diff options
Diffstat (limited to 'fs')
56 files changed, 893 insertions, 692 deletions
diff --git a/fs/Kconfig b/fs/Kconfig index 219ec06a8c7..987b5d7cb21 100644 --- a/fs/Kconfig +++ b/fs/Kconfig @@ -1674,6 +1674,8 @@ config NFSD select CRYPTO_MD5 if NFSD_V4 select CRYPTO if NFSD_V4 select FS_POSIX_ACL if NFSD_V4 + select PROC_FS if NFSD_V4 + select PROC_FS if SUNRPC_GSS help If you want your Linux box to act as an NFS *server*, so that other computers on your local network which support NFS can access certain diff --git a/fs/dlm/dir.c b/fs/dlm/dir.c index 46754553fdc..ff97ba92433 100644 --- a/fs/dlm/dir.c +++ b/fs/dlm/dir.c @@ -49,7 +49,7 @@ static struct dlm_direntry *get_free_de(struct dlm_ls *ls, int len) spin_unlock(&ls->ls_recover_list_lock); if (!found) - de = allocate_direntry(ls, len); + de = kzalloc(sizeof(struct dlm_direntry) + len, GFP_KERNEL); return de; } @@ -62,7 +62,7 @@ void dlm_clear_free_entries(struct dlm_ls *ls) de = list_entry(ls->ls_recover_list.next, struct dlm_direntry, list); list_del(&de->list); - free_direntry(de); + kfree(de); } spin_unlock(&ls->ls_recover_list_lock); } @@ -171,7 +171,7 @@ void dlm_dir_remove_entry(struct dlm_ls *ls, int nodeid, char *name, int namelen } list_del(&de->list); - free_direntry(de); + kfree(de); out: write_unlock(&ls->ls_dirtbl[bucket].lock); } @@ -302,7 +302,7 @@ static int get_entry(struct dlm_ls *ls, int nodeid, char *name, write_unlock(&ls->ls_dirtbl[bucket].lock); - de = allocate_direntry(ls, namelen); + de = kzalloc(sizeof(struct dlm_direntry) + namelen, GFP_KERNEL); if (!de) return -ENOMEM; @@ -313,7 +313,7 @@ static int get_entry(struct dlm_ls *ls, int nodeid, char *name, write_lock(&ls->ls_dirtbl[bucket].lock); tmp = search_bucket(ls, name, namelen, bucket); if (tmp) { - free_direntry(de); + kfree(de); de = tmp; } else { list_add_tail(&de->list, &ls->ls_dirtbl[bucket].list); @@ -329,49 +329,47 @@ int dlm_dir_lookup(struct dlm_ls *ls, int nodeid, char *name, int namelen, return get_entry(ls, nodeid, name, namelen, r_nodeid); } -/* Copy the names of master rsb's into the buffer provided. - Only select names whose dir node is the given nodeid. */ +static struct dlm_rsb *find_rsb_root(struct dlm_ls *ls, char *name, int len) +{ + struct dlm_rsb *r; + + down_read(&ls->ls_root_sem); + list_for_each_entry(r, &ls->ls_root_list, res_root_list) { + if (len == r->res_length && !memcmp(name, r->res_name, len)) { + up_read(&ls->ls_root_sem); + return r; + } + } + up_read(&ls->ls_root_sem); + return NULL; +} + +/* Find the rsb where we left off (or start again), then send rsb names + for rsb's we're master of and whose directory node matches the requesting + node. inbuf is the rsb name last sent, inlen is the name's length */ void dlm_copy_master_names(struct dlm_ls *ls, char *inbuf, int inlen, char *outbuf, int outlen, int nodeid) { struct list_head *list; - struct dlm_rsb *start_r = NULL, *r = NULL; - int offset = 0, start_namelen, error, dir_nodeid; - char *start_name; + struct dlm_rsb *r; + int offset = 0, dir_nodeid; uint16_t be_namelen; - /* - * Find the rsb where we left off (or start again) - */ - - start_namelen = inlen; - start_name = inbuf; - - if (start_namelen > 1) { - /* - * We could also use a find_rsb_root() function here that - * searched the ls_root_list. - */ - error = dlm_find_rsb(ls, start_name, start_namelen, R_MASTER, - &start_r); - DLM_ASSERT(!error && start_r, - printk("error %d\n", error);); - DLM_ASSERT(!list_empty(&start_r->res_root_list), - dlm_print_rsb(start_r);); - dlm_put_rsb(start_r); - } - - /* - * Send rsb names for rsb's we're master of and whose directory node - * matches the requesting node. - */ - down_read(&ls->ls_root_sem); - if (start_r) - list = start_r->res_root_list.next; - else + + if (inlen > 1) { + r = find_rsb_root(ls, inbuf, inlen); + if (!r) { + inbuf[inlen - 1] = '\0'; + log_error(ls, "copy_master_names from %d start %d %s", + nodeid, inlen, inbuf); + goto out; + } + list = r->res_root_list.next; + } else { list = ls->ls_root_list.next; + } for (offset = 0; list != &ls->ls_root_list; list = list->next) { r = list_entry(list, struct dlm_rsb, res_root_list); diff --git a/fs/dlm/dlm_internal.h b/fs/dlm/dlm_internal.h index d2fc2384c3b..ec61bbaf25d 100644 --- a/fs/dlm/dlm_internal.h +++ b/fs/dlm/dlm_internal.h @@ -570,5 +570,21 @@ static inline int dlm_no_directory(struct dlm_ls *ls) return (ls->ls_exflags & DLM_LSFL_NODIR) ? 1 : 0; } +int dlm_netlink_init(void); +void dlm_netlink_exit(void); +void dlm_timeout_warn(struct dlm_lkb *lkb); + +#ifdef CONFIG_DLM_DEBUG +int dlm_register_debugfs(void); +void dlm_unregister_debugfs(void); +int dlm_create_debug_file(struct dlm_ls *ls); +void dlm_delete_debug_file(struct dlm_ls *ls); +#else +static inline int dlm_register_debugfs(void) { return 0; } +static inline void dlm_unregister_debugfs(void) { } +static inline int dlm_create_debug_file(struct dlm_ls *ls) { return 0; } +static inline void dlm_delete_debug_file(struct dlm_ls *ls) { } +#endif + #endif /* __DLM_INTERNAL_DOT_H__ */ diff --git a/fs/dlm/lock.c b/fs/dlm/lock.c index 3915b8e1414..ff4a198fa67 100644 --- a/fs/dlm/lock.c +++ b/fs/dlm/lock.c @@ -1,7 +1,7 @@ /****************************************************************************** ******************************************************************************* ** -** Copyright (C) 2005-2007 Red Hat, Inc. All rights reserved. +** Copyright (C) 2005-2008 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 @@ -88,7 +88,6 @@ static void __receive_convert_reply(struct dlm_rsb *r, struct dlm_lkb *lkb, static int receive_extralen(struct dlm_message *ms); static void do_purge(struct dlm_ls *ls, int nodeid, int pid); static void del_timeout(struct dlm_lkb *lkb); -void dlm_timeout_warn(struct dlm_lkb *lkb); /* * Lock compatibilty matrix - thanks Steve @@ -335,7 +334,7 @@ static struct dlm_rsb *create_rsb(struct dlm_ls *ls, char *name, int len) { struct dlm_rsb *r; - r = allocate_rsb(ls, len); + r = dlm_allocate_rsb(ls, len); if (!r) return NULL; @@ -478,7 +477,7 @@ static int find_rsb(struct dlm_ls *ls, char *name, int namelen, error = _search_rsb(ls, name, namelen, bucket, 0, &tmp); if (!error) { write_unlock(&ls->ls_rsbtbl[bucket].lock); - free_rsb(r); + dlm_free_rsb(r); r = tmp; goto out; } @@ -490,12 +489,6 @@ static int find_rsb(struct dlm_ls *ls, char *name, int namelen, return error; } -int dlm_find_rsb(struct dlm_ls *ls, char *name, int namelen, - unsigned int flags, struct dlm_rsb **r_ret) -{ - return find_rsb(ls, name, namelen, flags, r_ret); -} - /* This is only called to add a reference when the code already holds a valid reference to the rsb, so there's no need for locking. */ @@ -519,7 +512,7 @@ static void toss_rsb(struct kref *kref) list_move(&r->res_hashchain, &ls->ls_rsbtbl[r->res_bucket].toss); r->res_toss_time = jiffies; if (r->res_lvbptr) { - free_lvb(r->res_lvbptr); + dlm_free_lvb(r->res_lvbptr); r->res_lvbptr = NULL; } } @@ -589,7 +582,7 @@ static int create_lkb(struct dlm_ls *ls, struct dlm_lkb **lkb_ret) uint32_t lkid = 0; uint16_t bucket; - lkb = allocate_lkb(ls); + lkb = dlm_allocate_lkb(ls); if (!lkb) return -ENOMEM; @@ -683,8 +676,8 @@ static int __put_lkb(struct dlm_ls *ls, struct dlm_lkb *lkb) /* for local/process lkbs, lvbptr points to caller's lksb */ if (lkb->lkb_lvbptr && is_master_copy(lkb)) - free_lvb(lkb->lkb_lvbptr); - free_lkb(lkb); + dlm_free_lvb(lkb->lkb_lvbptr); + dlm_free_lkb(lkb); return 1; } else { write_unlock(&ls->ls_lkbtbl[bucket].lock); @@ -988,7 +981,7 @@ static int shrink_bucket(struct dlm_ls *ls, int b) if (is_master(r)) dir_remove(r); - free_rsb(r); + dlm_free_rsb(r); count++; } else { write_unlock(&ls->ls_rsbtbl[b].lock); @@ -1171,7 +1164,7 @@ static void set_lvb_lock(struct dlm_rsb *r, struct dlm_lkb *lkb) return; if (!r->res_lvbptr) - r->res_lvbptr = allocate_lvb(r->res_ls); + r->res_lvbptr = dlm_allocate_lvb(r->res_ls); if (!r->res_lvbptr) return; @@ -1203,7 +1196,7 @@ static void set_lvb_unlock(struct dlm_rsb *r, struct dlm_lkb *lkb) return; if (!r->res_lvbptr) - r->res_lvbptr = allocate_lvb(r->res_ls); + r->res_lvbptr = dlm_allocate_lvb(r->res_ls); if (!r->res_lvbptr) return; @@ -1852,7 +1845,7 @@ static void send_blocking_asts_all(struct dlm_rsb *r, struct dlm_lkb *lkb) static int set_master(struct dlm_rsb *r, struct dlm_lkb *lkb) { struct dlm_ls *ls = r->res_ls; - int error, dir_nodeid, ret_nodeid, our_nodeid = dlm_our_nodeid(); + int i, error, dir_nodeid, ret_nodeid, our_nodeid = dlm_our_nodeid(); if (rsb_flag(r, RSB_MASTER_UNCERTAIN)) { rsb_clear_flag(r, RSB_MASTER_UNCERTAIN); @@ -1886,7 +1879,7 @@ static int set_master(struct dlm_rsb *r, struct dlm_lkb *lkb) return 1; } - for (;;) { + for (i = 0; i < 2; i++) { /* It's possible for dlm_scand to remove an old rsb for this same resource from the toss list, us to create a new one, look up the master locally, and find it @@ -1900,6 +1893,8 @@ static int set_master(struct dlm_rsb *r, struct dlm_lkb *lkb) log_debug(ls, "dir_lookup error %d %s", error, r->res_name); schedule(); } + if (error && error != -EEXIST) + return error; if (ret_nodeid == our_nodeid) { r->res_first_lkid = 0; @@ -1941,8 +1936,11 @@ static void confirm_master(struct dlm_rsb *r, int error) break; case -EAGAIN: - /* the remote master didn't queue our NOQUEUE request; - make a waiting lkb the first_lkid */ + case -EBADR: + case -ENOTBLK: + /* the remote request failed and won't be retried (it was + a NOQUEUE, or has been canceled/unlocked); make a waiting + lkb the first_lkid */ r->res_first_lkid = 0; @@ -2108,17 +2106,18 @@ static int validate_unlock_args(struct dlm_lkb *lkb, struct dlm_args *args) /* an lkb may be waiting for an rsb lookup to complete where the lookup was initiated by another lock */ - if (args->flags & (DLM_LKF_CANCEL | DLM_LKF_FORCEUNLOCK)) { - if (!list_empty(&lkb->lkb_rsb_lookup)) { + if (!list_empty(&lkb->lkb_rsb_lookup)) { + if (args->flags & (DLM_LKF_CANCEL | DLM_LKF_FORCEUNLOCK)) { log_debug(ls, "unlock on rsb_lookup %x", lkb->lkb_id); list_del_init(&lkb->lkb_rsb_lookup); queue_cast(lkb->lkb_resource, lkb, args->flags & DLM_LKF_CANCEL ? -DLM_ECANCEL : -DLM_EUNLOCK); unhold_lkb(lkb); /* undoes create_lkb() */ - rv = -EBUSY; - goto out; } + /* caller changes -EBUSY to 0 for CANCEL and FORCEUNLOCK */ + rv = -EBUSY; + goto out; } /* cancel not allowed with another cancel/unlock in progress */ @@ -2986,7 +2985,7 @@ static int receive_lvb(struct dlm_ls *ls, struct dlm_lkb *lkb, if (lkb->lkb_exflags & DLM_LKF_VALBLK) { if (!lkb->lkb_lvbptr) - lkb->lkb_lvbptr = allocate_lvb(ls); + lkb->lkb_lvbptr = dlm_allocate_lvb(ls); if (!lkb->lkb_lvbptr) return -ENOMEM; len = receive_extralen(ms); @@ -3006,11 +3005,9 @@ static int receive_request_args(struct dlm_ls *ls, struct dlm_lkb *lkb, lkb->lkb_bastaddr = (void *) (long) (ms->m_asts & AST_BAST); lkb->lkb_astaddr = (void *) (long) (ms->m_asts & AST_COMP); - DLM_ASSERT(is_master_copy(lkb), dlm_print_lkb(lkb);); - if (lkb->lkb_exflags & DLM_LKF_VALBLK) { /* lkb was just created so there won't be an lvb yet */ - lkb->lkb_lvbptr = allocate_lvb(ls); + lkb->lkb_lvbptr = dlm_allocate_lvb(ls); if (!lkb->lkb_lvbptr) return -ENOMEM; } @@ -3021,16 +3018,6 @@ static int receive_request_args(struct dlm_ls *ls, struct dlm_lkb *lkb, static int receive_convert_args(struct dlm_ls *ls, struct dlm_lkb *lkb, struct dlm_message *ms) { - if (lkb->lkb_nodeid != ms->m_header.h_nodeid) { - log_error(ls, "convert_args nodeid %d %d lkid %x %x", - lkb->lkb_nodeid, ms->m_header.h_nodeid, - lkb->lkb_id, lkb->lkb_remid); - return -EINVAL; - } - - if (!is_master_copy(lkb)) - return -EINVAL; - if (lkb->lkb_status != DLM_LKSTS_GRANTED) return -EBUSY; @@ -3046,8 +3033,6 @@ static int receive_convert_args(struct dlm_ls *ls, struct dlm_lkb *lkb, static int receive_unlock_args(struct dlm_ls *ls, struct dlm_lkb *lkb, struct dlm_message *ms) { - if (!is_master_copy(lkb)) - return -EINVAL; if (receive_lvb(ls, lkb, ms)) return -ENOMEM; return 0; @@ -3063,6 +3048,50 @@ static void setup_stub_lkb(struct dlm_ls *ls, struct dlm_message *ms) lkb->lkb_remid = ms->m_lkid; } +/* This is called after the rsb is locked so that we can safely inspect + fields in the lkb. */ + +static int validate_message(struct dlm_lkb *lkb, struct dlm_message *ms) +{ + int from = ms->m_header.h_nodeid; + int error = 0; + + switch (ms->m_type) { + case DLM_MSG_CONVERT: + case DLM_MSG_UNLOCK: + case DLM_MSG_CANCEL: + if (!is_master_copy(lkb) || lkb->lkb_nodeid != from) + error = -EINVAL; + break; + + case DLM_MSG_CONVERT_REPLY: + case DLM_MSG_UNLOCK_REPLY: + case DLM_MSG_CANCEL_REPLY: + case DLM_MSG_GRANT: + case DLM_MSG_BAST: + if (!is_process_copy(lkb) || lkb->lkb_nodeid != from) + error = -EINVAL; + break; + + case DLM_MSG_REQUEST_REPLY: + if (!is_process_copy(lkb)) + error = -EINVAL; + else if (lkb->lkb_nodeid != -1 && lkb->lkb_nodeid != from) + error = -EINVAL; + break; + + default: + error = -EINVAL; + } + + if (error) + log_error(lkb->lkb_resource->res_ls, + "ignore invalid message %d from %d %x %x %x %d", + ms->m_type, from, lkb->lkb_id, lkb->lkb_remid, + lkb->lkb_flags, lkb->lkb_nodeid); + return