute *tune_attrs[] = { &tune_attr_quota_cache_secs.attr, &tune_attr_stall_secs.attr, &tune_attr_statfs_quantum.attr, - &tune_attr_scand_secs.attr, &tune_attr_recoverd_secs.attr, &tune_attr_logd_secs.attr, &tune_attr_quotad_secs.attr, diff --git a/fs/gfs2/trans.c b/fs/gfs2/trans.c index f8dabf8446b..717983e2c2a 100644 --- a/fs/gfs2/trans.c +++ b/fs/gfs2/trans.c @@ -142,25 +142,25 @@ void gfs2_trans_add_bh(struct gfs2_glock *gl, struct buffer_head *bh, int meta) lops_add(sdp, &bd->bd_le); } -void gfs2_trans_add_revoke(struct gfs2_sbd *sdp, u64 blkno) +void gfs2_trans_add_revoke(struct gfs2_sbd *sdp, struct gfs2_bufdata *bd) { - struct gfs2_revoke *rv = kmalloc(sizeof(struct gfs2_revoke), - GFP_NOFS | __GFP_NOFAIL); - lops_init_le(&rv->rv_le, &gfs2_revoke_lops); - rv->rv_blkno = blkno; - lops_add(sdp, &rv->rv_le); + BUG_ON(!list_empty(&bd->bd_le.le_list)); + BUG_ON(!list_empty(&bd->bd_ail_st_list)); + BUG_ON(!list_empty(&bd->bd_ail_gl_list)); + lops_init_le(&bd->bd_le, &gfs2_revoke_lops); + lops_add(sdp, &bd->bd_le); } void gfs2_trans_add_unrevoke(struct gfs2_sbd *sdp, u64 blkno) { - struct gfs2_revoke *rv; + struct gfs2_bufdata *bd; int found = 0; gfs2_log_lock(sdp); - list_for_each_entry(rv, &sdp->sd_log_le_revoke, rv_le.le_list) { - if (rv->rv_blkno == blkno) { - list_del(&rv->rv_le.le_list); + list_for_each_entry(bd, &sdp->sd_log_le_revoke, bd_le.le_list) { + if (bd->bd_blkno == blkno) { + list_del_init(&bd->bd_le.le_list); gfs2_assert_withdraw(sdp, sdp->sd_log_num_revoke); sdp->sd_log_num_revoke--; found = 1; @@ -172,7 +172,7 @@ void gfs2_trans_add_unrevoke(struct gfs2_sbd *sdp, u64 blkno) if (found) { struct gfs2_trans *tr = current->journal_info; - kfree(rv); + kmem_cache_free(gfs2_bufdata_cachep, bd); tr->tr_num_revoke_rm++; } } diff --git a/fs/gfs2/trans.h b/fs/gfs2/trans.h index 23d4cbe1de5..043d5f4b9c4 100644 --- a/fs/gfs2/trans.h +++ b/fs/gfs2/trans.h @@ -32,7 +32,7 @@ void gfs2_trans_end(struct gfs2_sbd *sdp); void gfs2_trans_add_gl(struct gfs2_glock *gl); void gfs2_trans_add_bh(struct gfs2_glock *gl, struct buffer_head *bh, int meta); -void gfs2_trans_add_revoke(struct gfs2_sbd *sdp, u64 blkno); +void gfs2_trans_add_revoke(struct gfs2_sbd *sdp, struct gfs2_bufdata *bd); void gfs2_trans_add_unrevoke(struct gfs2_sbd *sdp, u64 blkno); void gfs2_trans_add_rg(struct gfs2_rgrpd *rgd); diff --git a/fs/ntfs/ChangeLog b/fs/ntfs/ChangeLog index af4ef808fa9..345798ebd36 100644 --- a/fs/ntfs/ChangeLog +++ b/fs/ntfs/ChangeLog @@ -17,6 +17,18 @@ ToDo/Notes: happen is unclear however so it is worth waiting until someone hits the problem. +2.1.29 - Fix a deadlock at mount time. + + - During mount the VFS holds s_umount lock on the superblock. So when + we try to empty the journal $LogFile contents by calling + ntfs_attr_set() when the machine does not have much memory and the + journal is large ntfs_attr_set() results in the VM trying to balance + dirty pages which in turn tries to that the s_umount lock and thus we + get a deadlock. The solution is to not use ntfs_attr_set() and + instead do the zeroing by hand at the block level rather than page + cache level. + - Fix sparse warnings. + 2.1.28 - Fix a deadlock. - Fix deadlock in fs/ntfs/inode.c::ntfs_put_inode(). Thanks to Sergey diff --git a/fs/ntfs/Makefile b/fs/ntfs/Makefile index 82550838556..58b6be99254 100644 --- a/fs/ntfs/Makefile +++ b/fs/ntfs/Makefile @@ -6,7 +6,7 @@ ntfs-objs := aops.o attrib.o collate.o compress.o debug.o dir.o file.o \ index.o inode.o mft.o mst.o namei.o runlist.o super.o sysctl.o \ unistr.o upcase.o -EXTRA_CFLAGS = -DNTFS_VERSION=\"2.1.28\" +EXTRA_CFLAGS = -DNTFS_VERSION=\"2.1.29\" ifeq ($(CONFIG_NTFS_DEBUG),y) EXTRA_CFLAGS += -DDEBUG diff --git a/fs/ntfs/aops.c b/fs/ntfs/aops.c index 6e5c2534f4b..cfdc7900d27 100644 --- a/fs/ntfs/aops.c +++ b/fs/ntfs/aops.c @@ -2,7 +2,7 @@ * aops.c - NTFS kernel address space operations and page cache handling. * Part of the Linux-NTFS project. * - * Copyright (c) 2001-2006 Anton Altaparmakov + * Copyright (c) 2001-2007 Anton Altaparmakov * Copyright (c) 2002 Richard Russon * * This program/include file is free software; you can redistribute it and/or @@ -396,7 +396,7 @@ static int ntfs_readpage(struct file *file, struct page *page) loff_t i_size; struct inode *vi; ntfs_inode *ni, *base_ni; - u8 *kaddr; + u8 *addr; ntfs_attr_search_ctx *ctx; MFT_RECORD *mrec; unsigned long flags; @@ -491,15 +491,15 @@ retry_readpage: /* Race with shrinking truncate. */ attr_len = i_size; } - kaddr = kmap_atomic(page, KM_USER0); + addr = kmap_atomic(page, KM_USER0); /* Copy the data to the page. */ - memcpy(kaddr, (u8*)ctx->attr + + memcpy(addr, (u8*)ctx->attr + le16_to_cpu(ctx->attr->data.resident.value_offset), attr_len); /* Zero the remainder of the page. */ - memset(kaddr + attr_len, 0, PAGE_CACHE_SIZE - attr_len); + memset(addr + attr_len, 0, PAGE_CACHE_SIZE - attr_len); flush_dcache_page(page); - kunmap_atomic(kaddr, KM_USER0); + kunmap_atomic(addr, KM_USER0); put_unm_err_out: ntfs_attr_put_search_ctx(ctx); unm_err_out: @@ -1344,7 +1344,7 @@ static int ntfs_writepage(struct page *page, struct writeback_control *wbc) loff_t i_size; struct inode *vi = page->mapping->host; ntfs_inode *base_ni = NULL, *ni = NTFS_I(vi); - char *kaddr; + char *addr; ntfs_attr_search_ctx *ctx = NULL; MFT_RECORD *m = NULL; u32 attr_len; @@ -1484,14 +1484,14 @@ retry_writepage: /* Shrinking cannot fail. */ BUG_ON(err); } - kaddr = kmap_atomic(page, KM_USER0); + addr = kmap_atomic(page, KM_USER0); /* Copy the data from the page to the mft record. */ memcpy((u8*)ctx->attr + le16_to_cpu(ctx->attr->data.resident.value_offset), - kaddr, attr_len); + addr, attr_len); /* Zero out of bounds area in the page cache page. */ - memset(kaddr + attr_len, 0, PAGE_CACHE_SIZE - attr_len); - kunmap_atomic(kaddr, KM_USER0); + memset(addr + attr_len, 0, PAGE_CACHE_SIZE - attr_len); + kunmap_atomic(addr, KM_USER0); flush_dcache_page(page); flush_dcache_mft_record_page(ctx->ntfs_ino); /* We are done with the page. */ diff --git a/fs/ntfs/attrib.c b/fs/ntfs/attrib.c index 1c08fefe487..92dabdcf2b8 100644 --- a/fs/ntfs/attrib.c +++ b/fs/ntfs/attrib.c @@ -1,7 +1,7 @@ /** * attrib.c - NTFS attribute operations. Part of the Linux-NTFS project. * - * Copyright (c) 2001-2006 Anton Altaparmakov + * Copyright (c) 2001-2007 Anton Altaparmakov * Copyright (c) 2002 Richard Russon * * This program/include file is free software; you can redistribute it and/or @@ -2500,7 +2500,7 @@ int ntfs_attr_set(ntfs_inode *ni, const s64 ofs, const s64 cnt, const u8 val) struct page *page; u8 *kaddr; pgoff_t idx, end; - unsigned int start_ofs, end_ofs, size; + unsigned start_ofs, end_ofs, size; ntfs_debug("Entering for ofs 0x%llx, cnt 0x%llx, val 0x%hx.", (long long)ofs, (long long)cnt, val); @@ -2548,6 +2548,8 @@ int ntfs_attr_set(ntfs_inode *ni, const s64 ofs, const s64 cnt, const u8 val) kunmap_atomic(kaddr, KM_USER0); set_page_dirty(page); page_cache_release(page); + balance_dirty_pages_ratelimited(mapping); + cond_resched(); if (idx == end) goto done; idx++; @@ -2604,6 +2606,8 @@ int ntfs_attr_set(ntfs_inode *ni, const s64 ofs, const s64 cnt, const u8 val) kunmap_atomic(kaddr, KM_USER0); set_page_dirty(page); page_cache_release(page); + balance_dirty_pages_ratelimited(mapping); + cond_resched(); } done: ntfs_debug("Done."); diff --git a/fs/ntfs/file.c b/fs/ntfs/file.c index ffcc504a166..c814204d4ea 100644 --- a/fs/ntfs/file.c +++ b/fs/ntfs/file.c @@ -1,7 +1,7 @@ /* * file.c - NTFS kernel file operations. Part of the Linux-NTFS project. * - * Copyright (c) 2001-2006 Anton Altaparmakov + * Copyright (c) 2001-2007 Anton Altaparmakov * * This program/include file is free software; you can redistribute it and/or * modify it under the terms of the GNU General Public License as published @@ -26,7 +26,6 @@ #include <linux/swap.h> #include <linux/uio.h> #include <linux/writeback.h> -#include <linux/sched.h> #include <asm/page.h> #include <asm/uaccess.h> @@ -362,7 +361,7 @@ static inline void ntfs_fault_in_pages_readable(const char __user *uaddr, volatile char c; /* Set @end to the first byte outside the last page we care about. */ - end = (const char __user*)PAGE_ALIGN((ptrdiff_t __user)uaddr + bytes); + end = (const char __user*)PAGE_ALIGN((unsigned long)uaddr + bytes); while (!__get_user(c, uaddr) && (uaddr += PAGE_SIZE, uaddr < end)) ; @@ -532,7 +531,8 @@ static int ntfs_prepare_pages_for_non_resident_write(struct page **pages, blocksize_bits = vol->sb->s_blocksize_bits; u = 0; do { - struct page *page = pages[u]; + page = pages[u]; + BUG_ON(!page); /* * create_empty_buffers() will create uptodate/dirty buffers if * the page is uptodate/dirty. @@ -1291,7 +1291,7 @@ static inline size_t ntfs_copy_from_user(struct page **pages, size_t bytes) { struct page **last_page = pages + nr_pages; - char *kaddr; + char *addr; size_t total = 0; unsigned len; int left; @@ -1300,13 +1300,13 @@ static inline size_t ntfs_copy_from_user(struct page **pages, len = PAGE_CACHE_SIZE - ofs; if (len > bytes) len = bytes; - kaddr = kmap_atomic(*pages, KM_USER0); - left = __copy_from_user_inatomic(kaddr + ofs, buf, len); - kunmap_atomic(kaddr, KM_USER0); + addr = kmap_atomic(*pages, KM_USER0); + left = __copy_from_user_inatomic(addr + ofs, buf, len); + kunmap_atomic(addr, KM_USER0); if (unlikely(left)) { /* Do it the slow way. */ - kaddr = kmap(*pages); - left = __copy_from_user(kaddr + ofs, buf, len); + addr = kmap(*pages); + left = __copy_from_user(addr + ofs, buf, len); kunmap(*pages); if (unlikely(left)) goto err_out; @@ -1408,26 +1408,26 @@ static inline size_t ntfs_copy_from_user_iovec(struct page **pages, size_t *iov_ofs, size_t bytes) { struct page **last_page = pages + nr_pages; - char *kaddr; + char *addr; size_t copied, len, total = 0; do { len = PAGE_CACHE_SIZE - ofs; if (len > bytes) len = bytes; - kaddr = kmap_atomic(*pages, KM_USER0); - copied = __ntfs_copy_from_user_iovec_inatomic(kaddr + ofs, + addr = kmap_atomic(*pages, KM_USER0); + copied = __ntfs_copy_from_user_iovec_inatomic(addr + ofs, *iov, *iov_ofs, len); - kunmap_atomic(kaddr, KM_USER0); + kunmap_atomic(addr, KM_USER0); if (unlikely(copied != len)) { /* Do it the slow way. */ - kaddr = kmap(*pages); - copied = __ntfs_copy_from_user_iovec_inatomic(kaddr + ofs, + addr = kmap(*pages); + copied = __ntfs_copy_from_user_iovec_inatomic(addr + ofs, *iov, *iov_ofs, len); /* * Zero the rest of the target like __copy_from_user(). */ - memset(kaddr + ofs + copied, 0, len - copied); + memset(addr + ofs + copied, 0, len - copied); kunmap(*pages); if (unlikely(copied != len)) goto err_out; @@ -1735,8 +1735,6 @@ static int ntfs_commit_pages_after_write(struct page **pages, read_unlock_irqrestore(&ni->size_lock, flags); BUG_ON(initialized_size != i_size); if (end > initialized_size) { - unsigned long flags; - write_lock_irqsave(&ni->size_lock, flags); ni->initialized_size = end; i_size_write(vi, end); diff --git a/fs/ntfs/inode.c b/fs/ntfs/inode.c index b532a730cec..e9da092e277 100644 --- a/fs/ntfs/inode.c +++ b/fs/ntfs/inode.c @@ -34,7 +34,6 @@ #include "dir.h" #include "debug.h" #include "inode.h" -#include "attrib.h" #include "lcnalloc.h" #include "malloc.h" #include "mft.h" @@ -2500,8 +2499,6 @@ retry_truncate: /* Resize the attribute record to best fit the new attribute size. */ if (new_size < vol->mft_record_size && !ntfs_resident_attr_value_resize(m, a, new_size)) { - unsigned long flags; - /* The resize succeeded! */ flush_dcache_mft_record_page(ctx->ntfs_ino); mark_mft_record_dirty(ctx->ntfs_ino); diff --git a/fs/ntfs/logfile.c b/fs/ntfs/logfile.c index acfed325f4e..d7932e95b1f 100644 --- a/fs/ntfs/logfile.c +++ b/fs/ntfs/logfile.c @@ -1,7 +1,7 @@ /* * logfile.c - NTFS kernel journal handling. Part of the Linux-NTFS project. * - * Copyright (c) 2002-2005 Anton Altaparmakov + * Copyright (c) 2002-2007 Anton Altaparmakov * * This program/include file is free software; you can redistribute it and/or * modify it under the terms of the GNU General Public License as published @@ -724,24 +724,139 @@ bool ntfs_is_logfile_clean(struct inode *log_vi, const RESTART_PAGE_HEADER *rp) */ bool ntfs_empty_logfile(struct inode *log_vi) { - ntfs_volume *vol = NTFS_SB(log_vi->i_sb); + VCN vcn, end_vcn; + ntfs_inode *log_ni = NTFS_I(log_vi); + ntfs_volume *vol = log_ni->vol; + struct super_block *sb = vol->sb; + runlist_element *rl; + unsigned long flags; + unsigned block_size, block_size_bits; + int err; + bool should_wait = true; ntfs_debug("Entering."); - if (!NVolLogFileEmpty(vol)) { - int err; - - err = ntfs_attr_set(NTFS_I(log_vi), 0, i_size_read(log_vi), - 0xff); - if (unlikely(err)) { - ntfs_error(vol->sb, "Failed to fill $LogFile with " - "0xff bytes (error code %i).", err); - return false; - } - /* Set the flag so we do not have to do it again on remount. */ - NVolSetLogFileEmpty(vol); + if (NVolLogFileEmpty(vol)) { + ntfs_debug("Done."); + return true; } + /* + * We cannot use ntfs_attr_set() because we may be still in the middle + * of a mount operation. Thus we do the emptying by hand by first + * zapping the page cache pages for the $LogFile/$DATA attribute and + * then emptying each of the buffers in each of the clusters specified + * by the runlist by hand. + */ + block_size = sb->s_blocksize; + block_size_bits = sb->s_blocksize_bits; + vcn = 0; + read_lock_irqsave(&log_ni->size_lock, flags); + end_vcn = (log_ni->initialized_size + vol->cluster_size_mask) >> + vol->cluster_size_bits; + read_unlock_irqrestore(&log_ni->size_lock, flags); + truncate_inode_pages(log_vi->i_mapping, 0); + down_write(&log_ni->runlist.lock); + rl = log_ni->runlist.rl; + if (unlikely(!rl || vcn < rl->vcn || !rl->length)) { +map_vcn: + err = ntfs_map_runlist_nolock(log_ni, vcn, NULL); + if (err) { + ntfs_error(sb, "Failed to map runlist fragment (error " + "%d).", -err); + goto err; + } + rl = log_ni->runlist.rl; + BUG_ON(!rl || vcn < rl->vcn || !rl->length); + } + /* Seek to the runlist element containing @vcn. */ + while (rl->length && vcn >= rl[1].vcn) + rl++; + do { + LCN lcn; + sector_t block, end_block; + s64 len; + + /* + * If this run is not mapped map it now and start again as the + * runlist will have been updated. + */ + lcn = rl->lcn; + if (unlikely(lcn == LCN_RL_NOT_MAPPED)) { + vcn = rl->vcn; + goto map_vcn; + } + /* If this run is not valid abort with an error. */ + if (unlikely(!rl->length || lcn < LCN_HOLE)) + goto rl_err; + /* Skip holes. */ + if (lcn == LCN_HOLE) + continue; + block = lcn << vol->cluster_size_bits >> block_size_bits; + len = rl->length; + if (rl[1].vcn > end_vcn) + len = end_vcn - rl->vcn; + end_block = (lcn + len) << vol->cluster_size_bits >> + block_size_bits; + /* Iterate over the blocks in the run and empty them. */ + do { + struct buffer_head *bh; + + /* Obtain the buffer, possibly not uptodate. */ + bh = sb_getblk(sb, block); + BUG_ON(!bh); + /* Setup buffer i/o submission. */ + lock_buffer(bh); + bh->b_end_io = end_buffer_write_sync; + get_bh(bh); + /* Set the entire contents of the buffer to 0xff. */ + memset(bh->b_data, -1, block_size); + if (!buffer_uptodate(bh)) + set_buffer_uptodate(bh); + if (buffer_dirty(bh)) + clear_buffer_dirty(bh); + /* + * Submit the buffer and wait for i/o to complete but + * only for the first buffer so we do not miss really + * serious i/o errors. Once the first buffer has + * completed ignore errors afterwards as we can assume + * that if one buffer worked all of them will work. + */ + submit_bh(WRITE, bh); + if (should_wait) { + should_wait = false; + wait_on_buffer(bh); + if (unlikely(!buffer_uptodate(bh))) + goto io_err; + } + brelse(bh); + } while (++block < end_block); + } while ((++rl)->vcn < end_vcn); + up_write(&log_ni->runlist.lock); + /* + * Zap the pages again just in case any got instantiated whilst we were + * emptying the blocks by hand. FIXME: We may not have completed + * writing to all the buffer heads yet so this may happen too early. + * We really should use a kernel thread to do the emptying + * asynchronously and then we can also set the volume dirty and output + * an error message if emptying should fail. + */ + truncate_inode_pages(log_vi->i_mapping, 0); + /* Set the flag so we do not have to do it again on remount. */ + NVolSetLogFileEmpty(vol); ntfs_debug("Done."); return true; +io_err: + ntfs_error(sb, "Failed to write buffer. Unmount and run chkdsk."); + goto dirty_err; +rl_err: + ntfs_error(sb, "Runlist is corrupt. Unmount and run chkdsk."); +dirty_err: + NVolSetErrors(vol); + err = -EIO; +err: + up_write(&log_ni->runlist.lock); + ntfs_error(sb, "Failed to fill $LogFile with 0xff bytes (error %d).", + -err); + return false; } #endif /* NTFS_RW */ diff --git a/fs/ntfs/runlist.c b/fs/ntfs/runlist.c index 9afd72c7ad0..56a9a6d25a2 100644 --- a/fs/ntfs/runlist.c +++ b/fs/ntfs/runlist.c @@ -1,7 +1,7 @@ /** * runlist.c - NTFS runlist handling code. Part of the Linux-NTFS project. * - * Copyright (c) 2001-2005 Anton Altaparmakov + * Copyright (c) 2001-2007 Anton Altaparmakov * Copyright (c) 2002-2005 Richard Russon * * This program/include file is free software; you can redistribute it and/or @@ -1714,7 +1714,7 @@ extend_hole: sizeof(*rl)); /* Adjust the beginning of the tail if necessary. */ if (end > rl->vcn) { - s64 delta = end - rl->vcn; + delta = end - rl->vcn; rl->vcn = end; rl->length -= delta; /* Only adjust the lcn if it is real. */ diff --git a/fs/ocfs2/alloc.c b/fs/ocfs2/alloc.c index 778a850b463..4ba7f0bdc24 100644 --- a/fs/ocfs2/alloc.c +++ b/fs/ocfs2/alloc.c @@ -354,7 +354,6 @@ struct ocfs2_insert_type { enum ocfs2_append_type ins_appending; enum ocfs2_contig_type ins_contig; int ins_contig_index; - int