From 28c0254ede13ab575d2df5c6585ed3d4817c3e6b Mon Sep 17 00:00:00 2001 From: "Yan, Zheng" Date: Mon, 28 May 2012 14:44:30 +0800 Subject: ceph: check PG_Private flag before accessing page->private I got lots of NULL pointer dereference Oops when compiling kernel on ceph. The bug is because the kernel page migration routine replaces some pages in the page cache with new pages, these new pages' private can be non-zero. Signed-off-by: Zheng Yan Signed-off-by: Sage Weil --- fs/ceph/addr.c | 21 ++++++++++++--------- 1 file changed, 12 insertions(+), 9 deletions(-) (limited to 'fs') diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c index 173b1d22e59b..8b67304e4b80 100644 --- a/fs/ceph/addr.c +++ b/fs/ceph/addr.c @@ -54,7 +54,12 @@ (CONGESTION_ON_THRESH(congestion_kb) - \ (CONGESTION_ON_THRESH(congestion_kb) >> 2)) - +static inline struct ceph_snap_context *page_snap_context(struct page *page) +{ + if (PagePrivate(page)) + return (void *)page->private; + return NULL; +} /* * Dirty a page. Optimistically adjust accounting, on the assumption @@ -142,10 +147,9 @@ static void ceph_invalidatepage(struct page *page, unsigned long offset) { struct inode *inode; struct ceph_inode_info *ci; - struct ceph_snap_context *snapc = (void *)page->private; + struct ceph_snap_context *snapc = page_snap_context(page); BUG_ON(!PageLocked(page)); - BUG_ON(!page->private); BUG_ON(!PagePrivate(page)); BUG_ON(!page->mapping); @@ -182,7 +186,6 @@ static int ceph_releasepage(struct page *page, gfp_t g) struct inode *inode = page->mapping ? page->mapping->host : NULL; dout("%p releasepage %p idx %lu\n", inode, page, page->index); WARN_ON(PageDirty(page)); - WARN_ON(page->private); WARN_ON(PagePrivate(page)); return 0; } @@ -443,7 +446,7 @@ static int writepage_nounlock(struct page *page, struct writeback_control *wbc) osdc = &fsc->client->osdc; /* verify this is a writeable snap context */ - snapc = (void *)page->private; + snapc = page_snap_context(page); if (snapc == NULL) { dout("writepage %p page %p not dirty?\n", inode, page); goto out; @@ -451,7 +454,7 @@ static int writepage_nounlock(struct page *page, struct writeback_control *wbc) oldest = get_oldest_context(inode, &snap_size); if (snapc->seq > oldest->seq) { dout("writepage %p page %p snapc %p not writeable - noop\n", - inode, page, (void *)page->private); + inode, page, snapc); /* we should only noop if called by kswapd */ WARN_ON((current->flags & PF_MEMALLOC) == 0); ceph_put_snap_context(oldest); @@ -591,7 +594,7 @@ static void writepages_finish(struct ceph_osd_request *req, clear_bdi_congested(&fsc->backing_dev_info, BLK_RW_ASYNC); - ceph_put_snap_context((void *)page->private); + ceph_put_snap_context(page_snap_context(page)); page->private = 0; ClearPagePrivate(page); dout("unlocking %d %p\n", i, page); @@ -795,7 +798,7 @@ get_more_pages: } /* only if matching snap context */ - pgsnapc = (void *)page->private; + pgsnapc = page_snap_context(page); if (pgsnapc->seq > snapc->seq) { dout("page snapc %p %lld > oldest %p %lld\n", pgsnapc, pgsnapc->seq, snapc, snapc->seq); @@ -984,7 +987,7 @@ retry_locked: BUG_ON(!ci->i_snap_realm); down_read(&mdsc->snap_rwsem); BUG_ON(!ci->i_snap_realm->cached_context); - snapc = (void *)page->private; + snapc = page_snap_context(page); if (snapc && snapc != ci->i_head_snapc) { /* * this page is already dirty in another (older) snap -- cgit v1.2.3-58-ga151 From 15d9882c336db2db73ccf9871ae2398e452f694c Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Sat, 26 May 2012 23:26:43 -0500 Subject: libceph: embed ceph messenger structure in ceph_client A ceph client has a pointer to a ceph messenger structure in it. There is always exactly one ceph messenger for a ceph client, so there is no need to allocate it separate from the ceph client structure. Switch the ceph_client structure to embed its ceph_messenger structure. Signed-off-by: Alex Elder Reviewed-by: Yehuda Sadeh Reviewed-by: Sage Weil --- fs/ceph/mds_client.c | 2 +- include/linux/ceph/libceph.h | 2 +- include/linux/ceph/messenger.h | 9 +++++---- net/ceph/ceph_common.c | 18 +++++------------- net/ceph/messenger.c | 30 +++++++++--------------------- net/ceph/mon_client.c | 6 +++--- net/ceph/osd_client.c | 4 ++-- 7 files changed, 26 insertions(+), 45 deletions(-) (limited to 'fs') diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index 200bc87eceb1..ad30261cd4c0 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -394,7 +394,7 @@ static struct ceph_mds_session *register_session(struct ceph_mds_client *mdsc, s->s_seq = 0; mutex_init(&s->s_mutex); - ceph_con_init(mdsc->fsc->client->msgr, &s->s_con); + ceph_con_init(&mdsc->fsc->client->msgr, &s->s_con); s->s_con.private = s; s->s_con.ops = &mds_con_ops; s->s_con.peer_name.type = CEPH_ENTITY_TYPE_MDS; diff --git a/include/linux/ceph/libceph.h b/include/linux/ceph/libceph.h index 92eef7c3d3c5..927361c4b0a8 100644 --- a/include/linux/ceph/libceph.h +++ b/include/linux/ceph/libceph.h @@ -131,7 +131,7 @@ struct ceph_client { u32 supported_features; u32 required_features; - struct ceph_messenger *msgr; /* messenger instance */ + struct ceph_messenger msgr; /* messenger instance */ struct ceph_mon_client monc; struct ceph_osd_client osdc; diff --git a/include/linux/ceph/messenger.h b/include/linux/ceph/messenger.h index 74f6c9bd8074..3fbd4be804ed 100644 --- a/include/linux/ceph/messenger.h +++ b/include/linux/ceph/messenger.h @@ -211,10 +211,11 @@ extern int ceph_msgr_init(void); extern void ceph_msgr_exit(void); extern void ceph_msgr_flush(void); -extern struct ceph_messenger *ceph_messenger_create( - struct ceph_entity_addr *myaddr, - u32 features, u32 required); -extern void ceph_messenger_destroy(struct ceph_messenger *); +extern void ceph_messenger_init(struct ceph_messenger *msgr, + struct ceph_entity_addr *myaddr, + u32 supported_features, + u32 required_features, + bool nocrc); extern void ceph_con_init(struct ceph_messenger *msgr, struct ceph_connection *con); diff --git a/net/ceph/ceph_common.c b/net/ceph/ceph_common.c index cc913193d992..2de3ea1bbd64 100644 --- a/net/ceph/ceph_common.c +++ b/net/ceph/ceph_common.c @@ -468,19 +468,15 @@ struct ceph_client *ceph_create_client(struct ceph_options *opt, void *private, /* msgr */ if (ceph_test_opt(client, MYIP)) myaddr = &client->options->my_addr; - client->msgr = ceph_messenger_create(myaddr, - client->supported_features, - client->required_features); - if (IS_ERR(client->msgr)) { - err = PTR_ERR(client->msgr); - goto fail; - } - client->msgr->nocrc = ceph_test_opt(client, NOCRC); + ceph_messenger_init(&client->msgr, myaddr, + client->supported_features, + client->required_features, + ceph_test_opt(client, NOCRC)); /* subsystems */ err = ceph_monc_init(&client->monc, client); if (err < 0) - goto fail_msgr; + goto fail; err = ceph_osdc_init(&client->osdc, client); if (err < 0) goto fail_monc; @@ -489,8 +485,6 @@ struct ceph_client *ceph_create_client(struct ceph_options *opt, void *private, fail_monc: ceph_monc_stop(&client->monc); -fail_msgr: - ceph_messenger_destroy(client->msgr); fail: kfree(client); return ERR_PTR(err); @@ -515,8 +509,6 @@ void ceph_destroy_client(struct ceph_client *client) ceph_debugfs_client_cleanup(client); - ceph_messenger_destroy(client->msgr); - ceph_destroy_options(client->options); kfree(client); diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c index 2ca491fc50e2..d8423a3f6698 100644 --- a/net/ceph/messenger.c +++ b/net/ceph/messenger.c @@ -2245,18 +2245,14 @@ out: /* - * create a new messenger instance + * initialize a new messenger instance */ -struct ceph_messenger *ceph_messenger_create(struct ceph_entity_addr *myaddr, - u32 supported_features, - u32 required_features) +void ceph_messenger_init(struct ceph_messenger *msgr, + struct ceph_entity_addr *myaddr, + u32 supported_features, + u32 required_features, + bool nocrc) { - struct ceph_messenger *msgr; - - msgr = kzalloc(sizeof(*msgr), GFP_KERNEL); - if (msgr == NULL) - return ERR_PTR(-ENOMEM); - msgr->supported_features = supported_features; msgr->required_features = required_features; @@ -2269,19 +2265,11 @@ struct ceph_messenger *ceph_messenger_create(struct ceph_entity_addr *myaddr, msgr->inst.addr.type = 0; get_random_bytes(&msgr->inst.addr.nonce, sizeof(msgr->inst.addr.nonce)); encode_my_addr(msgr); + msgr->nocrc = nocrc; - dout("messenger_create %p\n", msgr); - return msgr; -} -EXPORT_SYMBOL(ceph_messenger_create); - -void ceph_messenger_destroy(struct ceph_messenger *msgr) -{ - dout("destroy %p\n", msgr); - kfree(msgr); - dout("destroyed messenger %p\n", msgr); + dout("%s %p\n", __func__, msgr); } -EXPORT_SYMBOL(ceph_messenger_destroy); +EXPORT_SYMBOL(ceph_messenger_init); static void clear_standby(struct ceph_connection *con) { diff --git a/net/ceph/mon_client.c b/net/ceph/mon_client.c index 1845cde26227..704dc95dc620 100644 --- a/net/ceph/mon_client.c +++ b/net/ceph/mon_client.c @@ -763,7 +763,7 @@ int ceph_monc_init(struct ceph_mon_client *monc, struct ceph_client *cl) monc->con = kmalloc(sizeof(*monc->con), GFP_KERNEL); if (!monc->con) goto out_monmap; - ceph_con_init(monc->client->msgr, monc->con); + ceph_con_init(&monc->client->msgr, monc->con); monc->con->private = monc; monc->con->ops = &mon_con_ops; @@ -880,8 +880,8 @@ static void handle_auth_reply(struct ceph_mon_client *monc, } else if (!was_auth && monc->auth->ops->is_authenticated(monc->auth)) { dout("authenticated, starting session\n"); - monc->client->msgr->inst.name.type = CEPH_ENTITY_TYPE_CLIENT; - monc->client->msgr->inst.name.num = + monc->client->msgr.inst.name.type = CEPH_ENTITY_TYPE_CLIENT; + monc->client->msgr.inst.name.num = cpu_to_le64(monc->auth->global_id); __send_subscribe(monc); diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c index b098e7b591f0..cca4c7f1c780 100644 --- a/net/ceph/osd_client.c +++ b/net/ceph/osd_client.c @@ -639,7 +639,7 @@ static struct ceph_osd *create_osd(struct ceph_osd_client *osdc) INIT_LIST_HEAD(&osd->o_osd_lru); osd->o_incarnation = 1; - ceph_con_init(osdc->client->msgr, &osd->o_con); + ceph_con_init(&osdc->client->msgr, &osd->o_con); osd->o_con.private = osd; osd->o_con.ops = &osd_con_ops; osd->o_con.peer_name.type = CEPH_ENTITY_TYPE_OSD; @@ -1391,7 +1391,7 @@ void ceph_osdc_handle_map(struct ceph_osd_client *osdc, struct ceph_msg *msg) epoch, maplen); newmap = osdmap_apply_incremental(&p, next, osdc->osdmap, - osdc->client->msgr); + &osdc->client->msgr); if (IS_ERR(newmap)) { err = PTR_ERR(newmap); goto bad; -- cgit v1.2.3-58-ga151 From 1bfd89f4e6e1adc6a782d94aa5d4c53be1e404d7 Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Sat, 26 May 2012 23:26:43 -0500 Subject: libceph: fully initialize connection in con_init() Move the initialization of a ceph connection's private pointer, operations vector pointer, and peer name information into ceph_con_init(). Rearrange the arguments so the connection pointer is first. Hide the byte-swapping of the peer entity number inside ceph_con_init() Signed-off-by: Alex Elder Reviewed-by: Sage Weil --- fs/ceph/mds_client.c | 7 ++----- include/linux/ceph/messenger.h | 6 ++++-- net/ceph/messenger.c | 9 ++++++++- net/ceph/mon_client.c | 8 +++----- net/ceph/osd_client.c | 7 ++----- 5 files changed, 19 insertions(+), 18 deletions(-) (limited to 'fs') diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index ad30261cd4c0..ecd7f15741c1 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -394,11 +394,8 @@ static struct ceph_mds_session *register_session(struct ceph_mds_client *mdsc, s->s_seq = 0; mutex_init(&s->s_mutex); - ceph_con_init(&mdsc->fsc->client->msgr, &s->s_con); - s->s_con.private = s; - s->s_con.ops = &mds_con_ops; - s->s_con.peer_name.type = CEPH_ENTITY_TYPE_MDS; - s->s_con.peer_name.num = cpu_to_le64(mds); + ceph_con_init(&s->s_con, s, &mds_con_ops, &mdsc->fsc->client->msgr, + CEPH_ENTITY_TYPE_MDS, mds); spin_lock_init(&s->s_gen_ttl_lock); s->s_cap_gen = 0; diff --git a/include/linux/ceph/messenger.h b/include/linux/ceph/messenger.h index 5e852f444f68..dd27837f79ac 100644 --- a/include/linux/ceph/messenger.h +++ b/include/linux/ceph/messenger.h @@ -227,8 +227,10 @@ extern void ceph_messenger_init(struct ceph_messenger *msgr, u32 required_features, bool nocrc); -extern void ceph_con_init(struct ceph_messenger *msgr, - struct ceph_connection *con); +extern void ceph_con_init(struct ceph_connection *con, void *private, + const struct ceph_connection_operations *ops, + struct ceph_messenger *msgr, __u8 entity_type, + __u64 entity_num); extern void ceph_con_open(struct ceph_connection *con, struct ceph_entity_addr *addr); extern bool ceph_con_opened(struct ceph_connection *con); diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c index 36b440a00cc2..3b65f6e6911b 100644 --- a/net/ceph/messenger.c +++ b/net/ceph/messenger.c @@ -521,15 +521,22 @@ void ceph_con_put(struct ceph_connection *con) /* * initialize a new connection. */ -void ceph_con_init(struct ceph_messenger *msgr, struct ceph_connection *con) +void ceph_con_init(struct ceph_connection *con, void *private, + const struct ceph_connection_operations *ops, + struct ceph_messenger *msgr, __u8 entity_type, __u64 entity_num) { dout("con_init %p\n", con); memset(con, 0, sizeof(*con)); + con->private = private; + con->ops = ops; atomic_set(&con->nref, 1); con->msgr = msgr; con_sock_state_init(con); + con->peer_name.type = (__u8) entity_type; + con->peer_name.num = cpu_to_le64(entity_num); + mutex_init(&con->mutex); INIT_LIST_HEAD(&con->out_queue); INIT_LIST_HEAD(&con->out_sent); diff --git a/net/ceph/mon_client.c b/net/ceph/mon_client.c index 6adbea78b168..ab6b24a5169e 100644 --- a/net/ceph/mon_client.c +++ b/net/ceph/mon_client.c @@ -142,11 +142,9 @@ static int __open_session(struct ceph_mon_client *monc) monc->sub_renew_after = jiffies; /* i.e., expired */ monc->want_next_osdmap = !!monc->want_next_osdmap; - ceph_con_init(&monc->client->msgr, &monc->con); - monc->con.private = monc; - monc->con.ops = &mon_con_ops; - monc->con.peer_name.type = CEPH_ENTITY_TYPE_MON; - monc->con.peer_name.num = cpu_to_le64(monc->cur_mon); + ceph_con_init(&monc->con, monc, &mon_con_ops, + &monc->client->msgr, + CEPH_ENTITY_TYPE_MON, monc->cur_mon); dout("open_session mon%d opening\n", monc->cur_mon); ceph_con_open(&monc->con, diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c index 5b41a6929cd9..448c9da8beff 100644 --- a/net/ceph/osd_client.c +++ b/net/ceph/osd_client.c @@ -640,11 +640,8 @@ static struct ceph_osd *create_osd(struct ceph_osd_client *osdc, int onum) INIT_LIST_HEAD(&osd->o_osd_lru); osd->o_incarnation = 1; - ceph_con_init(&osdc->client->msgr, &osd->o_con); - osd->o_con.private = osd; - osd->o_con.ops = &osd_con_ops; - osd->o_con.peer_name.type = CEPH_ENTITY_TYPE_OSD; - osd->o_con.peer_name.num = cpu_to_le64(onum); + ceph_con_init(&osd->o_con, osd, &osd_con_ops, &osdc->client->msgr, + CEPH_ENTITY_TYPE_OSD, onum); INIT_LIST_HEAD(&osd->o_keepalive_item); return osd; -- cgit v1.2.3-58-ga151 From b7a9e5dd40f17a48a72f249b8bbc989b63bae5fd Mon Sep 17 00:00:00 2001 From: Sage Weil Date: Wed, 27 Jun 2012 12:24:08 -0700 Subject: libceph: set peer name on con_open, not init The peer name may change on each open attempt, even when the connection is reused. Signed-off-by: Sage Weil --- fs/ceph/mds_client.c | 7 ++++--- include/linux/ceph/messenger.h | 4 ++-- net/ceph/messenger.c | 12 +++++++----- net/ceph/mon_client.c | 4 ++-- net/ceph/osd_client.c | 10 ++++++---- 5 files changed, 21 insertions(+), 16 deletions(-) (limited to 'fs') diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index ecd7f15741c1..5ac6434185ae 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -394,8 +394,7 @@ static struct ceph_mds_session *register_session(struct ceph_mds_client *mdsc, s->s_seq = 0; mutex_init(&s->s_mutex); - ceph_con_init(&s->s_con, s, &mds_con_ops, &mdsc->fsc->client->msgr, - CEPH_ENTITY_TYPE_MDS, mds); + ceph_con_init(&s->s_con, s, &mds_con_ops, &mdsc->fsc->client->msgr); spin_lock_init(&s->s_gen_ttl_lock); s->s_cap_gen = 0; @@ -437,7 +436,8 @@ static struct ceph_mds_session *register_session(struct ceph_mds_client *mdsc, mdsc->sessions[mds] = s; atomic_inc(&s->s_ref); /* one