error; +} + static void receive_request(struct dlm_ls *ls, struct dlm_message *ms) { struct dlm_lkb *lkb; @@ -3124,17 +3153,21 @@ static void receive_convert(struct dlm_ls *ls, struct dlm_message *ms) hold_rsb(r); lock_rsb(r); + error = validate_message(lkb, ms); + if (error) + goto out; + receive_flags(lkb, ms); error = receive_convert_args(ls, lkb, ms); if (error) - goto out; + goto out_reply; reply = !down_conversion(lkb); error = do_convert(r, lkb); - out: + out_reply: if (reply) send_convert_reply(r, lkb, error); - + out: unlock_rsb(r); put_rsb(r); dlm_put_lkb(lkb); @@ -3160,15 +3193,19 @@ static void receive_unlock(struct dlm_ls *ls, struct dlm_message *ms) hold_rsb(r); lock_rsb(r); + error = validate_message(lkb, ms); + if (error) + goto out; + receive_flags(lkb, ms); error = receive_unlock_args(ls, lkb, ms); if (error) - goto out; + goto out_reply; error = do_unlock(r, lkb); - out: + out_reply: send_unlock_reply(r, lkb, error); - + out: unlock_rsb(r); put_rsb(r); dlm_put_lkb(lkb); @@ -3196,9 +3233,13 @@ static void receive_cancel(struct dlm_ls *ls, struct dlm_message *ms) hold_rsb(r); lock_rsb(r); + error = validate_message(lkb, ms); + if (error) + goto out; + error = do_cancel(r, lkb); send_cancel_reply(r, lkb, error); - + out: unlock_rsb(r); put_rsb(r); dlm_put_lkb(lkb); @@ -3217,22 +3258,26 @@ static void receive_grant(struct dlm_ls *ls, struct dlm_message *ms) error = find_lkb(ls, ms->m_remid, &lkb); if (error) { - log_error(ls, "receive_grant no lkb"); + log_debug(ls, "receive_grant from %d no lkb %x", + ms->m_header.h_nodeid, ms->m_remid); return; } - DLM_ASSERT(is_process_copy(lkb), dlm_print_lkb(lkb);); r = lkb->lkb_resource; hold_rsb(r); lock_rsb(r); + error = validate_message(lkb, ms); + if (error) + goto out; + receive_flags_reply(lkb, ms); if (is_altmode(lkb)) munge_altmode(lkb, ms); grant_lock_pc(r, lkb, ms); queue_cast(r, lkb, 0); - + out: unlock_rsb(r); put_rsb(r); dlm_put_lkb(lkb); @@ -3246,18 +3291,22 @@ static void receive_bast(struct dlm_ls *ls, struct dlm_message *ms) error = find_lkb(ls, ms->m_remid, &lkb); if (error) { - log_error(ls, "receive_bast no lkb"); + log_debug(ls, "receive_bast from %d no lkb %x", + ms->m_header.h_nodeid, ms->m_remid); return; } - DLM_ASSERT(is_process_copy(lkb), dlm_print_lkb(lkb);); r = lkb->lkb_resource; hold_rsb(r); lock_rsb(r); - queue_bast(r, lkb, ms->m_bastmode); + error = validate_message(lkb, ms); + if (error) + goto out; + queue_bast(r, lkb, ms->m_bastmode); + out: unlock_rsb(r); put_rsb(r); dlm_put_lkb(lkb); @@ -3323,15 +3372,19 @@ static void receive_request_reply(struct dlm_ls *ls, struct dlm_message *ms) error = find_lkb(ls, ms->m_remid, &lkb); if (error) { - log_error(ls, "receive_request_reply no lkb"); + log_debug(ls, "receive_request_reply from %d no lkb %x", + ms->m_header.h_nodeid, ms->m_remid); return; } - DLM_ASSERT(is_process_copy(lkb), dlm_print_lkb(lkb);); r = lkb->lkb_resource; hold_rsb(r); lock_rsb(r); + error = validate_message(lkb, ms); + if (error) + goto out; + mstype = lkb->lkb_wait_type; error = remove_from_waiters(lkb, DLM_MSG_REQUEST_REPLY); if (error) @@ -3383,6 +3436,7 @@ static void receive_request_reply(struct dlm_ls *ls, struct dlm_message *ms) if (is_overlap(lkb)) { /* we'll ignore error in cancel/unlock reply */ queue_cast_overlap(r, lkb); + confirm_master(r, result); unhold_lkb(lkb); /* undoes create_lkb() */ } else _request_lock(r, lkb); @@ -3463,6 +3517,10 @@ static void _receive_convert_reply(struct dlm_lkb *lkb, struct dlm_message *ms) hold_rsb(r); lock_rsb(r); + error = validate_message(lkb, ms); + if (error) + goto out; + /* stub reply can happen with waiters_mutex held */ error = remove_from_waiters_ms(lkb, ms); if (error) @@ -3481,10 +3539,10 @@ static void receive_convert_reply(struct dlm_ls *ls, struct dlm_message *ms) error = find_lkb(ls, ms->m_remid, &lkb); if (error) { - log_error(ls, "receive_convert_reply no lkb"); + log_debug(ls, "receive_convert_reply from %d no lkb %x", + ms->m_header.h_nodeid, ms->m_remid); return; } - DLM_ASSERT(is_process_copy(lkb), dlm_print_lkb(lkb);); _receive_convert_reply(lkb, ms); dlm_put_lkb(lkb); @@ -3498,6 +3556,10 @@ static void _receive_unlock_reply(struct dlm_lkb *lkb, struct dlm_message *ms) hold_rsb(r); lock_rsb(r); + error = validate_message(lkb, ms); + if (error) + goto out; + /* stub reply can happen with waiters_mutex held */ error = remove_from_waiters_ms(lkb, ms); if (error) @@ -3529,10 +3591,10 @@ static void receive_unlock_reply(struct dlm_ls *ls, struct dlm_message *ms) error = find_lkb(ls, ms->m_remid, &lkb); if (error) { - log_error(ls, "receive_unlock_reply no lkb"); + log_debug(ls, "receive_unlock_reply from %d no lkb %x", + ms->m_header.h_nodeid, ms->m_remid); return; } - DLM_ASSERT(is_process_copy(lkb), dlm_print_lkb(lkb);); _receive_unlock_reply(lkb, ms); dlm_put_lkb(lkb); @@ -3546,6 +3608,10 @@ static void _receive_cancel_reply(struct dlm_lkb *lkb, struct dlm_message *ms) hold_rsb(r); lock_rsb(r); + error = validate_message(lkb, ms); + if (error) + goto out; + /* stub reply can happen with waiters_mutex held */ error = remove_from_waiters_ms(lkb, ms); if (error) @@ -3577,10 +3643,10 @@ static void receive_cancel_reply(struct dlm_ls *ls, struct dlm_message *ms) error = find_lkb(ls, ms->m_remid, &lkb); if (error) { - log_error(ls, "receive_cancel_reply no lkb"); + log_debug(ls, "receive_cancel_reply from %d no lkb %x", + ms->m_header.h_nodeid, ms->m_remid); return; } - DLM_ASSERT(is_process_copy(lkb), dlm_print_lkb(lkb);); _receive_cancel_reply(lkb, ms); dlm_put_lkb(lkb); @@ -3640,6 +3706,13 @@ static void receive_lookup_reply(struct dlm_ls *ls, struct dlm_message *ms) static void _receive_message(struct dlm_ls *ls, struct dlm_message *ms) { + if (!dlm_is_member(ls, ms->m_header.h_nodeid)) { + log_debug(ls, "ignore non-member message %d from %d %x %x %d", + ms->m_type, ms->m_header.h_nodeid, ms->m_lkid, + ms->m_remid, ms->m_result); + return; + } + switch (ms->m_type) { /* messages sent to a master node */ @@ -3778,8 +3851,9 @@ void dlm_receive_buffer(struct dlm_header *hd, int nodeid) 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 (dlm_config.ci_log_debug) + log_print("invalid 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); @@ -3806,6 +3880,7 @@ static void recover_convert_waiter(struct dlm_ls *ls, struct dlm_lkb *lkb) ls->ls_stub_ms.m_type = DLM_MSG_CONVERT_REPLY; ls->ls_stub_ms.m_result = -EINPROGRESS; ls->ls_stub_ms.m_flags = lkb->lkb_flags; + ls->ls_stub_ms.m_header.h_nodeid = lkb->lkb_nodeid; _receive_convert_reply(lkb, &ls->ls_stub_ms); /* Same special case as in receive_rcom_lock_args() */ @@ -3847,6 +3922,7 @@ static int waiter_needs_recovery(struct dlm_ls *ls, struct dlm_lkb *lkb) void dlm_recover_waiters_pre(struct dlm_ls *ls) { struct dlm_lkb *lkb, *safe; + int wait_type, stub_unlock_result, stub_cancel_result; mutex_lock(&ls->ls_waiters_mutex); @@ -3865,7 +3941,33 @@ void dlm_recover_waiters_pre(struct dlm_ls *ls) if (!waiter_needs_recovery(ls, lkb)) continue; - switch (lkb->lkb_wait_type) { + wait_type = lkb->lkb_wait_type; + stub_unlock_result = -DLM_EUNLOCK; + stub_cancel_result = -DLM_ECANCEL; + + /* Main reply may have been received leaving a zero wait_type, + but a reply for the overlapping op may not have been + received. In that case we need to fake the appropriate + reply for the overlap op. */ + + if (!wait_type) { + if (is_overlap_cancel(lkb)) { + wait_type = DLM_MSG_CANCEL; + if (lkb->lkb_grmode == DLM_LOCK_IV) + stub_cancel_result = 0; + } + if (is_overlap_unlock(lkb)) { + wait_type = DLM_MSG_UNLOCK; + if (lkb->lkb_grmode == DLM_LOCK_IV) + stub_unlock_result = -ENOENT; + } + + log_debug(ls, "rwpre overlap %x %x %d %d %d", + lkb->lkb_id, lkb->lkb_flags, wait_type, + stub_cancel_result, stub_unlock_result); + } + + switch (wait_type) { case DLM_MSG_REQUEST: lkb->lkb_flags |= DLM_IFL_RESEND; @@ -3878,8 +3980,9 @@ void dlm_recover_waiters_pre(struct dlm_ls *ls) case DLM_MSG_UNLOCK: hold_lkb(lkb); ls->ls_stub_ms.m_type = DLM_MSG_UNLOCK_REPLY; - ls->ls_stub_ms.m_result = -DLM_EUNLOCK; + ls->ls_stub_ms.m_result = stub_unlock_result; ls->ls_stub_ms.m_flags = lkb->lkb_flags; + ls->ls_stub_ms.m_header.h_nodeid = lkb->lkb_nodeid; _receive_unlock_reply(lkb, &ls->ls_stub_ms); dlm_put_lkb(lkb); break; @@ -3887,15 +3990,16 @@ void dlm_recover_waiters_pre(struct dlm_ls *ls) case DLM_MSG_CANCEL: hold_lkb(lkb); ls->ls_stub_ms.m_type = DLM_MSG_CANCEL_REPLY; - ls->ls_stub_ms.m_result = -DLM_ECANCEL; + ls->ls_stub_ms.m_result = stub_cancel_result; ls->ls_stub_ms.m_flags = lkb->lkb_flags; + ls->ls_stub_ms.m_header.h_nodeid = lkb->lkb_nodeid; _receive_cancel_reply(lkb, &ls->ls_stub_ms); dlm_put_lkb(lkb); break; default: - log_error(ls, "invalid lkb wait_type %d", - lkb->lkb_wait_type); + log_error(ls, "invalid lkb wait_type %d %d", + lkb->lkb_wait_type, wait_type); } schedule(); } @@ -4184,7 +4288,7 @@ static int receive_rcom_lock_args(struct dlm_ls *ls, struct dlm_lkb *lkb, lkb->lkb_astaddr = (void *) (long) (rl->rl_asts & AST_COMP); if (lkb->lkb_exflags & DLM_LKF_VALBLK) { - lkb->lkb_lvbptr = allocate_lvb(ls); + lkb->lkb_lvbptr = dlm_allocate_lvb(ls); if (!lkb->lkb_lvbptr) return -ENOMEM; lvblen = rc->rc_header.h_length - sizeof(struct dlm_rcom) - @@ -4259,7 +4363,7 @@ int dlm_recover_master_copy(struct dlm_ls *ls, struct dlm_rcom *rc) put_rsb(r); out: if (error) - log_print("recover_master_copy %d %x", error, rl->rl_lkid); + log_debug(ls, "recover_master_copy %d %x", error, rl->rl_lkid); rl->rl_result = error; return error; } @@ -4342,7 +4446,7 @@ int dlm_user_request(struct dlm_ls *ls, struct dlm_user_args *ua, } } - /* After ua is attached to lkb it will be freed by free_lkb(). + /* After ua is attached to lkb it will be freed by dlm_free_lkb(). When DLM_IFL_USER is set, the dlm knows that this is a userspace lock and that lkb_astparam is the dlm_user_args structure. */ @@ -4679,6 +4783,7 @@ void dlm_clear_proc_locks(struct dlm_ls *ls, struct dlm_user_proc *proc) } list_for_each_entry_safe(lkb, safe, &proc->asts, lkb_astqueue) { + lkb->lkb_ast_type = 0; list_del(&lkb->lkb_astqueue); dlm_put_lkb(lkb); } diff --git a/fs/dlm/lock.h b/fs/dlm/lock.h index ada04680a1e..27b6ed30291 100644 --- a/fs/dlm/lock.h +++ b/fs/dlm/lock.h @@ -19,8 +19,6 @@ void dlm_print_lkb(struct dlm_lkb *lkb); 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); void dlm_put_rsb(struct dlm_rsb *r); void dlm_hold_rsb(struct dlm_rsb *r); int dlm_put_lkb(struct dlm_lkb *lkb); diff --git a/fs/dlm/lockspace.c b/fs/dlm/lockspace.c index 5c108c49cb8..b180fdc5108 100644 --- a/fs/dlm/lockspace.c +++ b/fs/dlm/lockspace.c @@ -24,14 +24,6 @@ #include "recover.h" #include "requestqueue.h" -#ifdef CONFIG_DLM_DEBUG -int dlm_create_debug_file(struct dlm_ls *ls); -void dlm_delete_debug_file(struct dlm_ls *ls); -#else -static inline int dlm_create_debug_file(struct dlm_ls *ls) { return 0; } -static inline void dlm_delete_debug_file(struct dlm_ls *ls) { } -#endif - static int ls_count; static struct mutex ls_lock; static struct list_head lslist; @@ -684,9 +676,9 @@ static int release_lockspace(struct dlm_ls *ls, int force) dlm_del_ast(lkb); if (lkb->lkb_lvbptr && lkb->lkb_flags & DLM_IFL_MSTCPY) - free_lvb(lkb->lkb_lvbptr); + dlm_free_lvb(lkb->lkb_lvbptr); - free_lkb(lkb); + dlm_free_lkb(lkb); } } dlm_astd_resume(); @@ -704,7 +696,7 @@ static int release_lockspace(struct dlm_ls *ls, int force) res_hashchain); list_del(&rsb->res_hashchain); - free_rsb(rsb); + dlm_free_rsb(rsb); } head = &ls->ls_rsbtbl[i].toss; @@ -712,7 +704,7 @@ static int release_lockspace(struct dlm_ls *ls, int force) rsb = list_entry(head->next, struct dlm_rsb, res_hashchain); list_del(&rsb->res_hashchain); - free_rsb(rsb); + dlm_free_rsb(rsb); } } diff --git a/fs/dlm/lowcomms.c b/fs/dlm/lowcomms.c index e9923ca9c2d..7c1e5e5cccd 100644 --- a/fs/dlm/lowcomms.c +++ b/fs/dlm/lowcomms.c @@ -864,7 +864,7 @@ static void sctp_init_assoc(struct connection *con) static void tcp_connect_to_sock(struct connection *con) { int result = -EHOSTUNREACH; - struct sockaddr_storage saddr; + struct sockaddr_storage saddr, src_addr; int addr_len; struct socket *sock; @@ -898,6 +898,17 @@ static void tcp_connect_to_sock(struct connection *con) con->connect_action = tcp_connect_to_sock; add_sock(sock, con); + /* Bind to our cluster-known address connecting to avoid + routing problems */ + memcpy(&src_addr, dlm_local_addr[0], sizeof(src_addr)); + make_sockaddr(&src_addr, 0, &addr_len); + result = sock->ops->bind(sock, (struct sockaddr *) &src_addr, + addr_len); + if (result < 0) { + log_print("could not bind for connect: %d", result); + /* This *may* not indicate a critical error */ + } + make_sockaddr(&saddr, dlm_config.ci_tcp_port, &addr_len); log_print("connecting to %d", con->nodeid); @@ -1426,6 +1437,8 @@ void dlm_lowcomms_stop(void) con = __nodeid2con(i, 0); if (con) { close_connection(con, true); + if (con->othercon) + kmem_cache_free(con_cache, con->othercon); kmem_cache_free(con_cache, con); } } diff --git a/fs/dlm/main.c b/fs/dlm/main.c index eca2907f238..58487fb95a4 100644 --- a/fs/dlm/main.c +++ b/fs/dlm/main.c @@ -18,16 +18,6 @@ #include "memory.h" #include "config.h" -#ifdef CONFIG_DLM_DEBUG -int dlm_register_debugfs(void); -void dlm_unregister_debugfs(void); -#else -static inline int dlm_register_debugfs(void) { return 0; } -static inline void dlm_unregister_debugfs(void) { } -#endif -int dlm_netlink_init(void); -void dlm_netlink_exit(void); - static int __init init_dlm(void) { int error; diff --git a/fs/dlm/member.c b/fs/dlm/member.c index e9cdcab306e..fa17f5a2788 100644 --- a/fs/dlm/member.c +++ b/fs/dlm/member.c @@ -1,7 +1,7 @@ /****************************************************************************** ******************************************************************************* ** -** Copyright (C) 2005-2007 Red Hat, Inc. All rights reserved. +** Copyright (C) 2005-2008 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 @@ -70,7 +70,7 @@ static void dlm_remove_member(struct dlm_ls *ls, struct dlm_member *memb) ls->ls_num_nodes--; } -static int dlm_is_member(struct dlm_ls *ls, int nodeid) +int dlm_is_member(struct dlm_ls *ls, int nodeid) { struct dlm_member *memb; diff --git a/fs/dlm/member.h b/fs/dlm/member.h index 927c08c1921..7a26fca1e0b 100644 --- a/fs/dlm/member.h +++ b/fs/dlm/member.h @@ -1,7 +1,7 @@ /****************************************************************************** ******************************************************************************* ** -** Copyright (C) 2005 Red Hat, Inc. All rights reserved. +** Copyright (C) 2005-2008 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 @@ -19,6 +19,7 @@ void dlm_clear_members(struct dlm_ls *ls); void dlm_clear_members_gone(struct dlm_ls *ls); int dlm_recover_members(struct dlm_ls *ls, struct dlm_recover *rv,int *neg_out); int dlm_is_removed(struct dlm_ls *ls, int nodeid); +int dlm_is_member(struct dlm_ls *ls, int nodeid); #endif /* __MEMBER_DOT_H__ */ diff --git a/fs/dlm/memory.c b/fs/dlm/memory.c index ecf0e5cb203..f7783867491 100644 --- a/fs/dlm/memory.c +++ b/fs/dlm/memory.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 @@ -35,7 +35,7 @@ void dlm_memory_exit(void) kmem_cache_destroy(lkb_cache); } -char *allocate_lvb(struct dlm_ls *ls) +char *dlm_allocate_lvb(struct dlm_ls *ls) { char *p; @@ -43,7 +43,7 @@ char *allocate_lvb(struct dlm_ls *ls) return p; } -void free_lvb(char *p) +void dlm_free_lvb(char *p) { kfree(p); } @@ -51,7 +51,7 @@ void free_lvb(char *p) /* FIXME: have some minimal space built-in to rsb for the name and kmalloc a separate name if needed, like dentries are done */ -struct dlm_rsb *allocate_rsb(struct dlm_ls *ls, int namelen) +struct dlm_rsb *dlm_allocate_rsb(struct dlm_ls *ls, int namelen) { struct dlm_rsb *r; @@ -61,14 +61,14 @@ struct dlm_rsb *allocate_rsb(struct dlm_ls *ls, int namelen) return r; } -void free_rsb(struct dlm_rsb *r) +void dlm_free_rsb(struct dlm_rsb *r) { if (r->res_lvbptr) - free_lvb(r->res_lvbptr); + dlm_free_lvb(r->res_lvbptr); kfree(r); } -struct dlm_lkb *allocate_lkb(struct dlm_ls *ls) +struct dlm_lkb *dlm_allocate_lkb(struct dlm_ls *ls) { struct dlm_lkb *lkb; @@ -76,7 +76,7 @@ struct dlm_lkb *allocate_lkb(struct dlm_ls *ls) return lkb; } -void free_lkb(struct dlm_lkb *lkb) +void dlm_free_lkb(struct dlm_lkb *lkb) { if (lkb->lkb_flags & DLM_IFL_USER) { struct dlm_user_args *ua; @@ -90,19 +90,3 @@ void free_lkb(struct dlm_lkb *lkb) kmem_cache_free(lkb_cache, lkb); } -struct dlm_direntry *allocate_direntry(struct dlm_ls *ls, int namelen) -{ - struct dlm_direntry *de; - - DLM_ASSERT(namelen <= DLM_RESNAME_MAXLEN, - printk("namelen = %d\n", namelen);); - - de = kzalloc(sizeof(*de) + namelen, GFP_KERNEL); - return de; -} - -void free_direntry(struct dlm_direntry *de) -{ - kfree(de); -} - diff --git a/fs/dlm/memory.h b/fs/dlm/memory.h index 6ead158ccc5..485fb29143b 100644 --- a/fs/dlm/memory.h +++ b/fs/dlm/memory.h @@ -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 @@ -16,14 +16,12 @@ int dlm_memory_init(void); void dlm_memory_exit(void); -struct dlm_rsb *allocate_rsb(struct dlm_ls *ls, int namelen); -void free_rsb(struct dlm_rsb *r); -struct dlm_lkb *allocate_lkb(struct dlm_ls *ls); -void free_lkb(struct dlm_lkb *l); -struct dlm_direntry *allocate_direntry(struct dlm_ls *ls, int namelen); -void free_direntry(struct dlm_direntry *de); -char *allocate_lvb(struct dlm_ls *ls); -void free_lvb(char *l); +struct dlm_rsb *dlm_allocate_rsb(struct dlm_ls *ls, int namelen); +void dlm_free_rsb(struct dlm_rsb *r); +struct dlm_lkb *dlm_allocate_lkb(struct dlm_ls *ls); +void dlm_free_lkb(struct dlm_lkb *l); +char *dlm_allocate_lvb(struct dlm_ls *ls); +void dlm_free_lvb(char *l); #endif /* __MEMORY_DOT_H__ */ diff --git a/fs/dlm/midcomms.c b/fs/dlm/midcomms.c index f8c69dda16a..e69926e984d 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) 2004-2007 Red Hat, Inc. All rights reserved. +** Copyright (C) 2004-2008 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 @@ -58,8 +58,12 @@ static void copy_from_cb(void *dst, const void *base, unsigned offset, int dlm_process_incoming_buffer(int nodeid, const void *base, unsigned offset, unsigned len, unsigned limit) { - unsigned char __tmp[DLM_INBUF_LEN]; - struct dlm_header *msg = (struct dlm_header *) __tmp; + union { + unsigned char __buf[DLM_INBUF_LEN]; + /* this is to force proper alignment on some arches */ + struct dlm_header dlm; + } __tmp; + struct dlm_header *msg = &__tmp.dlm; int ret = 0; int err = 0; uint16_t msglen; @@ -100,8 +104,7 @@ int dlm_process_incoming_buffer(int nodeid, const void *base, in the buffer on the stack (which should work for most ordinary messages). */ - if (msglen > sizeof(__tmp) && - msg == (struct dlm_header *) __tmp) { + if (msglen > DLM_INBUF_LEN && msg == &__tmp.dlm) { msg = kmalloc(dlm_config.ci_buffer_size, GFP_KERNEL); if (msg == NULL) return ret; @@ -119,7 +122,7 @@ int dlm_process_incoming_buffer(int nodeid, const void *base, dlm_receive_buffer(msg, nodeid); } - if (msg != (struct dlm_header *) __tmp) + if (msg != &__tmp.dlm) kfree(msg); return err ? err : ret; diff --git a/fs/dlm/rcom.c b/fs/dlm/rcom.c index ae2fd97fa4a..026824cd3ac 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) 2005-2007 Red Hat, Inc. All rights reserved. +** Copyright (C) 2005-2008 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 @@ -197,11 +197,6 @@ static void receive_sync_reply(struct dlm_ls *ls, struct dlm_rcom *rc_in) spin_unlock(&ls->ls_rcom_spin); } -static void receive_rcom_status_reply(struct dlm_ls *ls, struct dlm_rcom *rc_in) -{ - receive_sync_reply(ls, rc_in); -} - int dlm_rcom_names(struct dlm_ls *ls, int nodeid, char *last_name, int last_len) { struct dlm_rcom *rc; @@ -254,11 +249,6 @@ static void receive_rcom_names(struct dlm_ls *ls, struct dlm_rcom *rc_in) send_rcom(ls, mh, rc); } -static void receive_rcom_names_reply(struct dlm_ls *ls, struct dlm_rcom *rc_in) -{ - receive_sync_reply(ls, rc_in); -} - int dlm_send_rcom_lookup(struct dlm_rsb *r, int dir_nodeid) { struct dlm_rcom *rc; @@ -381,11 +371,6 @@ static void receive_rcom_lock(struct dlm_ls *ls, struct dlm_rcom *rc_in) send_rcom(ls, mh, rc); } -static void receive_rcom_lock_reply(struct dlm_ls *ls, struct dlm_rcom *rc_in) -{ - dlm_recover_process_copy(ls, 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. */ @@ -481,11 +466,11 @@ void dlm_receive_rcom(struct dlm_ls *ls, struct dlm_rcom *rc, int nodeid) break; case DLM_RCOM_STATUS_REPLY: - receive_rcom_status_reply(ls, rc); + receive_sync_reply(ls, rc); break; case DLM_RCOM_NAMES_REPLY: - receive_rcom_names_reply(ls, rc); + receive_sync_reply(ls, rc); break; case DLM_RCOM_LOOKUP_REPLY: @@ -493,11 +478,11 @@ void dlm_receive_rcom(struct dlm_ls *ls, struct dlm_rcom *rc, int nodeid) break; case DLM_RCOM_LOCK_REPLY: - receive_rcom_lock_reply(ls, rc); + dlm_recover_process_copy(ls, rc); break; default: - DLM_ASSERT(0, printk("rc_type=%x\n", rc->rc_type);); + log_error(ls, "receive_rcom bad type %d", rc->rc_type); } out: return; diff --git a/fs/dlm/recover.c b/fs/dlm/recover.c index c2cc7694cd1..df075dc300f 100644 --- a/fs/dlm/recover.c +++ b/fs/dlm/recover.c @@ -629,7 +629,7 @@ static void recover_lvb(struct dlm_rsb *r) goto out; if (!r->res_lvbptr) { - r->res_lvbptr = allocate_lvb(r->res_ls); + r->res_lvbptr = dlm_allocate_lvb(r->res_ls); if (!r->res_lvbptr) goto out; } @@ -731,6 +731,20 @@ int dlm_create_root_list(struct dlm_ls *ls) list_add(&r->res_root_list, &ls->ls_root_list); dlm_hold_rsb(r); } + + /* If we're using a directory, add tossed rsbs to the root + list; they'll have entries created in the new directory, + but no other recovery steps should do anything with them. */ + + if (dlm_no_directory(ls)) { + read_unlock(&ls->ls_rsbtbl[i].lock); + continue; + } + + list_for_each_entry(r, &ls->ls_rsbtbl[i].toss, res_hashchain) { + list_add(&r->res_root_list, &ls->ls_root_list); + dlm_hold_rsb(r); + } read_unlock(&ls->ls_rsbtbl[i].lock); } out: @@ -750,6 +764,11 @@ void dlm_release_root_list(struct dlm_ls *ls) up_write(&ls->ls_root_sem); } +/* If not using a directory, clear the entire toss list, there's no benefit to + caching the master value since it's fixed. If we are using a dir, keep the + rsb's we're the master of. Recovery will add them to the root list and from + there they'll be entered in the rebuilt directory. */ + void dlm_clear_toss_list(struct dlm_ls *ls) { struct dlm_rsb *r, *safe; @@ -759,8 +778,10 @@ void dlm_clear_toss_list(struct dlm_ls *ls) write_lock(&ls->ls_rsbtbl[i].lock); list_for_each_entry_safe(r, safe, &ls->ls_rsbtbl[i].toss, res_hashchain) { - list_del(&r->res_hashchain); - free_rsb(r); + if (dlm_no_directory(ls) || !is_master(r)) { + list_del(&r->res_hashchain); + dlm_free_rsb(r); + } } write_unlock(&ls->ls_rsbtbl[i].lock); } diff --git a/fs/dlm/recoverd.c b/fs/dlm/recoverd.c index 4b89e20eebe..997f9531d59 100644 --- a/fs/dlm/recoverd.c +++ b/fs/dlm/recoverd.c @@ -67,17 +67,18 @@ static int ls_recover(struct dlm_ls *ls, struct dlm_recover *rv) dlm_astd_resume(); /* - * This list of root rsb's will be the basis of most of the recovery - * routines. + * Free non-master tossed rsb's. Master rsb's are kept on toss + * list and put on root list to be included in resdir recovery. */ - dlm_create_root_list(ls); + dlm_clear_toss_list(ls); /* - * Free all the tossed rsb's so we don't have to recover them. + * This list of root rsb's will be the basis of most of the recovery + * routines. */ - dlm_clear_toss_list(ls); + dlm_create_root_list(ls); /* * Add or remove nodes from the lockspace's ls_nodes list. diff --git a/fs/dlm/user.c b/fs/dlm/user.c index 4f741546f4b..7cbc6826239 100644 --- a/fs/dlm/user.c +++ b/fs/dlm/user.c @@ -24,8 +24,7 @@ #include "lvb_table.h" #include "user.h" -static const char *name_prefix="dlm"; -static struct miscdevice ctl_device; +static const char name_prefix[] = "dlm"; static const struct file_operations device_fops; #ifdef CONFIG_COMPAT @@ -82,7 +81,8 @@ struct dlm_lock_result32 { }; static void compat_input(struct dlm_write_request *kb, - struct dlm_write_request32 *kb32) + struct dlm_write_request32 *kb32, + int max_namelen) { kb->version[0] = kb32->version[0]; kb->version[1] = kb32->version[1]; @@ -112,7 +112,11 @@ static void compat_input(struct dlm_write_request *kb, kb->i.lock.bastaddr = (void *)(long)kb32->i.lock.bastaddr; kb->i.lock.lksb = (void *)(long)kb32->i.lock.lksb; memcpy(kb->i.lock.lvb, kb32->i.lock.lvb, DLM_USER_LVB_LEN); - memcpy(kb->i.lock.name, kb32->i.lock.name, kb->i.lock.namelen); + if (kb->i.lock.namelen <= max_namelen) + memcpy(kb->i.lock.name, kb32->i.lock.name, + kb->i.lock.namelen); + else + kb->i.lock.namelen = max_namelen; } } @@ -236,12 +240,12 @@ void dlm_user_add_ast(struct dlm_lkb *lkb, int type) spin_unlock(&proc->asts_spin); if (eol) { - spin_lock(&ua->proc->locks_spin); + spin_lock(&proc->locks_spin); if (!list_empty(&lkb->lkb_ownqueue)) { list_del_init(&lkb->lkb_ownqueue); dlm_put_lkb(lkb); } - spin_unlock(&ua->proc->locks_spin); + spin_unlock(&proc->locks_spin); } out: mutex_unlock(&ls->ls_clear_proc_locks); @@ -529,7 +533,8 @@ static ssize_t device_write(struct file *file, const char __user *buf, if (proc) set_bit(DLM_PROC_FLAGS_COMPAT, &proc->flags); - compat_input(kbuf, k32buf); + compat_input(kbuf, k32buf, + count - sizeof(struct dlm_write_request32)); kfree(k32buf); } #endif @@ -896,14 +901,16 @@ static const struct file_operations ctl_device_fops = { .owner = THIS_MODULE, }; +static struct miscdevice ctl_device = { + .name = "dlm-control", + .fops = &ctl_device_fops, + .minor = MISC_DYNAMIC_MINOR, +}; + int dlm_user_init(void) { int error; - ctl_device.name = "dlm-control"; - ctl_device.fops = &ctl_device_fops; - ctl_device.minor = MISC_DYNAMIC_MINOR; - error = misc_register(&ctl_device); if (error) log_print("misc_register failed for control device"); diff --git a/fs/dlm/util.c b/fs/dlm/util.c index 963889cf674..4d9c1f4e1bd 100644 --- a/fs/dlm/util.c +++ b/fs/dlm/util.c @@ -1,7 +1,7 @@ /****************************************************************************** ******************************************************************************* ** -** Copyright (C) 2005 Red Hat, Inc. All rights reserved. +** Copyright (C) 2005-2008 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 @@ -14,6 +14,14 @@ #include "rcom.h" #include "util.h" +#define DLM_ERRNO_EDEADLK 35 +#define DLM_ERRNO_EBADR 53 +#define DLM_ERRNO_EBADSLT 57 +#define DLM_ERRNO_EPROTO 71 +#define DLM_ERRNO_EOPNOTSUPP 95 +#define DLM_ERRNO_ETIMEDOUT 110 +#define DLM_ERRNO_EINPROGRESS 115 + static void header_out(struct dlm_header *hd) { hd->h_version = cpu_to_le32(hd->h_version); @@ -30,11 +38,54 @@ static void header_in(struct dlm_header *hd) hd->h_length = le16_to_cpu(hd->h_length); } -void dlm_message_out(struct dlm_message *ms) +/* higher errno values are inconsistent across architectures, so select + one set of values for on the wire */ + +static int to_dlm_errno(int err) +{ + switch (err) { + case -EDEADLK: + return -DLM_ERRNO_EDEADLK; + case -EBADR: + return -DLM_ERRNO_EBADR; + case -EBADSLT: + return -DLM_ERRNO_EBADSLT; + case -EPROTO: + return -DLM_ERRNO_EPROTO; + case -EOPNOTSUPP: + return -DLM_ERRNO_EOPNOTSUPP; + case -ETIMEDOUT: + return -DLM_ERRNO_ETIMEDOUT; + case -EINPROGRESS: + return -DLM_ERRNO_EINPROGRESS; + } + return err; +} + +static int from_dlm_errno(int err) { - struct dlm_header *hd = (struct dlm_header *) ms; + switch (err) { + case -DLM_ERRNO_EDEADLK: + return -EDEADLK; + case -DLM_ERRNO_EBADR: + return -EBADR; + case -DLM_ERRNO_EBADSLT: + return -EBADSLT; + case -DLM_ERRNO_EPROTO: + return -EPROTO; + case -DLM_ERRNO_EOPNOTSUPP: + return -EOPNOTSUPP; + case -DLM_ERRNO_ETIMEDOUT: + return -ETIMEDOUT; + case -DLM_ERRNO_EINPROGRESS: + return -EINPROGRESS; + } + return err; +} - header_out(hd); +void dlm_message_out(struct dlm_message *ms) +{ + header_out(&ms->m_header); ms->m_type = cpu_to_le32(ms->m_type); ms->m_nodeid = cpu_to_le32(ms->m_nodeid); @@ -53,14 +104,12 @@ void dlm_message_out(struct dlm_message *ms) ms->m_rqmode = cpu_to_le32(ms->m_rqmode); ms->m_bastmode = cpu_to_le32(ms->m_bastmode); ms->m_asts = cpu_to_le32(ms->m_asts); - ms->m_result = cpu_to_le32(ms->m_result); + ms->m_result = cpu_to_le32(to_dlm_errno(ms->m_result)); } void dlm_message_in(struct dlm_message *ms) { - struct dlm_header *hd = (struct dlm_header *) ms; - - header_in(hd); + header_in(&ms->m_header); ms->m_type = le32_to_cpu(ms->m_type); ms->m_nodeid = le32_to_cpu(ms->m_nodeid); @@ -79,7 +128,7 @@ void dlm_message_in(struct dlm_message *ms) ms->m_rqmode = le32_to_cpu(ms->m_rqmode); ms->m_bastmode = le32_to_cpu(ms->m_bastmode); ms->m_asts = le32_to_cpu(ms->m_asts); - ms->m_result = le32_to_cpu(ms->m_result); + ms->m_result = from_dlm_errno(le32_to_cpu(ms->m_result)); } static void rcom_lock_out(struct rcom_lock *rl) @@ -126,10 +175,9 @@ static void rcom_config_in(struct rcom_config *rf) void dlm_rcom_out(struct dlm_rcom *rc) { - struct dlm_header *hd = (struct dlm_header *) rc; int type = rc->rc_type; - header_out(hd); + header_out(&rc->rc_header); rc->rc_type = cpu_to_le32(rc->rc_type); rc->rc_result = cpu_to_le32(rc->rc_result); @@ -137,7 +185,7 @@ void dlm_rcom_out(struct dlm_rcom *rc) rc->rc_seq = cpu_to_le64(rc->rc_seq); rc->rc_seq_reply = cpu_to_le64(rc->rc_seq_reply); - if (type == DLM_RCOM_LOCK) + if ((type == DLM_RCOM_LOCK) || (type == DLM_RCOM_LOCK_REPLY)) rcom_lock_out((struct rcom_lock *) rc->rc_buf); else if (type == DLM_RCOM_STATUS_REPLY) @@ -146,9 +194,9 @@ void dlm_rcom_out(struct dlm_rcom *rc) void dlm_rcom_in(struct dlm_rcom *rc) { - struct dlm_header *hd = (struct dlm_header *) rc; + int type; - header_in(hd); + header_in(&rc->rc_header); rc->rc_type = le32_to_cpu(rc->rc_type); rc->rc_result = le32_to_cpu(rc->rc_result); @@ -156,10 +204,12 @@ void dlm_rcom_in(struct dlm_rcom *rc) rc->rc_seq = le64_to_cpu(rc->rc_seq); rc->rc_seq_reply = le64_to_cpu(rc->rc_seq_reply); - if (rc->rc_type == DLM_RCOM_LOCK) + type = rc->rc_type; + + if ((type == DLM_RCOM_LOCK) || (type == DLM_RCOM_LOCK_REPLY)) rcom_lock_in((struct rcom_lock *) rc->rc_buf); - else if (rc->rc_type == DLM_RCOM_STATUS_REPLY) + else if (type == DLM_RCOM_STATUS_REPLY) rcom_config_in((struct rcom_config *) rc->rc_buf); } diff --git a/fs/eventpoll.c b/fs/eventpoll.c index 34f68f3a069..81c04abfb1a 100644 --- a/fs/eventpoll.c +++ b/fs/eventpoll.c @@ -656,8 +656,7 @@ is_linked: * wait list. */ if (waitqueue_active(&ep->wq)) - __wake_up_locked(&ep->wq, TASK_UNINTERRUPTIBLE | - TASK_INTERRUPTIBLE); + wake_up_locked(&ep->wq); if (waitqueue_active(&ep->poll_wait)) pwake++; @@ -780,7 +779,7 @@ static int ep_insert(struct eventpoll *ep, struct epoll_event *event, /* Notify waiting tasks that events are available */ if (waitqueue_active(&ep->wq)) - __wake_up_locked(&ep->wq, TASK_UNINTERRUPTIBLE | TASK_INTERRUPTIBLE); + wake_up_locked(&ep->wq); if (waitqueue_active(&ep->poll_wait)) pwake++; } @@ -854,8 +853,7 @@ static int ep_modify(struct eventpoll *ep, struct epitem *epi, struct epoll_even /* Notify waiting tasks that events are available */ if (waitqueue_active(&ep->wq)) - __wake_up_locked(&ep->wq, TASK_UNINTERRUPTIBLE | - TASK_INTERRUPTIBLE); + wake_up_locked(&ep->wq); if (waitqueue_active(&ep->poll_wait)) pwake++; } @@ -978,8 +976,7 @@ errxit: * wait list (delayed after we release the lock). */ if (waitqueue_active(&ep->wq)) - __wake_up_locked(&ep->wq, TASK_UNINTERRUPTIBLE | - TASK_INTERRUPTIBLE); + wake_up_locked(&ep->wq); if (waitqueue_active(&ep->poll_wait)) pwake++; } diff --git a/fs/lockd/host.c b/fs/lockd/host.c index 572601e98dc..ca6b16fc310 100644 --- a/fs/lockd/host.c +++ b/fs/lockd/host.c @@ -34,10 +34,10 @@ static DEFINE_MUTEX(nlm_host_mutex); static void nlm_gc_hosts(void); static struct nsm_handle * __nsm_find(const struct sockaddr_in *, - const char *, int, int); + const char *, unsigned int, int); static struct nsm_handle * nsm_find(const struct sockaddr_in *sin, const char *hostname, - int hostname_len); + unsigned int hostname_len); /* * Common host lookup routine for server & client @@ -45,7 +45,8 @@ static struct nsm_handle * nsm_find(const struct sockaddr_in *sin, static struct nlm_host * nlm_lookup_host(int server, const struct sockaddr_in *sin, int proto, int version, const char *hostname, - int hostname_len, const struct sockaddr_in *ssin) + unsigned int hostname_len, + const struct sockaddr_in *ssin) { struct hlist_head *chain; struct hlist_node *pos; @@ -176,7 +177,7 @@ nlm_destroy_host(struct nlm_host *host) */ struct nlm_host * nlmclnt_lookup_host(const struct sockaddr_in *sin, int proto, int version, - const char *hostname, int hostname_len) + const char *hostname, unsigned int hostname_len) { struct sockaddr_in ssin = {0}; @@ -189,7 +190,7 @@ nlmclnt_lookup_host(const struct sockaddr_in *sin, int proto, int version, */ struct nlm_host * nlmsvc_lookup_host(struct svc_rqst *rqstp, - const char *hostname, int hostname_len) + const char *hostname, unsigned int hostname_len) { struct sockaddr_in ssin = {0}; @@ -307,7 +308,8 @@ void nlm_release_host(struct nlm_host *host) * Release all resources held by that peer. */ void nlm_host_rebooted(const struct sockaddr_in *sin, - const char *hostname, int hostname_len, + const char *hostname, + unsigned int hostname_len, u32 new_state) { struct hlist_head *chain; @@ -377,8 +379,13 @@ nlm_shutdown_hosts(void) /* First, make all hosts eligible for gc */ dprintk("lockd: nuking all hosts...\n"); for (chain = nlm_hosts; chain < nlm_hosts + NLM_HOST_NRHASH; ++chain) { - hlist_for_each_entry(host, pos, chain, h_hash) + hlist_for_each_entry(host, pos, chain, h_hash) { host->h_expires = jiffies - 1; + if (host->h_rpcclnt) { + rpc_shutdown_client(host->h_rpcclnt); + host->h_rpcclnt = NULL; + } + } } /* Then, perform a garbage collection pass */ @@ -449,7 +456,7 @@ static DEFINE_MUTEX(nsm_mutex); static struct nsm_handle * __nsm_find(const struct sockaddr_in *sin, - const char *hostname, int hostname_len, + const char *hostname, unsigned int hostname_len, int create) { struct nsm_handle *nsm = NULL; @@ -503,7 +510,8 @@ out: } static struct nsm_handle * -nsm_find(const struct sockaddr_in *sin, const char *hostname, int hostname_len) +nsm_find(const struct sockaddr_in *sin, const char *hostname, + unsigned int hostname_len) { return __nsm_find(sin, hostname, hostname_len, 1); } diff --git a/fs/lockd/svc.c b/fs/lockd/svc.c index 82e2192a0d5..08226464e56 100644 --- a/fs/lockd/svc.c +++ b/fs/lockd/svc.c @@ -219,19 +219,6 @@ lockd(struct svc_rqst *rqstp) module_put_and_exit(0); } - -static int find_socket(struct svc_serv *serv, int proto) -{ - struct svc_sock *svsk; - int found = 0; - list_for_each_entry(svsk, &serv->sv_permsocks, sk_list) - if (svsk->sk_sk->sk_protocol == proto) { - found = 1; - break; - } - return found; -} - /* * Make any sockets that are needed but not present. * If nlm_udpport or nlm_tcpport were set as module @@ -240,17 +227,25 @@ static int find_socket(struct svc_serv *serv, int proto) static int make_socks(struct svc_serv *serv, int proto) { static int warned; + struct svc_xprt *xprt; int err = 0; - if (proto == IPPROTO_UDP || nlm_udpport) - if (!find_socket(serv, IPPROTO_UDP)) - err = svc_makesock(serv, IPPROTO_UDP, nlm_udpport, - SVC_SOCK_DEFAULTS); - if (err >= 0 && (proto == IPPROTO_TCP || nlm_tcpport)) - if (!find_socket(serv, IPPROTO_TCP)) - err = svc_makesock(serv, IPPROTO_TCP, nlm_tcpport, - SVC_SOCK_DEFAULTS); - + if (proto == IPPROTO_UDP || nlm_udpport) { + xprt = svc_find_xprt(serv, "udp", 0, 0); + if (!xprt) + err = svc_create_xprt(serv, "udp", nlm_udpport, + SVC_SOCK_DEFAULTS); + else + svc_xprt_put(xprt); + } + if (err >= 0 && (proto == IPPROTO_TCP || nlm_tcpport)) { + xprt = svc_find_xprt(serv, "tcp", 0, 0); + if (!xprt) + err = svc_create_xprt(serv, "tcp", nlm_tcpport, + SVC_SOCK_DEFAULTS); + else + svc_xprt_put(xprt); + } if (err >= 0) { warned = 0; err = 0; diff --git a/fs/lockd/svc4proc.c b/fs/lockd/svc4proc.c index bf27b6c6cb6..385437e3387 100644 --- a/fs/lockd/svc4proc.c +++ b/fs/lockd/svc4proc.c @@ -84,6 +84,7 @@ nlm4svc_proc_test(struct svc_rqst *rqstp, struct nlm_args *argp, { struct nlm_host *host; struct nlm_file *file; + int rc = rpc_success; dprintk("lockd: TEST4 called\n"); resp->cookie = argp->cookie; @@ -91,7 +92,7 @@ nlm4svc_proc_test(struct svc_rqst *rqstp, struct nlm_args *argp, /* Don't accept test requests during grace period */ if (nlmsvc_grace_period) { resp->status = nlm_lck_denied_grace_period; - return rpc_success; + return rc; } /* Obtain client and file */ @@ -101,12 +102,13 @@ nlm4svc_proc_test(struct svc_rqst *rqstp, struct nlm_args *argp, /* Now check for conflicting locks */ resp->status = nlmsvc_testlock(rqstp, file, &argp->lock, &resp->lock, &resp->cookie); if (resp->status == nlm_drop_reply) - return rpc_drop_reply; + rc = rpc_drop_reply; + else + dprintk("lockd: TEST4 status %d\n", ntohl(resp->status)); - dprintk("lockd: TEST4 status %d\n", ntohl(resp->status)); nlm_release_host(host); nlm_release_file(file); - return rpc_success; + return rc; } static __be32 @@ -115,6 +117,7 @@ nlm4svc_proc_lock(struct svc_rqst *rqstp, struct nlm_args *argp, { struct nlm_host *host; struct nlm_file *file; + int rc = rpc_success; dprintk("lockd: LOCK called\n"); @@ -123,7 +126,7 @@ nlm4svc_proc_lock(struct svc_rqst *rqstp, struct nlm_args *argp, /* Don't accept new lock requests during grace period */ if (nlmsvc_grace_period && !argp->reclaim) { resp->status = nlm_lck_denied_grace_period; - return rpc_success; + return rc; } /* Obtain client and file */ @@ -146,12 +149,13 @@ nlm4svc_proc_lock(struct svc_rqst *rqstp, struct nlm_args *argp, resp->status = nlmsvc_lock(rqstp, file, &argp->lock, argp->block, &argp->cookie); if (resp->status == nlm_drop_reply) - return rpc_drop_reply; + rc = rpc_drop_reply; + else + dprintk("lockd: LOCK status %d\n", ntohl(resp->status)); - dprintk("lockd: LOCK status %d\n", ntohl(resp->status)); nlm_release_host(host); nlm_release_file(file); - return rpc_success; + return rc; } static __be32 diff --git a/fs/lockd/svclock.c b/fs/lockd/svclock.c index d120ec39bcb..2f4d8fa6668 100644 --- a/fs/lockd/svclock.c +++ b/fs/lockd/svclock.c @@ -501,25 +501,29 @@ nlmsvc_testlock(struct svc_rqst *rqstp, struct nlm_file *file, block, block->b_flags, block->b_fl); if (block->b_flags & B_TIMED_OUT) { nlmsvc_unlink_block(block); - return nlm_lck_denied; + ret = nlm_lck_denied; + goto out; } if (block->b_flags & B_GOT_CALLBACK) { + nlmsvc_unlink_block(block); if (block->b_fl != NULL && block->b_fl->fl_type != F_UNLCK) { lock->fl = *block->b_fl; goto conf_lock; - } - else { - nlmsvc_unlink_block(block); - return nlm_granted; + } else { + ret = nlm_granted; + goto out; } } - return nlm_drop_reply; + ret = nlm_drop_reply; + goto out; } error = vfs_test_lock(file->f_file, &lock->fl); - if (error == -EINPROGRESS) - return nlmsvc_defer_lock_rqst(rqstp, block); + if (error == -EINPROGRESS) { + ret = nlmsvc_defer_lock_rqst(rqstp, block); + goto out; + } if (error) { ret = nlm_lck_denied_nolocks; goto out; diff --git a/fs/lockd/svcproc.c b/fs/lockd/svcproc.c index 9cd5c8b3759..88379cc6e0b 100644 --- a/fs/lockd/svcproc.c +++ b/fs/lockd/svcproc.c @@ -113,6 +113,7 @@ nlmsvc_proc_test(struct svc_rqst *rqstp, struct nlm_args *argp, { struct nlm_host *host; struct nlm_file *file; + int rc = rpc_success; dprintk("lockd: TEST called\n"); resp->cookie = argp->cookie; @@ -120,7 +121,7 @@ nlmsvc_proc_test(struct svc_rqst *rqstp, struct nlm_args *argp, /* Don't accept test requests during grace period */ if (nlmsvc_grace_period) { resp->status = nlm_lck_denied_grace_period; - return rpc_success; + return rc; } /* Obtain client and file */ @@ -130,13 +131,14 @@ nlmsvc_proc_test(struct svc_rqst *rqstp, struct nlm_args *argp, /* Now check for conflicting locks */ resp->status = cast_status(nlmsvc_testlock(rqstp, file, &argp->lock, &resp->lock, &resp->cookie)); if (resp->status == nlm_drop_reply) - return rpc_drop_reply; + rc = rpc_drop_reply; + else + dprintk("lockd: TEST status %d vers %d\n", + ntohl(resp->status), rqstp->rq_vers); - dprintk("lockd: TEST status %d vers %d\n", - ntohl(resp->status), rqstp->rq_vers); nlm_release_host(host); nlm_release_file(file); - return rpc_success; + return rc; } static __be32 @@ -145,6 +147,7 @@ nlmsvc_proc_lock(struct svc_rqst *rqstp, struct nlm_args *argp, { struct nlm_host *host; struct nlm_file *file; + int rc = rpc_success; dprintk("lockd: LOCK called\n"); @@ -153,7 +156,7 @@ nlmsvc_proc_lock(struct svc_rqst *rqstp, struct nlm_args *argp, /* Don't accept new lock requests during grace period */ if (nlmsvc_grace_period && !argp->reclaim) { resp->status = nlm_lck_denied_grace_period; - return rpc_success; + return rc; } /* Obtain client and file */ @@ -176,12 +179,13 @@ nlmsvc_proc_lock(struct svc_rqst *rqstp, struct nlm_args *argp, resp->status = cast_status(nlmsvc_lock(rqstp, file, &argp->lock, argp->block, &argp->cookie)); if (resp->status == nlm_drop_reply) - return rpc_drop_reply; + rc = rpc_drop_reply; + else + dprintk("lockd: LOCK status %d\n", ntohl(resp->status)); - dprintk("lockd: LOCK status %d\n", ntohl(resp->status)); nlm_release_host(host); nlm_release_file(file); - return rpc_success; + return rc; } static __be32 diff --git a/fs/lockd/svcsubs.c b/fs/lockd/svcsubs.c index 84ebba33b98..dbbefbcd671 100644 --- a/fs/lockd/svcsubs.c +++ b/fs/lockd/svcsubs.c @@ -87,7 +87,7 @@ nlm_lookup_file(struct svc_rqst *rqstp, struct nlm_file **result, unsigned int hash; __be32 nfserr; - nlm_debug_print_fh("nlm_file_lookup", f); + nlm_debug_print_fh("nlm_lookup_file", f); hash = file_hash(f); diff --git a/fs/nfs/callback.c b/fs/nfs/callback.c index 9b6bbf1b978..bd185a572a2 100644 --- a/fs/nfs/callback.c +++ b/fs/nfs/callback.c @@ -119,8 +119,8 @@ int nfs_callback_up(void) if (!serv) goto out_err; - ret = svc_makesock(serv, IPPROTO_TCP, nfs_callback_set_tcpport, - SVC_SOCK_ANONYMOUS); + ret = svc_create_xprt(serv, "tcp", nfs_callback_set_tcpport, + SVC_SOCK_ANONYMOUS); if (ret <= 0) goto out_destroy; nfs_callback_tcpport = ret; diff --git a/fs/nfs/client.c b/fs/nfs/client.c index 685c43f810c..c5c0175898f 100644 --- a/fs/nfs/client.c +++ b/fs/nfs/client.c @@ -386,7 +386,7 @@ found_client: if (new) nfs_free_client(new); - error = wait_event_interruptible(nfs_client_active_wq, + error = wait_event_killable(nfs_client_active_wq, clp->cl_cons_state != NFS_CS_INITING); if (error < 0) { nfs_put_client(clp); @@ -589,10 +589,6 @@ static int nfs_init_server_rpcclient(struct nfs_server *server, if (server->flags & NFS_MOUNT_SOFT) server->client->cl_softrtry = 1; - server->client->cl_intr = 0; - if (server->flags & NFS4_MOUNT_INTR) - server->client->cl_intr = 1; - return 0; } diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c index f8e165c7d5a..16844f98f50 100644 --- a/fs/nfs/direct.c +++ b/fs/nfs/direct.c @@ -188,17 +188,12 @@ static void nfs_direct_req_release(struct nfs_direct_req *dreq) static ssize_t nfs_direct_wait(struct nfs_direct_req *dreq) { ssize_t result = -EIOCBQUEUED; - struct rpc_clnt *clnt; - sigset_t oldset; /* Async requests don't wait here */ if (dreq->iocb) goto out; - clnt = NFS_CLIENT(dreq->inode); - rpc_clnt_sigmask(clnt, &oldset); - result = wait_for_completion_interruptible(&dreq->completion); - rpc_clnt_sigunmask(clnt, &oldset); + result = wait_for_completion_killable(&dreq->completion); if (!result) result = dreq->error; diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index 3f332e54e76..966a8850aa3 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -433,15 +433,11 @@ static int nfs_wait_schedule(void *word) */ static int nfs_wait_on_inode(struct inode *inode) { - struct rpc_clnt *clnt = NFS_CLIENT(inode); struct nfs_inode *nfsi = NFS_I(inode); - sigset_t oldmask; int error; - rpc_clnt_sigmask(clnt, &oldmask); error = wait_on_bit_lock(&nfsi->flags, NFS_INO_REVALIDATING, - nfs_wait_schedule, TASK_INTERRUPTIBLE); - rpc_clnt_sigunmask(clnt, &oldmask); + nfs_wait_schedule, TASK_KILLABLE); return error; } diff --git a/fs/nfs/mount_clnt.c b/fs/nfs/mount_clnt.c index 8afd9f7e7a9..49c7cd0502c 100644 --- a/fs/nfs/mount_clnt.c +++ b/fs/nfs/mount_clnt.c @@ -56,7 +56,7 @@ int nfs_mount(struct sockaddr *addr, size_t len, char *hostname, char *path, .program = &mnt_program, .version = version, .authflavor = RPC_AUTH_UNIX, - .flags = RPC_CLNT_CREATE_INTR, + .flags = 0, }; struct rpc_clnt *mnt_clnt; int status; diff --git a/fs/nfs/nfs3proc.c b/fs/nfs/nfs3proc.c index b353c1a05bf..549dbce714a 100644 --- a/fs/nfs/nfs3proc.c +++ b/fs/nfs/nfs3proc.c @@ -27,17 +27,14 @@ static int nfs3_rpc_wrapper(struct rpc_clnt *clnt, struct rpc_message *msg, int flags) { - sigset_t oldset; int res; - rpc_clnt_sigmask(clnt, &oldset); do { res = rpc_call_sync(clnt, msg, flags); if (res != -EJUKEBOX) break; - schedule_timeout_interruptible(NFS_JUKEBOX_RETRY_TIME); + schedule_timeout_killable(NFS_JUKEBOX_RETRY_TIME); res = -ERESTARTSYS; - } while (!signalled()); - rpc_clnt_sigunmask(clnt, &oldset); + } while (!fatal_signal_pending(current)); return res; } diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 5c189bd57eb..027e1095256 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -316,12 +316,9 @@ static void nfs4_opendata_put(struct nfs4_opendata *p) static int nfs4_wait_for_completion_rpc_task(struct rpc_task *task) { - sigset_t oldset; int ret; - rpc_clnt_sigmask(task->tk_client, &oldset); ret = rpc_wait_for_completion_task(task); - rpc_clnt_sigunmask(task->tk_client, &oldset); return ret; } @@ -2785,9 +2782,9 @@ nfs4_async_handle_error(struct rpc_task *task, const struct nfs_server *server) return 0; } -static int nfs4_wait_bit_interruptible(void *word) +static int nfs4_wait_bit_killable(void *word) { - if (signal_pending(current)) + if (fatal_signal_pending(current)) return -ERESTARTSYS; schedule(); return 0; @@ -2795,18 +2792,14 @@ static int nfs4_wait_bit_interruptible(void *word) static int nfs4_wait_clnt_recover(struct rpc_clnt *clnt, struct nfs_client *clp) { - sigset_t oldset; int res; might_sleep(); rwsem_acquire(&clp->cl_sem.dep_map, 0, 0, _RET_IP_); - rpc_clnt_sigmask(clnt, &oldset); res = wait_on_bit(&clp->cl_state, NFS4CLNT_STATE_RECOVER, - nfs4_wait_bit_interruptible, - TASK_INTERRUPTIBLE); - rpc_clnt_sigunmask(clnt, &oldset); + nfs4_wait_bit_killable, TASK_KILLABLE); rwsem_release(&clp->cl_sem.dep_map, 1, _RET_IP_); return res; @@ -2814,7 +2807,6 @@ static int nfs4_wait_clnt_recover(struct rpc_clnt *clnt, struct nfs_client *clp) static int nfs4_delay(struct rpc_clnt *clnt, long *timeout) { - sigset_t oldset; int res = 0; might_sleep(); @@ -2823,14 +2815,9 @@ static int nfs4_delay(struct rpc_clnt *clnt, long *timeout) *timeout = NFS4_POLL_RETRY_MIN; if (*timeout > NFS4_POLL_RETRY_MAX) *timeout = NFS4_POLL_RETRY_MAX; - rpc_clnt_sigmask(clnt, &oldset); - if (clnt->cl_intr) { - schedule_timeout_interruptible(*timeout); - if (signalled()) - res = -ERESTARTSYS; - } else - schedule_timeout_uninterruptible(*timeout); - rpc_clnt_sigunmask(clnt, &oldset); + schedule_timeout_killable(*timeout); + if (fatal_signal_pending(current)) + res = -ERESTARTSYS; *timeout <<= 1; return res; } @@ -3069,7 +3056,7 @@ int nfs4_proc_delegreturn(struct inode *inode, struct rpc_cred *cred, const nfs4 static unsigned long nfs4_set_lock_task_retry(unsigned long timeout) { - schedule_timeout_interruptible(timeout); + schedule_timeout_killable(timeout); timeout <<= 1; if (timeout > NFS4_LOCK_MAXTIMEOUT) return NFS4_LOCK_MAXTIMEOUT; diff --git a/fs/nfs/nfsroot.c b/fs/nfs/nfsroot.c index 4b0334590ee..531379d3682 100644 --- a/fs/nfs/nfsroot.c +++ b/fs/nfs/nfsroot.c @@ -228,10 +228,7 @@ static int __init root_nfs_parse(char *name, char *buf) nfs_data.flags &= ~NFS_MOUNT_SOFT; break; case Opt_intr: - nfs_data.flags |= NFS_MOUNT_INTR; - break; case Opt_nointr: - nfs_data.flags &= ~NFS_MOUNT_INTR; break; case Opt_posix: nfs_data.flags |= NFS_MOUNT_POSIX; diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c index 3b3dbb94393..7f079209d70 100644 --- a/fs/nfs/pagelist.c +++ b/fs/nfs/pagelist.c @@ -58,7 +58,6 @@ nfs_create_request(struct nfs_open_context *ctx, struct inode *inode, struct page *page, unsigned int offset, unsigned int count) { - struct nfs_server *server = NFS_SERVER(inode); struct nfs_page *req; for (;;) { @@ -67,7 +66,7 @@ nfs_create_request(struct nfs_open_context *ctx, struct inode *inode, if (req != NULL) break; - if (signalled() && (server->flags & NFS_MOUNT_INTR)) + if (fatal_signal_pending(current)) return ERR_PTR(-ERESTARTSYS); yield(); } @@ -177,11 +176,11 @@ void nfs_release_request(struct nfs_page *req) kref_put(&req->wb_kref, nfs_free_request); } -static int nfs_wait_bit_interruptible(void *word) +static int nfs_wait_bit_killable(void *word) { int ret = 0; - if (signal_pending(current)) + if (fatal_signal_pending(current)) ret = -ERESTARTSYS; else schedule(); @@ -192,26 +191,18 @@ static int nfs_wait_bit_interruptible(void *word) * nfs_wait_on_request - Wait for a request to complete. * @req: request to wait upon. * - * Interruptible by signals only if mounted with intr flag. + * Interruptible by fatal signals only. * The user is responsible for holding a count on the request. */ int nfs_wait_on_request(struct nfs_page *req) { - struct rpc_clnt *clnt = NFS_CLIENT(req->wb_context->path.dentry->d_inode); - sigset_t oldmask; int ret = 0; if (!test_bit(PG_BUSY, &req->wb_flags)) goto out; - /* - * Note: the call to rpc_clnt_sigmask() suffices to ensure that we - * are not interrupted if intr flag is not set - */ - rpc_clnt_sigmask(clnt, &oldmask); ret = out_of_line_wait_on_bit(&req->wb_flags, PG_BUSY, - nfs_wait_bit_interruptible, TASK_INTERRUPTIBLE); - rpc_clnt_sigunmask(clnt, &oldmask); + nfs_wait_bit_killable, TASK_KILLABLE); out: return ret; } diff --git a/fs/nfs/super.c b/fs/nfs/super.c index 22c49c02897..7f4505f6ac6 100644 --- a/fs/nfs/super.c +++ b/fs/nfs/super.c @@ -448,7 +448,6 @@ static void nfs_show_mount_options(struct seq_file *m, struct nfs_server *nfss, const char *nostr; } nfs_info[] = { { NFS_MOUNT_SOFT, ",soft", ",hard" }, - { NFS_MOUNT_INTR, ",intr", ",nointr" }, { NFS_MOUNT_NOCTO, ",nocto", "" }, { NFS_MOUNT_NOAC, ",noac", "" }, { NFS_MOUNT_NONLM, ",nolock", "" }, @@ -708,10 +707,7 @@ static int nfs_parse_mount_options(char *raw, mnt->flags &= ~NFS_MOUNT_SOFT; break; case Opt_intr: - mnt->flags |= NFS_MOUNT_INTR; - break; case Opt_nointr: - mnt->flags &= ~NFS_MOUNT_INTR; break; case Opt_posix: mnt->flags |= NFS_MOUNT_POSIX; diff --git a/fs/nfs/write.c b/fs/nfs/write.c index 5ac5b27b639..522efff3e2c 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -488,7 +488,7 @@ int nfs_reschedule_unstable_write(struct nfs_page *req) /* * Wait for a request to complete. * - * Interruptible by signals only if mounted with intr flag. + * Interruptible by fatal signals only. */ static int nfs_wait_on_requests_locked(struct inode *inode, pgoff_t idx_start, unsigned int npages) { diff --git a/fs/nfsd/auth.h b/fs/nfsd/auth.h new file mode 100644 index 00000000000..78b3c0e9382 --- /dev/null +++ b/fs/nfsd/auth.h @@ -0,0 +1,22 @@ +/* + * nfsd-specific authentication stuff. + * uid/gid mapping not yet implemented. + * + * Copyright (C) 1995, 1996 Olaf Kirch <okir@monad.swb.de> + */ + +#ifndef LINUX_NFSD_AUTH_H +#define LINUX_NFSD_AUTH_H + +#define nfsd_luid(rq, uid) ((u32)(uid)) +#define nfsd_lgid(rq, gid) ((u32)(gid)) +#define nfsd_ruid(rq, uid) ((u32)(uid)) +#define nfsd_rgid(rq, gid) ((u32)(gid)) + +/* + * Set the current process's fsuid/fsgid etc to those of the NFS + * client user + */ +int nfsd_setuser(struct svc_rqst *, struct svc_export *); + +#endif /* LINUX_NFSD_AUTH_H */ diff --git a/fs/nfsd/export.c b/fs/nfsd/export.c index 66d0aeb32a4..79b4bf81296 100644 --- a/fs/nfsd/export.c +++ b/fs/nfsd/export.c @@ -1357,8 +1357,6 @@ exp_pseudoroot(struct svc_rqst *rqstp, struct svc_fh *fhp) mk_fsid(FSID_NUM, fsidv, 0, 0, 0, NULL); exp = rqst_exp_find(rqstp, FSID_NUM, fsidv); - if (PTR_ERR(exp) == -ENOENT) - return nfserr_perm; if (IS_ERR(exp)) return nfserrno(PTR_ERR(exp)); rv = fh_compose(fhp, exp, exp->ex_dentry, NULL); @@ -1637,13 +1635,19 @@ exp_verify_string(char *cp, int max) /* * Initialize the exports module. */ -void +int nfsd_export_init(void) { + int rv; dprintk("nfsd: initializing export module.