diff options
author | Trond Myklebust <Trond.Myklebust@netapp.com> | 2008-03-19 17:59:44 -0400 |
---|---|---|
committer | Trond Myklebust <Trond.Myklebust@netapp.com> | 2008-03-19 17:59:44 -0400 |
commit | c7c350e92aab1bba68f26a6027b734adcf9824ba (patch) | |
tree | aa99bd94c3049dd871d9c030d70a5f3d87591a95 /fs | |
parent | 2f42b5d043ee271d1e5d30ecd77186b6c4d4e534 (diff) | |
parent | f8512ad0da16cbe156f3a7627971cdf0b39c4138 (diff) |
Merge branch 'hotfixes' into devel
Diffstat (limited to 'fs')
-rw-r--r-- | fs/bio.c | 2 | ||||
-rw-r--r-- | fs/hfs/brec.c | 18 | ||||
-rw-r--r-- | fs/nfs/read.c | 5 | ||||
-rw-r--r-- | fs/nfs/write.c | 8 | ||||
-rw-r--r-- | fs/nfsd/nfsfh.c | 4 | ||||
-rw-r--r-- | fs/ocfs2/cluster/tcp.c | 9 | ||||
-rw-r--r-- | fs/ocfs2/dlm/dlmcommon.h | 21 | ||||
-rw-r--r-- | fs/ocfs2/dlm/dlmconvert.c | 2 | ||||
-rw-r--r-- | fs/ocfs2/dlm/dlmdomain.c | 103 | ||||
-rw-r--r-- | fs/ocfs2/dlm/dlmmaster.c | 18 | ||||
-rw-r--r-- | fs/ocfs2/dlm/dlmrecovery.c | 57 | ||||
-rw-r--r-- | fs/ocfs2/dlm/dlmthread.c | 6 | ||||
-rw-r--r-- | fs/ocfs2/dlmglue.c | 2 | ||||
-rw-r--r-- | fs/ocfs2/resize.c | 2 | ||||
-rw-r--r-- | fs/proc/base.c | 25 | ||||
-rw-r--r-- | fs/proc/generic.c | 26 | ||||
-rw-r--r-- | fs/proc/internal.h | 7 | ||||
-rw-r--r-- | fs/proc/proc_net.c | 117 | ||||
-rw-r--r-- | fs/proc/task_mmu.c | 18 |
19 files changed, 332 insertions, 118 deletions
@@ -1194,6 +1194,8 @@ EXPORT_SYMBOL(bio_hw_segments); EXPORT_SYMBOL(bio_add_page); EXPORT_SYMBOL(bio_add_pc_page); EXPORT_SYMBOL(bio_get_nr_vecs); +EXPORT_SYMBOL(bio_map_user); +EXPORT_SYMBOL(bio_unmap_user); EXPORT_SYMBOL(bio_map_kern); EXPORT_SYMBOL(bio_pair_release); EXPORT_SYMBOL(bio_split); diff --git a/fs/hfs/brec.c b/fs/hfs/brec.c index 878bf25dbc6..92fb358ce82 100644 --- a/fs/hfs/brec.c +++ b/fs/hfs/brec.c @@ -229,7 +229,7 @@ skip: static struct hfs_bnode *hfs_bnode_split(struct hfs_find_data *fd) { struct hfs_btree *tree; - struct hfs_bnode *node, *new_node; + struct hfs_bnode *node, *new_node, *next_node; struct hfs_bnode_desc node_desc; int num_recs, new_rec_off, new_off, old_rec_off; int data_start, data_end, size; @@ -248,6 +248,17 @@ static struct hfs_bnode *hfs_bnode_split(struct hfs_find_data *fd) new_node->type = node->type; new_node->height = node->height; + if (node->next) + next_node = hfs_bnode_find(tree, node->next); + else + next_node = NULL; + + if (IS_ERR(next_node)) { + hfs_bnode_put(node); + hfs_bnode_put(new_node); + return next_node; + } + size = tree->node_size / 2 - node->num_recs * 2 - 14; old_rec_off = tree->node_size - 4; num_recs = 1; @@ -261,6 +272,8 @@ static struct hfs_bnode *hfs_bnode_split(struct hfs_find_data *fd) /* panic? */ hfs_bnode_put(node); hfs_bnode_put(new_node); + if (next_node) + hfs_bnode_put(next_node); return ERR_PTR(-ENOSPC); } @@ -315,8 +328,7 @@ static struct hfs_bnode *hfs_bnode_split(struct hfs_find_data *fd) hfs_bnode_write(node, &node_desc, 0, sizeof(node_desc)); /* update next bnode header */ - if (new_node->next) { - struct hfs_bnode *next_node = hfs_bnode_find(tree, new_node->next); + if (next_node) { next_node->prev = new_node->this; hfs_bnode_read(next_node, &node_desc, 0, sizeof(node_desc)); node_desc.prev = cpu_to_be32(next_node->prev); diff --git a/fs/nfs/read.c b/fs/nfs/read.c index be9e8270f4d..ab2f7d233e0 100644 --- a/fs/nfs/read.c +++ b/fs/nfs/read.c @@ -531,7 +531,10 @@ readpage_async_filler(void *data, struct page *page) if (len < PAGE_CACHE_SIZE) zero_user_segment(page, len, PAGE_CACHE_SIZE); - nfs_pageio_add_request(desc->pgio, new); + if (!nfs_pageio_add_request(desc->pgio, new)) { + error = desc->pgio->pg_error; + goto out_unlock; + } return 0; out_error: error = PTR_ERR(new); diff --git a/fs/nfs/write.c b/fs/nfs/write.c index 1667e398441..4cb88df12f8 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -39,6 +39,7 @@ static struct nfs_page * nfs_update_request(struct nfs_open_context*, unsigned int, unsigned int); static void nfs_pageio_init_write(struct nfs_pageio_descriptor *desc, struct inode *inode, int ioflags); +static void nfs_redirty_request(struct nfs_page *req); static const struct rpc_call_ops nfs_write_partial_ops; static const struct rpc_call_ops nfs_write_full_ops; static const struct rpc_call_ops nfs_commit_ops; @@ -279,7 +280,12 @@ static int nfs_page_async_flush(struct nfs_pageio_descriptor *pgio, BUG(); } spin_unlock(&inode->i_lock); - nfs_pageio_add_request(pgio, req); + if (!nfs_pageio_add_request(pgio, req)) { + nfs_redirty_request(req); + nfs_end_page_writeback(page); + nfs_clear_page_tag_locked(req); + return pgio->pg_error; + } return 0; } diff --git a/fs/nfsd/nfsfh.c b/fs/nfsd/nfsfh.c index 1eb771d79cc..3e6b3f41ee1 100644 --- a/fs/nfsd/nfsfh.c +++ b/fs/nfsd/nfsfh.c @@ -232,6 +232,7 @@ fh_verify(struct svc_rqst *rqstp, struct svc_fh *fhp, int type, int access) fhp->fh_dentry = dentry; fhp->fh_export = exp; nfsd_nr_verified++; + cache_get(&exp->h); } else { /* * just rechecking permissions @@ -241,6 +242,7 @@ fh_verify(struct svc_rqst *rqstp, struct svc_fh *fhp, int type, int access) dprintk("nfsd: fh_verify - just checking\n"); dentry = fhp->fh_dentry; exp = fhp->fh_export; + cache_get(&exp->h); /* * Set user creds for this exportpoint; necessary even * in the "just checking" case because this may be a @@ -252,8 +254,6 @@ fh_verify(struct svc_rqst *rqstp, struct svc_fh *fhp, int type, int access) if (error) goto out; } - cache_get(&exp->h); - error = nfsd_mode_check(rqstp, dentry->d_inode->i_mode, type); if (error) diff --git a/fs/ocfs2/cluster/tcp.c b/fs/ocfs2/cluster/tcp.c index ee50c9610e7..b8057c51b20 100644 --- a/fs/ocfs2/cluster/tcp.c +++ b/fs/ocfs2/cluster/tcp.c @@ -451,9 +451,9 @@ static void o2net_set_nn_state(struct o2net_node *nn, /* delay if we're withing a RECONNECT_DELAY of the * last attempt */ delay = (nn->nn_last_connect_attempt + - msecs_to_jiffies(o2net_reconnect_delay(sc->sc_node))) + msecs_to_jiffies(o2net_reconnect_delay(NULL))) - jiffies; - if (delay > msecs_to_jiffies(o2net_reconnect_delay(sc->sc_node))) + if (delay > msecs_to_jiffies(o2net_reconnect_delay(NULL))) delay = 0; mlog(ML_CONN, "queueing conn attempt in %lu jiffies\n", delay); queue_delayed_work(o2net_wq, &nn->nn_connect_work, delay); @@ -1552,12 +1552,11 @@ static void o2net_connect_expired(struct work_struct *work) spin_lock(&nn->nn_lock); if (!nn->nn_sc_valid) { - struct o2nm_node *node = nn->nn_sc->sc_node; mlog(ML_ERROR, "no connection established with node %u after " "%u.%u seconds, giving up and returning errors.\n", o2net_num_from_nn(nn), - o2net_idle_timeout(node) / 1000, - o2net_idle_timeout(node) % 1000); + o2net_idle_timeout(NULL) / 1000, + o2net_idle_timeout(NULL) % 1000); o2net_set_nn_state(nn, NULL, 0, -ENOTCONN); } diff --git a/fs/ocfs2/dlm/dlmcommon.h b/fs/ocfs2/dlm/dlmcommon.h index 9843ee17ea2..dc8ea666efd 100644 --- a/fs/ocfs2/dlm/dlmcommon.h +++ b/fs/ocfs2/dlm/dlmcommon.h @@ -176,6 +176,7 @@ struct dlm_mig_lockres_priv { struct dlm_lock_resource *lockres; u8 real_master; + u8 extra_ref; }; struct dlm_assert_master_priv @@ -602,17 +603,19 @@ enum dlm_query_join_response_code { JOIN_PROTOCOL_MISMATCH, }; +struct dlm_query_join_packet { + u8 code; /* Response code. dlm_minor and fs_minor + are only valid if this is JOIN_OK */ + u8 dlm_minor; /* The minor version of the protocol the + dlm is speaking. */ + u8 fs_minor; /* The minor version of the protocol the + filesystem is speaking. */ + u8 reserved; +}; + union dlm_query_join_response { u32 intval; - struct { - u8 code; /* Response code. dlm_minor and fs_minor - are only valid if this is JOIN_OK */ - u8 dlm_minor; /* The minor version of the protocol the - dlm is speaking. */ - u8 fs_minor; /* The minor version of the protocol the - filesystem is speaking. */ - u8 reserved; - } packet; + struct dlm_query_join_packet packet; }; struct dlm_lock_request diff --git a/fs/ocfs2/dlm/dlmconvert.c b/fs/ocfs2/dlm/dlmconvert.c index ecb4d997221..75997b4deaf 100644 --- a/fs/ocfs2/dlm/dlmconvert.c +++ b/fs/ocfs2/dlm/dlmconvert.c @@ -487,7 +487,7 @@ int dlm_convert_lock_handler(struct o2net_msg *msg, u32 len, void *data, "cookie=%u:%llu\n", dlm_get_lock_cookie_node(be64_to_cpu(cnv->cookie)), dlm_get_lock_cookie_seq(be64_to_cpu(cnv->cookie))); - __dlm_print_one_lock_resource(res); + dlm_print_one_lock_resource(res); goto leave; } diff --git a/fs/ocfs2/dlm/dlmdomain.c b/fs/ocfs2/dlm/dlmdomain.c index 638d2ebb892..0879d86113e 100644 --- a/fs/ocfs2/dlm/dlmdomain.c +++ b/fs/ocfs2/dlm/dlmdomain.c @@ -713,14 +713,46 @@ static int dlm_query_join_proto_check(char *proto_type, int node, return rc; } +/* + * struct dlm_query_join_packet is made up of four one-byte fields. They + * are effectively in big-endian order already. However, little-endian + * machines swap them before putting the