ins_free_records; int ins_tree_depth; }; @@ -362,7 +361,6 @@ struct ocfs2_merge_ctxt { enum ocfs2_contig_type c_contig_type; int c_has_empty_extent; int c_split_covers_rec; - int c_used_tail_recs; }; /* @@ -2808,36 +2806,28 @@ static int ocfs2_try_to_merge_extent(struct inode *inode, struct ocfs2_merge_ctxt *ctxt) { - int ret = 0, delete_tail_recs = 0; + int ret = 0; struct ocfs2_extent_list *el = path_leaf_el(left_path); struct ocfs2_extent_rec *rec = &el->l_recs[split_index]; BUG_ON(ctxt->c_contig_type == CONTIG_NONE); - if (ctxt->c_split_covers_rec) { - delete_tail_recs++; - - if (ctxt->c_contig_type == CONTIG_LEFTRIGHT || - ctxt->c_has_empty_extent) - delete_tail_recs++; - - if (ctxt->c_has_empty_extent) { - /* - * The merge code will need to create an empty - * extent to take the place of the newly - * emptied slot. Remove any pre-existing empty - * extents - having more than one in a leaf is - * illegal. - */ - ret = ocfs2_rotate_tree_left(inode, handle, left_path, - dealloc); - if (ret) { - mlog_errno(ret); - goto out; - } - split_index--; - rec = &el->l_recs[split_index]; + if (ctxt->c_split_covers_rec && ctxt->c_has_empty_extent) { + /* + * The merge code will need to create an empty + * extent to take the place of the newly + * emptied slot. Remove any pre-existing empty + * extents - having more than one in a leaf is + * illegal. + */ + ret = ocfs2_rotate_tree_left(inode, handle, left_path, + dealloc); + if (ret) { + mlog_errno(ret); + goto out; } + split_index--; + rec = &el->l_recs[split_index]; } if (ctxt->c_contig_type == CONTIG_LEFTRIGHT) { @@ -3593,6 +3583,7 @@ static int ocfs2_figure_insert_type(struct inode *inode, struct buffer_head *di_bh, struct buffer_head **last_eb_bh, struct ocfs2_extent_rec *insert_rec, + int *free_records, struct ocfs2_insert_type *insert) { int ret; @@ -3633,7 +3624,7 @@ static int ocfs2_figure_insert_type(struct inode *inode, * XXX: This test is simplistic, we can search for empty * extent records too. */ - insert->ins_free_records = le16_to_cpu(el->l_count) - + *free_records = le16_to_cpu(el->l_count) - le16_to_cpu(el->l_next_free_rec); if (!insert->ins_tree_depth) { @@ -3730,10 +3721,13 @@ int ocfs2_insert_extent(struct ocfs2_super *osb, struct ocfs2_alloc_context *meta_ac) { int status; + int uninitialized_var(free_records); struct buffer_head *last_eb_bh = NULL; struct ocfs2_insert_type insert = {0, }; struct ocfs2_extent_rec rec; + BUG_ON(OCFS2_I(inode)->ip_dyn_features & OCFS2_INLINE_DATA_FL); + mlog(0, "add %u clusters at position %u to inode %llu\n", new_clusters, cpos, (unsigned long long)OCFS2_I(inode)->ip_blkno); @@ -3752,7 +3746,7 @@ int ocfs2_insert_extent(struct ocfs2_super *osb, rec.e_flags = flags; status = ocfs2_figure_insert_type(inode, fe_bh, &last_eb_bh, &rec, - &insert); + &free_records, &insert); if (status < 0) { mlog_errno(status); goto bail; @@ -3762,9 +3756,9 @@ int ocfs2_insert_extent(struct ocfs2_super *osb, "Insert.contig_index: %d, Insert.free_records: %d, " "Insert.tree_depth: %d\n", insert.ins_appending, insert.ins_contig, insert.ins_contig_index, - insert.ins_free_records, insert.ins_tree_depth); + free_records, insert.ins_tree_depth); - if (insert.ins_contig == CONTIG_NONE && insert.ins_free_records == 0) { + if (insert.ins_contig == CONTIG_NONE && free_records == 0) { status = ocfs2_grow_tree(inode, handle, fe_bh, &insert.ins_tree_depth, &last_eb_bh, meta_ac); @@ -3847,26 +3841,17 @@ leftright: if (le16_to_cpu(rightmost_el->l_next_free_rec) == le16_to_cpu(rightmost_el->l_count)) { - int old_depth = depth; - ret = ocfs2_grow_tree(inode, handle, di_bh, &depth, last_eb_bh, meta_ac); if (ret) { mlog_errno(ret); goto out; } - - if (old_depth != depth) { - eb = (struct ocfs2_extent_block *)(*last_eb_bh)->b_data; - rightmost_el = &eb->h_list; - } } memset(&insert, 0, sizeof(struct ocfs2_insert_type)); insert.ins_appending = APPEND_NONE; insert.ins_contig = CONTIG_NONE; - insert.ins_free_records = le16_to_cpu(rightmost_el->l_count) - - le16_to_cpu(rightmost_el->l_next_free_rec); insert.ins_tree_depth = depth; insert_range = le32_to_cpu(split_rec.e_cpos) + @@ -4015,11 +4000,6 @@ static int __ocfs2_mark_extent_written(struct inode *inode, } else rightmost_el = path_root_el(path); - ctxt.c_used_tail_recs = le16_to_cpu(rightmost_el->l_next_free_rec); - if (ctxt.c_used_tail_recs > 0 && - ocfs2_is_empty_extent(&rightmost_el->l_recs[0])) - ctxt.c_used_tail_recs--; - if (rec->e_cpos == split_rec->e_cpos && rec->e_leaf_clusters == split_rec->e_leaf_clusters) ctxt.c_split_covers_rec = 1; @@ -4028,10 +4008,9 @@ static int __ocfs2_mark_extent_written(struct inode *inode, ctxt.c_has_empty_extent = ocfs2_is_empty_extent(&el->l_recs[0]); - mlog(0, "index: %d, contig: %u, used_tail_recs: %u, " - "has_empty: %u, split_covers: %u\n", split_index, - ctxt.c_contig_type, ctxt.c_used_tail_recs, - ctxt.c_has_empty_extent, ctxt.c_split_covers_rec); + mlog(0, "index: %d, contig: %u, has_empty: %u, split_covers: %u\n", + split_index, ctxt.c_contig_type, ctxt.c_has_empty_extent, + ctxt.c_split_covers_rec); if (ctxt.c_contig_type == CONTIG_NONE) { if (ctxt.c_split_covers_rec) @@ -4180,27 +4159,18 @@ static int ocfs2_split_tree(struct inode *inode, struct buffer_head *di_bh, if (le16_to_cpu(rightmost_el->l_next_free_rec) == le16_to_cpu(rightmost_el->l_count)) { - int old_depth = depth; - ret = ocfs2_grow_tree(inode, handle, di_bh, &depth, &last_eb_bh, meta_ac); if (ret) { mlog_errno(ret); goto out; } - - if (old_depth != depth) { - eb = (struct ocfs2_extent_block *)last_eb_bh->b_data; - rightmost_el = &eb->h_list; - } } memset(&insert, 0, sizeof(struct ocfs2_insert_type)); insert.ins_appending = APPEND_NONE; insert.ins_contig = CONTIG_NONE; insert.ins_split = SPLIT_RIGHT; - insert.ins_free_records = le16_to_cpu(rightmost_el->l_count) - - le16_to_cpu(rightmost_el->l_next_free_rec); insert.ins_tree_depth = depth; ret = ocfs2_do_insert_extent(inode, handle, di_bh, &split_rec, &insert); @@ -5665,12 +5635,50 @@ static int ocfs2_ordered_zero_func(handle_t *handle, struct buffer_head *bh) return ocfs2_journal_dirty_data(handle, bh); } +static void ocfs2_map_and_dirty_page(struct inode *inode, handle_t *handle, + unsigned int from, unsigned int to, + struct page *page, int zero, u64 *phys) +{ + int ret, partial = 0; + + ret = ocfs2_map_page_blocks(page, phys, inode, from, to, 0); + if (ret) + mlog_errno(ret); + + if (zero) + zero_user_page(page, from, to - from, KM_USER0); + + /* + * Need to set the buffers we zero'd into uptodate + * here if they aren't - ocfs2_map_page_blocks() + * might've skipped some + */ + if (ocfs2_should_order_data(inode)) { + ret = walk_page_buffers(handle, + page_buffers(page), + from, to, &partial, + ocfs2_ordered_zero_func); + if (ret < 0) + mlog_errno(ret); + } else { + ret = walk_page_buffers(handle, page_buffers(page), + from, to, &partial, + ocfs2_writeback_zero_func); + if (ret < 0) + mlog_errno(ret); + } + + if (!partial) + SetPageUptodate(page); + + flush_dcache_page(page); +} + static void ocfs2_zero_cluster_pages(struct inode *inode, loff_t start, loff_t end, struct page **pages, int numpages, u64 phys, handle_t *handle) { - int i, ret, partial = 0; - void *kaddr; + int i; struct page *page; unsigned int from, to = PAGE_CACHE_SIZE; struct super_block *sb = inode->i_sb; @@ -5691,87 +5699,31 @@ static void ocfs2_zero_cluster_pages(struct inode *inode, loff_t start, BUG_ON(from > PAGE_CACHE_SIZE); BUG_ON(to > PAGE_CACHE_SIZE); - ret = ocfs2_map_page_blocks(page, &phys, inode, from, to, 0); - if (ret) - mlog_errno(ret); - - kaddr = kmap_atomic(page, KM_USER0); - memset(kaddr + from, 0, to - from); - kunmap_atomic(kaddr, KM_USER0); - - /* - * Need to set the buffers we zero'd into uptodate - * here if they aren't - ocfs2_map_page_blocks() - * might've skipped some - */ - if (ocfs2_should_order_data(inode)) { - ret = walk_page_buffers(handle, - page_buffers(page), - from, to, &partial, - ocfs2_ordered_zero_func); - if (ret < 0) - mlog_errno(ret); - } else { - ret = walk_page_buffers(handle, page_buffers(page), - from, to, &partial, - ocfs2_writeback_zero_func); - if (ret < 0) - mlog_errno(ret); - } - - if (!partial) - SetPageUptodate(page); - - flush_dcache_page(page); + ocfs2_map_and_dirty_page(inode, handle, from, to, page, 1, + &phys); start = (page->index + 1) << PAGE_CACHE_SHIFT; } out: - if (pages) { - for (i = 0; i < numpages; i++) { - page = pages[i]; - unlock_page(page); - mark_page_accessed(page); - page_cache_release(page); - } - } + if (pages) + ocfs2_unlock_and_free_pages(pages, numpages); } static int ocfs2_grab_eof_pages(struct inode *inode, loff_t start, loff_t end, - struct page **pages, int *num, u64 *phys) + struct page **pages, int *num) { - int i, numpages = 0, ret = 0; - unsigned int ext_flags; + int numpages, ret = 0; struct super_block *sb = inode->i_sb; struct address_space *mapping = inode->i_mapping; unsigned long index; loff_t last_page_bytes; - BUG_ON(!ocfs2_sparse_alloc(OCFS2_SB(sb))); BUG_ON(start > end); - if (start == end) - goto out; - BUG_ON(start >> OCFS2_SB(sb)->s_clustersize_bits != (end - 1) >> OCFS2_SB(sb)->s_clustersize_bits); - ret = ocfs2_extent_map_get_blocks(inode, start >> sb->s_blocksize_bits, - phys, NULL, &ext_flags); - if (ret) { - mlog_errno(ret); - goto out; - } - - /* Tail is a hole. */ - if (*phys == 0) - goto out; - - /* Tail is marked as unwritten, we can count on write to zero - * in that case. */ - if (ext_flags & OCFS2_EXT_UNWRITTEN) - goto out; - + numpages = 0; last_page_bytes = PAGE_ALIGN(end); index = start >> PAGE_CACHE_SHIFT; do { @@ -5788,14 +5740,8 @@ static int ocfs2_grab_eof_pages(struct inode *inode, loff_t start, loff_t end, out: if (ret != 0) { - if (pages) { - for (i = 0; i < numpages; i++) { - if (pages[i]) { - unlock_page(pages[i]); - page_cache_release(pages[i]); - } - } - } + if (pages) + ocfs2_unlock_and_free_pages(pages, numpages); numpages = 0; } @@ -5816,18 +5762,20 @@ out: int ocfs2_zero_range_for_truncate(struct inode *inode, handle_t *handle, u64 range_start, u64 range_end) { - int ret, numpages; + int ret = 0, numpages; struct page **pages = NULL; u64 phys; + unsigned int ext_flags; + struct super_block *sb = inode->i_sb; /* * File systems which don't support sparse files zero on every * extend. */ - if (!ocfs2_sparse_alloc(OCFS2_SB(inode->i_sb))) + if (!ocfs2_sparse_alloc(OCFS2_SB(sb))) return 0; - pages = kcalloc(ocfs2_pages_per_cluster(inode->i_sb), + pages = kcalloc(ocfs2_pages_per_cluster(sb), sizeof(struct page *), GFP_NOFS); if (pages == NULL) { ret = -ENOMEM; @@ -5835,16 +5783,31 @@ int ocfs2_zero_range_for_truncate(struct inode *inode, handle_t *handle, goto out; } - ret = ocfs2_grab_eof_pages(inode, range_start, range_end, pages, - &numpages, &phys); + if (range_start == range_end) + goto out; + + ret = ocfs2_extent_map_get_blocks(inode, + range_start >> sb->s_blocksize_bits, + &phys, NULL, &ext_flags); if (ret) { mlog_errno(ret); goto out; } - if (numpages == 0) + /* + * Tail is a hole, or is marked unwritten. In either case, we + * can count on read and write to return/push zero's. + */ + if (phys == 0 || ext_flags & OCFS2_EXT_UNWRITTEN) goto out; + ret = ocfs2_grab_eof_pages(inode, range_start, range_end, pages, + &numpages); + if (ret) { + mlog_errno(ret); + goto out; + } + ocfs2_zero_cluster_pages(inode, range_start, range_end, pages, numpages, phys, handle); @@ -5865,6 +5828,178 @@ out: return ret; } +static void ocfs2_zero_dinode_id2(struct inode *inode, struct ocfs2_dinode *di) +{ + unsigned int blocksize = 1 << inode->i_sb->s_blocksize_bits; + + memset(&di->id2, 0, blocksize - offsetof(struct ocfs2_dinode, id2)); +} + +void ocfs2_dinode_new_extent_list(struct inode *inode, + struct ocfs2_dinode *di) +{ + ocfs2_zero_dinode_id2(inode, di); + di->id2.i_list.l_tree_depth = 0; + di->id2.i_list.l_next_free_rec = 0; + di->id2.i_list.l_count = cpu_to_le16(ocfs2_extent_recs_per_inode(inode->i_sb)); +} + +void ocfs2_set_inode_data_inline(struct inode *inode, struct ocfs2_dinode *di) +{ + struct ocfs2_inode_info *oi = OCFS2_I(inode); + struct ocfs2_inline_data *idata = &di->id2.i_data; + + spin_lock(&oi->ip_lock); + oi->ip_dyn_features |= OCFS2_INLINE_DATA_FL; + di->i_dyn_features = cpu_to_le16(oi->ip_dyn_features); + spin_unlock(&oi->ip_lock); + + /* + * We clear the entire i_data structure here so that all + * fields can be properly initialized. + */ + ocfs2_zero_dinode_id2(inode, di); + + idata->id_count = cpu_to_le16(ocfs2_max_inline_data(inode->i_sb)); +} + +int ocfs2_convert_inline_data_to_extents(struct inode *inode, + struct buffer_head *di_bh) +{ + int ret, i, has_data, num_pages = 0; + handle_t *handle; + u64 uninitialized_var(block); + struct ocfs2_inode_info *oi = OCFS2_I(inode); + struct ocfs2_super *osb = OCFS2_SB(inode->i_sb); + struct ocfs2_dinode *di = (struct ocfs2_dinode *)di_bh->b_data; + struct ocfs2_alloc_context *data_ac = NULL; + struct page **pages = NULL; + loff_t end = osb->s_clustersize; + + has_data = i_size_read(inode) ? 1 : 0; + + if (has_data) { + pages = kcalloc(ocfs2_pages_per_cluster(osb->sb), + sizeof(struct page *), GFP_NOFS); + if (pages == NULL) { + ret = -ENOMEM; + mlog_errno(ret); + goto out; + } + + ret = ocfs2_reserve_clusters(osb, 1, &data_ac); + if (ret) { + mlog_errno(ret); + goto out; + } + } + + handle = ocfs2_start_trans(osb, OCFS2_INLINE_TO_EXTENTS_CREDITS); + if (IS_ERR(handle)) { + ret = PTR_ERR(handle); + mlog_errno(ret); + goto out_unlock; + } + + ret = ocfs2_journal_access(handle, inode, di_bh, + OCFS2_JOURNAL_ACCESS_WRITE); + if (ret) { + mlog_errno(ret); + goto out_commit; + } + + if (has_data) { + u32 bit_off, num; + unsigned int page_end; + u64 phys; + + ret = ocfs2_claim_clusters(osb, handle, data_ac, 1, &bit_off, + &num); + if (ret) { + mlog_errno(ret); + goto out_commit; + } + + /* + * Save two copies, one for insert, and one that can + * be changed by ocfs2_map_and_dirty_page() below. + */ + block = phys = ocfs2_clusters_to_blocks(inode->i_sb, bit_off); + + /* + * Non sparse file systems zero on extend, so no need + * to do that now. + */ + if (!ocfs2_sparse_alloc(osb) && + PAGE_CACHE_SIZE < osb->s_clustersize) + end = PAGE_CACHE_SIZE; + + ret = ocfs2_grab_eof_pages(inode, 0, end, pages, &num_pages); + if (ret) { + mlog_errno(ret); + goto out_commit; + } + + /* + * This should populate the 1st page for us and mark + * it up to date. + */ + ret = ocfs2_read_inline_data(inode, pages[0], di_bh); + if (ret) { + mlog_errno(ret); + goto out_commit; + } + + page_end = PAGE_CACHE_SIZE; + if (PAGE_CACHE_SIZE > osb->s_clustersize) + page_end = osb->s_clustersize; + + for (i = 0; i < num_pages; i++) + ocfs2_map_and_dirty_page(inode, handle, 0, page_end, + pages[i], i > 0, &phys); + } + + spin_lock(&oi->ip_lock); + oi->ip_dyn_features &= ~OCFS2_INLINE_DATA_FL; + di->i_dyn_features = cpu_to_le16(oi->ip_dyn_features); + spin_unlock(&oi->ip_lock); + + ocfs2_dinode_new_extent_list(inode, di); + + ocfs2_journal_dirty(handle, di_bh); + + if (has_data) { + /* + * An error at this point should be extremely rare. If + * this proves to be false, we could always re-build + * the in-inode data from our pages. + */ + ret = ocfs2_insert_extent(osb, handle, inode, di_bh, + 0, block, 1, 0, NULL); + if (ret) { + mlog_errno(ret); + goto out_commit; + } + + inode->i_blocks = ocfs2_inode_sector_count(inode); + } + +out_commit: + ocfs2_commit_trans(osb, handle); + +out_unlock: + if (data_ac) + ocfs2_free_alloc_context(data_ac); + +out: + if (pages) { + ocfs2_unlock_and_free_pages(pages, num_pages); + kfree(pages); + } + + return ret; +} + /* * It is expected, that by the time you call this function, * inode->i_size and fe->i_size have been adjusted. @@ -6090,6 +6225,81 @@ bail: return status; } +/* + * 'start' is inclusive, 'end' is not. + */ +int ocfs2_truncate_inline(struct inode *inode, struct buffer_head *di_bh, + unsigned int start, unsigned int end, int trunc) +{ + int ret; + unsigned int numbytes; + handle_t *handle; + struct ocfs2_super *osb = OCFS2_SB(inode->i_sb); + struct ocfs2_dinode *di = (struct ocfs2_dinode *)di_bh->b_data; + struct ocfs2_inline_data *idata = &di->id2.i_data; + + if (end > i_size_read(inode)) + end = i_size_read(inode); + + BUG_ON(start >= end); + + if (!(OCFS2_I(inode)->ip_dyn_features & OCFS2_INLINE_DATA_FL) || + !