ref to sessions[], one to caller */ - ceph_con_open(&s->s_con, ceph_mdsmap_get_addr(mdsc->mdsmap, mds)); + ceph_con_open(&s->s_con, CEPH_ENTITY_TYPE_MDS, mds, + ceph_mdsmap_get_addr(mdsc->mdsmap, mds)); return s; @@ -2529,6 +2529,7 @@ static void send_mds_reconnect(struct ceph_mds_client *mdsc, session->s_seq = 0; ceph_con_open(&session->s_con, + CEPH_ENTITY_TYPE_MDS, mds, ceph_mdsmap_get_addr(mdsc->mdsmap, mds)); /* replay unsafe requests */ diff --git a/include/linux/ceph/messenger.h b/include/linux/ceph/messenger.h index dd4ef1f8ec93..478f814f2100 100644 --- a/include/linux/ceph/messenger.h +++ b/include/linux/ceph/messenger.h @@ -232,9 +232,9 @@ extern void ceph_messenger_init(struct ceph_messenger *msgr, extern void ceph_con_init(struct ceph_connection *con, void *private, const struct ceph_connection_operations *ops, - struct ceph_messenger *msgr, __u8 entity_type, - __u64 entity_num); + struct ceph_messenger *msgr); extern void ceph_con_open(struct ceph_connection *con, + __u8 entity_type, __u64 entity_num, struct ceph_entity_addr *addr); extern bool ceph_con_opened(struct ceph_connection *con); extern void ceph_con_close(struct ceph_connection *con); diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c index dcc50e4cd5cd..ae082d95fc72 100644 --- a/net/ceph/messenger.c +++ b/net/ceph/messenger.c @@ -523,12 +523,17 @@ EXPORT_SYMBOL(ceph_con_close); /* * Reopen a closed connection, with a new peer address. */ -void ceph_con_open(struct ceph_connection *con, struct ceph_entity_addr *addr) +void ceph_con_open(struct ceph_connection *con, + __u8 entity_type, __u64 entity_num, + struct ceph_entity_addr *addr) { dout("con_open %p %s\n", con, ceph_pr_addr(&addr->in_addr)); set_bit(OPENING, &con->state); WARN_ON(!test_and_clear_bit(CLOSED, &con->state)); + con->peer_name.type = (__u8) entity_type; + con->peer_name.num = cpu_to_le64(entity_num); + memcpy(&con->peer_addr, addr, sizeof(*addr)); con->delay = 0; /* reset backoff memory */ queue_con(con); @@ -548,7 +553,7 @@ bool ceph_con_opened(struct ceph_connection *con) */ void ceph_con_init(struct ceph_connection *con, void *private, const struct ceph_connection_operations *ops, - struct ceph_messenger *msgr, __u8 entity_type, __u64 entity_num) + struct ceph_messenger *msgr) { dout("con_init %p\n", con); memset(con, 0, sizeof(*con)); @@ -558,9 +563,6 @@ void ceph_con_init(struct ceph_connection *con, void *private, con_sock_state_init(con); - con->peer_name.type = (__u8) entity_type; - con->peer_name.num = cpu_to_le64(entity_num); - mutex_init(&con->mutex); INIT_LIST_HEAD(&con->out_queue); INIT_LIST_HEAD(&con->out_sent); diff --git a/net/ceph/mon_client.c b/net/ceph/mon_client.c index e9db3de20b2e..bcc80a0e2a98 100644 --- a/net/ceph/mon_client.c +++ b/net/ceph/mon_client.c @@ -143,11 +143,11 @@ static int __open_session(struct ceph_mon_client *monc) monc->want_next_osdmap = !!monc->want_next_osdmap; ceph_con_init(&monc->con, monc, &mon_con_ops, - &monc->client->msgr, - CEPH_ENTITY_TYPE_MON, monc->cur_mon); + &monc->client->msgr); dout("open_session mon%d opening\n", monc->cur_mon); ceph_con_open(&monc->con, + CEPH_ENTITY_TYPE_MON, monc->cur_mon, &monc->monmap->mon_inst[monc->cur_mon].addr); /* initiatiate authentication handshake */ diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c index db2da54f7336..c2527113d2ae 100644 --- a/net/ceph/osd_client.c +++ b/net/ceph/osd_client.c @@ -639,8 +639,7 @@ static struct ceph_osd *create_osd(struct ceph_osd_client *osdc, int onum) INIT_LIST_HEAD(&osd->o_osd_lru); osd->o_incarnation = 1; - ceph_con_init(&osd->o_con, osd, &osd_con_ops, &osdc->client->msgr, - CEPH_ENTITY_TYPE_OSD, onum); + ceph_con_init(&osd->o_con, osd, &osd_con_ops, &osdc->client->msgr); INIT_LIST_HEAD(&osd->o_keepalive_item); return osd; @@ -750,7 +749,8 @@ static int __reset_osd(struct ceph_osd_client *osdc, struct ceph_osd *osd) ret = -EAGAIN; } else { ceph_con_close(&osd->o_con); - ceph_con_open(&osd->o_con, &osdc->osdmap->osd_addr[osd->o_osd]); + ceph_con_open(&osd->o_con, CEPH_ENTITY_TYPE_OSD, osd->o_osd, + &osdc->osdmap->osd_addr[osd->o_osd]); osd->o_incarnation++; } return