packet on the wire (because + * query_join's response is a status, and that status is treated as a u32 + * on the wire). Thus, a big-endian and little-endian machines will treat + * this structure differently. + * + * The solution is to have little-endian machines swap the structure when + * converting from the structure to the u32 representation. This will + * result in the structure having the correct format on the wire no matter + * the host endian format. + */ +static void dlm_query_join_packet_to_wire(struct dlm_query_join_packet *packet, + u32 *wire) +{ + union dlm_query_join_response response; + + response.packet = *packet; + *wire = cpu_to_be32(response.intval); +} + +static void dlm_query_join_wire_to_packet(u32 wire, + struct dlm_query_join_packet *packet) +{ + union dlm_query_join_response response; + + response.intval = cpu_to_be32(wire); + *packet = response.packet; +} + static int dlm_query_join_handler(struct o2net_msg *msg, u32 len, void *data, void **ret_data) { struct dlm_query_join_request *query; - union dlm_query_join_response response = { - .packet.code = JOIN_DISALLOW, + struct dlm_query_join_packet packet = { + .code = JOIN_DISALLOW, }; struct dlm_ctxt *dlm = NULL; + u32 response; u8 nodenum; query = (struct dlm_query_join_request *) msg->buf; @@ -737,11 +769,11 @@ static int dlm_query_join_handler(struct o2net_msg *msg, u32 len, void *data, mlog(0, "node %u is not in our live map yet\n", query->node_idx); - response.packet.code = JOIN_DISALLOW; + packet.code = JOIN_DISALLOW; goto respond; } - response.packet.code = JOIN_OK_NO_MAP; + packet.code = JOIN_OK_NO_MAP; spin_lock(&dlm_domain_lock); dlm = __dlm_lookup_domain_full(query->domain, query->name_len); @@ -760,7 +792,7 @@ static int dlm_query_join_handler(struct o2net_msg *msg, u32 len, void *data, mlog(0, "disallow join as node %u does not " "have node %u in its nodemap\n", query->node_idx, nodenum); - response.packet.code = JOIN_DISALLOW; + packet.code = JOIN_DISALLOW; goto unlock_respond; } } @@ -780,23 +812,23 @@ static int dlm_query_join_handler(struct o2net_msg *msg, u32 len, void *data, /*If this is a brand new context and we * haven't started our join process yet, then * the other node won the race. */ - response.packet.code = JOIN_OK_NO_MAP; + packet.code = JOIN_OK_NO_MAP; } else if (dlm->joining_node != DLM_LOCK_RES_OWNER_UNKNOWN) { /* Disallow parallel joins. */ - response.packet.code = JOIN_DISALLOW; + packet.code = JOIN_DISALLOW; } else if (dlm->reco.state & DLM_RECO_STATE_ACTIVE) { mlog(0, "node %u trying to join, but recovery " "is ongoing.\n", bit); - response.packet.code = JOIN_DISALLOW; + packet.code = JOIN_DISALLOW; } else if (test_bit(bit, dlm->recovery_map)) { mlog(0, "node %u trying to join, but it " "still needs recovery.\n", bit); - response.packet.code = JOIN_DISALLOW; + packet.code = JOIN_DISALLOW; } else if (test_bit(bit, dlm->domain_map)) { mlog(0, "node %u trying to join, but it " "is still in the domain! needs recovery?\n", bit); - response.packet.code = JOIN_DISALLOW; + packet.code = JOIN_DISALLOW; } else { /* Alright we're fully a part of this domain * so we keep some state as to who's joining @@ -807,19 +839,15 @@ static int dlm_query_join_handler(struct o2net_msg *msg, u32 len, void *data, if (dlm_query_join_proto_check("DLM", bit, &dlm->dlm_locking_proto, &query->dlm_proto)) { - response.packet.code = - JOIN_PROTOCOL_MISMATCH; + packet.code = JOIN_PROTOCOL_MISMATCH; } else if (dlm_query_join_proto_check("fs", bit, &dlm->fs_locking_proto, &query->fs_proto)) { - response.packet.code = - JOIN_PROTOCOL_MISMATCH; + packet.code = JOIN_PROTOCOL_MISMATCH; } else { - response.packet.dlm_minor = - query->dlm_proto.pv_minor; - response.packet.fs_minor = - query->fs_proto.pv_minor; - response.packet.code = JOIN_OK; + packet.dlm_minor = query->dlm_proto.pv_minor; + packet.fs_minor = query->fs_proto.pv_minor; + packet.code = JOIN_OK; __dlm_set_joining_node(dlm, query->node_idx); } } @@ -830,9 +858,10 @@ unlock_respond: spin_unlock(&dlm_domain_lock); respond: - mlog(0, "We respond with %u\n", response.packet.code); + mlog(0, "We respond with %u\n", packet.code); - return response.intval; + dlm_query_join_packet_to_wire(&packet, &response); + return response; } static int dlm_assert_joined_handler(struct o2net_msg *msg, u32 len, void *data, @@ -937,7 +966,7 @@ static int dlm_send_join_cancels(struct