(le16_to_cpu(di->i_dyn_features) & OCFS2_INLINE_DATA_FL) || + !ocfs2_supports_inline_data(osb)) { + ocfs2_error(inode->i_sb, + "Inline data flags for inode %llu don't agree! " + "Disk: 0x%x, Memory: 0x%x, Superblock: 0x%x\n", + (unsigned long long)OCFS2_I(inode)->ip_blkno, + le16_to_cpu(di->i_dyn_features), + OCFS2_I(inode)->ip_dyn_features, + osb->s_feature_incompat); + ret = -EROFS; + goto out; + } + + handle = ocfs2_start_trans(osb, OCFS2_INODE_UPDATE_CREDITS); + if (IS_ERR(handle)) { + ret = PTR_ERR(handle); + mlog_errno(ret); + goto out; + } + + ret = ocfs2_journal_access(handle, inode, di_bh, + OCFS2_JOURNAL_ACCESS_WRITE); + if (ret) { + mlog_errno(ret); + goto out_commit; + } + + numbytes = end - start; + memset(idata->id_data + start, 0, numbytes); + + /* + * No need to worry about the data page here - it's been + * truncated already and inline data doesn't need it for + * pushing zero's to disk, so we'll let readpage pick it up + * later. + */ + if (trunc) { + i_size_write(inode, start); + di->i_size = cpu_to_le64(start); + } + + inode->i_blocks = ocfs2_inode_sector_count(inode); + inode->i_ctime = inode->i_mtime = CURRENT_TIME; + + di->i_ctime = di->i_mtime = cpu_to_le64(inode->i_ctime.tv_sec); + di->i_ctime_nsec = di->i_mtime_nsec = cpu_to_le32(inode->i_ctime.tv_nsec); + + ocfs2_journal_dirty(handle, di_bh); + +out_commit: + ocfs2_commit_trans(osb, handle); + +out: + return ret; +} + static void ocfs2_free_truncate_context(struct ocfs2_truncate_context *tc) { /* diff --git a/fs/ocfs2/alloc.h b/fs/ocfs2/alloc.h index 990df48ae8d..42ff94bd801 100644 --- a/fs/ocfs2/alloc.h +++ b/fs/ocfs2/alloc.h @@ -62,6 +62,11 @@ static inline int ocfs2_extend_meta_needed(struct ocfs2_dinode *fe) return le16_to_cpu(fe->id2.i_list.l_tree_depth) + 2; } +void ocfs2_dinode_new_extent_list(struct inode *inode, struct ocfs2_dinode *di); +void ocfs2_set_inode_data_inline(struct inode *inode, struct ocfs2_dinode *di); +int ocfs2_convert_inline_data_to_extents(struct inode *inode, + struct buffer_head *di_bh); + int ocfs2_truncate_log_init(struct ocfs2_super *osb); void ocfs2_truncate_log_shutdown(struct ocfs2_super *osb); void ocfs2_schedule_truncate_log_flush(struct ocfs2_super *osb, @@ -115,6 +120,8 @@ int ocfs2_commit_truncate(struct ocfs2_super *osb, struct inode *inode, struct buffer_head *fe_bh, struct ocfs2_truncate_context *tc); +int ocfs2_truncate_inline(struct inode *inode, struct buffer_head *di_bh, + unsigned int start, unsigned int end, int trunc); int ocfs2_find_leaf(struct inode *inode, struct ocfs2_extent_list *root_el, u32 cpos, struct buffer_head **leaf_bh); diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c index f37f25c931f..34d10452c56 100644 --- a/fs/ocfs2/aops.c +++ b/fs/ocfs2/aops.c @@ -206,9 +206,70 @@ bail: return err; } +int ocfs2_read_inline_data(struct inode *inode, struct page *page, + struct buffer_head *di_bh) +{ + void *kaddr; + unsigned int size; + struct ocfs2_dinode *di = (struct ocfs2_dinode *)di_bh->b_data; + + if (!(le16_to_cpu(di->i_dyn_features) & OCFS2_INLINE_DATA_FL)) { + ocfs2_error(inode->i_sb, "Inode %llu lost inline data flag", + (unsigned long long)OCFS2_I(inode)->ip_blkno); + return -EROFS; + } + + size = i_size_read(inode); + + if (size > PAGE_CACHE_SIZE || + size > ocfs2_max_inline_data(inode->i_sb)) { + ocfs2_error(inode->i_sb, + "Inode %llu has with inline data has bad size: %u", + (unsigned long long)OCFS2_I(inode)->ip_blkno, size); + return -EROFS; + } + + kaddr = kmap_atomic(page, KM_USER0); + if (size) + memcpy(kaddr, di->id2.i_data.id_data, size); + /* Clear the remaining part of the page */ + memset(kaddr + size, 0, PAGE_CACHE_SIZE - size); + flush_dcache_page(page); + kunmap_atomic(kaddr, KM_USER0); + + SetPageUptodate(page); + + return 0; +} + +static int ocfs2_readpage_inline(struct inode *inode, struct page *page) +{ + int ret; + struct buffer_head *di_bh = NULL; + struct ocfs2_super *osb = OCFS2_SB(inode->i_sb); + + BUG_ON(!PageLocked(page)); + BUG_ON(!OCFS2_I(inode)->ip_dyn_features & OCFS2_INLINE_DATA_FL); + + ret = ocfs2_read_block(osb, OCFS2_I(inode)->ip_blkno, &di_bh, + OCFS2_BH_CACHED, inode); + if (ret) { + mlog_errno(ret); + goto out; + } + + ret = ocfs2_read_inline_data(inode, page, di_bh); +out: + unlock_page(page); + + brelse(di_bh); + return ret; +} + static int ocfs2_readpage(struct file *file, struct page *page) { struct inode *inode = page->mapping->host; + struct ocfs2_inode_info *oi = OCFS2_I(inode); loff_t start = (loff_t)page->index << PAGE_CACHE_SHIFT; int ret, unlock = 1; @@ -222,7 +283,7 @@ static int ocfs2_readpage(struct file *file, struct page *page) goto out; } - if (down_read_trylock(&OCFS2_I(inode)->ip_alloc_sem) == 0) { + if (down_read_trylock(&oi->ip_alloc_sem) == 0) { ret = AOP_TRUNCATED_PAGE; goto out_meta_unlock; } @@ -252,7 +313,10 @@ static int ocfs2_readpage(struct file *file, struct page *page) goto out_alloc; } - ret = block_read_full_page(page, ocfs2_get_block); + if (oi->ip_dyn_features & OCFS2_INLINE_DATA_FL) + ret = ocfs2_readpage_inline(inode, page); + else + ret = block_read_full_page(page, ocfs2_get_block); unlock = 0; ocfs2_data_unlock(inode, 0); @@ -301,12 +365,8 @@ int ocfs2_prepare_write_nolock(struct inode *inode, struct page *page, { int ret; - down_read(&OCFS2_I(inode)->ip_alloc_sem); - ret = block_prepare_write(page, from, to, ocfs2_get_block); - up_read(&OCFS2_I(inode)->ip_alloc_sem); - return ret; } @@ -401,7 +461,9 @@ static sector_t ocfs2_bmap(struct address_space *mapping, sector_t block) down_read(&OCFS2_I(inode)->ip_alloc_sem); } - err = ocfs2_extent_map_get_blocks(inode, block, &p_blkno, NULL, NULL); + if (!(OCFS2_I(inode)->ip_dyn_features & OCFS2_INLINE_DATA_FL)) + err = ocfs2_extent_map_get_blocks(inode, block, &p_blkno, NULL, + NULL); if (!INODE_JOURNAL(inode)) { up_read(&OCFS2_I(inode)->ip_alloc_sem); @@ -415,7 +477,6 @@ static sector_t ocfs2_bmap(struct address_space *mapping, sector_t block) goto bail; } - bail: status = err ? 0 : p_blkno; @@ -570,6 +631,13 @@ static ssize_t ocfs2_direct_IO(int rw, mlog_entry_void(); + /* + * Fallback to buffered I/O if we see an inode without + * extents. + */ + if (OCFS2_I(inode)->ip_dyn_features & OCFS2_INLINE_DATA_FL) + return 0; + if (!ocfs2_sparse_alloc(OCFS2_SB(inode->i_sb))) { /* * We get PR data locks even for O_DIRECT. This @@ -834,18 +902,22 @@ struct ocfs2_write_ctxt { struct ocfs2_cached_dealloc_ctxt w_dealloc; }; -static void ocfs2_free_write_ctxt(struct ocfs2_write_ctxt *wc) +void ocfs2_unlock_and_free_pages(struct page **pages, int num_pages) { int i; - for(i = 0; i < wc->w_num_pages; i++) { - if (wc->w_pages[i] == NULL) - continue; - - unlock_page(wc->w_pages[i]); - mark_page_accessed(wc->w_pages[i]); - page_cache_release(wc->w_pages[i]); + for(i = 0; i < num_pages; i++) { + if (pages[i]) { + unlock_page(pages[i]); + mark_page_accessed(pages[i]); + page_cache_release(pages[i]); + } } +} + +static void ocfs2_free_write_ctxt(struct ocfs2_write_ctxt *wc) +{ + ocfs2_unlock_and_free_pages(wc->w_pages, wc->w_num_pages); brelse(wc->w_di_bh); kfree(wc); @@ -1360,6 +1432,160 @@ out: return ret; } +static int ocfs2_write_begin_inline(struct address_space *mapping, + struct inode *inode, + struct ocfs2_write_ctxt *wc) +{ + int ret; + struct ocfs2_super *osb = OCFS2_SB(inode->i_sb); + struct page *page; + handle_t *handle; + struct ocfs2_dinode *di = (struct ocfs2_dinode *)wc->w_di_bh->b_data; + + page = find_or_create_page(mapping, 0, GFP_NOFS); + if (!page) { + ret = -ENOMEM; + mlog_errno(ret); + goto out; + } + /* + * If we don't set w_num_pages then this page won't get unlocked + * and freed on cleanup of the write context. + */ + wc->w_pages[0] = wc->w_target_page = page; + wc->w_num_pages = 1; + + handle = ocfs2_start_trans(osb, OCFS2_INODE_UPDATE_CREDITS); + if (IS_ERR(handle)) { + ret = PTR_ERR(handle); + mlog_errno(ret); + goto out; + } + + ret = ocfs2_journal_access(handle, inode, wc->w_di_bh, + OCFS2_JOURNAL_ACCESS_WRITE); + if (ret) { + ocfs2_commit_trans(osb, handle); + + mlog_errno(ret); + goto out; + } + + if (!(OCFS2_I(inode)->ip_dyn_features & OCFS2_INLINE_DATA_FL)) + ocfs2_set_inode_data_inline(inode, di); + + if (!PageUptodate(page)) { + ret = ocfs2_read_inline_data(inode, page, wc->w_di_bh); + if (ret) { + ocfs2_commit_trans(osb, handle); + + goto out; + } + } + + wc->w_handle = handle; +out: + return ret; +} + +int ocfs2_size_fits_inline_data(struct buffer_head *di_bh, u64 new_size) +{ + struct ocfs2_dinode *di = (struct ocfs2_dinode *)di_bh->b_data; + + if (new_size < le16_to_cpu(di->id2.i_data.id_count)) + return 1; + return 0; +} + +static int ocfs2_try_to_write_inline_data(struct address_space *mapping, + struct inode *inode, loff_t pos, + unsigned len, struct page *mmap_page, + struct ocfs2_write_ctxt *wc) +{ + int ret, written = 0; + loff_t end = pos + len; + struct ocfs2_inode_info *oi = OCFS2_I(inode); + + mlog(0, "Inode %llu, write of %u bytes at off %llu. features: 0x%x\n", + (unsigned long long)oi->ip_blkno, len, (unsigned long long)pos, + oi->ip_dyn_features); + + /* + * Handle inodes which already have inline data 1st. + */ + if (oi->ip_dyn_features & OCFS2_INLINE_DATA_FL) { + if (mmap_page == NULL && + ocfs2_size_fits_inline_data(wc->w_di_bh, end)) + goto do_inline_write; + + /* + * The write won't fit - we have to give this inode an + * inline extent list now. + */ + ret = ocfs2_convert_inline_data_to_extents(inode, wc->w_di_bh); + if (ret) + mlog_errno(ret); + goto out; + } + + /* + * Check whether the inode can accept inline data. + */ + if (oi->ip_clusters != 0 || i_size_read(inode) != 0) + return 0; + + /* + * Check whether the write can fit. + */ + if (mmap_page || end > ocfs2_max_inline_data(inode->i_sb)) + return 0; + +do_inline_write: + ret = ocfs2_write_begin_inline(mapping, inode, wc); + if (ret) { + mlog_errno(ret); + goto out; + } + + /* + * This signals to the caller that the data can be written + * inline. + */ + written = 1; +out: + return written ? written : ret; +} + +/* + * This function only does anything for file systems which can't + * handle sparse files. + * + * What we want to do here is fill in any hole between the current end + * of allocation and the end of our write. That way the rest of the + * write path can treat it as an non-allocating write, which has no + * special case code for sparse/nonsparse files. + */ +static int ocfs2_expand_nonsparse_inode(struct inode *inode, loff_t pos, + unsigned len, + struct ocfs2_write_ctxt *wc) +{ + int ret; + struct ocfs2_super *osb = OCFS2_SB(inode->i_sb); + loff_t newsize = pos + len; + + if (ocfs2_sparse_alloc(osb)) + return 0; + + if (newsize <= i_size_read(inode)) + return 0; + + ret = ocfs2_extend_no_holes(inode, newsize, newsize - len); + if (ret) + mlog_errno(ret); + + return ret; +} + int ocfs2_write_begin_nolock(struct address_space *mapping, loff_t pos, unsigned len, unsigned flags, struct page **pagep, void **fsdata, @@ -1381,6 +1607,25 @@ int ocfs2_write_begin_nolock(struct address_space *mapping, return ret; } + if (ocfs2_supports_inline_data(osb)) { + ret = ocfs2_try_to_write_inline_data(mapping, inode, pos, len, + mmap_page, wc); + if (ret == 1) { + ret = 0; + goto success; + } + if (ret < 0) { + mlog_errno(ret); + goto out; + } + } + + ret = ocfs2_expand_nonsparse_inode(inode, pos, len, wc); + if (ret) { + mlog_errno(ret); + goto out; + } + ret = ocfs2_populate_write_desc(inode, wc, &clusters_to_alloc, &extents_to_split); if (ret) { @@ -1462,6 +1707,7 @@ int ocfs2_write_begin_nolock(struct address_space *mapping, if (meta_ac) ocfs2_free_alloc_context(meta_ac); +success: *pagep = wc->w_target_page; *fsdata = wc; return 0; @@ -1529,6 +1775,31 @@ out_fail: return ret; } +static void ocfs2_write_end_inline(struct inode *inode, loff_t pos, + unsigned len, unsigned *copied, + struct ocfs2_dinode *di, + struct ocfs2_write_ctxt *wc) +{ + void *kaddr; + + if (unlikely(*copied < len)) { + if (!PageUptodate(wc->w_target_page)) { + *copied = 0; + return; + } + } + + kaddr = kmap_atomic(wc->w_target_page, KM_USER0); + memcpy(di->id2.i_data.id_data + pos, kaddr + pos, *copied); + kunmap_atomic(kaddr, KM_USER0); + + mlog(0, "Data written to inode at offset %llu. " + "id_count = %u, copied = %u, i_dyn_features = 0x%x\n", + (unsigned long long)pos, *copied, + le16_to_cpu(di->id2.i_data.id_count), + le16_to_cpu(di->i_dyn_features)); +} + int ocfs2_write_end_nolock(struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, struct page *page, void *fsdata) @@ -1542,6 +1813,11 @@ int ocfs2_write_end_nolock(struct address_space *mapping, handle_t *handle = wc->w_handle; struct page *tmppage; + if (OCFS2_I(inode)->ip_dyn_features & OCFS2_INLINE_DATA_FL) { + ocfs2_write_end_inline(inode, pos, len, &copied, di, wc); + goto out_write_size; + } + if (unlikely(copied < len)) { if (!PageUptodate(wc->w_target_page)) copied = 0; @@ -1579,6 +1855,7 @@ int ocfs2_write_end_nolock(struct address_space *mapping, block_commit_write(tmppage, from, to); } +out_write_size: pos += copied; if (pos > inode->i_size) { i_size_write(inode, pos); diff --git a/fs/ocfs2/aops.h b/fs/ocfs2/aops.h index 389579bd64e..113560877db 100644 --- a/fs/ocfs2/aops.h +++ b/fs/ocfs2/aops.h @@ -34,6 +34,8 @@ int ocfs2_map_page_blocks(struct page *page, u64 *p_blkno, struct inode *inode, unsigned int from, unsigned int to, int new); +void ocfs2_unlock_and_free_pages(struct page **pages, int num_pages); + int walk_page_buffers( handle_t *handle, struct buffer_head *head, unsigned from, @@ -59,6 +61,10 @@ int ocfs2_write_begin_nolock(struct address_space *mapping, struct page **pagep, void **fsdata, struct buffer_head *di_bh, struct page *mmap_page); +int ocfs2_read_inline_data(struct inode *inode, struct page *page, + struct buffer_head *di_bh); +int ocfs2_size_fits_inline_data(struct buffer_head *di_bh, u64 new_size); + /* all ocfs2_dio_end_io()'s fault */ #define ocfs2_iocb_is_rw_locked(iocb) \ test_bit(0, (unsigned long *)&iocb->private) diff --git a/fs/ocfs2/dir.c b/fs/ocfs2/dir.c index 0d5fdde959c..7453b70c1a1 100644 --- a/fs/ocfs2/dir.c +++ b/fs/ocfs2/dir.c @@ -55,10 +55,16 @@ #include "journal.h" #include "namei.h" #include "suballoc.h" +#include "super.h" #include "uptodate.h" #include "buffer_head_io.h" +#define NAMEI_RA_CHUNKS 2 +#define NAMEI_RA_BLOCKS 4 +#define NAMEI_RA_SIZE (NAMEI_RA_CHUNKS * NAMEI_RA_BLOCKS) +#define NAMEI_RA_INDEX(c,b) (((c) * NAMEI_RA_BLOCKS) + (b)) + static unsigned char ocfs2_filetype_table[] = { DT_UNKNOWN, DT_REG, DT_DIR, DT_CHR, DT_BLK, DT_FIFO, DT_SOCK, DT_LNK }; @@ -66,12 +72,614 @@ static unsigned char ocfs2_filetype_table[] = { static int ocfs2_extend_dir(struct ocfs2_super *osb, struct inode *dir, struct buffer_head *parent_fe_bh, + unsigned int blocks_wanted, struct buffer_head **new_de_bh); +static int ocfs2_do_extend_dir(struct super_block *sb, + handle_t *handle, + struct inode *dir, + struct buffer_head *parent_fe_bh, + struct ocfs2_alloc_context *data_ac, + struct ocfs2_alloc_context *meta_ac, + struct buffer_head **new_bh); + /* - * ocfs2_readdir() + * bh passed here can be an inode block or a dir data block, depending + * on the inode inline data flag. + */ +static int ocfs2_check_dir_entry(struct inode * dir, + struct ocfs2_dir_entry * de, + struct buffer_head * bh, + unsigned long offset) +{ + const char *error_msg = NULL; + const int rlen = le16_to_cpu(de->rec_len); + + if (rlen < OCFS2_DIR_REC_LEN(1)) + error_msg = "rec_len is smaller than minimal"; + else if (rlen % 4 != 0) + error_msg = "rec_len % 4 != 0"; + else if (rlen < OCFS2_DIR_REC_LEN(de->name_len)) + error_msg = "rec_len is too small for name_len"; + else if (((char *) de - bh->b_data) + rlen > dir->i_sb->s_blocksize) + error_msg = "directory entry across blocks"; + + if (error_msg != NULL) + mlog(ML_ERROR, "bad entry in directory #%llu: %s - " + "offset=%lu, inode=%llu, rec_len=%d, name_len=%d\n", + (unsigned long long)OCFS2_I(dir)->ip_blkno, error_msg, + offset, (unsigned long long)le64_to_cpu(de->inode), rlen, + de->name_len); + return error_msg == NULL ? 1 : 0; +} + +static inline int ocfs2_match(int len, + const char * const name, + struct ocfs2_dir_entry *de) +{ + if (len != de->name_len) + return 0; + if (!de->inode) + return 0; + return !memcmp(name, de->name, len); +} + +/* + * Returns 0 if not found, -1 on failure, and 1 on success + */ +static int inline ocfs2_search_dirblock(struct buffer_head *bh, + struct inode *dir, + const char *name, int namelen, + unsigned long offset, + char *first_de, + unsigned int bytes, + struct ocfs2_dir_entry **res_dir) +{ + struct ocfs2_dir_entry *de; + char *dlimit, *de_buf; + int de_len; + int ret = 0; + + mlog_entry_void(); + + de_buf = first_de; + dlimit = de_buf + bytes; + + while (de_buf < dlimit) { + /* this code is executed quadratically often */ + /* do minimal checking `by hand' */ + + de = (struct ocfs2_dir_entry *) de_buf; + + if (de_buf + namelen <= dlimit && + ocfs2_match(namelen, name, de)) { + /* found a match - just to be sure, do a full check */ + if (!ocfs2_check_dir_entry(dir, de, bh, offset)) { + ret = -1; + goto bail; + } + *res_dir = de; + ret = 1; + goto bail; + } + + /* prevent looping on a bad block */ + de_len = le16_to_cpu(de->rec_len); + if (de_len <= 0) { + ret = -1; + goto bail; + } + + de_buf += de_len; + offset += de_len; + } + +bail: + mlog_exit(ret); + return ret; +} + +static struct buffer_head *ocfs2_find_entry_id(const char *name, + int namelen, + struct inode *dir, + struct ocfs2_dir_entry **res_dir) +{ + int ret, found; + struct buffer_head *di_bh = NULL; + struct ocfs2_dinode *di; + struct ocfs2_inline_data *data; + + ret = ocfs2_read_block(OCFS2_SB(dir->i_sb), OCFS2_I(dir)->ip_blkno, + &di_bh, OCFS2_BH_CACHED, dir); + if (ret) { + mlog_errno(ret); + goto out; + } + + di = (struct ocfs2_dinode *)di_bh->b_data; + data = &di->id2.i_data; + + found = ocfs2_search_dirblock(di_bh, dir, name, namelen, 0, + data->id_data, i_size_read(dir), res_dir); + if (found == 1) + return di_bh; + + brelse(di_bh); +out: + return NULL; +} + +struct buffer_head *ocfs2_find_entry_el(const char *name, int namelen, + struct inode *dir, + struct ocfs2_dir_entry **res_dir) +{ + struct super_block *sb; + struct buffer_head *bh_use[NAMEI_RA_SIZE]; + struct buffer_head *bh, *ret = NULL; + unsigned long start, block, b; + int ra_max = 0; /* Number of bh's in the readahead + buffer, bh_use[] */ + int ra_ptr = 0; /* Current index into readahead + buffer */ + int num = 0; + int nblocks, i, err; + + mlog_entry_void(); + + sb = dir->i_sb; + + nblocks = i_size_read(dir) >> sb->s_blocksize_bits; + start = OCFS2_I(dir)->ip_dir_start_lookup; + if (start >= nblocks) + start = 0; + block = start; + +restart: + do { + /* + * We deal with the read-ahead logic here. + */ + if (ra_ptr >= ra_max) { + /* Refill the readahead buffer */ + ra_ptr = 0; + b = block; + for (ra_max = 0; ra_max < NAMEI_RA_SIZE; ra_max++) { + /* + * Terminate if we reach the end of the + * directory