ret; @@ -1005,7 +1005,9 @@ static int __map_request(struct ceph_osd_client *osdc, dout("map_request osd %p is osd%d\n", req->r_osd, o); __insert_osd(osdc, req->r_osd); - ceph_con_open(&req->r_osd->o_con, &osdc->osdmap->osd_addr[o]); + ceph_con_open(&req->r_osd->o_con, + CEPH_ENTITY_TYPE_OSD, o, + &osdc->osdmap->osd_addr[o]); } if (req->r_osd) { -- cgit v1.2.3-58-ga151 From 8842b3be96c376f174ae0d4f282d14728ad5febf Mon Sep 17 00:00:00 2001 From: Sage Weil Date: Thu, 7 Jun 2012 13:43:35 -0700 Subject: ceph: clean up useless d_parent checks d_parent is never NULL, and IS_ROOT() is the proper way to check for a (non-self-referential) parent. Reported-by: Al Viro Signed-off-by: Sage Weil --- fs/ceph/dir.c | 7 +++---- fs/ceph/mds_client.c | 11 ----------- 2 files changed, 3 insertions(+), 15 deletions(-) (limited to 'fs') diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c index 3e8094be4604..6a66bd2d4da0 100644 --- a/fs/ceph/dir.c +++ b/fs/ceph/dir.c @@ -51,8 +51,7 @@ int ceph_init_dentry(struct dentry *dentry) goto out_unlock; } - if (dentry->d_parent == NULL || /* nfs fh_to_dentry */ - ceph_snap(dentry->d_parent->d_inode) == CEPH_NOSNAP) + if (ceph_snap(dentry->d_parent->d_inode) == CEPH_NOSNAP) d_set_d_op(dentry, &ceph_dentry_ops); else if (ceph_snap(dentry->d_parent->d_inode) == CEPH_SNAPDIR) d_set_d_op(dentry, &ceph_snapdir_dentry_ops); @@ -79,7 +78,7 @@ struct inode *ceph_get_dentry_parent_inode(struct dentry *dentry) return NULL; spin_lock(&dentry->d_lock); - if (dentry->d_parent) { + if (!IS_ROOT(dentry)) { inode = dentry->d_parent->d_inode; ihold(inode); } @@ -1140,7 +1139,7 @@ static void ceph_d_prune(struct dentry *dentry) dout("ceph_d_prune %p\n", dentry); /* do we have a valid parent? */ - if (!dentry->d_parent || IS_ROOT(dentry)) + if (IS_ROOT(dentry)) return; /* if we are not hashed, we don't affect D_COMPLETE */ diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index 5ac6434185ae..418f6a82c90d 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -1469,11 +1469,6 @@ retry: else len += 1 + temp->d_name.len; temp = temp->d_parent; - if (temp == NULL) { - rcu_read_unlock(); - pr_err("build_path corrupt dentry %p\n", dentry); - return ERR_PTR(-EINVAL); - } } rcu_read_unlock(); if (len) @@ -1510,12 +1505,6 @@ retry: if (pos) path[--pos] = '/'; temp = temp->d_parent; - if (temp == NULL) { - rcu_read_unlock(); - pr_err("build_path corrupt dentry\n"); - kfree(path); - return ERR_PTR(-EINVAL); - } } rcu_read_unlock(); if (pos != 0 || read_seqretry(&rename_lock, seq)) { -- cgit v1.2.3-58-ga151 From 1fe60e51a3744528f3939b1b1167ca909133d9ae Mon Sep 17 00:00:00 2001 From: Sage Weil Date: Mon, 30 Jul 2012 16:23:22 -0700 Subject: libceph: move feature bits to separate header This is simply cleanup that will keep things more closely synced with the userland code. Signed-off-by: Sage Weil Reviewed-by: Alex Elder Reviewed-by: Yehuda Sadeh --- fs/ceph/mds_client.c | 1 + fs/ceph/super.c | 1 + include/linux/ceph/ceph_features.h | 24 ++++++++++++++++++++++++ include/linux/ceph/ceph_fs.h | 14 -------------- include/linux/ceph/libceph.h | 6 ------ net/ceph/ceph_common.c | 5 +++-- 6 files changed, 29 insertions(+), 22 deletions(-) create mode 100644 include/linux/ceph/ceph_features.h (limited to 'fs') diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index 418f6a82c90d..39b76d66bc5d 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -10,6 +10,7 @@ #include "super.h" #include "mds_client.h" +#include #include #include #include diff --git a/fs/ceph/super.c b/fs/ceph/super.c index 1e67dd7305a4..2c47ecfe4373 100644 --- a/fs/ceph/super.c +++ b/fs/ceph/super.c @@ -18,6 +18,7 @@ #include "super.h" #include "mds_client.h" +#include #include #include #include diff --git a/include/linux/ceph/ceph_features.h b/include/linux/ceph/ceph_features.h new file mode 100644 index 000000000000..342f93dbe162 --- /dev/null +++ b/include/linux/ceph/ceph_features.h @@ -0,0 +1,24 @@ +#ifndef __CEPH_FEATURES +#define __CEPH_FEATURES + +/* + * feature bits + */ +#define CEPH_FEATURE_UID (1<<0) +#define CEPH_FEATURE_NOSRCADDR (1<<1) +#define CEPH_FEATURE_MONCLOCKCHECK (1<<2) +#define CEPH_FEATURE_FLOCK (1<<3) +#define CEPH_FEATURE_SUBSCRIBE2 (1<<4) +#define CEPH_FEATURE_MONNAMES (1<<5) +#define CEPH_FEATURE_RECONNECT_SEQ (1<<6) +#define CEPH_FEATURE_DIRLAYOUTHASH (1<<7) + +/* + * Features supported. + */ +#define CEPH_FEATURES_SUPPORTED_DEFAULT \ + (CEPH_FEATURE_NOSRCADDR) + +#define CEPH_FEATURES_REQUIRED_DEFAULT \ + (CEPH_FEATURE_NOSRCADDR) +#endif diff --git a/include/linux/ceph/ceph_fs.h b/include/linux/ceph/ceph_fs.h index e81ab30d4896..d021610efd65 100644 --- a/include/linux/ceph/ceph_fs.h +++ b/include/linux/ceph/ceph_fs.h @@ -35,20 +35,6 @@ /* arbitrary limit on max # of monitors (cluster of 3 is typical) */ #define CEPH_MAX_MON 31 - -/* - * feature bits - */ -#define CEPH_FEATURE_UID (1<<0) -#define CEPH_FEATURE_NOSRCADDR (1<<1) -#define CEPH_FEATURE_MONCLOCKCHECK (1<<2) -#define CEPH_FEATURE_FLOCK (1<<3) -#define CEPH_FEATURE_SUBSCRIBE2 (1<<4) -#define CEPH_FEATURE_MONNAMES (1<<5) -#define CEPH_FEATURE_RECONNECT_SEQ (1<<6) -#define CEPH_FEATURE_DIRLAYOUTHASH (1<<7) - - /* * ceph_file_layout - describe data layout for a file/inode */ diff --git a/include/linux/ceph/libceph.h b/include/linux/ceph/libceph.h index 98ec36ae8a3b..ea072e1f9db9 100644 --- a/include/linux/ceph/libceph.h +++ b/include/linux/ceph/libceph.h @@ -22,12 +22,6 @@ #include "osd_client.h" #include "ceph_fs.h" -/* - * Supported features - */ -#define CEPH_FEATURE_SUPPORTED_DEFAULT CEPH_FEATURE_NOSRCADDR -#define CEPH_FEATURE_REQUIRED_DEFAULT CEPH_FEATURE_NOSRCADDR - /* * mount options */ diff --git a/net/ceph/ceph_common.c b/net/ceph/ceph_common.c index 3b45e01fa8d1..69e38db28e5f 100644 --- a/net/ceph/ceph_common.c +++ b/net/ceph/ceph_common.c @@ -17,6 +17,7 @@ #include +#include #include #include #include @@ -460,9 +461,9 @@ struct ceph_client *ceph_create_client(struct ceph_options *opt, void *private, client->auth_err = 0; client->extra_mon_dispatch = NULL; - client->supported_features = CEPH_FEATURE_SUPPORTED_DEFAULT | + client->supported_features = CEPH_FEATURES_SUPPORTED_DEFAULT | supported_features; - client->required_features = CEPH_FEATURE_REQUIRED_DEFAULT | + client->required_features = CEPH_FEATURES_REQUIRED_DEFAULT | required_features; /* msgr */ -- cgit v1.2.3-58-ga151 From a53aab645c82f0146e35684b34692c69b5118121 Mon Sep 17 00:00:00 2001 From: Sage Weil Date: Mon, 30 Jul 2012 16:21:17 -0700 Subject: ceph: close old con before reopening on mds reconnect When we detect a mds session reset, close the old ceph_connection before reopening it. This ensures we clean up the old socket properly and keep the ceph_connection state correct. Signed-off-by: Sage Weil Reviewed-by: Alex Elder Reviewed-by: Yehuda Sadeh --- fs/ceph/mds_client.c | 1 + 1 file changed, 1 insertion(+) (limited to 'fs') diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index 39b76d66bc5d..a5a735422aa7 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -2518,6 +2518,7 @@ static void send_mds_reconnect(struct ceph_mds_client *mdsc, session->s_state = CEPH_MDS_SESSION_RECONNECTING; session->s_seq = 0; + ceph_con_close(&session->s_con); ceph_con_open(&session->s_con, CEPH_ENTITY_TYPE_MDS, mds, ceph_mdsmap_get_addr(mdsc->mdsmap, mds)); -- cgit v1.2.3-58-ga151 From 21ec6ffa46719a4ed45531b5b01014c26f0416c4 Mon Sep 17 00:00:00 2001 From: Alan Cox Date: Fri, 20 Jul 2012 08:18:36 -0500 Subject: ceph: fix potential double free We re-run the loop but we don't re-set the attrs pointer back to NULL. Signed-off-by: Alan Cox Reviewed-by: Alex Elder --- fs/ceph/xattr.c | 1 + 1 file changed, 1 insertion(+) (limited to 'fs') diff --git a/fs/ceph/xattr.c b/fs/ceph/xattr.c index 785cb3057c95..2c2ae5be9902 100644 --- a/fs/ceph/xattr.c +++ b/fs/ceph/xattr.c @@ -457,6 +457,7 @@ start: for (i = 0; i < numattr; i++) kfree(xattrs[i]); kfree(xattrs); + xattrs = NULL; goto start; } err = -EIO; -- cgit