dlm_ctxt *dlm, sizeof(unsigned long))) { mlog(ML_ERROR, "map_size %u != BITS_TO_LONGS(O2NM_MAX_NODES) %u\n", - map_size, BITS_TO_LONGS(O2NM_MAX_NODES)); + map_size, (unsigned)BITS_TO_LONGS(O2NM_MAX_NODES)); return -EINVAL; } @@ -968,7 +997,8 @@ static int dlm_request_join(struct dlm_ctxt *dlm, { int status; struct dlm_query_join_request join_msg; - union dlm_query_join_response join_resp; + struct dlm_query_join_packet packet; + u32 join_resp; mlog(0, "querying node %d\n", node); @@ -984,11 +1014,12 @@ static int dlm_request_join(struct dlm_ctxt *dlm, status = o2net_send_message(DLM_QUERY_JOIN_MSG, DLM_MOD_KEY, &join_msg, sizeof(join_msg), node, - &join_resp.intval); + &join_resp); if (status < 0 && status != -ENOPROTOOPT) { mlog_errno(status); goto bail; } + dlm_query_join_wire_to_packet(join_resp, &packet); /* -ENOPROTOOPT from the net code means the other side isn't listening for our message type -- that's fine, it means @@ -997,10 +1028,10 @@ static int dlm_request_join(struct dlm_ctxt *dlm, if (status == -ENOPROTOOPT) { status = 0; *response = JOIN_OK_NO_MAP; - } else if (join_resp.packet.code == JOIN_DISALLOW || - join_resp.packet.code == JOIN_OK_NO_MAP) { - *response = join_resp.packet.code; - } else if (join_resp.packet.code == JOIN_PROTOCOL_MISMATCH) { + } else if (packet.code == JOIN_DISALLOW || + packet.code == JOIN_OK_NO_MAP) { + *response = packet.code; + } else if (packet.code == JOIN_PROTOCOL_MISMATCH) { mlog(ML_NOTICE, "This node requested DLM locking protocol %u.%u and " "filesystem locking protocol %u.%u. At least one of " @@ -1012,14 +1043,12 @@ static int dlm_request_join(struct dlm_ctxt *dlm, dlm->fs_locking_proto.pv_minor, node); status = -EPROTO; - *response = join_resp.packet.code; - } else if (join_resp.packet.code == JOIN_OK) { - *response = join_resp.packet.code; + *response = packet.code; + } else if (packet.code == JOIN_OK) { + *response = packet.code; /* Use the same locking protocol as the remote node */ - dlm->dlm_locking_proto.pv_minor = - join_resp.packet.dlm_minor; - dlm->fs_locking_proto.pv_minor = - join_resp.packet.fs_minor; + dlm->dlm_locking_proto.pv_minor = packet.dlm_minor; + dlm->fs_locking_proto.pv_minor = packet.fs_minor; mlog(0, "Node %d responds JOIN_OK with DLM locking protocol " "%u.%u and fs locking protocol %u.%u\n", @@ -1031,11 +1060,11 @@ static int dlm_request_join(struct dlm_ctxt *dlm, } else { status = -EINVAL; mlog(ML_ERROR, "invalid response %d from node %u\n", - join_resp.packet.code, node); + packet.code, node); } mlog(0, "status %d, node %d response is %d\n", status, node, - *response); + *response); bail: return status; diff --git a/fs/ocfs2/dlm/dlmmaster.c b/fs/ocfs2/dlm/dlmmaster.c index c92d1b19fc0..ea6b8957786 100644 --- a/fs/ocfs2/dlm/dlmmaster.c +++ b/fs/ocfs2/dlm/dlmmaster.c @@ -1663,7 +1663,12 @@ way_up_top: dlm_put_mle(tmpmle); } send_response: - + /* + * __dlm_lookup_lockres() grabbed a reference to this lockres. + * The reference is released by dlm_assert_master_worker() under + * the call to dlm_dispatch_assert_master(). If + * dlm_assert_master_worker() isn't called, we drop it here. + */ if (dispatch_assert) { if (response != DLM_MASTER_RESP_YES) mlog(ML_ERROR, "invalid response %d\n", response); @@ -1678,7 +1683,11 @@ send_response: if (ret < 0) { mlog(ML_ERROR, "failed to dispatch assert master work\n"); response = DLM_MASTER_RESP_ERROR; + dlm_lockres_put(res); } + } else { + if (res) + dlm_lockres_put(res); } dlm_put(dlm); @@ -2348,7 +2357,7 @@ int dlm_deref_lockres_handler(struct o2net_msg *msg, u32 len, void *data, mlog(ML_ERROR, "%s:%.*s: node %u trying to drop ref " "but it is already dropped!\n", dlm->name, res->lockname.len, res->lockname.name, node); - __dlm_print_one_lock_resource(res); + dlm_print_one_lock_resource(res); } ret = 0; goto done; @@ -2408,7 +2417,7 @@ static void dlm_deref_lockres_worker(struct dlm_work_item *item, void *data) mlog(ML_ERROR, "%s:%.*s: node %u trying to drop ref " "but it is already dropped!