and must wrap, or if our + * search has finished at this block. + */ + if (b >= nblocks || (num && block == start)) { + bh_use[ra_max] = NULL; + break; + } + num++; + + bh = ocfs2_bread(dir, b++, &err, 1); + bh_use[ra_max] = bh; + } + } + if ((bh = bh_use[ra_ptr++]) == NULL) + goto next; + wait_on_buffer(bh); + if (!buffer_uptodate(bh)) { + /* read error, skip block & hope for the best */ + ocfs2_error(dir->i_sb, "reading directory %llu, " + "offset %lu\n", + (unsigned long long)OCFS2_I(dir)->ip_blkno, + block); + brelse(bh); + goto next; + } + i = ocfs2_search_dirblock(bh, dir, name, namelen, + block << sb->s_blocksize_bits, + bh->b_data, sb->s_blocksize, + res_dir); + if (i == 1) { + OCFS2_I(dir)->ip_dir_start_lookup = block; + ret = bh; + goto cleanup_and_exit; + } else { + brelse(bh); + if (i < 0) + goto cleanup_and_exit; + } + next: + if (++block >= nblocks) + block = 0; + } while (block != start); + + /* + * If the directory has grown while we were searching, then + * search the last part of the directory before giving up. + */ + block = nblocks; + nblocks = i_size_read(dir) >> sb->s_blocksize_bits; + if (block < nblocks) { + start = 0; + goto restart; + } + +cleanup_and_exit: + /* Clean up the read-ahead blocks */ + for (; ra_ptr < ra_max; ra_ptr++) + brelse(bh_use[ra_ptr]); + + mlog_exit_ptr(ret); + return ret; +} + +/* + * Try to find an entry of the provided name within 'dir'. * + * If nothing was found, NULL is returned. Otherwise, a buffer_head + * and pointer to the dir entry are passed back. + * + * Caller can NOT assume anything about the contents of the + * buffer_head - it is passed back only so that it can be passed into + * any one of the manipulation functions (add entry, delete entry, + * etc). As an example, bh in the extent directory case is a data + * block, in the inline-data case it actually points to an inode. */ -int ocfs2_readdir(struct file * filp, void * dirent, filldir_t filldir) +struct buffer_head *ocfs2_find_entry(const char *name, int namelen, + struct inode *dir, + struct ocfs2_dir_entry **res_dir) +{ + *res_dir = NULL; + + if (OCFS2_I(dir)->ip_dyn_features & OCFS2_INLINE_DATA_FL) + return ocfs2_find_entry_id(name, namelen, dir, res_dir); + + return ocfs2_find_entry_el(name, namelen, dir, res_dir); +} + +/* + * Update inode number and type of a previously found directory entry. + */ +int ocfs2_update_entry(struct inode *dir, handle_t *handle, + struct buffer_head *de_bh, struct ocfs2_dir_entry *de, + struct inode *new_entry_inode) +{ + int ret; + + /* + * The same code works fine for both inline-data and extent + * based directories, so no need to split this up. + */ + + ret = ocfs2_journal_access(handle, dir, de_bh, + OCFS2_JOURNAL_ACCESS_WRITE); + if (ret) { + mlog_errno(ret); + goto out; + } + + de->inode = cpu_to_le64(OCFS2_I(new_entry_inode)->ip_blkno); + ocfs2_set_de_type(de, new_entry_inode->i_mode); + + ocfs2_journal_dirty(handle, de_bh); + +out: + return ret; +} + +static int __ocfs2_delete_entry(handle_t *handle, struct inode *dir, + struct ocfs2_dir_entry *de_del, + struct buffer_head *bh, char *first_de, + unsigned int bytes) +{ + struct ocfs2_dir_entry *de, *pde; + int i, status = -ENOENT; + + mlog_entry("(0x%p, 0x%p, 0x%p, 0x%p)\n", handle, dir, de_del, bh); + + i = 0; + pde = NULL; + de = (struct ocfs2_dir_entry *) first_de; + while (i < bytes) { + if (!ocfs2_check_dir_entry(dir, de, bh, i)) { + status = -EIO; + mlog_errno(status); + goto bail; + } + if (de == de_del) { + status = ocfs2_journal_access(handle, dir, bh, + OCFS2_JOURNAL_ACCESS_WRITE); + if (status < 0) { + status = -EIO; + mlog_errno(status); + goto bail; + } + if (pde) + pde->rec_len = + cpu_to_le16(le16_to_cpu(pde->rec_len) + + le16_to_cpu(de->rec_len)); + else + de->inode = 0; + dir->i_version++; + status = ocfs2_journal_dirty(handle, bh); + goto bail; + } + i += le16_to_cpu(de->rec_len); + pde = de; + de = (struct ocfs2_dir_entry *)((char *)de + le16_to_cpu(de->rec_len)); + } +bail: + mlog_exit(status); + return status; +} + +static inline int ocfs2_delete_entry_id(handle_t *handle, + struct inode *dir, + struct ocfs2_dir_entry *de_del, + struct buffer_head *bh) +{ + int ret; + struct buffer_head *di_bh = NULL; + struct ocfs2_dinode *di; + struct ocfs2_inline_data *data; + + ret = ocfs2_read_block(OCFS2_SB(dir->i_sb), OCFS2_I(dir)->ip_blkno, + &di_bh, OCFS2_BH_CACHED, dir); + if (ret) { + mlog_errno(ret); + goto out; + } + + di = (struct ocfs2_dinode *)di_bh->b_data; + data = &di->id2.i_data; + + ret = __ocfs2_delete_entry(handle, dir, de_del, bh, data->id_data, + i_size_read(dir)); + + brelse(di_bh); +out: + return ret; +} + +static inline int ocfs2_delete_entry_el(handle_t *handle, + struct inode *dir, + struct ocfs2_dir_entry *de_del, + struct buffer_head *bh) +{ + return __ocfs2_delete_entry(handle, dir, de_del, bh, bh->b_data, + bh->b_size); +} + +/* + * ocfs2_delete_entry deletes a directory entry by merging it with the + * previous entry + */ +int ocfs2_delete_entry(handle_t *handle, + struct inode *dir, + struct ocfs2_dir_entry *de_del, + struct buffer_head *bh) +{ + if (OCFS2_I(dir)->ip_dyn_features & OCFS2_INLINE_DATA_FL) + return ocfs2_delete_entry_id(handle, dir, de_del, bh); + + return ocfs2_delete_entry_el(handle, dir, de_del, bh); +} + +/* + * Check whether 'de' has enough room to hold an entry of + * 'new_rec_len' bytes. + */ +static inline int ocfs2_dirent_would_fit(struct ocfs2_dir_entry *de, + unsigned int new_rec_len) +{ + unsigned int de_really_used; + + /* Check whether this is an empty record with enough space */ + if (le64_to_cpu(de->inode) == 0 && + le16_to_cpu(de->rec_len) >= new_rec_len) + return 1; + + /* + * Record might have free space at the end which we can + * use. + */ + de_really_used = OCFS2_DIR_REC_LEN(de->name_len); + if (le16_to_cpu(de->rec_len) >= (de_really_used + new_rec_len)) + return 1; + + return 0; +} + +/* we don't always have a dentry for what we want to add, so people + * like orphan dir can call this instead. + * + * If you pass me insert_bh, I'll skip the search of the other dir + * blocks and put the record in there. + */ +int __ocfs2_add_entry(handle_t *handle, + struct inode *dir, + const char *name, int namelen, + struct inode *inode, u64 blkno, + struct buffer_head *parent_fe_bh, + struct buffer_head *insert_bh) +{ + unsigned long offset; + unsigned short rec_len; + struct ocfs2_dir_entry *de, *de1; + struct ocfs2_dinode *di = (struct ocfs2_dinode *)parent_fe_bh->b_data; + struct super_block *sb = dir->i_sb; + int retval, status; + unsigned int size = sb->s_blocksize; + char *data_start = insert_bh->b_data; + + mlog_entry_void(); + + if (!namelen) + return -EINVAL; + + if (OCFS2_I(dir)->ip_dyn_features & OCFS2_INLINE_DATA_FL) { + data_start = di->id2.i_data.id_data; + size = i_size_read(dir); + + BUG_ON(insert_bh != parent_fe_bh); + } + + rec_len = OCFS2_DIR_REC_LEN(namelen); + offset = 0; + de = (struct ocfs2_dir_entry *) data_start; + while (1) { + BUG_ON((char *)de >= (size + data_start)); + + /* These checks should've already been passed by the + * prepare function, but I guess we can leave them + * here anyway. */ + if (!ocfs2_check_dir_entry(dir, de, insert_bh, offset)) { + retval = -ENOENT; + goto bail; + } + if (ocfs2_match(namelen, name, de)) { + retval = -EEXIST; + goto bail; + } + + if (ocfs2_dirent_would_fit(de, rec_len)) { + dir->i_mtime = dir->i_ctime = CURRENT_TIME; + retval = ocfs2_mark_inode_dirty(handle, dir, parent_fe_bh); + if (retval < 0) { + mlog_errno(retval); + goto bail; + } + + status = ocfs2_journal_access(handle, dir, insert_bh, + OCFS2_JOURNAL_ACCESS_WRITE); + /* By now the buffer is marked for journaling */ + offset += le16_to_cpu(de->rec_len); + if (le64_to_cpu(de->inode)) { + de1 = (struct ocfs2_dir_entry *)((char *) de + + OCFS2_DIR_REC_LEN(de->name_len)); + de1->rec_len = + cpu_to_le16(le16_to_cpu(de->rec_len) - + OCFS2_DIR_REC_LEN(de->name_len)); + de->rec_len = cpu_to_le16(OCFS2_DIR_REC_LEN(de->name_len)); + de = de1; + } + de->file_type = OCFS2_FT_UNKNOWN; + if (blkno) { + de->inode = cpu_to_le64(blkno); + ocfs2_set_de_type(de, inode->i_mode); + } else + de->inode = 0; + de->name_len = namelen; + memcpy(de->name, name, namelen); + + dir->i_version++; + status = ocfs2_journal_dirty(handle, insert_bh); + retval = 0; + goto bail; + } + offset += le16_to_cpu(de->rec_len); + de = (struct ocfs2_dir_entry *) ((char *) de + le16_to_cpu(de->rec_len)); + } + + /* when you think about it, the assert above should prevent us + * from ever getting here. */ + retval = -ENOSPC; +bail: + + mlog_exit(retval); + return retval; +} + +static int ocfs2_dir_foreach_blk_id(struct inode *inode, + unsigned long *f_version, + loff_t *f_pos, void *priv, + filldir_t filldir, int *filldir_err) +{ + int ret, i, filldir_ret; + unsigned long offset = *f_pos; + struct buffer_head *di_bh = NULL; + struct ocfs2_dinode *di; + struct ocfs2_inline_data *data; + struct ocfs2_dir_entry *de; + + ret = ocfs2_read_block(OCFS2_SB(inode->i_sb), OCFS2_I(inode)->ip_blkno, + &di_bh, OCFS2_BH_CACHED, inode); + if (ret) { + mlog(ML_ERROR, "Unable to read inode block for dir %llu\n", + (unsigned long long)OCFS2_I(inode)->ip_blkno); + goto out; + } + + di = (struct ocfs2_dinode *)di_bh->b_data; + data = &di->id2.i_data; + + while (*f_pos < i_size_read(inode)) { +revalidate: + /* If the dir block has changed since the last call to + * readdir(2), then we might be pointing to an invalid + * dirent right now. Scan from the start of the block + * to make sure. */ + if (*f_version != inode->i_version) { + for (i = 0; i < i_size_read(inode) && i < offset; ) { + de = (struct ocfs2_dir_entry *) + (data->id_data + i); + /* It's too expensive to do a full + * dirent test each time round this + * loop, but we do have to test at + * least that it is non-zero. A + * failure will be detected in the + * dirent test below. */ + if (le16_to_cpu(de->rec_len) < + OCFS2_DIR_REC_LEN(1)) + break; + i += le16_to_cpu(de->rec_len); + } + *f_pos = offset = i; + *f_version = inode->i_version; + } + + de = (struct ocfs2_dir_entry *) (data->id_data + *f_pos); + if (!ocfs2_check_dir_entry(inode, de, di_bh, *f_pos)) { + /* On error, skip the f_pos to the end. */ + *f_pos = i_size_read(inode); + goto out; + } + offset += le16_to_cpu(de->rec_len); + if (le64_to_cpu(de->inode)) { + /* We might block in the next section + * if the data destination is + * currently swapped out. So, use a + * version stamp to detect whether or + * not the directory has been modified + * during the copy operation. + */ + unsigned long version = *f_version; + unsigned char d_type = DT_UNKNOWN; + + if (de->file_type < OCFS2_FT_MAX) + d_type = ocfs2_filetype_table[de->file_type]; + + filldir_ret = filldir(priv, de->name, + de->name_len, + *f_pos, + le64_to_cpu(de->inode), + d_type); + if (filldir_ret) { + if (filldir_err) + *filldir_err = filldir_ret; + break; + } + if (version != *f_version) + goto revalidate; + } + *f_pos += le16_to_cpu(de->rec_len); + } + +out: + brelse(di_bh); + + return 0; +} + +static int ocfs2_dir_foreach_blk_el(struct inode *inode, + unsigned long *f_version, + loff_t *f_pos, void *priv, + filldir_t filldir, int *filldir_err) { int error = 0; unsigned long offset, blk, last_ra_blk = 0; @@ -79,45 +687,23 @@ int ocfs2_readdir(struct file * filp, void * dirent, filldir_t filldir) struct buffer_head * bh, * tmp; struct ocfs2_dir_entry * de; int err; - struct inode *inode = filp->f_path.dentry->d_inode; struct super_block * sb = inode->i_sb; unsigned int ra_sectors = 16; - int lock_level = 0; - - mlog_entry("dirino=%llu\n", - (unsigned long long)OCFS2_I(inode)->ip_blkno); stored = 0; bh = NULL; - error = ocfs2_meta_lock_atime(inode, filp->f_vfsmnt, &lock_level); - if (lock_level && error >= 0) { - /* We release EX lock which used to update atime - * and get PR lock again to reduce contention - * on commonly accessed directories. */ - ocfs2_meta_unlock(inode, 1); - lock_level = 0; - error = ocfs2_meta_lock(inode, NULL, 0); - } - if (error < 0) { - if (error != -ENOENT) - mlog_errno(error); - /* we haven't got any yet, so propagate the error. */ - stored = error; - goto bail_nolock; - } + offset = (*f_pos) & (sb->s_blocksize - 1); - offset = filp->f_pos & (sb->s_blocksize - 1); - - while (!error && !stored && filp->f_pos < i_size_read(inode)) { - blk = (filp->f_pos) >> sb->s_blocksize_bits; + while (!error && !stored && *f_pos < i_size_read(inode)) { + blk = (*f_pos) >> sb->s_blocksize_bits; bh = ocfs2_bread(inode, blk, &err, 0); if (!bh) { mlog(ML_ERROR, "directory #%llu contains a hole at offset %lld\n", (unsigned long long)OCFS2_I(inode)->ip_blkno, - filp->f_pos); - filp->f_pos += sb->s_blocksize - offset; + *f_pos); + *f_pos += sb->s_blocksize - offset; continue; } @@ -143,7 +729,7 @@ revalidate: * readdir(2), then we might be pointing to an invalid * dirent right now. Scan from the start of the block * to make sure. */ - if (filp->f_version != inode->i_version) { + if (*f_version != inode->i_version) { for (i = 0; i < sb->s_blocksize && i < offset; ) { de = (struct ocfs2_dir_entry *) (bh->b_data + i); /* It's too expensive to do a full @@ -158,21 +744,20 @@ revalidate: i += le16_to_cpu(de->rec_len); } offset = i; - filp->f_pos = (filp->f_pos & ~(sb->s_blocksize - 1)) + *f_pos = ((*f_pos) & ~(sb->s_blocksize - 1)) | offset; - filp->f_version = inode->i_version; + *f_version = inode->i_version; } - while (!error && filp->f_pos < i_size_read(inode) + while (!error && *f_pos < i_size_read(inode) && offset < sb->s_blocksize) { de = (struct ocfs2_dir_entry *) (bh->b_data + offset); if (!ocfs2_check_dir_entry(inode, de, bh, offset)) { /* On error, skip the f_pos to the next block. */ - filp->f_pos = (filp->f_pos | - (sb->s_blocksize - 1)) + 1; + *f_pos = ((*f_pos) | (sb->s_blocksize - 1)) + 1; brelse(bh); - goto bail; + goto out; } offset += le16_to_cpu(de->rec_len); if (le64_to_cpu(de->inode)) { @@ -183,36 +768,109 @@ revalidate: * not the directory has been modified * during the copy operation. */ - unsigned long version = filp->f_version; + unsigned long version = *f_version; unsigned char d_type = DT_UNKNOWN; if (de->file_type < OCFS2_FT_MAX) d_type = ocfs2_filetype_table[de->file_type]; - error = filldir(dirent, de->name, + error = filldir(priv, de->name, de->name_len, - filp->f_pos, - ino_from_blkno(sb, le64_to_cpu(de->inode)), + *f_pos, + le64_to_cpu(de->inode), d_type); - if (error) + if (error) { + if (filldir_err) + *filldir_err = error; break; - if (version != filp->f_version) + } + if (version != *f_version) goto revalidate; stored ++; } - filp->f_pos += le16_to_cpu(de->rec_len); + *f_pos += le16_to_cpu(de->rec_len); } offset = 0; brelse(bh); } stored = 0; -bail: +out: + return stored; +} + +static int ocfs2_dir_foreach_blk(struct inode *inode, unsigned long *f_version, + loff_t *f_pos, void *priv, filldir_t filldir, + int *filldir_err) +{ + if (OCFS2_I(inode)->ip_dyn_features & OCFS2_INLINE_DATA_FL) + return ocfs2_dir_foreach_blk_id(inode, f_version, f_pos, priv, + filldir, filldir_err); + + return ocfs2_dir_foreach_blk_el(inode, f_version, f_pos, priv, filldir, + filldir_err); +} + +/* + * This is intended to be called from inside other kernel functions, + * so we fake some arguments. + */ +int ocfs2_dir_foreach(struct inode *inode, loff_t *f_pos, void *priv, + filldir_t filldir) +{ + int ret = 0, filldir_err = 0; + unsigned long version = inode->i_version; + + while (*f_pos < i_size_read(inode)) { + ret = ocfs2_dir_foreach_blk(inode, &version, f_pos, priv, + filldir, &filldir_err); + if (ret || filldir_err) + break; + } + + if (ret > 0) + ret = -EIO; + + return 0; +} + +/* + * ocfs2_readdir() + * + */ +int ocfs2_readdir(struct file * filp, void * dirent, filldir_t filldir) +{ + int error = 0; + struct inode *inode = filp->f_path.dentry->d_inode; + int lock_level = 0; + + mlog_entry("dirino=%llu\n", + (unsigned long long)OCFS2_I(inode)->ip_blkno); + + error = ocfs2_meta_lock_atime(inode, filp->f_vfsmnt, &lock_level); + if (lock_level && error >= 0) { + /* We release EX lock which used to update atime + * and get PR lock again to reduce contention + * on commonly accessed directories. */ + ocfs2_meta_unlock(inode, 1); + lock_level = 0; + error = ocfs2_meta_lock(inode, NULL, 0); + } + if (error < 0) { + if (error != -ENOENT) + mlog_errno(error); + /* we haven't got any yet, so propagate the error. */ + goto bail_nolock; + } + + error = ocfs2_dir_foreach_blk(inode, &filp->f_version, &filp->f_pos, + dirent, filldir, NULL); + ocfs2_meta_unlock(inode, lock_level); bail_nolock: - mlog_exit(stored); + mlog_exit(error); - return stored; + return error; } /* @@ -252,6 +910,23 @@ leave: return status; } +/* + * Convenience function for callers which just want the block number + * mapped to a name and don't require the full dirent info, etc. + */ +int ocfs2_lookup_ino_from_name(struct inode *dir, const char *name, + int namelen, u64 *blkno) +{ + int ret; + struct buffer_head *bh = NULL; + struct ocfs2_dir_entry *dirent = NULL; + + ret = ocfs2_find_files_on_disk(name, namelen, blkno, dir, &bh, &dirent); + brelse(bh); + + return ret; +} + /* Check for a name within a directory. * * Return 0 if the name does not exist @@ -284,77 +959,414 @@ bail: return ret; } +struct ocfs2_empty_dir_priv { + unsigned seen_dot; + unsigned seen_dot_dot; + unsigned seen_other; +}; +static int ocfs2_empty_dir_filldir(void *priv, const char *name, int name_len, + loff_t pos, u64 ino, unsigned type) +{ + struct ocfs2_empty_dir_priv *p = priv; + + /* + * Check the positions of "." and ".." records to be sure + * they're in the correct place. + */ + if (name_len == 1 && !strncmp(".", name, 1) && pos == 0) { + p->seen_dot = 1; + return 0; + } + + if (name_len == 2 && !strncmp("..", name, 2) && + pos == OCFS2_DIR_REC_LEN(1)) { + p->seen_dot_dot = 1; + return 0; + } + + p->seen_other = 1; + return 1; +} /* * routine to check that the specified directory is empty (for rmdir) + * + * Returns 1 if dir is empty, zero otherwise. */ int ocfs2_empty_dir(struct inode *inode) { - unsigned long offset; - struct buffer_head * bh; - struct ocfs2_dir_entry * de, * de1; - struct super_block * sb; - int err; + int ret; + loff_t start = 0; + struct ocfs2_empty_dir_priv priv; + + memset(&priv, 0, sizeof(priv)); + + ret = ocfs2_dir_foreach(inode, &start, &priv, ocfs2_empty_dir_filldir); + if (ret) + mlog_errno(ret); - sb = inode->i_sb; - if ((i_size_read(inode) < - (OCFS2_DIR_REC_LEN(1) + OCFS2_DIR_REC_LEN(2))) || - !