v1.2.3-58-ga151 From aa711ee3402ad10ffd5b70ce0417fadc9a95cccf Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Fri, 13 Jul 2012 20:35:11 -0500 Subject: ceph: define snap counts as u32 everywhere There are two structures in which a count of snapshots are maintained: struct ceph_snap_context { ... u32 num_snaps; ... } and struct ceph_snap_realm { ... u32 num_prior_parent_snaps; /* had prior to parent_since */ ... u32 num_snaps; ... } These fields never take on negative values (e.g., to hold special meaning), and so are really inherently unsigned. Furthermore they take their value from over-the-wire or on-disk formatted 32-bit values. So change their definition to have type u32, and change some spots elsewhere in the code to account for this change. Signed-off-by: Alex Elder Reviewed-by: Josh Durgin --- fs/ceph/snap.c | 18 ++++++++++-------- fs/ceph/super.h | 4 ++-- include/linux/ceph/libceph.h | 2 +- 3 files changed, 13 insertions(+), 11 deletions(-) (limited to 'fs') diff --git a/fs/ceph/snap.c b/fs/ceph/snap.c index e5206fc76562..cbb2f54a3019 100644 --- a/fs/ceph/snap.c +++ b/fs/ceph/snap.c @@ -296,8 +296,7 @@ static int build_snap_context(struct ceph_snap_realm *realm) struct ceph_snap_realm *parent = realm->parent; struct ceph_snap_context *snapc; int err = 0; - int i; - int num = realm->num_prior_parent_snaps + realm->num_snaps; + u32 num = realm->num_prior_parent_snaps + realm->num_snaps; /* * build parent context, if it hasn't been built. @@ -321,11 +320,11 @@ static int build_snap_context(struct ceph_snap_realm *realm) realm->cached_context->seq == realm->seq && (!parent || realm->cached_context->seq >= parent->cached_context->seq)) { - dout("build_snap_context %llx %p: %p seq %lld (%d snaps)" + dout("build_snap_context %llx %p: %p seq %lld (%u snaps)" " (unchanged)\n", realm->ino, realm, realm->cached_context, realm->cached_context->seq, - realm->cached_context->num_snaps); + (unsigned int) realm->cached_context->num_snaps); return 0; } @@ -342,6 +341,8 @@ static int build_snap_context(struct ceph_snap_realm *realm) num = 0; snapc->seq = realm->seq; if (parent) { + u32 i; + /* include any of parent's snaps occurring _after_ my parent became my parent */ for (i = 0; i < parent->cached_context->num_snaps; i++) @@ -361,8 +362,9 @@ static int build_snap_context(struct ceph_snap_realm *realm) sort(snapc->snaps, num, sizeof(u64), cmpu64_rev, NULL); snapc->num_snaps = num; - dout("build_snap_context %llx %p: %p seq %lld (%d snaps)\n", - realm->ino, realm, snapc, snapc->seq, snapc->num_snaps); + dout("build_snap_context %llx %p: %p seq %lld (%u snaps)\n", + realm->ino, realm, snapc, snapc->seq, + (unsigned int) snapc->num_snaps); if (realm->cached_context) ceph_put_snap_context(realm->cached_context); @@ -402,9 +404,9 @@ static void rebuild_snap_realms(struct ceph_snap_realm *realm) * helper to allocate and decode an array of snapids. free prior * instance, if any. */ -static int dup_array(u64 **dst, __le64 *src, int num) +static int dup_array(u64 **dst, __le64 *src, u32 num) { - int i; + u32 i; kfree(*dst); if (num) { diff --git a/fs/ceph/super.h b/fs/ceph/super.h index fc35036d258d..3ea48b7b98b3 100644 --- a/fs/ceph/super.h +++ b/fs/ceph/super.h @@ -612,9 +612,9 @@ struct ceph_snap_realm { u64 parent_since; /* snapid when our current parent became so */ u64 *prior_parent_snaps; /* snaps inherited from any parents we */ - int num_prior_parent_snaps; /* had prior to parent_since */ + u32 num_prior_parent_snaps; /* had prior to parent_since */ u64 *snaps; /* snaps specific to this realm */ - int num_snaps; + u32 num_snaps; struct ceph_snap_realm *parent; struct list_head children; /* list of child realms */ diff --git a/include/linux/ceph/libceph.h b/include/linux/ceph/libceph.h index ea072e1f9db9..42624789b06f 100644 --- a/include/linux/ceph/libceph.h +++ b/include/linux/ceph/libceph.h @@ -154,7 +154,7 @@ struct ceph_client { struct ceph_snap_context { atomic_t nref; u64 seq; - int num_snaps; + u32 num_snaps; u64 snaps[]; }; -- cgit v1.2.3-58-ga151