\n", dlm->name, res->lockname.len, res->lockname.name, node); - __dlm_print_one_lock_resource(res); + dlm_print_one_lock_resource(res); } dlm_lockres_put(res); @@ -2933,6 +2942,9 @@ static void dlm_remove_nonlocal_locks(struct dlm_ctxt *dlm, dlm_lockres_clear_refmap_bit(lock->ml.node, res); list_del_init(&lock->list); dlm_lock_put(lock); + /* In a normal unlock, we would have added a + * DLM_UNLOCK_FREE_LOCK action. Force it. */ + dlm_lock_put(lock); } } queue++; diff --git a/fs/ocfs2/dlm/dlmrecovery.c b/fs/ocfs2/dlm/dlmrecovery.c index 91f747b8a53..bcb9260c373 100644 --- a/fs/ocfs2/dlm/dlmrecovery.c +++ b/fs/ocfs2/dlm/dlmrecovery.c @@ -519,9 +519,9 @@ static int dlm_do_recovery(struct dlm_ctxt *dlm) return 0; master_here: - mlog(0, "(%d) mastering recovery of %s:%u here(this=%u)!\n", - task_pid_nr(dlm->dlm_reco_thread_task), - dlm->name, dlm->reco.dead_node, dlm->node_num); + mlog(ML_NOTICE, "(%d) Node %u is the Recovery Master for the Dead Node " + "%u for Domain %s\n", task_pid_nr(dlm->dlm_reco_thread_task), + dlm->node_num, dlm->reco.dead_node, dlm->name); status = dlm_remaster_locks(dlm, dlm->reco.dead_node); if (status < 0) { @@ -1191,7 +1191,7 @@ static int dlm_add_lock_to_array(struct dlm_lock *lock, (ml->type == LKM_EXMODE || memcmp(mres->lvb, lock->lksb->lvb, DLM_LVB_LEN))) { mlog(ML_ERROR, "mismatched lvbs!\n"); - __dlm_print_one_lock_resource(lock->lockres); + dlm_print_one_lock_resource(lock->lockres); BUG(); } memcpy(mres->lvb, lock->lksb->lvb, DLM_LVB_LEN); @@ -1327,6 +1327,7 @@ int dlm_mig_lockres_handler(struct o2net_msg *msg, u32 len, void *data, (struct dlm_migratable_lockres *)msg->buf; int ret = 0; u8 real_master; + u8 extra_refs = 0; char *buf = NULL; struct dlm_work_item *item = NULL; struct dlm_lock_resource *res = NULL; @@ -1404,16 +1405,28 @@ int dlm_mig_lockres_handler(struct o2net_msg *msg, u32 len, void *data, __dlm_insert_lockres(dlm, res); spin_unlock(&dlm->spinlock); + /* Add an extra ref for this lock-less lockres lest the + * dlm_thread purges it before we get the chance to add + * locks to it */ + dlm_lockres_get(res); + + /* There are three refs that need to be put. + * 1. Taken above. + * 2. kref_init in dlm_new_lockres()->dlm_init_lockres(). + * 3. dlm_lookup_lockres() + * The first one is handled at the end of this function. The + * other two are handled in the worker thread after locks have + * been attached. Yes, we don't wait for purge time to match + * kref_init. The lockres will still have atleast one ref + * added because it is in the hash __dlm_insert_lockres() */ + extra_refs++; + /* now that the new lockres is inserted, * make it usable by other processes */ spin_lock(&res->spinlock); res->state &= ~DLM_LOCK_RES_IN_PROGRESS; spin_unlock(&res->spinlock); wake_up(&res->wq); - - /* add an extra ref for just-allocated lockres - * otherwise the lockres will be purged immediately */ - dlm_lockres_get(res); } /* at this point we have allocated everything we need, @@ -1443,12 +1456,17 @@ int dlm_mig_lockres_handler(struct o2net_msg *msg, u32 len, void *data, dlm_init_work_item(dlm, item, dlm_mig_lockres_worker, buf); item->u.ml.lockres = res; /* already have a ref */ item->u.ml.real_master = real_master; + item->u.ml.extra_ref = extra_refs; spin_lock(&dlm->work_lock); list_add_tail(&item->list, &dlm->work_list); spin_unlock(&dlm->work_lock); queue_work(dlm->dlm_worker, &dlm->dispatched_work); leave: + /* One extra ref taken needs to be put here */ + if (extra_refs) + dlm_lockres_put(res); + dlm_put(dlm); if (ret < 0) { if (buf) @@ -1464,17 +1482,19 @@ leave: static void dlm_mig_lockres_worker(struct dlm_work_item *item, void *data) { - struct dlm_ctxt *dlm = data; + struct dlm_ctxt *dlm; struct dlm_migratable_lockres *mres; int ret = 0; struct dlm_lock_resource *res; u8 real_master; + u8 extra_ref; dlm = item->dlm; mres = (struct dlm_migratable_lockres *)data; res = item->u.ml.lockres; real_master = item->u.ml.real_master; + extra_ref = item->u.ml.extra_ref; if (real_master == DLM_LOCK_RES_OWNER_UNKNOWN) { /* this case is super-rare. only occurs if @@ -1517,6 +1537,12 @@ again: } leave: + /* See comment in dlm_mig_lockres_handler() */ + if (res) { + if (extra_ref) + dlm_lockres_put(res); + dlm_lockres_put(res); + } kfree(data); mlog_exit(ret); } @@ -1644,7 +1670,8 @@ int dlm_master_requery_handler(struct o2net_msg *msg, u32 len, void *data, /* retry!? */ BUG(); } - } + } else /* put.. incase we are not the master */ + dlm_lockres_put(res); spin_unlock(&res->spinlock); } spin_unlock(&dlm->spinlock); @@ -1921,6 +1948,7 @@ void dlm_move_lockres_to_recovery_list(struct dlm_ctxt *dlm, "Recovering res %s:%.*s, is already on recovery list!