(bh = ocfs2_bread(inode, 0, &err, 0))) { - mlog(ML_ERROR, "bad directory (dir #%llu) - no data block\n", + if (!priv.seen_dot || !priv.seen_dot_dot) { + mlog(ML_ERROR, "bad directory (dir #%llu) - no `.' or `..'\n", (unsigned long long)OCFS2_I(inode)->ip_blkno); + /* + * XXX: Is it really safe to allow an unlink to continue? + */ return 1; } - de = (struct ocfs2_dir_entry *) bh->b_data; - de1 = (struct ocfs2_dir_entry *) - ((char *)de + le16_to_cpu(de->rec_len)); - if ((le64_to_cpu(de->inode) != OCFS2_I(inode)->ip_blkno) || - !le64_to_cpu(de1->inode) || - strcmp(".", de->name) || - strcmp("..", de1->name)) { - mlog(ML_ERROR, "bad directory (dir #%llu) - no `.' or `..'\n", - (unsigned long long)OCFS2_I(inode)->ip_blkno); - brelse(bh); - return 1; + return !priv.seen_other; +} + +static void ocfs2_fill_initial_dirents(struct inode *inode, + struct inode *parent, + char *start, unsigned int size) +{ + struct ocfs2_dir_entry *de = (struct ocfs2_dir_entry *)start; + + de->inode = cpu_to_le64(OCFS2_I(inode)->ip_blkno); + de->name_len = 1; + de->rec_len = + cpu_to_le16(OCFS2_DIR_REC_LEN(de->name_len)); + strcpy(de->name, "."); + ocfs2_set_de_type(de, S_IFDIR); + + de = (struct ocfs2_dir_entry *) ((char *)de + le16_to_cpu(de->rec_len)); + de->inode = cpu_to_le64(OCFS2_I(parent)->ip_blkno); + de->rec_len = cpu_to_le16(size - OCFS2_DIR_REC_LEN(1)); + de->name_len = 2; + strcpy(de->name, ".."); + ocfs2_set_de_type(de, S_IFDIR); +} + +/* + * This works together with code in ocfs2_mknod_locked() which sets + * the inline-data flag and initializes the inline-data section. + */ +static int ocfs2_fill_new_dir_id(struct ocfs2_super *osb, + handle_t *handle, + struct inode *parent, + struct inode *inode, + struct buffer_head *di_bh) +{ + int ret; + struct ocfs2_dinode *di = (struct ocfs2_dinode *)di_bh->b_data; + struct ocfs2_inline_data *data = &di->id2.i_data; + unsigned int size = le16_to_cpu(data->id_count); + + ret = ocfs2_journal_access(handle, inode, di_bh, + OCFS2_JOURNAL_ACCESS_WRITE); + if (ret) { + mlog_errno(ret); + goto out; } - offset = le16_to_cpu(de->rec_len) + le16_to_cpu(de1->rec_len); - de = (struct ocfs2_dir_entry *)((char *)de1 + le16_to_cpu(de1->rec_len)); - while (offset < i_size_read(inode) ) { - if (!bh || (void *)de >= (void *)(bh->b_data + sb->s_blocksize)) { - brelse(bh); - bh = ocfs2_bread(inode, - offset >> sb->s_blocksize_bits, &err, 0); - if (!bh) { - mlog(ML_ERROR, "dir %llu has a hole at %lu\n", - (unsigned long long)OCFS2_I(inode)->ip_blkno, offset); - offset += sb->s_blocksize; - continue; - } - de = (struct ocfs2_dir_entry *) bh->b_data; - } - if (!ocfs2_check_dir_entry(inode, de, bh, offset)) { - brelse(bh); - return 1; + + ocfs2_fill_initial_dirents(inode, parent, data->id_data, size); + + ocfs2_journal_dirty(handle, di_bh); + if (ret) { + mlog_errno(ret); + goto out; + } + + i_size_write(inode, size); + inode->i_nlink = 2; + inode->i_blocks = ocfs2_inode_sector_count(inode); + + ret = ocfs2_mark_inode_dirty(handle, inode, di_bh); + if (ret < 0) + mlog_errno(ret); + +out: + return ret; +} + +static int ocfs2_fill_new_dir_el(struct ocfs2_super *osb, + handle_t *handle, + struct inode *parent, + struct inode *inode, + struct buffer_head *fe_bh, + struct ocfs2_alloc_context *data_ac) +{ + int status; + struct buffer_head *new_bh = NULL; + + mlog_entry_void(); + + status = ocfs2_do_extend_dir(osb->sb, handle, inode, fe_bh, + data_ac, NULL, &new_bh); + if (status < 0) { + mlog_errno(status); + goto bail; + } + + ocfs2_set_new_buffer_uptodate(inode, new_bh); + + status = ocfs2_journal_access(handle, inode, new_bh, + OCFS2_JOURNAL_ACCESS_CREATE); + if (status < 0) { + mlog_errno(status); + goto bail; + } + memset(new_bh->b_data, 0, osb->sb->s_blocksize); + + ocfs2_fill_initial_dirents(inode, parent, new_bh->b_data, + osb->sb->s_blocksize); + + status = ocfs2_journal_dirty(handle, new_bh); + if (status < 0) { + mlog_errno(status); + goto bail; + } + + i_size_write(inode, inode->i_sb->s_blocksize); + inode->i_nlink = 2; + inode->i_blocks = ocfs2_inode_sector_count(inode); + status = ocfs2_mark_inode_dirty(handle, inode, fe_bh); + if (status < 0) { + mlog_errno(status); + goto bail; + } + + status = 0; +bail: + if (new_bh) + brelse(new_bh); + + mlog_exit(status); + return status; +} + +int ocfs2_fill_new_dir(struct ocfs2_super *osb, + handle_t *handle, + struct inode *parent, + struct inode *inode, + struct buffer_head *fe_bh, + struct ocfs2_alloc_context *data_ac) +{ + BUG_ON(!ocfs2_supports_inline_data(osb) && data_ac == NULL); + + if (OCFS2_I(inode)->ip_dyn_features & OCFS2_INLINE_DATA_FL) + return ocfs2_fill_new_dir_id(osb, handle, parent, inode, fe_bh); + + return ocfs2_fill_new_dir_el(osb, handle, parent, inode, fe_bh, + data_ac); +} + +static void ocfs2_expand_last_dirent(char *start, unsigned int old_size, + unsigned int new_size) +{ + struct ocfs2_dir_entry *de; + struct ocfs2_dir_entry *prev_de; + char *de_buf, *limit; + unsigned int bytes = new_size - old_size; + + limit = start + old_size; + de_buf = start; + de = (struct ocfs2_dir_entry *)de_buf; + do { + prev_de = de; + de_buf += le16_to_cpu(de->rec_len); + de = (struct ocfs2_dir_entry *)de_buf; + } while (de_buf < limit); + + le16_add_cpu(&prev_de->rec_len, bytes); +} + +/* + * We allocate enough clusters to fulfill "blocks_wanted", but set + * i_size to exactly one block. Ocfs2_extend_dir() will handle the + * rest automatically for us. + * + * *first_block_bh is a pointer to the 1st data block allocated to the + * directory. + */ +static int ocfs2_expand_inline_dir(struct inode *dir, struct buffer_head *di_bh, + unsigned int blocks_wanted, + struct buffer_head **first_block_bh) +{ + int ret, credits = OCFS2_INLINE_TO_EXTENTS_CREDITS; + u32 alloc, bit_off, len; + struct super_block *sb = dir->i_sb; + u64 blkno, bytes = blocks_wanted << sb->s_blocksize_bits; + struct ocfs2_super *osb = OCFS2_SB(dir->i_sb); + struct ocfs2_inode_info *oi = OCFS2_I(dir); + struct ocfs2_alloc_context *data_ac; + struct buffer_head *dirdata_bh = NULL; + struct ocfs2_dinode *di = (struct ocfs2_dinode *)di_bh->b_data; + handle_t *handle; + + alloc = ocfs2_clusters_for_bytes(sb, bytes); + + /* + * We should never need more than 2 clusters for this - + * maximum dirent size is far less than one block. In fact, + * the only time we'd need more than one cluster is if + * blocksize == clustersize and the dirent won't fit in the + * extra space that the expansion to a single block gives. As + * of today, that only happens on 4k/4k file systems. + */ + BUG_ON(alloc > 2); + + ret = ocfs2_reserve_clusters(osb, alloc, &data_ac); + if (ret) { + mlog_errno(ret); + goto out; + } + + down_write(&oi->ip_alloc_sem); + + /* + * Prepare for worst case allocation scenario of two seperate + * extents. + */ + if (alloc == 2) + credits += OCFS2_SUBALLOC_ALLOC; + + handle = ocfs2_start_trans(osb, credits); + if (IS_ERR(handle)) { + ret = PTR_ERR(handle); + mlog_errno(ret); + goto out_sem; + } + + /* + * Try to claim as many clusters as the bitmap can give though + * if we only get one now, that's enough to continue. The rest + * will be claimed after the conversion to extents. + */ + ret = ocfs2_claim_clusters(osb, handle, data_ac, 1, &bit_off, &len); + if (ret) { + mlog_errno(ret); + goto out_commit; + } + + /* + * Operations are carefully ordered so that we set up the new + * data block first. The conversion from inline data to + * extents follows. + */ + blkno = ocfs2_clusters_to_blocks(dir->i_sb, bit_off); + dirdata_bh = sb_getblk(sb, blkno); + if (!dirdata_bh) { + ret = -EIO; + mlog_errno(ret); + goto out_commit; + } + + ocfs2_set_new_buffer_uptodate(dir, dirdata_bh); + + ret = ocfs2_journal_access(handle, dir, dirdata_bh, + OCFS2_JOURNAL_ACCESS_CREATE); + if (ret) { + mlog_errno(ret); + goto out_commit; + } + + memcpy(dirdata_bh->b_data, di->id2.i_data.id_data, i_size_read(dir)); + memset(dirdata_bh->b_data + i_size_read(dir), 0, + sb->s_blocksize - i_size_read(dir)); + ocfs2_expand_last_dirent(dirdata_bh->b_data, i_size_read(dir), + sb->s_blocksize); + + ret = ocfs2_journal_dirty(handle, dirdata_bh); + if (ret) { + mlog_errno(ret); + goto out_commit; + } + + /* + * Set extent, i_size, etc on the directory. After this, the + * inode should contain the same exact dirents as before and + * be fully accessible from system calls. + * + * We let the later dirent insert modify c/mtime - to the user + * the data hasn't changed. + */ + ret = ocfs2_journal_access(handle, dir, di_bh, + OCFS2_JOURNAL_ACCESS_CREATE); + if (ret) { + mlog_errno(ret); + goto out_commit; + } + + spin_lock(&oi->ip_lock); + oi->ip_dyn_features &= ~OCFS2_INLINE_DATA_FL; + di->i_dyn_features = cpu_to_le16(oi->ip_dyn_features); + spin_unlock(&oi->ip_lock); + + ocfs2_dinode_new_extent_list(dir, di); + + i_size_write(dir, sb->s_blocksize); + dir->i_mtime = dir->i_ctime = CURRENT_TIME; + + di->i_size = cpu_to_le64(sb->s_blocksize); + di->i_ctime = di->i_mtime = cpu_to_le64(dir->i_ctime.tv_sec); + di->i_ctime_nsec = di->i_mtime_nsec = cpu_to_le32(dir->i_ctime.tv_nsec); + dir->i_blocks = ocfs2_inode_sector_count(dir); + + /* + * This should never fail as our extent list is empty and all + * related blocks have been journaled already. + */ + ret = ocfs2_insert_extent(osb, handle, dir, di_bh, 0, blkno, len, 0, + NULL); + if (ret) { + mlog_errno(ret); + goto out; + } + + ret = ocfs2_journal_dirty(handle, di_bh); + if (ret) { + mlog_errno(ret); + goto out_commit; + } + + /* + * We asked for two clusters, but only got one in the 1st + * pass. Claim the 2nd cluster as a separate extent. + */ + if (alloc > len) { + ret = ocfs2_claim_clusters(osb, handle, data_ac, 1, &bit_off, + &len); + if (ret) { + mlog_errno(ret); + goto out_commit; } - if (le64_to_cpu(de->inode)) { - brelse(bh); - return 0; + blkno = ocfs2_clusters_to_blocks(dir->i_sb, bit_off); + + ret = ocfs2_insert_extent(osb, handle, dir, di_bh, 1, blkno, + len, 0, NULL); + if (ret) { + mlog_errno(ret); + goto out; } - offset += le16_to_cpu(de->rec_len); - de = (struct ocfs2_dir_entry *) - ((char *)de + le16_to_cpu(de->rec_len)); } - brelse(bh); - return 1; + + *first_block_bh = dirdata_bh; + dirdata_bh = NULL; + +out_commit: + ocfs2_commit_trans(osb, handle); + +out_sem: + up_write(&oi->ip_alloc_sem); + +out: + if (data_ac) + ocfs2_free_alloc_context(data_ac); + + brelse(dirdata_bh); + + return ret; } /* returns a bh of the 1st new block in the allocation. */ -int ocfs2_do_extend_dir(struct super_block *sb, - handle_t *handle, - struct inode *dir, - struct buffer_head *parent_fe_bh, - struct ocfs2_alloc_context *data_ac, - struct ocfs2_alloc_context *meta_ac, - struct buffer_head **new_bh) +static int ocfs2_do_extend_dir(struct super_block *sb, + handle_t *handle, + struct inode *dir, + struct buffer_head *parent_fe_bh, + struct ocfs2_alloc_context *data_ac, + struct ocfs2_alloc_context *meta_ac, + struct buffer_head **new_bh) { int status; int extend; @@ -396,10 +1408,18 @@ bail: return status; } -/* assumes you already have a cluster lock on the directory. */ +/* + * Assumes you already have a cluster lock on the directory. + * + * 'blocks_wanted' is only used if we have an inline directory which + * is to be turned into an extent based one. The size of the dirent to + * insert might be larger than the space gained by growing to just one + * block, so we may have to grow the inode by two blocks in that case. + */ static int ocfs2_extend_dir(struct ocfs2_super *osb, struct inode *dir, struct buffer_head *parent_fe_bh, + unsigned int blocks_wanted, struct buffer_head **new_de_bh) { int status = 0; @@ -415,6 +1435,38 @@ static int ocfs2_extend_dir(struct ocfs2_super *osb, mlog_entry_void(); + if (OCFS2_I(dir)->ip_dyn_features & OCFS2_INLINE_DATA_FL) { + status = ocfs2_expand_inline_dir(dir, parent_fe_bh, + blocks_wanted, &new_bh); + if (status) { + mlog_errno(status); + goto bail; + } + + if (blocks_wanted == 1) { + /* + * If the new dirent will fit inside the space + * created by pushing out to one block, then + * we can complete the operation + * here. Otherwise we have to expand i_size + * and format the 2nd block below. + */ + BUG_ON(new_bh == NULL); + goto bail_bh; + } + + /* + * Get rid of 'new_bh' - we want to format the 2nd + * data block and return that instead. + */ + brelse(new_bh); + new_bh = NULL; + + dir_i_size = i_size_read(dir); + credits = OCFS2_SIMPLE_DIR_EXTEND_CREDITS; + goto do_extend; + } + dir_i_size = i_size_read(dir); mlog(0, "extending dir %llu (i_size = %lld)\n", (unsigned long long)OCFS2_I(dir)->ip_blkno, dir_i_size); @@ -452,6 +1504,7 @@ static int ocfs2_extend_dir(struct ocfs2_super *osb, credits = OCFS2_SIMPLE_DIR_EXTEND_CREDITS; } +do_extend: down_write(&OCFS2_I(dir)->ip_alloc_sem); drop_alloc_sem = 1; @@ -497,6 +1550,7 @@ static int ocfs2_extend_dir(struct ocfs2_super *osb, goto bail; } +bail_bh: *new_de_bh = new_bh; get_bh(*new_de_bh); bail: @@ -517,41 +1571,71 @@ bail: return status; } -/* - * Search the dir for a good spot, extending it if necessary. The - * block containing an appropriate record is returned in ret_de_bh. - */ -int ocfs2_prepare_dir_for_insert(struct ocfs2_super *osb, - struct inode *dir, - struct buffer_head *parent_fe_bh, - const char *name, - int namelen, - struct buffer_head **ret_de_bh) +static int ocfs2_find_dir_space_id(struct inode *dir, struct buffer_head *di_bh, + const char *name, int namelen, + struct buffer_head **ret_de_bh, + unsigned int *blocks_wanted) { - unsigned long offset; - struct buffer_head * bh = NULL; - unsigned short rec_len; - struct ocfs2_dinode *fe; - struct ocfs2_dir_entry *de; - struct super_block *sb; - int status; + int ret; + struct ocfs2_dinode *di = (struct ocfs2_dinode *)di_bh->b_data; + struct ocfs2_dir_entry *de, *last_de = NULL; + char *de_buf, *limit; + unsigned long offset = 0; + unsigned int rec_len, new_rec_len; + + de_buf = di->id2.i_data.id_data; + limit = de_buf + i_size_read(dir); + rec_len = OCFS2_DIR_REC_LEN(namelen); - mlog_entry_void(); + while (de_buf < limit) { + de = (struct ocfs2_dir_entry *)de_buf; - mlog(0, "getting ready to insert namelen %d into dir %llu\n", - namelen, (unsigned long long)OCFS2_I(dir)->ip_blkno); + if (!ocfs2_check_dir_entry(dir, de, di_bh, offset)) { + ret = -ENOENT; + goto out; + } + if (ocfs2_match(namelen, name, de)) { + ret = -EEXIST; + goto out; + } + if (ocfs2_dirent_would_fit(de, rec_len)) { + /* Ok, we found a spot. Return this bh and let + * the caller actually fill it in. */ + *ret_de_bh = di_bh; + get_bh(*ret_de_bh); + ret = 0; + goto out; + } - BUG_ON(!S_ISDIR(dir->i_mode)); - fe = (struct ocfs2_dinode *) parent_fe_bh->b_data; - BUG_ON(le64_to_cpu(fe->i_size) != i_size_read(dir)); + last_de = de; + de_buf += le16_to_cpu(de->rec_len); + offset += le16_to_cpu(de->rec_len); + } - sb = dir->i_sb; + /* + * We're going to require expansion of the directory - figure + * out how many blocks we'll need so that a place for the + * dirent can be found. + */ + *blocks_wanted = 1; + new_rec_len = le16_to_cpu(last_de->rec_len) + (dir->i_sb->s_blocksize - i_size_read(dir)); + if (new_rec_len < (rec_len + OCFS2_DIR_REC_LEN(last_de->name_len))) + *blocks_wanted = 2; + + ret = -ENOSPC; +out: + return ret; +} - if (!namelen) { - status = -EINVAL; - mlog_errno(status); - goto bail; - } +static int ocfs2_find_dir_space_el(struct inode *dir, const char *name, + int namelen, struct buffer_head **ret_de_bh) +{ + unsigned long offset; + struct buffer_head *bh = NULL; + unsigned short rec_len; + struct ocfs2_dir_entry *de; + struct super_block *sb = dir->i_sb; + int status; bh = ocfs2_bread(dir, 0, &status, 0); if (!bh) { @@ -568,17 +1652,11 @@ int ocfs2_prepare_dir_for_insert(struct ocfs2_super *osb, bh = NULL; if (i_size_read(dir) <= offset) { - status = ocfs2_extend_dir(osb, - dir, - parent_fe_bh, - &bh); - if (status < 0) { - mlog_errno(status); - goto bail; - } - BUG_ON(!bh); - *ret_de_bh = bh; - get_bh(*ret_de_bh); + /* + * Caller will have to expand this + * directory. + */ + status = -ENOSPC; goto bail; } bh = ocfs2_bread(dir, @@ -600,10 +1678,7 @@ int ocfs2_prepare_dir_for_insert(struct ocfs2_super *osb, status = -EEXIST; goto bail; } - if (((le64_to_cpu(de->inode) == 0) && - (le16_to_cpu(de->rec_len) >= rec_len)) || - (le16_to_cpu(de->rec_len) >= - (OCFS2_DIR_REC_LEN(de->name_len) + rec_len))) { + if (ocfs2_dirent_would_fit(de, rec_len)) { /* Ok, we found a spot. Return this bh and let * the caller actually fill it in. */ *ret_de_bh = bh; @@ -623,3 +1698,61 @@ bail: mlog_exit(status); return status; } + +int ocfs2_prepare_dir_for_insert(struct ocfs2_super *osb, + struct inode *dir, + struct buffer_head *parent_fe_bh, + const char *name, + int namelen, + struct buffer_head **ret_de_bh) +{ + int ret; + unsigned