\n"); - cache_register(&svc_export_cache); - cache_register(&svc_expkey_cache); + rv = cache_register(&svc_export_cache); + if (rv) + return rv; + rv = cache_register(&svc_expkey_cache); + if (rv) + cache_unregister(&svc_export_cache); + return rv; } @@ -1670,10 +1674,8 @@ nfsd_export_shutdown(void) exp_writelock(); - if (cache_unregister(&svc_expkey_cache)) - printk(KERN_ERR "nfsd: failed to unregister expkey cache\n"); - if (cache_unregister(&svc_export_cache)) - printk(KERN_ERR "nfsd: failed to unregister export cache\n"); + cache_unregister(&svc_expkey_cache); + cache_unregister(&svc_export_cache); svcauth_unix_purge(); exp_writeunlock(); diff --git a/fs/nfsd/nfs2acl.c b/fs/nfsd/nfs2acl.c index 0e5fa11e6b4..1c3b7654e96 100644 --- a/fs/nfsd/nfs2acl.c +++ b/fs/nfsd/nfs2acl.c @@ -221,12 +221,17 @@ static int nfsaclsvc_encode_getaclres(struct svc_rqst *rqstp, __be32 *p, struct nfsd3_getaclres *resp) { struct dentry *dentry = resp->fh.fh_dentry; - struct inode *inode = dentry->d_inode; + struct inode *inode; struct kvec *head = rqstp->rq_res.head; unsigned int base; int n; int w; + /* + * Since this is version 2, the check for nfserr in + * nfsd_dispatch actually ensures the following cannot happen. + * However, it seems fragile to depend on that. + */ if (dentry == NULL || dentry->d_inode == NULL) return 0; inode = dentry->d_inode; diff --git a/fs/nfsd/nfs3xdr.c b/fs/nfsd/nfs3xdr.c index f917fd25858..d7647f70e02 100644 --- a/fs/nfsd/nfs3xdr.c +++ b/fs/nfsd/nfs3xdr.c @@ -21,6 +21,7 @@ #include <linux/sunrpc/svc.h> #include <linux/nfsd/nfsd.h> #include <linux/nfsd/xdr3.h> +#include "auth.h" #define NFSDDBG_FACILITY NFSDDBG_XDR @@ -88,10 +89,10 @@ encode_fh(__be32 *p, struct svc_fh *fhp) * no slashes or null bytes. */ static __be32 * -decode_filename(__be32 *p, char **namp, int *lenp) +decode_filename(__be32 *p, char **namp, unsigned int *lenp) { char *name; - int i; + unsigned int i; if ((p = xdr_decode_string_inplace(p, namp, lenp, NFS3_MAXNAMLEN)) != NULL) { for (i = 0, name = *namp; i < *lenp; i++, name++) { @@ -452,8 +453,7 @@ int nfs3svc_decode_symlinkargs(struct svc_rqst *rqstp, __be32 *p, struct nfsd3_symlinkargs *args) { - unsigned int len; - int avail; + unsigned int len, avail; char *old, *new; struct kvec *vec; @@ -486,7 +486,8 @@ nfs3svc_decode_symlinkargs(struct svc_rqst *rqstp, __be32 *p, /* now copy next page if there is one */ if (len && !avail && rqstp->rq_arg.page_len) { avail = rqstp->rq_arg.page_len; - if (avail > PAGE_SIZE) avail = PAGE_SIZE; + if (avail > PAGE_SIZE) + avail = PAGE_SIZE; old = page_address(rqstp->rq_arg.pages[0]); } while (len && avail && *old) { @@ -816,11 +817,11 @@ static __be32 * encode_entryplus_baggage(struct nfsd3_readdirres *cd, __be32 *p, struct svc_fh *fhp) { - p = encode_post_op_attr(cd->rqstp, p, fhp); - *p++ = xdr_one; /* yes, a file handle follows */ - p = encode_fh(p, fhp); - fh_put(fhp); - return p; + p = encode_post_op_attr(cd->rqstp, p, fhp); + *p++ = xdr_one; /* yes, a file handle follows */ + p = encode_fh(p, fhp); + fh_put(fhp); + return p; } static int diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c index 9d536a8cb37..aae2b29ae2c 100644 --- a/fs/nfsd/nfs4callback.c +++ b/fs/nfsd/nfs4callback.c @@ -350,30 +350,6 @@ static struct rpc_version * nfs_cb_version[] = { static int do_probe_callback(void *data) { struct nfs4_client *clp = data; - struct nfs4_callback *cb = &clp->cl_callback; - struct rpc_message msg = { - .rpc_proc = &nfs4_cb_procedures[NFSPROC4_CLNT_CB_NULL], - .rpc_argp = clp, - }; - int status; - - status = rpc_call_sync(cb->cb_client, &msg, RPC_TASK_SOFT); - - if (status) { - rpc_shutdown_client(cb->cb_client); - cb->cb_client = NULL; - } else - atomic_set(&cb->cb_set, 1); - put_nfs4_client(clp); - return 0; -} - -/* - * Set up the callback client and put a NFSPROC4_CB_NULL on the wire... - */ -void -nfsd4_probe_callback(struct nfs4_client *clp) -{ struct sockaddr_in addr; struct nfs4_callback *cb = &clp->cl_callback; struct rpc_timeout timeparms = { @@ -390,13 +366,15 @@ nfsd4_probe_callback(struct nfs4_client *clp) .timeout = &timeparms, .program = program, .version = nfs_cb_version[1]->number, - .authflavor = RPC_AUTH_UNIX, /* XXX: need AUTH_GSS... */ + .authflavor = RPC_AUTH_UNIX, /* XXX: need AUTH_GSS... */ .flags = (RPC_CLNT_CREATE_NOPING), }; - struct task_struct *t; - - if (atomic_read(&cb->cb_set)) - return; + struct rpc_message msg = { + .rpc_proc = &nfs4_cb_procedures[NFSPROC4_CLNT_CB_NULL], + .rpc_argp = clp, + }; + struct rpc_clnt *client; + int status; /* Initialize address */ memset(&addr, 0, sizeof(addr)); @@ -416,29 +394,50 @@ nfsd4_probe_callback(struct nfs4_client *clp) program->stats->program = program; /* Create RPC client */ - cb->cb_client = rpc_create(&args); - if (IS_ERR(cb->cb_client)) { + client = rpc_create(&args); + if (IS_ERR(client)) { dprintk("NFSD: couldn't create callback client\n"); + status = PTR_ERR(client); goto out_err; } + status = rpc_call_sync(client, &msg, RPC_TASK_SOFT); + + if (status) + goto out_release_client; + + cb->cb_client = client; + atomic_set(&cb->cb_set, 1); + put_nfs4_client(clp); + return 0; +out_release_client: + rpc_shutdown_client(client); +out_err: + put_nfs4_client(clp); + dprintk("NFSD: warning: no callback path to client %.*s\n", + (int)clp->cl_name.len, clp->cl_name.data); + return status; +} + +/* + * Set up the callback client and put a NFSPROC4_CB_NULL on the wire... + */ +void +nfsd4_probe_callback(struct nfs4_client *clp) +{ + struct task_struct *t; + + BUG_ON(atomic_read(&clp->cl_callback.cb_set)); + /* the task holds a reference to the nfs4_client struct */ atomic_inc(&clp->cl_count); t = kthread_run(do_probe_callback, clp, "nfs4_cb_probe"); if (IS_ERR(t)) - goto out_release_clp; + atomic_dec(&clp->cl_count); return; - -out_release_clp: - atomic_dec(&clp->cl_count); - rpc_shutdown_client(cb->cb_client); -out_err: - cb->cb_client = NULL; - dprintk("NFSD: warning: no callback path to client %.*s\n", - (int)clp->cl_name.len, clp->cl_name.data); } /* @@ -458,9 +457,6 @@ nfsd4_cb_recall(struct nfs4_delegation *dp) int retries = 1; int status = 0; - if ((!atomic_read(&clp->cl_callback.cb_set)) || !clnt) - return; - cbr->cbr_trunc = 0; /* XXX need to implement truncate optimization */ cbr->cbr_dp = dp; @@ -469,6 +465,7 @@ nfsd4_cb_recall(struct nfs4_delegation *dp) switch (status) { case -EIO: /* Network partition? */ + atomic_set(&clp->cl_callback.cb_set, 0); case -EBADHANDLE: case -NFS4ERR_BAD_STATEID: /* Race: client probably got cb_recall @@ -481,11 +478,10 @@ nfsd4_cb_recall(struct nfs4_delegation *dp) status = rpc_call_sync(clnt, &msg, RPC_TASK_SOFT); } out_put_cred: - if (status == -EIO) - atomic_set(&clp->cl_callback.cb_set, 0); - /* Success or failure, now we're either waiting for lease expiration - * or deleg_return. */ - dprintk("NFSD: nfs4_cb_recall: dp %p dl_flock %p dl_count %d\n",dp, dp->dl_flock, atomic_read(&dp->dl_count)); + /* + * Success or failure, now we're either waiting for lease expiration + * or deleg_return. + */ put_nfs4_client(clp); nfs4_put_delegation(dp); return; diff --git a/fs/nfsd/nfs4idmap.c b/fs/nfsd/nfs4idmap.c index 4c0c683ce07..996bd88b75b 100644 --- a/fs/nfsd/nfs4idmap.c +++ b/fs/nfsd/nfs4idmap.c @@ -255,13 +255,10 @@ idtoname_parse(struct cache_detail *cd, char *buf, int buflen) goto out; if (len == 0) set_bit(CACHE_NEGATIVE, &ent.h.flags); - else { - if (error >= IDMAP_NAMESZ) { - error = -EINVAL; - goto out; - } + else if (len >= IDMAP_NAMESZ) + goto out; + else memcpy(ent.name, buf1, sizeof(ent.name)); - } error = -ENOMEM; res = idtoname_update(&ent, res); if (res == NULL) @@ -467,20 +464,25 @@ nametoid_update(struct ent *new, struct ent *old) * Exported API */ -void +int nfsd_idmap_init(void) { - cache_register(&idtoname_cache); - cache_register(&nametoid_cache); + int rv; + + rv = cache_register(&idtoname_cache); + if (rv) + return rv; + rv = cache_register(&nametoid_cache); + if (rv) + cache_unregister(&idtoname_cache); + return rv; } void nfsd_idmap_shutdown(void) { - if (cache_unregister(&idtoname_cache)) - printk(KERN_ERR "nfsd: failed to unregister idtoname cache\n"); - if (cache_unregister(&nametoid_cache)) - printk(KERN_ERR "nfsd: failed to unregister nametoid cache\n"); + cache_unregister(&idtoname_cache); + cache_unregister(&nametoid_cache); } /* diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c index 18ead1790bb..c593db047d8 100644 --- a/fs/nfsd/nfs4proc.c +++ b/fs/nfsd/nfs4proc.c @@ -750,7 +750,7 @@ _nfsd4_verify(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, cstate->current_fh.fh_export, cstate->current_fh.fh_dentry, buf, &count, verify->ve_bmval, - rqstp); + rqstp, 0); /* this means that nfsd4_encode_fattr() ran out of space */ if (status == nfserr_resource && count == 0) diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index 31673cd251c..f6744bc03da 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -61,7 +61,6 @@ static time_t lease_time = 90; /* default lease time */ static time_t user_lease_time = 90; static time_t boot_time; static int in_grace = 1; -static u32 current_clientid = 1; static u32 current_ownerid = 1; static u32 current_fileid = 1; static u32 current_delegid = 1; @@ -340,21 +339,20 @@ STALE_CLIENTID(clientid_t *clid) * This type of memory management is somewhat inefficient, but we use it * anyway since SETCLIENTID is not a common operation. */ -static inline struct nfs4_client * -alloc_client(struct xdr_netobj name) +static struct nfs4_client *alloc_client(struct xdr_netobj name) { struct nfs4_client *clp; - if ((clp = kzalloc(sizeof(struct nfs4_client), GFP_KERNEL))!= NULL) { - if ((clp->cl_name.data = kmalloc(name.len, GFP_KERNEL)) != NULL) { - memcpy(clp->cl_name.data, name.data, name.len); - clp->cl_name.len = name.len; - } - else { - kfree(clp); - clp = NULL; - } + clp = kzalloc(sizeof(struct nfs4_client), GFP_KERNEL); + if (clp == NULL) + return NULL; + clp->cl_name.data = kmalloc(name.len, GFP_KERNEL); + if (clp->cl_name.data == NULL) { + kfree(clp); + return NULL; } + memcpy(clp->cl_name.data, name.data, name.len); + clp->cl_name.len = name.len; return clp; } @@ -363,8 +361,11 @@ shutdown_callback_client(struct nfs4_client *clp) { struct rpc_clnt *clnt = clp->cl_callback.cb_client; - /* shutdown rpc client, ending any outstanding recall rpcs */ if (clnt) { + /* + * Callback threads take a reference on the client, so there + * should be no outstanding callbacks at this point. + */ clp->cl_callback.cb_client = NULL; rpc_shutdown_client(clnt); } @@ -422,12 +423,13 @@ expire_client(struct nfs4_client *clp) put_nfs4_client(clp); } -static struct nfs4_client * -create_client(struct xdr_netobj name, char *recdir) { +static struct nfs4_client *create_client(struct xdr_netobj name, char *recdir) +{ struct nfs4_client *clp; - if (!(clp = alloc_client(name))) - goto out; + clp = alloc_client(name); + if (clp == NULL) + return NULL; memcpy(clp->cl_recdir, recdir, HEXDIR_LEN); atomic_set(&clp->cl_count, 1); atomic_set(&clp->cl_callback.cb_set, 0); @@ -436,32 +438,30 @@ create_client(struct xdr_netobj name, char *recdir) { INIT_LIST_HEAD(&clp->cl_openowners); INIT_LIST_HEAD(&clp->cl_delegations); INIT_LIST_HEAD(&clp->cl_lru); -out: return clp; } -static void -copy_verf(struct nfs4_client *target, nfs4_verifier *source) { - memcpy(target->cl_verifier.data, source->data, sizeof(target->cl_verifier.data)); +static void copy_verf(struct nfs4_client *target, nfs4_verifier *source) +{ + memcpy(target->cl_verifier.data, source->data, + sizeof(target->cl_verifier.data)); } -static void -copy_clid(struct nfs4_client *target, struct nfs4_client *source) { +static void copy_clid(struct nfs4_client *target, struct nfs4_client *source) +{ target->cl_clientid.cl_boot = source->cl_clientid.cl_boot; target->cl_clientid.cl_id = source->cl_clientid.cl_id; } -static void -copy_cred(struct svc_cred *target, struct svc_cred *source) { - +static void copy_cred(struct svc_cred *target, struct svc_cred *source) +{ target->cr_uid = source->cr_uid; target->cr_gid = source->cr_gid; target->cr_group_info = source->cr_group_info; get_group_info(target->cr_group_info); } -static inline int -same_name(const char *n1, const char *n2) +static int same_name(const char *n1, const char *n2) { return 0 == memcmp(n1, n2, HEXDIR_LEN); } @@ -485,26 +485,26 @@ same_creds(struct svc_cred *cr1, struct svc_cred *cr2) return cr1->cr_uid == cr2->cr_uid; } -static void -gen_clid(struct nfs4_client *clp) { +static void gen_clid(struct nfs4_client *clp) +{ + static u32 current_clientid = 1; + clp->cl_clientid.cl_boot = boot_time; clp->cl_clientid.cl_id = current_clientid++; } -static void -gen_confirm(struct nfs4_client *clp) { - struct timespec tv; - u32 * p; +static void gen_confirm(struct nfs4_client *clp) +{ + static u32 i; + u32 *p; - tv = CURRENT_TIME; p = (u32 *)clp->cl_confirm.data; - *p++ = tv.tv_sec; - *p++ = tv.tv_nsec; + *p++ = get_seconds(); + *p++ = i++; } -static int -check_name(struct xdr_netobj name) { - +static int check_name(struct xdr_netobj name) +{ if (name.len == 0) return 0; if (name.len > NFS4_OPAQUE_LIMIT) { @@ -683,39 +683,6 @@ out_err: return; } -/* - * RFC 3010 has a complex implmentation description of processing a - * SETCLIENTID request consisting of 5 bullets, labeled as - * CASE0 - CASE4 below. - * - * NOTES: - * callback information will be processed in a future patch - * - * an unconfirmed record is added when: - * NORMAL (part of CASE 4): there is no confirmed nor unconfirmed record. - * CASE 1: confirmed record found with matching name, principal, - * verifier, and clientid. - * CASE 2: confirmed record found with matching name, principal, - * and there is no unconfirmed record with matching - * name and principal - * - * an unconfirmed record is replaced when: - * CASE 3: confirmed record found with matching name, principal, - * and an unconfirmed record is found with matching - * name, principal, and with clientid and - * confirm that does not match the confirmed record. - * CASE 4: there is no confirmed record with matching name and - * principal. there is an unconfirmed record with - * matching name, principal. - * - * an unconfirmed record is deleted when: - * CASE 1: an unconfirmed record that matches input name, verifier, - * and confirmed clientid. - * CASE 4: any unconfirmed records with matching name and principal - * that exist after an unconfirmed record has been replaced - * as described above. - * - */ __be32 nfsd4_setclientid(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, struct nfsd4_setclientid *setclid) @@ -748,11 +715,7 @@ nfsd4_setclientid(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, nfs4_lock_state(); conf = find_confirmed_client_by_str(dname, strhashval); if (conf) { - /* - * CASE 0: - * clname match, confirmed, different principal - * or different ip_address - */ + /* RFC 3530 14.2.33 CASE 0: */ status = nfserr_clid_inuse; if (!same_creds(&conf->cl_cred, &rqstp->rq_cred) || conf->cl_addr != sin->sin_addr.s_addr) { @@ -761,12 +724,17 @@ nfsd4_setclientid(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, goto out; } } + /* + * section 14.2.33 of RFC 3530 (under the heading "IMPLEMENTATION") + * has a description of SETCLIENTID request processing consisting + * of 5 bullet points, labeled as CASE0 - CASE4 below. + */ unconf = find_unconfirmed_client_by_str(dname, strhashval); status = nfserr_resource; if (!conf) { - /* - * CASE 4: - * placed first, because it is the normal case. + /* + * RFC 3530 14.2.33 CASE 4: + * placed first, because it is the normal case */ if (unconf) expire_client(unconf); @@ -776,17 +744,8 @@ nfsd4_setclientid(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, gen_clid(new); } else if (same_verf(&conf->cl_verifier, &clverifier)) { /* - * CASE 1: - * cl_name match, confirmed, principal match - * verifier match: probable callback update - * - * remove any unconfirmed nfs4_client with - * matching cl_name, cl_verifier, and cl_clientid - * - * create and insert an unconfirmed nfs4_client with same - * cl_name, cl_verifier, and cl_clientid as existing - * nfs4_client, but with the new callback info and a - * new cl_confirm + * RFC 3530 14.2.33 CASE 1: + * probable callback update */ if (unconf) { /* Note this is removing unconfirmed {*x***}, @@ -802,43 +761,25 @@ nfsd4_setclientid(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, copy_clid(new, conf); } else if (!unconf) { /* - * CASE 2: - * clname match, confirmed, principal match - * verfier does not match - * no unconfirmed. create a new unconfirmed nfs4_client - * using input clverifier, clname, and callback info - * and generate a new cl_clientid and cl_confirm. + * RFC 3530 14.2.33 CASE 2: + * probable client reboot; state will be removed if + * confirmed. */ new = create_client(clname, dname); if (new == NULL) goto out; gen_clid(new); - } else if (!same_verf(&conf->cl_confirm, &unconf->cl_confirm)) { - /* - * CASE3: - * confirmed found (name, principal match) - * confirmed verifier does not match input clverifier - * - * unconfirmed found (name match) - * confirmed->cl_confirm != unconfirmed->cl_confirm - * - * remove unconfirmed. - * - * create an unconfirmed nfs4_client - * with same cl_name as existing confirmed nfs4_client, - * but with new callback info, new cl_clientid, - * new cl_verifier and a new cl_confirm + } else { + /* + * RFC 3530 14.2.33 CASE 3: + * probable client reboot; state will be removed if + * confirmed. */ expire_client(unconf); new = create_client(clname, dname); if (new == NULL) goto out; gen_clid(new); - } else { - /* No cases hit !!! */ - status = nfserr_inval; - goto out; - } copy_verf(new, &clverifier); new->cl_addr = sin->sin_addr.s_addr; @@ -857,11 +798,9 @@ out: /* - * RFC 3010 has a complex implmentation description of processing a - * SETCLIENTID_CONFIRM request consisting of 4 bullets describing - * processing on a DRC miss, labeled as CASE1 - CASE4 below. - * - * NOTE: callback information will be processed here in a future patch + * Section 14.2.34 of RFC 3530 (under the heading "IMPLEMENTATION") has + * a description of SETCLIENTID_CONFIRM request processing consisting of 4 + * bullets, labeled as CASE1 - CASE4 below. */ __be32 nfsd4_setclientid_confirm(struct svc_rqst *rqstp, @@ -892,16 +831,16 @@ nfsd4_setclientid_confirm(struct svc_rqst *rqstp, if (unconf && unconf->cl_addr != sin->sin_addr.s_addr) goto out; - if ((conf && unconf) && - (same_verf(&unconf->cl_confirm, &confirm)) && - (same_verf(&conf->cl_verifier, &unconf->cl_verifier)) && - (same_name(conf->cl_recdir,unconf->cl_recdir)) && - (!same_verf(&conf->cl_confirm, &unconf->cl_confirm))) { - /* CASE 1: - * unconf record that matches input clientid and input confirm. - * conf record that matches input clientid. - * conf and unconf records match names, verifiers - */ + /* + * section 14.2.34 of RFC 3530 has a description of + * SETCLIENTID_CONFIRM request processing consisting + * of 4 bullet points, labeled as CASE1 - CASE4 below. + */ + if (conf && unconf && same_verf(&confirm, &unconf->cl_confirm)) { + /* + * RFC 3530 14.2.34 CASE 1: + * callback update + */ if (!same_creds(&conf->cl_cred, &unconf->cl_cred)) status = nfserr_clid_inuse; else { @@ -914,15 +853,11 @@ nfsd4_setclientid_confirm(struct svc_rqst *rqstp, status = nfs_ok; } - } else if ((conf && !unconf) || - ((conf && unconf) && - (!same_verf(&conf->cl_verifier, &unconf->cl_verifier) || - !same_name(conf->cl_recdir, unconf->cl_recdir)))) { - /* CASE 2: - * conf record that matches input clientid. - * if unconf record matches input clientid, then - * unconf->cl_name or unconf->cl_verifier don't match the - * conf record. + } else if (conf && !unconf) { + /* + * RFC 3530 14.2.34 CASE 2: + * probable retransmitted request; play it safe and + * do nothing. */ if (!same_creds(&conf->cl_cred, &rqstp->rq_cred)) status = nfserr_clid_inuse; @@ -930,10 +865,9 @@ nfsd4_setclientid_confirm(struct svc_rqst *rqstp, status = nfs_ok; } else if (!conf && unconf && same_verf(&unconf->cl_confirm, &confirm)) { - /* CASE 3: - * conf record not found. - * unconf record found. - * unconf->cl_confirm matches input confirm + /* + * RFC 3530 14.2.34 CASE 3: + * Normal case; new or rebooted client: */ if (!same_creds(&unconf->cl_cred, &rqstp->rq_cred)) { status = nfserr_clid_inuse; @@ -948,16 +882,15 @@ nfsd4_setclientid_confirm(struct svc_rqst *rqstp, } move_to_confirmed(unconf); conf = unconf; + nfsd4_probe_callback(conf); status = nfs_ok; } } else if ((!conf || (conf && !same_verf(&conf->cl_confirm, &confirm))) && (!unconf || (unconf && !same_verf(&unconf->cl_confirm, &confirm)))) { - /* CASE 4: - * conf record not found, or if conf, conf->cl_confirm does not - * match input confirm. - * unconf record not found, or if unconf, unconf->cl_confirm - * does not match input confirm. + /* + * RFC 3530 14.2.34 CASE 4: + * Client probably hasn't noticed that we rebooted yet. */ status = nfserr_stale_clientid; } else { @@ -965,8 +898,6 @@ nfsd4_setclientid_confirm(struct svc_rqst *rqstp, status = nfserr_clid_inuse; } out: - if (!status) - nfsd4_probe_callback(conf); nfs4_unlock_state(); return status; } @@ -1226,14 +1157,19 @@ find_file(struct inode *ino) return NULL; } -static int access_valid(u32 x) +static inline int access_valid(u32 x) { - return (x > 0 && x < 4); + if (x < NFS4_SHARE_ACCESS_READ) + return 0; + if (x > NFS4_SHARE_ACCESS_BOTH) + return 0; + return 1; } -static int deny_valid(u32 x) +static inline int deny_valid(u32 x) { - return (x >= 0 && x < 5); + /* Note: unlike access bits, deny bits may be zero. */ + return x <= NFS4_SHARE_DENY_BOTH; } static void @@ -2162,8 +2098,10 @@ nfs4_preprocess_seqid_op(struct svc_fh *current_fh, u32 seqid, stateid_t *statei goto check_replay; } + *stpp = stp; + *sopp = sop = stp->st_stateowner; + if (lock) { - struct nfs4_stateowner *sop = stp->st_stateowner; clientid_t *lockclid = &lock->v.new.clientid; struct nfs4_client *clp = sop->so_client; int lkflg = 0; @@ -2193,9 +2131,6 @@ nfs4_preprocess_seqid_op(struct svc_fh *current_fh, u32 seqid, stateid_t *statei return nfserr_bad_stateid; } - *stpp = stp; - *sopp = sop = stp->st_stateowner; - /* * We now validate the seqid and stateid generation numbers. * For the moment, we ignore the possibility of diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c index 57333944af7..b0592e7c378 100644 --- a/fs/nfsd/nfs4xdr.c +++ b/fs/nfsd/nfs4xdr.c @@ -148,12 +148,12 @@ xdr_error: \ } \ } while (0) -static __be32 *read_buf(struct nfsd4_compoundargs *argp, int nbytes) +static __be32 *read_buf(struct nfsd4_compoundargs *argp, u32 nbytes) { /* We want more bytes than seem to be available. * Maybe we need a new page, maybe we have just run out */ - int avail = (char*)argp->end - (char*)argp->p; + unsigned int avail = (char *)argp->end - (char *)argp->p; __be32 *p; if (avail + argp->pagelen < nbytes) return NULL; @@ -169,6 +169,11 @@ static __be32 *read_buf(struct nfsd4_compoundargs *argp, int nbytes) return NULL; } + /* + * The following memcpy is safe because read_buf is always + * called with nbytes > avail, and the two cases above both + * guarantee p points to at least nbytes bytes. + */ memcpy(p, argp->p, avail); /* step to next page */ argp->p = page_address(argp->pagelist[0]); @@ -1448,7 +1453,7 @@ static __be32 fattr_handle_absent_fs(u32 *bmval0, u32 *bmval1, u32 *rdattr_err) __be32 nfsd4_encode_fattr(struct svc_fh *fhp, struct svc_export *exp, struct dentry *dentry, __be32 *buffer, int *countp, u32 *bmval, - struct svc_rqst *rqstp) + struct svc_rqst *rqstp, int ignore_crossmnt) { u32 bmval0 = bmval[0]; u32 bmval1 = bmval[1]; @@ -1828,7 +1833,12 @@ out_acl: if (bmval1 & FATTR4_WORD1_MOUNTED_ON_FILEID) { if ((buflen -= 8) < 0) goto out_resource; - if (exp->ex_mnt->mnt_root->d_inode == dentry->d_inode) { + /* + * Get parent's attributes if not ignoring crossmount + * and this is the root of a cross-mounted filesystem. + */ + if (ignore_crossmnt == 0 && + exp->ex_mnt->mnt_root->d_inode == dentry->d_inode) { err = vfs_getattr(exp->ex_mnt->mnt_parent, exp->ex_mnt->mnt_mountpoint, &stat); if (err) @@ -1864,13 +1874,25 @@ nfsd4_encode_dirent_fattr(struct nfsd4_readdir *cd, struct svc_export *exp = cd->rd_fhp->fh_export; struct dentry *dentry; __be32 nfserr; + int ignore_crossmnt = 0; dentry = lookup_one_len(name, cd->rd_fhp->fh_dentry, namlen); if (IS_ERR(dentry)) return nfserrno(PTR_ERR(dentry)); exp_get(exp); - if (d_mountpoint(dentry)) { + /* + * In the case of a mountpoint, the client may be asking for + * attributes that are only properties of the underlying filesystem + * as opposed to the cross-mounted file system. In such a case, + * we will not follow the cross mount and will fill the attribtutes + * directly from the mountpoint dentry. + */ + if (d_mountpoint(dentry) && + (cd->rd_bmval[0] & ~FATTR4_WORD0_RDATTR_ERROR) == 0 && + (cd->rd_bmval[1] & ~FATTR4_WORD1_MOUNTED_ON_FILEID) == 0) + ignore_crossmnt = 1; + else if (d_mountpoint(dentry)) { int err; /* @@ -1889,7 +1911,7 @@ nfsd4_encode_dirent_fattr(struct nfsd4_readdir *cd, } nfserr = nfsd4_encode_fattr(NULL, exp, dentry, p, buflen, cd->rd_bmval, - cd->rd_rqstp); + cd->rd_rqstp, ignore_crossmnt); out_put: dput(dentry); exp_put(exp); @@ -2043,7 +2065,7 @@ nfsd4_encode_getattr(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4 buflen = resp->end - resp->p - (COMPOUND_ERR_SLACK_SPACE >> 2); nfserr = nfsd4_encode_fattr(fhp, fhp->fh_export, fhp->fh_dentry, resp->p, &buflen, getattr->ga_bmval, - resp->rqstp); + resp->rqstp, 0); if (!nfserr) resp->p += buflen; return nfserr; diff --git a/fs/nfsd/nfscache.c b/fs/nfsd/nfscache.c index 578f2c9d56b..5bfc2ac60d5 100644 --- a/fs/nfsd/nfscache.c +++ b/fs/nfsd/nfscache.c @@ -44,17 +44,17 @@ static int nfsd_cache_append(struct svc_rqst *rqstp, struct kvec *vec); */ static DEFINE_SPINLOCK(cache_lock); -void -nfsd_cache_init(void) +int nfsd_reply_cache_init(void) { struct svc_cacherep *rp; int i; INIT_LIST_HEAD(&lru_head); i = CACHESIZE; - while(i) { + while (i) { rp = kmalloc(sizeof(*rp), GFP_KERNEL); - if (!rp) break; + if (!rp) + goto out_nomem; list_add(&rp->c_lru, &lru_head); rp->c_state = RC_UNUSED; rp->c_type = RC_NOCACHE; @@ -62,23 +62,19 @@ nfsd_cache_init(void) i--; } - if (i) - printk (KERN_ERR "nfsd: cannot allocate all %d cache entries, only got %d\n", - CACHESIZE, CACHESIZE-i); - hash_list = kcalloc (HASHSIZE, sizeof(struct hlist_head), GFP_KERNEL); - if (!hash_list) { - nfsd_cache_shutdown(); - printk (KERN_ERR "nfsd: cannot allocate %Zd bytes for hash list\n", - HASHSIZE * sizeof(struct hlist_head)); - return; - } + if (!hash_list) + goto out_nomem; cache_disabled = 0; + return 0; +out_nomem: + printk(KERN_ERR "nfsd: failed to allocate reply cache\n"); + nfsd_reply_cache_shutdown(); + return -ENOMEM; } -void -nfsd_cache_shutdown(void) +void nfsd_reply_cache_shutdown(void) { struct svc_cacherep *rp; diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c index 77dc9893b7b..8516137cdbb 100644 --- a/fs/nfsd/nfsctl.c +++ b/fs/nfsd/nfsctl.c @@ -304,6 +304,9 @@ static ssize_t write_filehandle(struct file *file, char *buf, size_t size) struct auth_domain *dom; struct knfsd_fh fh; + if (size == 0) + return -EINVAL; + if (buf[size-1] != '\n') return -EINVAL; buf[size-1] = 0; @@ -503,7 +506,7 @@ static ssize_t write_ports(struct file *file, char *buf, size_t size) int len = 0; lock_kernel(); if (nfsd_serv) - len = svc_sock_names(buf, nfsd_serv, NULL); + len = svc_xprt_names(nfsd_serv, buf, 0); unlock_kernel(); return len; } @@ -540,7 +543,7 @@ static ssize_t write_ports(struct file *file, char *buf, size_t size) } return err < 0 ? err : 0; } - if (buf[0] == '-') { + if (buf[0] == '-' && isdigit(buf[1])) { char *toclose = kstrdup(buf+1, GFP_KERNEL); int len = 0; if (!toclose) @@ -554,6 +557,53 @@ static ssize_t write_ports(struct file *file, char *buf, size_t size) kfree(toclose); return len; } + /* + * Add a transport listener by writing it's transport name + */ + if (isalpha(buf[0])) { + int err; + char transport[16]; + int port; + if (sscanf(buf, "%15s %4d", transport, &port) == 2) { + err = nfsd_create_serv(); + if (!err) { + err = svc_create_xprt(nfsd_serv, + transport, port, + SVC_SOCK_ANONYMOUS); + if (err == -ENOENT) + /* Give a reasonable perror msg for + * bad transport string */ + err = -EPROTONOSUPPORT; + } + return err < 0 ? err : 0; + } + } + /* + * Remove a transport by writing it's transport name and port number + */ + if (buf[0] == '-' && isalpha(buf[1])) { + struct svc_xprt *xprt; + int err = -EINVAL; + char transport[16]; + int port; + if (sscanf(&buf[1], "%15s %4d", transport, &port) == 2) { + if (port == 0) + return -EINVAL; + lock_kernel(); + if (nfsd_serv) { + xprt = svc_find_xprt(nfsd_serv, transport, + AF_UNSPEC, port); + if (xprt) { + svc_close_xprt(xprt); + svc_xprt_put(xprt); + err = 0; + } else + err = -ENOTCONN; + } + unlock_kernel(); + return err < 0 ? err : 0; + } + } return -EINVAL; } @@ -616,7 +666,7 @@ static ssize_t write_recoverydir(struct file *file, char *buf, size_t size) char *recdir; int len, status; - if (size > PATH_MAX || buf[size-1] != '\n') + if (size == 0 || size > PATH_MAX || buf[size-1] != '\n') return -EINVAL; buf[size-1] = 0; @@ -674,6 +724,27 @@ static struct file_system_type nfsd_fs_type = { .kill_sb = kill_litter_super, }; +#ifdef CONFIG_PROC_FS +static int create_proc_exports_entry(void) +{ + struct proc_dir_entry *entry; + + entry = proc_mkdir("fs/nfs", NULL); + if (!entry) + return -ENOMEM; + entry = create_proc_entry("fs/nfs/exports", 0, NULL); + if (!entry) + return -ENOMEM; + entry->proc_fops = &exports_operations; + return 0; +} +#else /* CONFIG_PROC_FS */ +static int create_proc_exports_entry(void) +{ + return 0; +} +#endif + static int __init init_nfsd(void) { int retval; @@ -683,32 +754,43 @@ static int __init init_nfsd(void) if (retval) return retval; nfsd_stat_init(); /* Statistics */ - nfsd_cache_init(); /* RPC reply cache */ - nfsd_export_init(); /* Exports table */ + retval = nfsd_reply_cache_init(); + if (retval) + goto out_free_stat; + retval = nfsd_export_init(); + if (retval) + goto out_free_cache; nfsd_lockd_init(); /* lockd->nfsd callbacks */ - nfsd_idmap_init(); /* Name to ID mapping */ - if (proc_mkdir("fs/nfs", NULL)) { - struct proc_dir_entry *entry; - entry = create_proc_entry("fs/nfs/exports", 0, NULL); - if (entry) - entry->proc_fops = &exports_operations; - } + retval = nfsd_idmap_init(); + if (retval) + goto out_free_lockd; + retval = create_proc_exports_entry(); + if (retval) + goto out_free_idmap; retval = register_filesystem(&nfsd_fs_type); - if (retval) { - nfsd_export_shutdown(); - nfsd_cache_shutdown(); - remove_proc_entry("fs/nfs/exports", NULL); - remove_proc_entry("fs/nfs", NULL); - nfsd_stat_shutdown(); - nfsd_lockd_shutdown(); - } + if (retval) + goto out_free_all; + return 0; +out_free_all: + remove_proc_entry("fs/nfs/exports", NULL); + remove_proc_entry("fs/nfs", NULL); +out_free_idmap: + nfsd_idmap_shutdown(); +out_free_lockd: + nfsd_lockd_shutdown(); + nfsd_export_shutdown(); +out_free_cache: + nfsd_reply_cache_shutdown(); +out_free_stat: + nfsd_stat_shutdown(); + nfsd4_free_slabs(); return retval; } static void __exit exit_nfsd(void) { nfsd_export_shutdown(); - nfsd_cache_shutdown(); + nfsd_reply_cache_shutdown(); remove_proc_entry("fs/nfs/exports", NULL); remove_proc_entry("fs/nfs", NULL); nfsd_stat_shutdown(); diff --git a/fs/nfsd/nfsfh.c b/fs/nfsd/nfsfh.c index 468f17a7844..8fbd2dc08a9 100644 --- a/fs/nfsd/nfsfh.c +++ b/fs/nfsd/nfsfh.c @@ -22,6 +22,7 @@ #include <linux/sunrpc/svc.h> #include <linux/sunrpc/svcauth_gss.h> #include <linux/nfsd/nfsd.h> +#include "auth.h" #define NFSDDBG_FACILITY NFSDDBG_FH diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c index 1190aeaa92b..9647b0f7bc0 100644 --- a/fs/nfsd/nfssvc.c +++ b/fs/nfsd/nfssvc.c @@ -155,8 +155,8 @@ static int killsig; /* signal that was used to kill last nfsd */ static void nfsd_last_thread(struct svc_serv *serv) { /* When last nfsd thread exits we need to do some clean-up */ - struct svc_sock *svsk; - list_for_each_entry(svsk, &serv->sv_permsocks, sk_list) + struct svc_xprt *xprt; + list_for_each_entry(xprt, &serv->sv_permsocks, xpt_list) lockd_down(); nfsd_serv = NULL; nfsd_racache_shutdown(); @@ -236,7 +236,7 @@ static int nfsd_init_socks(int port) error = lockd_up(IPPROTO_UDP); if (error >= 0) { - error = svc_makesock(nfsd_serv, IPPROTO_UDP, port, + error = svc_create_xprt(nfsd_serv, "udp", port, SVC_SOCK_DEFAULTS); if (error < 0) lockd_down(); @@ -247,7 +247,7 @@ static int nfsd_init_socks(int port) #ifdef CONFIG_NFSD_TCP error = lockd_up(IPPROTO_TCP); if (error >= 0) { - error = svc_makesock(nfsd_serv, IPPROTO_TCP, port, + error = svc_create_xprt(nfsd_serv, "tcp", port, SVC_SOCK_DEFAULTS); if (error < 0) lockd_down(); diff --git a/fs/nfsd/nfsxdr.c b/fs/nfsd/nfsxdr.c index b86e3658a0a..61ad61743d9 100644 --- a/fs/nfsd/nfsxdr.c +++ b/fs/nfsd/nfsxdr.c @@ -15,6 +15,7 @@ #include <linux/nfsd/nfsd.h> #include <linux/nfsd/xdr.h> #include <linux/mm.h> +#include "auth.h" #define NFSDDBG_FACILITY NFSDDBG_XDR @@ -62,10 +63,10 @@ encode_fh(__be32 *p, struct svc_fh *fhp) * no slashes or null bytes. */ static __be32 * -decode_filename(__be32 *p, char **namp, int *lenp) +decode_filename(__be32 *p, char **namp, unsigned int *lenp) { char *name; - int i; + unsigned int i; if ((p = xdr_decode_string_inplace(p, namp, lenp, NFS_MAXNAMLEN)) != NULL) { for (i = 0, name = *namp; i < *lenp; i++, name++) { @@ -78,10 +79,10 @@ decode_filename(__be32 *p, char **namp, int *lenp) } static __be32 * -decode_pathname(__be32 *p, char **namp, int *lenp) +decode_pathname(__be32 *p, char **namp, unsigned int *lenp) { char *name; - int i; + unsigned int i; if ((p = xdr_decode_string_inplace(p, namp, lenp, NFS_MAXPATHLEN)) != NULL) { for (i = 0, name = *namp; i < *lenp; i++, name++) { diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index d0199189924..cc75e4fcd02 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -132,7 +132,7 @@ out: __be32 nfsd_lookup_dentry(struct svc_rqst *rqstp, struct svc_fh *fhp, - const char *name, int len, + const char *name, unsigned int len, struct svc_export **exp_ret, struct dentry **dentry_ret) { struct svc_export *exp; @@ -226,7 +226,7 @@ out_nfserr: */ __be32 nfsd_lookup(struct svc_rqst *rqstp, struct svc_fh *fhp, const char *name, - int len, struct svc_fh *resfh) + unsigned int len, struct svc_fh *resfh) { struct svc_export *exp; struct dentry *dentry; @@ -1151,6 +1151,26 @@ nfsd_commit(struct svc_rqst *rqstp, struct svc_fh *fhp, } #endif /* CONFIG_NFSD_V3 */ +__be32 +nfsd_create_setattr(struct svc_rqst *rqstp, struct svc_fh *resfhp, + struct iattr *iap) +{ + /* + * Mode has already been set earlier in create: + */ + iap->ia_valid &= ~ATTR_MODE; + /* + * Setting uid/gid works only for root. Irix appears to + * send along the gid on create when it tries to implement + * setgid directories via NFS: + */ + if (current->fsuid != 0) + iap->ia_valid &= ~(ATTR_UID|ATTR_GID); + if (iap->ia_valid) + return nfsd_setattr(rqstp, resfhp, iap, 0, (time_t)0); + return 0; +} + /* * Create a file (regular, directory, device, fifo); UNIX sockets * not yet implemented. @@ -1167,6 +1187,7 @@ nfsd_create(struct svc_rqst *rqstp, struct svc_fh *fhp, struct dentry *dentry, *dchild = NULL; struct inode *dirp; __be32 err; + __be32 err2; int host_err; err = nfserr_perm; @@ -1257,16 +1278,9 @@ nfsd_create(struct svc_rqst *rqstp, struct svc_fh *fhp, } - /* Set file attributes. Mode has already been set and - * setting uid/gid works only for root. Irix appears to - * send along the gid when it tries to implement setgid - * directories via NFS. - */ - if ((iap->ia_valid &= ~(ATTR_UID|ATTR_GID|ATTR_MODE)) != 0) { - __be32 err2 = nfsd_setattr(rqstp, resfhp, iap, 0, (time_t)0); - if (err2) - err = err2; - } + err2 = nfsd_create_setattr(rqstp, resfhp, iap); + if (err2) + err = err2; /* * Update the file handle to get the new inode info. */ @@ -1295,6 +1309,7 @@ nfsd_create_v3(struct svc_rqst *rqstp, struct svc_fh *fhp, struct dentry *dentry, *dchild = NULL; struct inode *dirp; __be32 err; + __be32 err2; int host_err; __u32 v_mtime=0, v_atime=0; @@ -1399,16 +1414,10 @@ nfsd_create_v3(struct svc_rqst *rqstp, struct svc_fh *fhp, iap->ia_atime.tv_nsec = 0; } - /* Set file attributes. - * Irix appears to send along the gid when it tries to - * implement setgid directories via NFS. Clear out all that cruft. - */ set_attr: - if ((iap->ia_valid &= ~(ATTR_UID|ATTR_GID|ATTR_MODE)) != 0) { - __be32 err2 = nfsd_setattr(rqstp, resfhp, iap, 0, (time_t)0); - if (err2) - err = err2; - } + err2 = nfsd_create_setattr(rqstp, resfhp, iap); + if (err2) + err = err2; /* * Update the filehandle to get the new inode info. diff --git a/fs/proc/array.c b/fs/proc/array.c index eb97f2897e2..b380313092b 100644 --- a/fs/proc/array.c +++ b/fs/proc/array.c @@ -141,12 +141,7 @@ static const char *task_state_array[] = { static inline const char *get_task_state(struct task_struct *tsk) { - unsigned int state = (tsk->state & (TASK_RUNNING | - TASK_INTERRUPTIBLE | - TASK_UNINTERRUPTIBLE | - TASK_STOPPED | - TASK_TRACED)) | - tsk->exit_state; + unsigned int state = (tsk->state & TASK_REPORT) | tsk->exit_state; const char **p = &task_state_array[0]; while (state) { diff --git a/fs/proc/base.c b/fs/proc/base.c index 91fa8e6ce8a..33537487f5a 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -199,7 +199,7 @@ static int proc_root_link(struct inode *inode, struct dentry **dentry, struct vf (task == current || \ (task->parent == current && \ (task->ptrace & PT_PTRACED) && \ - (task->state == TASK_STOPPED || task->state == TASK_TRACED) && \ + (task_is_stopped_or_traced(task)) && \ security_ptrace(current,task) == 0)) struct mm_struct *mm_for_maps(struct task_struct *task) @@ -984,7 +984,7 @@ static ssize_t proc_loginuid_read(struct file * file, char __user * buf, if (!task) return -ESRCH; length = scnprintf(tmpbuf, TMPBUFLEN, "%u", - audit_get_loginuid(task->audit_context)); + audit_get_loginuid(task)); put_task_struct(task); return simple_read_from_buffer(buf, count, ppos, tmpbuf, length); } diff --git a/fs/readdir.c b/fs/readdir.c index efe52e67657..4e026e5407f 100644 --- a/fs/readdir.c +++ b/fs/readdir.c @@ -30,7 +30,10 @@ int vfs_readdir(struct file *file, filldir_t filler, void *buf) if (res) goto out; - mutex_lock(&inode->i_mutex); + res = mutex_lock_killable(&inode->i_mutex); + if (res) + goto out; + res = -ENOENT; if (!IS_DEADDIR(inode)) { res = file->f_op->readdir(file, buf, filler); diff --git a/fs/smbfs/request.c b/fs/smbfs/request.c index ca4b2d59c0c..45f45933e86 100644 --- a/fs/smbfs/request.c +++ b/fs/smbfs/request.c @@ -105,7 +105,7 @@ struct smb_request *smb_alloc_request(struct smb_sb_info *server, int bufsize) if (nfs_try_to_free_pages(server)) continue; - if (signalled() && (server->flags & NFS_MOUNT_INTR)) + if (fatal_signal_pending(current)) return ERR_PTR(-ERESTARTSYS); current->policy = SCHED_YIELD; schedule(); diff --git a/fs/splice.c b/fs/splice.c index 1577a7391d2..4ee49e86edd 100644 --- a/fs/splice.c +++ b/fs/splice.c @@ -1033,9 +1033,7 @@ ssize_t splice_direct_to_actor(struct file *in, struct splice_desc *sd, done: pipe->nrbufs = pipe->curbuf = 0; - if (bytes > 0) - file_accessed(in); - + file_accessed(in); return bytes; out_release: |