\n", dlm->name, res->lockname.len, res->lockname.name); list_del_init(&res->recovering); + dlm_lockres_put(res); } /* We need to hold a reference while on the recovery list */ dlm_lockres_get(res); @@ -2130,11 +2158,16 @@ static void dlm_free_dead_locks(struct dlm_ctxt *dlm, assert_spin_locked(&dlm->spinlock); assert_spin_locked(&res->spinlock); + /* We do two dlm_lock_put(). One for removing from list and the other is + * to force the DLM_UNLOCK_FREE_LOCK action so as to free the locks */ + /* TODO: check pending_asts, pending_basts here */ list_for_each_entry_safe(lock, next, &res->granted, list) { if (lock->ml.node == dead_node) { list_del_init(&lock->list); dlm_lock_put(lock); + /* Can't schedule DLM_UNLOCK_FREE_LOCK - do manually */ + dlm_lock_put(lock); freed++; } } @@ -2142,6 +2175,8 @@ static void dlm_free_dead_locks(struct dlm_ctxt *dlm, if (lock->ml.node == dead_node) { list_del_init(&lock->list); dlm_lock_put(lock); + /* Can't schedule DLM_UNLOCK_FREE_LOCK - do manually */ + dlm_lock_put(lock); freed++; } } @@ -2149,6 +2184,8 @@ static void dlm_free_dead_locks(struct dlm_ctxt *dlm, if (lock->ml.node == dead_node) { list_del_init(&lock->list); dlm_lock_put(lock); + /* Can't schedule DLM_UNLOCK_FREE_LOCK - do manually */ + dlm_lock_put(lock); freed++; } } diff --git a/fs/ocfs2/dlm/dlmthread.c b/fs/ocfs2/dlm/dlmthread.c index cebd089f895..4060bb328bc 100644 --- a/fs/ocfs2/dlm/dlmthread.c +++ b/fs/ocfs2/dlm/dlmthread.c @@ -176,12 +176,14 @@ static int dlm_purge_lockres(struct dlm_ctxt *dlm, res->lockname.name, master); if (!master) { + /* drop spinlock... retake below */ + spin_unlock(&dlm->spinlock); + spin_lock(&res->spinlock); /* This ensures that clear refmap is sent after the set */ __dlm_wait_on_lockres_flags(res, DLM_LOCK_RES_SETREF_INPROG); spin_unlock(&res->spinlock); - /* drop spinlock to do messaging, retake below */ - spin_unlock(&dlm->spinlock); + /* clear our bit from the master's refmap, ignore errors */ ret = dlm_drop_lockres_ref(dlm, res); if (ret < 0) { diff --git a/fs/ocfs2/dlmglue.c b/fs/ocfs2/dlmglue.c index f7794306b2b..1f1873bf41f 100644 --- a/fs/ocfs2/dlmglue.c +++ b/fs/ocfs2/dlmglue.c @@ -2409,7 +2409,7 @@ static int ocfs2_dlm_seq_show(struct seq_file *m, void *v) return 0; } -static struct seq_operations ocfs2_dlm_seq_ops = { +static const struct seq_operations ocfs2_dlm_seq_ops = { .start = ocfs2_dlm_seq_start, .stop = ocfs2_dlm_seq_stop, .next = ocfs2_dlm_seq_next, diff --git a/fs/ocfs2/resize.c b/fs/ocfs2/resize.c index 37835ffcb03..8166968e901 100644 --- a/fs/ocfs2/resize.c +++ b/fs/ocfs2/resize.c @@ -597,7 +597,7 @@ int ocfs2_group_add(struct inode *inode, struct ocfs2_new_group_input *input) memset(cr, 0, sizeof(struct ocfs2_chain_rec)); } - cr->c_blkno = le64_to_cpu(input->group); + cr->c_blkno = cpu_to_le64(input->group); le32_add_cpu(&cr->c_total, input->clusters * cl_bpc); le32_add_cpu(&cr->c_free, input->frees * cl_bpc); diff --git a/fs/proc/base.c b/fs/proc/base.c index 91a1bd67ac1..8a10f6fe24a 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -1036,6 +1036,26 @@ static const struct file_operations proc_loginuid_operations = { .read = proc_loginuid_read, .write = proc_loginuid_write, }; + +static ssize_t proc_sessionid_read(struct file * file, char __user * buf, + size_t count, loff_t *ppos) +{ + struct inode * inode = file->f_path.dentry->d_inode; + struct task_struct *task = get_proc_task(inode); + ssize_t length; + char tmpbuf[TMPBUFLEN]; + + if (!task) + return -ESRCH; + length = scnprintf(tmpbuf, TMPBUFLEN, "%u", + audit_get_sessionid(task)); + put_task_struct(task); + return simple_read_from_buffer(buf, count, ppos, tmpbuf, length); +} + +static const struct file_operations proc_sessionid_operations = { + .read = proc_sessionid_read, +}; #endif #ifdef CONFIG_FAULT_INJECTION @@ -2269,6 +2289,9 @@ static const struct pid_entry tgid_base_stuff[] = { DIR("task", S_IRUGO|S_IXUGO, task), DIR("fd", S_IRUSR|S_IXUSR, fd), DIR("fdinfo", S_IRUSR|S_IXUSR, fdinfo), +#ifdef CONFIG_NET + DIR("net", S_IRUGO|S_IXUSR, net), +#endif REG("environ", S_IRUSR, environ), INF("auxv", S_IRUSR, pid_auxv), ONE("status", S_IRUGO, pid_status), @@ -2316,6 +2339,7 @@ static const struct pid_entry tgid_base_stuff[] = { REG("oom_adj", S_IRUGO|S_IWUSR, oom_adjust), #ifdef CONFIG_AUDITSYSCALL REG("loginuid", S_IWUSR|S_IRUGO, loginuid), + REG("sessionid", S_IRUSR, sessionid), #endif #ifdef CONFIG_FAULT_INJECTION REG("make-it-fail", S_IRUGO|S_IWUSR, fault_inject), @@ -2646,6 +2670,7 @@ static const struct pid_entry tid_base_stuff[] = { REG("oom_adj", S_IRUGO|S_IWUSR, oom_adjust), #ifdef CONFIG_AUDITSYSCALL REG("loginuid", S_IWUSR|S_IRUGO, loginuid), + REG("sessionid", S_IRUSR, sessionid), #endif #ifdef CONFIG_FAULT_INJECTION REG("make-it-fail", S_IRUGO|S_IWUSR, fault_inject), diff --git a/fs/proc/generic.c b/fs/proc/generic.c index 68971e66cd4..a36ad3c75cf 100644 --- a/fs/proc/generic.c +++ b/fs/proc/generic.c @@ -377,15 +377,14 @@ static struct dentry_operations proc_dentry_operations = * Don't create negative dentries here, return -ENOENT by hand * instead. */ -struct dentry *proc_lookup(struct inode * dir, struct dentry *dentry, struct nameidata *nd) +struct dentry *proc_lookup_de(struct proc_dir_entry *de, struct inode *dir, + struct dentry *dentry) { struct inode *inode = NULL; - struct proc_dir_entry * de; int error = -ENOENT; lock_kernel(); spin_lock(&proc_subdir_lock); - de = PDE(dir); if (de) { for (de = de->subdir; de ; de = de->next) { if (de->namelen != dentry->d_name.len) @@ -393,8 +392,6 @@ struct dentry *proc_lookup(struct inode * dir, struct dentry *dentry, struct nam if (!memcmp(dentry->d_name.name, de->name, de->namelen)) { unsigned int ino; - if (de->shadow_proc) - de = de->shadow_proc(current, de); ino = de->low_ino; de_get(de); spin_unlock(&proc_subdir_lock); @@ -417,6 +414,12 @@ out_unlock: return ERR_PTR(error); } +struct dentry *proc_lookup(struct inode *dir, struct dentry *dentry, + struct nameidata *nd) +{ + return proc_lookup_de(PDE(dir), dir, dentry); +} + /* * This returns non-zero if at EOF, so that the /proc * root directory can use this and check if it should @@ -426,10 +429,9 @@ out_unlock: * value of the readdir() call, as long as it's non-negative * for success.. */ -int proc_readdir(struct file * filp, - void * dirent, filldir_t filldir) +int proc_readdir_de(struct proc_dir_entry *de, struct file *filp, void *dirent, + filldir_t filldir) { - struct proc_dir_entry * de; unsigned int ino; int i; struct inode *inode = filp->f_path.dentry->d_inode; @@ -438,7 +440,6 @@ int proc_readdir(struct file * filp, lock_kernel(); ino = inode->i_ino; - de = PDE(inode); if (!de) { ret = -EINVAL; goto out; @@ -499,6 +500,13 @@ out: unlock_kernel(); return ret; } +int proc_readdir(struct file *filp, void *dirent, filldir_t filldir) +{ + struct inode *inode = filp->f_path.dentry->d_inode; + + return proc_readdir_de(PDE(inode), filp, dirent, filldir); +} + /* * These are the generic /proc directory operations. They * use the in-memory "struct proc_dir_entry" tree to parse diff --git a/fs/proc/internal.h b/fs/proc/internal.h index 1c81c8f1aee..bc72f5c8c47 100644 --- a/fs/proc/internal.h +++ b/fs/proc/internal.h @@ -64,6 +64,8 @@ extern const struct file_operations proc_numa_maps_operations; extern const struct file_operations proc_smaps_operations; extern const struct file_operations proc_clear_refs_operations; extern const struct file_operations proc_pagemap_operations; +extern const struct file_operations proc_net_operations; +extern const struct inode_operations proc_net_inode_operations; void free_proc_entry(struct proc_dir_entry *de); @@ -83,3 +85,8 @@ static inline int proc_fd(struct inode *inode) { return PROC_I(inode)->fd; } + +struct dentry *proc_lookup_de(struct proc_dir_entry *de, struct inode *ino, + struct dentry *dentry); +int proc_readdir_de(struct proc_dir_entry *de, struct file *filp, void *dirent, + filldir_t filldir); diff --git a/fs/proc/proc_net.c b/fs/proc/proc_net.c index 14e9b5aaf86..4caa5f774fb 100644 --- a/fs/proc/proc_net.c +++ b/fs/proc/proc_net.c @@ -63,6 +63,82 @@ int seq_release_net(struct inode *ino, struct file *f) } EXPORT_SYMBOL_GPL(seq_release_net); +static struct net *get_proc_task_net(struct inode *dir) +{ + struct task_struct *task; + struct nsproxy *ns; + struct net *net = NULL; + + rcu_read_lock(); + task = pid_task(proc_pid(dir), PIDTYPE_PID); + if (task != NULL) { + ns = task_nsproxy(task); + if (ns != NULL) + net = get_net(ns->net_ns); + } + rcu_read_unlock(); + + return net; +} + +static struct dentry *proc_tgid_net_lookup(struct inode *dir, + struct dentry *dentry, struct nameidata *nd) +{ + struct dentry *de; + struct net *net; + + de = ERR_PTR(-ENOENT); + net = get_proc_task_net(dir); + if (net != NULL) { + de = proc_lookup_de(net->proc_net, dir, dentry); + put_net(net); + } + return de; +} + +static