int blocks_wanted = 1; + struct buffer_head *bh = NULL; + + mlog(0, "getting ready to insert namelen %d into dir %llu\n", + namelen, (unsigned long long)OCFS2_I(dir)->ip_blkno); + + *ret_de_bh = NULL; + + if (!namelen) { + ret = -EINVAL; + mlog_errno(ret); + goto out; + } + + if (OCFS2_I(dir)->ip_dyn_features & OCFS2_INLINE_DATA_FL) { + ret = ocfs2_find_dir_space_id(dir, parent_fe_bh, name, + namelen, &bh, &blocks_wanted); + } else + ret = ocfs2_find_dir_space_el(dir, name, namelen, &bh); + + if (ret && ret != -ENOSPC) { + mlog_errno(ret); + goto out; + } + + if (ret == -ENOSPC) { + /* + * We have to expand the directory to add this name. + */ + BUG_ON(bh); + + ret = ocfs2_extend_dir(osb, dir, parent_fe_bh, blocks_wanted, + &bh); + if (ret) { + if (ret != -ENOSPC) + mlog_errno(ret); + goto out; + } + + BUG_ON(!bh); + } + + *ret_de_bh = bh; + bh = NULL; +out: + if (bh) + brelse(bh); + return ret; +} diff --git a/fs/ocfs2/dir.h b/fs/ocfs2/dir.h index 3f67e146864..ce48b9080d8 100644 --- a/fs/ocfs2/dir.h +++ b/fs/ocfs2/dir.h @@ -26,17 +26,49 @@ #ifndef OCFS2_DIR_H #define OCFS2_DIR_H +struct buffer_head *ocfs2_find_entry(const char *name, + int namelen, + struct inode *dir, + struct ocfs2_dir_entry **res_dir); +int ocfs2_delete_entry(handle_t *handle, + struct inode *dir, + struct ocfs2_dir_entry *de_del, + struct buffer_head *bh); +int __ocfs2_add_entry(handle_t *handle, + struct inode *dir, + const char *name, int namelen, + struct inode *inode, u64 blkno, + struct buffer_head *parent_fe_bh, + struct buffer_head *insert_bh); +static inline int ocfs2_add_entry(handle_t *handle, + struct dentry *dentry, + struct inode *inode, u64 blkno, + struct buffer_head *parent_fe_bh, + struct buffer_head *insert_bh) +{ + return __ocfs2_add_entry(handle, dentry->d_parent->d_inode, + dentry->d_name.name, dentry->d_name.len, + inode, blkno, parent_fe_bh, insert_bh); +} +int ocfs2_update_entry(struct inode *dir, handle_t *handle, + struct buffer_head *de_bh, struct ocfs2_dir_entry *de, + struct inode *new_entry_inode); + int ocfs2_check_dir_for_entry(struct inode *dir, const char *name, int namelen); -int ocfs2_empty_dir(struct inode *inode); /* FIXME: to namei.c */ +int ocfs2_empty_dir(struct inode *inode); int ocfs2_find_files_on_disk(const char *name, int namelen, u64 *blkno, struct inode *inode, struct buffer_head **dirent_bh, struct ocfs2_dir_entry **dirent); +int ocfs2_lookup_ino_from_name(struct inode *dir, const char *name, + int namelen, u64 *blkno); int ocfs2_readdir(struct file *filp, void *dirent, filldir_t filldir); +int ocfs2_dir_foreach(struct inode *inode, loff_t *f_pos, void *priv, + filldir_t filldir); int ocfs2_prepare_dir_for_insert(struct ocfs2_super *osb, struct inode *dir, struct buffer_head *parent_fe_bh, @@ -44,11 +76,11 @@ int ocfs2_prepare_dir_for_insert(struct ocfs2_super *osb, int namelen, struct buffer_head **ret_de_bh); struct ocfs2_alloc_context; -int ocfs2_do_extend_dir(struct super_block *sb, - handle_t *handle, - struct inode *dir, - struct buffer_head *parent_fe_bh, - struct ocfs2_alloc_context *data_ac, - struct ocfs2_alloc_context *meta_ac, - struct buffer_head **new_bh); +int ocfs2_fill_new_dir(struct ocfs2_super *osb, + handle_t *handle, + struct inode *parent, + struct inode *inode, + struct buffer_head *fe_bh, + struct ocfs2_alloc_context *data_ac); + #endif /* OCFS2_DIR_H */ diff --git a/fs/ocfs2/dlmglue.c b/fs/ocfs2/dlmglue.c index f71250ed166..41c76ff2fcf 100644 --- a/fs/ocfs2/dlmglue.c +++ b/fs/ocfs2/dlmglue.c @@ -1482,6 +1482,7 @@ static void __ocfs2_stuff_meta_lvb(struct inode *inode) lvb->lvb_imtime_packed = cpu_to_be64(ocfs2_pack_timespec(&inode->i_mtime)); lvb->lvb_iattr = cpu_to_be32(oi->ip_attr); + lvb->lvb_idynfeatures = cpu_to_be16(oi->ip_dyn_features); lvb->lvb_igeneration = cpu_to_be32(inode->i_generation); out: @@ -1515,6 +1516,7 @@ static void ocfs2_refresh_inode_from_lvb(struct inode *inode) i_size_write(inode, be64_to_cpu(lvb->lvb_isize)); oi->ip_attr = be32_to_cpu(lvb->lvb_iattr); + oi->ip_dyn_features = be16_to_cpu(lvb->lvb_idynfeatures); ocfs2_set_inode_flags(inode); /* fast-symlinks are a special case */ diff --git a/fs/ocfs2/dlmglue.h b/fs/ocfs2/dlmglue.h index 492bad32a8c..87a785e4120 100644 --- a/fs/ocfs2/dlmglue.h +++ b/fs/ocfs2/dlmglue.h @@ -29,12 +29,12 @@ #include "dcache.h" -#define OCFS2_LVB_VERSION 4 +#define OCFS2_LVB_VERSION 5 struct ocfs2_meta_lvb { __u8 lvb_version; __u8 lvb_reserved0; - __be16 lvb_reserved1; + __be16 lvb_idynfeatures; __be32 lvb_iclusters; __be32 lvb_iuid; __be32 lvb_igid; diff --git a/fs/ocfs2/export.c b/fs/ocfs2/export.c index bc48177bd18..c3bbc198f9c 100644 --- a/fs/ocfs2/export.c +++ b/fs/ocfs2/export.c @@ -88,8 +88,6 @@ static struct dentry *ocfs2_get_parent(struct dentry *child) struct dentry *parent; struct inode *inode; struct inode *dir = child->d_inode; - struct buffer_head *dirent_bh = NULL; - struct ocfs2_dir_entry *dirent; mlog_entry("(0x%p, '%.*s')\n", child, child->d_name.len, child->d_name.name); @@ -105,8 +103,7 @@ static struct dentry *ocfs2_get_parent(struct dentry *child) goto bail; } - status = ocfs2_find_files_on_disk("..", 2, &blkno, dir, &dirent_bh, - &dirent); + status = ocfs2_lookup_ino_from_name(dir, "..", 2, &blkno); if (status < 0) { parent = ERR_PTR(-ENOENT); goto bail_unlock; @@ -131,9 +128,6 @@ static struct dentry *ocfs2_get_parent(struct dentry *child) bail_unlock: ocfs2_meta_unlock(dir, 0); - if (dirent_bh) - brelse(dirent_bh); - bail: mlog_exit_ptr(parent); diff --git a/fs/ocfs2/extent_map.c b/fs/ocfs2/extent_map.c index 03c1d365c78..c58668a326f 100644 --- a/fs/ocfs2/extent_map.c +++ b/fs/ocfs2/extent_map.c @@ -387,6 +387,12 @@ int ocfs2_get_clusters(struct inode *inode, u32 v_cluster, struct ocfs2_extent_rec *rec; u32 coff; + if (OCFS2_I(inode)->ip_dyn_features & OCFS2_INLINE_DATA_FL) { + ret = -ERANGE; + mlog_errno(ret); + goto out; + } + ret = ocfs2_extent_map_lookup(inode, v_cluster, p_cluster, num_clusters, extent_flags); if (ret == 0) diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c index f3bc3658e7a..a62b14eb406 100644 --- a/fs/ocfs2/file.c +++ b/fs/ocfs2/file.c @@ -397,6 +397,15 @@ static int ocfs2_truncate_file(struct inode *inode, unmap_mapping_range(inode->i_mapping, new_i_size + PAGE_SIZE - 1, 0, 1); truncate_inode_pages(inode->i_mapping, new_i_size); + if (OCFS2_I(inode)->ip_dyn_features & OCFS2_INLINE_DATA_FL) { + status = ocfs2_truncate_inline(inode, di_bh, new_i_size, + i_size_read(inode), 0); + if (status) + mlog_errno(status); + + goto bail_unlock_data; + } + /* alright, we're going to need to do a full blown alloc size * change. Orphan the inode so that recovery can complete the * truncate if necessary. This does the task of marking @@ -779,25 +788,6 @@ leave: return status; } -static int ocfs2_extend_allocation(struct inode *inode, u32 logical_start, - u32 clusters_to_add, int mark_unwritten) -{ - int ret; - - /* - * The alloc sem blocks peope in read/write from reading our - * allocation until we're done changing it. We depend on - * i_mutex to block other extend/truncate calls while we're - * here. - */ - down_write(&OCFS2_I(inode)->ip_alloc_sem); - ret = __ocfs2_extend_allocation(inode, logical_start, clusters_to_add, - mark_unwritten); - up_write(&OCFS2_I(inode)->ip_alloc_sem); - - return ret; -} - /* Some parts of this taken from generic_cont_expand, which turned out * to be too fragile to do exactly what we need without us having to * worry about recursive locking in ->prepare_write() and @@ -889,25 +879,48 @@ out: return ret; } -/* - * A tail_to_skip value > 0 indicates that we're being called from - * ocfs2_file_aio_write(). This has the following implications: - * - * - we don't want to update i_size - * - di_bh will be NULL, which is fine because it's only used in the - * case where we want to update i_size. - * - ocfs2_zero_extend() will then only be filling the hole created - * between i_size and the start of the write. - */ +int ocfs2_extend_no_holes(struct inode *inode, u64 new_i_size, u64 zero_to) +{ + int ret; + u32 clusters_to_add; + struct ocfs2_inode_info *oi = OCFS2_I(inode); + + clusters_to_add = ocfs2_clusters_for_bytes(inode->i_sb, new_i_size); + if (clusters_to_add < oi->ip_clusters) + clusters_to_add = 0; + else + clusters_to_add -= oi->ip_clusters; + + if (clusters_to_add) { + ret = __ocfs2_extend_allocation(inode, oi->ip_clusters, + clusters_to_add, 0); + if (ret) { + mlog_errno(ret); + goto out; + } + } + + /* + * Call this even if we don't add any clusters to the tree. We + * still need to zero the area between the old i_size and the + * new i_size. + */ + ret = ocfs2_zero_extend(inode, zero_to); + if (ret < 0) + mlog_errno(ret); + +out: + return ret; +} + static int ocfs2_extend_file(struct inode *inode, struct buffer_head *di_bh, - u64 new_i_size, - size_t tail_to_skip) + u64 new_i_size) { - int ret = 0; - u32 clusters_to_add = 0; + int ret = 0, data_locked = 0; + struct ocfs2_inode_info *oi = OCFS2_I(inode); - BUG_ON(!tail_to_skip && !di_bh); + BUG_ON(!di_bh); /* setattr sometimes calls us like this. */ if (new_i_size == 0) @@ -917,13 +930,18 @@ static int ocfs2_extend_file(struct inode *inode, goto out; BUG_ON(new_i_size < i_size_read(inode)); - if (ocfs2_sparse_alloc(OCFS2_SB(inode->i_sb))) { - BUG_ON(tail_to_skip != 0); + /* + * Fall through for converting inline data, even if the fs + * supports sparse files. + * + * The check for inline data here is legal - nobody can add + * the feature since we have i_mutex. We must check it again + * after acquiring ip_alloc_sem though, as paths like mmap + * might have raced us to converting the inode to extents. + */ + if (!(oi->ip_dyn_features & OCFS2_INLINE_DATA_FL) + && ocfs2_sparse_alloc(OCFS2_SB(inode->i_sb))) goto out_update_size; - } - - clusters_to_add = ocfs2_clusters_for_bytes(inode->i_sb, new_i_size) - - OCFS2_I(inode)->ip_clusters; /* * protect the pages that ocfs2_zero_extend is going to be @@ -937,39 +955,52 @@ static int ocfs2_extend_file(struct inode *inode, mlog_errno(ret); goto out; } + data_locked = 1; + + /* + * The alloc sem blocks people in read/write from reading our + * allocation until we're done changing it. We depend on + * i_mutex to block other extend/truncate calls while we're + * here. + */ + down_write(&oi->ip_alloc_sem); + + if (oi->ip_dyn_features & OCFS2_INLINE_DATA_FL) { + /* + * We can optimize small extends by keeping the inodes + * inline data. + */ + if (ocfs2_size_fits_inline_data(di_bh, new_i_size)) { + up_write(&oi->ip_alloc_sem); + goto out_update_size; + } + + ret = ocfs2_convert_inline_data_to_extents(inode, di_bh); + if (ret) { + up_write(&oi->ip_alloc_sem); - if (clusters_to_add) { - ret = ocfs2_extend_allocation(inode, - OCFS2_I(inode)->ip_clusters, - clusters_to_add, 0); - if (ret < 0) { mlog_errno(ret); goto out_unlock; } } - /* - * Call this even if we don't add any clusters to the tree. We - * still need to zero the area between the old i_size and the - * new i_size. - */ - ret = ocfs2_zero_extend(inode, (u64)new_i_size - tail_to_skip); + if (!ocfs2_sparse_alloc(OCFS2_SB(inode->i_sb))) + ret = ocfs2_extend_no_holes(inode, new_i_size, new_i_size); + + up_write(&oi->ip_alloc_sem); + if (ret < 0) { mlog_errno(ret); goto out_unlock; } out_update_size: - if (!tail_to_skip) { - /* We're being called from ocfs2_setattr() which wants - * us to update i_size */ - ret = ocfs2_simple_size_update(inode, di_bh, new_i_size); - if (ret < 0) - mlog_errno(ret); - } + ret = ocfs2_simple_size_update(inode, di_bh, new_i_size); + if (ret < 0) + mlog_errno(ret); out_unlock: - if (!ocfs2_sparse_alloc(OCFS2_SB(inode->i_sb))) + if (data_locked) ocfs2_data_unlock(inode, 1); out: @@ -1035,7 +1066,7 @@ int ocfs2_setattr(struct dentry *dentry, struct iattr *attr) if (i_size_read(inode) > attr->ia_size) status = ocfs2_truncate_file(inode, bh, attr->ia_size); else - status = ocfs2_extend_file(inode, bh, attr->ia_size, 0); + status = ocfs2_extend_file(inode, bh, attr->ia_size); if (status < 0) { if (status != -ENOSPC) mlog_errno(status); @@ -1243,6 +1274,31 @@ static int ocfs2_allocate_unwritten_extents(struct inode *inode, { int ret; u32 cpos, phys_cpos, clusters, alloc_size; + u64 end = start + len; + struct buffer_head *di_bh = NULL; + + if (OCFS2_I(inode)->ip_dyn_features & OCFS2_INLINE_DATA_FL) { + ret = ocfs2_read_block(OCFS2_SB(inode->i_sb), + OCFS2_I(inode)->ip_blkno, &di_bh, + OCFS2_BH_CACHED, inode); + if (ret) { + mlog_errno(ret); + goto out; + } + + /* + * Nothing to do if the requested reservation range + * fits within the inode. + */ + if (ocfs2_size_fits_inline_data(di_bh, end)) + goto out; + + ret = ocfs2_convert_inline_data_to_extents(inode, di_bh); + if (ret) { + mlog_errno(ret); + goto out; + } + } /* * We consider both start and len to be inclusive. @@ -1288,6 +1344,8 @@ next: ret = 0; out: + + brelse(di_bh); return ret; } @@ -1469,6 +1527,14 @@ static int ocfs2_remove_inode_range(struct inode *inode, if (byte_len == 0) return 0; + if (OCFS2_I(inode)->ip_dyn_features & OCFS2_INLINE_DATA_FL) { + ret = ocfs2_truncate_inline(inode, di_bh, byte_start, + byte_start + byte_len, 1); + if (ret) + mlog_errno(ret); + return ret; + } + trunc_start = ocfs2_clusters_for_bytes(osb->sb, byte_start); trunc_len = (byte_start + byte_len) >> osb->s_clustersize_bits; if (trunc_len >= trunc_start) @@ -1713,15 +1779,13 @@ static int ocfs2_prepare_inode_for_write(struct dentry *dentry, int appending, int *direct_io) { - int ret = 0, meta_level = appending; + int ret = 0, meta_level = 0; struct inode *inode = dentry->d_inode; - u32 clusters; - loff_t newsize, saved_pos; + loff_t saved_pos, end; /* - * We sample i_size under a read level meta lock to see if our write - * is extending the file, if it is we back off and get a write level - * meta lock. + * We start with a read level meta lock and only jump to an ex + * if we need to make modifications here. */ for(;;) { ret = ocfs2_meta_lock(inode, NULL, meta_level); @@ -1763,87 +1827,47 @@ static int ocfs2_prepare_inode_for_write(struct dentry *dentry, saved_pos = *ppos; } - if (ocfs2_sparse_alloc(OCFS2_SB(inode->i_sb))) { - loff_t end = saved_pos + count; + end = saved_pos + count; - /* - * Skip the O_DIRECT checks if we don't need - * them. - */ - if (!direct_io || !(*direct_io)) - break; - - /* - * Allowing concurrent direct writes means - * i_size changes wouldn't be synchronized, so - * one node could wind up truncating another - * nodes writes. - */ - if (end > i_size_read(inode)) { - *direct_io = 0; - break; - } - - /* - * We don't fill holes during direct io, so - * check for them here. If any are found, the - * caller will have to retake some cluster - * locks and initiate the io as buffered. - */ - ret = ocfs2_check_range_for_holes(inode, saved_pos, - count); - if (ret == 1) { - *direct_io = 0; - ret = 0; - } else if (ret < 0) - mlog_errno(ret); + /* + * Skip the O_DIRECT checks if we don't need + * them. + */ + if (!direct_io || !(*direct_io)) break; - } /* - * The rest of this loop is concerned with legacy file - * systems which don't support sparse files. + * There's no sane way to do direct writes to an inode + * with inline data. */ - - newsize = count + saved_pos; - - mlog(0, "pos=%lld newsize=%lld cursize=%lld\n", - (long long) saved_pos, (long long) newsize, - (long long) i_size_read(inode)); - - /* No need for a higher level metadata lock if we're - * never going past i_size. */ - if (newsize <= i_size_read(inode)) + if (OCFS2_I(inode)->ip_dyn_features & OCFS2_INLINE_DATA_FL) { + *direct_io = 0; break; - - if (meta_level == 0) { - ocfs2_meta_unlock(inode, meta_level); - meta_level = 1; - continue; } - spin_lock(&OCFS2_I(inode)->ip_lock); - clusters = ocfs2_clusters_for_bytes(inode->i_sb, newsize) - - OCFS2_I(inode)->ip_clusters; - spin_unlock(&OCFS2_I(inode)->ip_lock); - - mlog(0, "Writing at EOF, may need more allocation: " - "i_size = %lld, newsize = %lld, need %u clusters\n", - (long long) i_size_read(inode), (long long) newsize, - clusters); - - /* We only want to continue the rest of this loop if - * our extend will actually require more - * allocation. */ - if (!clusters) + /* + * Allowing concurrent direct writes means + * i_size changes wouldn't be synchronized, so + * one node could wind up truncating another + * nodes writes. + */ + if (end > i_size_read(inode)) { + *direct_io = 0; break; - - ret = ocfs2_extend_file(inode, NULL, newsize, count); - if (ret < 0) { - if (ret != -ENOSPC) - mlog_errno(ret); - goto out_unlock; } + + /* + * We don't fill holes during direct io, so + * check for them here. If any are found, the + * caller will have to retake some cluster + * locks and initiate the io as buffered. + */ + ret = ocfs2_check_range_for_holes(inode, saved_pos, count); + if (ret == 1) { + *direct_io = 0; + ret = 0; + } else if (ret < 0) + mlog_errno(ret); break; } diff --git a/fs/ocfs2/file.h b/fs/ocfs2/file.h index 36fe27f268e..066f14add3a 100644 --- a/fs/ocfs2/file.h +++ b/fs/ocfs2/file.h @@ -47,6 +47,8 @@ int ocfs2_do_extend_allocation(struct ocfs2_super *osb, struct ocfs2_alloc_context *data_ac, struct ocfs2_alloc_context *meta_ac, enum ocfs2_alloc_restarted *reason_ret); +int ocfs2_extend_no_holes(struct inode *inode, u64 new_i_size, + u64 zero_to); int ocfs2_lock_allocators(struct inode *inode, struct ocfs2_dinode *di, u32 clusters_to_add, u32 extents_to_split, struct ocfs2_alloc_context **data_ac, diff --git a/fs/ocfs2/inode.c b/fs/ocfs2/inode.c index c53a6763bbb..1d5e0cb0fda 100644 --- a/fs/ocfs2/inode.c +++ b/fs/ocfs2/inode.c @@ -241,6 +241,7 @@ int ocfs2_populate_inode(struct inode *inode, struct ocfs2_dinode *fe, OCFS2_I(inode)->ip_clusters = le32_to_cpu(fe->i_clusters); OCFS2_I(inode)->ip_attr = le32_to_cpu(fe->i_attr); + OCFS2_I(inode)->ip_dyn_features = le16_to_cpu(fe->i_dyn_features); inode->i_version = 1; inode->i_generation = le32_to_cpu(fe->i_generation); @@ -513,6 +514,10 @@ static int ocfs2_truncate_for_delete(struct ocfs2_super *osb, fe = (struct ocfs2_dinode *) fe_bh->b_data; + /* + * This check will also skip truncate of inodes with inline + * data and fast symlinks. + */ if (fe->i_clusters) { handle = ocfs2_start_trans(osb, OCFS2_INODE_UPDATE_CREDITS); if (IS_ERR(handle)) { @@ -1220,6 +1225,7 @@ int ocfs2_mark_inode_dirty(handle_t *handle, fe->i_clusters = cpu_to_le32(OCFS2_I(inode)->ip_clusters); ocfs2_get_inode_flags(OCFS2_I(inode)); fe->i_attr = cpu_to_le32(OCFS2_I(inode)->ip_attr); + fe->i_dyn_features = cpu_to_le16(OCFS2_I(inode)->ip_dyn_features); spin_unlock(&OCFS2_I(inode)->ip_lock); fe->i_size = cpu_to_le64(i_size_read(inode)); @@ -1257,6 +1263,7 @@ void ocfs2_refresh_inode(struct inode *inode, OCFS2_I(inode)->ip_clusters = le32_to_cpu(fe->i_clusters); OCFS2_I(inode)->ip_attr = le32_to_cpu(fe->i_attr); + OCFS2_I(inode)->ip_dyn_features = le16_to_cpu(fe->i_dyn_features); ocfs2_set_inode_flags(inode); i_size_write(inode, le64_to_cpu(fe->i_size)); inode->i_nlink = le16_to_cpu(fe->i_links_count); diff --git a/fs/ocfs2/inode.h b/fs/ocfs2/inode.h index a41d0817121..70e881c5553 100644 --- a/fs/ocfs2/inode.h +++ b/fs/ocfs2/inode.h @@ -51,6 +51,7 @@ struct ocfs2_inode_info u32 ip_flags; /* see below */ u32 ip_attr; /* inode attributes */ + u16 ip_dyn_features; /* protected by recovery_lock. */ struct inode *ip_next_orphan; diff --git a/fs/ocfs2/journal.c b/fs/ocfs2/journal.c index dbfb20bb27e..f9d01e25298 100644 --- a/fs/ocfs2/journal.c +++ b/fs/ocfs2/journal.c @@ -35,13 +35,13 @@ #include "ocfs2.h" #include "alloc.h" +#include "dir.h" #include "dlmglue.h" #include "extent_map.h" #include "heartbeat.h" #include "inode.h" #include "journal.h" #include "localalloc.h" -#include "namei.h" #include "slot_map.h" #include "super.h" #include "vote.h" @@ -1213,17 +1213,49 @@ bail: return status; } +struct ocfs2_orphan_filldir_priv { + struct inode *head; + struct ocfs2_super *osb; +}; + +static int ocfs2_orphan_filldir(void *priv, const char *name, int name_len, + loff_t pos, u64 ino, unsigned type) +{ + struct ocfs2_orphan_filldir_priv *p = priv; + struct inode *iter; + + if (name_len == 1 && !strncmp(".", name, 1)) + return 0; + if (name_len == 2 && !strncmp("..", name, 2)) + return 0; + + /* Skip bad inodes so that recovery can continue */ + iter = ocfs2_iget(p->osb, ino, + OCFS2_FI_FLAG_ORPHAN_RECOVERY); + if (IS_ERR(iter)) + return 0; + + mlog(0, "queue orphan %llu\n", + (unsigned long long)OCFS2_I(iter)->ip_blkno); + /* No locking is required for the next_orphan queue as there + * is only ever a single process doing orphan recovery. */ + OCFS2_I(iter)->ip_next_orphan = p->head; + p->head = iter; + + return 0; +} + static int ocfs2_queue_orphans(struct ocfs2_super *osb, int slot, struct inode **head) { int status; struct inode *orphan_dir_inode = NULL; - struct inode *iter; - unsigned long offset, blk, local; - struct buffer_head *bh = NULL; - struct ocfs2_dir_entry *de; - struct super_block *sb = osb->sb; + struct ocfs2_orphan_filldir_priv priv; + loff_t pos = 0; + + priv.osb = osb; + priv.head = *head; orphan_dir_inode = ocfs2_get_system_file_inode(osb, ORPHAN_DIR_SYSTEM_INODE, @@ -1241,77 +1273,15 @@ static int ocfs2_queue_orphans(struct ocfs2_super *osb, goto out; } - offset = 0; - iter = NULL; - while(offset < i_size_read(orphan_dir_inode)) { - blk = offset >> sb->s_blocksize_bits; - - bh = ocfs2_bread(orphan_dir_inode, blk, &status, 0); - if (!bh) - status = -EINVAL; - if (status < 0) { - if (bh) - brelse(bh); - mlog_errno(status); - goto out_unlock; - } - - local = 0; - while(offset < i_size_read(orphan_dir_inode) - && local < sb->s_blocksize) { - de = (struct ocfs2_dir_entry *) (bh->b_data + local); - - if (!ocfs2_check_dir_entry(orphan_dir_inode, - de, bh, local)) { - status = -EINVAL; - mlog_errno(status); - brelse(bh); - goto out_unlock; - } - - local += le16_to_cpu(de->rec_len); - offset += le16_to_cpu(de->rec_len); - - /* I guess we silently fail on no inode? */ - if (!le64_to_cpu(de->inode)) - continue; - if (de->file_type > OCFS2_FT_MAX) { - mlog(ML_ERROR, - "block %llu contains invalid de: " - "inode = %llu, rec_len = %u, " - "name_len = %u, file_type = %u, " - "name='%.*s'\n", - (unsigned long long)bh->b_blocknr, - (unsigned long long)le64_to_cpu(de->inode), - le16_to_cpu(de->rec_len), - de->name_len, - de->file_type, - de->name_len, - de->name); - continue; - } - if (de->name_len == 1 && !strncmp(".", de->name, 1)) - continue; - if (de->name_len == 2 && !strncmp("..", de->name, 2)) - continue; - - iter = ocfs2_iget(osb, le64_to_cpu(de->inode), - OCFS2_FI_FLAG_ORPHAN_RECOVERY); - if (IS_ERR(iter)) - continue; - - mlog(0, "queue orphan %llu\n", - (unsigned long long)OCFS2_I(iter)->ip_blkno); - /* No locking is required for the next_orphan - * queue as there is only ever a single - * process doing orphan recovery. */ - OCFS2_I(iter)->ip_next_orphan = *head; - *head = iter; - } - brelse(bh); + status = ocfs2_dir_foreach(orphan_dir_inode, &pos, &priv, + ocfs2_orphan_filldir); + if (status) { + mlog_errno(status); + goto out; } -out_unlock: + *head = priv.head; + ocfs2_meta_unlock(orphan_dir_inode, 0); out: mutex_unlock(&orphan_dir_inode->i_mutex); diff --git a/fs/ocfs2/journal.h b/fs/ocfs2/journal.h index ce60aab013a..4b32e096156 100644 --- a/fs/ocfs2/journal.h +++ b/fs/ocfs2/journal.h @@ -282,6 +282,9 @@ int ocfs2_journal_dirty_data(handle_t *handle, * prev. group desc. if we relink. */ #define OCFS2_SUBALLOC_ALLOC (3) +#define OCFS2_INLINE_TO_EXTENTS_CREDITS (OCFS2_SUBALLOC_ALLOC \ + + OCFS2_INODE_UPDATE_CREDITS) + /* dinode + group descriptor update. We don't relink on free yet. */ #define OCFS2_SUBALLOC_FREE (2) diff --git a/fs/ocfs2/namei.c b/fs/ocfs2/namei.c index 701e6d04ed5..729259016c1 100644 --- a/fs/ocfs2/namei.c +++ b/fs/ocfs2/namei.c @@ -64,29 +64,6 @@ #include "buffer_head_io.h" -#define NAMEI_RA_CHUNKS 2 -#define NAMEI_RA_BLOCKS 4 -#define NAMEI_RA_SIZE (NAMEI_RA_CHUNKS * NAMEI_RA_BLOCKS) -#define NAMEI_RA_INDEX(c,b) (((c) * NAMEI_RA_BLOCKS) + (b)) - -static int inline ocfs2_search_dirblock(struct buffer_head *bh, - struct inode *dir, - const char *name, int namelen, - unsigned long offset, - struct ocfs2_dir_entry **res_dir); - -static int ocfs2_delete_entry(handle_t *handle, - struct inode *dir, - struct ocfs2_dir_entry *de_del, - struct buffer_head *bh); - -static int __ocfs2_add_entry(handle_t *handle, - struct inode *dir, - const char *name, int namelen, - struct inode *inode, u64 blkno, - struct buffer_head *parent_fe_bh, - struct buffer_head *insert_bh); - static int ocfs2_mknod_locked(struct ocfs2_super *osb, struct inode *dir, struct dentry *dentry, int mode, @@ -97,13 +74,6 @@ static int ocfs2_mknod_locked(struct ocfs2_super *osb, struct inode **ret_inode, struct ocfs2_alloc_context *inode_ac); -static int ocfs2_fill_new_dir(struct ocfs2_super *osb, - handle_t *handle, - struct inode *parent, - struct inode *inode, - struct buffer_head *fe_bh, - struct ocfs2_alloc_context *data_ac); - static int ocfs2_prepare_orphan_dir(struct ocfs2_super *osb, struct inode **ret_orphan_dir, struct inode *inode, @@ -123,17 +93,6 @@ static int ocfs2_create_symlink_data(struct ocfs2_super *osb, struct inode *inode, const char *symname); -static inline int ocfs2_add_entry(handle_t *handle, - struct dentry *dentry, - struct inode *inode, u64 blkno, - struct buffer_head *parent_fe_bh, - struct buffer_head *insert_bh) -{ - return __ocfs2_add_entry(handle, dentry->d_parent->d_inode, - dentry->d_name.name, dentry->d_name.len, - inode, blkno, parent_fe_bh, insert_bh); -} - /* An orphan dir name is an 8 byte value, printed as a hex string */ #define OCFS2_ORPHAN_NAMELEN ((int)(2 * sizeof(u64))) @@ -142,10 +101,8 @@ static struct dentry *ocfs2_lookup(struct inode *dir, struct dentry *dentry, { int status; u64 blkno; - struct buffer_head *dirent_bh = NULL; struct inode *inode = NULL; struct dentry *ret; - struct ocfs2_dir_entry *dirent; struct ocfs2_inode_info *oi; mlog_entry("(0x%p, 0x%p, '%.*s')\n", dir, dentry, @@ -167,9 +124,8 @@ static struct dentry *ocfs2_lookup(struct inode *dir, struct dentry *dentry, goto bail; } - status = ocfs2_find_files_on_disk(dentry->d_name.name, - dentry->d_name.len, &blkno, - dir, &dirent_bh, &dirent); + status = ocfs2_lookup_ino_from_name(dir, dentry->d_name.name, + dentry->d_name.len, &blkno); if (status < 0) goto bail_add; @@ -224,83 +180,12 @@ bail_unlock: ocfs2_meta_unlock(dir, 0); bail: - if (dirent_bh) - brelse(dirent_bh); mlog_exit_ptr(ret); return ret; } -static int ocfs2_fill_new_dir(struct ocfs2_super *osb, - handle_t *handle, - struct inode *parent, - struct inode *inode, - struct buffer_head *fe_bh, - struct ocfs2_alloc_context *data_ac) -{ - int status; - struct buffer_head *new_bh = NULL; - struct ocfs2_dir_entry *de = NULL; - - mlog_entry_void(); - - status = ocfs2_do_extend_dir(osb->sb, handle, inode, fe_bh, - data_ac, NULL, &new_bh); - if (status < 0) { - mlog_errno(status); - goto bail; - } - - ocfs2_set_new_buffer_uptodate(inode, new_bh); - - status = ocfs2_journal_access(handle, inode, new_bh, - OCFS2_JOURNAL_ACCESS_CREATE); - if (status < 0) { - mlog_errno(status); - goto bail; - } - memset(new_bh->b_data, 0, osb->sb->s_blocksize); - - de = (struct ocfs2_dir_entry *) new_bh->b_data; - de->inode = cpu_to_le64(OCFS2_I(inode)->ip_blkno); - de->name_len = 1; - de->rec_len = - cpu_to_le16(OCFS2_DIR_REC_LEN(de->name_len)); - strcpy(de->name, "."); - ocfs2_set_de_type(de, S_IFDIR); - de = (struct ocfs2_dir_entry *) ((char *)de + le16_to_cpu(de->rec_len)); - de->inode = cpu_to_le64(OCFS2_I(parent)->ip_blkno); - de->rec_len = cpu_to_le16(inode->i_sb->s_blocksize - - OCFS2_DIR_REC_LEN(1)); - de->name_len = 2; - strcpy(de->name, ".."); - ocfs2_set_de_type(de, S_IFDIR); - - status = ocfs2_journal_dirty(handle, new_bh); - if (status < 0) { - mlog_errno(status); - goto bail; - } - - i_size_write(inode, inode->i_sb->s_blocksize); - inode->i_nlink = 2; - inode->i_blocks = ocfs2_inode_sector_count(inode); - status = ocfs2_mark_inode_dirty(handle, inode, fe_bh); - if (status < 0) { - mlog_errno(status); - goto bail; - } - - status = 0; -bail: - if (new_bh) - brelse(new_bh); - - mlog_exit(status); - return status; -} - static int ocfs2_mknod(struct inode *dir, struct dentry *dentry, int mode, @@ -365,9 +250,8 @@ static int ocfs2_mknod(struct inode *dir, goto leave; } - /* are we making a directory? If so, reserve a cluster for his - * 1st extent. */ - if (S_ISDIR(mode)) { + /* Reserve a cluster if creating an extent based directory. */ + if (S_ISDIR(mode) && !ocfs2_supports_inline_data(osb)) { status = ocfs2_reserve_clusters(osb, 1, &data_ac); if (status < 0) { if (status != -ENOSPC) @@ -564,10 +448,21 @@ static int ocfs2_mknod_locked(struct ocfs2_super *osb, cpu_to_le32(CURRENT_TIME.tv_nsec); fe->i_dtime = 0; - fel = &fe->id2.i_list; - fel->l_tree_depth = 0; - fel->l_next_free_rec = 0; - fel->l_count = cpu_to_le16(ocfs2_extent_recs_per_inode(osb->sb)); + /* + * If supported, directories start with inline data. + */ + if (S_ISDIR(mode) && ocfs2_supports_inline_data(osb)) { + u16 feat = le16_to_cpu(fe->i_dyn_features); + + fe->i_dyn_features = cpu_to_le16(feat | OCFS2_INLINE_DATA_FL); + + fe->id2.i_data.id_count = cpu_to_le16(ocfs2_max_inline_data(osb->sb)); + } else { + fel = &fe->id2.i_list; + fel->l_tree_depth = 0; + fel->l_next_free_rec = 0; + fel->l_count = cpu_to_le16(ocfs2_extent_recs_per_inode(osb->sb)); + } status = ocfs2_journal_dirty(handle, *new_fe_bh); if (status < 0) { @@ -1048,11 +943,6 @@ static void ocfs2_double_unlock(struct inode *inode1, struct inode *inode2) ocfs2_meta_unlock(inode2, 1); } -#define PARENT_INO(buffer) \ - ((struct ocfs2_dir_entry *) \ - ((char *)buffer + \ - le16_to_cpu(((struct ocfs2_dir_entry *)buffer)->rec_len)))->inode - static int ocfs2_rename(struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, @@ -1070,12 +960,12 @@ static int ocfs2_rename(struct inode *old_dir, struct buffer_head *old_inode_bh = NULL; struct buffer_head *insert_entry_bh = NULL; struct ocfs2_super *osb = NULL; - u64 newfe_blkno; + u64 newfe_blkno, old_de_ino; handle_t *handle = NULL; struct buffer_head *old_dir_bh = NULL; struct buffer_head *new_dir_bh = NULL; - struct ocfs2_dir_entry *old_de = NULL, *new_de = NULL; // dirent for old_dentry - // and new_dentry + struct ocfs2_dir_entry *old_inode_dot_dot_de = NULL, *old_de = NULL, + *new_de = NULL; struct buffer_head *new_de_bh = NULL, *old_de_bh = NULL; // bhs for above struct buffer_head *old_inode_de_bh = NULL; // if old_dentry is a dir, // this is the 1st dirent bh @@ -1159,27 +1049,35 @@ static int ocfs2_rename(struct inode *old_dir, } if (S_ISDIR(old_inode->i_mode)) { - status = -EIO; - old_inode_de_bh = ocfs2_bread(old_inode, 0, &status, 0); - if (!old_inode_de_bh) + u64 old_inode_parent; + + status = ocfs2_find_files_on_disk("..", 2, &old_inode_parent, + old_inode, &old_inode_de_bh, + &old_inode_dot_dot_de); + if (status) { + status = -EIO; goto bail; + } - status = -EIO; - if (le64_to_cpu(PARENT_INO(old_inode_de_bh->b_data)) != - OCFS2_I(old_dir)->ip_blkno) + if (old_inode_parent != OCFS2_I(old_dir)->ip_blkno) { + status = -EIO; goto bail; - status = -EMLINK; - if (!new_inode && new_dir!=old_dir && - new_dir->i_nlink >= OCFS2_LINK_MAX) + } + + if (!new_inode && new_dir != old_dir && + new_dir->i_nlink >= OCFS2_LINK_MAX) { + status = -EMLINK; goto bail; + } } - status = -ENOENT; - old_de_bh = ocfs2_find_entry(old_dentry->d_name.name, - old_dentry->d_name.len, - old_dir, &old_de); - if (!old_de_bh) + status = ocfs2_lookup_ino_from_name(old_dir, old_dentry->d_name.name, + old_dentry->d_name.len, + &old_de_ino); + if (status) { + status = -ENOENT; goto bail; + } /* * Check for inode number is _not_ due to possible IO errors. @@ -1187,8 +1085,10 @@ static int ocfs2_rename(struct inode *old_dir, * and merrily kill the link to whatever was created under the * same name. Goodbye sticky bit ;-< */ - if (le64_to_cpu(old_de->inode) != OCFS2_I(old_inode)->ip_blkno) + if (old_de_ino != OCFS2_I(old_inode)->ip_blkno) { + status = -ENOENT; goto bail; + } /* check if the target already exists (in which case we need * to delete it */ @@ -1321,20 +1221,13 @@ static int ocfs2_rename(struct inode *old_dir, } /* change the dirent to point to the correct inode */ - status = ocfs2_journal_access(handle, new_dir, new_de_bh, - OCFS2_JOURNAL_ACCESS_WRITE); + status = ocfs2_update_entry(new_dir, handle, new_de_bh, + new_de, old_inode); if (status < 0) { mlog_errno(status); goto bail; } - new_de->inode = cpu_to_le64(OCFS2_I(old_inode)->ip_blkno); - new_de->file_type = old_de->file_type; new_dir->i_version++; - status = ocfs2_journal_dirty(handle, new_de_bh); - if (status < 0) { - mlog_errno(status); - goto bail; - } if (S_ISDIR(new_inode->i_mode)) newfe->i_links_count = 0; @@ -1370,7 +1263,21 @@ static int ocfs2_rename(struct inode *old_dir, } else mlog_errno(status); - /* now that the name has been added to new_dir, remove the old name */ + /* + * Now that the name has been added to new_dir, remove the old name. + * + * We don't keep any directory entry context around until now + * because the insert might have changed the type of directory + * we're dealing with. + */ + old_de_bh = ocfs2_find_entry(old_dentry->d_name.name, + old_dentry->d_name.len, + old_dir, &old_de); + if (!old_de_bh) { + status = -EIO; + goto bail; + } + status = ocfs2_delete_entry(handle, old_dir, old_de, old_de_bh); if (status < 0) { mlog_errno(status); @@ -1383,12 +1290,8 @@ static int ocfs2_rename(struct inode *old_dir, } old_dir->i_ctime = old_dir->i_mtime = CURRENT_TIME; if (old_inode_de_bh) { - status = ocfs2_journal_access(handle, old_inode, - old_inode_de_bh, - OCFS2_JOURNAL_ACCESS_WRITE); - PARENT_INO(old_inode_de_bh->b_data) = - cpu_to_le64(OCFS2_I(new_dir)->ip_blkno); - status = ocfs2_journal_dirty(handle, old_inode_de_bh); + status = ocfs2_update_entry(old_inode, handle, old_inode_de_bh, + old_inode_dot_dot_de, new_dir); old_dir->i_nlink--; if (new_inode) { new_inode->i_nlink--; @@ -1767,329 +1670,6 @@ bail: return status; } -int ocfs2_check_dir_entry(struct inode * dir, - struct ocfs2_dir_entry * de, - struct buffer_head * bh, - unsigned long offset) -{ - const char *error_msg = NULL; - const int rlen = le16_to_cpu(de->rec_len); - - if (rlen < OCFS2_DIR_REC_LEN(1)) - error_msg = "rec_len is smaller than minimal"; - else if (rlen % 4 != 0) - error_msg = "rec_len % 4 != 0"; - else if (rlen < OCFS2_DIR_REC_LEN(de->name_len)) - error_msg = "rec_len is too small for name_len"; - else if (((char *) de - bh->b_data) + rlen > dir->i_sb->s_blocksize) - error_msg = "directory entry across blocks"; - - if (error_msg != NULL) - mlog(ML_ERROR, "bad entry in directory #%llu: %s - " - "offset=%lu, inode=%llu, rec_len=%d, name_len=%d\n", - (unsigned long long)OCFS2_I(dir)->ip_blkno, error_msg, - offset, (unsigned long long)le64_to_cpu(de->inode), rlen, - de->name_len); - return error_msg == NULL ? 1 : 0; -} - -/* we don't always have a dentry for what we want to add, so people - * like orphan dir can call this instead. - * - * If you pass me insert_bh, I'll skip the search of the other dir - * blocks and put the record in there. - */ -static int __ocfs2_add_entry(handle_t *handle, - struct inode *dir, - const char *name, int namelen, - struct inode *inode, u64 blkno, - struct buffer_head *parent_fe_bh, - struct buffer_head *insert_bh) -{ - unsigned long offset; - unsigned short rec_len; - struct ocfs2_dir_entry *de, *de1; - struct super_block *sb; - int retval, status; - - mlog_entry_void(); - - sb = dir->i_sb; - - if (!namelen) - return -EINVAL; - - rec_len = OCFS2_DIR_REC_LEN(namelen); - offset = 0; - de = (struct ocfs2_dir_entry *) insert_bh->b_data; - while (1) { - BUG_ON((char *)de >= sb->s_blocksize + insert_bh->b_data); - /* These checks should've already been passed by the - * prepare function, but I guess we can leave them - * here anyway. */ - if (!ocfs2_check_dir_entry(dir, de, insert_bh, offset)) { - retval = -ENOENT; - goto bail; - } - if (ocfs2_match(namelen, name, de)) { - retval = -EEXIST; - goto bail; - } - if (((le64_to_cpu(de->inode) == 0) && - (le16_to_cpu(de->rec_len) >= rec_len)) || - (le16_to_cpu(de->rec_len) >= - (OCFS2_DIR_REC_LEN(de->name_len) + rec_len))) { - dir->i_mtime = dir->i_ctime = CURRENT_TIME; - retval = ocfs2_mark_inode_dirty(handle, dir, parent_fe_bh); - if (retval < 0) { - mlog_errno(retval); - goto bail; - } - - status = ocfs2_journal_access(handle, dir, insert_bh, - OCFS2_JOURNAL_ACCESS_WRITE); - /* By now the buffer is marked for journaling */ - offset += le16_to_cpu(de->rec_len); - if (le64_to_cpu(de->inode)) { - de1 = (struct ocfs2_dir_entry *)((char *) de + - OCFS2_DIR_REC_LEN(de->name_len)); - de1->rec_len = - cpu_to_le16(le16_to_cpu(de->rec_len) - - OCFS2_DIR_REC_LEN(de->name_len)); - de->rec_len = cpu_to_le16(OCFS2_DIR_REC_LEN(de->name_len)); - de = de1; - } - de->file_type = OCFS2_FT_UNKNOWN; - if (blkno) { - de->inode = cpu_to_le64(blkno); - ocfs2_set_de_type(de, inode->i_mode); - } else - de->inode = 0; - de->name_len = namelen; - memcpy(de->name, name, namelen); - - dir->i_version++; - status = ocfs2_journal_dirty(handle, insert_bh); - retval = 0; - goto bail; - } - offset += le16_to_cpu(de->rec_len); - de = (struct ocfs2_dir_entry *) ((char *) de + le16_to_cpu(de->rec_len)); - } - - /* when you think about it, the assert above should prevent us - * from ever getting here. */ - retval = -ENOSPC; -bail: - - mlog_exit(retval); - return retval; -} - - -/* - * ocfs2_delete_entry deletes a directory entry by merging it with the - * previous entry - */ -static int ocfs2_delete_entry(handle_t *handle, - struct inode *dir, - struct ocfs2_dir_entry *de_del, - struct buffer_head *bh) -{ - struct ocfs2_dir_entry *de, *pde; - int i, status = -ENOENT; - - mlog_entry("(0x%p, 0x%p, 0x%p, 0x%p)\n", handle, dir, de_del, bh); - - i = 0; - pde = NULL; - de = (struct ocfs2_dir_entry *) bh->b_data; - while (i < bh->b_size) { - if (!ocfs2_check_dir_entry(dir, de, bh, i)) { - status = -EIO; - mlog_errno(status); - goto bail; - } - if (de == de_del) { - status = ocfs2_journal_access(handle, dir, bh, - OCFS2_JOURNAL_ACCESS_WRITE); - if (status < 0) { - status = -EIO; - mlog_errno(status); - goto bail; - } - if (pde) - pde->rec_len = - cpu_to_le16(le16_to_cpu(pde->rec_len) + - le16_to_cpu(de->rec_len)); - else - de->inode = 0; - dir->i_version++; - status = ocfs2_journal_dirty(handle, bh); - goto bail; - } - i += le16_to_cpu(de->rec_len); - pde = de; - de = (struct ocfs2_dir_entry *)((char *)de + le16_to_cpu(de->rec_len)); - } -bail: - mlog_exit(status); - return status; -} - -/* - * Returns 0 if not found, -1 on failure, and 1 on success - */ -static int inline ocfs2_search_dirblock(struct buffer_head *bh, - struct inode *dir, - const char *name, int namelen, - unsigned long offset, - struct ocfs2_dir_entry **res_dir) -{ - struct ocfs2_dir_entry *de; - char *dlimit, *de_buf; - int de_len; - int ret = 0; - - mlog_entry_void(); - - de_buf = bh->b_data; - dlimit = de_buf + dir->i_sb->s_blocksize; - - while (de_buf < dlimit) { - /* this code is executed quadratically often */ - /* do minimal checking `by hand' */ - - de = (struct ocfs2_dir_entry *) de_buf; - - if (de_buf + namelen <= dlimit && - ocfs2_match(namelen, name, de)) { - /* found a match - just to be sure, do a full check */ - if (!ocfs2_check_dir_entry(dir, de, bh, offset)) { - ret = -1; - goto bail; - } - *res_dir = de; - ret = 1; - goto bail; - } - - /* prevent looping on a bad block */ - de_len = le16_to_cpu(de->rec_len); - if (de_len <= 0) { - ret = -1; - goto bail; - } - - de_buf += de_len; - offset += de_len; - } - -bail: - mlog_exit(ret); - return ret; -} - -struct buffer_head *ocfs2_find_entry(const char *name, int namelen, - struct inode *dir, - struct ocfs2_dir_entry **res_dir) -{ - struct super_block *sb; - struct buffer_head *bh_use[NAMEI_RA_SIZE]; - struct buffer_head *bh, *ret = NULL; - unsigned long start, block, b; - int ra_max = 0; /* Number of bh's in the readahead - buffer, bh_use[] */ - int ra_ptr = 0; /* Current index into readahead - buffer */ - int num = 0; - int nblocks, i, err; - - mlog_entry_void(); - - *res_dir = NULL; - sb = dir->i_sb; - - nblocks = i_size_read(dir) >> sb->s_blocksize_bits; - start = OCFS2_I(dir)->ip_dir_start_lookup; - if (start >= nblocks) - start = 0; - block = start; - -restart: - do { - /* - * We deal with the read-ahead logic here. - */ - if (ra_ptr >= ra_max) { - /* Refill the readahead buffer */ - ra_ptr = 0; - b = block; - for (ra_max = 0; ra_max < NAMEI_RA_SIZE; ra_max++) { - /* - * Terminate if we reach the end of the - * directory and must wrap, or if our - * search has finished at this block. - */ - if (b >= nblocks || (num && block == start)) { - bh_use[ra_max] = NULL; - break; - } - num++; - - bh = ocfs2_bread(dir, b++, &err, 1); - bh_use[ra_max] = bh; - } - } - if ((bh = bh_use[ra_ptr++]) == NULL) - goto next; - wait_on_buffer(bh); - if (!buffer_uptodate(bh)) { - /* read error, skip block & hope for the best */ - ocfs2_error(dir->i_sb, "reading directory %llu, " - "offset %lu\n", - (unsigned long long)OCFS2_I(dir)->ip_blkno, - block); - brelse(bh); - goto next; - } - i = ocfs2_search_dirblock(bh, dir, name, namelen, - block << sb->s_blocksize_bits, - res_dir); - if (i == 1) { - OCFS2_I(dir)->ip_dir_start_lookup = block; - ret = bh; - goto cleanup_and_exit; - } else { - brelse(bh); - if (i < 0) - goto cleanup_and_exit; - } - next: - if (++block >= nblocks) - block = 0; - } while (block != start); - - /* - * If the directory has grown while we were searching, then - * search the last part of the directory before giving up. - */ - block = nblocks; - nblocks = i_size_read(dir) >> sb->s_blocksize_bits; - if (block < nblocks) { - start = 0; - goto restart; - } - -cleanup_and_exit: - /* Clean up the read-ahead blocks */ - for (; ra_ptr < ra_max; ra_ptr++) - brelse(bh_use[ra_ptr]); - - mlog_exit_ptr(ret); - return ret; -} - static int ocfs2_blkno_stringify(u64 blkno, char *name) { int status, namelen; diff --git a/fs/ocfs2/namei.h b/fs/ocfs2/namei.h index 0975c7b7212..688aef64c87 100644 --- a/fs/ocfs2/namei.h +++ b/fs/ocfs2/namei.h @@ -30,29 +30,10 @@ extern const struct inode_operations ocfs2_dir_iops; struct dentry *ocfs2_get_parent(struct dentry *child); -int ocfs2_check_dir_entry (struct inode *dir, - struct ocfs2_dir_entry *de, - struct buffer_head *bh, - unsigned long offset); -struct buffer_head *ocfs2_find_entry(const char *name, - int namelen, - struct inode *dir, - struct ocfs2_dir_entry **res_dir); int ocfs2_orphan_del(struct ocfs2_super *osb, handle_t *handle, struct inode *orphan_dir_inode, struct inode *inode, struct buffer_head *orphan_dir_bh); -static inline int ocfs2_match(int len, - const char * const name, - struct ocfs2_dir_entry *de) -{ - if (len != de->name_len) - return 0; - if (!de->inode) - return 0; - return !memcmp(name, de->name, len); -} - #endif /* OCFS2_NAMEI_H */ diff --git a/fs/ocfs2/ocfs2.h b/fs/ocfs2/ocfs2.h index 58307853fb4..60a23e1906b 100644 --- a/fs/ocfs2/ocfs2.h +++ b/fs/ocfs2/ocfs2.h @@ -319,6 +319,13 @@ static inline int ocfs2_writes_unwritten_extents(struct ocfs2_super *osb) return 0; } +static inline int ocfs2_supports_inline_data(struct ocfs2_super *osb) +{ + if (osb->s_feature_incompat & OCFS2_FEATURE_INCOMPAT_INLINE_DATA) + return 1; + return 0; +} + /* set / clear functions because cluster events can make these happen * in parallel so we want the transitions to be atomic. this also * means that any future flags osb_flags must be protected by spinlock diff --git a/fs/ocfs2/ocfs2_fs.h b/fs/ocfs2/ocfs2_fs.h index 82f8a75b207..6ef876759a7 100644 --- a/fs/ocfs2/ocfs2_fs.h +++ b/fs/ocfs2/ocfs2_fs.h @@ -87,7 +87,8 @@ #define OCFS2_FEATURE_COMPAT_SUPP OCFS2_FEATURE_COMPAT_BACKUP_SB #define OCFS2_FEATURE_INCOMPAT_SUPP (OCFS2_FEATURE_INCOMPAT_LOCAL_MOUNT \ - | OCFS2_FEATURE_INCOMPAT_SPARSE_ALLOC) + | OCFS2_FEATURE_INCOMPAT_SPARSE_ALLOC \ + | OCFS2_FEATURE_INCOMPAT_INLINE_DATA) #define OCFS2_FEATURE_RO_COMPAT_SUPP OCFS2_FEATURE_RO_COMPAT_UNWRITTEN /* @@ -111,6 +112,20 @@ #define OCFS2_FEATURE_INCOMPAT_SPARSE_ALLOC 0x0010 /* + * Tunefs sets this incompat flag before starting an operation which + * would require cleanup on abort. This is done to protect users from + * inadvertently mounting the fs after an aborted run without + * fsck-ing. + * + * s_tunefs_flags on the super block describes precisely which + * operations were in progress. + */ +#define OCFS2_FEATURE_INCOMPAT_TUNEFS_INPROG 0x0020 + +/* Support for data packed into inode blocks */ +#define OCFS2_FEATURE_INCOMPAT_INLINE_DATA 0x0040 + +/* * backup superblock flag is used to indicate that this volume * has backup superblocks. */ @@ -130,6 +145,11 @@ #define OCFS2_MAX_BACKUP_SUPERBLOCKS 6 /* + * Flags on ocfs2_super_block.s_tunefs_flags + */ +#define OCFS2_TUNEFS_INPROG_REMOVE_SLOT 0x0001 /* Removing slots */ + +/* * Flags on ocfs2_dinode.i_flags */ #define OCFS2_VALID_FL (0x00000001) /* Inode is valid */ @@ -146,6 +166,17 @@ #define OCFS2_CHAIN_FL (0x00000400) /* Chain allocator */ #define OCFS2_DEALLOC_FL (0x00000800) /* Truncate log */ +/* + * Flags on ocfs2_dinode.i_dyn_features + * + * These can change much more often than i_flags. When adding flags, + * keep in mind that i_dyn_features is only 16 bits wide. + */ +#define OCFS2_INLINE_DATA_FL (0x0001) /* Data stored in inode block */ +#define OCFS2_HAS_XATTR_FL (0x0002) +#define OCFS2_INLINE_XATTR_FL (0x0004) +#define OCFS2_INDEXED_DIR_FL (0x0008) + /* Inode attributes, keep in sync with EXT2 */ #define OCFS2_SECRM_FL (0x00000001) /* Secure deletion */ #define OCFS2_UNRM_FL (0x00000002) /* Undelete */ @@ -447,8 +478,8 @@ struct ocfs2_super_block { __le32 s_clustersize_bits; /* Clustersize for this fs */ /*40*/ __le16 s_max_slots; /* Max number of simultaneous mounts before tunefs required */ - __le16 s_reserved1; - __le32 s_reserved2; + __le16 s_tunefs_flag; + __le32 s_reserved1; __le64 s_first_cluster_group; /* Block offset of 1st cluster * group header */ /*50*/ __u8 s_label[OCFS2_MAX_VOL_LABEL_LEN]; /* Label for mounting, etc. */ @@ -471,6 +502,19 @@ struct ocfs2_local_alloc }; /* + * Data-in-inode header. This is only used if i_dyn_features has + * OCFS2_INLINE_DATA_FL set. + */ +struct ocfs2_inline_data +{ +/*00*/ __le16 id_count; /* Number of bytes that can be used + * for data, starting at id_data */ + __le16 id_reserved0; + __le32 id_reserved1; + __u8 id_data[0]; /* Start of user data */ +}; + +/* * On disk inode for OCFS2 */ struct ocfs2_dinode { @@ -502,7 +546,7 @@ struct ocfs2_dinode { __le32 i_attr; __le16 i_orphaned_slot; /* Only valid when OCFS2_ORPHANED_FL was set in i_flags */ - __le16 i_reserved1; + __le16 i_dyn_features; /*70*/ __le64 i_reserved2[8]; /*B8*/ union { __le64 i_pad1; /* Generic way to refer to this @@ -528,6 +572,7 @@ struct ocfs2_dinode { struct ocfs2_chain_list i_chain; struct ocfs2_extent_list i_list; struct ocfs2_truncate_log i_dealloc; + struct ocfs2_inline_data i_data; __u8 i_symlink[0]; } id2; /* Actual on-disk size is one block */ @@ -577,6 +622,12 @@ static inline int ocfs2_fast_symlink_chars(struct super_block *sb) offsetof(struct ocfs2_dinode, id2.i_symlink); } +static inline int ocfs2_max_inline_data(struct super_block *sb) +{ + return sb->s_blocksize - + offsetof(struct ocfs2_dinode, id2.i_data.id_data); +} + static inline int ocfs2_extent_recs_per_inode(struct super_block *sb) { int size; @@ -656,6 +707,11 @@ static inline int ocfs2_fast_symlink_chars(int blocksize) return blocksize - offsetof(struct ocfs2_dinode, id2.i_symlink); } +static inline int ocfs2_max_inline_data(int blocksize) +{ + return blocksize - offsetof(struct ocfs2_dinode, id2.i_data.id_data); +} + static inline int ocfs2_extent_recs_per_inode(int blocksize) { int size; diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c index c034b5129c1..0e2a1b45bf9 100644 --- a/fs/ocfs2/super.c +++ b/fs/ocfs2/super.c @@ -39,6 +39,7 @@ #include <linux/parser.h> #include <linux/crc32.h> #include <linux/debugfs.h> +#include <linux/mount.h> #include <cluster/nodemanager.h> @@ -91,6 +92,7 @@ struct mount_options static int ocfs2_parse_options(struct super_block *sb, char *options, struct mount_options *mopt, int is_remount); +static int ocfs2_show_options(struct seq_file *s, struct vfsmount *mnt); static void ocfs2_put_super(struct super_block *sb); static int ocfs2_mount_volume(struct super_block *sb); static int ocfs2_remount(struct super_block *sb, int *flags, char *data); @@ -105,7 +107,7 @@ static int ocfs2_sync_fs(struct super_block *sb, int wait); static int ocfs2_init_global_system_inodes(struct ocfs2_super *osb); static int ocfs2_init_local_system_inodes(struct ocfs2_super *osb); -static int ocfs2_release_system_inodes(struct ocfs2_super *osb); +static void ocfs2_release_system_inodes(struct ocfs2_super *osb); static int ocfs2_fill_local_node_info(struct ocfs2_super *osb); static int ocfs2_check_volume(struct ocfs2_super *osb); static int ocfs2_verify_volume(struct ocfs2_dinode *di, @@ -133,6 +135,7 @@ static const struct super_operations ocfs2_sops = { .write_super = ocfs2_write_super, .put_super = ocfs2_put_super, .remount_fs = ocfs2_remount, + .show_options = ocfs2_show_options, }; enum { @@ -177,7 +180,7 @@ static void ocfs2_write_super(struct super_block *sb) static int ocfs2_sync_fs(struct super_block *sb, int wait) { - int status = 0; + int status; tid_t target; struct ocfs2_super *osb = OCFS2_SB(sb); @@ -275,9 +278,9 @@ bail: return status; } -static int ocfs2_release_system_inodes(struct ocfs2_super *osb) +static void ocfs2_release_system_inodes(struct ocfs2_super *osb) { - int status = 0, i; + int i; struct inode *inode; mlog_entry_void(); @@ -302,8 +305,7 @@ static int ocfs2_release_system_inodes(struct ocfs2_super *osb) osb->root_inode = NULL; } - mlog_exit(status); - return status; + mlog_exit(0); } /* We're allocating fs objects, use GFP_NOFS */ @@ -453,7 +455,7 @@ static int ocfs2_sb_probe(struct super_block *sb, struct buffer_head **bh, int *sector_size) { - int status = 0, tmpstat; + int status, tmpstat; struct ocfs1_vol_disk_hdr *hdr; struct ocfs2_dinode *di; int blksize; @@ -830,6 +832,41 @@ bail: return status; } +static int ocfs2_show_options(struct seq_file *s, struct vfsmount *mnt) +{ + struct ocfs2_super *osb = OCFS2_SB(mnt->mnt_sb); + unsigned long opts = osb->s_mount_opt; + + if (opts & OCFS2_MOUNT_HB_LOCAL) + seq_printf(s, ",_netdev,heartbeat=local"); + else + seq_printf(s, ",heartbeat=none"); + + if (opts & OCFS2_MOUNT_NOINTR) + seq_printf(s, ",nointr"); + + if (opts & OCFS2_MOUNT_DATA_WRITEBACK) + seq_printf(s, ",data=writeback"); + else + seq_printf(s, ",data=ordered"); + + if (opts & OCFS2_MOUNT_BARRIER) + seq_printf(s, ",barrier=1"); + + if (opts & OCFS2_MOUNT_ERRORS_PANIC) + seq_printf(s, ",errors=panic"); + else + seq_printf(s, ",errors=remount-ro"); + + if (osb->preferred_slot != OCFS2_INVALID_SLOT) + seq_printf(s, ",preferred_slot=%d", osb->preferred_slot); + + if (osb->s_atime_quantum != OCFS2_DEFAULT_ATIME_QUANTUM) + seq_printf(s, ",atime_quantum=%u", osb->s_atime_quantum); + + return 0; +} + static int __init ocfs2_init(void) { int status; @@ -1209,12 +1246,13 @@ static void ocfs2_dismount_volume(struct super_block *sb, int mnt_err) tmp = ocfs2_request_umount_vote(osb); if (tmp < 0) mlog_errno(tmp); + } - if (osb->slot_num != OCFS2_INVALID_SLOT) - ocfs2_put_slot(osb); + if (osb->slot_num != OCFS2_INVALID_SLOT) + ocfs2_put_slot(osb); + if (osb->dlm) ocfs2_super_unlock(osb, 1); - } ocfs2_release_system_inodes(osb); @@ -1275,7 +1313,7 @@ static int ocfs2_initialize_super(struct super_block *sb, struct buffer_head *bh, int sector_size) { - int status = 0; + int status; int i, cbits, bbits; struct ocfs2_dinode *di = (struct ocfs2_dinode *)bh->b_data; struct inode *inode = NULL; @@ -1596,7 +1634,7 @@ static int ocfs2_verify_volume(struct ocfs2_dinode *di, static int ocfs2_check_volume(struct ocfs2_super *osb) { - int status = 0; + int status; int dirty; int local; struct ocfs2_dinode *local_alloc = NULL; /* only used if we diff --git a/fs/ocfs2/sysfile.c b/fs/ocfs2/sysfile.c index 5df6e35d09b..fd2e846e3e6 100644 --- a/fs/ocfs2/sysfile.c +++ b/fs/ocfs2/sysfile.c @@ -100,17 +100,14 @@ static struct inode * _ocfs2_get_system_file_inode(struct ocfs2_super *osb, char namebuf[40]; struct inode *inode = NULL; u64 blkno; - struct buffer_head *dirent_bh = NULL; - struct ocfs2_dir_entry *de = NULL; int status = 0; ocfs2_sprintf_system_inode_name(namebuf, sizeof(namebuf), type, slot); - status = ocfs2_find_files_on_disk(namebuf, strlen(namebuf), - &blkno, osb->sys_root_inode, - &dirent_bh, &de); + status = ocfs2_lookup_ino_from_name(osb->sys_root_inode, namebuf, + strlen(namebuf), &blkno); if (status < 0) { goto bail; } @@ -122,8 +119,7 @@ static struct inode * _ocfs2_get_system_file_inode(struct ocfs2_super *osb, goto bail; } bail: - if (dirent_bh) - brelse(dirent_bh); + return inode; } |