int proc_tgid_net_getattr(struct vfsmount *mnt, struct dentry *dentry, + struct kstat *stat) +{ + struct inode *inode = dentry->d_inode; + struct net *net; + + net = get_proc_task_net(inode); + + generic_fillattr(inode, stat); + + if (net != NULL) { + stat->nlink = net->proc_net->nlink; + put_net(net); + } + + return 0; +} + +const struct inode_operations proc_net_inode_operations = { + .lookup = proc_tgid_net_lookup, + .getattr = proc_tgid_net_getattr, +}; + +static int proc_tgid_net_readdir(struct file *filp, void *dirent, + filldir_t filldir) +{ + int ret; + struct net *net; + + ret = -EINVAL; + net = get_proc_task_net(filp->f_path.dentry->d_inode); + if (net != NULL) { + ret = proc_readdir_de(net->proc_net, filp, dirent, filldir); + put_net(net); + } + return ret; +} + +const struct file_operations proc_net_operations = { + .read = generic_read_dir, + .readdir = proc_tgid_net_readdir, +}; + struct proc_dir_entry *proc_net_fops_create(struct net *net, const char *name, mode_t mode, const struct file_operations *fops) @@ -83,14 +159,6 @@ struct net *get_proc_net(const struct inode *inode) } EXPORT_SYMBOL_GPL(get_proc_net); -static struct proc_dir_entry *shadow_pde; - -static struct proc_dir_entry *proc_net_shadow(struct task_struct *task, - struct proc_dir_entry *de) -{ - return task->nsproxy->net_ns->proc_net; -} - struct proc_dir_entry *proc_net_mkdir(struct net *net, const char *name, struct proc_dir_entry *parent) { @@ -104,45 +172,39 @@ EXPORT_SYMBOL_GPL(proc_net_mkdir); static __net_init int proc_net_ns_init(struct net *net) { - struct proc_dir_entry *root, *netd, *net_statd; + struct proc_dir_entry *netd, *net_statd; int err; err = -ENOMEM; - root = kzalloc(sizeof(*root), GFP_KERNEL); - if (!root) + netd = kzalloc(sizeof(*netd), GFP_KERNEL); + if (!netd) goto out; - err = -EEXIST; - netd = proc_net_mkdir(net, "net", root); - if (!netd) - goto free_root; + netd->data = net; + netd->nlink = 2; + netd->name = "net"; + netd->namelen = 3; + netd->parent = &proc_root; err = -EEXIST; net_statd = proc_net_mkdir(net, "stat", netd); if (!net_statd) goto free_net; - root->data = net; - - net->proc_net_root = root; net->proc_net = netd; net->proc_net_stat = net_statd; - err = 0; + return 0; +free_net: + kfree(netd); out: return err; -free_net: - remove_proc_entry("net", root); -free_root: - kfree(root); - goto out; } static __net_exit void proc_net_ns_exit(struct net *net) { remove_proc_entry("stat", net->proc_net); - remove_proc_entry("net", net->proc_net_root); - kfree(net->proc_net_root); + kfree(net->proc_net); } static struct pernet_operations __net_initdata proc_net_ns_ops = { @@ -152,8 +214,7 @@ static struct pernet_operations __net_initdata proc_net_ns_ops = { int __init proc_net_init(void) { - shadow_pde = proc_mkdir("net", NULL); - shadow_pde->shadow_proc = proc_net_shadow; + proc_symlink("net", NULL, "self/net"); return register_pernet_subsys(&proc_net_ns_ops); } diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 6dc0334815f..4206454734e 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -640,17 +640,17 @@ static ssize_t pagemap_read(struct file *file, char __user *buf, ret = -EACCES; if (!ptrace_may_attach(task)) - goto out; + goto out_task; ret = -EINVAL; /* file position must be aligned */ if (*ppos % PM_ENTRY_BYTES) - goto out; + goto out_task; ret = 0; mm = get_task_mm(task); if (!mm) - goto out; + goto out_task; ret = -ENOMEM; uaddr = (unsigned long)buf & PAGE_MASK; @@ -658,7 +658,7 @@ static ssize_t pagemap_read(struct file *file, char __user *buf, pagecount = (PAGE_ALIGN(uend) - uaddr) / PAGE_SIZE; pages = kmalloc(pagecount * sizeof(struct page *), GFP_KERNEL); if (!pages) - goto out_task; + goto out_mm; down_read(¤t->mm->mmap_sem); ret = get_user_pages(current, current->mm, uaddr, pagecount, @@ -668,6 +668,12 @@ static ssize_t pagemap_read(struct file *file, char __user *buf, if (ret < 0) goto out_free; + if (ret != pagecount) { + pagecount = ret; + ret = -EFAULT; + goto out_pages; + } + pm.out = buf; pm.end = buf + count; @@ -699,15 +705,17 @@ static ssize_t pagemap_read(struct file *file, char __user *buf, ret = pm.out - buf; } +out_pages: for (; pagecount; pagecount--) { page = pages[pagecount-1]; if (!PageReserved(page)) SetPageDirty(page); page_cache_release(page); } - mmput(mm); out_free: kfree(pages); +out_mm: + mmput(mm); out_task: put_task_struct(task); out: |